JP7751822B2 - Intelligent vibration digital twin system and method for industrial environments - Google Patents

Description

CROSS-REFERENCE TO RELATED APPLICATIONS
This application claims the benefit of priority to the following U.S. provisional patent applications: Provisional Application No. 62/939,769, entitled "METHODS AND SYSTEMS FOR DETECTION IN AN INDUSTRIAL INTERNET OF THINGS DATA COLLECTION ENVIRONMENT WITH LARGE DATA SETS," filed November 25, 2019; Provisional Application No. 63/016,974, entitled "DIGITAL TWIN SYSTEMS FOR INDUSTRIAL ENVIRONMENTS," filed April 28, 2020; Provisional Application No. 63/054,600, entitled "INTELLIGENT VIBRATION DIGITAL TWIN SYSTEMS AND METHODS FOR INDUSTRIAL ENVIRONMENTS," filed July 21, 2020; and Provisional Application No. 63/054,600, entitled "INFORMATION TECHNOLOGY SYSTEMS AND METHODS FOR INDUSTRIAL ENVIRONMENTS," filed August 24, 2020. No. 63/069,548, entitled "METHODS FOR MANUFACTURING ARTIFICIAL INTELLIGENCE LEVERAGING DIGITAL TWINS." This application also claims the benefit of priority to U.S. patent application Ser. No. 17/104,964, filed Nov. 25, 2020, entitled "INTELLIGENT VIBRATION DIGITAL TWIN SYSTEMS AND METHODS FOR INDUSTRIAL ENVIRONMENTS." Each of the above applications is incorporated herein by reference in its entirety as if fully set forth herein.

This disclosure relates to an intelligent digital twin system that creates, manages, and provides digital twins of industrial entities using vibration data, etc.

Industrial environments, such as those for large-scale manufacturing (e.g., aircraft, ships, trucks, automobiles, and large industrial machinery manufacturing), energy production (e.g., oil and gas plants, renewable energy environments), energy extraction (e.g., mining, drilling), and construction (e.g., large building construction), contain highly complex machines, devices, systems, and workflows that require operators to consider numerous parameters, metrics, and the like to optimize the design, development, deployment, and operation of various technologies to improve overall outcomes. Historically, data collection in industrial environments has been performed by humans using specialized data collection equipment, often recording batches of specific sensor data onto media such as tape or hard drives for later analysis. Traditionally, data batches have been returned to a central office for analysis, e.g., signal processing or other analytics performed on the data collected by various sensors, which can then be used as the basis for diagnosing environmental problems or proposing ways to improve operations. This work has traditionally been performed on timescales of weeks to months and with limited data sets.

The advent of the Internet of Things (IoT) has enabled continuous connectivity to and between a wider range of devices. Most of these devices are consumer devices, such as lights, thermostats, etc. However, in more complex industrial environments, the range of available data is often limited, and the complexity of handling data from multiple sensors means that creating effective "smart" solutions for the industrial sector remains more challenging. A need exists for improved methods and systems for data collection in industrial environments, and for using the collected data to provide improved monitoring, control, intelligent diagnosis of problems, and intelligent optimization of operations in a variety of heavy industrial environments.

With the proliferation of vibration sensors and other Industrial Internet of Things (IIoT) sensors, vast amounts of data related to industrial environments are becoming available. This data is useful for predicting maintenance needs and classifying potential problems in industrial environments. However, there are many unexplored applications of vibration sensor data and other IIoT sensor data that can improve the operation and uptime of industrial environments and provide industrial entities with the agility to respond to issues before they become critical.

Industrial companies that rely on industry experts struggle to capture the knowledge of these experts when they move to another company or leave the workforce. There is a need in the art to capture industry expertise and use the captured industry expertise in training new workers or mobile electronics industry entities to perform industry-related tasks.

The present disclosure is directed to a platform for facilitating the development of intelligence in an Industrial Internet of Things (IIoT) system. The platform may be composed of multiple distinct data processing layers. The multiple distinct data processing layers may include an industrial monitoring system layer that collects data from or about multiple industrial entities in the IIoT system; an industrial entity-oriented data storage system layer that stores data collected by the industrial monitoring system layer; an adaptive intelligent system layer that facilitates the coordinated development and deployment of intelligent systems in the IIoT system; and an industrial management application platform layer that includes multiple applications and manages the platform in a common application environment. The adaptive intelligent system layer may include a robotic process automation system that develops and deploys automation capabilities for one or more of the multiple industrial entities in the IIoT system.

In embodiments, the present disclosure includes a method for updating one or more properties of one or more digital twins, including receiving a request for one or more digital twins; retrieving one or more digital twins necessary to fulfill the request from a digital twin data store; retrieving one or more dynamic models corresponding to one or more properties depicted in the one or more digital twins indicated by the request; selecting a data source from a set of available data sources based on one or more inputs of the one or more dynamic models; retrieving data from the selected data source; using the retrieved data as one or more inputs to the one or more dynamic models to determine one or more outputs; and updating one or more properties of the one or more digital twins based on the one or more outputs of the one or more dynamic models.

In embodiments, the request is received from a client application corresponding to the industrial environment and/or one or more industrial entities within the industrial environment. In embodiments, the request is received from a client application supporting an Industrial Internet of Things sensor system. In embodiments, the digital twin is a digital twin of at least one of the industrial entity and the industrial environment. In embodiments, the one or more dynamic models acquire data selected from a set of temperature, pressure, humidity, wind, rainfall, tide, storm surge, cloud cover, snowfall, visibility, radiation, audio, video, imagery, water level, quantum, flow rate, signal power, signal frequency, motion, speed, acceleration, lighting level, analyte concentration, biological compound concentration, metal concentration, and organic compound concentration data. In embodiments, the selected data source includes an Internet of Things connected device. In embodiments, the selected data source includes a machine vision system.

In an embodiment, obtaining the one or more dynamic models includes identifying one or more dynamic models based on one or more properties depicted in the digital twins indicated by the request and the respective types of the one or more digital twins. In an embodiment, the one or more dynamic models are identified using a lookup table.

In embodiments, the present disclosure includes a method that includes receiving import data from one or more data sources, the import data corresponding to an industrial environment; generating an environment digital twin that represents the industrial environment based on the import data; identifying one or more industrial entities within the industrial environment; generating a set of discrete digital twins that represent the one or more industrial entities within the environment; embedding the set of discrete digital twins within the environment digital twin; establishing a connection with a sensor system of the industrial environment; receiving real-time sensor data from one or more sensors of the sensor system via the connection; and updating at least one of the environment digital twin and the set of discrete digital twins based on the real-time sensor data.

In an embodiment, a connection with the sensor system is established via one of a web hook and an application programming interface (API). In an embodiment, the environment digital twin and the set of discrete digital twins are visual digital twins configured to be rendered in a visual manner. In an embodiment, the present disclosure includes outputting the visual digital twin to a client application that displays the visual digital twin through a virtual reality headset. In an embodiment, the present disclosure includes outputting the visual digital twin to a client application that displays the visual digital twin through a display device of a user device. In an embodiment, the present disclosure includes outputting the visual digital twin to a client application that displays the visual digital twin through an augmented reality-enabled device. In an embodiment, the present disclosure includes receiving user input related to one or more steps performed in an industrial process associated with an industrial environment; and generating, with respect to the industrial environment and one or more of a set of industrial entities, a process digital twin that defines the steps of the industrial process. In an embodiment, the present disclosure includes instantiating a graph database having a set of nodes connected by edges, wherein a first node of the set of nodes includes data defining the environment digital twin and one or more entity nodes each include respective data defining a respective discrete digital twin of the set of discrete digital twins. In embodiments, each edge represents a relationship between two respective digital twins. In embodiments, embedding the discrete digital twins includes connecting entity nodes corresponding to the respective discrete digital twins to the first node with edges representing respective relationships between the respective industrial entities represented by the respective discrete digital twins and the industrial environment. In embodiments, each edge represents a spatial relationship between the two respective digital twins and an operational relationship between the two respective digital twins. In embodiments, each edge stores metadata corresponding to the relationship between the two respective digital twins. In embodiments, each entity node of the one or more entity nodes includes one or more respective properties of the respective industrial entities represented by the entity node. In embodiments, each entity node of the one or more entity nodes includes one or more behaviors of the respective properties of the respective industrial entities represented by the entity node. In embodiments, an environment node includes one or more properties of the environment. In embodiments, an environment node includes one or more behaviors of the environment.

In an embodiment, the disclosure includes performing a simulation based on an environment digital twin and one or more discrete digital twins. In an embodiment, the simulation simulates one of the operation of a machine in an industrial environment generating an output based on a set of inputs and the movement of a worker in the industrial environment. In an embodiment, the imported data includes a three-dimensional scan of the environment. In an embodiment, the imported data includes a LIDAR scan of the industrial environment. In an embodiment, generating a digital twin of the industrial environment includes one of generating a set of surfaces of the industrial environment and configuring a set of dimensions of the industrial environment. In an embodiment, generating the set of discrete digital twins includes importing a predefined digital twin of the industrial entity from a manufacturer of the industrial entity, the predefined digital twin including properties and behaviors of the industrial entity. In an embodiment, generating the set of discrete digital twins includes classifying industrial entities in the imported data of the industrial environment and generating a discrete digital twin corresponding to the classified industrial entity.

In an embodiment, the present disclosure includes a system for monitoring interactions within an industrial environment. In an embodiment, the system includes a digital twin data store including data collected by a set of proximity sensors disposed within the industrial environment, the data including location data indicating respective locations of a plurality of elements within the industrial environment, and one or more processors configured to: maintain an industrial environment digital twin for the industrial environment via the digital twin data store; receive signals from the plurality of elements indicating activation of at least one proximity sensor in the set of proximity sensors by a real-world element; collect updated location data of the real-world element using the at least one proximity sensor in response to activation of the at least one proximity sensor; and update the industrial environment digital twin in the digital twin data store to include the updated location data.

In an embodiment, each of the set of proximity sensors is configured to detect a device associated with a user. In an embodiment, the devices are a wearable device and an RFID device. In an embodiment, each of the plurality of elements is a mobile element. In an embodiment, each of the plurality of elements is a respective worker. In an embodiment, the plurality of elements includes a mobile device element and a worker, and the mobile device location data is determined using data transmitted by the respective mobile device element, and the worker location data is determined using data acquired by the system. In an embodiment, the worker location data is determined using information transmitted from a device associated with the respective worker. In an embodiment, activation of at least one proximity sensor occurs in response to an interaction between the respective worker and the proximity sensor. In an embodiment, activation of the at least one proximity sensor occurs in response to an interaction between the worker and at least one respective proximity sensor digital twin corresponding to the at least one proximity sensor. In an embodiment, the one or more processors collect updated location data for the plurality of elements using the set of proximity sensors in response to activation of the at least one proximity sensor.

In an embodiment, the present disclosure includes a system for modeling moving elements for an industrial digital twin. The system includes a digital twin data store storing industrial environment digital twins corresponding to the industrial elements, the industrial environment digital twin including real-world element digital twins embedded therein, each real-world element digital twin corresponding to a respective real-world element located within the industrial environment, the real-world element digital twins including mobile element digital twins corresponding to respective mobile elements within the industrial environment, and one or more processors configured to: determine, for each mobile element, whether the mobile element is moving; obtain path information from the mobile element; and model, via the digital twin simulation system, traffic within the industrial environment in response to obtaining the path information for each mobile element.

In an embodiment, the route information is obtained from a navigation module of the mobile element. In an embodiment, the one or more processors are further configured to obtain the route information by: detecting movement of the mobile element using a plurality of sensors in the industrial environment; obtaining a destination of the mobile element; calculating an optimized route for the mobile element using the plurality of sensors in the industrial environment; and instructing the mobile element to navigate the optimized route.

In an embodiment, the optimized route includes route information of other mobile elements within the real-world element, and the optimized route minimizes interactions between the mobile elements and humans within the industrial environment. In an embodiment, the mobile elements include autonomous vehicles and non-autonomous vehicles, and the optimized route reduces interactions between the autonomous vehicles and the non-autonomous vehicles. In an embodiment, the traffic modeling includes the use of a particle traffic model, a trigger-response mobile element following traffic model, a macroscopic traffic model, a microscopic traffic model, a sub-microscopic traffic model, a mesoscopic traffic model, or a combination thereof.

In an embodiment, the present disclosure includes a method for updating one or more vibration fault level states of one or more digital twins, the method including: receiving a request from a client application to update one or more vibration fault level states of one or more digital twins; retrieving one or more digital twins necessary to fulfill the request; retrieving one or more dynamic models necessary to fulfill the request, the one or more dynamic models including a dynamic model that predicts when a vibration fault level will occur based on an input data set; selecting a data source from a set of available data sources based on one or more inputs of the one or more dynamic models; obtaining data from the selected data source; using the retrieved data as one or more inputs to the one or more dynamic models to determine one or more outputs; and updating one or more vibration fault level states of the one or more digital twins based on the outputs of the one or more dynamic models.

In embodiments, the request is received from a client application corresponding to the industrial environment and/or one or more industrial entities within the industrial environment. In embodiments, the request is received from a client application supporting an Industrial Internet of Things sensor system. In embodiments, the digital twin is a digital twin of at least one of the industrial entity and the industrial environment. In embodiments, the dynamic model acquires data selected from the set consisting of vibration, temperature, pressure, humidity, wind, rainfall, tide, storm surge, cloud cover, snowfall, visibility, radiation, audio, video, imagery, water level, quantum, flow rate, signal power, signal frequency, motion, displacement, velocity, acceleration, light level, finance, cost, stock market, news, social media, revenue, workers, maintenance, productivity, asset performance, worker performance, worker response time, analyte concentration, biological chemical concentration, metal concentration, and organic compound concentration data.

In an embodiment, the data source is selected from the set consisting of an Internet of Things connected device, a machine vision system, an analog vibration sensor, a digital vibration sensor, a fixed digital vibration sensor, a three-axis vibration sensor, a single-axis vibration sensor, an optical vibration sensor, and a crosspoint switch. In an embodiment, obtaining the one or more dynamic models includes identifying one or more dynamic models based on one or more properties and respective types of the one or more digital twins indicated in the request. In an embodiment, the one or more dynamic models are identified using a lookup table.

In an embodiment, the present disclosure includes a system for monitoring navigational path data through an industrial environment having real-world elements disposed therein. The system includes a digital twin data store including an industrial environment digital twin corresponding to the industrial environment and a worker digital twin corresponding to each worker in a set of workers within the industrial environment; and one or more processors configured to: maintain the industrial environment digital twin to include contemporaneous positions for the set of workers within the industrial environment via the digital twin data store; monitor the movements of each worker in the set of workers via a sensor array; determine navigational path data for each worker in response to detecting the movements of each worker; and update the industrial environment digital twin to include indices of the navigational path data for each worker and to represent the movement of the worker digital twin along a path corresponding to the navigational path data. In an embodiment, the one or more processors are further configured to determine navigational path data for the remaining workers in the set of workers in response to representing the movements of each worker. In an embodiment, the navigational path data is automatically transmitted to the system by one or more personal-associated devices. In an embodiment, the personal-associated devices are one of a mobile device with cellular data capability and a wearable device associated with the worker. In embodiments, the navigational path data is determined via environment-related sensors. In embodiments, the navigational path data is determined using historical path data stored in a digital twin data store. In embodiments, the historical path data is obtained from a device associated with the respective worker. In embodiments, the historical path data is obtained from a device associated with another worker. In embodiments, the historical path data is associated with the worker's current task. In embodiments, the digital twin data store includes an industrial environment digital twin. In embodiments, the one or more processors are further configured to: determine the existence of a conflict between the navigational path data and the industrial environment digital twin; modify the worker's navigational path data in response to determining accuracy of the industrial environment digital twin via the sensor array; and update the industrial environment digital twin in response to determining inaccuracy of the industrial environment digital twin via the sensor array, thereby resolving the conflict.

In an embodiment, the industrial environment digital twin is updated using collected data transmitted from workers. In an embodiment, the collected data includes proximity sensor data, image data, or a combination thereof. In an embodiment, the navigation path includes a path for collecting vibration measurements.

In embodiments, the present disclosure includes a method for updating one or more properties of one or more digital twins, the method including receiving a request for one or more digital twins; retrieving one or more digital twins necessary to fulfill the request from a digital twin data store; retrieving one or more dynamic models corresponding to one or more properties depicted in the one or more digital twins indicated by the request; selecting data sources from a set of available data sources based on one or more inputs of the one or more dynamic models; retrieving data from the selected data sources; determining one or more outputs using the retrieved data as one or more inputs to the one or more dynamic models; and updating one or more properties of the one or more digital twins based on the one or more outputs of the one or more dynamic models.

In embodiments, the request is received from a client application corresponding to the industrial environment and/or one or more industrial entities within the industrial environment. In embodiments, the request is received from a client application supporting an Industrial Internet of Things sensor system. In embodiments, the digital twin is a digital twin of at least one of the industrial entity and the industrial environment. In embodiments, the one or more dynamic models take data selected from the set consisting of temperature, pressure, humidity, wind, rainfall, tide, storm surge, cloud cover, snowfall, visibility, radiation, audio, video, imagery, water level, quantum, flow rate, signal power, signal frequency, motion, speed, acceleration, lighting level, analyte concentration, biological compound concentration, metal concentration, and organic compound concentration data. In embodiments, the selected data source includes an Internet of Things connected device. In embodiments, the selected data source includes a machine vision system.

In an embodiment, obtaining the one or more dynamic models includes identifying one or more dynamic models based on one or more properties depicted in the digital twins indicated by the request and the respective types of the one or more digital twins. In an embodiment, the one or more dynamic models are identified using a lookup table.

In an embodiment, the disclosure includes a method including receiving import data from one or more data sources, the import data corresponding to an industrial environment; generating an environment digital twin representing the industrial environment based on the import data; identifying one or more industrial entities within the industrial environment; generating a set of discrete digital twins representing the one or more industrial entities within the environment; embedding the set of discrete digital twins within the environment digital twin; establishing a connection with a sensor system of the industrial environment; receiving real-time sensor data from one or more sensors of the sensor system via the connection; and updating at least one of the environment digital twin and the set of discrete digital twins based on the real-time sensor data.

In an embodiment, a connection with the sensor system is established via one of a web hook and an application programming interface (API). In an embodiment, the environment digital twin and the set of discrete digital twins are visual digital twins configured to be rendered in a visual manner. In an embodiment, the present disclosure includes outputting the visual digital twin to a client application that displays the visual digital twin through a virtual reality headset. In an embodiment, the present disclosure includes outputting the visual digital twin to a client application that displays the visual digital twin through a display device of a user device. In an embodiment, the present disclosure includes outputting the visual digital twin to a client application that displays the visual digital twin through an augmented reality-enabled device. In an embodiment, the present disclosure includes receiving user input related to one or more steps performed in an industrial process associated with an industrial environment, and generating a process digital twin that defines the steps of the industrial process with respect to one or more of the industrial environment and the set of industrial entities. In an embodiment, the present disclosure includes instantiating a graph database having a set of nodes connected by edges, wherein a first node of the set of nodes includes data defining the environment digital twin and one or more entity nodes each include respective data defining a respective discrete digital twin of the set of discrete digital twins. In embodiments, each edge represents a relationship between two respective digital twins. In embodiments, embedding the discrete digital twins includes connecting entity nodes corresponding to the respective discrete digital twins to the first node with edges representing respective relationships between the respective industrial entities represented by the respective discrete digital twins and the industrial environment. In embodiments, each edge represents a spatial relationship between the two respective digital twins and an operational relationship between the two respective digital twins. In embodiments, each edge stores metadata corresponding to the relationship between the two respective digital twins. In embodiments, each entity node of the one or more entity nodes includes one or more respective properties of the respective industrial entities represented by the entity node. In embodiments, each entity node of the one or more entity nodes includes one or more behaviors of the respective properties of the respective industrial entities represented by the entity node. In embodiments, an environment node includes one or more properties of the environment. In embodiments, an environment node includes one or more behaviors of the environment.

In embodiments, the disclosure includes performing a simulation based on an environment digital twin and one or more discrete digital twins. In embodiments, the simulation simulates one of the operation of a machine in an industrial environment generating an output based on a set of inputs and the movement of a worker in the industrial environment. In embodiments, the imported data includes a three-dimensional scan of the environment. In embodiments, the imported data includes a LIDAR scan of the industrial environment. In embodiments, generating a digital twin of the industrial environment includes one of generating a set of surfaces of the industrial environment and configuring a set of dimensions of the industrial environment. In embodiments, generating the set of discrete digital twins includes importing predefined digital twins of industrial entities from a manufacturer of the industrial entities, the predefined digital twin including properties and behaviors of the industrial entities. In embodiments, generating the set of discrete digital twins includes classifying industrial entities in the imported data of the industrial environment and generating discrete digital twins corresponding to the classified industrial entities.

In an embodiment, the present disclosure includes a system for monitoring interactions within an industrial environment. In an embodiment, the system includes a digital twin data store including data collected by a set of proximity sensors disposed within the industrial environment, the data including location data indicating respective locations of a plurality of elements within the industrial environment, and one or more processors configured to: maintain an industrial environment digital twin for the industrial environment via the digital twin data store; receive signals from the plurality of elements indicative of activation of at least one proximity sensor in the set of proximity sensors by a real-world element; collect updated location data of the real-world element using the at least one proximity sensor in response to the activation of the at least one proximity sensor; and update the industrial environment digital twin in the digital twin data store to include the updated location data.

In an embodiment, each of the set of proximity sensors is configured to detect a device associated with a user. In an embodiment, the device is a wearable device and an RFID device. In an embodiment, each of the plurality of elements is a mobile element. In an embodiment, each of the plurality of elements is a respective worker. In an embodiment, the plurality of elements includes a mobile device element and a worker, and the mobile device location data is determined using data transmitted by the respective mobile device element, and the worker location data is determined using data acquired by the system. In an embodiment, the worker location data is determined using information transmitted from a device associated with each worker. In an embodiment, activation of at least one proximity sensor occurs in response to an interaction between the respective worker and the proximity sensor. In an embodiment, activation of the at least one proximity sensor occurs in response to an interaction between the worker and each of at least one proximity sensor digital twin corresponding to the at least one proximity sensor. In an embodiment, the one or more processors collect updated location data for the plurality of elements using the set of proximity sensors in response to activation of the at least one proximity sensor.

In an embodiment, the present disclosure includes a system for modeling moving elements for an industrial digital twin. The system includes a digital twin data store that stores industrial environment digital twins corresponding to industrial elements, the industrial environment digital twin including real-world element digital twins embedded therein, each real-world element digital twin corresponding to a respective real-world element located within the industrial environment, the real-world element digital twins including mobile element digital twins corresponding to respective mobile elements within the industrial environment, and the system further includes one or more processors configured to: for each mobile element, determine whether the mobile element is moving; obtain route information from the mobile element; and, in response to obtaining the route information for each mobile element, model traffic within the industrial environment via the digital twin simulation system.

In an embodiment, the route information is obtained from a navigation module of the mobile element. In an embodiment, the one or more processors are further configured to obtain the route information by: detecting movement of the mobile element using a plurality of sensors in the industrial environment; obtaining a destination of the mobile element; calculating an optimized route for the mobile element using a plurality of sensors in the industrial environment; and instructing the mobile element to navigate the optimized route.

In an embodiment, the optimized route includes route information for other mobile elements within the real-world element, and the optimized route minimizes interactions between the mobile elements and humans within the industrial environment. In an embodiment, the mobile elements include autonomous and non-autonomous vehicles, and the optimized route reduces interactions between the autonomous and non-autonomous vehicles. In an embodiment, the traffic modeling includes the use of a particle traffic model, a trigger-response mobile element following traffic model, a macroscopic traffic model, a microscopic traffic model, a sub-microscopic traffic model, a mesoscopic traffic model, or a combination thereof.

In an embodiment, the present disclosure includes a method for updating one or more vibration fault level states of one or more digital twins, the method including: receiving a request from a client application to update one or more vibration fault level states of one or more digital twins; retrieving one or more digital twins necessary to fulfill the request; retrieving one or more dynamic models necessary to fulfill the request, the one or more dynamic models including a dynamic model that predicts when a vibration fault level will occur based on an input data set; selecting a data source from a set of available data sources based on one or more inputs of the one or more dynamic models; acquiring data from the selected data sources; using the acquired data as one or more inputs to the one or more dynamic models to determine one or more outputs; and updating one or more vibration fault level states of the one or more digital twins based on the outputs of the one or more dynamic models.

In embodiments, the request is received from a client application corresponding to the industrial environment and/or one or more industrial entities within the industrial environment. In embodiments, the request is received from a client application supporting an Industrial Internet of Things sensor system. In embodiments, the digital twin is a digital twin of at least one of the industrial entity and the industrial environment. In embodiments, the dynamic model retrieves data selected from a set consisting of vibration, temperature, pressure, humidity, wind, rainfall, tide, storm surge, cloud cover, snowfall, visibility, radiation, audio, video, imagery, water level, quantum, flow rate, signal power, signal frequency, motion, displacement, velocity, acceleration, light level, finance, cost, stock market, news, social media, revenue, workers, maintenance, productivity, asset performance, worker performance, worker response time, analyte concentration, biological chemical concentration, metal concentration, and organic compound concentration data.

In an embodiment, the data source is selected from the set consisting of an Internet of Things connected device, a machine vision system, an analog vibration sensor, a digital vibration sensor, a fixed digital vibration sensor, a three-axis vibration sensor, a single-axis vibration sensor, an optical vibration sensor, and a crosspoint switch. In an embodiment, obtaining the one or more dynamic models includes identifying one or more dynamic models based on the one or more characteristics indicated in the request and the respective types of the one or more digital twins. In an embodiment, the one or more dynamic models are identified using a lookup table.

In an embodiment, the present disclosure includes a system for monitoring navigational path data through an industrial environment having real-world elements disposed therein. The system includes a digital twin data store including an industrial environment digital twin corresponding to the industrial environment and a worker digital twin corresponding to each worker in a set of workers within the industrial environment, and one or more processors configured to: maintain the industrial environment digital twin via the digital twin data store to include contemporaneous locations of the set of workers within the industrial environment; monitor the movements of each worker in the set of workers via a sensor array; determine navigational path data for each worker in response to detecting the movements of each worker; and update the industrial environment digital twin to include indices of the navigational path data for each worker and to indicate the movements of the worker digital twins along paths corresponding to the navigational path data. In an embodiment, the one or more processors are further configured to determine navigational path data for remaining workers in the set of workers in response to representing the movements of each worker. In an embodiment, the navigational path data is automatically transmitted to the system by one or more personal-associated devices. In an embodiment, the personal-associated devices are one of a mobile device with cellular data capability and a wearable device associated with the worker. In embodiments, the navigational path data is determined via environment-related sensors. In embodiments, the navigational path data is determined using historical path data stored in a digital twin data store. In embodiments, the historical path data is obtained from a device associated with the respective worker. In embodiments, the historical path data is obtained from a device associated with another worker. In embodiments, the historical path data is associated with the worker's current task. In embodiments, the digital twin data store includes an industrial environment digital twin. In embodiments, the one or more processors are further configured to: determine the existence of a conflict between the navigational path data and the industrial environment digital twin; modify the worker's navigational path data in response to determining accuracy of the industrial environment digital twin via the sensor array; and update the industrial environment digital twin in response to determining inaccuracy of the industrial environment digital twin via the sensor array, thereby resolving the conflict.

In an embodiment, the industrial environment digital twin is updated using collected data submitted by workers. In an embodiment, the collected data includes proximity sensor data, image data, or a combination thereof. In an embodiment, the navigation path includes a path for collecting vibration measurements.

In accordance with some embodiments of the present disclosure, provided herein are methods and systems for updating properties of a digital twin of an industrial entity and a digital twin of an industrial environment, including, but not limited to, based on the impact of collected vibration data on a set of digital twin dynamic models, such that the digital twin provides a computer-generated representation of the industrial entity or environment.

According to some embodiments of the present disclosure, a method for updating one or more properties of one or more digital twins is disclosed. The method includes receiving a request to update one or more properties of one or more digital twins; obtaining one or more digital twins necessary to satisfy the request; obtaining one or more dynamic models necessary to satisfy the request; selecting data sources from a set of available data sources based on one or more inputs of the one or more dynamic models; obtaining data from the selected data sources; using the obtained data as one or more inputs to the one or more dynamic models to calculate one or more outputs; and updating one or more properties of the one or more digital twins based on the outputs of the one or more dynamic models.

In an embodiment, the request is received from a client application corresponding to the industrial environment and/or one or more industrial entities within the industrial environment.

In an embodiment, the request is received from a client application supporting an Industrial Internet of Things sensor system.

In an embodiment, the request is received from a client application supporting the vibration sensor system.

In an embodiment, the digital twin is a digital twin of an industrial entity.

In an embodiment, the digital twin is a digital twin of an industrial environment.

In an embodiment, the dynamic model incorporates data selected from the set consisting of vibration, temperature, pressure, humidity, wind, rainfall, tide, storm surge, cloud cover, snowfall, visibility, radiation, audio, video, imagery, water level, quantum, flow rate, signal power, signal frequency, motion, displacement, velocity, acceleration, light level, finance, cost, stock market, news, social media, revenue, workers, maintenance, productivity, asset performance, worker performance, worker response time, analyte concentration, biological compound concentration, metal concentration, and organic compound concentration data.

In an embodiment, the data source is selected from the set consisting of an analog vibration sensor, a digital vibration sensor, a fixed digital vibration sensor, a three-axis vibration sensor, a single-axis vibration sensor, an optical vibration sensor, a crosspoint switch, an Internet of Things connected device, and a machine vision system.

In an embodiment, obtaining the one or more dynamic models includes identifying the one or more dynamic models based on one or more properties indicated in the request and the respective types of the one or more digital twins.

In an embodiment, one or more dynamic models are identified using a lookup table.

According to some embodiments of the present disclosure, a method for updating one or more vibration fault level states of one or more digital twins is disclosed. The method includes receiving a request from a client application to update one or more vibration fault level states of one or more digital twins; obtaining one or more digital twins necessary to satisfy the request; obtaining one or more dynamic models necessary to satisfy the request; selecting a data source from a set of available data sources based on one or more inputs of the one or more dynamic models; obtaining data from the selected data source; using the obtained data as one or more inputs to the one or more dynamic models to calculate one or more outputs; and updating one or more vibration fault level states of the one or more digital twins based on the outputs of the one or more dynamic models.

In an embodiment, the vibration fault level condition is selected from the set of normal, suboptimal, critical, and warning.

In an embodiment, the request is received from a client application corresponding to the industrial environment and/or one or more industrial entities within the industrial environment.

In an embodiment, the request is received from a client application supporting an Industrial Internet of Things sensor system.

In an embodiment, the request is received from a client application supporting the vibration sensor system.

In an embodiment, the dynamic model incorporates data selected from the group of data related to vibration, temperature, pressure, humidity, wind, rainfall, tides, storm surges, cloud cover, snowfall, visibility, radiation, audio, video, images, water level, quantum, flow rate, signal power, signal frequency, motion, displacement, velocity, acceleration, light level, finance, costs, stock market, news, social media, revenue, workers, maintenance, productivity, asset performance, worker performance, worker response time, analyte concentration, biochemical concentration, metal concentration, and organic compound concentration.

In an embodiment, the data source is selected from the set consisting of an analog vibration sensor, a digital vibration sensor, a fixed digital vibration sensor, a three-axis vibration sensor, a single-axis vibration sensor, an optical vibration sensor, a crosspoint switch, an Internet of Things connected device, and a machine vision system.

In an embodiment, obtaining the one or more dynamic models includes identifying the one or more dynamic models based on one or more properties indicated in the request and the respective types of the one or more digital twins.

In an embodiment, one or more dynamic models are identified using a lookup table.

According to some embodiments of the present disclosure, a method for updating one or more vibration severity unit values of one or more digital twins is disclosed. The method includes receiving a request from a client application to update one or more vibration severity unit values of one or more digital twins; obtaining one or more digital twins necessary to satisfy the request; obtaining one or more dynamic models necessary to satisfy the request; selecting a data source from a set of available data sources based on one or more inputs of the one or more dynamic models; obtaining data from the selected data source; using the obtained data as one or more inputs to the one or more dynamic models to calculate one or more outputs; and updating the one or more vibration severity unit values of the one or more digital twins based on the outputs of the one or more dynamic models.

In an embodiment, the vibration severity units represent displacement.

In an embodiment, the unit of vibration severity represents speed.

In an embodiment, the vibration severity units represent acceleration.

In an embodiment, the request is received from a client application corresponding to the industrial environment and/or one or more industrial entities within the industrial environment.

In an embodiment, the request is received from a client application supporting an Industrial Internet of Things sensor system.

In an embodiment, the request is received from a client application supporting the vibration sensor system.

In an embodiment, the digital twin is a digital twin of an industrial entity.

In an embodiment, the digital twin is a digital twin of an industrial environment.

In an embodiment, the dynamic model obtains selected data from a group of data representing vibration, temperature, pressure, humidity, wind, rainfall, tides, storm surges, cloud cover, snowfall, visibility, radiation, audio, video, images, water level, quantum, flow rate, signal power, signal frequency, motion, displacement, velocity, acceleration, light level, finance, costs, stock market, news, social media, revenue, workers, maintenance, productivity, asset performance, worker performance, worker response time, analyte concentration, biological compound concentration, metal concentration, and organic compound concentration.

In an embodiment, the data source is selected from the set consisting of an analog vibration sensor, a digital vibration sensor, a fixed digital vibration sensor, a three-axis vibration sensor, a single-axis vibration sensor, an optical vibration sensor, a crosspoint switch, an Internet of Things connected device, and a machine vision system.

In an embodiment, obtaining the one or more dynamic models includes identifying the one or more dynamic models based on one or more properties indicated in the request and the respective types of the one or more digital twins.

In an embodiment, one or more dynamic models are identified using a lookup table.

According to some embodiments of the present disclosure, a method for updating one or more failure probability values of one or more digital twins is disclosed. The method includes receiving a request from a client application to update one or more failure probability values of one or more digital twins; obtaining one or more digital twins necessary to satisfy the request; obtaining one or more dynamic models necessary to satisfy the request; selecting data sources from a set of available data sources based on one or more inputs of the one or more dynamic models; obtaining data from the selected data sources; using the obtained data as one or more inputs to the one or more dynamic models to calculate one or more outputs; and updating the failure probability values of the one or more digital twins based on the outputs of the one or more dynamic models.

In an embodiment, the request is received from a client application corresponding to the industrial environment and/or one or more industrial entities within the industrial environment.

In an embodiment, the request is received from a client application supporting an Industrial Internet of Things sensor system.

In an embodiment, the request is received from a client application supporting the vibration sensor system.

In an embodiment, the digital twin is a digital twin of an industrial entity.

In an embodiment, the digital twin is a digital twin of an industrial environment.

In an embodiment, the dynamic model incorporates data selected from a set of data representing vibration, temperature, pressure, humidity, wind, rainfall, tides, storm surges, cloud cover, snowfall, visibility, radiation, audio, video, images, water level, quantum, flow rate, signal power, signal frequency, motion, displacement, velocity, acceleration, light level, finance, cost, stock market, news, social media, revenue, workers, maintenance, productivity, asset performance, worker performance, worker response time, analyte concentration, biological compound concentration, metal concentration, and organic compound concentration.

In an embodiment, the data source is selected from the set consisting of an analog vibration sensor, a digital vibration sensor, a fixed digital vibration sensor, a three-axis vibration sensor, a single-axis vibration sensor, an optical vibration sensor, a crosspoint switch, an Internet of Things connected device, and a machine vision system.

In an embodiment, obtaining the one or more dynamic models includes identifying the one or more dynamic models based on one or more properties indicated in the request and the respective types of the one or more digital twins.

In an embodiment, one or more dynamic models are identified using a lookup table.

According to some embodiments of the present disclosure, a method for updating one or more downtime probability values of one or more digital twins is disclosed. The method includes receiving a request from a client application to update one or more downtime probability values of one or more digital twins; obtaining one or more digital twins necessary to fulfill the request; obtaining one or more dynamic models necessary to fulfill the request; selecting data sources from a set of available data sources based on one or more inputs of the one or more dynamic models; obtaining data from the selected data sources; using the obtained data as one or more inputs to the one or more dynamic models to calculate one or more outputs; and updating one or more values associated with the downtime probability values of the one or more digital twins based on the outputs of the one or more dynamic models.

In an embodiment, the request is received from a client application corresponding to the industrial environment and/or one or more industrial entities within the industrial environment.

In an embodiment, the request is received from a client application supporting an Industrial Internet of Things sensor system.

In an embodiment, the request is received from a client application supporting the vibration sensor system.

In an embodiment, the digital twin is a digital twin of an industrial entity.

In an embodiment, the digital twin is a digital twin of an industrial environment.

In an embodiment, the dynamic model takes data selected from the set consisting of vibration, temperature, pressure, humidity, wind, rainfall, tide, storm surge, cloud cover, snowfall, visibility, radiation, audio, video, imagery, water level, quantum, flow rate, signal power, signal frequency, motion, displacement, velocity, acceleration, light level, finance, cost, stock market, news, social media, revenue, workers, maintenance, productivity, asset performance, worker performance, worker response time, analyte concentration, biochemical concentration, metal concentration, and organic concentration data.

In an embodiment, the data source is selected from the set consisting of an analog vibration sensor, a digital vibration sensor, a fixed digital vibration sensor, a three-axis vibration sensor, a single-axis vibration sensor, an optical vibration sensor, a crosspoint switch, an Internet of Things connected device, and a machine vision system.

In an embodiment, obtaining the one or more dynamic models includes identifying the one or more dynamic models based on one or more properties indicated in the request and the respective types of the one or more digital twins.

In an embodiment, one or more dynamic models are identified using a lookup table.

According to some embodiments of the present disclosure, a method for updating one or more shutdown probability values for one or more digital twins is disclosed. The method includes receiving a request from a client application to update one or more shutdown probability values for one or more digital twins; obtaining one or more digital twins necessary to fulfill the request; obtaining one or more dynamic models necessary to fulfill the request; selecting data sources from a set of available data sources based on one or more inputs of the one or more dynamic models; obtaining data from the selected data sources; using the obtained data as one or more inputs to the one or more dynamic models to calculate one or more outputs; and updating one or more values related to downtime probability for the one or more digital twins based on the outputs of the one or more dynamic models.

In an embodiment, the request is received from a client application corresponding to the industrial environment and/or one or more industrial entities within the industrial environment.

In an embodiment, the request is received from a client application supporting an Industrial Internet of Things sensor system.

In an embodiment, the request is received from a client application supporting the vibration sensor system.

In an embodiment, the digital twin is a digital twin of an industrial entity.

In an embodiment, the digital twin is a digital twin of an industrial environment.

In an embodiment, the dynamic model takes data selected from the set consisting of vibration, temperature, pressure, humidity, wind, rainfall, tide, storm surge, cloud cover, snowfall, visibility, radiation, audio, video, imagery, water level, quantum, flow rate, signal power, signal frequency, motion, displacement, velocity, acceleration, light level, finance, cost, stock market, news, social media, revenue, workers, maintenance, productivity, asset performance, worker performance, worker response time, analyte concentration, biochemical concentration, metal concentration, and organic compound concentration data.

In an embodiment, the data source is selected from the set consisting of an analog vibration sensor, a digital vibration sensor, a fixed digital vibration sensor, a three-axis vibration sensor, a single-axis vibration sensor, an optical vibration sensor, a crosspoint switch, an Internet of Things connected device, and a machine vision system.

In an embodiment, obtaining the one or more dynamic models includes identifying the one or more dynamic models based on one or more properties indicated in the request and the respective types of the one or more digital twins.

In an embodiment, one or more dynamic models are identified using a lookup table.

According to some embodiments of the present disclosure, a method for updating one or more downtime cost values of one or more digital twins is disclosed. The method includes receiving a request from a client application to update one or more downtime cost values of one or more digital twins; obtaining one or more digital twins necessary to fulfill the request; obtaining one or more dynamic models necessary to fulfill the request; selecting data sources from a set of available data sources based on one or more inputs of the one or more dynamic models; obtaining data from the selected data sources; using the obtained data as one or more inputs to the one or more dynamic models to calculate one or more outputs; and updating one or more values associated with the downtime cost values of the one or more digital twins based on the outputs of the one or more dynamic models.

In an embodiment, the downtime cost value is selected from the set consisting of downtime cost per hour, downtime cost per day, downtime cost per week, downtime cost per month, downtime cost per quarter, and downtime cost per year.

In an embodiment, the request is received from a client application corresponding to the industrial environment and/or one or more industrial entities within the industrial environment.

In an embodiment, the request is received from a client application supporting an Industrial Internet of Things sensor system.

In an embodiment, the request is received from a client application supporting the vibration sensor system.

In an embodiment, the digital twin is a digital twin of an industrial entity.

In an embodiment, the digital twin is a digital twin of an industrial environment.

In an embodiment, the dynamic model obtains data selected from the set consisting of vibration, temperature, pressure, humidity, wind, rainfall, tide, storm surge, cloud cover, snowfall, visibility, radiation, audio, video, imagery, water level, quantum, flow rate, signal power, signal frequency, motion, displacement, velocity, acceleration, light level, finance, cost, stock market, news, social media, revenue, workers, maintenance, productivity, asset performance, worker performance, worker response time, analyte concentration, biological compound concentration, metal concentration, and organic compound concentration data.

In an embodiment, the data source is selected from the set consisting of an analog vibration sensor, a digital vibration sensor, a fixed digital vibration sensor, a three-axis vibration sensor, a single-axis vibration sensor, an optical vibration sensor, a crosspoint switch, an Internet of Things connected device, and a machine vision system.

In an embodiment, obtaining the one or more dynamic models includes identifying the one or more dynamic models based on one or more properties indicated in the request and the respective types of the one or more digital twins.

In an embodiment, one or more dynamic models are identified using a lookup table.

According to some embodiments of the present disclosure, a method is disclosed for updating one or more manufacturing key performance indicator (KPI) values of one or more digital twins. The method includes receiving a request from a client application to update one or more manufacturing KPI values of one or more digital twins; retrieving one or more digital twins necessary to satisfy the request; retrieving one or more dynamic models necessary to satisfy the request; selecting data sources from a set of available data sources based on one or more inputs of the one or more dynamic models; retrieving data from the selected data sources; using the retrieved data as one or more inputs to the one or more dynamic models to calculate one or more outputs; and updating the one or more manufacturing KPI values of the one or more digital twins based on the outputs of the one or more dynamic models.

In an embodiment, the manufacturing KPIs are selected from the set consisting of uptime, utilization rate, standard operating efficiency, overall operating efficiency, overall equipment effectiveness, machine downtime, unplanned downtime, machine setup time, inventory turns, inventory accuracy, quality (e.g., defect rate), first-order yield, rework, scrap, rejected inspections, on-time delivery, customer returns, training time, employee turnover, reportable health and safety incidents, revenue per employee, profit per employee, schedule maintenance, total cycle time, throughput, changeover time, yield, planned maintenance rate, and utilization rate.

In an embodiment, the request is received from a client application corresponding to the industrial environment and/or one or more industrial entities within the industrial environment.

In an embodiment, the request is received from a client application supporting an Industrial Internet of Things sensor system.

In an embodiment, the request is received from a client application supporting the vibration sensor system.

In an embodiment, the digital twin is a digital twin of an industrial entity.

In an embodiment, the digital twin is a digital twin of an industrial environment.

In an embodiment, the dynamic model takes data selected from the set consisting of vibration, temperature, pressure, humidity, wind, rainfall, tide, storm surge, cloud cover, snowfall, visibility, radiation, audio, video, imagery, water level, quantum, flow rate, signal power, signal frequency, motion, displacement, velocity, acceleration, light level, finance, cost, stock market, news, social media, revenue, workers, maintenance, productivity, asset performance, worker performance, worker response time, analyte concentration, biological compound concentration, metal concentration, and organic compound concentration data.

In an embodiment, the data source is selected from the set consisting of an analog vibration sensor, a digital vibration sensor, a fixed digital vibration sensor, a three-axis vibration sensor, a single-axis vibration sensor, an optical vibration sensor, a crosspoint switch, an Internet of Things connected device, and a machine vision system.

In an embodiment, obtaining the one or more dynamic models includes identifying the one or more dynamic models based on one or more properties indicated in the request and the respective types of the one or more digital twins.

In an embodiment, one or more dynamic models are identified using a lookup table.

According to some embodiments of the present disclosure, a method is disclosed. The method includes receiving import data from one or more data sources, the import data corresponding to an industrial environment; generating an environment digital twin representing the industrial environment based on the import data; identifying one or more industrial entities within the industrial environment; generating a set of discrete digital twins representing the one or more industrial entities within the environment; establishing a connection with a sensor system of the industrial environment; receiving real-time sensor data from one or more sensors of the sensor system via the connection; and updating at least one of the environment digital twin and the set of discrete digital twins based on the real-time sensor data.

In an embodiment, connectivity to the sensor system is established via an application programming interface (API).

In embodiments, the set of environmental digital twins and discrete digital twins is a visual digital twin configured to be rendered in a visual manner. In some embodiments, the method further includes outputting the visual digital twin to a client application that displays the visual digital twin through a virtual reality headset. In some embodiments, the method further includes outputting the visual digital twin to a client application that displays the visual digital twin through a display device of the user device. In some embodiments, the method further includes outputting the visual digital twin to a client application that displays the visual digital twin within a display interface, with information related to the visual digital twin overlaid on the visual digital twin and/or displayed within the display interface. In some embodiments, the method further includes outputting the visual digital twin to a client application that displays the visual digital twin through an augmented reality-enabled device.

In some embodiments, the method further includes instantiating a graph database having a set of nodes connected by edges, wherein a first node of the set of nodes includes data defining the environment digital twin, and one or more entity nodes each include respective data defining a respective discrete digital twin of the set of discrete digital twins. In some embodiments, each edge represents a relationship between two respective digital twins. In some of these embodiments, embedding the discrete digital twins includes connecting an entity node corresponding to each discrete digital twin to the first node with an edge representing a respective relationship between a respective industrial entity represented by the respective discrete digital twin and the industrial environment. In some embodiments, each edge represents a spatial relationship between the two respective digital twins. In some embodiments, each edge represents an operational relationship between the two respective digital twins. In some embodiments, each edge stores metadata corresponding to the relationship between the two respective digital twins. In some embodiments, each entity node of the one or more entity nodes includes one or more respective properties of the respective industrial entity represented by the entity node. In some embodiments, each entity node of the one or more entity nodes includes one or more behaviors of a respective property of the respective industry entity represented by the entity node. In some embodiments, an environment node includes one or more properties of an environment. In some embodiments, an environment node includes one or more behaviors of an environment.

In some embodiments, the method further includes running a simulation based on the environmental digital twin and the one or more discrete digital twins. In some embodiments, the simulation simulates the operation of a machine that generates outputs based on a set of inputs. In some embodiments, the simulation simulates vibration patterns of bearings in a machine in an industrial environment.

In an embodiment, the one or more industrial entities are selected from the set consisting of a machine component, an infrastructure component, an equipment component, a workpiece component, a tool component, a building component, an electrical component, a fluid handling component, a mechanical component, a power component, a manufacturing component, an energy production component, a material extraction component, a worker, a robot, an assembly line, and an autonomous vehicle.

In an embodiment, the industrial environment is one of a factory, an energy production facility, a material extraction facility, a mining facility, a drilling facility, an industrial agriculture facility, and an industrial storage facility.

In an embodiment, the imported data includes a three-dimensional scan of the environment.

In an embodiment, the imported data includes a LIDAR scan of the industrial environment.

In an embodiment, generating a digital twin of an industrial environment includes generating a set of surfaces of the industrial environment.

In an embodiment, generating a digital twin of an industrial environment includes constructing a set of dimensions of the industrial environment.

In an embodiment, generating the set of discrete digital twins includes importing a predefined digital twin of the industrial entity from a manufacturer of the industrial entity, the predefined digital twin including the properties and behavior of the industrial entity.

In an embodiment, generating a set of discrete digital twins includes classifying industrial entities in the import data of the industrial environment and generating discrete digital twins corresponding to the classified industrial entities.

According to aspects of the present disclosure, a system for monitoring interactions within an industrial environment includes a digital twin data store and one or more processors. The digital twin data store includes data collected by a set of proximity sensors disposed within the industrial environment. The data includes position data indicating the respective positions of a plurality of elements within the industrial environment. The one or more processors are configured to maintain an industrial environment digital twin for the industrial environment via the digital twin data store, receive signals from the plurality of elements indicative of actuation of at least one proximity sensor in the set of proximity sensors by a real-world element, collect updated position data for the real-world element using the at least one proximity sensor in response to the actuation of the at least one proximity sensor, and update the industrial environment digital twin in the digital twin data store to include the updated position data.

In an embodiment, each of the set of proximity sensors is configured to detect a device associated with a user.

In an embodiment, the device is a wearable device.

In an embodiment, the device is an RFID device.

In an embodiment, each element of the plurality of elements is a mobile element.

In an embodiment, each of the multiple elements is a respective worker.

In an embodiment, the multiple elements include mobile device elements and workers, and the mobile device location data is measured using data transmitted by each mobile device element, and the worker location data is measured using data acquired by the system.

In an embodiment, worker location data is measured using information transmitted from devices associated with each worker.

In an embodiment, activation of at least one proximity sensor occurs in response to interaction between a respective worker and the proximity sensor.

In an embodiment, activation of at least one proximity sensor occurs in response to an interaction between a worker and at least one respective proximity sensor digital twin corresponding to the at least one proximity sensor.

In an embodiment, one or more processors collect updated position data for the plurality of elements using the set of proximity sensors in response to activation of at least one proximity sensor.

According to aspects of the present disclosure, a system for monitoring an industrial environment having real-world elements disposed therein includes a digital twin data store and one or more processors. The digital twin data store includes a set of states stored therein. The set of states includes one or more states of the real-world elements. Each state in the set of states is uniquely identifiable by a set of criteria from a set of monitored attributes. The monitored attributes correspond to signals received from a sensor array operably coupled to the real-world elements. The one or more processors are configured to maintain an industrial environment digital twin for the industrial environment via the digital twin data store; receive signals for one or more attributes in the set of monitored attributes via the sensor array; determine one or more current states of the real-world elements in response to determining that the signals for the one or more attributes satisfy a respective set of the identification criteria; and update the industrial environment digital twin to include the current states of the one or more real-world elements in response to determining the current states. The current states correspond to each state in the set of states.

In an embodiment, the cognitive intelligence system stores the identification criteria in a digital twin data store.

In an embodiment, in response to receiving the discrimination criteria, the cognitive intelligence system updates the trigger conditions for the set of monitored attributes to include the updated trigger conditions.

In an embodiment, the updated trigger condition reduces the time interval between receiving a sensed attribute from the set of monitored attributes.

In an embodiment, the sensed attributes are attributes that correspond to the discrimination criteria.

In one embodiment, the sensed attributes are all attributes corresponding to each real-world element.

In an embodiment, the cognitive intelligence system determines whether instructions exist for responding to the condition, and in response to determining that instructions do not exist, the cognitive intelligence system uses the digital twin simulation system to determine instructions for responding to the condition.

In an embodiment, the digital twin simulation system and cognitive intelligence system repeatedly iterate the simulation values and response actions until the associated cost function is minimized, and the one or more processors are further configured to, in response to minimizing the associated cost function, store the response action that minimizes the associated cost function in the digital twin data store.

In an embodiment, the cognitive intelligence system is configured to affect responsive behavior associated with the condition.

In an embodiment, the cognitive intelligence system is configured to stop the operation of one or more real-world elements identified by the responsive action.

In an embodiment, the cognitive intelligence system is configured to determine resources for the industrial environment identified by the responsive action and modify the resources in response.

In an embodiment, the resource includes data transfer bandwidth, and modifying the resource includes establishing additional connections to thereby increase the data transfer bandwidth.

According to an aspect of the present disclosure, a system for monitoring navigation path data through an industrial environment having real-world elements disposed therein includes a digital twin data store and one or more processors. The digital twin data store includes an industrial environment digital twin corresponding to the industrial environment and a worker digital twin corresponding to each worker in a set of workers within the industrial environment. The one or more processors are configured to maintain the industrial environment digital twin via the digital twin data store to include contemporaneous positions of the set of workers within the industrial environment; monitor the movement of each worker in the set of workers via a sensor array; determine navigation path data for each worker in response to detecting the movement of each worker; update the industrial environment digital twin to include an indicator of the navigation path data for each worker; and move the worker digital twin along the path of the navigation path data.

In an embodiment, the one or more processors are further configured to update determining navigation path data for remaining workers in the set of workers in response to representing the movement of each worker.

In an embodiment, the navigation route data includes a route for collecting vibration measurements from one or more machines in an industrial environment.

In an embodiment, navigation route data is automatically transmitted to the system by one or more individual-associated devices.

In an embodiment, the personal device is a mobile device with cellular data capability.

In an embodiment, the personal device is a wearable device associated with the worker.

In an embodiment, navigation path data is determined via environment-related sensors.

In an embodiment, navigation route data is determined using historical route data stored in a digital twin data store.

In an embodiment, past route data is obtained using each worker.

In an embodiment, past route data is obtained using a separate worker.

In an embodiment, historical route data is associated with the worker's current task.

In an embodiment, the digital twin data store includes an industrial environment digital twin.

In an embodiment, the one or more processors are further configured to determine the existence of a conflict between the navigation path data and the industrial environment digital twin, modify the worker's navigation path data in response to determining the accuracy of the industrial environment digital twin via the sensor array, and update the industrial environment digital twin in response to determining the inaccuracy of the industrial environment digital twin via the sensor array, thereby resolving the conflict.

In an embodiment, the industrial environment digital twin is updated using collected data sent by workers.

In an embodiment, the collected data includes proximity sensor data, image data, or a combination thereof.

According to an aspect of the present disclosure, a system for monitoring navigation path data includes a digital twin data store and one or more processors. The digital twin data store stores an industrial environment digital twin with real-world element digital twins embedded therein. The industrial environment digital twin provides a digital twin of the industrial environment. Each real-world element digital twin provides a digital twin of a corresponding real-world element in the industrial environment. The real-world elements include a set of workers. The one or more processors are configured to monitor movements of each worker in the set of workers, determine navigation path data for at least one worker in the set of workers, and represent the movements of the at least one worker by movements of an associated digital twin using the navigation path data.

In an embodiment, the one or more processors are further configured to determine navigation path data for the remaining workers in the set of workers in response to representing the movement of at least one worker.

In an embodiment, the navigation route data includes a route for collecting vibration measurements from one or more machines in an industrial environment.

In an embodiment, navigation route data is automatically transmitted to the system by one or more personal associated devices.

In an embodiment, the personal device is a mobile device with cellular data capability.

In an embodiment, the personal device is a wearable device associated with the worker.

In an embodiment, navigation path data is determined via environment-related sensors.

In an embodiment, navigation route data is determined using historical route data stored in a digital twin data store.

In an embodiment, past route data is obtained using each worker.

In an embodiment, past route data is obtained using a separate operator.

In an embodiment, the historical route data is associated with the worker's current task.

In an embodiment, the digital twin data store includes an industrial environment digital twin.

In an embodiment, the one or more processors are further configured to determine the existence of a conflict between the navigation path data and the industrial environment digital twin, modify the worker's navigation path data in response to determining the accuracy of the industrial environment digital twin via the sensor array, and update the industrial environment digital twin in response to determining the inaccuracy of the industrial environment digital twin via the sensor array, thereby resolving the conflict.

In an embodiment, the industrial environment digital twin is updated using collected data sent by workers.

In an embodiment, the collected data includes proximity sensor data, image data, or a combination thereof.

According to an aspect of the present disclosure, a system for representing an industrial workpiece object in a digital twin includes a digital twin data store and one or more processors. The digital twin data store stores an industrial environment digital twin with real-world element digital twins embedded therein. The industrial environment digital twin provides a digital twin of the industrial environment. Each real-world element digital twin provides a digital twin of a corresponding real-world element in the industrial environment. The real-world elements include an industrial workpiece and a worker. The one or more processors are configured to simulate, using a digital twin simulation system, a set of physical interactions performed by a worker on the industrial workpiece. The simulation includes obtaining the set of physical interactions, estimating an expected duration for performance of each physical interaction in the set of physical interactions based on historical data of the worker, and storing, in the digital twin data store, an industrial workpiece digital twin corresponding to the performance of the set of physical interactions of the industrial workpiece.

In an embodiment, historical data is obtained from user-entered data.

In an embodiment, historical data is obtained from a sensor array in an industrial environment.

In an embodiment, historical data is obtained from a wearable device worn by the worker.

In an embodiment, each data item in the historical data includes an indicator of a first time and a second time, the first time being the time of execution of the physical interaction.

In one embodiment, the second time is the time when the worker's expected break period begins.

In an embodiment, the historical data further includes an indicator of the duration of the expected break.

In one embodiment, the second time is the time when the worker's expected break period ends.

In an embodiment, the historical data further includes an indicator of the duration of the expected break.

In one embodiment, the second time is the time that ends the worker's unexpected break.

In an embodiment, the historical data further includes an indicator of the duration of the unexpected break.

In an embodiment, each datum in the historical data includes an indicator of successive interactions between the worker and multiple other workpieces prior to performing a set of physical interactions with the workpiece.

In an embodiment, each datum in the historical data includes an indicator of the number of consecutive days the worker was present in the industrial environment.

In an embodiment, each piece of historical data includes an indicator of the worker's age.

In an embodiment, the historical data further includes an indicator of a first duration of the worker's expected break time and a second duration of the worker's unexpected break time, each datum of the historical data including an indicator of a plurality of times, an indicator of consecutive interactions of the worker with a plurality of other workpieces prior to performing a set of physical interactions with the workpieces, an indicator of the number of consecutive days the worker was present in the industrial environment, and/or an indicator of the worker's age. The plurality of times includes a first time, a second time, a third time, and a fourth time. The first time is the duration of the physical interaction, the second time is the start time of the expected break time, the third time is the end time of the expected break time, and the fourth time is the end time of the unexpected break time.

In an embodiment, the industrial workpiece digital twin is a first industrial workpiece digital twin corresponding to the industrial workpiece before any physical interactions have been performed, and a second industrial workpiece digital twin corresponding to the industrial workpiece after a set of physical interactions have been performed.

In an embodiment, the industrial workpiece digital twin is a plurality of industrial workpiece digital twins, each of which corresponds to the industrial workpiece after performing a respective one of the set of physical interactions.

According to aspects of the present disclosure, a system for inducing experiences via wearable devices includes a digital twin data store and one or more processors. The digital twin data store stores industrial environment digital twins with real-world element digital twins embedded therein. The industrial environment digital twins provide a digital twin of the industrial environment. Each real-world element digital twin provides a digital twin of a corresponding real-world element in the industrial environment. The real-world elements include a wearable device worn by a wearer in the industrial environment. The one or more processors are configured to embed a set of control instructions for the wearable device in the digital twin and to induce an experience for a wearer of the wearable device in response to an interaction between the wearable device and a respective one of the digital twins.

In embodiments, the wearable device is configured to output video, audio, haptic feedback, or a combination thereof to elicit an experience for the wearer.

In an embodiment, the experience is a virtual reality experience.

In an embodiment, the wearable device includes an image capture device, and the interaction includes the wearable device capturing an image of the digital twin.

In an embodiment, the wearable device includes a display device and the experience includes displaying information related to each digital twin.

In an embodiment, the displayed information includes financial data related to the digital twin.

In an embodiment, the information displayed includes profits or losses associated with the operation of the digital twin.

In an embodiment, the displayed information includes information related to an occluded element that is at least partially occluded by a foreground element.

In an embodiment, the displayed information includes the operating parameters of the occluded element.

In an embodiment, the displayed information further includes a comparison of the displayed operating parameters with corresponding design parameters.

In an embodiment, the comparison includes modifying the display of the operational parameter to change the color, size, or display duration of the operational parameter.

In an embodiment, the information includes a virtual model of the occluded element overlaid on the occluded element and visualized together with the foreground element.

In an embodiment, the information includes indicators for removable elements configured to provide access to the occluded elements. Each indicator is displayed in proximity to a respective removable element.

In one embodiment, the indicators are displayed sequentially such that a first indicator corresponding to a first removable element is displayed, and in response to the operator removing the first removable element, a second indicator corresponding to a second removable element is displayed.

According to aspects of the present disclosure, a system for embedding device outputs in an industrial digital twin includes a digital twin data store and one or more processors. The digital twin data store stores an industrial environment digital twin having real-world element digital twins embedded therein. The industrial environment digital twin provides a digital twin of the industrial environment. Each real-world element digital twin provides a digital twin of a corresponding real-world element in the industrial environment. The real-world elements include simultaneous position and mapping sensors. The one or more processors are configured to acquire position information from the simultaneous position and mapping sensors, determine that the simultaneous position and mapping sensors are located within the environment, collect mapping information, path information, or a combination thereof from the simultaneous position and mapping sensors, and update the industrial environment digital twin using the mapping information, path information, or a combination thereof. The collection occurs in response to determining that the simultaneous position and mapping sensors are located within the industrial environment.

In an embodiment, the one or more processors are configured to: detect objects in the mapping information; for each detected object in the mapping information, determine whether the detected object corresponds to an existing real-world element digital twin; in response to determining that the detected object does not correspond to an existing real-world element digital twin, add the digital twin of the detected object to a real-world element digital twin in the digital twin data store using a digital twin generation system; and in response to determining that the detected object does not correspond to an existing real-world element digital twin, update the real-world element digital twin to include the new information detected by the synchronous position and mapping sensors.

In an embodiment, the synchronous position and mapping sensor is configured to generate mapping information using a sub-optimal mapping algorithm.

In an embodiment, the suboptimal mapping algorithm generates bounded-region representations of elements within an industrial environment.

In an embodiment, the one or more processors are further configured to obtain the object detected by the sub-optimal mapping algorithm, determine whether the detected object corresponds to an existing real-world element digital twin, and, in response to determining that the detected object corresponds to an existing real-world element digital twin, update the mapping information to include dimensional information of the real-world element digital twin.

In an embodiment, updated mapping information is provided to synchronous position and mapping sensors to thereby optimize navigation through industrial environments.

In an embodiment, the one or more processors are further configured to, in response to determining that the detected object does not correspond to an existing real-world element digital twin, request updated data for the detected object from a synchronous location and mapping sensor configured to generate a refined map of the detected object.

In an embodiment, the synchronous position and mapping sensor provides updated data using a second algorithm. The second algorithm is configured to increase the resolution of detected objects.

In an embodiment, the synchronous location and mapping sensor captures updated data of real-world elements corresponding to detected objects in response to receiving a request.

In an embodiment, the synchronous position and mapping sensors are located in an autonomous vehicle navigating an industrial environment.

In an embodiment, navigation of an autonomous vehicle includes use of a digital twin received from a digital twin data store.

According to aspects of the present disclosure, a system for embedding device outputs in an industrial digital twin includes a digital twin data store and one or more processors. The digital twin data store stores an industrial environment digital twin having real-world element digital twins embedded therein. The industrial environment digital twin provides a digital twin of the industrial environment. Each real-world element digital twin provides a digital twin for a corresponding real-world element in the industrial environment. The real-world element includes a light detection and ranging sensor. The one or more processors are configured to obtain output from the light detection and ranging sensor and embed the output of the light detection and ranging sensor in the industrial environment digital twin to define at least one external feature of the real-world element in the industrial environment.

In an embodiment, the one or more processors are further configured to analyze the output of the light detection and ranging sensor to identify a plurality of detected objects within the output. Each of the plurality of detected objects is a closed shape.

In an embodiment, the one or more processors are configured to compare the plurality of detected objects to real-world element digital twins in the digital twin data store; and, for each of the plurality of detected objects, update a respective real-world element digital twin in the digital twin data store in response to determining that the detected object corresponds to one or more of the real-world element digital twins; and add a new real-world element digital twin to the digital twin data store in response to determining that the detected object does not correspond to a real-world element digital twin.

In an embodiment, output from the light detection and ranging sensor is received at a first resolution, and the one or more processors are further configured to compare the plurality of detected objects to real-world element digital twins in the digital twin data store, and for each of the plurality of detected objects that does not correspond to a real-world element digital twin, instruct the light detection and ranging sensor to increase the scan resolution to a second resolution and perform a scan of the detected object using the second resolution.

In an embodiment, the scan is at a resolution at least five times greater than the first resolution.

In an embodiment, the scan is at a resolution at least 10 times greater than the first resolution.

In an embodiment, output from the light detection and ranging sensor is received at a first resolution, and the one or more processors are further configured to compare the plurality of detected objects to real-world element digital twins in the digital twin data store and, for each of the plurality of detected objects, update a respective real-world element digital twin in the digital twin data store in response to determining that the detected object corresponds to one or more of the real-world element digital twins. In response to determining that the detected object does not correspond to a real-world element digital twin, the system is further configured to instruct the light detection and ranging sensor to increase the scanning resolution to a second resolution, scan the detected object using the second resolution, and add a new real-world element digital twin for the detected object to the digital twin data store.

According to aspects of the present disclosure, a system for embedding device outputs in an industrial digital twin includes a digital twin data store and one or more processors. The digital twin data store includes an industrial environment digital twin providing a digital twin of an industrial environment. The industrial environment includes real-world elements disposed therein. The real-world elements include a plurality of wearable devices. The industrial environment digital twin includes a plurality of real-world element digital twins embedded therein, each real-world element digital twin corresponding to a respective one of the real-world elements. The one or more processors are configured, for each of the plurality of wearable devices, to obtain output from the wearable device and, in response to detecting a trigger condition, update the industrial environment digital twin using the output from the wearable device.

In one embodiment, the trigger condition is the receipt of an output from the wearable device.

In an embodiment, the trigger condition is a determination that the output from the wearable device differs from a previously stored output from the wearable device.

In an embodiment, the trigger condition is a determination that a received output from another wearable device in the plurality of wearable devices is different from a previously stored output from that other wearable device.

In an embodiment, the trigger condition includes a mismatch between an output from one wearable device and a contemporaneous output from another of the wearable devices.

In an embodiment, the trigger condition includes a mismatch between an output from the wearable device and a simulated value for the wearable device.

In an embodiment, the trigger condition includes user interaction with a digital twin corresponding to the wearable device.

In an embodiment, the one or more processors are further configured to detect objects in the mapping information received from the synchronous location and mapping sensors. For each detected object in the mapping information, the system is further configured to determine whether the detected object corresponds to an existing real-world element digital twin; in response to determining that the detected object does not correspond to an existing real-world element digital twin, add the detected object's digital twin to the real-world element digital twin in the digital twin data store using the digital twin generation system; and in response to determining that the detected object corresponds to an existing real-world element digital twin, update the real-world element digital twin to include the new information detected by the synchronous location and mapping sensors.

In an embodiment, the synchronous position and mapping sensor is configured to generate mapping information using a suboptimal mapping algorithm.

In an embodiment, a suboptimal mapping algorithm generates a boundary region representation of elements within an industrial environment.

In an embodiment, the one or more processors are further configured to obtain the object detected by the sub-optimal mapping algorithm, determine whether the detected object corresponds to an existing real-world element digital twin, and, in response to determining that the detected object corresponds to an existing real-world element digital twin, update the mapping information to include dimensional information from the real-world element digital twin.

In an embodiment, updated mapping information is provided to synchronous position and mapping sensors to thereby optimize navigation through industrial environments.

In an embodiment, the one or more processors are further configured to, in response to determining that the detected object does not correspond to an existing real-world element digital twin, request updated data for the detected object from a synchronous location and mapping sensor configured to generate a refined map of the detected object.

In an embodiment, the synchronous position and mapping sensor provides updated data using a second algorithm. The second algorithm is configured to increase the resolution of detected objects.

In an embodiment, the synchronous location and mapping sensor retrieves updated data for real-world elements corresponding to detected objects in response to receiving a request.

In an embodiment, the synchronous position and mapping sensors are located in an autonomous vehicle navigating an industrial environment.

In an embodiment, navigation of an autonomous vehicle includes use of real-world element digital twins received from a digital twin data store.

According to aspects of the present disclosure, a system for representing attributes in an industrial digital twin includes a digital twin data store and one or more processors. The digital twin data store stores an industrial environment digital twin including real-world element digital twins embedded therein. The industrial environment digital twin corresponds to an industrial environment. Each real-world element digital twin provides a digital twin of a respective real-world element located within the industrial environment. The real-world element digital twin includes a mobile element digital twin. Each mobile element digital twin provides a digital twin of a respective mobile element within the real-world element. The one or more processors are configured, for each mobile element, to estimate a location of the mobile element in response to an occurrence of a trigger condition, and to update the mobile element digital twin corresponding to the mobile element to reflect the location of the mobile element in response to estimating the location of the mobile element.

In an embodiment, the mobile element is a worker in an industrial environment.

In an embodiment, the mobile element is a vehicle in an industrial environment.

In one embodiment, the trigger condition is the expiration of a dynamically determined time interval.

In an embodiment, the dynamically determined time interval is increased in response to determining a single mobile element in the industrial environment.

In an embodiment, the dynamically determined time interval is increased in response to determining the occurrence of a predetermined period of reduced environmental activity.

In an embodiment, the dynamically determined time interval is decreased in response to determining anomalous activity within the industrial environment.

In an embodiment, the dynamically determined time interval is a first time interval, and the dynamically determined time interval is reduced to a second time interval in response to determining movement of the mobile element.

In an embodiment, the dynamically determined time interval is increased from the second time interval to the first time interval in response to determining non-movement of the mobile element for at least a third time interval.

In an embodiment, the trigger condition is the expiration of a time interval. The time interval is calculated based on the probability that the mobile element has moved.

In an embodiment, the trigger condition is the proximity of one mobile element to another.

In an embodiment, the trigger condition is based on the density of moving elements in the industrial environment.

In an embodiment, the route information is obtained from the navigation module of the mobile element.

In an embodiment, the one or more processors are further configured to obtain route information including detecting movement of the mobile element using a plurality of sensors in the industrial environment, obtaining a destination for the mobile element, calculating an optimized route for the mobile element using a plurality of sensors in the industrial environment, and instructing the mobile element to navigate the optimized route.

In an embodiment, the optimized route includes using route information of other mobile elements within the real-world element.

In embodiments, the optimized route minimizes interactions between mobile elements and humans in industrial environments.

In an embodiment, the mobile elements include autonomous and non-autonomous vehicles, and the optimized route reduces interaction between the autonomous and non-autonomous vehicles.

In an embodiment, traffic modeling includes the use of a particle traffic model, a trigger-response mobile element following traffic model, a macroscopic traffic model, a microscopic traffic model, a mesoscopic traffic model, or a combination thereof.

According to aspects of the present disclosure, a system for representing design specification information includes a digital twin data store and one or more processors. The digital twin data store stores an industrial environment digital twin that includes real-world element digital twins embedded therein. The industrial environment digital twin corresponds to an industrial environment. Each real-world element digital twin provides a digital twin of a respective real-world element located within the industrial environment. The one or more processors are configured to: determine, for each real-world element, a real-world element design specification; associate the design specification with the real-world element digital twin; and display the design specification to a user in response to the user interacting with the real-world element digital twin.

In an embodiment, a user's interaction with a real-world element digital twin includes the user selecting the real-world element digital twin.

In an embodiment, a user's interaction with a real-world element digital twin includes the user pointing an image capture device at the real-world element digital twin.

In an embodiment, the image capture device is a wearable device.

In an embodiment, the real-world element digital twin is an industrial environment digital twin.

In an embodiment, the design specifications are stored in a digital twin data store in response to user input.

In an embodiment, the design specifications are determined using a digital twin simulation system.

In an embodiment, the one or more processors are further configured to: detect, for each of the real-world elements, one or more synchronous operating parameters using sensors in the industrial environment; compare the one or more synchronous operating parameters to a design specification; and, in response to a discrepancy between the one or more synchronous operating parameters and the design specification, automatically display the design specification, the one or more synchronous operating parameters, or a combination thereof. The one or more synchronous operating parameters correspond to the design specification of the real-world element.

In an embodiment, the display of the design specifications includes indicators of synchronous operating parameters.

In an embodiment, the display of the design specifications includes a source indicator for the specification information.

In an embodiment, the source indicator notifies the user that the design specifications were determined through the use of a digital twin simulation system.

A more complete understanding of the present disclosure will be appreciated from the following description and accompanying drawings, as well as the claims.

In an embodiment, one or more dynamic models are identified using a lookup table.

According to some embodiments of the present disclosure, a method for updating one or more fluid dynamics-related values of one or more digital twins is disclosed. The method includes: receiving a request from a client application to update one or more fluid dynamics-related values of one or more digital twins; retrieving one or more digital twins necessary to satisfy the request; retrieving one or more dynamic models necessary to satisfy the request; selecting a data source from a set of available data sources based on one or more inputs of the one or more dynamic models; retrieving data from the selected data source; using the retrieved data as one or more inputs to the one or more dynamic models to calculate one or more outputs; and updating one or more values related to the fluid dynamics-related values of the one or more digital twins based on the outputs of the one or more dynamic models.

In an embodiment, the request is received from a client application corresponding to the industrial environment and/or one or more industrial entities within the industrial environment.

In an embodiment, the request is received from a client application supporting an Industrial Internet of Things sensor system.

In an embodiment, the digital twin is a digital twin of an industrial entity.

In an embodiment, the digital twin is a digital twin of an industrial environment.

In an embodiment, the dynamic model takes data selected from the set consisting of temperature, pressure, humidity, wind, rainfall, tide, storm surge, cloud cover, snowfall, visibility, radiation, audio, video, image, water level, quantum, flow rate, signal power, signal frequency, motion, speed, acceleration, light level, analyte concentration, biological compound concentration, metal concentration, and organic compound concentration data.

In an embodiment, the data source is a device connected to the Internet of Things.

In one embodiment, the data source is a machine vision system.

In an embodiment, the fluid dynamics-related value is a fluid flow rate value.

In an embodiment, obtaining the one or more dynamic models includes identifying the one or more dynamic models based on one or more properties indicated in the request and the respective types of the one or more digital twins.

In an embodiment, one or more dynamic models are identified using a lookup table.

According to some embodiments of the present disclosure, a method for updating one or more radiation values of one or more digital twins is disclosed. The method includes: receiving a request from a client application to update one or more radiation values of one or more digital twins; retrieving one or more digital twins necessary to fulfill the request; retrieving one or more dynamic models necessary to fulfill the request; selecting a data source from a set of available data sources based on one or more inputs of the one or more dynamic models; retrieving data from the selected data source; using the retrieved data as one or more inputs to the one or more dynamic models to calculate one or more outputs; and updating one or more values related to radiation doses of the one or more digital twins based on the outputs of the one or more dynamic models.

In an embodiment, the request is received from a client application corresponding to the industrial environment and/or one or more industrial entities within the industrial environment.

In an embodiment, the request is received from a client application supporting an Industrial Internet of Things sensor system.

In an embodiment, the digital twin is a digital twin of an industrial entity.

In an embodiment, the digital twin is a digital twin of an industrial environment.

In an embodiment, the dynamic model obtains data selected from the set consisting of temperature, pressure, humidity, wind, rainfall, tide, storm surge, cloud cover, snowfall, visibility, radiation, audio, video, imagery, water level, quantum, flow rate, signal power, signal frequency, motion, speed, acceleration, light level, analyte concentration, biological compound concentration, metal concentration, and organic compound concentration data.

In an embodiment, the data source is a device connected to the Internet of Things.

In one embodiment, the data source is a machine vision system.

In an embodiment, the radiation value is a gamma dose rate value.

In an embodiment, obtaining the one or more dynamic models includes identifying the one or more dynamic models based on one or more properties indicated in the request and the respective types of the one or more digital twins.

In an embodiment, one or more dynamic models are identified using a lookup table.

According to some embodiments of the present disclosure, a method for updating one or more quantum mechanical values of one or more digital twins is disclosed. The method includes: receiving a request from a client application to update one or more quantum mechanical values of one or more digital twins; retrieving one or more digital twins necessary to fulfill the request; retrieving one or more dynamic models necessary to fulfill the request; selecting a data source from a set of available data sources based on one or more inputs of the one or more dynamic models; retrieving data from the selected data source; using the retrieved data as one or more inputs to the one or more dynamic models to calculate one or more outputs; and updating one or more values related to the quantum mechanical values of the one or more digital twins based on the outputs of the one or more dynamic models.

In an embodiment, the request is received from a client application corresponding to the industrial environment and/or one or more industrial entities within the industrial environment.

In an embodiment, the request is received from a client application supporting an Industrial Internet of Things sensor system.

In an embodiment, the digital twin is a digital twin of an industrial entity.

In an embodiment, the digital twin is a digital twin of an industrial environment.

In an embodiment, the dynamic model incorporates data selected from the set consisting of temperature, pressure, humidity, wind, rainfall, tide, storm surge, cloud cover, snowfall, visibility, radiation, audio, video, imagery, water level, quantum, flow rate, signal power, signal frequency, motion, speed, acceleration, light level, analyte concentration, biological compound concentration, metal concentration, and organic compound concentration data.

In an embodiment, the data source is a device connected to the Internet of Things.

In one embodiment, the data source is a machine vision system.

In an embodiment, obtaining the one or more dynamic models includes identifying the one or more dynamic models based on one or more properties indicated in the request and the respective types of the one or more digital twins.

In an embodiment, one or more dynamic models are identified using a lookup table.

According to some embodiments of the present disclosure, a method for updating one or more location values of one or more digital twins is disclosed. The method includes: receiving a request from a client application to update one or more location values of one or more digital twins; retrieving one or more digital twins necessary to fulfill the request; retrieving one or more dynamic models necessary to fulfill the request; selecting a data source from a set of available data sources based on one or more inputs of the one or more dynamic models; retrieving data from the selected data source; using the retrieved data as one or more inputs to the one or more dynamic models to calculate one or more outputs; and updating one or more values related to the location values of the one or more digital twins based on the outputs of the one or more dynamic models.

In an embodiment, the request is received from a client application corresponding to the industrial environment and/or one or more industrial entities within the industrial environment.

In an embodiment, the request is received from a client application supporting an Industrial Internet of Things sensor system.

In an embodiment, the digital twin is a digital twin of an industrial entity.

In an embodiment, the digital twin is a digital twin of an industrial environment.

In an embodiment, the dynamic model incorporates data selected from the set consisting of temperature, pressure, humidity, wind, rainfall, tide, storm surge, cloud cover, snowfall, visibility, radiation, audio, video, imagery, water level, quantum, flow rate, signal power, signal frequency, motion, speed, acceleration, light level, analyte concentration, biological compound concentration, metal concentration, and organic compound concentration data.

In an embodiment, the data source is a device connected to the Internet of Things.

In one embodiment, the data source is a machine vision system.

In an embodiment, obtaining the one or more dynamic models includes identifying the one or more dynamic models based on one or more properties indicated in the request and the respective types of the one or more digital twins.

In an embodiment, one or more dynamic models are identified using a lookup table.

According to some embodiments of the present disclosure, a method for updating one or more metal concentration values of one or more digital twins is disclosed. The method includes:

Receiving a request from a client application to update one or more metal concentration values of one or more digital twins; retrieving one or more digital twins necessary to fulfill the request; retrieving one or more dynamic models necessary to fulfill the request; selecting a data source from a set of available data sources based on one or more inputs of the one or more dynamic models; retrieving data from the selected data source; using the retrieved data as one or more inputs to the one or more dynamic models to calculate one or more outputs; and updating one or more values related to the metal concentration values of the one or more digital twins based on the outputs of the one or more dynamic models.

In an embodiment, the request is received from a client application corresponding to the industrial environment and/or one or more industrial entities within the industrial environment.

In an embodiment, the request is received from a client application supporting an Industrial Internet of Things sensor system.

In an embodiment, the digital twin is a digital twin of an industrial entity.

In an embodiment, the digital twin is a digital twin of an industrial environment.

In an embodiment, the dynamic model takes data selected from the set consisting of temperature, pressure, humidity, wind, rainfall, tide, storm surge, cloud cover, snowfall, visibility, radiation, audio, video, image, water level, quantum, flow rate, signal power, signal frequency, motion, speed, acceleration, light level, analyte concentration, biological compound concentration, metal concentration, and organic compound concentration data.

In an embodiment, the data source is a device connected to the Internet of Things.

In one embodiment, the data source is a machine vision system.

In an embodiment, the metal is selected from the set of copper, chromium, nickel, and zinc.

In an embodiment, obtaining the one or more dynamic models includes identifying the one or more dynamic models based on one or more properties indicated in the request and the respective types of the one or more digital twins.

In an embodiment, one or more dynamic models are identified using a lookup table.

According to some embodiments of the present disclosure, a method for updating one or more organic compound concentration values of one or more digital twins is disclosed. The method includes: receiving a request from a client application to update one or more organic compound concentration values of one or more digital twins; retrieving one or more digital twins necessary to fulfill the request; retrieving one or more dynamic models necessary to fulfill the request; selecting a data source from a set of available data sources based on one or more inputs of the one or more dynamic models; retrieving data from the selected data source; using the retrieved data as one or more inputs of the one or more dynamic models to calculate one or more outputs; and updating one or more values related to the organic compound concentration values of the one or more digital twins based on the outputs of the one or more dynamic models.

In an embodiment, the request is received from a client application corresponding to the industrial environment and/or one or more industrial entities within the industrial environment.

In an embodiment, the request is received from a client application supporting an Industrial Internet of Things sensor system.

In an embodiment, the digital twin is a digital twin of an industrial entity.

In an embodiment, the digital twin is a digital twin of an industrial environment.

In an embodiment, the dynamic model incorporates data selected from the set consisting of temperature, pressure, humidity, wind, rainfall, tide, storm surge, cloud cover, snowfall, visibility, radiation, audio, video, imagery, water level, quantum, flow rate, signal power, signal frequency, motion, speed, acceleration, light level, analyte concentration, biological compound concentration, metal concentration, and organic compound concentration data.

In an embodiment, the data source is a device connected to the Internet of Things.

In one embodiment, the data source is a machine vision system.

In an embodiment, obtaining the one or more dynamic models includes identifying the one or more dynamic models based on one or more properties indicated in the request and the respective types of the one or more digital twins.

In an embodiment, one or more dynamic models are identified using a lookup table.

According to some embodiments of the present disclosure, a method for updating one or more biological compound concentration values of one or more digital twins is disclosed. The method includes: receiving a request from a client application to update one or more biological compound concentration values of one or more digital twins; retrieving one or more digital twins necessary to fulfill the request; retrieving one or more dynamic models necessary to fulfill the request; selecting a data source from a set of available data sources based on one or more inputs of the one or more dynamic models; retrieving data from the selected data source; using the retrieved data as one or more inputs to the one or more dynamic models to calculate one or more outputs; and updating one or more values related to the biological compound concentration values of the one or more digital twins based on the outputs of the one or more dynamic models.

In an embodiment, the request is received from a client application corresponding to the industrial environment and/or one or more industrial entities within the industrial environment.

In an embodiment, the request is received from a client application supporting an Industrial Internet of Things sensor system.

In an embodiment, the digital twin is a digital twin of an industrial entity.

In an embodiment, the digital twin is a digital twin of an industrial environment.

In an embodiment, the dynamic model acquires data selected from the set consisting of temperature, pressure, humidity, wind, rainfall, tide, storm surge, cloud cover, snowfall, visibility, radiation, audio, video, imagery, water level, quantum, flow rate, signal power, signal frequency, motion, speed, acceleration, light level, analyte concentration, biological compound concentration, metal concentration, and organic compound concentration data.

In an embodiment, the data source is an Internet of Things connected device.

In one embodiment, the data source is a machine vision system.

In an embodiment, obtaining the one or more dynamic models includes identifying the one or more dynamic models based on one or more properties indicated in the request and the respective types of the one or more digital twins.

In some embodiments, the method further includes receiving user input related to one or more steps performed in an industrial process associated with the industrial environment, and generating a process digital twin that defines the steps of the industrial process with respect to the industrial environment and one or more of the set of industrial entities.

According to an aspect of the present disclosure, a system for representing a power outage includes a digital twin data store and one or more processors. The digital twin data store stores an industrial environment digital twin with real-world element digital twins embedded therein. The industrial environment digital twin provides a digital twin of the industrial environment. Each real-world element digital twin provides a digital twin of a corresponding real-world element in the industrial environment. The real-world elements include a set of electrically powered elements. The one or more processors are configured to monitor a power supply for the set of electrically powered elements, determine whether the power supply meets criteria for identifying a power loss condition, and, for each of the set of electrically powered elements, represent the effect of the power loss condition on the electrically powered elements using a corresponding digital twin.

In an embodiment, the one or more processors are further configured to simulate the effect of a power loss condition on each of the real-world elements via the digital twin simulation system and store the effect of the power loss condition via the digital twin data store.

In an embodiment, the one or more processors are further configured to automatically perform a mitigating action in response to determining that the supplied power meets the criteria for identifying a power loss condition.

In an embodiment, the mitigation action includes selecting a first portion of the real-world element and a second portion of the real-world element, stopping power consumption for the first portion of the real-world element, and continuing power consumption for the second portion of the real-world element.

In an embodiment, continuing to consume power for the second portion of the real-world elements includes reducing the power consumed by each real-world element to a sub-optimal operating level.

In an embodiment, the non-optimal operating level is the minimum power level required to operate each real-world element.

In an embodiment, the mitigation action further includes powering a second portion of the real-world elements from stored power, the stored power being present in the industrial environment prior to the occurrence of the power loss condition.

In an embodiment, the stored power is provided by a battery within the environment.

In an embodiment, the real-world elements include a third portion of real-world elements, each real-world element within the third portion of real-world elements including a respective battery disposed therein, each battery configured to provide power to the respective real-world element in response to the occurrence of a power loss condition, and the one or more processors further configured to power the second portion of real-world elements using the battery of the third portion of real-world elements.

In an embodiment, the mitigation action is determined by: simulating the effect of a power loss condition on an industrial environment by simulating the effect of the power loss condition on each of the real-world element digital twins using a digital twin simulation system; determining a plurality of potential actions using a cognitive intelligence system; evaluating the effect of each of the plurality of potential actions on the industrial environment using the cognitive intelligence system and the digital twin simulation system; and selecting a mitigation action from the plurality of potential actions based on minimizing a cost function using the cognitive intelligence system. The plurality of potential actions include maintaining power, reducing power, and shutting down power to each real-world element.

In an embodiment, minimizing the cost function includes maximizing output from the industrial environment to a downstream process.

In an embodiment, minimizing the cost function includes minimizing maintenance of real-world elements caused by power loss conditions.

In an embodiment, minimizing the cost function includes minimizing the time period for achieving steady-state operation after the termination of a power loss condition.

In an embodiment, the one or more processors are further configured to maintain stored power in the backup power system at a sub-capacity level, calculate a probability of a power loss condition occurring before a predetermined period of time has elapsed, and, in response to the probability of a power loss condition occurring exceeding a predetermined threshold, increase stored power in the backup power system to the full capacity of the backup power system.

In one embodiment, the predetermined period is the period until the backup power system reaches full capacity.

In an embodiment, calculating the probability of a power loss condition occurring includes using weather forecast data.

According to an aspect of the present disclosure, a system for representing a loss of data connectivity includes a digital twin data store and one or more processors. The digital twin data store stores an industrial environment digital twin with real-world element digital twins embedded therein. The industrial environment digital twin provides a digital twin of the industrial environment. Each real-world element digital twin provides a digital twin of a corresponding real-world element in the industrial environment, the real-world element including a plurality of sensors in data communication with connected devices outside the industrial environment. The one or more processors are configured to monitor connectivity between the real-world elements and the connected devices, determine whether the monitored connectivity meets network connectivity status identification criteria, and represent an impact of the network connectivity status on each real-world element digital twin.

In an embodiment, the one or more processors are further configured to simulate the effect of the network connectivity conditions on each of the real-world elements via the digital twin simulation system and store the effect of the network connectivity conditions via the digital twin data store.

In an embodiment, the one or more processors are further configured to automatically perform mitigating actions in response to determining the occurrence of a network connectivity condition.

In an embodiment, the mitigation actions include determining that the network connection state is bandwidth-limited, selecting a first portion of sensors and a second portion of sensors, reducing network communication to the first portion of sensors, and continuing network communication to the second portion of sensors.

In an embodiment, reducing network communications for the first portion of the sensors includes increasing the time interval between communications from the first portion of the sensors.

In an embodiment, reducing network communication for the first portion of the sensor includes reducing the amount of information transmitted from the first portion of the sensor.

In an embodiment, reducing network communication of the first portion of the sensors includes edge processing data collected by the first portion of the sensors, thereby generating edge-processed data, and transmitting the edge-processed data to the connected device.

In an embodiment, the mitigation operations include selecting a first portion of real-world elements and a second portion of real-world elements, establishing a direct connection between the first portion of real-world elements and a device external to the industrial environment, and transmitting data from the second portion of real-world elements to the connected device via the direct connection. Each real-world element in the first portion of real-world elements includes a wireless communication module and is configured to directly connect to the device external to the industrial environment and transmit data originating from the respective real-world element via the direct connection.

In an embodiment, the mitigation action further includes inhibiting the transfer of data originating from each real-world element via each direct connection.

In an embodiment, the mitigation action is determined by: simulating the impact of network connectivity conditions on the industrial environment by simulating the impact of network connectivity conditions on reporting and control from each of the real-world element digital twins using a digital twin simulation system; determining a plurality of potential actions using a cognitive intelligence system; evaluating the impact of each of the plurality of potential actions on the industrial environment using the cognitive intelligence system and the digital twin simulation system; and selecting a mitigation action from the plurality of potential actions based on minimizing a cost function using the cognitive intelligence system. The plurality of potential actions includes reducing communication with each real-world element and establishing an alternative communication mode.

In an embodiment, minimizing the cost function includes minimizing the impact on downstream processes from the industrial environment.

In an embodiment, minimizing the cost function includes minimizing the time period for achieving steady-state operation after a network connectivity outage.

According to aspects of the present disclosure, a system for representing power source characteristics includes a digital twin data store and one or more processors. The digital twin data store includes an industrial environment digital twin providing a digital twin of an industrial environment. The industrial environment digital twin includes power source digital twins representing power sources that provide electrical energy to the industrial environment. The industrial environment digital twin further includes real-world element digital twins embedded therein. Each real-world element digital twin corresponds to a respective real-world element located within the industrial environment. The one or more processors are configured to determine contemporaneous characteristics of the power source in response to an occurrence of a trigger condition, and to update the power source digital twin to represent the contemporaneous characteristics in response to determining the contemporaneous characteristics of the power source.

In an embodiment, the contemporaneous characteristics of the power source include the power factor supplied to the industrial environment.

In an embodiment, the contemporaneous characteristics of the power source include power quality.

In an embodiment, the contemporaneous characteristics of the power source include utility frequency.

In an embodiment, the one or more processors are further configured to: simulate one or more operating parameters of the real-world elements in response to being provided with contemporaneous characteristics of the industrial environment using the real-world element digital twin via the digital twin simulation system; calculate mitigation actions to be taken by the one or more real-world elements in response to one or more operating parameters deviating from their respective design parameters via the digital twin simulation system; and actuate the mitigation actions in response to detecting contemporaneous characteristics of the power source.

In an embodiment, simulations and calculations are performed before determining contemporaneous characteristics.

In an embodiment, the mitigation action includes activating one of an inductive circuit or a capacitive circuit operably coupled between the power source and the real-world element.

In an embodiment, the mitigation action includes activating a second power source to provide power to one or more of the real-world elements. The second power source is located within the industrial environment.

In one embodiment, the second power source is a backup power source integrated with another real-world element.

Further areas of applicability of the present disclosure will become apparent from the detailed description provided hereinafter. It should be understood that the detailed description and specific examples are for purposes of illustration only and are not intended to limit the scope of the present disclosure.

1-5 each illustrate a portion of an overall view of an Industrial Internet of Things (IoT) data collection, monitoring and control system according to the present disclosure. 1-5 each illustrate a portion of an overall view of an Industrial Internet of Things (IoT) data collection, monitoring and control system according to the present disclosure. 1-5 each illustrate a portion of an overall view of an Industrial Internet of Things (IoT) data collection, monitoring and control system according to the present disclosure. 1-5 each illustrate a portion of an overall view of an Industrial Internet of Things (IoT) data collection, monitoring and control system according to the present disclosure. 1-5 each illustrate a portion of an overall view of an Industrial Internet of Things (IoT) data collection, monitoring and control system according to the present disclosure.

FIG. 6 is a diagram of a platform including a local data collection system deployed within an industrial environment to collect data from or regarding elements of the environment, such as machines, components, systems, subsystems, ambient conditions, states, workflows, processes, and other elements, in accordance with the present disclosure.

FIG. 7 is a diagram illustrating elements of an industrial data collection system for collecting analog sensor data in an industrial environment according to the present disclosure.

FIG. 8 is a diagram of a rotating or vibrating machine having a data acquisition module configured to acquire waveform data in accordance with the present disclosure.

FIG. 9 is a diagram of an exemplary three-axis sensor mounted on a motor bearing of an exemplary rotating machine according to the present disclosure.

FIG. 10 is a diagram of components and interactions of a data collection architecture including the application of cognitive and machine learning systems to data collection and processing according to the present disclosure.

FIG. 11 is a diagram of components and interactions of a data collection architecture including applications of a platform with a cognitive data marketplace according to the present disclosure.

FIG. 12 is a diagram of components and interactions of a data collection architecture including the application of a self-organizing swarm of data collectors in accordance with the present disclosure.

FIG. 13 is a diagram of components and interactions of a data collection architecture involving the application of a haptic user interface according to the present disclosure.

FIG. 14 is a diagram illustrating a multi-format streaming data collection system according to the present disclosure.

FIG. 15 is a diagram illustrating combined legacy and streaming data collection and storage according to the present disclosure.

FIG. 16 is an illustration of industrial machine sensing using both legacy sensor data processing and updated stream sensor data processing in accordance with the present disclosure.

FIG. 17 is a diagram of an industrial machine sensing data processing system that facilitates portal algorithm use and alignment of legacy and streaming sensor data in accordance with the present disclosure.

FIG. 18 is a diagram of components and interactions of a data collection architecture including streaming data acquisition equipment receiving analog sensor signals from an industrial environment connected to a cloud network facility in accordance with the present disclosure.

FIG. 19 is a diagram of components and interactions of a data collection architecture including an alarm module, an expert analysis module, and a streaming data acquisition appliance with a driver API that facilitates communication with cloud network facilities in accordance with the present disclosure.

FIG. 20 is a diagram of the components and interactions of a data collection architecture including streaming data acquisition equipment and a first-in, first-out memory architecture to provide a real-time operating system in accordance with the present disclosure.

FIG. 21 is a diagram of the components and interactions of a data collection architecture including multiple streaming data acquisition devices that receive analog sensor signals and digitize them to be acquired by a streaming hub server in accordance with the present disclosure.

FIG. 22 is a diagram of the components and interactions of a data collection architecture including a master raw data server that processes new streaming data and data that has already been extracted and processed according to the present disclosure.

23, 24, and 25 are diagrammatic representations of the components and interactions of a data collection architecture including processing, analysis, reporting, and archiving servers that handle new streaming data and already extracted and processed data in accordance with the present disclosure. 23, 24, and 25 are diagrammatic representations of the components and interactions of a data collection architecture including processing, analysis, reporting, and archiving servers that handle new streaming data and already extracted and processed data in accordance with the present disclosure. 23, 24, and 25 are diagrammatic representations of the components and interactions of a data collection architecture including processing, analysis, reporting, and archiving servers that handle new streaming data and already extracted and processed data in accordance with the present disclosure.

FIG. 26 is a diagram of components and interactions of a data collection architecture including a relational database server, a data archive, and connectivity with cloud network facilities in accordance with the present disclosure.

27-32 are diagrams of components and interactions of a data collection architecture including a virtual streaming data acquisition appliance receiving analog sensor signals from an industrial environment connected to a cloud network facility in accordance with the present disclosure. 27-32 are diagrams of components and interactions of a data collection architecture including a virtual streaming data acquisition appliance receiving analog sensor signals from an industrial environment connected to a cloud network facility in accordance with the present disclosure. 27-32 are diagrams of components and interactions of a data collection architecture including a virtual streaming data acquisition appliance receiving analog sensor signals from an industrial environment connected to a cloud network facility in accordance with the present disclosure. 27-32 are diagrams of components and interactions of a data collection architecture including a virtual streaming data acquisition appliance receiving analog sensor signals from an industrial environment connected to a cloud network facility in accordance with the present disclosure. 27-32 are diagrams of components and interactions of a data collection architecture including a virtual streaming data acquisition appliance receiving analog sensor signals from an industrial environment connected to a cloud network facility in accordance with the present disclosure. 27-32 are diagrams of components and interactions of a data collection architecture including a virtual streaming data acquisition appliance receiving analog sensor signals from an industrial environment connected to a cloud network facility in accordance with the present disclosure.

33-40 are diagrams of components and interactions of a data collection architecture including a data channel method and system for industrial machine data collection according to the present disclosure. 33-40 are diagrams of components and interactions of a data collection architecture including a data channel method and system for industrial machine data collection according to the present disclosure. 33-40 are diagrams of components and interactions of a data collection architecture including a data channel method and system for industrial machine data collection according to the present disclosure. 33-40 are diagrams of components and interactions of a data collection architecture including a data channel method and system for industrial machine data collection according to the present disclosure. 33-40 are diagrams of components and interactions of a data collection architecture including a data channel method and system for industrial machine data collection according to the present disclosure. 33-40 are diagrams of components and interactions of a data collection architecture including a data channel method and system for industrial machine data collection according to the present disclosure. 33-40 are diagrams of components and interactions of a data collection architecture including a data channel method and system for industrial machine data collection according to the present disclosure. 33-40 are diagrams of components and interactions of a data collection architecture including a data channel method and system for industrial machine data collection according to the present disclosure.

FIG. 41 illustrates an embodiment of a data monitoring device according to the present disclosure.

42 and 43 are diagrams illustrating an embodiment of a data monitoring device according to the present disclosure. 42 and 43 are diagrams illustrating an embodiment of a data monitoring device according to the present disclosure.

FIG. 44 illustrates an embodiment of a data monitoring device according to the present disclosure.

45 and 46 are diagrams illustrating one embodiment of a system for data collection according to the present disclosure. 45 and 46 are diagrams illustrating one embodiment of a system for data collection according to the present disclosure.

47 and 48 are diagrams illustrating one embodiment of a system for collecting data comprising multiple data monitoring devices according to the present disclosure. 47 and 48 are diagrams illustrating one embodiment of a system for collecting data comprising multiple data monitoring devices according to the present disclosure.

FIG. 49 illustrates one embodiment of a data monitoring device incorporating sensors according to the present disclosure.

50 and 51 illustrate embodiments of a data monitoring device in communication with an external sensor according to the present disclosure. 50 and 51 illustrate embodiments of a data monitoring device in communication with an external sensor according to the present disclosure.

FIG. 52 illustrates an embodiment of a data monitoring device that adds further details to the signal evaluation circuitry according to the present disclosure.

FIG. 53 illustrates an embodiment of a data monitoring device that adds further details to the signal evaluation circuitry according to the present disclosure.

FIG. 54 illustrates an embodiment of a data monitoring device that adds further details to the signal evaluation circuitry according to the present disclosure.

FIG. 55 illustrates an embodiment of a system for data collection according to the present disclosure.

FIG. 56 illustrates an embodiment of a system for data collection including multiple data monitoring devices according to the present disclosure.

FIG. 57 illustrates an embodiment of a data monitoring device according to the present disclosure.

58 and 59 are diagrams illustrating an embodiment of a data monitoring device according to the present disclosure. 58 and 59 are diagrams illustrating an embodiment of a data monitoring device according to the present disclosure.

60 and 61 are diagrams illustrating an embodiment of a data monitoring device according to the present disclosure. 60 and 61 are diagrams illustrating an embodiment of a data monitoring device according to the present disclosure.

62 and 63 are diagrams illustrating an embodiment of a data monitoring device according to the present disclosure. 62 and 63 are diagrams illustrating an embodiment of a data monitoring device according to the present disclosure.

64 and 65 are diagrams illustrating embodiments of a system for data collection including multiple data monitoring devices according to the present disclosure. 64 and 65 are diagrams illustrating embodiments of a system for data collection including multiple data monitoring devices according to the present disclosure.

FIG. 66 illustrates an embodiment of a data monitoring device according to the present disclosure.

67 and 68 illustrate embodiments of data monitoring devices according to the present disclosure. 67 and 68 illustrate embodiments of data monitoring devices according to the present disclosure.

FIG. 69 illustrates an embodiment of a data monitoring device according to the present disclosure.

FIG. 70 illustrates an embodiment of a data monitoring device according to the present disclosure.

71 and 72 are diagrams illustrating an embodiment of a system for data collection according to the present disclosure. 71 and 72 are diagrams illustrating an embodiment of a system for data collection according to the present disclosure.

73 and 74 illustrate an embodiment of a system for data collection including multiple data monitoring devices according to the present disclosure. 73 and 74 illustrate an embodiment of a system for data collection including multiple data monitoring devices according to the present disclosure.

FIG. 75 illustrates an embodiment of a data monitoring device according to the present disclosure.

76 and 77 are diagrams illustrating an embodiment of a data monitoring device according to the present disclosure. 76 and 77 are diagrams illustrating an embodiment of a data monitoring device according to the present disclosure.

FIG. 78 illustrates an embodiment of a data monitoring device according to the present disclosure.

79 and 80 illustrate an embodiment of a system for data collection according to the present disclosure. 79 and 80 illustrate an embodiment of a system for data collection according to the present disclosure.

81 and 82 are diagrams illustrating an embodiment of a system for data collection including multiple data monitoring devices according to the present disclosure. 81 and 82 are diagrams illustrating an embodiment of a system for data collection including multiple data monitoring devices according to the present disclosure.

FIG. 83 illustrates an embodiment of a data monitoring device according to the present disclosure.

84 and 85 illustrate embodiments of data monitoring devices according to the present disclosure. 84 and 85 illustrate embodiments of data monitoring devices according to the present disclosure.

FIG. 86 illustrates an embodiment of a data monitoring device according to the present disclosure.

87 and 88 illustrate an embodiment of a system for data collection according to the present disclosure. 87 and 88 illustrate an embodiment of a system for data collection according to the present disclosure.

89 and 90 illustrate embodiments of a system for data collection including multiple data monitoring devices according to the present disclosure. 89 and 90 illustrate embodiments of a system for data collection including multiple data monitoring devices according to the present disclosure.

FIG. 91 illustrates an embodiment of a data monitoring device according to the present disclosure.

92 and 93 illustrate embodiments of a data monitoring device according to the present disclosure. 92 and 93 illustrate embodiments of a data monitoring device according to the present disclosure.

FIG. 94 illustrates an embodiment of a data monitoring device according to the present disclosure.

95 and 96 illustrate an embodiment of a system for data collection according to the present disclosure. 95 and 96 illustrate an embodiment of a system for data collection according to the present disclosure.

97 and 98 illustrate embodiments of a system for data collection including multiple data monitoring devices according to the present disclosure. 97 and 98 illustrate embodiments of a system for data collection including multiple data monitoring devices according to the present disclosure.

99-101 are diagrammatic illustrations of components and interactions of a data collection architecture including a collector of route templates and routing data collectors in an industrial environment in accordance with the present disclosure. 99-101 are diagrammatic illustrations of components and interactions of a data collection architecture including a collector of route templates and routing data collectors in an industrial environment in accordance with the present disclosure. 99-101 are diagrammatic illustrations of components and interactions of a data collection architecture including a collector of route templates and routing data collectors in an industrial environment in accordance with the present disclosure.

FIG. 102 is a diagram illustrating a monitoring system employing a data collection band according to the present disclosure.

FIG. 103 illustrates a system for using vibrations and other noises in predicting conditions and outcomes according to the present disclosure.

FIG. 104 is a diagram illustrating a system for data collection in an industrial environment according to the present disclosure.

FIG. 105 is a diagram illustrating an apparatus for data collection in an industrial environment according to the present disclosure.

FIG. 106 is a schematic flow diagram illustrating a procedure for data collection in an industrial environment according to the present disclosure.

FIG. 107 is a diagram illustrating a system for data collection in an industrial environment according to the present disclosure.

FIG. 108 illustrates an apparatus for data collection in an industrial environment according to the present disclosure.

FIG. 109 is a schematic flow diagram illustrating a procedure for data collection in an industrial environment according to the present disclosure.

FIG. 110 illustrates industry-specific feedback in an industrial environment according to the present disclosure.

FIG. 111 is a diagram depicting an example user interface for smart band configuration of a system for data collection in an industrial environment in accordance with the present disclosure.

FIG. 112 illustrates a graphical approach 11300 for inverse calculations according to the present disclosure.

FIG. 113 illustrates a wearable tactile user interface device for providing a user with tactile stimuli responsive to data collected in an industrial environment by a system adapted to collect data in an industrial environment in accordance with the present disclosure.

FIG. 114 illustrates an augmented reality display of a heat map based on data collected in an industrial environment by a system adapted to collect data in the environment in accordance with the present disclosure.

FIG. 115 is a diagram illustrating an augmented reality display with real-time data overlaid on a view of an industrial environment in accordance with the present disclosure.

FIG. 116 is a diagram illustrating components of a user interface display and a neural network in a graphical user interface according to the present disclosure.

FIG. 117 is a diagram of components and interactions of a data collection architecture including swarming data collectors and a sensor mesh protocol in an industrial environment according to the present disclosure.

FIG. 118 is a diagram illustrating a data collection system according to some aspects of the present disclosure.

FIG. 119 illustrates a system for self-organized network-sensitive data collection in an industrial environment according to the present disclosure.

FIG. 120 illustrates an apparatus for self-organized network-sensitive data collection in an industrial environment according to the present disclosure.

FIG. 121 illustrates an apparatus for self-organized network-sensitive data collection in an industrial environment according to the present disclosure.

FIG. 122 illustrates an apparatus for self-organized network-sensitive data collection in an industrial environment according to the present disclosure.

123 and 124 are diagrams illustrating embodiments of transmission conditions according to the present disclosure. 123 and 124 are diagrams illustrating embodiments of transmission conditions according to the present disclosure.

FIG. 125 illustrates an embodiment of a sensor data transmission protocol according to the present disclosure.

126 and 127 are diagrams illustrating embodiments of benchmarking data according to the present disclosure. 126 and 127 are diagrams illustrating embodiments of benchmarking data according to the present disclosure.

FIG. 128 illustrates an embodiment of a system for data collection and storage in an industrial environment according to the present disclosure.

FIG. 129 illustrates an embodiment of an apparatus for self-organizing storage for data collection in an industrial system according to the present disclosure.

FIG. 130 illustrates an embodiment of a storage time definition according to the present disclosure.

FIG. 131 is a diagram illustrating an embodiment of a data resolution description according to the present disclosure.

132 and 133 are diagrams of an apparatus for self-organizing network coding for data collection in an industrial system according to the present disclosure. 132 and 133 are diagrams of an apparatus for self-organizing network coding for data collection in an industrial system according to the present disclosure.

134 and 135 are diagrams of a data marketplace that interacts with data collection in an industrial system according to the present disclosure. 134 and 135 are diagrams of a data marketplace that interacts with data collection in an industrial system according to the present disclosure.

FIG. 136 is a diagram illustrating a smart heating system as an element in a network for an Industrial Internet of Things ecosystem according to the present disclosure.

FIG. 137 illustrates the architecture of an Industrial Internet of Things solution according to the present disclosure, its components, and functional relationships.

FIG. 138 is a schematic diagram illustrating an example of a sensor kit deployed in an industrial environment, according to some embodiments of the present disclosure.

FIG. 139 is a schematic diagram illustrating an example of a sensor kit network having a star network topology according to some embodiments of the present disclosure.

FIG. 140 is a schematic diagram illustrating an example of a sensor kit network having a mesh network topology, according to some embodiments of the present disclosure.

FIG. 141 is a schematic diagram illustrating an example of a sensor kit network having a hierarchical network topology, according to some embodiments of the present disclosure.

FIG. 142 is a schematic diagram illustrating an example of a sensor according to some embodiments of the present disclosure.

FIG. 143 is a schematic diagram illustrating an example schema of a reporting packet according to some embodiments of the present disclosure.

FIG. 144 is a schematic diagram illustrating an example of an edge device of a sensor kit according to some embodiments of the present disclosure.

FIG. 145 is a schematic diagram illustrating an example of a backend system receiving sensor data from sensor kits deployed in an industrial environment, according to some embodiments of the present disclosure.

FIG. 146 is a flowchart illustrating an example set of method operations for encoding sensor data captured by a sensor kit, according to some embodiments of the present disclosure.

FIG. 147 is a flowchart illustrating an example set of method operations for decoding sensor data provided by a sensor kit to a backend system according to some embodiments of the present disclosure.

FIG. 148 is a flowchart illustrating an example set of method operations for encoding sensor data captured by a sensor kit using a media codec, according to some embodiments of the present disclosure.

FIG. 149 is a flowchart illustrating an example set of operations of a method for decoding sensor data provided by a sensor kit to a backend system using a media codec, according to some embodiments of the present disclosure.

FIG. 150 is a flowchart illustrating an example set of operations for a method for determining a transmission strategy and/or a storage strategy for sensor data collected by a sensor kit based on the sensor data, according to some embodiments of the present disclosure.

151-155 are schematic diagrams illustrating different configurations of sensor kits according to some embodiments of the present disclosure. 151-155 are schematic diagrams illustrating different configurations of sensor kits according to some embodiments of the present disclosure. 151-155 are schematic diagrams illustrating different configurations of sensor kits according to some embodiments of the present disclosure. 151-155 are schematic diagrams illustrating different configurations of sensor kits according to some embodiments of the present disclosure. 151-155 are schematic diagrams illustrating different configurations of sensor kits according to some embodiments of the present disclosure.

FIG. 156 is a flowchart illustrating an example set of method operations for monitoring an industrial setting using an automatically configured backend system, according to some embodiments of the present disclosure.

FIG. 157 is a plan view of a manufacturing facility illustrating an example implementation of a sensor kit including an edge device, according to some embodiments of the present disclosure.

FIG. 158 is a plan view of a surface portion of an underwater industrial installation showing an exemplary implementation of a sensor kit including an edge device according to some embodiments of the present disclosure.

FIG. 159 is a plan view of an indoor farming facility showing an example implementation of a sensor kit including an edge device, according to some embodiments of the present disclosure.

FIG. 160 is a schematic diagram illustrating an example of a sensor kit in communication with a data processing platform, according to some embodiments of the present disclosure.

161-164 illustrate an embodiment of a system for using one or more wearable devices for mobile data collection in accordance with the present disclosure. 161-164 illustrate an embodiment of a system for using one or more wearable devices for mobile data collection in accordance with the present disclosure. 161-164 illustrate an embodiment of a system for using one or more wearable devices for mobile data collection in accordance with the present disclosure. 161-164 illustrate an embodiment of a system for using one or more wearable devices for mobile data collection in accordance with the present disclosure.

165-167 illustrate an embodiment of a system for using one or more mobile robots and/or mobile vehicles for mobile data collection according to the present disclosure. 165-167 illustrate an embodiment of a system for using one or more mobile robots and/or mobile vehicles for mobile data collection according to the present disclosure. 165-167 illustrate an embodiment of a system for using one or more mobile robots and/or mobile vehicles for mobile data collection according to the present disclosure.

168-171 illustrate embodiments of a system for using one or more handheld devices for mobile data collection according to the present disclosure. 168-171 illustrate embodiments of a system for using one or more handheld devices for mobile data collection according to the present disclosure. 168-171 illustrate embodiments of a system for using one or more handheld devices for mobile data collection according to the present disclosure. 168-171 illustrate embodiments of a system for using one or more handheld devices for mobile data collection according to the present disclosure.

172-174 illustrate embodiments of a computer vision system according to the present disclosure. 172-174 illustrate embodiments of a computer vision system according to the present disclosure. 172-174 illustrate embodiments of a computer vision system according to the present disclosure.

175-176 illustrate an embodiment of a deep learning system for training a computer vision system according to the present disclosure. 175-176 illustrate an embodiment of a deep learning system for training a computer vision system according to the present disclosure.

Figure 177 is a diagram illustrating the predictive maintenance ecosystem network architecture.

Figure 178 depicts using machine learning to find service workers for the predictive maintenance ecosystem in Figure 177.

Figure 179 shows parts and service ordering in a predictive maintenance ecosystem.

FIG. 180 is a diagram illustrating the placement of smart RFID elements in an industrial machine environment.

Figure 181 shows a generalized data structure of machine information in smart RFID.

Figure 182 is a block level diagram of the storage structure of a smart RFID.

FIG. 183 is a diagram showing an example of data stored in a smart RFID.

FIG. 184 is a flow diagram of a method for collecting information from a machine.

Figure 185 is a flow diagram of a method for collecting data from a production environment.

FIG. 186 illustrates an online maintenance management system with interfaces for data sources to update information in the online maintenance management system's data storage.

Figure 187 illustrates a distributed ledger for predictive maintenance information and its role-specific access methods.

FIG. 188 illustrates a process for capturing an image of a portion of industrial machinery.

Figure 189 shows the process of using machine learning on images to recognize what is likely to be the internal structure of industrial machinery.

FIG. 190 is a diagram showing a knowledge graph of predictive maintenance collection information.

FIG. 191 illustrates an artificial intelligence system that generates service recommendations and the like based on predictive maintenance analysis.

FIG. 192 illustrates a predictive maintenance timeline overlaid with a preventive maintenance timeline.

FIG. 193 is a block diagram of potential sources of diagnostic information.

Figure 194 is a diagram of the process for rating vendors.

FIG. 195 is a diagram of the process for rating procedures.

Figure 196 is a diagram of blockchain applied to transactions in the predictive maintenance ecosystem.

FIG. 197 shows a transfer function that facilitates converting vibration data into precise units.

FIG. 198 is a diagram showing a table that facilitates associating vibration data with severity units.

Figure 199 shows a composite frequency graph of the conventional vibration rating and the rating in severity units.

FIG. 200 shows a rendering of a portion of an industrial machine for use in an electronic user interface for depicting and locating severity units and related information regarding rotating components of the industrial machine.

FIG. 201 shows a data table of rotating component design parameters used to predict maintenance events.

FIG. 202 is a flowchart for predicting maintenance of at least one of gears, motors, and roller bearings based on severity units such as the number of gear teeth and the number of actuators.

FIG. 203 is a schematic diagram of an exemplary platform for facilitating the development of intelligence in Industrial Internet of Things (IIoT) systems, according to some aspects of the present disclosure.

FIG. 204 is a schematic diagram showing additional details, components, subsystems, and other elements of any implementation of the exemplary platform of FIG. 203.

FIG. 205 is a schematic diagram illustrating a robotic process automation (hereinafter "RPA") system of the exemplary platform of FIG. 203.

FIG. 206 is a schematic diagram illustrating the opportunity mining system and adaptive intelligence layer of the exemplary platform of FIG. 203.

FIG. 207 is a schematic diagram illustrating optional elements of the adaptive intelligent systems layer that facilitate improved edge intelligence for the exemplary platform of FIG. 203.

FIG. 208 is a schematic diagram illustrating optional elements of the industry entity-oriented data storage system layer of the exemplary platform of FIG. 203.

FIG. 209 is a schematic diagram illustrating a robotic process automation system of the exemplary platform of FIG.

FIG. 210 is a schematic diagram of an example system for data processing in an industrial environment utilizing a protocol adapter according to some aspects of the present disclosure.

FIG. 211 is another schematic diagram showing additional components and elements of the exemplary system of FIG. 210; and

FIG. 212 illustrates an example connection attempt for the example system of FIG. 210, according to some aspects of the disclosure.

FIG. 213 is a schematic diagram illustrating an example of the architecture of a digital twin system according to an embodiment of the present disclosure.

FIG. 214 is a schematic diagram illustrating exemplary components of a digital twin management system according to an embodiment of the present disclosure.

FIG. 215 is a schematic diagram illustrating an example of a digital twin I/O system interfacing with an environment, a digital twin system, and/or components thereof to provide bidirectional transfer of data between coupled components, according to an embodiment of the present disclosure.

FIG. 216 is a schematic diagram illustrating an example set of identification states for an industrial environment that a digital twin system may identify and/or store for access by an intelligent system (e.g., a cognitive intelligence system) or user of the digital twin system, according to an embodiment of the present disclosure.

FIG. 217 is a schematic diagram illustrating an exemplary embodiment of a method for updating a set of properties of a digital twin of the present disclosure on behalf of a client application and/or one or more embedded digital twins according to an embodiment of the present disclosure.

FIG. 218 is a display diagram illustrating an example embodiment of a display interface of the present disclosure rendering a digital twin of a dryer centrifuge with information related to the dryer centrifuge in accordance with an embodiment of the present disclosure.

FIG. 219 is a schematic diagram illustrating an example embodiment of a method for updating a set of vibration fault level conditions of machine components, such as bearings, in a digital twin of an industrial machine on behalf of a client application according to an embodiment of the present disclosure.

FIG. 220 is a schematic diagram illustrating an example embodiment of a method for updating a set of vibration severity unit values of a machine component, such as a bearing, in a digital twin of a machine on behalf of a client application, in accordance with an embodiment of the present disclosure.

FIG. 221 is a schematic diagram illustrating an example embodiment of a method for updating a set of failure probability values in a digital twin of a machine part on behalf of a client application, according to an embodiment of the present disclosure.

FIG. 222 is a schematic diagram illustrating an example embodiment of a method for updating a set of downtime probability values for machines in a digital twin of a manufacturing facility on behalf of a client application, in accordance with an embodiment of the present disclosure.

FIG. 223 is a schematic diagram illustrating an exemplary embodiment of a method for updating a set of shutdown probability values for manufacturing equipment in an enterprise's digital twin on behalf of a client application, according to an embodiment of the present disclosure.

FIG. 224 is a schematic diagram illustrating an exemplary embodiment of a method for updating a cost set of machine downtime values in a digital twin of a manufacturing facility, according to an embodiment of the present disclosure.

FIG. 225 is a schematic diagram illustrating an example embodiment of a method for updating one or more manufacturing KPI values in a digital twin of a manufacturing facility on behalf of a client application according to an embodiment of the present disclosure.

FIG. 226 is a display diagram illustrating a further exemplary embodiment of a display interface of the present disclosure rendering a digital twin of a dryer centrifuge with information related to its drive components, in accordance with an embodiment of the present disclosure.

FIG. 227 is a display diagram illustrating a further exemplary embodiment of a display interface of the present disclosure that provides a digital twin showing components of a vibration according to an embodiment of the present disclosure.

FIG. 228 is a display diagram illustrating a further exemplary embodiment of a display interface of the present disclosure providing selection of digital twins showing various components experiencing faults, according to an embodiment of the present disclosure.

FIG. 229 is a display diagram illustrating an example embodiment of a display interface of the present disclosure rendering a digital twin of views each incorporating a connected machine having a drive bearing according to an embodiment of the present disclosure.

FIG. 230 is a display diagram illustrating an exemplary embodiment of a display interface of the present disclosure, each rendering views incorporating a connected machine having a drive bearing exhibiting off-nominal motion in accordance with an embodiment of the present disclosure.

FIG. 231 is a display diagram illustrating an exemplary embodiment of a display interface of the present disclosure rendering a digital twin showing a drive bearing corrected to nominal motion in accordance with an embodiment of the present disclosure.

FIG. 232 is a display diagram showing an example of a display interface of the present disclosure rendering digital twins each incorporating a connected machine such as a motor and a mill having a drive bearing exhibiting off-nominal motion according to an embodiment of the present disclosure.

FIG. 233 is a display diagram illustrating an exemplary embodiment of a display interface of the present disclosure rendering a digital twin showing a drive bearing corrected to nominal motion in accordance with an embodiment of the present disclosure.

FIG. 234 is a schematic diagram illustrating an example of a portion of an information technology system for manufacturing artificial intelligence utilizing digital twins, according to some embodiments of the present disclosure.

While detailed embodiments of the present disclosure are disclosed herein, it should be understood that the disclosed embodiments are merely exemplary and may be embodied in various forms. Therefore, the specific structural and functional details disclosed herein should not be construed as limiting, but merely as a basis for the claims and as representative basis for teaching those skilled in the art how to variously employ the present disclosure in substantially any appropriately detailed structure.

The methods and systems described herein for streaming, collecting, processing, and storing industrial machine sensor data may be configured to operate with existing data collection, processing, and storage systems while maintaining access to data in existing formats, frequency ranges, and resolutions that are compatible with the existing data collection systems. While the data streaming facilities described herein for industrial machine sensors may collect large amounts of data from sensors at wider frequency ranges and higher resolutions than existing data collection systems, the methods and systems may be employed to provide access to data from streams of data representing one or more frequency ranges and/or one or more resolution lines that are intentionally compatible with the existing systems. Furthermore, portions of the streamed data may be identified, extracted, stored, and/or transferred to existing data processing systems to facilitate operation of the existing data processing systems that substantially matches the operation of existing data processing systems using the existing collection-based data. In this way, newly deployed systems for sensing aspects of industrial machinery, such as aspects of moving parts of industrial machinery, can facilitate the continued use of existing sensed data processing facilities, algorithms, models, pattern recognizers, user interfaces, and the like.

By identifying existing frequency ranges, formats, and/or resolutions, such as by accessing data structures that define these aspects of the existing data, the higher resolution stream data can be configured to represent specific frequencies, frequency ranges, formats, and/or resolutions. This configured stream data can be stored in a data structure that is compatible with the existing sensed data structure, allowing existing processing systems and equipment to access and process the data substantially as if it were existing data. One approach to adapting streamed data for compatibility with existing sensed data includes aligning the streamed data with the existing data, such that portions of the streamed data that align with the existing data are extracted, stored, and made available for processing by existing data processing methods. Alternatively, the data processing methods may be configured to process portions of the corresponding stream data, such as by aligning them with the existing data, using methods that implement substantially similar functionality to methods used to process the existing data, such as methods that process data including a specific frequency range or a specific resolution.

The method used to process existing data may be related to particular characteristics of the sensed data, such as a particular frequency range, the source of the data, etc. As an example, a method for processing bearing sensing information for moving parts of industrial machinery may be able to process data from bearing sensors that fall within a particular frequency range. The method can therefore be identified at least in part by these characteristics of the data being processed. Thus, a data processing system can select an appropriate method given a set of conditions, such as the moving equipment being sensed, the type of industrial machinery, and the frequency of the sensed data. Furthermore, given such conditions, the industrial machinery's data sensing and processing equipment can configure elements such as data filters, routers, and processors to process data that meets the conditions.

Figures 1-5 depict a portion of an overall view of an Industrial Internet of Things (IoT) data collection, monitoring, and control system 10. Figure 2 depicts a mobile ad hoc network ("MANET") 20 that may form a secure, temporary network connection 22 (sometimes connected, sometimes isolated) with a cloud 30 or other remote networking system, allowing network functions to occur on the MANET 20 within the environment without the need for an external network, while at other times transmitting information to and from a central location. This allows industrial environments to utilize the benefits of networking and control technologies while ensuring security, such as preventing cyberattacks. The MANET 20 may use cognitive radio technologies 40, including routers 42, MAC 44, and physical layer technologies 46, which form the equivalent of IP protocols. In certain embodiments, the systems depicted in Figures 1-5 provide network-sensitive or network-aware transport of data over the network to and from data collection devices or heavy industrial machinery.

Figures 3-4 depict intelligent data collection technologies deployed locally at the edge of an IoT deployment, where heavy industrial machinery is located. This includes various sensors 52, IoT devices 54, data storage capabilities (e.g., data pool 60, or distributed ledger 62) (including intelligent self-organizing storage), sensor fusion (including self-organizing sensor fusion), etc. Interfaces for data collection are shown, including multi-sensor interfaces, tablets, smartphones 58, etc. Figure 3 also illustrates a data pool 60 that can collect data exposed by machines or sensors detecting machine conditions, such as for later consumption by local or remote intelligence. The distributed ledger system 62 may distribute storage across local storage in various elements of the environment or more broadly across the system. FIG. 4 also illustrates on-device sensor fusion 80, such as for storing data from multiple analog sensors 82 on-device, which may be analyzed locally or in the cloud, such as by machine learning 84, including training a machine based on an initial model created by a human, augmented by providing feedback (e.g., based on measures of success) in operating the methods and systems disclosed herein.

Figure 1 depicts the server-based portion of an Industrial IoT system, which may be deployed in the cloud or on the premises of an enterprise owner or operator. The server portion includes network coding (including self-organizing network coding and/or auto-configuration) that can configure a network coding model based on feedback measures, network conditions, etc., to efficiently transport large amounts of data over the network to and from data collection systems and the cloud. The network coding, as depicted in Figure 1, may provide a wide range of functionality for intelligence, analytics, remote control, remote operation, remote optimization, various storage configurations, etc. The various storage configurations may include distributed ledger storage to support transaction data or other elements of the system.

Figure 5 depicts a programmatic data marketplace 70, which may be a self-organizing marketplace, such as for making available data collected in an industrial environment, including data collectors, data pools, distributed ledgers, and other elements disclosed herein. Additional details regarding the various components and subcomponents of Figures 1-5 are provided throughout this disclosure.

6, one embodiment of platform 100 may include a local data collection system 102 disposed in an environment 104, such as an industrial environment similar to that shown in FIG. 3, to collect data from or about elements of the environment, such as machines, components, systems, subsystems, ambience, conditions, workflows, processes, and other elements. Platform 100 may be connected to or include part of the industrial IoT data collection, monitoring, and control system 10 depicted in FIGS. 1-5. Platform 100 may include a network data transport system 108 for transporting data to and from local data collection system 102 over a network 110, such as to a host processing system 112 disposed in a cloud computing environment or on an enterprise premises, or comprised of distributed components that interact with each other to process data collected by local data collection system 102. The host processing system 112, sometimes referred to for convenience as the host system 112, may include various systems, components, methods, processes, equipment, etc., for enabling automated or automation-assisted processing of data, such as for monitoring one or more environments 104 or networks 110 or for remotely controlling one or more elements within the local environment 104 or network 110. The platform 100 may also include one or more local autonomous systems, such as for enabling autonomous operation based on application of a set of rules or models to input data from the local data collection system 102 or one or more input sources 116, which may comprise information feeds and inputs from a wide range of sources, including the local environment 104, the network 110, the host system 112, or one or more external systems, databases, etc. The platform 100 may also include one or more intelligent systems 118, which may be located in, integrated with, or serve as input to one or more components of the platform 100. Details of these and other components of the platform 100 are provided throughout this disclosure.

The intelligent system 118 may include a cognitive system 120 that enables some degree of cognitive operation as a result of the coordination of processing elements, such as in a mesh, peer-to-peer, ring, serial, or other architecture, where one or more node elements coordinate with other node elements to provide collective, coordinated operation to assist with processing, communication, data collection, and the like. The MANET 20 depicted in FIG. 2 may also use cognitive radio technologies, including routers 42, MAC 44, and physical layer technologies 46, which form the equivalent of IP protocols. In one example, the cognitive system technology stack may include that disclosed in U.S. Patent No. 8,060,017 to Schlicht et al., issued November 15, 2011, and incorporated by reference as if fully set forth herein.

The intelligent system may include a machine learning system 122, such as for learning from one or more datasets. The one or more datasets may include information collected using the local data collection system 102 or other information from input sources 116, such as for recognizing states, objects, events, patterns, conditions, etc., which may in turn be used for processing by the host system 112 as input to components of the platform 100 and portions of the industrial IoT data collection, monitoring, and control system 10. Learning may be human-supervised, such as using one or more input sources 116 to provide datasets with information about the items to be learned, or may be fully automated. Machine learning may use one or more models, rules, semantic understandings, workflows, or other structured or semi-structured understandings of the world, such as for automated optimization of control of a system or process based on feedback or feedforward to a model of the system or process behavior. One such machine learning technique for semantic and contextual understanding, workflow, or other structured and semi-structured understanding is disclosed in U.S. Patent No. 8,200,775, issued June 12, 2012, to Moore, and incorporated by reference as if fully set forth herein. Machine learning can be used to improve upon the foregoing, such as by adjusting one or more weights, structures, rules, etc. (e.g., changing functions within the model) based on feedback (e.g., regarding the model's success in a given situation) or iteration (e.g., in a recursive process). Machine learning can be performed without an underlying model when a sufficient understanding of the system's underlying structure or behavior is unavailable, when insufficient data is available, or in other cases that may be desirable for various reasons. That is, input sources can be weighted, structured, etc. within a machine learning facility without any a priori understanding of the structure, and results (e.g., results based on measures of success in achieving various desired objectives) can be continuously fed to the machine learning system to learn how to achieve the desired objective. For example, machine learning may involve defect recognition, pattern recognition, model or feature development, rule development, performance optimization, failure rate minimization, profit optimization, resource utilization optimization, flow optimization (e.g., traffic flow), or many other parameters associated with successful outcomes (e.g., outcomes across a wide range of environments). Machine learning may use genetic programming techniques to promote or demote one or more input sources, structures, data types, objects, weights, nodes, links, or other elements based on feedback (so that successful elements emerge over a series of generations). For example, alternative available sensor inputs for the data collection system 102 may be arranged in alternative configurations and permutations such that the system, using generic programming techniques over a series of data collection events, determines which permutations provide successful outcomes based on various conditions (e.g., conditions of the platform 100 components, conditions of the network 110, conditions of the data collection system 102, conditions of the environment 104, etc.). In embodiments, local machine learning may sequentially turn on or off one or more sensors in multi-sensor data collector 102 over time while tracking success outcomes such as contribution to successful failure prediction, contribution to a performance indicator (e.g., efficiency, effectiveness, return on investment, yield), contribution to optimization of one or more parameters, or identification of patterns (related to threats, failure modes, success modes, etc.). For example, the system may derive what set of sensors should be turned on or off under given conditions to achieve the highest value utilization of data collector 102. In embodiments, similar techniques may be used to handle optimization of data transport in platform 100 (e.g., network 110) by using general-purpose programming or other machine learning techniques to learn configurations of network elements (e.g., configurations of network transport paths, configurations of network coding types and architectures, configurations of network security elements, etc.).

In an embodiment, the local data collection system 102 may include a high-performance, multi-sensor data collector with numerous novel features for collecting and processing analog and other sensor data. In an embodiment, the local data collection system 102 may be deployed in an industrial facility such as that depicted in FIG. 3. The local data collection system 102 may also be deployed monitoring other machines, such as machine 2200. The data collection system 102 may have an on-board intelligent system 118 (e.g., learning to optimize the configuration and operation of the data collection device, such as configuring permutations and combinations of sensors based on context and conditions). In one example, the data collection system 102 includes a crosspoint switch 130 or other analog switch. The automated, intelligent configuration of the local data collection system 102 may be based on various types of information, such as information from various input sources, including available power, power requirements of sensors, value of collected data (e.g., based on feedback information from other elements of the platform 100), relative value of information (e.g., value based on the availability of other sources of the same or similar information), power availability (e.g., to power sensors), network conditions, ambient conditions, operating states, operating contexts, operating events, and many others.

FIG. 7 illustrates elements and subcomponents of a data collection and analysis system 1100 for sensor data (e.g., analog sensor data) collected in an industrial environment. As depicted in FIG. 7, embodiments of the methods and systems disclosed herein may include hardware with several different modules, starting with a multiplexer (“MUX”) main board 1104. In embodiments, there may be a MUX option board 1108. The MUX 114 main board is where sensors connect to the system. These connections are on the top for ease of installation. Numerous settings are then located on the underside of this board and on the Mux option board 1108, which attaches to the MUX main board 1104 via two headers, one on each end of the board. In embodiments, the Mux option board has a male header that mates with a female header on the Mux main board. This allows MUX option boards to be stacked, resulting in a smaller footprint.

In an embodiment, the main Mux board and/or MUX option board then connect via cables to mother (e.g., having four simultaneous channels) and daughter (e.g., having four additional channels for a total of eight channels) analog boards 1110, where some of the signal conditioning (e.g., hardware integration) occurs. The signal then travels from the analog board 1110 to an anti-aliasing board (not shown), where some of the potential aliasing is removed. The remaining portion of the aliasing removal occurs on the delta-sigma board 1112, which performs more of the aliasing countermeasures, along with other signal conditioning and digitization. The data then travels to the Jennie board 1114 for further digitization and communication to a computer via USB or Ethernet. In an embodiment, replacing the Jennie board 1114 with a Pic board 1118 allows for more advanced and efficient data collection and communication. Once the data is transferred to the computer software 1102, the computer software 1102 can manipulate the data to display trends, spectra, waveforms, statistics, and analysis.

In embodiments, this means the system captures any type of data, from volts to 4-20 mA signals. In embodiments, open formats for data storage and communication can be used. In some instances, certain parts of the system can be dedicated to research and data portions specifically related to analysis and reporting. In embodiments, smart band analysis breaks down data into easy-to-analyze pieces and can be combined with other smart bands to create new, simpler, yet sophisticated analyses. In embodiments, this unique information is taken and depicted using graphics, as pictorial depictions are more useful to users. In embodiments, complex programs and user interfaces are simplified, allowing anyone to manipulate data like an expert.

In embodiments, the system essentially operates in a big loop. The system begins with software with a general user interface ("GUI") 1124. In embodiments, rapid route creation can utilize hierarchical templates. In embodiments, the GUI is created so that any general user can enter the information themselves using simple templates. Once the templates are created, users can copy and paste what they need. Users can also develop their own templates for future ease of use and knowledge institutionalization. Once the user has entered all the information and connected all the sensors, they can begin acquiring data with the system.

Embodiments of the methods and systems disclosed herein can include unique electrostatic protection for trigger and vibration inputs. Proper transducer and trigger input protection is required in many critical industrial environments where large electrostatic forces that can potentially harm electrical equipment can build up, such as rotating machinery and slow-speed balancing with large belts. Embodiments describe a low-cost yet efficient method for providing such protection without the need for external auxiliary equipment.

Typically, vibration data collectors are not designed to handle large input voltages due to expense and often not required. As technology improves and monitoring costs plummet, there is a need for these data collectors to capture many different types of RPM data. In this embodiment, rather than using traditional reed relay methods, a method is used that uses established OptoMOS technology, which allows for pre-switching of high-voltage signals. Many historical concerns about nonlinear zero crossings and other nonlinear solid-state behavior are eliminated when passing weak, buffered analog signals. Furthermore, in this embodiment, the PCB wiring topology places all of the input circuitry for each individual channel as close as possible to the input connector. In this embodiment, unique electrostatic protection for the trigger and vibration inputs is placed on the front of the Mux and DAQ hardware, allowing for the dissipation of charge buildup as signals pass from the sensor to the hardware. In this embodiment, the Mux and analog board support high-amperage inputs using a design topology consisting of wider traces and solid-state relays for the upfront circuitry.

In some systems, the multiplexer is an afterthought and the quality of the signal coming out of the multiplexer is not taken into consideration. A poor multiplexer can result in a loss of signal quality of 30 dB or more. Thus, using a 24-bit DAQ with a 110 dB signal-to-noise ratio can result in significant signal quality loss, and if the signal-to-noise ratio at the mux drops to 80 dB, it may be much worse than a 16-bit system from 20 years ago. In this system embodiment, a key part of the stage before the mux is upfront signal conditioning on the mux to improve the signal-to-noise ratio. In embodiments, signal conditioning (range/gain control, integration, filtering, etc.) may be performed on not only vibration but also other signal inputs before the mux switching to achieve the best signal-to-noise ratio.

In addition to providing a better signal, in embodiments, a multiplexer may also provide continuous monitoring alarm functionality. True continuous systems monitor all sensors constantly but tend to be expensive. Typical multiplexer systems monitor only a set number of channels at a time, switching between banks of larger sensor sets. As a result, sensors not currently being sampled are not monitored, and rising levels go unnoticed to the user. In embodiments, a multiplexer can have continuous monitoring alarm functionality even when the data acquisition ("DAQ") is not monitoring the inputs by placing circuitry in the multiplexer that can measure the levels of input channels for known alarm conditions. A continuous monitor mux bypass allows channels not sampled by the mux system to be continuously monitored for critical alarm conditions via some trigger condition using a filtered peak-hold circuit or similar circuitry, but these conditions are passed to the monitoring system in a convenient manner using hardware interrupts or other means. This allows the system to be continuously monitored, although without the ability to immediately obtain data about a problem as with a true continuous system. In embodiments, this alarm functionality may be combined with adaptive scheduling techniques for continuous monitoring, allowing the continuous monitoring system software to adapt and adjust data collection sequences based on statistics, analytics, data alarms, and dynamic analysis, allowing the system to rapidly collect dynamic spectral data from the alarm sensor immediately after the alarm sounds.

Another limitation of typical multiplexers is their limited channel count. In an embodiment, distributed Complex Programmable Logic Device (CPLD) chips with dedicated buses for logic control of multiple Muxes and data acquisition units allow the CPLD to control multiple Muxes and DAQs, eliminating the need for a limited number of channels. Interfacing with multiple types of predictive maintenance and vibration transducers requires a lot of switching. This includes AC/DC coupling, 4-20 interfaces, integrated electronic piezoelectric transducers, channel power-down (to conserve op-amp power), single-ended or differential grounding options, and more. Also required are controls for digital pots for range and gain adjustment, switches for hardware integration, AA filtering, and triggering. This logic can be implemented on a series of CPLD chips strategically placed for the task at hand. A single, large CPLD requires long circuit routes, which allows for greater density within a single, large CPLD. In an embodiment, distributed CPLDs address these concerns while also providing significant flexibility. A bus is created, with each CPLD having its own unique device address, with fixed assignments. In an embodiment, multiplexers and DAQs are stacked to provide additional input/output channels to the system. Multiple boards (e.g., multiple Mux boards) have jumpers available to set multiple addresses. In another example, up to eight boards can be jumper-programmed with 3 bits. In an embodiment, a bus protocol is defined so that each CPLD on the bus can be addressed individually or as a group.

Typical multiplexers may be limited to collecting only sensors from the same bank. This can be limiting, as there is great value in being able to simultaneously view data from sensors on the same machine for detailed analysis. Systems using traditional fixed-bank multiplexers can only compare a limited number of channels (based on the number of channels per bank) assigned to specific groups during installation. Flexibility can only be achieved by overlapping channels or by incorporating a large amount of redundancy into the system, both of which come at a significant cost (and in some cases, the cost can increase exponentially relative to the flexibility). The simplest mux design selects one of many inputs and routes it to a single output line. A banked design consists of a group of these simple building blocks, each handling a fixed group of inputs and routing them to their own outputs. Inputs are typically non-overlapping, meaning that inputs from one mux group cannot be routed to another mux group. While traditional mux chips typically switch selected channels from a fixed group or bank to a single output (e.g., groups of 2, 4, 8, etc.), crosspoint muxes allow users to assign any input to any output. Traditionally, crosspoint multiplexers have been used for specialized applications such as RGB digital video and were too noisy for analog applications such as vibration analysis, but recent technological advances have made them feasible. Another advantage of crosspoint muxes is that their outputs can be disabled by placing them in a high-impedance state. This feature is ideal for output buses, where multiple mux cards can be stacked to combine output buses without the need for a bus switch.

In embodiments, this problem can be addressed by using analog crosspoint switches to collect variable groups of vibration input channels and providing a matrix circuit that allows the system to access any set of eight channels from the total number of input sensors.

In an embodiment, multiple multiplexers can be controlled using a distributed CPLD chip with dedicated buses for logic control and data acquisition of multiple muxes. The section is enhanced with a hierarchical multiplexer, allowing multiple DAQs to acquire data from multiple multiplexers. The hierarchical multiplexer can modularly output 16, 24, or more channels to multiple 8-channel card sets. This allows for faster data acquisition and the ability to simultaneously acquire more channels for more complex analysis. In an embodiment, the muxes can be made portable with minor configuration, and the data acquisition parking feature can be used to turn the SV3X DAQ into a protected system embodiment.

In embodiments, once the signal leaves the multiplexer and hierarchical Mux, it travels to the analog board where other enhancements occur. In embodiments, the following power-saving techniques may be used: powering down analog channels when not in use, powering down component boards, powering down analog signal processing op-amps for unselected channels, and powering down channels on mother and daughter analog boards. Because the DAQ system's low-level firmware can power down component boards and other hardware, sophisticated application control over power-saving features is relatively easy. Explicit control of the hardware is always possible, but is not required by default. In embodiments, this power-saving benefit may be valuable in protected systems, especially when battery- or solar-powered.

In an embodiment, to maximize the signal-to-noise ratio and provide the best possible data, the autoscaling peak detector routes the highest peak in each data set to a separate A/D converter, allowing the system to quickly scale the data to that peak. For vibration analysis, the A/D converters built into many microprocessors are often insufficient in terms of bit count, channel count, and sampling frequency, and it may be necessary to avoid significantly slowing down the microprocessor. Despite these limitations, using them for autoscaling purposes can be useful. In an embodiment, a separate, less powerful, and less expensive A/D converter may be used. For each input channel, after the signal is buffered (usually with appropriate AC or DC coupling), but before signal conditioning, it is fed directly to the microprocessor or a low-cost A/D converter. Unlike the conditioned signal, where range, gain, and filter switches are engaged, these switches are not changed. This allows the autoscaling data to be sampled simultaneously while the input data is processed and fed to a more robust external A/D converter, and then routed to onboard memory via Direct Memory Access (DMA), bypassing the CPU. This significantly simplifies the autoscaling process by eliminating the need for settling time after throwing a switch, which significantly slows down the autoscaling process. Furthermore, data can be collected simultaneously, ensuring the highest signal-to-noise ratio. A reduction in the number of bits, etc., is typically more than sufficient for autoscaling purposes. In embodiments, improved integration using both analog and digital methods creates an innovative hybrid integration that also improves or maintains the highest possible signal-to-noise ratio.

In embodiments, sections of the analog board can route raw or buffered trigger channels to other analog channels. This may allow the user to route triggers to either channel for analysis or troubleshooting. Systems may have trigger channels for purposes of determining the relative phase between various input data sets or acquiring important data without repeating unnecessary inputs. In embodiments, digitally controlled relays may be used to switch raw or buffered trigger signals to either of the input channels. It may be desirable to verify the quality of the trigger pulse, as it may be corrupted for a variety of reasons, including improper placement of the trigger sensor, wiring issues, or dirty reflective tape when using optical sensors. The ability to view either the raw or buffered signal allows for superior diagnostics and debugging. Recorded data signals may also be utilized for various signal processing techniques, such as variable-rate filtering algorithms, to improve phase analysis capabilities.

In an embodiment, once the signal leaves the analog board, it passes to the delta-sigma board, where a precise voltage reference for the A/D zero reference provides more accurate DC sensor data. The high speed of delta-sigma also allows the delta-sigma A/D to have a higher input oversampling setting and output at a lower sampling rate to minimize the need for anti-aliasing filters. For higher sampling rates, a lower oversampling rate can be used. For example, a third-order AA filter set to the lowest sampling condition of 256 Hz (Fmax 100 Hz) is appropriate for Fmax ranges of 200 Hz and 500 Hz. For Fmax above 1 kHz, a higher cutoff AA filter can be used (using a second-order filter 2.56 times the highest sampling rate of 128 kHz). In an embodiment, a CPLD can be used as a clock divider for the delta-sigma A/D to achieve lower sampling rates without the need for digital resampling. In an embodiment, a CPLD can be used as a programmable clock divider to divide a high-frequency crystal reference to a lower frequency. The precision of the divided low frequencies is greater relative to the longer time period of the original source, and the need for resampling by the delta-sigma A/D is minimized.

The data then travels from the Delta Sigma board to the Jennie board, which uses an onboard timer to digitally derive the phase relative to the input and trigger channels. The Jennie board also has the ability to store calibration data and system maintenance history data on a set of cards. The Jennie board can also acquire long blocks of data at a high sampling rate, rather than multiple data acquisitions at different sampling rates, allowing for streaming data or acquiring long blocks of data for advanced analysis in the future.

In an embodiment, after the signal passes through the Jennie board, it can be sent to a computer. In an embodiment, computer software is used to add intelligence to the system, starting with an expert system GUI. This GUI is a graphical expert system with a simple user interface for defining smart bands and diagnostics, allowing anyone to easily perform complex analyses. In an embodiment, this user interface revolves around the smart band, a simple approach for general users to perform complex yet flexible analyses. In an embodiment, the smart band may be combined with a self-learning neural network for a more advanced analytical approach. In an embodiment, the system may use machine hierarchy for further analytical insights. One key element of predictive maintenance is the ability to learn from known information during repairs and inspections. In an embodiment, a graphical approach for back-calculation can improve smart bands and correlations based on known failures and problems.

In embodiments, there is a smart route to adapt which sensors are collected simultaneously to gain additional correlation intelligence. In embodiments, a smart operational data store ("ODS") allows the system to select data collection for operational deflection shape analysis to further examine the condition of the machine. In embodiments, adaptive scheduling techniques allow the system to modify the data scheduled to be collected for full spectrum analysis across multiple (e.g., eight) correlation channels. In embodiments, the system can provide data enabling expanded statistical capabilities for continuous monitoring, as well as ambient local vibration, for combined analysis of changes in ambient and local temperature and vibration levels to identify machine issues.

In embodiments, the data acquisition device may be controlled by a personal computer (PC) to implement desired data acquisition commands. In embodiments, the DAQ box may be self-sufficient, capable of acquisition, processing, analysis, and monitoring independent of external PC control. In embodiments, Secure Digital (SD) card storage may be included. In embodiments, utilizing an SD card can provide significant additional storage capabilities. This may prove important for monitoring applications where important data may be permanently stored. Also, in the event of a power outage, the most recent data may be preserved even if it has not been offloaded to another system.

The current trend is to make DAQ systems as communicable as possible with the outside world, usually in the form of a network, including wireless. In the past, it was common to use a dedicated bus to control the DAQ system with either a microprocessor or microcontroller/microprocessor paired with a PC. In embodiments, a DAQ system may consist of one or more microprocessors/microcontrollers, specialized microcontrollers/microprocessors, or dedicated processors focused primarily on the communication aspects with the outside world. Examples include USB, Ethernet, wireless, and the ability to provide an IP address for hosting a web page. All communication with the outside world is done using simple text-based menus. The usual commands (over 100 in fact) are available, such as InitializeCard, AcquireData, StopAcquisition, and RetrieveCalibration Info.

In embodiments, intensive signal processing activities, including resampling, weighting, filtering, and spectral processing, may be performed by a dedicated processor, such as a field programmable gate array ("FPGA"), digital signal processor ("DSP"), microprocessor, microcontroller, or combination thereof. In embodiments, this subsystem may communicate with a communications processor via a dedicated hardware bus, facilitated by dual-port memory, semaphore logic, and the like. This embodiment significantly improves efficiency and enables significant increases in processing power, including data streaming and other high-end analysis techniques. This eliminates the need to constantly interrupt key processes, such as controlling signal conditioning circuits, triggering, acquiring raw data through the A/D, directing the A/D output to the appropriate onboard memory, and processing the data.

Embodiments may include sensor overload identification. A need exists for a monitoring system that identifies when a sensor is overloaded. There may be situations involving high frequency inputs that saturate the standard 100mv/g sensors most commonly used in the industry, and having the ability to sense the overload improves data quality for better analysis. While a monitoring system can identify when a system is overloaded, in embodiments, the system looks at the sensor voltage to determine if the overload is due to the sensor, allowing the user to obtain another sensor that is more appropriate for the situation or collect the data again.

In embodiments, sensors may be equipped with RFID (Radio Frequency Identification), inclinometers, or accelerometers to indicate which machine or bearing the sensor is attached to and in what orientation, allowing the software to automatically store data without user input. In embodiments, a user can simply attach the system to any machine, and the system will automatically configure and be ready to collect data within seconds.

Embodiments may include ultrasonic online monitoring by placing ultrasonic sensors inside transformers, motor control centers, breakers, etc., and continuously monitoring the sound spectrum for patterns that identify electrical issues such as arcing, corona, etc., that indicate faults or problems. Embodiments may include providing continuous ultrasonic monitoring of rotating elements and bearings of energy production equipment. In embodiments, an analytical engine may combine ultrasonic data with other parameters such as vibration, temperature, pressure, heat flux, magnetic field, electric field, current, voltage, capacitance, inductance, and combinations thereof (e.g., simple ratios) for use in identifying other faults in addition to ultrasonic online monitoring.

Embodiments of the methods and systems disclosed herein can include the use of analog crosspoint switches to collect variable groups of vibration input channels. For vibration analysis, it is useful to simultaneously acquire multiple channels from vibration transducers mounted in multiple orientations on different parts of a machine. Simultaneous acquisition allows, for example, comparing the relative phase of the inputs to diagnose various machine faults. Other types of cross-channel analysis can also be performed, such as cross-correlation, transfer function, and operating deflection shape (ODS).

Embodiments of the methods and systems disclosed herein may include a precision voltage reference for the A/D zero reference. Some A/D chips provide their own internal zero voltage reference, which is used as a midscale value for external signal conditioning circuitry to ensure that both the A/D and the external op amp use the same reference. While this sounds reasonable in principle, practical complications arise. Often, these references are inherently based on the supply voltage using a resistor divider. In many modern systems, especially those powered by a PC via a bus such as USB, the supply voltage often varies significantly with load, resulting in an unreliable reference. This is particularly true for delta-sigma A/D chips that require signal processing. While offsets vary with load, problems arise when digitally calibrating readings. To compensate for DC drift, it is common to digitally correct the voltage offset, expressed in counts, output by the A/D. However, in this case, determining an appropriate calibration offset for one load condition does not apply to other conditions. This makes the absolute DC offset, expressed in counts, inapplicable. This would require calibration for every load condition, which would become complex, unreliable, and ultimately unmanageable. In an embodiment, an external voltage reference that is simply independent of the power supply voltage is used for use as the zero offset.

In an embodiment, the system provides a phase-locked loop bandpass tracking filter method for obtaining low-speed RPM and phase for balancing purposes, and provides additional analysis from that data, for remote balancing of low-speed machinery, such as paper mills. Balancing may require balancing at very slow speeds. A typical tracking filter may be built based on a phase-locked loop or PLL design, where stability and speed range are paramount. In an embodiment, a number of digitally controlled switches are used to select appropriate RC and damping constants. This can all be done automatically after measuring the frequency of the incoming tach signal. Method and system embodiments disclosed herein may include digital derivation of phase for input and trigger channels using onboard timers. In an embodiment, digital phase derivation uses digital timers to determine the precise delay from the trigger event to the exact start of data acquisition. This delay or offset is applied to the analytically determined phase of the acquired data, with interpolation used to obtain a more precise offset. This phase results in an absolute phase with precise mechanical meaning, useful for one-shot balancing, alignment analysis, and more.

Embodiments of the methods and systems disclosed herein may include signal processing firmware/hardware. In embodiments, long blocks of data may be acquired at a high sampling rate, as opposed to multiple data sets acquired at different sampling rates. Generally, modem route collection for vibration analysis involves collecting data at a fixed sampling rate with a specified data length. The sampling rate and data length may vary at different points along the route, depending on the needs of the mechanical analysis. For example, a motor may require high resolution at a relatively low sampling rate to distinguish between harmonics of the running speed and harmonics of the line frequency. However, the practical tradeoff is that more collection time is required to achieve this increased resolution. In contrast, high-speed compressors and gearsets may require less precise resolution, but may require a much higher sampling rate to measure the amplitude of relatively high-frequency data. Ideally, however, data with a very long sample length would be collected at a very high sampling rate. When digital acquisition devices first became widespread in the early 1980s, A/D sampling, digital storage, and computing power were not at current levels, forcing compromises between data collection time and the required resolution and accuracy. These limitations led some field analysts to stick with analog tape recording systems, which lacked many of the drawbacks of digitalization. Some hybrid systems digitized and played back recorded analog data at multiple desired sampling rates and lengths, but these systems were not automated. A more common approach, as previously mentioned, balances data collection time and analysis capability by digitally acquiring data blocks at multiple sampling rates and lengths and digitally storing these blocks separately. In one embodiment, a long data length can be acquired and stored at the highest practical sampling rate (e.g., 102.4 kHz, corresponding to an Fmax of 40 kHz). This long data block can be acquired in the same time as the shorter length at a lower sampling rate used a priori, eliminating the additional effective delay associated with sampling at the measurement point, which is always a concern in route collection. In embodiments, analog tape recording of data is digitally simulated with such accuracy that it can be considered substantially continuous or "analog" for many purposes, including for purposes of embodiments of the present disclosure, unless the context dictates otherwise.

Embodiments of the methods and systems disclosed herein can include storing calibration data and maintenance history for the onboard card set. Many data acquisition devices that rely on interfacing with a PC to function store their calibration coefficients on the PC. This is especially true for complex data acquisition devices with many signal paths and therefore potentially large calibration tables. In embodiments, the calibration coefficients can be stored in flash memory, allowing this and other data to be stored, so that critical information is, for all practical purposes, permanently stored. This information includes nameplate information such as serial numbers for individual components, firmware or software version numbers, maintenance history, and calibration tables. In embodiments, the DAQ box remains calibrated and retains all of this critical information, regardless of which computer the box is ultimately connected to. PCs and external devices can poll this information at any time for portability or information exchange purposes.

Embodiments of the methods and systems disclosed herein can include rapid route creation using hierarchical templates. Similar to general parametric monitoring, vibration monitoring requires the existence of data monitoring points to be established in a database or equivalent. These points have various associated attributes, such as transducer attributes, data acquisition settings, machine parameters, and operational parameters. Transducer attributes include probe type, probe mounting type, and probe mounting direction or axis orientation. Measurement-related data acquisition attributes include sampling rate, data length, power and coupling requirements for integrated electronic piezoelectric probes, hardware integration requirements, 4-20 or voltage interface, range and gain settings (if applicable), and filter requirements. Machine parameter requirements associated with a particular point include items such as operating speed, bearing type, and bearing parameter data (e.g., pitch diameter, number of balls, inner race, and outer race diameter for rolling element bearings). For tilting pad bearings, this includes the number of pads. For measurement points on equipment such as gearboxes, required parameters may include, for example, the number of teeth on each gear. For induction motors, this includes the number of rotor bars or poles; for compressors, the number of blades or vanes; and for fans, the number of blades. For belt/pulley systems, the pulley dimensions and center-to-center distance allow for the calculation of the number of belts and the associated belt-pass frequency. Measurements near couplings require the type of coupling and the number of teeth for geared couplings. Operating parametric data includes operating load in megawatts, flow rate (air or fluid), rate, horsepower, and feet per minute. Other relevant parameters include ambient and operating temperatures, pressure, and humidity. Thus, the amount of configuration information required for each measurement point is significant. This information is also crucial for valid data analysis. Machine-, equipment-, and bearing-specific information is essential for identifying failure frequencies and predicting various types of specific failures. Transducer attributes and data acquisition parameters are essential for proper data interpretation and limiting the types of analysis techniques that are appropriate. Traditional methods of entering this data are manual and tedious. Typically, data is entered at the lowest hierarchical level (e.g., at the bearing level for machine parameters and at the transducer level for data collection configuration information). However, the importance of the hierarchical relationship required to organize data, not only for data storage and transfer, but also for analysis and interpretation, cannot be overemphasized. Here, we focus on data storage and transfer. While such configuration information is, by its nature, highly redundant at the lowest hierarchical levels, its strong hierarchical nature allows it to be stored in this form quite efficiently. In embodiments, the hierarchy can be exploited when copying data in the form of templates. As an example, a hierarchical storage structure suitable for many purposes, from general to specific, is defined, such as company, plant, site, unit, process, machine, equipment, shaft element, bearing, transducer, etc. Copying data related to a specific machine, equipment, shaft element, or bearing is much easier than copying only at the lowest transducer level. In embodiments, the system not only stores data in this hierarchical manner, but also provides robust support for rapid copying of data using these hierarchical templates. The similarity of elements at specific hierarchical levels lends itself to effective data storage in a hierarchical format. For example, many machines share common elements such as motors, gearboxes, compressors, belts, and fans. Specifically, many motors can be easily categorized as induction, DC, fixed speed, or variable speed. Many transmissions fall into commonly occurring groupings such as input/output, input pinion/intermediate pinion/output pinion, and 4-post. Within a factory or company, many similar types of equipment are purchased and standardized for cost and maintenance reasons. This results in a great deal of overlap between similar types of equipment, creating a great opportunity to utilize a hierarchical template approach.

Embodiments of the methods and systems disclosed herein can include smart bands. A smart band refers to processed signal characteristics derived from any dynamic input or group of inputs for the purpose of analyzing the data to achieve a correct diagnosis. Furthermore, smart bands can even include mini or relatively simple diagnostics for the purpose of achieving more robust and complex diagnostics. Historically, in the field of mechanical vibration analysis, alarm bands have been used to define spectral frequency bands of interest for the purpose of analyzing and/or trending important vibration patterns. Alarm bands consist of the spectral (amplitude plotted against frequency) region between low- and high-frequency boundaries. The amplitudes between these boundaries are summed in the same manner to calculate the overall amplitude. Smart bands are more flexible in that they can refer not only to specific frequency bands but also to groups of spectral peaks such as single-peak harmonics, true peak levels or crest factors derived from time waveforms, ensembles derived from vibration envelope spectra or other specialized signal analysis techniques, or logical combinations (e.g., AND, OR, XOR) of these signal attributes. Additionally, countless other parametric data, including system load, motor voltage and phase information, bearing temperatures, flow rates, etc., can similarly be used as the basis for forming additional smart bands. In embodiments, smart band symptoms can be used as components of an expert system that utilizes these inputs to perform diagnoses. Some of these mini-diagnoses can then be used as smart band symptoms (which can also include diagnoses) for more general diagnoses.

Embodiments of the methods and systems disclosed herein can include a neural net expert system that uses a smart band. A typical vibration analysis engine is rule-based (i.e., it uses a list of expert rules that, when satisfied, trigger a specific diagnosis). In contrast, a neural approach weights multiple input stimuli into small analysis engines (neurons), which provide simplified, weighted outputs to other neurons. The outputs of these neurons are classified as smart bands and provided to other neurons. This creates a more layered approach to expert diagnosis, as opposed to the one-shot approach of rule-based systems. In this embodiment, the expert system utilizes this neural approach with a smart band, but nothing prevents rule-based diagnoses from being reclassified as smart bands to serve as additional stimuli for the expert system. From this perspective, it can be viewed as a hybrid approach, although at the highest level it is essentially neural.

Embodiments of the methods and systems disclosed herein may include the use of a database hierarchy in which analytical smart band symptoms and diagnoses may be assigned to various hierarchical database levels. For example, a smart band may call "Looseness" at the bearing level, trigger "Looseness" at the equipment level, and trigger "Looseness" at the machine level. In another example, a smart band diagnosis of "Horizontal Plane Phase Reversal" may be made for the entire coupling, and a smart band diagnosis of "Vertical Coupling Misalignment" may be generated at the machine level.

Embodiments of the methods and systems disclosed herein may include an expert system GUI. In embodiments, the system employs a graphical approach to defining smart bands and diagnostics for the expert system. Entering symptoms, rules, or more generally smart bands to create specific machine diagnoses can be tedious and time-consuming. Providing a graphical means of wiring can make the process easier and more efficient. The proposed graphical interface is comprised of four major components: a symptom parts bin, a diagnostics bin, a tool bin, and a graphical wiring area ("GW A"). In embodiments, the symptom parts bin contains various spectra, waveforms, envelopes, and any type of signal processing characteristic or group of characteristics, such as spectral peaks, spectral harmonics, waveform true peaks, waveform crest factors, and spectral alarm bands. Additional characteristics can be assigned to each part. For example, parts of a spectral peak may be assigned orders of frequency or road speed. Some parts are predefined or user-defined, such as lx, 2x, 3x running speed, lx, 2x, 3x gear mesh, lx, 2x, 3x blade path, number of motor rotor bars x running speed.

In an embodiment, the diagnostic bin contains a variety of predefined and user-defined diagnoses, such as misalignment, unbalance, looseness, and bearing faults. Like parts, diagnoses can also be used as building blocks to construct more complex diagnoses. In an embodiment, the tool bin contains other methods of combining the various parts, such as logical operations like AND, OR, and XOR, as well as statistical operations like Find Max, Find Min, Interpolate, Average, and others. In an embodiment, the graphical wiring area contains parts from the parts bin or diagnoses from the diagnostic bin, which may be combined using tools to create a diagnosis. The various parts, tools, and diagnoses are represented by icons that are simply graphically wired in the desired manner.

Embodiments of the methods and systems disclosed herein may include a graphical approach for back-calculation definition. In embodiments, the expert system also provides an opportunity for the system to learn. If a specific set of stimuli or smart band is already known to correspond to a particular fault or diagnosis, it is possible to back-calculate a set of coefficients that, when applied to a future set of similar stimuli, will arrive at the same diagnosis. In embodiments, a best-fit approach can be used when there are multiple data sets. Unlike the smart band GUI, in this embodiment, the wiring diagram is self-generated. In embodiments, the user may adjust settings in the back-propagation approach and use a database browser to match a particular data set with the desired diagnosis. In embodiments, the desired diagnosis may be created or custom-tuned in the smart band GUI. In embodiments, the user may then press a "GENERATE" button, which may display a dynamic wiring from symptoms to diagnoses as it works through the algorithm to find the best fit. In embodiments, upon completion, various statistics are presented detailing how well the mapping process progressed. In some cases, mapping may not be achieved, for example, if the input data is all zeros or incorrect (misassigned) data. Embodiments of the methods and systems disclosed herein may include bearing analysis methods. In embodiments, the bearing analysis methods may be used in combination with computer-aided design ("CAD"), predictive deconvolution, minimum variance distortion-free response ("MVDR"), and spectral sum of harmonics.

In recent years, there has been a strong demand for power conservation, resulting in an influx of variable frequency drives and variable speed machines. In an embodiment, a bearing analysis method is provided. In an embodiment, torsional vibration detection and analysis is provided using transient signal analysis to provide advanced torsional vibration analysis for a more comprehensive approach to diagnosing torsional force-related machines (e.g., machines with rotating parts). Due to the declining cost of motor speed control systems and increased awareness of energy consumption, exploiting the significant energy-saving potential of load control has become economically justified. However, an often overlooked aspect of this problem is the issue of vibration. When a machine is designed to operate at only one speed, it is much easier to design the physical structure to avoid structural and torsional mechanical resonances, each of which dramatically reduces the machine's health. This includes structural characteristics such as the type of material used, its weight, stiffening requirements and placement, bearing type, bearing location, and base support constraints. Even for machines that operate at one speed, designing the structure to minimize vibration is a challenging task requiring computer modeling, finite element analysis, field testing, and more. Add variable speeds to the mix, and it's often impossible to design for every desired speed. The challenge then becomes minimizing or avoiding speeds. This is why many modern motor controllers are programmed to skip or quickly pass through certain speed ranges or bands. Embodiments can include identifying speed ranges in a vibration monitoring system. Non-torsional structural resonances are fairly easy to detect using traditional vibration analysis techniques. This is not the case for torsional resonances. Currently, torsional resonances are a growing problem. This is clearly due to the increase in torsional stresses caused by speed changes, as well as the operation of equipment at torsional resonance speeds. Unlike non-torsional structural resonances, which typically manifest themselves as a dramatic increase in casing or external vibrations, torsional resonances generally do not exhibit such effects. In the case of shaft torsional resonances, the torsional motion caused by the resonance can only be identified by examining the speed and phase changes. Current standard methods for analyzing torsional vibrations require the use of specialized equipment. The method and system presented here allows for the analysis of torsional vibrations without the need for such specialized equipment. This may involve shutting down the machine and using specialized fixtures such as strain gauges or speed encoder plates and gears. Friction wheels are another option, but they typically require manual implementation and specialized analysts. These techniques are generally very expensive and inconvenient. Continuous vibration monitoring systems are becoming more common due to reduced costs and increased convenience (e.g., remote access). In embodiments, there is the ability to identify torsional speed and/or phase fluctuations from the vibration signal alone. In embodiments, transient analysis techniques may be utilized to distinguish torsional-induced vibration from simple speed changes due to process control. In embodiments, factors for identification may focus on one or more of the following aspects: The rate of speed change due to variable speed motor control is relatively slow, sustained, and intentional. Torsional speed changes tend to be short, impulsive, and unsustained. Additionally, the small speed changes associated with torsion compared to the rotational speed of the shaft suggests that monitoring phase behavior will show quick or transient bursts of speed, as opposed to the slow phase changes (typical of Bode and Nyquist plots) historically associated with speeding machines up and down.

Embodiments of the methods and systems disclosed herein can include improved integration using both analog and digital methods. When signals are digitally integrated using software, the spectral low-frequency data is essentially multiplied by a function that expands as its amplitude approaches zero, creating what is known in the industry as a "ski slope" effect. This ski slope amplitude essentially becomes the noise floor of the instrument. A simple solution to this requires a traditional hardware integrator. Also, the amplification factor can be kept to a reasonable level, essentially prohibiting multiplication by very large numbers. However, at higher frequencies, the original amplitude, well above the noise floor, is multiplied by a very small number (1/f) that is well below the noise floor. Hardware integrators have a fixed noise floor, and although it is low, it does not scale down with low-amplitude high-frequency data. In contrast, if a digitized high-frequency signal is digitally multiplied in the same way, the noise floor is proportionally smaller. In embodiments, for ideal results, hardware integration may be used below the unity gain point (typically at a value determined by gain-based units and/or the desired signal-to-noise ratio), and software integration may be used above unity gain. In embodiments, this integration is performed in the frequency domain. In embodiments, the resulting hybrid data can be converted back into a waveform that should have a much better signal-to-noise ratio when compared to either the hardware-integrated or software-integrated data. In embodiments, the strengths of hardware integration are combined with the strengths of digital-software integration to achieve the highest signal-to-noise ratio. In embodiments, the high-pass filter and curve fitting of the first-order staged hardware integrator can pass relatively low-frequency data while reducing or eliminating noise, salvaging highly useful analytical data that would otherwise be lost with a steeper filter.

Embodiments of the methods and systems disclosed herein can include adaptive scheduling techniques for continuous monitoring. Continuous monitoring is often performed using an upfront mux, which selects a few channels of data from a large number of data sources to feed the hardware signal processing, A/D, and processing components of a DAQ system. This is primarily driven by practical cost considerations. The tradeoff is that not all points are monitored continuously (although they may be monitored to some extent via alternative hardware methods). Embodiments provide multiple scheduling levels. In embodiments, at the lowest level, which is mostly continuous, all measurement points are cycled through in a round-robin fashion. For example, if it takes 30 seconds to acquire and process a measurement point and there are 30 measurement points, each measurement point may be serviced once every 15 minutes. However, if a measurement point should alarm due to user-selected criteria, that measurement point may be prioritized and serviced more frequently. Just as there are multiple grades of severity for each alarm, there are also multiple priorities for monitoring. In embodiments, more serious alarms are monitored more frequently. In embodiments, many additional high-level signal processing techniques may be applied less frequently. In embodiments, the PC can take advantage of the increased processing power by temporarily suspending the round-robin route collection process (with its multiple layers of collection) and streaming the required amount of data for a selected point. In embodiments, various advanced processing techniques, such as envelope processing, wavelet analysis, and many other signal processing techniques, can be included. In embodiments, after acquiring this data, the DAQ card set continues its route at the interrupted point. In embodiments, the scheduled data acquisition for the various PCs follows its own schedule, occurring less frequently than the DAQ card routes. They may be set to hourly, daily, or per route cycle (e.g., once every 10 cycles), and may also be scheduled to increase based on alarm severity priority or measurement type (e.g., a motor may be monitored differently from a fan).

Embodiments of the methods and systems disclosed herein may include a data acquisition parking function. In embodiments, a data collection box used for path collection, real-time analysis, and general acquisition equipment may be detached from its PC (e.g., tablet) and powered by an external power source or a suitable battery. In embodiments, the data collection device retains continuous monitoring capabilities, and its on-board firmware may implement dedicated monitoring functions for extended periods of time or be remotely controlled for further analysis. Embodiments of the methods and systems disclosed herein may include extended statistical functions for continuous monitoring.

Embodiments of the methods and systems disclosed herein may include ambient sensing + local sensing + vibration for analysis. In embodiments, ambient environmental temperature and pressure, sensed temperature and pressure, may be combined with long-term/medium-term vibration analysis to predict any set of conditions or characteristics. In variations, infrared sensing, infrared thermography, ultrasound, and many other types of sensors and input types may be added in combination with vibration or with each other. Embodiments of the methods and systems disclosed herein may include smart routes. In embodiments, the software of the continuous monitoring system will adapt/adjust the data collection order based on statistics, analytics, data alarms, and dynamic analysis. Typically, routes are set based on the channel to which the sensor is attached. In embodiments, a crosspoint switch allows the Mux to couple any input Mux channel to (e.g., eight) output channels. In embodiments, when a channel goes into alarm or the system identifies a significant deviation, the normal route set in the software will be suspended in order to collect specific concurrent data from channels that share significant statistical changes for more advanced analysis. Embodiments include implementing a smart ODS or smart transfer function.

Embodiments of the methods and systems disclosed herein may include a smart ODS and one or more transfer functions. In embodiments, the system's multiplexer and crosspoint switch can perform ODS, transfer function, or other specialized tests on all vibration sensors attached to a machine/structure to accurately show how machine points are moving in relation to one another. In embodiments, data can be streamed at 40-50 kHz for longer data lengths (e.g., at least one minute), revealing information different from that shown by typical ODS or transfer functions. In embodiments, the system may determine a smart route function based on the data/statistics/analysis used to deviate from the standard route and implement ODS on a machine, structure, or across multiple machines and structures where conditions/data may show correlations to indicate. In embodiments, a transfer function may use an impact hammer on one channel and compare it to other vibration sensors on the machine. In embodiments, the system may implement a transfer function using changes in conditions such as load, speed, temperature, or other changes in the machine or system. In embodiments, different transfer functions may be compared to each other over time. In embodiments, different transfer functions may be stitched together like a movie that may show how a machine failure changes, such as a bearing that may show how a bearing goes through four stages of failure. Embodiments of the methods and systems disclosed herein may include hierarchical Muxes.

Referring to FIG. 8 , the present disclosure generally involves digitally collecting or streaming waveform data 2010 from a machine 2020 whose operating speeds can vary from relatively slow rotational or vibration speeds to much higher speeds under different circumstances. The waveform data 2010 can include, in at least one machine, data from a single-axis sensor 2030 mounted at a fixed reference location 2040 and data from a three-axis sensor 2050 mounted at varying locations (or at multiple locations), including location 2052. In an embodiment, the waveform data 2010 can be vibration data acquired simultaneously from each sensor 2030, 2050 in a gap-free format over a duration of multiple minutes, at a maximum resolvable frequency large enough to capture periodic and transient impact events. By way of example, the waveform data 2010 can include vibration data that can be used to create operational deflection shapes. It can also be used to diagnose vibrations and prescribe machine repair solutions, if desired.

In an embodiment, the machine 2020 may further include a housing 2100 that may include a drive motor 2110 that may drive a shaft 2120. The shaft 2120 may be supported for rotation or oscillation by a set of bearings 2130, such as a first bearing 2140 and a second bearing 2150. A data collection module 2160 may be connected to (or resident on) the machine 2020. In one example, the data collection module 2160 may be located and accessible via a cloud network facility 2170, and may collect waveform data 2010 from the machine 2020 and distribute the waveform data 2010 to a remote location. The working end 2180 of the drive shaft 2120 of the machine 2020 may drive a windmill, fan, pump, drill, gear system, drive system, or other operating element, such that the techniques described herein may be applied to a wide range of machines, devices, tools, and the like, including rotating or vibrating elements. In another example, a generator can be used in place of the motor 2110, and the working end of the drive shaft 2120 can be directed to the generator to generate power rather than consuming rotational energy.

In an embodiment, the waveform data 2010 can be acquired using a predetermined path format based on the layout of the machine 2020. The waveform data 2010 can include data from a single-axis sensor 2030 and a three-axis sensor 2050. The single-axis sensor 2030 functions as a reference probe with one channel of data and can be fixed at a fixed position 2040 on the machine being surveyed. The three-axis sensor 2050 can function as a three-axis probe (e.g., three orthogonal axes) with its three channels of data and can be moved along a predetermined diagnostic route format from one test point to the next. In one example, both sensors 2030, 2050 can be manually attached to the machine 2020 or, in certain service cases, can be connected to a separate portable computer. The reference probe can remain in one location, while a user can move the three-axis vibration probe along a predetermined route, such as from bearing to bearing on the machine. In this example, the user is instructed to place the sensors in predetermined locations to complete a survey (or portion of a survey) of the machine.

Referring to FIG. 9, a portion of an exemplary machine 2200 is shown having a three-axis sensor 2210 mounted at a location 2220 associated with a motor bearing of the machine 2200 having an output shaft 2230 and an output member 2240 in accordance with the present disclosure.

In further examples, the sensors and data acquisition modules and devices can be integrated into or resident on the rotating machinery. By these examples, the machine can include many single-axis sensors and many three-axis sensors at predetermined locations. The sensors can be original equipment installed and provided by the original equipment manufacturer, or installed at a different time in a retrofit application. A data collection module 2160 or the like can select and use one single-axis sensor to acquire data exclusively from during collection of waveform data 2010 while moving to each of the three-axis sensors. The data collection module 2160 can be resident on the machine 2020 and/or connected via a cloud network facility 2170.

Referring to FIG. 8, various embodiments include collecting waveform data 2010 by digitally recording locally or streaming via a cloud network facility 2170. The waveform data 2010 can be collected in an uninterrupted, gap-free manner and, in some respects, can be similar to an analog recording of waveform data. Waveform data 2010 from all channels can be collected for between one and two minutes, depending on the rotational or vibration speed of the machine being monitored. In embodiments, the data sampling rate can be a relatively high sampling rate relative to the operating frequency of the machine 2020.

In an embodiment, a second reference sensor can be used to collect data for a fifth channel. In this manner, a single-axis sensor can be the first channel, and triaxial vibration can occupy the second, third, and fourth data channels. This second reference sensor, like the first reference sensor, can be a single-axis sensor, such as an acceleration sensor. In an embodiment, the second reference sensor, like the first reference sensor, can remain in the same location on the machine throughout the entire vibration study of that machine. The location of the first reference sensor (i.e., the single-axis sensor) can be different from the location of the second reference sensor (i.e., another single-axis sensor). In a particular example, a second reference sensor can be used when a machine has two shafts with different operating speeds and two reference sensors are located on two different shafts. Following this example, additional single-axis reference sensors can be employed in additional, but different, permanent locations related to the rotating machine.

In an embodiment, the waveform data can be transmitted electronically in a gap-free format at a significantly higher sampling rate for a relatively long period of time. In one example, the period is 60 seconds to 120 seconds. In another example, the sampling rate is 100 kHz and the maximum resolvable frequency (Fmax) is 40 kHz. In light of the present disclosure, it will be appreciated that the waveform data can more closely approximate some of the wealth of data available from previous examples of analog recording of waveform data.

In embodiments, sampling, band selection, and filtering techniques may be used to undersample or oversample one or more portions of a long data stream (i.e., one to two minutes in duration) to achieve different effective sampling rates. To this end, interpolation and decimation may be used to further achieve different effective sampling rates. For example, oversampling may be applied to a frequency band near the rotational or vibration operating speed of the sampled machine, or its harmonics, since vibration effects tend to be more pronounced at these frequencies in the machine's operating range. In embodiments, the digitally sampled data set may be decimated to achieve a lower sampling rate. It will be understood in light of this disclosure that decimating in this context may be the opposite of interpolating. In embodiments, decimating the data set may include first applying a low-pass filter to the digitally sampled data set and then undersampling the data set.

As an example, a 100 Hz sampled waveform can be undersampled by undersampling every 10th point of the digital waveform to produce an effective sampling rate of 10 Hz, but the remaining 9 points in that portion of the waveform are effectively discarded and not included in the modeling of the sampled waveform. Furthermore, such naked undersampling can produce ghost frequencies due to the high undersampling rate (i.e., 10 Hz) relative to the 100 Hz sampled waveform.

Most hardware for analog-to-digital conversion uses sample-and-hold circuits that can charge a capacitor for a predetermined period of time so that the average value of the waveform over a particular time period can be determined. In light of this disclosure, it will be understood that the value of a waveform over a particular time period is not linear, but more closely resembles a cardinal sinusoidal ("sine") function. Therefore, the exponential decay of a cardinal sinusoidal signal from its center indicates that more importance can be placed on the waveform data at the center of the sampling interval.

Continuing with the example above, a waveform sampled at 100 Hz can be hardware sampled at 10 Hz, with each sample point averaged over 100 milliseconds (e.g., a signal sampled at 100 Hz can have each point averaged over 10 milliseconds). As opposed to effectively discarding 9 out of 10 data points of a sampled waveform, as discussed above, the present disclosure can include weighing adjacent data. Adjacent data can refer to the previously discarded sample point and the remaining point that is retained. In one example, a low-pass filter can linearly average adjacent sample data, i.e., determine the sum of every 10 points and then divide that sum by 10. In a further example, adjacent data can be weighted with a sinusoidal function. The process of weighting the original waveform with a sinusoidal function is sometimes referred to as an impulse function, or, in the time domain, as convolution.

The present disclosure is applicable not only to digitizing waveform signals based on detected voltages, but also to digitizing waveform signals based on image processing signals, including current waveforms, vibration waveforms, and rasterization of video signals. In one example, the resizing of a window on a computer screen may be decimated, albeit in at least two directions. In these further examples, it will be appreciated that undersampling, per se, may be shown to be insufficient. Thus, oversampling or upsampling, per se, may likewise be shown to be insufficient, and, like decimation, interpolation may be used in place of undersampling per se.

It will be understood in light of this disclosure that interpolation in this context can refer to first applying a low-pass filter to digitally sampled waveform data and then upsampling the waveform data. It will be understood in light of this disclosure that real-world examples may often require the use of non-integer factors for decimation, interpolation, or both. As such, this disclosure includes sequential interpolation and decimation to achieve non-integer factor ratios for interpolation and decimation. In one example, sequential interpolation and decimation may define applying a low-pass filter to the sample waveform, then interpolating the waveform after the low-pass filter, and then decimating the waveform after the interpolation. In embodiments, vibration data can be looped to intentionally emulate a traditional tape recorder loop, and digital filtering techniques can be used for efficient splicing to facilitate longer analysis. It will be understood in light of this disclosure that the above techniques do not preclude waveforms, spectra, and other types of analysis from being processed and displayed in a user GUI as they are collected. It will be appreciated in light of this disclosure that newer systems may enable this function to be performed in parallel with high performance collection of raw waveform data.

Regarding the issue of collection time, older systems use a compromised approach of improving data resolution by collecting at different sampling rates and data lengths, which can actually save as much time as expected. This results in latency issues every time the data collection hardware is stopped and started, especially if the hardware is auto-scaling. The same goes for data retrieval of route information (test locations), which is often in database format and can take a very long time. Also, saving raw data in bursts to disk (solid state or not) can be undesirably slow.

In contrast, many embodiments, as disclosed herein, involve digitally streaming the waveform data 2010, further benefiting from the need to load path parameter information only once while configuring the data collection hardware. Because the waveform data 2010 is streamed to only one file, there is no need to open and close files or switch between read and write operations on storage media. Collecting and saving waveform data 2010 as described herein can be shown to produce relatively meaningful data in significantly less time than traditional batch data collection approaches. An example of this is an electric motor. For electric motors, waveform data can be collected at a data length of 4K points (i.e., 4096) with a sufficiently high resolution, especially to distinguish electrical sideband frequencies. For fans and blowers, a resolution as low as IK (1,024) can be used. In some cases, IK may be the minimum waveform data length requirement. The sampling rate is 1,280 Hz, which corresponds to an Fmax of 500 Hz. The time to acquire this waveform data is 1,024 points at 1,280 Hz, or 800 milliseconds, which satisfies the 2x oversampling required by the Nyquist criterion.

To improve accuracy, waveform data can be averaged. Eight averages can be used, for example, with 50% overlap. This extends the time from 800 ms to 3.6 seconds: 800 ms x 8 averages x 0.5 (overlap) + 0.5 x 800 ms (non-overlapping head and tail ends). After collecting waveform data at Fmax = 500 Hz, a higher sampling rate can be used. In one example, ten times the previous sampling rate (lOx) can be used, resulting in Fmax = 10 kHz. In this example, eight averages can be used with 50% overlap to collect waveform data at this higher rate, resulting in a collection time of 360 ms, or 0.36 seconds. It will be appreciated that, in accordance with this disclosure, it may be necessary to read the hardware collection parameters for the higher sampling rate from the route list and perform hardware autoscaling and/or resetting other necessary hardware collection parameters. This can add a few seconds of latency to accommodate the change in sampling rate. In another example, the latency can accommodate hardware autoscaling and changes to hardware acquisition parameters that may be necessary when using the lower sampling rates disclosed herein. In addition to accommodating the sample rate change, additional time is required to read route point information from the database (i.e., where to monitor, where to monitor next), display the route information, and process the waveform data. Furthermore, displaying the waveform data and/or associated spectra also consumes significant time. Consequently, approximately 15 to 20 seconds is required to acquire waveform data at each measurement point.

In further examples, additional sampling rates can be added, potentially extending the total time for a vibration survey due to the additional time required to switch from one sampling rate to another and to acquire additional data at different sampling rates. In some examples, lower sampling rates are used. For example, if Fmax = 50 Hz, a 128 Hz sampling rate is used. In this example, acquiring the initial average data at this sampling rate requires an additional 36 seconds, in addition to the other data previously described, thereby significantly increasing the total time at each measurement point. Furthermore, this embodiment allows for the use of gap-free digital streaming of waveform data as disclosed herein for wind turbines and other machines with relatively slow rotating or vibrating systems. In many examples, the collected waveform data can include long samples of data at relatively high sampling rates. In one example, the sampling rate can be 100 kHz, and the sampling time can be two minutes for all channels being recorded. In many examples, one channel can be for a single-axis reference sensor, and three additional data channels can be for a three-axis, three-channel sensor. It will be appreciated in light of the present disclosure that longer data lengths can prove to facilitate the detection of extremely low-frequency phenomena. Long data lengths can also accommodate the inherent speed variations in wind turbine operation. Furthermore, long data lengths provide the opportunity to use multiple averages as described herein to achieve very high spectral resolution, demonstrating that tape loops for specific spectral analysis can be feasible. Many advanced analysis techniques are now available because they can use the long, uninterrupted lengths of waveform data available in accordance with the present disclosure.

It will also be appreciated in light of the present disclosure that collecting waveform data from multiple channels simultaneously facilitates performing transfer functions between the multiple channels. Furthermore, collecting waveform data from multiple channels simultaneously facilitates establishing phase relationships across the machine, allowing for more sophisticated correlations to be utilized by relying on the fact that waveforms from each channel are collected simultaneously. In another example, increasing the number of channels of data collection allows waveform data from multiple sensors to be acquired simultaneously, thereby reducing the time it takes to complete an entire vibration survey, rather than having to move from sensor to sensor during the vibration survey.

This disclosure includes using at least one single-axis reference probe in one of the channels to enable relative phase comparison between channels. The reference probe can be an accelerometer or other type of transducer that does not move during a vibration study of a machine and is therefore fixed in a fixed position. Multiple reference probes can be deployed in suitable locations, each fixed in a predetermined location (i.e., in a fixed location) during vibration data acquisition during a vibration study. In a specific example, up to seven reference probes can be deployed depending on the capacity of the data acquisition module 2160. Transfer function or similar techniques can be used to compare the relative phase of all channels to each other at all selected frequencies. By keeping one or more reference probes fixed in a fixed position and moving or monitoring other triaxial vibration sensors, it has been shown that the entire machine can be mapped in terms of amplitude and relative phase. This is true even when the number of measurement points is greater than the number of data acquisition channels. This information allows the creation of operational deflection profiles that can show the dynamic movement of the machine in 3D, making it an invaluable diagnostic tool. In embodiments, one or more reference probes may provide relative phase rather than absolute phase. In light of the present disclosure, it will be appreciated that while relative phase may be less valuable than absolute phase for some purposes, relative phase information may still prove very useful.

In embodiments, the sampling rate used during a vibration study can be digitally synchronized to a predetermined operating frequency that can be related to an appropriate parameter of the machine, such as rotation or vibration speed. This allows for even more information to be extracted using synchronous averaging techniques. It will be appreciated in light of the present disclosure that this can be done without the use of key phases or reference pulses from the rotating shaft. In this manner, asynchronous signals can be removed from a complex signal without the need to deploy synchronous averaging using key phases. This can prove very useful when analyzing a specific pinion in a gearbox or when applied to every component within a complex mechanical mechanism. Often, key phases or reference pulses are rarely available in route-collected data, but the techniques disclosed herein can overcome this absence. In embodiments, there can be multiple shafts operating at different speeds within the machine being analyzed. In some embodiments, there can be a single-axis reference probe on each axis. In other examples, it is possible to relate the phase of one shaft to another shaft using only one single-axis reference probe on one shaft at its constant position. In embodiments, variable-speed equipment can be more easily analyzed with relatively long data durations compared to single-speed equipment. Vibration studies can be performed at several machine speeds within the same continuous set of vibration data using the same techniques disclosed herein. These techniques also allow for the investigation of changes in the relationship between vibration and speed changes that were previously unavailable.

In embodiments, because raw waveform data can be captured in a gap-free digital format as disclosed herein, numerous analysis techniques arise. The gap-free digital format can facilitate numerous avenues for post-hoc analysis of the waveform data in numerous ways to identify specific problems. Vibration data collected in accordance with the techniques disclosed herein can provide analysis of transient, semi-periodic, and infrasonic phenomena. Waveform data acquired in accordance with the present disclosure can include a relatively long stream of raw, gap-free waveform data that can be conveniently replayed as needed, upon which many different sophisticated analysis techniques can be performed. Many such techniques can provide various forms of filtering to extract low-amplitude modulations from the transient impulse data that can be contained in the relatively long stream of raw, gap-free waveform data. It will be appreciated in light of the present disclosure that in past data collection methods, these types of phenomena were typically lost through the averaging process of spectral processing algorithms because the objective of the previous data collection module was purely periodic signals, or through file size reduction methods because much of the content from the original raw signal was discarded, knowing that it would not typically be used.

In one embodiment, there is a method for monitoring vibrations in a machine having at least one shaft supported by a set of bearings. The method includes monitoring a first data channel assigned to a single-axis sensor at a fixed location relative to the machine. The method also includes monitoring second, third, and fourth data channels assigned to a three-axis sensor. The method further includes simultaneously recording gap-free digital waveform data from all data channels during operation of the machine and determining relative phase changes based on the digital waveform data. The method also includes disposing a three-axis sensor at multiple locations relative to the machine while acquiring the digital waveforms. In one embodiment, the second, third, and fourth channels are jointly assigned to a set of three-axis sensors, each disposed at a different location relative to the machine. In one embodiment, data is received simultaneously on all channels from all sensors.

The method also includes determining an operational deflection shape based on the change in relative phase information and the waveform data. In an embodiment, the invariant position of the reference sensor is a position relative to the shaft of the machine. In an embodiment, each of the three-axis sensors in the sequence of three-axis sensors is located at a different location and is associated with a different bearing of the machine. In an embodiment, the invariant position is a position relative to the shaft of the machine, where each of the three-axis sensors in the sequence of three-axis sensors is located at a different location and is associated with a different bearing supporting the shaft within the machine. Various embodiments include a method for simultaneously sequentially monitoring vibration or similar process parameters and signals of a rotating or vibrating machine or similar process machine from multiple channels, which may be known as an ensemble. In various examples, an ensemble may include one to eight channels. In a further example, an ensemble may represent a logical grouping of measurements on the equipment being monitored, regardless of whether the measurement locations are temporary for the measurement, provided by the original equipment manufacturer, retrofitted at a later date, or one or more combinations thereof.

In one example, the ensemble can monitor bearing vibration in a single direction. In a further example, the ensemble can monitor three different directions (e.g., orthogonal directions) using a three-axis sensor. In yet another example, the ensemble can monitor four or more channels, with a first channel monitoring a single-axis vibration sensor and second, third, and fourth channels monitoring each of the three directions of the three-axis sensor. In another example, the ensemble can be fixed to a group of adjacent bearings on the same equipment or associated shafts. Various embodiments provide a method including a strategy for collecting waveform data from various ensembles deployed, such as for a vibration study, in a relatively efficient manner. The method also includes simultaneously monitoring a reference channel assigned to a constant reference location associated with the ensemble monitoring the machine. Coordination with the reference channel can be shown to support more complete correlation of waveforms collected from the ensembles. The reference sensor on the reference channel can be a single-axis vibration sensor or a phased reference sensor that can be triggered at a reference location, such as a rotating shaft. As disclosed herein, the method can further include simultaneously recording gap-free digital waveform data from all channels of each ensemble, thereby allowing recording at a relatively high sampling rate to include all frequencies deemed necessary for proper analysis of the monitored machine during operation. Data from the ensembles can be streamed gap-free to a storage medium connectable to a cloud network facility, a local data link, a Bluetooth connection, a cellular data connection, etc., for subsequent processing.

In embodiments, the methods disclosed herein include strategies for collecting data from various ensembles, including digital signal processing techniques that can be subsequently applied to the data from the ensembles to highlight or better isolate specific frequencies or waveform phenomena. This contrasts with current methods that collect multiple data sets at different sampling rates or use different hardware filtering configurations, including integration, which, due to their commitment to these configurations (known as a priori hardware configurations), offer relatively little flexibility in post-processing. These same hardware configurations have also been shown to increase vibration investigation times due to latency delays associated with configuring the hardware for each independent test. In embodiments, the methods for collecting data from various ensembles include data marker techniques that can be used to classify sections of stream data as homogeneous and belonging to a specific ensemble. In one example, classification can be defined as operating speed. This allows for the creation of multiple ensembles, where conventional systems could only collect one ensemble. Many embodiments also include post-processing analysis techniques for comparing the relative phase of all frequencies of interest not only between each channel in the collected ensemble, but also, when applicable, across all channels in the ensemble being monitored.

The present disclosure may include markers that can be applied to time marks or sample lengths within raw waveform data. Markers generally fall into two categories: preset or dynamic. Preset markers can be correlated to preset or existing operating conditions (e.g., load, head pressure, airflow cubic feet per minute, ambient temperature, RPM, etc.). These preset markers can be entered directly into a data acquisition system. In certain examples, preset markers can be collected in a data channel in parallel with waveform data (e.g., vibration, current, voltage, etc.). Preset marker values can also be entered manually.

For dynamic markers such as trend data, it may be important to compare similar data, such as vibration amplitude or pattern, across a repeatable set of operating parameters. One example in this disclosure includes one parallel channel input being a key phasor trigger pulse from a moving shaft, which can provide RPM information at the instantaneous time of collection. In this example dynamic marker, a section of the collected waveform data displays the appropriate speed or speed range.

The present disclosure may also include dynamic markers that can be correlated to data obtained from post-processing and analysis performed on sampled waveforms. In further embodiments, the dynamic markers may also be correlated to post-collection derived parameters, including RPM, as well as other operationally derived metrics, such as alarm conditions, such as maximum RPM. In a specific example, many modern devices that are candidates for vibration investigations using the portable data collection systems described herein do not include tachometer information. This is because, although measuring rotational speed is important for vibration investigations and analysis, adding a tachometer is not always practical or cost-justified. For fixed-speed machines, it will be appreciated that obtaining an accurate RPM measurement is less important, especially if the machine's approximate speed can be determined in advance. In light of the present disclosure, it will also be appreciated that various signal processing techniques allow RPM to be derived from raw data without the need for a dedicated tachometer signal.

In many embodiments, RPM information can be used to mark segments of raw waveform data over its collection history. Additionally, embodiments include techniques for collecting equipment data along a predetermined route in a vibration study. Dynamic markers allow analysis and trending software to utilize multiple segments of the collection interval (e.g., 2 minutes) indicated by the markers as multiple historical collection ensembles. This can be extended to any other operating parameter, such as load setting or ambient temperature, as previously mentioned. However, placing dynamic markers in an index file that points to a raw data stream allows for the classification of portions of the stream into homogenous entities, facilitating comparison with previously collected portions of the raw data stream.

Many embodiments include a hybrid relational metadata-binary storage approach that can use the best of existing technology for both relational and raw data streams. In embodiments, the hybrid relational metadata-binary storage approach can combine them using various marker linkages. Marker links enable: This enables many features not possible with traditional database technologies. This means that many features, integrations, compatibility, and extensibility not available with traditional database technologies are available.

MarkerLink can also store raw data quickly and efficiently using traditional binary storage and data compression techniques. This can be shown to take advantage of many of the features, integration, compatibility, and extensions offered by traditional raw data technologies, such as TMDS (National Instruments) and UFF (Universal File Format, such as UFF58). Furthermore, MarkerLink can be used to collect large, rich datasets from ensembles in the same collection time as traditional systems. Rich datasets from ensembles can store data snapshots associated with predetermined collection criteria, and the proposed system can utilize Marker technology to derive multiple snapshots from collected data streams. This can be shown to enable relatively rich analysis of collected data. One such advantage could include many more trend points of vibrations at specific frequencies or in the order of running speed vs. RPM, load, operating temperature, flow rate, etc., that can be collected in a similar amount of time compared to the time spent collecting data with traditional systems.

In an embodiment, the platform 100 may include a local data collection system 102 deployed in the environment 104 to monitor signals from machinery, elements of machinery, and the environment of machinery, including heavy machinery deployed at a local job site or distributed job sites under common control. Heavy industrial machinery may include earthmoving machinery, heavy industrial on-road industrial vehicles, heavy industrial off-road industrial vehicles, turbines, turbomachinery, generators, pumps, pulley systems, manifolds, and valve systems deployed in various settings, and the like. In an embodiment, heavy industrial machinery may also include earthmoving equipment, earth compaction equipment, transporting equipment, conveying equipment, aggregate manufacturing equipment, equipment used in concrete construction, and piling equipment. In examples, earthmoving equipment may include excavators, backhoes, loaders, bulldozers, skid steer loaders, trenchers, motor graders, motor scrapers, crawler loaders, and wheeled loading shovels. In examples, construction vehicles may include dump trucks, tankers, tippers, and trailers. In examples, material handling equipment may include cranes, conveyors, forklifts, and hoists. In examples, construction machinery may include tunneling and handling equipment, road rollers, concrete mixers, hot mix plants, road compactors, stone crushers, pavers, slurry sealers, spraying and plastering machines, and heavy industrial pumps. Further examples of heavy industrial equipment may include different systems, such as implement traction, structure, powertrain, control, and information. Heavy industrial equipment may include many different powertrains and combinations thereof to provide power for movement and to power accessories and onboard functionality. In each of these examples, the platform 100 deploys a local data collection system 102 in the environment 104 in which these machines, motors, pumps, etc. operate, which may be integrated and directly connected to each of the machines, motors, pumps, etc.

In an embodiment, the platform 100 may include a local data acquisition system 102 deployed in the environment 104 to monitor signals from operating machinery and machinery under construction, such as turbines and generator sets, such as Siemens SGT6-5000F gas turbines, SST-900 steam turbines, SGen6-1000A generators, and SGen6-100A generators. In an embodiment, the local data acquisition system 102 may be deployed to monitor a steam turbine rotating in an electrical current driven by high-temperature steam that may be directed through the turbine or otherwise originating from different sources, such as gas-fired burners, cores, or molten salt loops. In these systems, the local data acquisition system 102 may monitor the turbine and water or other fluid in a closed-loop cycle in which the water condenses and is then heated until it evaporates again. The local data acquisition system 102 may monitor the steam turbine separately from a fuel source deployed to heat the water to steam. In an example, the operating temperature of the steam turbine may be between 500 and 650°C. In many embodiments, an array of steam turbines may be arranged and configured for high, intermediate, and low pressures, thereby optimally converting each steam pressure into rotary motion.

The local data acquisition system 102 may also be deployed in a gas turbine configuration, thus monitoring not only the operating turbine, but also the supply of hot combustion gases to the turbine, which can exceed 1,500°C. Because these gases are much hotter than those of a steam turbine, the blades may be cooled with air that may escape through small openings to form a protective film or boundary layer between the exhaust gases and the blades. This temperature profile may be monitored by the local data acquisition system 102. Unlike a typical steam turbine, a gas turbine engine includes a compressor, a combustion chamber, and a turbine, all of which are journaled for rotation on a rotating shaft. The structure and operation of each of these components may be monitored by the local data acquisition system 102.

In an embodiment, the platform 100 may include a local data collection system 102 deployed in the environment 104 to monitor signals from a water turbine, which functions as a rotary engine that harvests energy from moving water and potentially uses it to generate electricity. The type of water turbine or hydroelectric plant selected for a project may be based on the height of standing water, often referred to as head, and the flow (or volume of water) at the site. In this example, a generator is installed at the end of a shaft that connects to the water turbine. As the water turbine rotates, its blades engage the naturally moving water, sending rotational power to the generator, generating electrical energy. In doing so, the platform 100 may monitor signals from the generator, turbine, local water systems, and flow control devices such as dam windows and gates. Additionally, the platform 100 may monitor local conditions on the electrical grid, including load, predicted demand, frequency response, etc., and include such information in the monitoring and control deployed by the platform 100 in these hydroelectric settings.

In embodiments, platform 100 may include a local data collection system 102 deployed in environment 104 to monitor signals from energy-producing environments, such as thermal, nuclear, geothermal, chemical, biomass, carbon-based fuel, and hybrid-renewable energy plants. Many of these plants may use multiple forms of energy harvesting equipment, such as wind turbines, hydroelectric turbines, and steam turbines powered by heat from nuclear, gas-fired, solar, and molten salt sources. In embodiments, elements in such systems may include power lines, heat exchangers, desulfurization scrubbers, pumps, chillers, condensers, and the like. In embodiments, specific implementations of turbomachinery, turbines, scroll compressors, and the like may be configured with arrayed controls to monitor large-scale facilities that create electricity for consumption, provide refrigeration, and create steam for local manufacturing and heating. The arrayed control platform may be provided by industrial equipment providers, such as Honeywell and their Experion PKS platform. In embodiments, platform 100 may specifically communicate with and integrate with local manufacturer-specific controls, enabling equipment from one manufacturer to communicate with other equipment. Additionally, the platform 100 allows the local data collection systems 102 to collect information across systems from many different manufacturers. In an embodiment, the platform 100 may include local data collection systems 102 deployed in the environment 104 to monitor signals from marine industrial equipment, marine diesel engines, shipbuilding, oil and gas plants, refineries, petrochemical plants, ballast water treatment solutions, marine pumps and turbines, etc.

In an embodiment, the platform 100 may include a local data collection system 102 deployed in the environment 104 to monitor signals from heavy industrial equipment and processes, including monitoring one or more sensors. By way of example, a sensor may be a device that can be used to detect or respond to any type of input from the physical environment, such as an electrical, thermal, or optical signal. In an embodiment, the local data collection system 102 may include multiple sensors, such as, but not limited to, a temperature sensor, a pressure sensor, a torque sensor, a flow sensor, a heat sensor, a smoke sensor, an arc sensor, a radiation sensor, a position sensor, an acceleration sensor, a strain sensor, a pressure cycle sensor, a pressure sensor, and an air temperature sensor. The torque sensor may include a magnetic torsion angle sensor. In one example, the torque and speed sensors of the local data collection system 102 may be similar to those discussed in U.S. Patent No. 8,352,149 to Meachem, issued January 8, 2013, and incorporated by reference as if fully set forth herein. In embodiments, one or more sensors may be provided, such as a tactile sensor, a biosensor, a chemical sensor, an image sensor, a humidity sensor, an inertial sensor, etc.

In an embodiment, the platform 100 may include a local data collection system 102 deployed in the environment 104 to monitor signals from sensors that may provide signals for fault detection, including excessive vibration, improper materials, improper material properties, improper size, improper shape, improper weight, and improper balance. Additionally, there may be sensors for inventory control, inspection to ensure parts are packaged as planned, that parts are within tolerances, and to identify packaging damage or stress, as well as sensors indicating impact or damage during shipping. Additional fault sensors may also be used to detect lack of lubrication, over-lubrication, the need to clean a sensor window, the need for maintenance due to lack of lubrication, and the need for maintenance due to blockage or reduction in flow in a lubricated area.

In an embodiment, platform 100 may include a local data acquisition system 102 deployed in environment 104, including aircraft operations and manufacturing, to monitor signals from special-purpose sensors, such as gyroscopes, accelerometers, and magnetometers, such as sensors used in aircraft attitude and heading reference systems (AHRS). In an embodiment, platform 100 may include a local data acquisition system 102 deployed in environment 104 to monitor signals from image sensors, such as semiconductor charge-coupled devices (CCDs) with complementary metal-oxide semiconductor (CMOS) or negative-type metal-oxide semiconductor (NMOS, Live MOS) technology, active pixel sensors, and the like. In an embodiment, platform 100 may include a local data acquisition system 102 deployed in environment 104 to monitor signals from sensors, such as infrared (IR) sensors, ultraviolet (UV) sensors, touch sensors, and proximity sensors. In an embodiment, the platform 100 may include a local data collection system 102 deployed in the environment 104 to monitor signals from sensors configured for optical character recognition (OCR), barcode reading, surface acoustic wave detection, transponder detection, communication with home automation systems, medical diagnostics, health monitoring, etc.

In an embodiment, the platform 100 may include a local data acquisition system 102 deployed in the environment 104 to monitor signals from sensors such as a Micro-Electro-Mechanical Systems (MEMS) sensor, such as ST Microelectronic's LSM303AH smart MEMS sensor, which includes an ultra-low-power, high-performance system-in-package featuring a 3D digital linear acceleration sensor and a 3D digital magnetic sensor.

In an embodiment, the platform 100 may include a local data collection system 102 deployed in the environment 104 to monitor signals from additional large machines, such as turbines, windmills, industrial vehicles, and robots. These large machines include multiple components and elements that provide multiple subsystems for each machine. To that end, the platform 100 may include a local data collection system 102 deployed in the environment 104 to monitor signals from individual elements, such as axles, bearings, belts, buckets, gears, shafts, gearboxes, cams, carriages, camshafts, clutches, brakes, drums, dynamos, feeds, flywheels, gaskets, pumps, jaws, robotic arms, seals, sockets, sleeves, valves, wheels, actuators, motors, and servomotors. Many of the machines and their elements may include servomotors. The local data collection system 102 may monitor the motors, rotary encoders, and potentiometers of servomechanisms to provide three-dimensional details of the position, location, and progress of the industrial process.

In an embodiment, the platform 100 may include a local data collection system 102 deployed in the environment 104 to monitor signals from gear drives, powertrains, transfer cases, multi-speed axles, transmissions, direct drives, chain drives, belt drives, shaft drives, magnetic drives, and similar intermeshing mechanical drives. In an embodiment, the platform 100 may include a local data collection system 102 deployed in the environment 104 to monitor signals from fault conditions in industrial machinery, including overheating, noise, gear grinding, locked gears, excessive vibration, wobble, under-inflation, over-inflation, and the like. Maintenance and operational issues can arise during operation, installation, and maintenance due to malfunctions, maintenance indicators, and interactions with other machinery. Defects can occur in the machinery of the industrial machinery, but also in the infrastructure supporting the machinery, such as its wiring or the local installation platform. In an embodiment, large industrial machinery can experience various types of fault conditions, including overheating, noise, gear grinding, excessive vibration in machine parts, fan vibration issues, and problems with rotating parts of large industrial machinery.

In an embodiment, the platform 100 includes a local data collection system 102 deployed in the environment 104 to monitor signals from industrial machinery, including premature bearing failures that may occur due to contamination or loss of bearing lubricant. In another example, mechanical defects such as bearing misalignment may occur. Many factors can contribute to failures such as metal fatigue, and therefore the local data collection system 102 may monitor cycles and local stresses. By way of example, the platform 100 may monitor for improper operation of machine components, lack of maintenance and servicing of components, corrosion of critical machine components such as couplings or gearboxes, misalignment of machine components, and the like. While failures cannot be completely prevented from occurring, many industrial failures can be mitigated, reducing operational and financial losses. The platform 100 provides real-time monitoring and predictive maintenance in many industrial environments, which has been shown to offer cost savings over regularly scheduled maintenance processes that replace parts according to strict time expiration rather than the actual load and wear of the element or machine. To that end, the platform 10 may provide reminders or implement some preventative measures, such as compliance with the machine's operating manual and mode instructions, proper lubrication and maintenance of machine parts, minimizing or eliminating machine overruns beyond defined capacities, replacing worn but still functional parts as needed, and properly training personnel for machine use.

In an embodiment, platform 100 may include a local data collection system 102 deployed in environment 104 to monitor multiple signals, which may be carried in multiple physical, electronic, and symbolic forms or signals. Platform 100 may employ signal processing, which includes multiple mathematical, statistical, computational, heuristic, and linguistic representations and processing of signals and multiple operations necessary to extract useful information from the signal processing operations, such as techniques for representing, modeling, analyzing, synthesizing, sensing, acquiring, and extracting information from signals. In examples, signal processing may be performed using multiple techniques, including, but not limited to, transforms, spectral estimation, statistical operations, probabilistic and stochastic operations, numerical theory analysis, data mining, and the like. Processing of various types of signals forms the basis of many electrical or computational processes. As such, signal processing is applied to nearly every field and application in industrial environments, including audio/video processing, image processing, wireless communications, process control, industrial automation, financial systems, quality enhancements such as feature extraction, noise removal, and image enhancement. Signal processing for images may include pattern recognition for manufacturing inspection, quality inspection, and automated operational inspection and maintenance. Platform 100 may employ many pattern recognition techniques, including those that may classify input data into classes based on key features with the goal of recognizing patterns or regularities in the data. Platform 100 may also implement pattern recognition processing using machine learning operations and may be used in applications such as computer vision, speech and text processing, radar processing, handwriting recognition, and CAD systems. Platform 100 may employ supervised and unsupervised classification. Supervised learning classification algorithms may be used to create classifiers for image or pattern recognition based on training data obtained from different object classes. Unsupervised learning classification algorithms may operate by finding hidden structures in unlabeled data using advanced analytical techniques such as segmentation and clustering. For example, some analytical techniques used in unsupervised learning include K-means clustering, Gaussian mixture models, and hidden Markov models. Algorithms used in supervised and unsupervised pattern recognition enable the use of pattern recognition in a variety of high-precision applications. Platform 100 can use pattern recognition in face detection related applications such as security systems, tracking, sports related applications, fingerprint analysis, medical and forensic related applications, navigation and guidance systems, vehicle tracking, public infrastructure systems such as transportation systems, license plate surveillance, etc.

In embodiments, the platform 100 may include a local data collection system 102 deployed in the environment 104 using machine learning, enabling derivation-based learning results from a computer without the need to program the computer. Thus, the platform 100 may learn and make decisions from a set of data by making data-driven predictions and adapting according to the set of data. In embodiments, the machine learning may include the performance of multiple machine learning tasks by a machine learning system, such as supervised learning, unsupervised learning, and reinforcement learning. Supervised learning may include presenting a machine learning system with a set of example inputs and desired outputs. Unsupervised learning may involve the learning algorithm itself structuring its inputs through methods such as pattern detection and/or feature learning. Reinforcement learning may involve the machine learning system performing in a dynamic environment and then providing feedback regarding correct and incorrect decisions. In embodiments, the machine learning may include multiple other tasks based on the output of the machine learning system. In examples, the tasks may also be categorized as machine learning problems, such as classification, regression, clustering, density estimation, dimensionality reduction, anomaly detection, etc. In embodiments, the machine learning may include multiple mathematical and statistical techniques. In examples, many types of machine learning algorithms may include decision tree-based learning, association rule learning, deep learning, artificial neural networks, genetic learning algorithms, inductive logic programming, support vector machines (SVMs), Bayesian networks, reinforcement learning, representation learning, rule-based machine learning, sparse dictionary learning, similarity and metric learning, learning classifier systems (LCS), logistic regression, random forests, K-means, gradient boosting and Adaboost, K-nearest neighbors (KNN), a priori algorithms, and the like. In embodiments, specific machine learning algorithms may be used, such as genetic algorithms defined to solve both constrained and unconstrained optimization problems that may be based on natural selection, a process that drives biological evolution. By way of example, genetic algorithms may be deployed to solve various optimization problems that are not well suited to standard optimization algorithms, including problems where the objective function is discontinuous, non-differentiable, stochastic, or highly nonlinear. As an example, genetic algorithms may be used to address mixed-integer programming problems, where some components are constrained to be integer-valued. Genetic algorithms and machine learning techniques and systems may be used in computational intelligence systems, computer vision, natural language processing (NLP), recommendation systems, reinforcement learning, graphical model building, and the like. In this example, machine learning systems may be used to perform intelligent computing-based control and response tasks in a wide variety of systems, such as interactive websites and portals, brain-machine interfaces, online security and fraud detection systems, medical applications such as diagnostic and treatment support systems, and DNA sequence classification. In this example, machine learning systems may be used in advanced computing applications, such as online advertising, natural language processing, robotics, search engines, software engineering, speech and handwriting recognition, pattern matching, gameplay, computational anatomy, and bioinformatics systems. As an example, machine learning may also be used in financial and marketing systems, such as user behavior analysis, online advertising, economic forecasting, and financial market analysis.

Additional details are provided below in connection with the methods, systems, devices, and components depicted in connection with FIGS. 1 through 6. In embodiments, methods and systems for cloud-based machine pattern recognition based on the fusion of remote analog industrial sensors are disclosed herein. For example, data streams from vibration, pressure, temperature, accelerometers, magnetic fields, electric fields, and other analog sensors may be multiplexed or otherwise fused, relayed over a network, and fed to a cloud-based machine learning facility, which may employ one or more models of the operating characteristics of the industrial machinery, industrial process, or its components or elements. The models may be created by humans familiar with the industrial environment and associated with a training dataset (e.g., models created by human or machine analysis of data collected by sensors in the environment or other similar environments). The learning machine may then operate on other data, initially using a set of rules or elements of the model, to provide various outputs, such as classifying the data into types, recognizing specific patterns (e.g., those indicating the presence of a fault, or those indicative of operational conditions such as fuel efficiency or energy production), and so on. Machine learning capabilities can receive feedback, such as one or more inputs or measures of success, to train or improve an initial model (e.g., by adjusting weights, rules, parameters, etc., based on the feedback). For example, a model of fuel consumption for an industrial machine might include physics model parameters that characterize factors indicative of consumption, such as weight, motion, resistance, momentum, inertia, and acceleration, as well as chemistry model parameters (e.g., parameters that predict energy produced and/or consumed, such as combustion, chemical reactions in charging and discharging a battery, etc.). The model can be refined by inputting data from sensors located in or within the machine's environment and data indicating actual fuel consumption. The machine can then provide outputs indicating what changes can be made to improve the accuracy of its sensor-based fuel consumption estimates and increase fuel consumption (e.g., by changing machine operating parameters or other elements of the environment, such as ambient temperature or the operation of nearby machines). For example, if resonance between two machines is negatively impacting one of the machines, the model can take this into account and automatically provide an output that would modify the operation of one of the machines (e.g., reducing the resonance and increasing the fuel efficiency of one or both machines). By continually adjusting parameters so that the output matches actual conditions, machine learning capabilities can self-organize and provide highly accurate models of the state of the environment (predicting failures, optimizing operating parameters, etc.). This can be used to improve fuel efficiency, reduce wear, increase power output, increase operating life, avoid fault conditions, and many other purposes.

FIG. 10 illustrates the components and interactions of a data collection architecture that includes the application of cognitive and machine learning systems to data collection and processing. Referring to FIG. 10, a data collection system 102 may be deployed in an environment (e.g., an industrial environment where one or more complex systems, such as electromechanical systems or machines, are manufactured, assembled, or operated). The data collection system 102 may include on-board sensors and may take inputs from one or more sensors (e.g., analog or digital sensors of any type disclosed herein) and from one or more input sources 116 (e.g., sources available via Wi-Fi, Bluetooth, NFC, or other local network connection or via the internet), such as via one or more input interfaces or ports 4008. The sensors may be combined and multiplexed (e.g., by one or more multiplexers 4002). The data may be cached or buffered in cache/buffer 4022 and available via one or more output interfaces and ports 4010 (which, in embodiments, may be separate from or the same as input interfaces and ports 4008) to an external system, such as a remote host processing system 112 as described elsewhere in this disclosure (which may include a broad processing architecture 4024 including any of the elements described throughout this disclosure and in connection with other embodiments illustrated in the figures). Data collection system 102 may be configured to take input from host processing system 112, such as from analysis system 4018, which may operate on data from data collection system 102 and data from other input sources 116 to provide analytical results, which may be provided as learning feedback input 4012 to the data collection system 102, such as to assist in the configuration and operation of data collection system 102.

The combination of inputs (including the selection of which sensors or input sources to turn "on" or "off") may be performed under the control of machine-based intelligence, such as using a local cognitive input selection system 4004, an optional remote cognitive input selection system 4114, or a combination of the two. The cognitive input selection systems 4004, 4014 may use intelligence and machine learning capabilities described elsewhere in this disclosure, such as using state information (including state information determined by a machine state recognition system 4020 capable of determining a state) related to detected conditions (such as conditions signaled by an input source 116 or sensor), operational conditions, environmental conditions, conditions within a known process or workflow, conditions including faults or diagnostic conditions, and the like. This may include optimizing input selection and configuration based on learning feedback from a learning feedback system 4012, which may include providing learning data (such as from the host processing system 112 or from other data collection systems 102 directly or from the host 112) and providing feedback metrics, such as success metrics, calculated within the analysis system 4018 of the host processing system 112. For example, if a data stream consisting of a particular combination of sensors and inputs produces positive results under a given set of conditions (such as providing improved pattern recognition, improved predictions, improved diagnostics, improved yield, improved return on investment, improved efficiency, etc.), metrics related to such results from the analysis system 4018 may be provided to the cognitive input selection system 4004, 4014 via the learning feedback system 4012 to assist in configuring future data collection to select that combination under those conditions (other input sources may be deselected, such as by powering down other sensors). In embodiments, the selection and deselection of sensor combinations under the control of one or more of the cognitive input selection systems 4004 may occur in an automated manner, such as using genetic programming techniques, based on learning feedback 4012, such as from the analytics system 4018, to promote effective combinations for a given state or set of conditions and demote less effective combinations, resulting in progressive optimization and adaptation of the local data collection system to each unique environment. In this manner, an automatically adapting multi-sensor data collection system is provided, in which cognitive input selection (along with feedback) is used to improve the effectiveness, efficiency, or other performance parameters of the data collection system within a particular environment. Performance parameters may relate to overall system metrics (such as financial yield, process optimization results, energy production or use), analytics metrics (such as the success of pattern recognition, predictions, data classification, etc.), and local system metrics (such as bandwidth utilization, storage utilization, power consumption, etc.). In embodiments, the host's analysis system 4018, status system 4020, and cognitive input selection system 4114 may acquire data from multiple data collection systems 102 to enable the coordinated operation of multiple systems 102 to perform optimization (including input selection). For example, the cognitive input selection system 4114 may understand that if one data collection system 102 is already collecting X-axis vibration data, it may turn off the X-axis vibration sensor of the other data collection system in favor of acquiring Y-axis data from the other data collection system. In this manner, through coordinated collection by the host cognitive input selection system 4114, the activity of multiple collectors 102 across different sensor hosts can provide a rich data set to the host processing system 112 without wasting energy, bandwidth, storage space, etc. As described above, optimization may be based on system-wide success metrics, analytical success metrics, local system metrics, or a combination thereof.

Disclosed herein are methods and systems for cloud-based machine pattern analysis of state information from multiple industrial sensors to provide predicted state information for an industrial system. In embodiments, machine learning can utilize a state machine, such as tracking the state of multiple analog and/or digital sensors, feeding the states to a pattern analysis facility, and determining a predicted state of the industrial system based on historical data regarding sequences of state information. For example, if an industrial machine's temperature state exceeds a threshold and a fault condition such as a bearing failure persists, the temperature state can be tracked by a pattern recognizer, which can generate an output data structure (each time the high temperature input state is recognized) indicating a predicted bearing fault state. Various measurements and predicted states can be managed by the state machine, such as temperature, pressure, vibration, acceleration, momentum, inertia, friction, heat, heat flux, galvanic state, magnetic field state, electric field state, capacitance state, charge/discharge state, motion, and position. The states can be organized into linked states, such that the data structure contains a series of states, each represented by a location within the byte-like data structure. For example, an industrial machine may be characterized by a genetic structure that provides pressure, temperature, vibration, and acoustic data. These measurements occupy a single location in a data structure, and the combined state can be manipulated as a byte-like structure, such as a structure for compactly characterizing the current combined state of the machine or environment, or a structure for compactly characterizing the expected state. For example, a structure for compactly representing the combined state of the current machine or environment, or a structure for compactly representing the expected state. Such byte-like structures can be utilized in state machines for machine learning. Such structures can be tracked and used in a wide variety of machine learning applications, representing various combinations of different lengths of various elements that can be sensed in an industrial environment. In embodiments, the byte-like structures can be used in genetic programming techniques. For example, by substituting different types of data, or data from various sources, and tracking the results over time, one or more advantageous structures can emerge, indicating successful prediction of expected states, or based on the structure's success when used in real-world situations, such as improved efficiency, successful routing of information, or achieving increased profits. That is, by varying the data types and sources used in the byte-like structures used for machine optimization over time, a genetic programming-based machine learning facility can "evolve" a set of data structures comprised of a preferred combination of data types (e.g., pressure, temperature, vibration) for a given purpose from a preferred combination of data sources (e.g., temperature from sensor X and vibration from sensor Y). For different desired outcomes, applying machine learning and promoting structures with favorable outcomes through genetic programming can result in different data structures over time that are best adapted to support the effective achievement of those outcomes. The promoted data structures may provide compact and efficient data for various activities, such as those described throughout this disclosure, including being stored in a data pool (which may be optimized by storing favorable data structures that provide the best operational results for a given environment), being presented in a data marketplace (e.g., being presented as the most effective structure for a given purpose), and so forth.

In an embodiment, a platform is provided with cloud-based machine pattern analysis of state information from multiple analog industrial sensors to provide predicted state information for an industrial system. In an embodiment, a host processing system 112, such as one located in the cloud, may include a state system 4020, which may be used to infer or calculate current states or determine predicted future states related to some aspect of the data collection system 102 or the environment in which the data collection system 102 is located, such as the state of a machine, component, workflow, process, event (e.g., whether an event has occurred), object, person, condition, function, etc. Maintaining the state information enables the host processing system 112 to perform analysis, such as with one or more analysis systems 4018, determine contextual information, apply semantic and conditional logic, and perform many other functions enabled by the processing architecture 4024 described throughout this disclosure.

In an embodiment, a platform with a cloud-based policy automation engine for IoT is provided, involving the creation, deployment, and management of IoT devices. In an embodiment, the platform 100 includes (or is integrated with or includes) a policy automation engine 4032 on a host processing system 112, such as on a cloud platform, for automating the creation, deployment, and management of policies for IoT devices. Policies, which may include access policies, network usage policies, storage usage policies, bandwidth usage policies, device connection policies, security policies, rule-based policies, role-based policies, and others, may be required to manage the use of IoT devices. For example, because IoT devices may have many different network and data communications with other devices, policies may be required that dictate which devices a given device can connect to, pass data to, and receive data from. With billions of devices with countless potential connections expected to be deployed in the near future, it will be impossible for humans to configure policies for IoT devices for each connection. Therefore, the intelligent policy automation engine 4032 may include cognitive capabilities for creating, configuring, and managing policies. The policy automation engine 4032 may consume information about possible policies, such as from a policy database or library, which may include one or more public sources of available policies. These may be written in one or more conventional policy languages or scripts. The policy automation engine 4032 may apply policies according to one or more models, such as based on characteristics of a given device, machine, or environment. For example, a large machine, such as a power generation machine, may include a policy that only a verifiable local controller can change certain power generation parameters, thereby preventing remote "takeover" by a hacker. This may in turn be achieved by automatically discovering and applying a security policy that prohibits the machine's control infrastructure from connecting to the Internet, such as by requiring access authentication. The policy automation engine 4032 may also include cognitive capabilities (e.g., capabilities based on state information from the state system 4020) to change policy application, policy configuration, etc. The policy automation engine 4032 may receive feedback, such as from the learning feedback system 4012, based on one or more analysis results from the analysis system 4018, based on system-wide results (e.g., security violations, degree of policy violations), local results, analysis results, etc. Such feedback-based variation and selection can enable the policy automation engine 4032, over time, to automatically create, deploy, configure, and manage policies across large numbers of devices, such as managing policies for configuring connections between IoT devices.

Disclosed herein are methods and systems for on-device sensor fusion and data storage for industrial IoT devices, where data from multiple sensors is multiplexed on the device for storage of a fused data stream. For example, pressure and temperature data may be multiplexed into a combined pressure and temperature data stream in a time series, e.g., a byte-like structure (time, pressure, and temperature are bytes in the data structure, so that pressure and temperature remain linked in time and the streams do not need to be processed separately by an external system), or by addition, division, multiplication, subtraction, etc., allowing the fused data to be stored on the device. Any of the sensor data types described throughout this disclosure can be fused in this manner and stored in a local data pool, storage, or data collector, machine component, or other IoT device.

In an embodiment, a platform with on-device sensor fusion and data storage for industrial IoT devices is provided. In an embodiment, a cognitive system is used for the self-organizing storage system 4028 for the data collection system 102. Sensor data, particularly analog sensor data, can consume a large amount of storage capacity, especially if the data collection device 102 has multiple sensor inputs onboard or from the local environment. Simply storing all data indefinitely is typically not a desirable option, and even transmitting all data can strain bandwidth limitations or exceed bandwidth allowances (e.g., exceeding a cellular data plan's capacity). Therefore, a storage strategy is required. For example, capturing only a portion of the data (e.g., snapshots), storing data for a limited period of time, or storing a portion of the data (e.g., in an intermediate or abstracted format). With many choices available from these and other options, determining the correct storage strategy can be very complex. In embodiments, the self-organizing storage system 4028 may use various metrics, e.g., system-wide metrics, analytical metrics, and local performance indicators, from the analysis system 4018 or other systems in the host cognitive input selection system 4114 based on the learning feedback 4012. The self-organizing storage system 4028 may automatically vary storage parameters such as storage location (including local storage on the data collection system 102, storage on a nearby data collection system 102 (e.g., using a peer-to-peer organization), or remote storage such as network-based storage), storage amount, storage duration, type of data being stored (including not only individual sensors or input sources 116 but also various combined or multiplexed data such as selected under the cognitive input selection system 4004, 4014), storage type (e.g., using RAM, Flash, or other short-term memory vs. available hard drive space), storage organization (raw form, hierarchical, etc.), etc. The variation of parameters may be done with feedback so that over time the data collection system 102 adapts its data storage to optimize itself to the conditions of the environment, such as a particular industrial environment, so that the required amount and type of data is stored and made available to the user.

In embodiments, the local cognitive input selection system 4004 may organize a fusion of data from various on-board sensors, external sensors (such as those of the local environment), and other input sources 116 for the local collection system 102 into one or more fused data streams, such as using a multiplexer 4002 to create various signals representing combinations, permutations, blends, layers, abstractions, data-metadata combinations, etc. of the source analog and/or digital data handled by the data collection system 102. The selection of a particular fusion of sensors may be determined locally by the cognitive input selection system 4004 based on learning feedback from the learning feedback system 4012, such as various overall system, analysis system, and local system results and metrics. In embodiments, the system may learn to fuse particular combinations and permutations of sensors, such as to best achieve correct prediction of states, as indicated by feedback from the analysis system 4018 regarding its ability to predict future states, such as various states handled by the state system 4020. For example, the input selection system 4004 may indicate a selection of a subset of sensors within a larger set of available sensors, and the inputs from the selected sensors may be combined by placing the input from each into bytes of a defined multi-bit data structure (e.g., combining by taking a signal from each at a predetermined sampling rate or time, placing the result into a byte structure, and then collecting and processing the bytes over time), or by multiplexing with a multiplexer 4002 (e.g., combining by additive mixing of successive signals). Any of a wide range of signal processing and data processing techniques for combining and fusing may be used, including convolution techniques, forcing techniques, transformation techniques, and the like. The particular fusion may be adapted to a given situation by cognitive learning, such as having the cognitive input selection system 4004 learn based on feedback 4012 from results (e.g., feedback conveyed by the analysis system 4018) so that the local data collection system 102 performs situation-adaptive sensor fusion.

In embodiments, the analysis system 4018 may employ statistical and econometric techniques (e.g., linear regression analysis, similarity matrix analysis, heat map-based techniques), inference techniques (e.g., Bayesian inference, rule-based inference, inductive inference), iterative techniques (e.g., feedback, recursion, feedforward, etc.), signal processing techniques (e.g., Fourier transforms), pattern recognition techniques (e.g., Kalman filtering), search techniques, probabilistic techniques (e.g., random walks, random forest algorithms), simulation techniques (e.g., random walks, random forest algorithms, linear optimization), etc. This may include the calculation of various statistics or metrics. In embodiments, the analysis system 4018 may be located, at least in part, on the data collection system 102, such that the local analysis system can calculate one or more metrics, such as those related to any of the topics noted throughout this disclosure. For example, measures of efficiency, power usage, storage usage, redundancy, entropy, and other factors may be calculated on-board, such that the data collection 102 enables the various cognitive and learning functions noted throughout this disclosure without relying on a remote (e.g., cloud-based) analysis system.

In an embodiment, the host processing system 112, the data collection system 102, or both may include, connect to, or integrate with a self-organizing networking system 4020, which may include a cognitive system for providing machine-based, intelligent, or orchestrated network utilization for transport of data in the data collection systems, such as for processing analog and other sensor data or other source data, such as between one or more local data collection systems 102 and the host system 112. This may include orchestration of network utilization for source data delivered to the data collection systems, feedback data such as analytical data provided to or via the learning feedback system 4012, data to support a market (as described in connection with other embodiments), and output data provided from one or more data collection systems 102 via output interfaces and ports 4010.

Disclosed herein are methods and systems for a self-organizing data marketplace for industrial IoT data, where available data elements are organized in a marketplace for consumer consumption based on feedback from training a self-organizing facility with a training set and measures of marketplace success. The marketplace may initially make available data collected from one or more industrial environments, such as presenting the data by type, source, environment, machine, one or more patterns (e.g., presenting it in a menu or hierarchy). The marketplace may vary the data collected, the organization of the data, the presentation of the data (including pushing the data to external sites, providing links, setting up APIs through which the data can be accessed), the pricing of the data, etc., under machine learning that varies any of the aforementioned different parameters. The machine learning functionality can self-organize and manage all of these parameters, for example, varying parameters over time (including varying elements of the data types presented), the data sources used to obtain each type of data, the data structure presented (e.g., byte-like structures, fused or multiplexed structures (e.g., representing multiple sensor types), etc.). These include pricing of the data, where the data is displayed, how the data is displayed (e.g., via API, link, push message), how the data is stored, and how the data is retrieved. Varying parameters provides feedback on success measures, such as number of views, yield per access (e.g., price paid), total yield, profit per unit, and total profit. Self-organizing machine learning promotes configurations that improve the success measures and demotes configurations that do not. Over time, the marketplace is gradually configured to present advantageous combinations of data types (e.g., those that provide robust predictions of expected conditions for a particular industrial environment of a given type) from advantageous sources (e.g., reliable, accurate, and low-priced) at effective pricing (e.g., pricing that tends to provide a high total profit from the marketplace). The marketplace may include spiders, web crawlers, etc., that seek input data sources, such as finding data pools, connected IoT devices, etc., that expose potentially relevant data. These may be trained by human users and improved by machine learning in a manner similar to that described elsewhere in this disclosure.

In an embodiment, a platform having a self-organizing data marketplace for industrial IoT data is provided. Referring to FIG. 11 , in an embodiment, a platform having a cognitive data marketplace 4102, sometimes referred to as a self-organizing data marketplace, is provided for data collected by one or more data collection systems 102 or data from other sensors or input sources 116 located in various data collection environments, such as industrial environments. In addition to data collection systems 102, data may include data collected, processed, or exchanged by IoT devices such as cameras, monitors, embedded sensors, mobile devices, diagnostic equipment and systems, instrumentation systems, telematics systems, etc., for monitoring various parameters and functions of machines, equipment, components, parts, operations, functions, conditions, states, events, workflows, and other elements (collectively encompassed by the term “state”) of such environments. The data may include metadata related to any of the foregoing, for example, describing the data, indicating provenance, indicating elements related to identity, access, roles, and permissions, providing a summary or abstraction of the data, or enriching one or more items of data to enable further processing, such as for data extraction, transformation, loading, and processing. Such data (a term that includes metadata unless the context requires otherwise) can be highly valuable to third parties, either individually (e.g., data about the state of an environment can be used as a condition in a process) or collectively (e.g., data collected arbitrarily from many systems and devices in different environments can be used to develop behavioral models, train learning systems, etc.). With the introduction of billions of IoT devices and countless connections, the amount of available data will explode. To enable data access and utilization, the cognitive data marketplace 4102 enables various components, features, services, and processes that allow users to source, search, consume, and trade packages of data, such as batches of data, streams of data (including event streams), and data from various data pools 4120. In embodiments, the cognitive data marketplace 4102 may be included in, connected to, or integrated with one or more other components of the host processing architecture 4024 of the host processing system 112, such as a cloud-based system, as well as connected to various sensors, input sources 115, data collection systems 102, etc. The cognitive data marketplace 4102 may include a marketplace interface 4108, which may include one or more supplier interfaces through which data suppliers can make data available and one or more consumer interfaces through which data can be found and acquired. The consumer interface may include an interface to a data market search system 4118, which may include functionality that allows users to indicate what type of data they want to acquire, such as by entering keywords that characterize the data or metadata into a natural language search interface. The search interface may use various search and filtering techniques, including keyword matching, collaborative filtering (such as using known preferences or characteristics of consumers to match similar consumers and the past performance of those other consumers), and ranking techniques (such as ranking based on the success of past performance according to various metrics as described in connection with other embodiments of this disclosure). In embodiments, the supply interface may enable data owners or suppliers to supply data to and through the cognitive data marketplace 4102 in one or more packages, such as packaging batches of data, streams of data, etc. Suppliers may pre-package data by providing data from a single input source 116, a single sensor, etc., or by providing combinations, permutations, etc. (e.g., multiplexed analog data, mixed bytes of data from multiple sources, results of extraction, loading and transformation, results of convolution, etc.), as well as metadata related to any of the foregoing. Packaging may include batch pricing, streaming pricing (e.g., subscriptions to feeds or streams such as event feeds), item pricing, revenue share pricing, etc. For data with pricing, the data transaction system 4114 may track ordering, delivery, and usage, including order fulfillment. The transaction system 4114 may include rich transaction functionality, including digital rights management to manage usage (e.g., permitting data to be used for a limited time, in a limited area, by limited users or roles, or for a limited purpose), such as by managing encryption keys that manage access control to purchased data. The transaction system 4114 may manage payments, such as by processing credit cards, wire transfers, debits, and other forms of consideration.

In embodiments, the cognitive data packaging system 4012 of the marketplace 4102 may package data using machine-based intelligence, such as by automatically configuring packages of data in batches, streams, pools, etc. In embodiments, packaging may be according to one or more rules, models, or parameters, such as by packaging or aggregating data that is likely to supplement or complement an existing model. For example, operational data from a group of similar machines (such as one or more industrial machines described throughout this disclosure) may be aggregated together based on metadata indicative of the type of data or by recognizing features or characteristics in the data stream that indicate the nature of the data. In embodiments, packaging may occur using machine learning and cognitive capabilities, such as by learning what combinations, permutations, blends, layers, etc. of information from input sources 116, sensors, data pools 4120, and information from data collection system 102 are likely to meet user requirements or result in measures of success. Learning may be based on learning feedback 4012, such as learning based on measurements determined by analysis system 4018, such as system performance measurements, data collection measurements, analysis measurements, etc. In embodiments, the success measures may be correlated with marketplace success measures, such as package views, engagement with the package, package purchases or licenses, and payments made for the package. Such measures may be calculated as follows: The analysis system 4018 includes associating specific feedback measures with search terms and other inputs, enabling the cognitive packaging system 4110 to find and configure packages designed to increase value for consumers and increase returns for data providers. In embodiments, the cognitive data packaging system 4110 can use the learning feedback 4012 to automatically vary packaging, such as by using different combinations, permutations, mixes, etc., or by varying the weights applied to given input sources, sensors, data pools, etc., to promote preferred packages and de-emphasize less preferred packages. This may occur using genetic programming and similar techniques to compare the results of different packages. Feedback may include state information from the state system 4020 (e.g., regarding various operating conditions) and market conditions, such as price and availability information from other data sources. In this manner, an adaptive cognitive data packaging system 4110 is provided that automatically adapts to conditions to provide advantageous data packages to the marketplace 4102.

In embodiments, a cognitive data pricing system 4112 may be provided to price data packages. In embodiments, the data pricing system 4112 may use a set of rules, models, etc. to set prices based on supply conditions, demand conditions, pricing of various available sources, etc. For example, pricing of a package may be configured to be set based on the sum of the component prices (e.g., input sources, sensor data, etc.), or may be configured to set prices based on rule-based discounts on the sum of the component prices, etc. Rules and conditional logic may be applied, such as rules that factor in cost factors (e.g., bandwidth or network usage, peak demand factors, scarcity factors, etc.) or usage parameters (e.g., package purpose, domain, user, role, duration, etc.). In embodiments, the cognitive data pricing system 4112 may include fully cognitive and intelligent capabilities, such as using genetic programming, including automatically varying pricing and tracking feedback on the results. Outcomes on which tracking feedback may be based include various financial yield metrics, utilization metrics, etc., which may be provided by calculating metrics in the analytics system 4018 based on data from the data transaction system 4114.

Disclosed herein are methods and systems for self-organizing data pools, which may include self-organizing data pools based on utilization and/or yield metrics, including utilization and/or yield metrics tracked for multiple data pools. A data pool may initially consist of unstructured or loosely structured data pools containing data from an industrial environment, such as sensor data from or about industrial machines or components. For example, a data pool may take streams of data from various machines or components in the environment, such as turbines, compressors, batteries, reactors, engines, motors, vehicles, pumps, rotors, axles, bearings, valves, etc., and the data streams may include analog and/or digital sensor data (of a wide variety), published data about operating conditions, diagnostic and fault data, machine or component identification data, asset tracking data, and many other types of data. Each stream has an identifier within the pool, such as an identifier indicating its source and, optionally, its type. A data pool may be accessed by external systems through one or more interfaces or APIs (e.g., RESTful APIs) or through data integration elements (e.g., gateways, brokers, bridges, connectors), and the data pool may use similar functions to gain access to available data streams. A data pool may be managed by a self-organizing machine learning facility, which may configure the data pool by managing the sources used by the pool, managing the available streams, managing the APIs or other connections into and out of the data pool, etc. Self-organization may be fed back based on success measures, including utilization and yield. Utilization and yield measures may include the cost of acquiring and/or storing the data and the benefit of the pool, measured either by profit or other measures, including user indications of usefulness. For example, a self-organizing data pool may recognize that chemical and radiation data from an energy-producing environment is regularly accessed and extracted, but vibration and temperature data is not being used. In this case, the data pool may automatically reorganize, such as by ceasing to store vibration and/or temperature data or acquiring better sources of such data. This automatic reorganization can also be applied to data structures, for example, to facilitate different data types, different data sources, different data structures, etc. through incremental iteration and feedback.

In an embodiment, a platform is provided with self-organization of data pools based on utilization and/or yield metrics. In an embodiment, the data pool 4020 may be a self-organizing data pool 4020, such as organized by cognitive capabilities as described throughout this disclosure. The data pool 4020 may self-organize in response to learning feedback 4012, such as based on feedback of measurements and results, including those calculated by the analysis system 4018. Organization may include determining the data or packages of data to store in the pool (e.g., representing particular combinations, permutations, aggregations, etc.), the structure of such data (e.g., flat, hierarchical, linked, or other structure), retention period, nature of the storage medium (e.g., hard disk, flash memory, SSD, network-based storage, etc.), arrangement of storage bits, and other parameters. The storage contents and nature may change such that the data pool 4020 grows and adapts based on the state of the host system 112, the state of one or more data collection systems 102, storage environment parameters (e.g., capacity, cost, and performance factors), data collection environment parameters, market parameters, and many other parameters. In an embodiment, the pool 4020 may be reamed and adapted in response to yield metrics (e.g., return on investment, optimized power usage, optimized revenue, etc.), such as by varying these and other parameters.

Disclosed herein are methods and systems for training AI models based on industry-specific feedback, including training the AI models based on industry-specific feedback reflecting utilization, yield, or impact measures, where the AI models operate on sensor data from an industrial environment. As discussed above, these models may include models of the operation of industrial environments, machines, and workflows; models that predict conditions; models that predict failures and optimize maintenance; models of self-organizing storage (on-device, in data pools, and/or in the cloud); models that optimize data transport (to optimize network coding, routing depending on network conditions, etc.); models that optimize data marketplaces; and many others.

In embodiments, a platform is provided with training AI models based on industry-specific feedback. In embodiments, various embodiments of the cognitive systems disclosed herein can take input and feedback from industry-specific and domain-specific sources 116 (such as those related to optimizing a particular machine, device, component, process, etc.). Thus, learning and adapting storage organization, network utilization, sensor and input data combination, data pooling, data packaging, data pricing, and other functions (such as for market 4102 or for other purposes of the host processing system 112) may be configured by learning with domain-specific feedback for a given environment or application, such as an application involving IoT devices (such as an industrial environment). This may include efficiency optimization (such as for electrical, electromechanical, magnetic, physical, thermodynamic, chemical, and other processes and systems), output optimization (such as for the production of energy, materials, products, services, and other outputs), and failure prediction, avoidance, and mitigation (such as for the aforementioned systems and processes). Optimization of performance metrics (return on investment, yield, profit, margin, revenue, etc.), cost reduction (labor costs, bandwidth costs, data costs, material input costs, license costs, etc.), benefit optimization (safety, satisfaction, health, etc.), workflow optimization (optimizing the allocation of time and resources to processes, etc.), etc.

Disclosed herein are methods and systems for a self-organizing swarm of industrial data collection devices that organizes among itself to optimize data collection based on the capabilities and conditions of its members. Each member of the swarm may be configured with intelligence and the ability to collaborate with other members. For example, swarm members may track information about what data other members are working with and intelligently allocate data collection activities, data storage, data processing, and data publishing across the swarm, taking into account environmental conditions, swarm member capabilities, operational parameters, rules (e.g., a rules engine governing the swarm's operation), and the member's current conditions. For example, one of four collectors with a relatively low current power level (e.g., low battery) may be temporarily assigned the role of publishing data, potentially receiving power from a reader or querying device (e.g., a REID reader) when it needs to publish data. A second collector with good power levels and robust processing capabilities might be assigned more complex functions, such as processing data, fusing data, and organizing the rest of the swarm (including self-organization under machine learning so that the swarm optimizes over time by adjusting operating parameters, rules, etc. based on feedback). A third collector in the swarm with robust storage capabilities might be tasked with collecting and storing categories of data that consume significant bandwidth, such as vibration sensor data. A fourth collector in the swarm, for example, one with low memory capabilities, might be tasked with collecting data that can normally be discarded, such as data about current diagnostic conditions, while only data about faults needs to be retained and passed on. Swarm members may be connected in a peer-to-peer relationship, using one member as a "master" or "hub," or in a series or ring, allowing each member to communicate data (including commands) to the next member and recognize the capabilities and nature of the command appropriate to the preceding and/or following member. A swarm may also be used to allocate storage across it, such as using each member's memory as an aggregate data store. In these examples, the aggregate data store may support a distributed ledger, which may store transaction data for transactions involving data collected by the swarm, transactions occurring in an industrial environment, etc. In embodiments, the transaction data may also include data used to manage the swarm, the environment, or machines or components thereof. The swarm may self-organize by machine learning functions deployed to one or more members of the swarm or based on instructions from an external machine learning facility, which may optimize storage, data collection, data processing, data presentation, data transport, and other functions based on management parameters associated with each. The machine learning facility may start with an initial configuration and vary swarm parameters related to any of the foregoing (including varying swarm membership), such as iterating based on feedback to the machine learning facility regarding success measures (utilization measures, efficiency measures, measures of success in predicting or forecasting conditions, productivity measures, yield measures, profit measures, etc.). Over time, the swarm may be optimized to a preferred configuration to achieve the desired success measures for the owner, operator, or host of the industrial environment or its machines, components, or processes.

The swarm 4202 may be organized based on a hierarchical organization (e.g., where a master data collector 102 organizes and directs the activities of one or more subordinate data collectors 102), a collaborative organization (e.g., where decision-making for the organization of the swarm 4202 is distributed among the data collectors 102, e.g., using various models for decision-making, such as a voting system, a points system, a least-cost routing system, a prioritization system, etc.). In embodiments, one or more of the data collection devices 102 may have mobile capabilities, such as where the data collection devices are located on or in a mobile robot, drone, mobile submersible, etc., and thus the organization may include the location and placement of the data collection devices 102. The data collection system 102 may be implemented using a mobile robot mounted on one or more of the collectors. The swarms 4202 may communicate with each other and with the host processing system 112, including sharing an aggregated allocated storage space, including storage accessible from the swarms 4202 (which in embodiments may be physically distributed but treated as a unified storage space, such as by using virtualization capabilities). Organization may be automated based on one or more rules, models, conditions, processes, etc. (e.g., embodied or executed by conditional logic), and the organization may be governed by policies, such as processed by a policy engine. Rules may be coordinated with the above, such as by configuring the swarm 4202 to collect selected types of data at specified locations and times, to define industry, application, and domain-specific objects, classes, events, workflows, processes, etc. The self-organization may be based on the data, processes, and systems. For example, the swarm 4202 may assign data collectors 102 to continuously collect diagnostic data, sensor data, instrumentation data, and/or telematic data from each of a series of machines that perform an industrial process (such as a robotic manufacturing process), such as at the time and location of the inputs to and outputs from each of those machines. In embodiments, the self-organization may be cognitive, such that the swarm varies one or more collection parameters, adapting the selection of parameters, weights applied to parameters, etc. over time. In an example, this may involve using the analysis system 4018 (which, in embodiments, may reside on the swarm 4202, the host processing system 112, or a combination thereof) to analyze the data processed by the swarm 4202, or The swarm 4202 may learn and respond to feedback, such as from a learning feedback system 4012, which may be based on various feedback measures that may be determined by applying them to other elements of the various embodiments disclosed herein (including market factors, etc.). Thus, the swarm 4202 may display adaptive behavior, such as adapting to the current state 4020 or the expected state of its environment (taking into account market behavior), the behavior of various objects (such as IoT devices, machines, components, and systems), processes (including events, states, workflows, etc.), and other factors at a given time. Parameters that can be varied in processes such as variation, selection, promotion, etc. (such as those enabled by genetic programming or other AI-based techniques) can be varied using neural nets, self-organizing maps, etc. The parameters that can be managed, varied, selected, and adapted by cognitive and machine learning include storage parameters (such as the location, type, duration, quantity, and structure of the entire swarm 4202), network parameters (such as how the swarm 4202 is organized, e.g., mesh, peer-to-peer, ring, serial, hierarchical, and other network configurations, as well as bandwidth utilization, data routing, network protocol selection, network coding type, and other network parameters), security parameters (such as the configuration of various security applications and services), and location and positioning parameters (such as routing the movement of mobile data collectors 102 to their locations). The feedback may include, but is not limited to, input selection parameters (such as input selection among sensors, input sources 116, etc., for each collector 102 and for the collective collection), data combination parameters (such as sensor fusion, input combining, combining multiplexing, mixing, layering, convolution, etc.), power parameters (such as power supply for various security applications and services), power parameters (such as parameters based on the power level and power availability of one or more collectors 102 or other objects, devices, etc.), state (such as the expected state and condition of the constellation 4202, an individual collection system 102, the host processing system 112, or one or more objects in the environment), events, and many others. Feedback may be based on any of the types of feedback described herein, such that over time the constellation can adapt to its current and expected circumstances to achieve a wide range of desired objectives.

Disclosed herein are methods and systems for an industrial IoT distributed ledger, including a distributed ledger that supports tracking of transactions performed in an automated data marketplace for industrial IoT data. The distributed ledger may distribute storage across devices using secure protocols such as those used in cryptocurrencies (e.g., the blockchain protocol used to support the Bitcoin currency). Each successive member of the chain may configure a structure to store data from previous transactions, and competitions may be held to determine which of the alternative data storage structures is the "best" (e.g., most complete). The ledger or similar transaction record may be stored across data collectors, industrial machines or components, data pools, data marketplaces, cloud computing elements, servers, and/or the IT infrastructure of an enterprise (e.g., the owner, operator, or host of an industrial environment or the system disclosed herein). The ledger or transactions may be optimized through machine learning to provide storage efficiency, security, redundancy, etc.

In embodiments, the cognitive data marketplace 4102 may use a secure architecture for tracking and resolving transactions, such as a distributed ledger 4004, enabling forensic analysis and verification, in which data package transactions are tracked in a chained, distributed data structure, such as a blockchain, with individual devices storing portions of the ledger representing data package transactions. The distributed ledger 4004 may be distributed across IoT devices, data pools 4020, data collection systems 102, etc., allowing transaction information to be verified without relying on a single, central repository of information. A transaction system 4114 may be configured to store data in the distributed ledger 4004 and retrieve data from the distributed ledger 4004 (and from constituent devices) to resolve transactions. In this manner, a distributed ledger 4004 is provided for processing transactions of data, such as packages of IoT data. In embodiments, a self-organizing storage system 4028 may be used to organize the storage of packages of data, such as IoT data, presentable on the marketplace 4102, as well as to optimize the storage of distributed ledger data.

Disclosed herein are methods and systems for network-sensitive collectors, including self-organizing multi-sensor data collectors that are sensitive to network conditions and can be optimized based on bandwidth, quality of service, pricing, and/or other network conditions. Network sensitivity includes awareness of the price of data transfer (e.g., allowing the system to pull or push data during off-peak periods or within the available parameters of a paid data plan), the quality of the network (e.g., avoiding error-prone periods), and the quality of environmental conditions (e.g., delaying transmission until signal quality is good, such as when the collector emerges from a shielded environment, avoiding wasting power when seeking a signal while shielded by large metal structures, such as those typical of industrial environments).

Disclosed herein are methods and systems for a remotely orchestrated universal data collector that can power on and off sensor interfaces based on identified needs and/or conditions in an industrial data collection environment. For example, the interface can recognize available sensors and turn on the interface and/or processor to take input from such sensors. This includes hardware interfaces that allow sensors to be plugged into the data collector, wireless data interfaces (e.g., where the collector pings the sensor and optionally provides some power via an interrogation signal), and software interfaces (e.g., for processing specific types of data). Thus, collectors capable of handling various types of data can be configured to adapt to specific uses in a given environment. In embodiments, configuration may occur automatically or under machine learning, which may improve the configuration by optimizing parameters based on feedback measurements over time.

Disclosed herein are methods and systems for self-organizing storage of multi-sensor data collectors, including self-organizing storage of industrial sensor data. The self-organizing storage may allocate storage based on the application of machine learning, which may improve the configuration of storage based on feedback measurements over time. Storage can be optimized by configuring what types of data are available, configuring compression, configuring data retention periods, configuring write strategies (such as striping data across multiple storage devices or using protocols where one device stores instructions to other devices in a chain), configuring storage tiers (such as providing pre-calculated intermediate statistics to enable faster access to frequently accessed data items), and so on. In this way, a highly intelligent storage system is configured and optimized over time based on feedback.

Disclosed herein are methods and systems for multi-sensor data networks, including self-organizing network coding for data networks transporting data from multiple sensors in industrial data collection environments. Network coding, including random linear network coding, can enable highly efficient and reliable transmission of large amounts of data over various types of networks. Based on the nature of the data being transported, network conditions such as environmental conditions, operating conditions, and other factors, different network coding configurations can be selected based on machine learning (including by training a network coding selection model over time based on feedback of success metrics, such as any of the metrics described herein) to optimize the network coding and other network transport characteristics.

In an embodiment, a platform with self-organizing network coding for a multi-sensor data network is provided. The cognitive system can vary one or more parameters for the network, such as network type selection (e.g., network type selection (e.g., local, cellular, satellite, Wi-Fi, Bluetooth, NFC, Zigbee, etc.), network selection (e.g., selecting a particular network, such as a network known to have desired security features), network coding selection (e.g., selecting a type of network coding for efficient transmission, such as random linear network coding or fixed coding), network timing selection (e.g., configuring delivery based on network pricing conditions, traffic, etc.), network characteristics (e.g., network capability selection (e.g., cognitive capabilities, security capabilities, etc.), network conditions (e.g., network quality based on current environmental and operating conditions), network feature selection (e.g., enabling available authentication, authorization, etc. systems), network protocol selection (e.g., HTTP, IP, TCP/IP, cellular, satellite, serial, packet, streaming, and many other protocols), bandwidth constraints, price fluctuations, environmental Given sensitivity to factors, security concerns, and the like, selecting the optimal network configuration can be highly complex and context-dependent. The self-organizing networking system 4030 may vary combinations and permutations of these parameters while receiving input from the learning feedback system 4012, such as using information from the analytics system 4018 regarding various measures of outcome. In many examples, outcomes may include system-wide measurements, analytical success measures, and local performance indicators. In embodiments, input from the learning feedback system 4012 may include taking information from various sensors and input sources 116, information regarding conditions (such as events, environmental conditions, operating conditions, and many other information) from the state system 4020, or other input. By varying and selecting alternative configurations of networking parameters in different states, the self-organizing networking system can find a configuration that best adapts to the environment monitored or controlled by the host system 112, such as the instance in which one or more data collection systems 102 are deployed, and that best adapts to emerging network conditions. In this manner, a self-organizing, network-condition-adaptive data collection system is provided.

Referring to FIG. 32, the data collection system 102 may have one or more output interfaces and/or ports 4010. These may include network ports and connections, application programming interfaces, and the like. Disclosed herein are methods and systems related to tactile or multisensory user interfaces, including wearable tactile or multisensory user interfaces for industrial sensor data collection devices, having vibration, thermal, electrical, and/or sound outputs. For example, the interface may be configured to provide input or feedback to a user based on data from sensors in the environment, etc., based on a data structure configured to support the interface. For example, a fault condition detected based on vibration data (such as due to bearing wear, axle misalignment, or a mechanical resonance condition) may be presented in the tactile interface via vibration of the interface, such as by shaking a wristwarm device. Similarly, thermal data indicating overheating may be presented by warming or cooling a wearable device, such as while the worker is working on a machine and cannot necessarily see the user interface. Similarly, electrical or magnetic data may be presented via a buzzer sound, such as to indicate the presence of an open electrical connection or wiring. That is, multisensory interfaces can intuitively help users (such as those with wearable devices) quickly understand what is happening in their environment, and wearable interfaces have a variety of interaction modes that do not require gazing at a graphical UI, which can be difficult or impossible in many industrial environments where users need to keep their eyes on the environment.

In an embodiment, a platform having a wearable haptic user interface for an industrial sensor data collection device is provided, having vibration, heat, electricity, and/or sound outputs. In an embodiment, the haptic user interface 4302 is provided as an output for the data collection system 102, such as a system for processing and providing information for the vibration, heat, electricity, and/or sound outputs, such as to one or more components of the data collection system 102 or another system, such as a wearable device, a mobile phone, etc. The data collection system 102 may be provided in a form factor suitable for providing a user with tactile input, such as vibration, heating or cooling, a buzzer, etc., such as an input located on headgear, an armband, a wristband, a watch, a belt, clothing, a uniform, etc. In such cases, the data collection system 102 can be integrated with gear, uniforms, equipment, etc. worn by a user, such as an individual responsible for operating or monitoring an industrial environment. In embodiments, signals from various sensors or input sources (or selective combinations, permutations, mixtures, etc., as managed by one or more of the cognitive input selection systems 4004, 4014) may trigger haptic feedback. For example, if nearby industrial machinery is overheating, the haptic interface may alert the user by heating it or by sending a signal to another device (such as a cell phone) to warm it up. Also, if the system is experiencing abnormal vibrations, the haptic interface may vibrate. In this manner, through various forms of haptic input, the data collection system 102 may inform the user of the need to pay attention to one or more devices, machines, or other factors (such as those in an industrial environment) without requiring the user to read a message or visually distract from the task at hand. The selection of the haptic interface and what output to provide may be considered in the cognitive input selection systems 4004, 4014. For example, user behavior (e.g., responses to inputs) may be monitored and analyzed by analysis system 4018, and feedback may be provided via learning feedback system 4012, which may provide signals at appropriate times and in appropriate ways based on an appropriate collection or packaging of sensors and inputs to optimize the effectiveness of haptic system 4202. This may include rule-based or model-based feedback (e.g., providing output that corresponds in some logical way to the source data being communicated). In embodiments, a cognitive haptic system may be provided, in which the selection of inputs or triggers for haptic feedback, the selection, timing, intensity level, duration, and other parameters (or weights applied thereto) of outputs may be varied in a process of variation, prompting, and selection (e.g., using genetic programming), with feedback based on real-world responses to feedback in actual situations or the results of simulations and testing of user behavior. In this manner, an adaptive haptic interface for data collection system 102 is provided that can learn and adapt feedback to meet requirements and optimize the impact on user behavior, including overall system performance, data collection performance, and analysis performance.

Disclosed herein are methods and systems for a presentation layer of AR/VR industrial glasses in which heatmap elements are presented based on patterns and/or parameters of collected data. Disclosed herein are methods and systems for conditionally and self-organizingly tuning an AR/VR interface based on feedback metrics and/or training in an industrial environment. In embodiments, any of the data, measurements, etc. described throughout this disclosure can be presented via visual elements, overlays, etc. for presentation in an AR/VR interface, such as industrial glasses, an AR/VR interface on a smartphone or tablet, an AR/VR interface on a data collector (which may be embodied in a smartphone or tablet), a display located on a machine or component, and/or a display located in the industrial environment.

In an embodiment, a platform is provided having a heat map displaying collected data for AR/VR. In an embodiment, the platform is provided having a heat map 4204 displaying data collected from the data collection system 102 to provide input to an AR/VR interface 4208. In an embodiment, the heat map interface 4304 is provided as an output of the data collection system 102, such as to one or more components of the data collection system 102 or to another system, such as a mobile device, tablet, dashboard, computer, or AR/VR device, for processing and providing information for visualization of various sensor data and other data (e.g., map data, analog sensor data, and other data). The data collection system 102 may be provided in a form factor suitable for providing visual input to a user, such as presenting a map including indicators of levels of analog and digital sensor data (e.g., data indicating levels of rotation, vibration, heating or cooling, pressure, and many other conditions). In such cases, the data collection system 102 may be integrated with equipment used by individuals responsible for operating or monitoring industrial environments. In embodiments, signals from various sensors or input sources (or selective combinations, permutations, blends, etc., managed by one or more of the cognitive input selection systems 4004, 4014) may provide input data for the heat map. The coordinates may include real-world location coordinates (such as geolocations or locations on a map of the environment), as well as other coordinates, such as time-based coordinates, frequency-based coordinates, or other coordinates that allow for the representation of various combinations of analog sensor signals, digital signals, input source information, and other coordinates in the map-based visualization, so that colors can represent various levels of input along the associated dimension. For example, if a nearby industrial machine is overheating, the heat map interface may alert the user by displaying the machine in a bright red. If a system is experiencing abnormal vibrations, the heat map interface may display a different color on the machine's visual element or may cause an icon or display element representing the machine to vibrate in the interface to call attention to that element. By clicking, touching, or otherwise interacting with the map, the user can drill down and view the underlying sensor or input data used as input for the heat map display. Thus, through various forms of display, the data collection system 102 can notify a user of the need for attention to one or more devices, machines, or other elements, such as those in an industrial environment, without the need to read a text-based message or input. The selection of the heatmap interface and what output to provide may be considered in the cognitive input selection system 4004, 4014. For example, user behavior (such as responses to inputs or displays) may be monitored and analyzed in the analysis system 4018, and feedback may be provided through the learning feedback system 4012, which can provide signals at the right time and in the right way based on the correct collection or package of sensors and inputs to optimize the effectiveness of the heatmap UI 4304. This may include rule-based or model-based feedback (such as feedback that provides an output that corresponds in some logical way to the source data being communicated). In embodiments, a cognitive heatmap system may be provided in which the selection of inputs or triggers, outputs, colors, visual elements, timing, intensity levels, duration, and other parameters (or weights applied thereto) for the heatmap display may be varied in a process of variation, promotion, and selection (e.g., selection by genetic programming) based on feedback based on real-world responses to feedback in actual situations or the results of simulations and testing of user behavior. Thus, an adaptive heatmap interface may be provided for the data collection system 102, or data collected thereby, or data handled by the host processing system 112, which may refine and adapt feedback to meet requirements and optimize the impact on overall system performance, data collection performance, analysis performance, etc., on user behavior and response.

In an embodiment, a platform having automatically tuned AR/VR visualization of data collected by a data collector is provided. In an embodiment, a platform having an automatically tuned AR/VR visualization system 4308 is provided for visualization of data collected by the data collection system 102, such as when the data collection system 102 has an AR/VR interface 4208 or provides input to the AR/VR interface 4308 (e.g., a mobile phone placed in a virtual reality or AR headset, a set of AR glasses, etc.). In an embodiment, the AR/VR system 4308 is provided as an output interface for the data collection system 102, such as one or more components of the data collection system 102 or another system, such as a mobile device, tablet, dashboard, computer, AR/VR device, or other system that handles and provides information for visualization of various sensor data and other data (e.g., map data, analog sensor data, etc.). The data collection system 102 may be provided in a form factor suitable for providing AR or VR visual, auditory, or other sensory input to a user, such as by presenting to the input source 116, or the like, one or more displays, such as 3D realistic visualizations, objects, maps, camera overlays, or other overlay elements, maps, etc., that include or correspond to indicators of levels of analog and digital sensor data (such as data indicative of levels of rotation, vibration, heating or cooling, pressure, and many other conditions). In such cases, the data collection system 102 may be integrated with equipment, etc., used by individuals responsible for operating or monitoring industrial environments.

In embodiments, signals from various sensors or input sources (or selective combinations, permutations, blends, etc. managed by one or more of the cognitive input selection systems 4004, 4014) may provide input data for populating, configuring, modifying, or otherwise determining the AR/VR elements. Visual elements may include a wide range of icons, map elements, menu elements, sliders, toggles, colors, shapes, sizes, etc. to represent analog sensor signals, digital signals, input source information, and various combinations. In many examples, the colors, shapes, and sizes of visual overlay elements can represent various levels of input along the relevant dimension of a sensor or combination of sensors. In a further example, if nearby industrial machinery is overheating, the AR element can alert the user by displaying an icon representing that type of machinery in a flashing red light on a portion of the AR glasses' display. Additionally, if a system is experiencing abnormal vibrations, a virtual reality interface visualizing machine components (e.g., a camera view of the machine overlaid with 3D visualization elements) may highlight the vibrating components with a highlighted color or animation, making them more visible in the virtual reality environment as the user monitors or repairs the machine. Additionally, interacting with visual elements in the AR/VR interface, such as by clicking, touching, or gazing, may allow for drill-down viewing of the underlying sensor data or inputs used as input to the display. In this manner, through various forms of display, the data collection system 102 can notify the user of the need for attention to one or more devices, machines, or other factors (e.g., in an industrial environment) without requiring the user to read text-based messages or inputs or without distracting from the applicable environment (whether a real environment with AR capabilities or a virtual environment for simulation, training, etc.).

Selection and configuration of the AR/VR output interface 4208 and what output or display to provide may be handled by the cognitive input selection system 4004, 4014. For example, user behavior (e.g., responses to input or display) may be monitored and analyzed in the analysis system 4018, feedback may be provided through the learning feedback system 4012, and AR/VR display signals may be provided at the appropriate time and in the appropriate manner based on an appropriate collection or packaging of sensors and inputs to optimize the effectiveness of the AR/VR UI 4308. This may include rule-based or model-based feedback (e.g., providing output that corresponds in some logical way to the source data being communicated). In embodiments, a cognitively tailored AR/VR interface control system 4308 may be provided, in which input or trigger selection for AR/VR display elements, outputs (such as color, visual elements, timing, intensity levels, duration, and other parameters [or weights applied thereto]), and other parameters of the VR/AR environment may be varied in a process of variation, prompting, and selection (such as using genetic programming) using feedback based on real-world responses in actual situations or based on the results of simulated and tested user behavior. In this manner, an adaptive, tailored AR/VR interface for data collection system 102, or data collected thereby, or data processed by host processing system 112, may be provided that can refine and adapt feedback to meet requirements and optimize the impact on user behavior and responses, including overall system performance, data collection performance, and analysis performance.

As described above, methods and systems for continuous ultrasonic monitoring are disclosed herein, including providing continuous ultrasonic monitoring of rotating elements and bearings of energy production equipment. Embodiments include using continuous ultrasonic monitoring of an industrial environment as a source for a cloud-deployed pattern recognizer. Embodiments include using the continuous ultrasonic monitoring to provide updated state information to a state machine that is used as input to the cloud-deployed pattern recognizer. Embodiments include making the continuous ultrasonic monitoring information available to users based on policies declared in a policy engine. Embodiments include storing the continuous ultrasonic monitoring data with other data in a fusion data structure on the industrial sensor device. Embodiments include making the stream of continuous ultrasonic monitoring data from the industrial environment available as a service from a data marketplace. Embodiments include feeding the stream of continuous ultrasonic monitoring data into a self-organizing data pool. Embodiments include training a machine learning model to monitor the continuous ultrasonic monitoring data stream, where the model is based on a training set created from human analysis of such data stream and is improved based on data collected about performance in the industrial environment.

An embodiment includes a group of data collectors, including at least one data collector for continuous ultrasonic monitoring of an industrial environment and at least one other type of data collector. An embodiment includes using a distributed ledger to store time series data from the continuous ultrasonic monitoring across multiple devices. An embodiment includes collecting the stream of continuous ultrasonic data in a self-organizing data collector, a network-sensitive data collector, a remotely organizing data collector, a data collector with self-organizing storage, or the like. An embodiment includes using self-organizing network coding to convey the stream of ultrasonic data collected from the industrial environment. An embodiment includes communicating an indication of a parameter of the continuously collected ultrasonic data stream via an interface, the interface being one of a sensory interface of a wearable device, a heatmap visual interface of a wearable device, an interface operating with self-organized tuning of an interface layer, or the like.

As described above, disclosed herein are methods and systems for cloud-based machine pattern recognition based on the fusion of remote analog industrial sensors. An embodiment includes acquiring inputs from multiple analog sensors located in an industrial environment, multiplexing the sensors into a multiplexed data stream, feeding the data stream to a cloud-deployed machine learning facility, and training a model in the machine learning facility to recognize defined patterns associated with the industrial environment. An embodiment includes using a cloud-based pattern recognizer on input states from a state machine that characterizes the state of the industrial environment. An embodiment includes deploying policies in the cloud-based machine learning through a policy engine that governs what data can be used by which users and for what purposes. An embodiment includes using a cloud-based platform to identify patterns in data across multiple data pools, including data published from industrial sensors. An embodiment includes training a model to identify a preferred sensor set for diagnosing the state of the industrial environment, where the training set is created by a human user and the model is improved based on feedback from data collected about the state of the industrial environment.

Embodiments include a swarm of data collectors governed by policies that are automatically propagated through the swarm. Embodiments include using a distributed ledger to store sensor fusion information across multiple devices. Embodiments include feeding input from a set of data collectors to a cloud-based pattern recognizer that uses data from multiple sensors for an industrial environment. The data collectors may be self-organizing data collectors, network-sensitive data collectors, remotely organized data collectors, a set of data collectors with self-organized storage, etc. Embodiments include a system for data collection in an industrial environment with self-organizing network coding for data transport of fused data from multiple sensors in the environment. Embodiments include conveying information formed by fusing inputs from multiple sensors in the industrial data collection system over an interface, such as a multi-sensor interface, a heatmap interface, or an interface that operates with self-organized tuning of an interface layer.

As described above, methods and systems for cloud-based machine pattern analysis of state information from multiple analog industrial sensors to provide predicted state information for an industrial system are disclosed herein. Embodiments include using a policy engine to determine state information usable for cloud-based machine analysis. Embodiments include providing inputs from multiple devices and on-device storage fusing multiple sensor streams to a cloud-based pattern recognizer to determine a predicted state of the industrial environment. Embodiments include making available output, such as predicted state information, from the cloud-based machine pattern recognizer that analyzes the fused data from the remotely located analog industrial sensors as a data service on a data marketplace. Embodiments include using the cloud-based pattern recognizer to determine a predicted state of the industrial environment based on data collected from a data pool including streams of information from machines in the environment. Embodiments include training a model that identifies favorable state information for diagnosing the state of the industrial environment, where the training set is created by a human user and the model is improved based on feedback from data collected about the state of the industrial environment. Embodiments include a group of data collectors feeding a state machine that maintains current state information for the industrial environment. An embodiment includes using a distributed ledger to store historical state information for fused sensor states with a self-organizing data collector feeding a state machine that maintains current state information for the industrial environment. An embodiment includes a data collector feeding the state machine that maintains current state information for the industrial environment, where the data collector may be a network-sensitive data collector, a remotely organized data collector, a data collector with self-organized storage, or the like. An embodiment includes a system for data collection in an industrial environment with self-organizing network coding for data transport, maintaining predicted state information for the environment. An embodiment includes communicating predicted state information determined by machine learning in the industrial data collection system with an interface, where the interface may be one or more of a multi-sensory interface, a heat map interface, an interface operating with self-organized tuning of an interface layer, or the like.

As described above, methods and systems are disclosed herein, including a cloud-based policy automation engine for IoT, that enables the creation, deployment, and management of policies applied to IoT devices. Policies can relate to data usage for an on-device storage system that stores fused data from multiple industrial sensors, or to what data can be made available to whom in a self-organizing marketplace for IoT sensor data. Policies can dictate how self-organizing swarms or data collectors are organized for a particular industrial environment, how network-sensitive data collectors for a particular industrial environment use network bandwidth, how remotely organized data collectors collect and make available data related to a particular industrial environment, or how data collectors self-organize storage for a particular industrial environment. Policies can be deployed to a set of self-organizing data pools containing data streamed from industrial sensing devices to manage the use of data from the pools or stored on the device to manage the use of the device's storage capabilities for a distributed ledger. Embodiments include training a model to determine what policies should be deployed to industrial data collection systems. Embodiments include a data collection system in an industrial environment with a policy engine for deploying policies within the system and, optionally, self-organizing network coding for data transport, where in certain embodiments, the policies apply to how data is presented in a multi-sensory interface, a heatmap visual interface, or an interface that operates with self-organizing tuning of the interface layer.

As described above, methods and systems are disclosed herein for on-device sensor fusion and data storage for industrial IoT devices, such as industrial data collectors, including self-organizing, remote-organizing, or network-sensitive industrial data collectors, where data from multiple sensors is multiplexed at the device for storage of a fused data stream. Embodiments include a self-organizing marketplace presenting fused sensor data extracted from the IoT device's on-device storage. Embodiments include streaming fused sensor information from multiple industrial sensors and from on-device data storage to a data pool. Embodiments include training a model in the data collection environment to determine which data to store on the device. Embodiments include a self-organizing group of industrial data collectors that organize among themselves to optimize data collection, at least some of the data collectors having on-device storage of fused data from multiple sensors. Embodiments include storing distributed ledger information with the fused sensor information at the industrial IoT device. Embodiments include a system for data collection with on-device sensor fusion, such as industrial sensor data, optionally with self-organizing network coding for data transport, where data structures are stored to support interfaces that operate with alternative multi-sensory presentation modes, visual heatmap presentation modes, and/or self-organized tuning of interface layers.

As described above, methods and systems are disclosed herein for a self-organizing data marketplace for industrial IoT data, where available data elements are organized in a marketplace for consumption by consumers based on feedback from training a self-organizing facility with a training set and measures of market success. Embodiments include organizing a set of data pools in the self-organizing data marketplace based on utilization metrics for the data pools. Embodiments include training a model to determine pricing for data in the data marketplace. The data marketplace is fed with data streams from a fleet of self-organized industrial data collectors, a set of industrial data collectors with self-organized storage, or self-organized, network-dependent, or remotely organized industrial data collectors. Embodiments include using a distributed ledger to store transaction data for the self-organizing marketplace for industrial IoT data. Embodiments include using self-organizing network coding for data transport to a marketplace for sensor data collected in an industrial environment. Embodiments include providing a library of data structures suitable for presenting data in alternative multi-sensory interface modes, in a data marketplace, in a heatmap visualization, and/or in an interface that operates with self-organized tuning of interface layers.

As described above, methods and systems are disclosed herein for data pools that self-organize based on utilization and/or yield metrics that can be tracked for multiple data pools. In embodiments, the pools include data from self-organizing data collectors. Embodiments include training a model to represent the most valuable data in a data marketplace, where the training is based on industry-specific success measures. Embodiments include populating a set of self-organizing data pools with data from a self-organizing swarm of data collectors. Embodiments include using a distributed ledger to store transaction information for data deployed in the data pools, where the distributed ledger is distributed across the data pools. Embodiments include populating a set of self-organizing data pools with data from a set of network-sensitive or remotely organized data collectors, or a set of data collectors with self-organizing storage. Embodiments include a system for data collection in an industrial environment with a self-organizing pool for data storage and self-organizing network coding for data transport, including a source data structure to support data presentation, for example, in a multi-sense interface, in a heat map interface, and/or in an interface operating with self-organizing tuning of the interface layer.

As described above, methods and systems are disclosed herein for training AI models based on industry-specific feedback, such as reflecting utilization, yield, or impact measures, where the AI models operate on sensor data from an industrial environment. Embodiments include training a swarm of data collectors, or data collectors, such as remotely organizing, self-organizing, or network-sensitive data collectors, based on industry-specific feedback or network and industry conditions in the industrial environment, such as configuring storage. Embodiments include training an AI model to identify and use available storage locations in the industrial environment for storing distributed ledger information. Embodiments include training a remote organizer for remotely organized data collectors based on industry-specific feedback measures. Embodiments include cloud-based training of network coding models to organize network coding for data transmission, or systems for data collection in industrial environments with facilities for managing the presentation of data in multisensory interfaces, heatmap interfaces, and/or interfaces operating with self-organizing tuning of interface layers.

As noted above, methods and systems are disclosed herein for a self-organizing swarm of industrial data collectors that organize among themselves to optimize data collection based on the capabilities and conditions of the swarm members. Embodiments include deploying a distributed ledger data structure across the swarm of data. The data collectors may be network-sensitive data collectors configured for remote organization and may have self-organizing storage. A system for data collection in an industrial environment using a swarm may include self-organizing network coding for data transport. The system includes a swarm that relays information for use in a multisensory interface, in a heatmap interface, and/or in an interface operating with self-organized tuning of the interface layer.

As described above, methods and systems for an industrial IoT distributed ledger are disclosed herein, including a distributed ledger that supports tracking of transactions performed in an automated data marketplace for industrial IoT data. Embodiments include a self-organizing data collector configured to distribute collected information to the distributed ledger. Embodiments include a network-sensitive data collector configured to distribute collected information to the distributed ledger based on network conditions. Embodiments include a remotely organized data collector configured to distribute collected information to the distributed ledger based on intelligent, remote management of distribution. Embodiments include a data collector with self-organizing local storage configured to distribute collected information to the distributed ledger. Embodiments include a system for data collection in an industrial environment using a distributed ledger for data storage and self-organizing network coding for data transport, where the data storage is in a data structure that supports a haptic interface for data presentation, a heatmap interface for data presentation, and/or an interface that operates with self-organized tuning of the interface layer.

As discussed above, methods and systems for self-organizing collectors are disclosed herein, including self-organizing multi-sensor data collectors capable of optimizing data collection, power, and/or yield based on environmental conditions, and optionally responsive to remote organization. Embodiments include self-organizing data collectors that organize at least in part based on network conditions. Embodiments include self-organizing data collectors with self-organizing storage for data collected in an industrial data collection environment. Embodiments include systems for data collection in industrial environments with self-organizing network coding for self-organizing data collection and data transport. Embodiments include systems for data collection in industrial environments with self-organizing data collectors that provide data structures supporting haptic or multi-sensory wearable interfaces for data presentation, heatmap interfaces for data presentation, and/or interfaces that operate with self-organized tuning of the interface layer.

As discussed above, methods and systems for network-sensitive collectors are disclosed herein, including self-organizing, network-condition-sensitive, multi-sensor data collectors that can optimize based on bandwidth, quality of service, pricing, and/or other network conditions. Embodiments include a remotely organized, network-condition-sensitive universal data collector that can power up and down sensor interfaces based on needs and/or conditions identified in the industrial data collection environment, including network conditions. Embodiments include a network-condition-sensitive data collector with self-organizing storage for data collected in the industrial data collection environment. Embodiments include a network-condition-sensitive data collector with self-organizing network coding for data transport in the industrial data collection environment. Embodiments include a system for data collection in an industrial environment, including a network-sensitive data collector that relays data structures supporting a tactile wearable interface for data presentation, a heatmap interface for data presentation, and/or an interface that operates with self-organized tuning of the interface layer.

As discussed above, methods and systems are disclosed herein for a remotely organized universal data collector that can power up and down sensor interfaces based on identified needs and/or conditions in an industrial data collection environment. Embodiments include a remotely organized universal data collector with self-organizing storage for data collected in the industrial data collection environment. Embodiments include a system for data collection in an industrial environment with remote control of data collection and self-organizing network coding for data transport. Embodiments include a remotely organized data collector for storing sensor data and distributing instructions for using the data in a haptic or multisensory wearable interface, a heatmap visual interface, and/or an interface operating with self-organizing tuning of the interface layer.

As noted above, methods and systems for self-organizing storage for multi-sensor data collectors are disclosed herein, including self-organizing storage for multi-sensor data collectors for industrial sensor data. Embodiments include systems for data collection in industrial environments with self-organizing data storage and self-organizing network coding for data transport. Embodiments include a self-organizing storage for storing sensor data and a data collector with instructions for transforming the data for use in a haptic wearable interface, a heat map presentation interface, and/or an interface operating with self-organizing tuning of the interface layer.

As noted above, disclosed herein are methods and systems for multi-sensor data networks, including self-organizing network coding for data networks transmitting data from multiple sensors in industrial data collection environments. The systems include a haptic wearable interface for data presentation, a heat map interface for data presentation, and/or a data structure supporting self-organizing tuning of interface layers for data presentation.

As described above, methods and systems for haptic or multi-sensory user interfaces are disclosed herein, including wearable haptic or multi-sensory user interfaces for industrial sensor data collectors with vibration, heat, electrical, and/or acoustic outputs. Embodiments include a wearable haptic user interface for conveying industrial condition information from the data collector with vibration, heat, electrical, and/or acoustic outputs. The wearable also has a visual presentation layer for presenting a heat map illustrating parameters of the data. In embodiments, AR/VR and multi-sensory interfaces can be conditionally self-tuning based on feedback metrics and/or training in an industrial environment.

As noted above, disclosed herein are methods and systems for a presentation layer of AR/VR industrial glasses in which heatmap elements are presented based on patterns and/or parameters of collected data. Embodiments include conditionally self-organizing and tuning the heatmap AR/VR interface based on feedback metrics and/or training in an industrial environment. As noted above, disclosed herein are methods and systems for conditionally self-organizing and tuning the AR/VR interface based on feedback metrics and/or training in an industrial environment.

The following exemplary paragraphs describe specific embodiments of the present disclosure. The data collection system referred to in the following disclosure may be a local data collection system 102, a host processing system 112 (e.g., using a cloud platform), or a combination of a local system and a host system. In embodiments, a data collection system or data collection and processing system is provided that includes the use of analog crosspoint switches to collect data with variable groups of analog sensor inputs, and in some embodiments, IP front-end signal conditioning on the multiplexer for improved signal-to-noise ratios, multiplexer continuous monitoring alarm functionality, the use of a distributed CPLD chip with a dedicated bus for logically controlling multiple MUXes and data collection units, high amperage input capability using solid-state relays and design topology, power-down capability for analog sensor channels and/or component boards, unique electrostatic protection for trigger and vibration inputs, and a precision voltage reference for the A/D zero reference.

Embodiments provide a data acquisition and processing system that uses an analog crosspoint switch to acquire data with a variable group of analog sensor inputs, has a phase-locked loop bandpass tracking filter to obtain slow RPM and phase information, and uses an on-board timer to digitally derive phase for the input and trigger channels. Other features include a peak detector (connected to another analog-to-digital converter for peak detection) for autoscaling, connecting raw or buffered trigger channels to other analog channels, using high input oversampling of a delta-sigma A/D for low sampling rate output to minimize AA filter requirements, and/or using a CPLD as a clock distributor for a delta-sigma analog-to-digital converter to achieve low sampling rates without the need for digital resampling.

Embodiments provide a data collection and processing system having a variable group of analog sensor inputs, the use of analog crosspoint switches to collect data having long blocks of data at a high sampling rate as opposed to multiple data sets acquired at different sampling rates, storage of calibration data using an onboard maintenance history card set, rapid route creation capabilities using hierarchical templates, intelligent management of data collection bands, and/or a neural net expert system with intelligent management of data collection bands.

Embodiments provide a data collection and processing system that includes the use of analog crosspoint switches to collect data with a variable group of analog sensor inputs, the use of a database hierarchy in sensor data analysis, a graphical approach in the expert system GUI to define intelligent data collection bands and expert system diagnostics, a graphical approach for back calculation definition, a proposed bearing analysis method, torsional vibration detection/analysis utilizing transient signal analysis, and improved integration using both analog and digital methods.

In embodiments, a data collection and processing system is provided that uses an analog crosspoint switch to collect data with a variable group of analog sensor inputs, adaptive scheduling techniques for continuous monitoring of analog data in the local environment, data collection parking, a self-contained data collection box, and SD card storage. It also provides enhanced on-board statistics for continuous monitoring, use of ambient, local, and vibration noise for prediction, smart rerouting based on input data and alarms to enable simultaneous acquisition of dynamic data for analysis and correlation, smart ODS and forwarding, hierarchical multiplexers, sensor overload identification and/or RF identification, and inclinometers.

In an embodiment, a data collection and processing system is provided. The system includes use of an analog crosspoint switch to collect data with a variable group of analog sensor inputs, continuous ultrasonic monitoring, cloud-based machine pattern recognition based on fusion of remote analog industrial sensors, cloud-based machine pattern analysis of state information from multiple analog industrial sensors to provide predicted state information for an industrial system, creation, deployment, and management of IoT devices, on-device sensor fusion and data storage for industrial IoT devices, a cloud-based policy automation engine with a self-organizing data marketplace for industrial IoT data, self-organization of data pools based on utilization and/or yield metrics, training of AI models based on industry-specific feedback, a self-organizing swarm of industrial data collectors, an IoT distributed ledger, a self-organizing collector, a network-sensitive collector, a remotely organizing collector, self-organizing storage for multi-sensor data collectors, self-organizing network coding for multi-sensor data networks, a wearable haptic user interface for industrial sensor data collectors with vibration, thermal, electrical, and/or sound outputs, a heat map displaying collected data for AR/VR, and/or an auto-adjusting AR/VR visualization of data collected by the data collectors.

In an embodiment, a data acquisition and processing system is provided with IP front-end signal conditioning on the multiplexer to improve signal-to-noise ratio. In an embodiment, a data acquisition and processing system is provided with IP front-end signal conditioning on the multiplexer to improve signal-to-noise ratio, and at least one of: multiplexer continuous monitoring alarm capability; IP front-end signal conditioning on the multiplexer to improve signal-to-noise ratio; and use of a distributed CPLD chip with a dedicated bus for logic control of multiple MUXes and the data acquisition section. In an embodiment, a data acquisition and processing system is provided with IP front-end signal conditioning on the multiplexer to improve signal-to-noise ratio, and at least one of: high amperage input capability using solid-state relays and design topology; power-down capability for at least one analog sensor channel and component board; unique electrostatic protection for trigger and vibration inputs; a precision voltage reference for the A/D zero reference; and a phase-locked loop bandpass tracking filter for obtaining slow RPM and phase information. In an embodiment, a data acquisition and processing system is provided with IP front-end signal conditioning on the multiplexer to improve signal-to-noise ratio, and at least one of: Digital derivation of phase for input and trigger channels using onboard timers, a peak detector for autoscaling that is routed to another analog-to-digital converter for peak detection, routing of raw or buffered trigger channels to other analog channels, use of high input oversampling of delta-sigma A/Ds for low sampling rate outputs to minimize AA filter requirements, and use of a CPLD as a clock distributor for delta-sigma analog-to-digital converters to achieve low sampling rates without the need for digital resampling. In embodiments, a data acquisition and processing system is provided having at least one of: IP front-end signal conditioning on a multiplexer to improve signal-to-noise ratio, long blocks of data at high sampling rates as opposed to multiple data sets acquired at different sampling rates, storage of calibration data with a card set that includes maintenance history, rapid route creation using hierarchical templates, intelligent management of data acquisition bands, and a neural net expert system using intelligent management of data acquisition bands. In an embodiment, a data collection and processing system is provided that has IP front-end signal conditioning on the multiplexer to improve signal-to-noise ratio, uses a database hierarchy in sensor data analysis, a graphical approach of an expert system GUI to define intelligent data collection bands and expert system diagnostics, and at least one of the following: back-calculation definition. In an embodiment, a data collection and processing system is provided that has IP front-end signal conditioning on the multiplexer to improve signal-to-noise ratio, and at least one of the following: a proposed bearing analysis method, torsional vibration detection/analysis utilizing transient signals, improved integration using both analog and digital methods, adaptive scheduling techniques for continuous monitoring of analog data in the local environment, data collection parking capabilities, a self-contained data collection box, and SD card storage. In an embodiment, a data collection and processing system is provided that has IP front-end signal conditioning on the multiplexer to improve signal-to-noise ratio, and at least one of extended on-board statistics for continuous monitoring, use of ambient, local, and vibration noise for prediction, smart rerouting based on input data or alarms to enable simultaneous dynamic data for analysis or correlation, smart ODS and forwarding capabilities, and a hierarchical multiplexer. In embodiments, a data collection and processing system is provided having IP front-end signal conditioning on a multiplexer to improve signal-to-noise ratio, and having at least one of sensor overload identification, RF identification and inclinometer, continuous ultrasonic monitoring, machine pattern recognition based on fusion of remote analog industrial sensors, and cloud-based machine pattern analysis of state information from multiple analog industrial sensors to provide predicted state information for an industrial system. In embodiments, a data collection and processing system is provided having IP front-end signal conditioning on a multiplexer to improve signal-to-noise ratio, and having at least one of a cloud-based policy automation engine for IoT to create, deploy, and manage IoT devices, on-device sensor fusion and data storage for industrial IoT devices, a self-organizing data marketplace for industrial IoT data, and self-organization of data pools based on utilization and/or yield metrics. In embodiments, a data collection and processing system is provided that performs IP front-end signal conditioning on the multiplexer to improve signal-to-noise ratio and has at least one of: training AI models based on industry-specific feedback, a self-organizing swarm of industrial data collectors, an IoT distributed ledger, a self-organizing collector, and a network-sensitive collector. In embodiments, a data collection and processing system is provided that has IP front-end signal conditioning on the multiplexer to improve signal-to-noise ratio and has at least one of the following: a remotely organized collector; self-organizing storage for a multi-sensor data collector; self-organizing network coding for a multi-sensor data network; a wearable haptic user interface for an industrial sensor data collector with vibration, heat, electricity, and/or sound outputs; a heat map that displays data collected for AR/VR; and an automatically adjusted AR/VR visualization of data collected by the data collector.

In an embodiment, a data acquisition and processing system is provided with multiplexer continuous monitoring alarm functionality. In an embodiment, a data acquisition and processing system is provided with multiplexer continuous monitoring alarm functionality and at least one of the following: use of a distributed CPLD chip with a dedicated bus for logical control of multiple MUXes and data acquisition units; high amperage input capability through solid-state relays and design topology; power-down capability for at least one of the analog sensor channels and the component board; unique electrostatic protection for trigger and vibration inputs; and a precise voltage reference for the A/D zero reference. In an embodiment, a data acquisition and processing system is provided with multiplexer continuous monitoring alarm functionality and at least one of: a phase-locked loop bandpass tracking filter for obtaining low speed RPM and phase information; digital derivation of phase for the input and trigger channels using an on-board timer; a peak detector for autoscaling that is sent to a separate analog-to-digital converter for peak detection; and routing of either a raw or buffered trigger channel to another analog channel. In an embodiment, a data acquisition and processing system is provided with multiplexer continuous monitoring alarm functionality and at least one of the following: These are selected from the following: use of high input oversampling for the ΔΣ A/D for low sampling rate output to minimize AA filter requirements; use of a CPLD as a clock divider for the ΔΣ analog-to-digital converter to achieve low sampling rates without the need for digital resampling; long blocks of high sampling rate data for multiple sets of data acquired at different sampling rates; storage of calibration data with on-board card set maintenance history; and rapid route generation capability using hierarchical templates. In embodiments, a data acquisition and processing system is provided with multiplexer continuous monitoring and alarm functionality and at least one of intelligent management of data collection bands, a neural net expert system with intelligent management of data collection bands, use of a database hierarchy in sensor data analysis, and an expert system GUI graphical approach for defining intelligent data collection bands and diagnostics for the expert system. In embodiments, a data acquisition and processing system is provided with multiplexer continuous monitoring and alarm functionality and at least one of a graphical approach for inverse calculation definition, a proposed bearing analysis method, torsional vibration detection/analysis using transient signal analysis, and improved integration using both analog and digital methods. In some embodiments, a data collection and processing system is provided that has a multiplexer continuous monitoring alarm function and at least one of adaptive scheduling technology for continuous monitoring of analog data in a local environment, data collection parking functionality, a self-sufficient data collection box, and SD card storage. In some embodiments, a data collection and processing system is provided that has a multiplexer continuous monitoring alarm function and at least one of extensive on-board statistics for continuous monitoring, use of ambient, local, and vibration noise for prediction, smart route changes based on received data or alarms to enable simultaneous dynamic data for analysis or correlation, and smart ODS and forwarding functionality. In some embodiments, a data collection and processing system is provided that has a multiplexer continuous monitoring alarm function and at least one of hierarchical multiplexers, sensor overload identification, RF identification, and inclinometers, cloud-based machine pattern recognition based on fusion of remote analog industrial sensors, and predicted state information of an industrial system through machine pattern analysis of state information from multiple analog industrial sensors. In embodiments, a data collection and processing system is provided that has multiplexer continuous monitoring and alarm capabilities and includes at least one of a cloud-based policy automation engine for IoT with IoT device creation, deployment, and management, on-device sensor fusion and data storage for industrial IoT devices, a self-organizing data marketplace for industrial IoT data, self-organizing data pools based on usage and/or yield metrics, and training of AI models based on industry-specific feedback. In embodiments, a data collection and processing system is provided that has multiplexer continuous monitoring and alarm capabilities and includes at least one of a self-organizing swarm of industrial data collectors, an IoT distributed ledger, a self-organizing collector, a network-sensitive collector, and a remote-organizing collector. In embodiments, a data collection and processing system is provided that has multiplexer continuous monitoring and alarm capabilities and includes at least one of self-organizing storage for multi-sensor data collectors and self-organizing network coding for multi-sensor data networks. In an embodiment, a data collection and processing system is provided that includes at least one of a wearable tactile user interface for an industrial sensor data collector with multiplexed continuous monitoring alarm capabilities and vibration, heat, electrical, and/or sound outputs, a heat map for displaying collected data for AR/VR, and an automatically adjusting AR/VR visualization of data collected by the data collector.

In embodiments, a data acquisition and processing system is provided that uses a distributed CPLD chip with a dedicated bus for logic control of multiple MUXes and data acquisition sections. In embodiments, a data acquisition and processing system is provided that has high amperage input capability using solid-state relays and a design topology with the use of a distributed CPLD chip with a dedicated bus for logic control of multiple MUXes and data acquisition sections. In embodiments, a data acquisition and processing system is provided that uses a distributed CPLD chip with a dedicated bus for logic control of multiple MUXes and data acquisition sections and has power-down capabilities for at least one of analog sensor channels and component boards. In embodiments, a data acquisition and processing system is provided that uses a distributed CPLD chip with a dedicated bus for logic control of multiple MUXes and data acquisition sections and has unique electrostatic protection for trigger and vibration inputs. In embodiments, a data acquisition and processing system is provided that uses a distributed CPLD chip with a dedicated bus for logic control of multiple MUXes and data acquisition sections and has an accurate voltage reference for the A/D zero reference. In one embodiment, a data acquisition and processing system is provided that uses a distributed CPLD chip with a dedicated bus for logical control of multiple MUXes and data acquisition sections and has a phase-locked loop bandpass tracking filter for obtaining slow rotation speed and phase information. In another embodiment, a data acquisition and processing system is provided that uses a distributed CPLD chip with a dedicated bus for logical control of multiple MUXes and data acquisition sections and digitally derives phase for input and trigger channels using on-board timers. In another embodiment, a data acquisition and processing system is provided that uses a distributed CPLD chip with a dedicated bus for logical control of multiple MUXes and data acquisition sections and has a peak detector for autoscaling that is routed to a separate analog-to-digital converter for peak detection. In another embodiment, a data acquisition and processing system is provided that uses a distributed CPLD chip with a dedicated bus for logical control of multiple MUXes and data acquisition sections and routes raw or buffered trigger channels to other analog channels. In one embodiment, a data acquisition and processing system is provided that uses a distributed CPLD chip with a dedicated bus for logic control of multiple MUXes and data acquisition sections, and uses higher input oversampling for the delta-sigma A/D for a lower sampling rate output to minimize AA filter requirements. In another embodiment, a data acquisition and processing system is provided that uses a distributed CPLD chip with a dedicated bus for logic control of multiple MUXes and data acquisition sections, and uses a CPLD as a clock distributor for the delta-sigma analog-to-digital converter to achieve lower sampling rates without the need for digital resampling. In another embodiment, a data acquisition and processing system is provided that uses a distributed CPLD chip with a dedicated bus for logic control of multiple MUXes and data acquisition sections, and has long data blocks with high sampling rates, as opposed to multiple data sets acquired at different sampling rates. In another embodiment, a data acquisition and processing system is provided that uses a distributed CPLD chip with a dedicated bus for logic control of multiple MUXes and data acquisition sections, and has calibration data with maintenance history on a card set. In embodiments, a data acquisition and processing system is provided that uses distributed CPLD chips with dedicated buses for logical control of multiple MUXes and data acquisition sections and has rapid route creation capabilities using hierarchical templates. In embodiments, a data acquisition and processing system is provided that uses distributed CPLD chips with dedicated buses for logical control of multiple MUXes and data acquisition sections and intelligently manages the data acquisition band. In embodiments, a data acquisition and processing system is provided that uses distributed CPLD chips with dedicated buses for logical control of multiple MUXes and data acquisition sections and has a neural net expert system that uses intelligent management of the data acquisition band. In embodiments, a data acquisition and processing system is provided that uses distributed CPLD chips with dedicated buses for logical control of multiple MUXes and data acquisition sections and uses a database hierarchy for sensor data analysis. In embodiments, a data acquisition and processing system is provided that uses distributed CPLD chips with dedicated buses for logical control of multiple MUXes and data acquisition sections and has an intelligent data acquisition band and an expert system GUI graphical approach for defining expert system diagnostics. In embodiments, a data acquisition and processing system is provided that uses a distributed CPLD chip with a dedicated bus for logical control of multiple MUXes and data acquisition units and has a graphical approach for inverse calculation definition. In embodiments, a data acquisition and processing system is provided that uses a distributed CPLD chip with a dedicated bus for logical control of multiple MUXes and data acquisition units and has a proposed bearing analysis method. In embodiments, a data acquisition and processing system is provided that uses a distributed CPLD chip with a dedicated bus for logical control of multiple MUXes and data acquisition units and detects and analyzes torsional vibrations using transient signal analysis. In embodiments, a data acquisition and processing system is provided that uses a distributed CPLD chip with a dedicated bus for logical control of multiple MUXes and data acquisition units and has improved integration with both analog and digital methods. In embodiments, a data acquisition and processing system is provided that uses a distributed CPLD chip with a dedicated bus for logical control of multiple MUXes and data acquisition units and has an adaptive scheduling technique for continuous monitoring of analog data in a local environment. In embodiments, a data acquisition and processing system is provided that uses a distributed CPLD chip with a dedicated bus for logical control of multiple MUXes and data acquisition units and has a data acquisition parking function. In embodiments, a data acquisition and processing system is provided that uses a distributed CPLD chip with a dedicated bus for logical control of multiple MUXes and data acquisition units, resulting in a self-contained data acquisition box. In embodiments, a data acquisition and processing system is provided that uses a distributed CPLD chip with a dedicated bus for logical control of multiple MUXes and data acquisition units, resulting in SD card storage. In embodiments, a data acquisition and processing system is provided that uses a distributed CPLD chip with a dedicated bus for logical control of multiple MUXes and data acquisition units, resulting in extensive on-board statistics for continuous monitoring. In embodiments, a data acquisition and processing system is provided that uses a distributed CPLD chip with a dedicated bus for logical control of multiple MUXes and data acquisition units, resulting in ambient noise, local noise, and vibration noise prediction. In embodiments, a data acquisition and processing system is provided that uses a distributed CPLD chip with a dedicated bus for logical control of multiple MUXes and data acquisition units, resulting in smart rerouting based on input data or alarms, simultaneously providing dynamic data for analysis or correlation. In embodiments, a data collection and processing system is provided that uses a distributed CPLD chip with a dedicated bus for logical control of multiple MUXes and data acquisition sections and has smart ODS and forwarding capabilities. In embodiments, the system includes a distributed CPLD chip with a dedicated bus for logical control of multiple MUXes and data acquisition sections and a hierarchical multiplexer. In embodiments, a data collection and processing system is provided that uses a distributed CPLD chip with a dedicated bus for logical control of multiple MUXes and data acquisition sections and has sensor overload identification. In embodiments, a data collection and processing system is provided that uses a distributed CPLD chip with a dedicated bus for logical control of multiple MUXes and data acquisition sections and has RF identification and inclinometers. In embodiments, a data collection and processing system is provided that uses a distributed CPLD chip with a dedicated bus for logical control of multiple MUXes and data acquisition sections and has continuous ultrasonic monitoring. In embodiments, a data collection and processing system is provided that uses a distributed CPLD chip with a dedicated bus for logical control of multiple MUXes and data acquisition sections and has cloud-based machine pattern recognition based on the fusion of remote analog industrial sensors. In embodiments, a data collection and processing system is provided that uses distributed CPLD chips with dedicated buses for logical control of multiple MUXes and data acquisition units and performs cloud-based machine pattern analysis of status information from multiple analog industrial sensors to provide predicted status information for an industrial system. In embodiments, a data collection and processing system is provided that uses distributed CPLD chips with dedicated buses for logical control of multiple MUXes and data acquisition units and has a cloud-based policy automation engine for IoT to create, deploy, and manage IoT devices. In embodiments, a data collection and processing system is provided that uses distributed CPLD chips with dedicated buses for logical control of multiple MUXes and data acquisition units and has on-device sensor fusion and data storage for industrial IoT devices. In embodiments, a data collection and processing system is provided that uses distributed CPLD chips with dedicated buses for logical control of multiple MUXes and data acquisition units and has a self-organizing data marketplace for industrial IoT data. In embodiments, a data collection and processing system is provided that uses distributed CPLD chips with dedicated buses for logical control of multiple MUXes and data acquisition units and has self-organization of data pools based on utilization and/or yield metrics. In embodiments, a data collection and processing system is provided that uses distributed CPLD chips with dedicated buses for logical control of multiple MUXes and data acquisition units and trains AI models based on industry-specific feedback. In embodiments, a data collection and processing system is provided that uses distributed CPLD chips with dedicated buses for logical control of multiple MUXes and data acquisition units and a self-organized group of industrial data collectors. In embodiments, a data collection and processing system is provided that uses distributed CPLD chips with dedicated buses for logical control of multiple MUXes and data acquisition units and has an IoT distributed ledger. In embodiments, a data collection and processing system is provided that uses distributed CPLD chips with dedicated buses for logical control of multiple MUXes and data acquisition units and has a self-organizing collector. In embodiments, a data collection and processing system is provided that uses distributed CPLD chips with dedicated buses for logical control of multiple MUXes and data acquisition units and has a network-sensitive collector. In embodiments, a data collection and processing system is provided that uses distributed CPLD chips with dedicated buses for logical control of multiple MUXes and data acquisition units and has remotely organized collectors. In embodiments, a data collection and processing system with self-organizing storage for a multi-sensor data collector is provided using distributed CPLD chips with dedicated buses for logical control of multiple MUXes and data acquisition sections. In embodiments, a data collection and processing system with self-organizing network coding for a multi-sensor data network is provided using distributed CPLD chips with dedicated buses for logical control of multiple MUXes and data acquisition sections. In embodiments, a data collection and processing system with a wearable tactile user interface for an industrial sensor data collector is provided using distributed CPLD chips with dedicated buses for logical control of multiple MUXes and data acquisition sections, with vibration, heat, electricity, and/or sound outputs. In embodiments, a data collection and processing system with a heat map displaying collected data for AR/VR is provided using distributed CPLD chips with dedicated buses for logical control of multiple MUXes and data acquisition sections. In embodiments, a data collection and processing system with a heat map displaying collected data for AR/VR is provided using distributed CPLD chips with dedicated buses for logical control of multiple MUXes and data acquisition sections. In embodiments, a data collection and processing system with a heat map displaying collected data for AR/VR is provided using distributed CPLD chips with dedicated buses for logical control of multiple MUXes and data acquisition sections.

Embodiments include high amperage input capability using solid-state relays and design topology, power-down capability for analog sensor channels and/or component boards, unique electrostatic protection for trigger and vibration inputs, a high precision voltage reference for the A/D zero reference, a phase-locked loop bandpass tracking filter for low speed RPM and phase information, digital derivation of phase for input and trigger channels using an onboard timer, high input oversampling for the delta-sigma A/D to minimize the need for anti-aliasing (AA) filters, use of a CPLD as a clock distributor for the delta-sigma A/D to achieve low sampling rates without the need for digital resampling, and the ability to capture multiple data at different sampling rates at a high sampling rate. Acquiring long data blocks, storing calibration data using a card recording maintenance history, rapid route creation function using hierarchical templates, intelligent management of data collection bands, neural net expert system with intelligent management of data collection bands, use of database hierarchy in sensor data analysis, definition and diagnosis of intelligent data collection bands using expert system GUI, graphical approach for defining back calculations, proposed bearing analysis method, detection/analysis of torsional vibration using transient signal analysis, improved integration using both analog and digital methods, adaptive scheduling technique for continuous monitoring of analog data in the local environment, data collection parking function, self-sufficient data collection box, SD card storage, expansion onboard for continuous monitoring Statistical functions, use for predicting ambient noise, local noise, and vibration noise; smart rerouting based on input data and alarms to simultaneously obtain dynamic data for analysis and correlation; smart ODS and forwarding functions; hierarchical multiplexers; sensor overload identification; RF identification and inclinometers; continuous ultrasonic monitoring; cloud-based machine pattern recognition based on fusion of remote analog industrial sensors; cloud-based machine pattern analysis of status information from multiple analog industrial sensors to provide predicted status information for industrial systems; cloud-based policy automation engine for IoT (creation, deployment, management of IoT devices; on-device sensor fusion; data storage for industrial IoT devices; self-organizing data marketplace for industrial IoT data; data analysis based on utilization and/or yield metrics). A data collection and processing system is provided having one or more of: self-organizing data pools, training AI models based on industry-specific feedback, self-organizing swarms of industrial data collectors, IoT distributed ledgers, self-organizing collectors, network-sensitive collectors, remotely organizing collectors, network-sensitive collectors, remotely organized collectors, self-organizing storage for multi-sensor data collectors, self-organizing network coding for multi-sensor data networks, a wearable haptic user interface for industrial sensor data collectors with vibration, heat, electricity, and/or sound outputs, a heat map displaying collected data for AR/VR, or an auto-tuned AR/VR visualization of data collected by the data collectors.

In embodiments, a platform is provided having one or more of: cloud-based machine pattern recognition based on fusion of remote analog industrial sensors; cloud-based machine pattern analysis of state information from multiple analog industrial sensors to provide predicted state information for an industrial system; a cloud-based policy automation engine for IoT with IoT device creation, deployment, and management; on-device sensor fusion and data storage for industrial IoT devices; a self-organizing data marketplace for industrial IoT data; self-organizing data pools based on utilization and/or yield metrics; training of AI models based on industry-specific feedback; a self-organizing swarm of industrial data collectors; an IoT distributed ledger; a self-organizing collector; a network-sensitive collector; a remote organizing collector; self-organizing storage of multi-sensor data collectors; self-organizing network coding for multi-sensor data networks; a wearable haptic user interface for industrial sensor data collectors with vibration, thermal, electrical, and/or acoustic outputs; a heat map displaying collected data for AR/VR; or an AR/VR visualization automatically adjusted for data collected by the data collectors.

With reference to FIG. 14, a series of existing data sensing and processing systems comprising an industrial sensing, processing, and storage system 4500 includes a streaming data collector 4510 that may be configured to accept data in a range of formats as described herein. In an embodiment, the range of formats may include data format A 4520, data format B 4522, data format C 4524, and data format D 4528, which may be sourced from a range of sensors. Further, the range of sensors may include equipment A 4540, equipment B 4542, equipment C 4544, and equipment D 4548. The streaming data collector 4510 may be configured with processing capabilities that allow access to the individual formats while leveraging the streaming, routing, self-organizing storage, and other capabilities described herein.

FIG. 15 illustrates a method and system 4600 for industrial machine sensor data streaming collection, processing, and storage that facilitates the use of a streaming data collector 4610 to collect and acquire data from legacy equipment 4620 and streaming equipment 4622. The legacy instruments 4620 and their data methods may capture and provide data that is limited to a particular range of frequencies, etc., due to legacy systems and acquisition procedures, such as existing data methods described above. The streaming data collector 4610 may be configured to capture streaming equipment data 4632 as well as legacy equipment data 4630. The streaming data collector 4610 may also be configured to capture current streaming equipment 4620 and legacy equipment 4622 and sensors using current and legacy data methods. These embodiments may be useful in migration applications from legacy equipment and processing to streaming equipment and processing, which may be current or desired equipment or methods. In embodiments, streaming data collector 4610 may be configured to process legacy device data 4630 so that it can be stored in a manner compatible with streaming device data 4632. Streaming data collector 4610 may process or parse streamed device data 4632 based on legacy device data 4630 to generate at least one extract 4642 of the streamed data that is compatible with legacy device data 4630, which can be processed into translated legacy data 4640. In embodiments, extracted data 4650, which may include extracted portions of translated legacy data 4652 and streamed data 4654, may be stored in a format that facilitates access and processing, such as by legacy instrument data processing and further processing that can emulate legacy instrument data processing methods. Also, in embodiments, portions of translated legacy data 4652 may be stored in a format that facilitates processing in a different manner that can take advantage of the higher frequency, resolution, and data volume possible with streaming devices.

FIG. 16 shows an alternative embodiment illustrating a method and system 4700 for streaming, collecting, processing, and storing industrial machine sensor data that facilitates integration of legacy equipment and processing. In an embodiment, a streaming data collector 4710 may be connected to an industrial machine 4712 and may include multiple sensors, such as streaming sensors 4720 and 4722, that may be configured to sense aspects of the industrial machine 4712 associated with at least one moving part of the machine 4712. The sensors 4720 and 4722 (or more) may communicate with one or more streaming devices 4740 that can facilitate streaming of data from one or more of the sensors to the streaming data collector 4710. In an embodiment, the industrial machine 4712 may also interface with or include one or more legacy equipment 4730 that can capture data associated with one or more moving parts of the industrial machine 4712 and store that data in a legacy data storage facility 4732.

In an embodiment, the frequency and/or resolution detection facility 4742 may be configured to facilitate detecting information about legacy instrument source data, such as the frequency range of the data or the resolution of the data. The detection facility 4742 may operate on data directly from the legacy instrument 4730 or on data stored in the legacy storage facility 4732. The detection facility 4742 may communicate detected information about the legacy instrument 4730, its source data, its stored data 4732, etc. to the streaming data collector 4710. Alternatively, the detection facility 4742 may access information about the frequency range, resolution, etc. that characterize the source data from the legacy instrument 4730 and/or may access it from a portion of the legacy storage facility 4732.

In embodiments, the streaming data collector 4710 may be configured with one or more automated processors, algorithms, and/or other data methods to match information captured by one or more legacy instruments 4730 with a portion of the data being provided by one or more streaming devices 4740 from one or more industrial machines 4712. Data from the streaming devices 4740 may include a wider range of frequencies and resolution than the legacy instrumentation 4730-sourced data, and therefore filtering and other such functions may be implemented to extract data from the streaming devices 4740 that corresponds in terms of frequency range, resolution, etc. to the legacy instrumentation 4730-sourced data. In embodiments, the configured streaming data collector 4710 may generate multiple streams of data, including a stream of data that may correspond to the stream of data from the streaming devices 4740 and another stream of data that is compatible in some aspects with the legacy instrumentation source data and the infrastructure for ingesting and automatically processing it. Alternatively, the streaming data collector 4710 may output data in a mode other than as a stream, such as a batch, aggregation, or summary.

The configured streaming data collector 4710 may communicate with a stream storage facility 4764 for storing at least one of the data output from the streaming device 4710 and data extracted therefrom that may be compatible in some aspects with the legacy instrument 4730 sourced data. The configured legacy compatible output streaming data collector 4710 may also be provided with a format adapter facility 4748, 4760 that configures, adapts, reformats, and otherwise adjusts the legacy compatibility data so that the legacy compatibility data can be stored in the legacy compatibility storage facility 4762 so that the legacy processing facility 4744 can perform data processing methods on the data, such as the legacy compatibility storage facility 4762, configured to process the legacy instrument 4730 sourced data. In embodiments in which the legacy compatible data is stored in the stream storage facility 4764, the legacy processing facility 4744 may also automatically process this data after it has optionally been processed by the format adapter 4760. By arranging the data collection, streaming, processing, formatting, and storage elements to provide data in a format that is fully compatible with the source data from the legacy equipment, migration from legacy systems is simplified and the source data from the legacy equipment can be easily compared with newly acquired data (which has more content) without losing the legacy value of the source data from the legacy equipment 4730.

FIG. 17 depicts an alternative embodiment of the method and system 4800 described herein for streaming, collecting, processing, and storing industrial machine sensor data that may be compatible with collecting and processing legacy equipment data. In an embodiment, processing industrial machine sensed data may be accomplished in various ways, including aligning legacy and streaming sources of data, such as aligning stored legacy data with streaming data, aligning stored legacy data with streams of sensed data, and aligning legacy data with streaming data as it is being collected. In an embodiment, the industrial machine 4810 may include, communicate with, or be integrated with one or more stream data sensors 4820 capable of sensing aspects of the industrial machine 4810, such as aspects of one or more moving parts of the machine. The industrial machine 4810 may also communicate with, include, or be integrated with one or more legacy data sensors 4830 capable of sensing similar aspects of the industrial machine 4810. In embodiments, one or more legacy data sensors 4830 may provide sensed data to one or more legacy data collectors 4840. The stream data sensor 4820 may encompass all aspects (i.e., a richer signal) and generate an output that is compatible with the sensed data from the legacy data sensor 4830. The stream data sensor 4820 may provide compatible data to the legacy data collector 4840. By mimicking the legacy data sensor 4830 or its data stream, the stream data sensor 4820 can replace (or serve as a suitable replica for) one or more legacy data sensors, such as during an upgrade of an industrial machine's sensing and processing system. Frequency ranges, resolutions, etc. may be mimicked by the stream data sensor 4820. The stream data is adapted to ensure that all forms of legacy data are captured or derived from the stream data. In embodiments, format conversion can also be performed by the stream data sensor 4820, if necessary. The stream data sensor 4820 may also generate an alternative data stream suitable for collection by the stream data collector 4850. In an embodiment, such an alternative data stream may be a superset of the legacy data sensor data in at least one or more of the frequency range, resolution, time period for sensing the data, etc.

In an embodiment, the industrial machine's sensory data processing facility 4860 may perform a wide range of sensory data processing methods, some of which may generate output that is compatible with data from the legacy data sensors 4830 and may satisfy legacy sensory data processing requirements. To facilitate use of the processing facility's 4860's extensive data processing capabilities, the legacy data and stream data may need to be aligned so that compatible portions of the stream data can be extracted for processing, such as in a legacy-compatible manner. In an embodiment, FIG. 17 depicts three different approaches for aligning the stream data to the legacy data. A first alignment approach 4862 involves aligning the legacy data output by the legacy data collector 4840 with the stream data output by the stream data collector 4850. Once the data is provided by the legacy data collector 4840, aspects of the data, such as resolution, frequency, duration, etc., may be detected and used as controls for processing methods to identify portions of the stream of data from the stream data collector 4850 that are intentionally compatible with the legacy data. The processing facility 4860 may apply one or more legacy compatible methods to the identified portions of the stream data to extract data that can be readily compared to or referenced against the legacy data.

In an embodiment, the second alignment method 4864 may include aligning the streaming data with data from the legacy storage facility 4882. In an embodiment, the third alignment method 4868 may include aligning the stored stream data from the stream storage facility 4884 with the legacy data from the legacy data storage facility 4882. In each of methods 4862, 4864, 4868, the alignment data may be determined by processing the legacy data to detect aspects such as resolution, duration, frequency range, etc. Alternatively, the alignment may be performed by alignment equipment, such as equipment using methods 4862, 4864, 4868, which may receive legacy data description information such as legacy frequency range, duration, resolution, etc., or may be configured with the legacy data description information.

In an embodiment, the industrial machine sensing data processing facility 4860 can access legacy-compatible methods and algorithms that may be stored in the legacy data and method storage facility 4880. These methods, algorithms, or other data in the legacy algorithm storage facility 4880 may also be a source of alignment information that may be communicated by the industrial machine sensing data processing facility 4860 to various alignment facilities with methods 4862, 4864, 4868. By having access to the legacy-compatible algorithms and methods, the data processing facility 4860 can facilitate processing legacy data, stream data compatible with legacy data, or portions of stream data representative of legacy data to generate legacy-compatible analytics.

In embodiments, the data processing facility 4860 may perform a wide variety of other sensed data processing methods, such as wavelet derivation, to generate streaming data analytics 4892. In embodiments, the streaming data collector 102, 4510, 4610, 4710 (FIGS. 3, 6, 14, 15, 16) or the data processing facility 4860 may include portable algorithms, methods, and inputs that may be defined and extracted from the data stream. In many instances, a user or company may already have existing, effective methods related to analyzing a particular machine or asset. These existing methods may be imported into the configured streaming data collector 102, 4510, 4610, 4710 or the data processing facility 4860 as portable algorithms or methods. Data processing as described herein for the configured streaming data collector 102, 4510, 4610, 4710 may contextualize the algorithm or method, then extract data from the stream, and adapt it to data methods from legacy acquisition or legacy acquisition technologies. In embodiments, the streaming data collectors 102, 4510, 4610, 4710 may be compatible with many types of systems and with systems of varying degrees of importance.

An exemplary industrial machine deployment of the methods and systems described herein will now be described. The industrial machine may be a gas compressor. In one example, the gas compressor may operate an oil pump on a very large turbomachine, such as a very large turbomachine containing a 10,000 HP motor. The oil pump is considered a critical system because its failure could shut down the entire plant. The gas compressor in this example may operate four stages at a very high frequency, such as 36,000 RPM, and include tilt pad bearings that ride on an oil film. The oil pump in this example uses roller bearings, and if a predicted failure is not detected by the user, it could cause the oil pump to stop operating and the entire turbomachine to fail. Continuing with this example, the streaming data collectors 102, 4510, 4610, and 4710 may collect vibration-related data, such as casing vibration and proximity probe vibration. Other examples of bearing-driven industrial machines include generators, power plants, boiler feed pumps, fans, forced draft fans, and induced draft fans. Streaming data collectors 102, 4510, 4610, 4710 for bearing systems used in the industrial gas industry may support predictive analysis on motors, such as performed by a model-based expert system - for example, using voltage, current, and vibration as analysis metrics.

Another exemplary industrial machine deployment may be a motor and a streaming data collector 102, 4510, 4610, 4710 that can assist in analyzing the motor by collecting, for example, motor voltage and current data.

Yet another exemplary industrial machine deployment may include oil quality sensing. The industrial machine may perform oil analysis, and the streaming data collectors 102, 4510, 4610, 4710 may assist in, for example, searching for metal fragments in the oil.

The methods and systems described herein can also be used in combination with a model-based system. The model-based system may be integrated with a proximity probe. The proximity probe may be used to sense machine problems and shut down the machine due to the detected problem. The model-based system integrated with the proximity probe can measure peak waveforms and send a signal to shut down the machine based on the peak waveform measurements.

Companies that operate industrial machinery may operate in many diverse industries. These industries may include those that operate manufacturing lines, those that provide computing infrastructure, those that support financial services, and those that provide HVAC equipment. These industries may be highly sensitive to lost uptime and the costs that result from lost uptime. HVAC equipment manufacturers, in particular, are interested in data related to ultrasound, vibration, infrared, etc., and may be able to obtain much more information about machine performance related to these metrics using methods and systems for streaming collection of industrial machine sensing data than traditional systems.

The methods and systems described herein for streaming, collecting, processing, and storing industrial machine sensor data may be configured to operate and integrate with existing data collection, processing, and storage systems and may include a method for capturing multiple streams of sensed data from sensors deployed to monitor an aspect of the industrial machine associated with at least one moving part of the industrial machine, at least one of the streams including multiple frequencies of data. The method may include identifying a subset of data from at least one of the multiple streams that corresponds to data representing at least one predefined frequency. The at least one predefined frequency is represented by a set of data collected from an alternate sensor deployed to monitor the aspect of the industrial machine associated with at least one moving part of the machine. The method may further include processing the identified data with data processing equipment configured to process the identified data with a data method configured to be applied to the set of data collected from the alternate sensor. Finally, the method may include storing at least one of the streams of data, the identified subset of data, and results of processing the identified data in an electronic dataset.

The method and system may include applying data captured from a sensor deployed to monitor an aspect of an industrial machine associated with at least one moving part of the machine, the data being captured at a predetermined line resolution covering a predetermined frequency range, to frequency matching equipment to identify a subset of data streamed from other sensors deployed to monitor the aspect of the industrial machine associated with at least one moving part of the machine, the streamed data including a plurality of line resolutions and frequency ranges, the identified subset of data corresponding to the line resolution and the predetermined frequency range. The method may include storing the subset of data in an electronic data record in a format corresponding to the format of the data captured at the predefined line resolutions, and signaling the existence of the stored subset of data to data processing equipment. The method may optionally include processing the subset of data using at least one of an algorithm, method, model, and pattern recognizer associated with processing data captured at a predefined line resolution covering a predefined frequency range.

The method and system may include a method for identifying a subset of streamed sensor data. The sensor data is captured from sensors deployed to monitor an aspect of an industrial machine associated with at least one moving part of the machine. The subset of streamed sensor data is lines of a predefined resolution for a predefined frequency range. The method includes establishing a first logical path for electronic communication between a first computing facility performing the identification and a second computing facility. The identified subset of the streamed sensor data is communicated exclusively via the established first logical route when communicating the subset of streamed sensor data from the first facility to the second facility. The method may further include establishing a second logical path for electronic communication between the first computing facility and the second computing facility for at least a portion of the streamed sensor data that is not the identified subset. The method may further include establishing a third logical path for electronic communication between the first computing facility and the second computing facility for at least one portion of the streamed sensor data that includes the identified subset and at least one other portion of the data that is not represented by the identified subset.

The method and system may include a first data sensing and processing system that captures first data from a first set of sensors deployed to monitor an aspect of the industrial machine associated with at least one moving part of the machine, the first data covering a set of lines of resolution and a set of frequency ranges. The system may also include a second data sensing and processing system that captures and streams second data from a second set of sensors deployed to monitor an aspect of the industrial machine associated with at least one moving part of the machine, the second data covering a plurality of lines of resolution including the set of lines of resolution and a plurality of frequencies including the frequency ranges. The system may enable: (1) selecting a portion of the second data corresponding to the set of lines of resolution and the frequency range of the first data; and (2) processing the selected portion of the second data with the first data sensing and processing system.

The method and system may include a method for automatically processing a portion of a stream of sensed data. Sensory data received from a first set of sensors deployed to monitor an aspect of the industrial machine associated with at least one moving part of the machine is responsive to an electronic data structure that facilitates extracting a subset of the stream of sensed data corresponding to a set of sensory data received from a second set of sensors deployed to monitor an aspect of the industrial machine associated with at least one moving part of the machine. The set of sensed data is constrained to a frequency range. The stream of sensed data includes a range of frequencies that exceeds the frequency range of the set of sensed data. The processing includes performing a data method on the portion of the stream of sensed data that is constrained to the frequency range of the set of sensed data. The data method is configured to process the set of sensed data.

The method and system may include receiving first data from a sensor deployed to monitor an aspect of an industrial machine associated with at least one moving part of the machine. The method may further include: (1) detecting at least one of a frequency range and a resolution line represented by the first data; and (2) receiving a stream of data from the sensor deployed to monitor the aspect of the industrial machine associated with at least one moving part of the machine. The stream of data includes a plurality of frequency ranges and a plurality of resolution lines that exceed the frequency range and resolution line represented by the first data. Extracting from the stream of data a set of data corresponding to at least one of the frequency range and resolution line represented by the first data, and processing the extracted set of data with a data processing method configured to process data within the frequency range and resolution line of the first data.

The methods and systems disclosed herein can include, connect to, or integrate with data acquisition equipment, and in many embodiments, FIG. 18 illustrates a method and system 5000 that includes a data acquisition (DAQ) streaming device 5002, also known as SDAQ. In embodiments, the output from sensors 5010, 5012, 5014 can be of various types, including vibration, temperature, pressure, ultrasound, etc. In many examples, one of the sensors may be used. In further examples, many of the sensors may be used, and their signals may be used individually or in predetermined combinations and/or at predetermined intervals, circumstances, settings, etc.

In embodiments, output signals from sensors 5010, 5012, and 5014 may be provided to instrument inputs 5020, 5022, and 5024 of DAQ device 5002, or may be configured with additional streaming functionality 5028. In many of these examples, output signals from sensors 5010, 5012, and 5014, or more, as applicable, may be conditioned as analog signals prior to digitization, at least with respect to scaling and filtering. The signals may then be digitized by analog-to-digital converter 5030. Signals received from all relevant channels (i.e., one or more channels may be switched on manually, by alarm, by path, etc.) may be simultaneously sampled at a predetermined rate sufficient to perform the maximum desired frequency analysis, which may be adjusted and reconditioned as necessary or otherwise held constant to ensure compatibility or conformance with other relevant data sets. In embodiments, signals are sampled as follows: This allows for sufficient individual sampling before further post-processing at a lower sampling rate.

In embodiments, data may be streamed from a collection of points, after which a next set of data may be collected from additional points according to a predetermined sequence, route, path, etc. In many examples, sensors 5010, 5012, 5014 or more may move to a next location according to a predetermined sequence, route, pre-deployed configuration, etc. In certain examples, not all of sensors 5010, 5012, 5014 may move, and thus some may remain fixed in place and be used for reference phase detection, etc.

In embodiments, a multiplexer (mux) 5032 may be used to switch between acquiring the next point, mixing two methods, or combining acquisition patterns, other predetermined routes, etc. Multiplexers 5032 may be stackable in a ladder-like fashion to effectively accommodate more channels than the DAQ device 5002 provides. In an example, the DAQ device 5002 may provide 8 channels, while the multiplexer 5032 may be stacked to provide 32 channels. Further variations are possible with one or more multiplexers. In embodiments, the multiplexer 5032 may be fed to the DAQ device 5002 via the device input 5034. In embodiments, the DAQ device 5002 may include a controller 5038, which may take the form of an on-board controller, a PC, other connected devices, a network-based service, or a combination thereof.

In embodiments, the sequences and panel conditions used to govern the data collection process may be retrieved from a multimedia probe (MMP) and probe control, sequence, and analysis (PCSA) information store 5040. In embodiments, the information store 5040 may be on-board the DAQ instrument 5002. In embodiments, the contents of the information store 5040 may be obtained via a cloud network facility, from other DAQ instruments, from other connected devices, from the sensed machine, from other relevant sources, and combinations thereof. In embodiments, the information store 5040 may include items such as the hierarchical structural relationships of a machine; for example, a machine may include certain pieces of equipment, each of which may include one or more shafts, each of which may have multiple associated bearings. Each of these types of bearings may be monitored by a particular type of transducer or probe, according to one or more specific predetermined sequences (paths, routes, etc.), and with one or more specific panel conditions that may be set on one or more DAQ instruments 5002. In this example, the panel conditions include hardware-specific switch settings and other acquisition parameters. In many examples, collection parameters include, but are not limited to, sampling rate, AC/DC coupling, voltage range and gain, integration, high-pass and low-pass filtering, anti-aliasing filtering, ICP transducers and other integrated circuit piezoelectric transducers, 4-20 mA loop sensors, etc. In embodiments, information store 5040 may also include machine-specific characteristics important for proper analysis, such as gear teeth, number of blades on a pump impeller, number of motor rotor bars, bearing-specific parameters needed to calculate bearing frequency, revolutions per minute information for all rotating elements and their RPM range multiples, etc. Information in the information store may also be used to extract stream data 5050 for permanent storage.

Based on instructions from the DAQ API software 5052, the digitized waveform may be uploaded using the DAQ driver service 5054 of the driver installed on the DAQ device 5002. In embodiments, the data may then be provided to a raw data server 5058, which can store the stream data 5050 in a stream data repository 5060. In embodiments, this data storage area is typically for storage until the data is copied from the DAQ device 5002 and verified. The DAQ API 5052 may also instruct the local data control application 5062 to extract and process recently acquired stream data 5050 and convert it to the same or a lower sampling rate long enough to provide one or more desired resolutions. By way of example, this data may be converted to a spectrum, averaged, processed in various ways, and stored, at least temporarily, as extracted/processed (EP) data 5064. It will be understood in light of this disclosure that legacy data may require unique sampling rates and resolutions to ensure compatibility, and that in many cases this sampling rate may not be integer proportional to the acquired sampling rate. It will also be appreciated in light of this disclosure that this may be particularly relevant to order sampled data where the sampling frequency is directly related to an external frequency (typically the execution speed of the machine or its local components) rather than more standard sampling rates employed by the DAQ equipment's internal crystal, clock functions, etc. (e.g., Fmax values of 100, 200, 500, 1K, 2K, 5K, 10K, 20K, etc.).

In embodiments, the extraction/processing (EP) alignment module 5068 of the local data control application 5062 may be able to fractionally adjust the sampling rate to these non-integer ratio rates, which meets a key requirement for making the data compatible with legacy systems. In embodiments, the length of the processed data may be adjustable, so that fractional rates can be more easily converted to integer ratio rates. It will be appreciated in light of this disclosure that if the data is not streamed but is simply stored as spectra with a standard or predetermined Fmax, in some circumstances it may not be possible to accurately convert it back to custom sampled data. It will also be appreciated in light of this disclosure that internal identification issues may also need to be accommodated. In many instances, the stream data may be converted to the appropriate sampling rate and resolution as described and stored (albeit temporarily) in the EP legacy data repository 5070 to ensure compatibility with the legacy data.

To support legacy data identification issues where an automated process for identity conversion does not exist (either partially or entirely), many embodiments include a user input module 5072. In such instances, one or more legacy systems (i.e., existing data acquisition) may be characterized by the data being imported being in a fully standardized format, such as Mimosa format or another similar format. Furthermore, sufficient indentation of the legacy data and/or the machine or machines on which the legacy data was generated may be required to complete an identity mapping table 5074 for associating and linking portions of the legacy data with portions of the newly acquired streamed data 5050. In many instances, an end user and/or legacy vendor may supply sufficient information to complete at least a portion of a functional identity (ID) mapping table 5074, thus providing the necessary database schema for the legacy system's raw data used to compare, analyze, and manipulate the newly streamed data 5050.

In an embodiment, the local data control application 5062 may direct streaming data as well as extracted/processed (EP) data to a cloud network facility 5080 via wired or wireless transmission. From the cloud network facility 5080, other devices may access, receive, and maintain data, including data from a master raw data server (MRDS) 5082. The movement, distribution, storage, and retrieval of data remote to the DAQ device 5002 may be coordinated by a cloud data management service ("CDMS") 5084.

FIG. 19 illustrates additional methods and systems including a DAQ device 5002 accessing associated cloud-based services. In embodiments, the DAQ API 5052 may control not only the data acquisition process but also its sequencing. By these examples, the DAQ API 5052 may provide the ability to edit the process, view plots of the data, control the processing of that data, view output data in its myriad forms, analyze this data, including expert analysis, and communicate with external devices via a local data control application 5062 and with a CDMS 5084 via a cloud network facility 5080. In embodiments, the DAQ API 5052 may also govern the movement of data, its filtering, and many other housekeeping functions.

In embodiments, the expert analysis module 5100 may generate reports 5102 that can use machine- or measurement-point-specific information from the information store 5040 to analyze the stream data 5050 using a local data control application 5062 with a stream data analyzer module 5104 and an extraction/processing ("EP") alignment module 5068. In embodiments, the expert analysis module 5100 may generate new alarms associated with the stream data 5050 or populate alarm settings in the alarm module 5108. In embodiments, the stream data analyzer module 5104 may provide manual or automated mechanisms for extracting meaningful information from the stream data 5050 in various plot and report formats. In embodiments, supervisory control of the expert analysis module 5100 is provided by the DAQ API 5052. In a further example, the expert analysis module 5100 may be provided (in whole or in part) via a cloud network facility 5080. In many instances, a cloud-based expert analysis module 5100 may be used over a locally deployed expert analysis module 5100 for a variety of reasons, such as using the latest software version, having more processing power, or referencing a larger amount of historical data. In many instances, it is important that the expert analysis module 5100 be available when an internet connection cannot be established, so having such redundancy can be important for seamless and time-efficient operation. To this end, many of the modular software applications and databases available on the DAQ device 5002 are implemented with redundancy of system components, providing operational robustness by providing connectivity to cloud services when needed, as well as operating well in isolated scenarios where connectivity is unavailable, or may be intentionally unavailable to enhance security, etc.

In embodiments, DAQ instrument acquisition may require a real-time operating system ("RTOS") for the hardware, particularly for streamed, gap-free data acquired by a PC. In some instances, the requirement for an RTOS may result in (or require) expensive custom hardware and software capable of running such a system. In many embodiments, such expensive custom hardware and software can be avoided, and an RTOS can be effectively and satisfactorily implemented using a standard Windows operating system or similar environment, including system interrupts in the procedural flow of specialized applications contained in such an operating system.

The methods and systems disclosed herein may include, connect to, or integrate with one or more DAQ devices. In many embodiments, FIG. 20 illustrates a method and system 5150 including a DAQ device 5002 (also known as streaming DAQ or SDAQ). In an embodiment, the DAQ device 5002 may effectively and sufficiently implement an RTOS using a standard Windows operating system (or other similar personal computing system), which may include a software driver configured in a first-in, first-out (FIFO) memory area 5152. The FIFO memory area 5152 can maintain and retain information long enough to handle the worst-case interrupts that may be encountered from the local operating system to effectively provide the RTOS. In many instances, configurations on the local personal computer or connected device may be maintained to minimize operating system interrupts. To support this, configurations may be maintained, controlled, or adjusted to eliminate (or isolate from) exposure to extreme environments where operating system interrupts may be problematic. In an embodiment, the DAQ device 5002 may generate a notification, alarm, message, etc. to notify the user when any gap errors are detected. In many of these instances, such errors may be shown to be rare, and even if an error does occur, the user may know when the error occurred and adjust the data if such a situation occurs.

In an embodiment, the DAQ device 5002 may maintain a sufficiently large FIFO memory area 5152 in which it can buffer incoming data so that data acquisition is not affected by operating system interrupts. It will be understood in light of this disclosure that the predetermined size of the FIFO memory area 5152 may be based on operating system interrupts, including those for writing data to disk or SSD, Windows system and application functions such as plotting, GUI interaction and standard Windows tasks, and low-level driver tasks such as servicing the DAQ hardware and acquiring data in bursts.

In an embodiment, a computer, controller, connected device, etc., which may be included in the DAQ instrument 5002, may be configured to acquire data from one or more hardware devices via a USB port, FireWire, Ethernet, etc. In an embodiment, the DAQ driver service 5054 may be configured to periodically deliver data so as not to miss data, i.e., to facilitate providing a channel-specific FIFO memory buffer that is gap-free. In an embodiment, the DAQ driver service 5054 may be configured to maintain a larger (than-device) channel-specific FIFO area 5152 that fills with new data obtained from the device. In an embodiment, the DAQ driver service 5054 may be configured to employ a further process in which the raw data server 5058 retrieves data from the FIFO 5110 and writes it as a continuous stream to a non-volatile storage area, such as a stream data repository 5060, which may be configured as one or more disk drives, SSDs, etc. In an embodiment, the FIFO 5110 may be configured to include start and stop markers or pointers to mark the location where the most recent stream was written. In these examples, the FIFO end marker 5114 may be configured to mark the end of the most recent data until it reaches the end of the spooler, after which it always cycles around and wraps around. In these examples, once the spooler is full, the FIFO 5110 always has 1 megabyte (or other configured amount) of the most recent data available. It will be understood that further configurations of FIFO memory space may be employed in light of this disclosure. In embodiments, the DAQ driver service 5054 may be configured to pipe the most recent data to a higher-level application for processing, graphing, and analysis purposes using the DAQ API 5052. In some examples, this data is not required to be gap-free, although even in these examples, it is useful to identify and mark gaps in the data. Furthermore, these data updates may be configured to occur frequently enough so that the user perceives the data as live. In many embodiments, the raw data is flushed to non-volatile storage without gaps for at least a predetermined period of time, an example of which may be from approximately 30 seconds to four hours or more. In light of this disclosure, it will be appreciated that many devices and their components may contribute to the relative required duration of a gap-free stream of data, which may be four hours or more in cases where there are many relatively low rates, where non-periodic transient activity occurs over a relatively long time frame, where duty cycles only permit operation in the relevant range for limited durations, etc.

Referring to FIG. 19, the stream data analyzer module 5104 may provide manual or extraction of information from the data stream in a variety of plot and report formats. In embodiments, resampling, filtering (including anti-aliasing), transfer functions, spectral analysis, envelopes, averaging, peak detection functions, and a host of other signal processing tools may be available to the analyst to analyze the stream data and generate very large arrays of snapshots. In light of the present disclosure, it will be appreciated that scheduling the collection of snapshots in advance, i.e., during initial data acquisition for the measurement points in question, creates a much larger array of snapshots than was previously possible.

In light of the present disclosure, it will be appreciated that vibration data sampling rates of up to 100 kHz (or higher in some scenarios) are also available for non-vibration sensors. In doing so, it will be further appreciated in light of the present disclosure that streaming data at these sampling rates for such periods can uncover new patterns to analyze. It will also be appreciated in light of the present disclosure that various sensors used for machine condition monitoring may provide measurements closer to static levels rather than fast-acting dynamic signals. In some cases, it may be necessary to use transducers with faster response times before faster sampling rates can be achieved.

In many embodiments, sensors may have relatively static outputs, such as temperature, pressure, or flow rate, that can be analyzed using dynamic signal processing systems and methods such as those disclosed herein. It will be understood in light of this disclosure that in many instances, the time scale may be slowed. In many instances, a collection of temperature measurements taken approximately every minute over two weeks or more may be analyzed for fluctuations, either alone or in conjunction with or fused with other related sensors. In these instances, DC or average levels may be omitted from all readings (e.g., by subtraction), and the resulting delta measurements may be processed (e.g., by Fourier transform). From these instances, the resulting spectral lines may be correlated to specific machine operation or other symptoms present in the industrial system process. In further examples, other techniques include envelope analysis, which looks for modulations; wavelets, which look for short-lived spectral patterns (e.g., bursts); and cross-channel analysis, which looks for correlations with other sensors, including vibrations.

FIG. 21 illustrates a DAQ instrument 5400 that may be integrated with one or more analog sensors 5402 and an endpoint node 5404 to provide a streaming sensor 5410 or smart sensor that may capture analog signals, then process and digitize them, and then transmit them to one or more external monitoring systems 5412 in many embodiments that may be connected to, interface with, or integrated with the methods and systems disclosed herein. The monitoring system 5412 may include a streaming hub server 5420 that may communicate with a CDMS 5084. In embodiments, the CDMS 5084 may contact, use, and integrate with cloud data 5430 and cloud services 5432 accessible via one or more cloud network facilities 5080. In embodiments, the streaming hub server 5420 may connect to a DAQ instrument 5442, an endpoint node 5444, and another streaming sensor 5440 that may include one or more analog sensors, such as an analog sensor 5448. The stemming hub server 5420 can connect to other streaming sensors, such as a DAQ instrument 5462, an endpoint node 5464, and a streaming sensor 5460, which can include one or more analog sensors, such as an analog sensor 5468.

In embodiments, there may be additional streaming hub servers, such as streaming hub server 5480, that may connect with other streaming sensors, such as streaming sensor 5490, which may include DAQ instrument 5492, endpoint node 5494, and one or more analog sensors, such as analog sensor 5498. In embodiments, streaming hub server 5480 may also connect with other streaming sensors, such as streaming sensor 5500, which may include DAQ instrument 5502, endpoint node 5504, and one or more analog sensors, such as analog sensor 5508. In embodiments, the transmission may include an averaged overall level, or in other examples, a dynamic signal sampled at a predetermined and/or fixed rate. In embodiments, streaming sensors 5410, 5440, 5460, 5490, and 5500 may be configured to acquire analog signals and then apply signal conditioning to those analog signals, including combining, averaging, integrating, differentiating, scaling, various types of filtering, and the like. The streaming sensors 5410, 5440, 5460, 5490, and 5500 may be configured to digitize analog signals at an acceptable rate and resolution (number of bits) and further process the digitized signals as needed. The streaming sensors 5410, 5440, 5460, 5490, and 5500 may be configured to transmit digitized signals at predetermined, adjustable, and re-adjustable rates. In embodiments, the streaming sensors 5410, 5440, 5460, 5490, and 5500 are configured to acquire, digitize, process, and transmit data at a sufficiently effective rate so that a relatively consistent stream of data can be maintained for a reasonable period of time so that multiple valid analyses can be demonstrated. In many embodiments, there will be no gaps in the data stream, and the length of the data should be relatively long, ideally of unlimited duration, although practical considerations typically dictate that the stream be terminated. It will be appreciated in light of the present disclosure that this long duration data stream, with substantially no gaps in the stream, contrasts with more commonly used burst collection, in which data is collected for a relatively short period (i.e., a short burst collection), followed by a pause, perhaps followed by another burst collection, and so on. In commonly used collections of data collected over non-contiguous bursts, data would be collected at a slow rate for low-frequency analysis and at a higher frequency for high-frequency analysis. In many embodiments of the present disclosure, by contrast, streaming data is collected (i) once, (ii) at the most useful possible sampling rate, and (iii) for a long enough time that low-frequency as well as high-frequency analysis can be performed. To facilitate the collection of streaming data, sufficient storage memory must be available in one or more streaming sensors, such as streaming sensors 5410, 5440, 5460, 5490, 5500, so that new data can be externally offloaded to another system before the memory overflows. In embodiments, the data in this memory will be stored in and accessed from a “first-in, first-out” (“FIFO”) mode. In these examples, the memory with the FIFO area may be dual-ported so that the sensor controller can write to one portion while the external system reads from a different portion. In embodiments, data flow traffic may be managed by semaphore logic.

In light of this disclosure, it will be appreciated that vibration transducers with large masses have a narrower linear frequency response range because the natural resonance of the probe decreases inversely with the square root of the mass. Therefore, because the resonant response is inherently nonlinear, vibrators with low natural frequencies have a narrower linear passband frequency response. It will also be appreciated in light of this disclosure that above the natural frequency, the amplitude response of the sensor decreases to non-negligible levels, rendering it unusable. For these reasons, high frequency acceleration sensors tend to have very small masses, on the order of 1/2 gram. It will also be appreciated in light of this disclosure that the addition of signal processing and digitization electronics required for streaming often renders the sensor incapable of measuring high frequency activity under certain circumstances.

In embodiments, a streaming hub, such as streaming hub 5420 or 5480, can effectively move the electronics required for streaming to an external hub via cable. It will be understood in light of this disclosure that the streaming hub may be located substantially next to the streaming sensor or up to a distance supported by the hub's electronic driving capabilities. In examples where Internet Cache Protocol ("ICP") is used, the distance supported by the hub's electronic driving capabilities may be anywhere from 100 to 1000 feet (30.5 to 305 meters) based on desired frequency response, cable capacity, etc. In embodiments, the streaming hub may be located in a convenient location to receive power as well as connect to a network (whether LAN or WAN). In embodiments, other power options may include solar, thermal, and energy harvesting. Transmission between the streaming sensor and the external system may be wireless or wired, and may include standard communication technologies such as 802.11 and 900 MHz wireless systems, Ethernet, USB, Firewire, etc.

18, many examples of the DAQ device 5002 include embodiments in which data may be uploaded from the local data control application 5062 to the master raw data server ("MRDS") 5082. In embodiments, information in the multimedia probe ("MMP") and probe control, sequence, and analysis ("PCSA") information store 5040 may also be downloaded from the MRDS 5082 to the DAQ device 5002. Further details of the MRDS 5082 are shown in FIG. 22, including embodiments in which data may be transferred from the DAQ device 5002 to the MRDS 5082 via a wired or wireless network, or via connection to one or more portable media, drives, other network connections, etc. In embodiments, the DAQ device 5002 may be configured to be portable and may be carried on one or more predetermined routes to evaluate predetermined measurement points. In many of these examples, the operating system that may be included in the MRDS 5082 may be a Windows, Linux, or MacOS operating system, or other similar operating system. Additionally, in these arrangements, the operating system, modules for the operating system, and other necessary libraries, data storage, etc. may be accessible, in whole or in part, through access to the cloud network facility 5080. In embodiments, the MRDS 5082 may reside directly on the DAQ device 5002, particularly in the example of an online system. In embodiments, the DAQ device 5002 may be linked over an intranet within the facility, but may otherwise be behind a firewall. In further examples, the DAQ device 5002 may be linked to the cloud network facility 5080. In various embodiments, one of the computer or mobile computing devices may substantially designate the MRDS 5082 to which all of the other computing devices may provide data, such as one of the MRDSs 6104, as depicted in FIGS. 31 and 32. In many examples where the DAQ devices 5002 may be deployed and configured to receive stream data in a swarm environment, one or more of the DAQ devices 5002 may substantially designate the MRDS 5082 to which all of the other computing devices may provide data. In many examples where DAQ devices 5002 may be deployed and configured to receive streamed data in an environment where the methods and systems disclosed herein intelligently allocate, control, regulate, and re-balance data pools, computing resources, network bandwidth for local data collection, and the like, one or more of the DAQ devices 5002 may effectively designate an MRDS 5082 to which all of the other computing devices may supply data.

With further reference to FIG. 22, new raw streaming data, extracted, processed, and aligned data (EP data), etc., may be uploaded to one or more master raw data servers, scaled as needed or in various environments. In an embodiment, the master raw data server ("MRDS") 5700 may connect to and receive data from other master raw data servers, such as the MRDS 5082. The MRDS 5700 may include a data distribution manager module 5702. In an embodiment, the new raw streaming data may be stored in a new stream data repository 5704. In many examples, like the raw data streams stored in the DAQ device 5002, the new stream data repository 5704 and the new extracted and processed data repository 5708 may similarly be configured as temporary storage areas.

In an embodiment, the MRDS 5700 may include a stream data analyzer module having an extraction and process alignment module 5710. The analyzer module 5710 may also be deployed on the DAQ device 5002, but may prove to be a more robust data analyzer and extractor than is typically found on portable streaming DAQ devices. In an embodiment, the analyzer module 5710 takes in the streaming data and instantiates it at a specific sampling rate and resolution similar to that of the local data control module 5062 on the DAQ device 5002. The specific sampling rate and resolution of the analyzer module 5710 may be based on either user input 5712 or automatic extraction from the multimedia probe ("MMP") and probe control, sequencing, and analysis ("PCSA") information store 5714 and/or identification mapping table 5718; user input 5712 may be required when there is incomplete information regarding various forms of legacy data similar to that detailed on the DAQ device 5002. In embodiments, legacy data may be processed by the analyzer module 5710 and stored in one or more temporary holding areas, such as the new legacy data repository 5720. One or more temporary areas may be configured to hold the data until it is copied to an archive and verified. The analyzer 5710 module may also facilitate detailed analysis by providing many different types of signal processing tools, including, but not limited to, filtering, Fourier transforms, weighting, resampling, envelope demodulation, wavelets, two-channel analysis, and the like. From this analysis, many different types of plots and mini-reports may be generated from the report and plot module 5724. In embodiments, the data is sent to the processing, analysis, reporting, and archiving ("PARA") server 5730 at user initiation or in an automated manner, particularly for online systems.

In embodiments, PARA server 5750 may connect to and receive data from other PARA servers, such as PARA server 5730. Referring to FIG. 24, PARA server 5730 may provide data to a monitoring module 5752 on PARA server 5750, which may be configured to provide at least one of processing, analysis, reporting, archiving, monitoring, and similar functionality. The monitoring module 5752 may also include extraction, process alignment functionality, and the like. In embodiments, incoming streaming data may first be stored in a raw data stream archive 5760 after appropriate validation. Based on analysis requirements derived from the multimedia probe ("MMP") and probe control, sequence, and analysis ("PCS A") information store 5762, as well as user settings, data may be extracted, analyzed, and stored in an extraction and processing ("EP") raw data archive 5764. In embodiments, various reports from a reporting module 5768 are generated from the monitoring module 5752. Various reports from the reporting module 5768 may include various smart bands along with statistical patterns, overall trend plots, etc. In embodiments, the reporting module 5768 may be configured to compare incoming data with historical data. By way of these examples, the reporting module 5768 may search for and analyze adverse trends, sudden changes, machine fault patterns, etc. In embodiments, the PARA server 5750 may include an expert analysis module 5770, from which reports may be generated and analysis may be performed. Upon completion, the archived data may be provided to a local master server ("LMS") 5772 via a server module 5774 that may be connected to a local area network. In embodiments, the archived data may be provided to the LMS 5772 via a cloud data management server ("CDMS") 5778 via a server module for the cloud network facility 5080. In an embodiment, the monitoring module 5752 on the PARA server 5750 may be configured to provide at least one of processing, analysis, reporting, archiving, monitoring, and similar functionality, from which alarms may be generated, evaluated, stored, modified, reassigned, and the like, using the alarm generation module 5782.

FIG. 24 depicts various embodiments including a PARA server 5800 and its connection to a LAN 5802. In embodiments, one or more DAQ instruments, such as a DAQ instrument 5002, may receive and process analog data from one or more analog sensors 5710, which may be captured by the DAQ instrument 5002. As discussed herein, the DAQ instrument 5002 may create a digital stream of data based on the captured analog data from the one or more analog sensors. The digital stream from the DAQ instrument 5002 may be uploaded to an MRDS 5082 and, from there, transmitted to a PARA server 5800, where multiple terminals, such as terminals 5810, 5812, and 5814, may each interface with the MRDS 5082 to display data and/or analysis reports. In embodiments, the PARA server 5800 may communicate with a network data server 5820, which may include an LMS 5822. In these examples, the LMS 5822 may be configured as an optional storage area for archived data. The LMS 5822 may also be configured as an external driver that may be connected to a PC or other computing device capable of executing the LMS 5822; or may be configured to run directly, where the LMS 5822 may be configured to operate and coexist with the PARA server 5800. The LMS 5822 may connect to a raw data stream archive 5824, an extraction and processing ("EP") raw data archive 5828, and an MMP and probe control, sequencing and analysis ("PCS A") information store 5830. In an embodiment, a CDMS 5832 may also connect to the LAN 5802 and may also support data archiving.

In embodiments, a mobile connectivity device 5850, such as a tablet 5852 and a smartphone 5854, may connect to the CDMS 5832 using web APIs 5860 and 5862, respectively, as depicted in FIG. 25. The APIs 5860, 5862 may be configured to run in a browser and may allow access via the cloud network facility 5870 of all (or a portion) of the functionality previously discussed as accessible via the PARA server 5800. In embodiments, a user's 5880 computing device, such as computing devices 5882, 5884, and 5888, may also access the cloud network facility 5870 via a browser or other connection to receive the same functionality. In embodiments, the thin client app does not require additional device drivers and may be facilitated by web services supported by Cloud Services 5890 and Cloud Data 5892. In many examples, the thin client app may be developed and reconfigured using, for example, the visual high-level LabVIEW programming language with NXG web-based virtual interface subroutines. In embodiments, the thin client app may provide high-level graphing capabilities such as those supported by the LabVIE tool. In embodiments, the LabVIEW tool can generate JScript and Java code that can be edited after compilation. The NXG tool can generate WebVis that provide only RESTful services and can be easily installed from any browser without requiring proprietary drivers. It will be understood in light of this disclosure that because various applications can be run within a browser, they can be run on any operating system, such as Windows, Linux, Android, etc., especially for personal devices, mobile devices, and handheld connected devices.

In an embodiment, the CDMS 5832 is depicted in further detail in FIG. 26. In an embodiment, the CDMS 5832 may provide all of the data storage and services that the PARA server 5800 (FIG. 34) can provide. In contrast, all APIs may be web APIs running in a browser, and all other apps may run on the PARA server 5800 or DAQ instrument 5002, typically running Windows, Linux, or other similar operating systems. In an embodiment, the CDMS 5832 includes at least one or a combination of the following functionality: The CDMS 5832 includes a cloud GUI 5900 that may be configured to provide access to all data plots, including trends, waveforms, spectra, envelopes, transfer functions, measurement event logs, analysis including experts, utilities, etc. In an embodiment, the CDMS 5832 may include a cloud data exchange 5902 configured to facilitate the transfer of data to and from the cloud network facility 5870. In embodiments, the CDMS 5832 may include a cloud plot/trend module 5904 configured to display all plots, including trends, waveforms, spectra, envelopes, transfer functions, etc., via a web app. In embodiments, the CDMS 5832 may include a cloud reporter 5908, which may be configured to provide all analysis reports, logs, expert analysis, trend plots, statistics, etc. In embodiments, the CDMS 5832 may include a cloud alarm module 5910. Alarms from the cloud alarm module 5910 may be generated and sent via email, text, or other messaging mechanisms to various devices 5920. From the various modules, data may be stored in new data 5914. The various devices 5920 may include a terminal 5922, a portable connectivity device 5924, or a tablet 5928. Alarms from the cloud alarm module are designed to be interactive, allowing end users to acknowledge alarms to avoid receiving redundant alarms and to view important context-sensitive data from the alarm point, which may include spectra, waveform statistics, etc.

In an embodiment, a relational database server ("RDS") 5930 may be used to access all information from the MMP and PCSA information store 5932. Similar to the PARA server 5800 (FIG. 26), information from the information store 5932 may be used with the EP and alignment module 5934, data exchange 5938, and expert system 5940. In an embodiment, a raw data stream archive 5942 and an extracted and processed raw data archive 5944 may also be used by the EP align 5934, data exchange 5938, and expert system 5940, similar to the PARA server 5800. In an embodiment, new stream raw data 5950, new extracted and processed raw data 5952, and new data 5954 (essentially all other raw data, such as overalls, smart bands, statistics, and data from the information store 5932) are directed by the CDMS 5832.

In embodiments, streaming data may be linked with the RDS 5930 and the MMP and PCSA information store 5932 using the Technical Data Management Streaming ("TDMS") file format. In embodiments, the information store 5932 may include a table for recording at least a portion of all measurement events. By way of example, a measurement event may be any single data capture, stream, snapshot, averaged level, or overall level. In addition to point identification information, each measurement event may have a date and timestamp. In embodiments, the TDMS format may be used to create links between streaming data, measurement events, and tables in the information store 5932. By way of example, links may be created by storing unique measurement point identification codes in a file structure having the TDMS format by including and assigning TDMS properties. In embodiments, files having the TDMS format may allow for a three-level hierarchy. By way of example, the three levels of hierarchy may be root, group, and channel. It will be understood in light of this disclosure that the Mimosa database schema may theoretically be unlimited. That said, there are advantages to a limited TDMS hierarchy. In many cases, the following characteristics can be suggested for addition to the TDMS stream structure while using a Mimosa-compatible database schema:

Root Level: Global ID 1: Text String (This can be a unique ID obtained from the web.); Global ID 2: Text String (This can be an additional ID obtained from the web.); Company Name: Text String; Company ID: Text String; Company Segment ID: 4-byte Integer; Company Segment ID: 4-byte Integer; Site Name: Text String; Site Segment ID: 4-byte Integer; Site Asset ID: 4-byte Integer; Route Name: Text String; Version Number: Text String

Group Level: Section 1 Name: Text String; Section 1 Segment ID: 4-byte Integer; Section 1 Asset ID: 4-byte Integer; Section 2 Name: Text String; Section 2 Segment ID: 4-byte Integer; Section 2 Asset ID: 4-byte Integer; Machine Name: Text String; Machine Segment ID: 4-byte Integer; Integer; Equipment Name: Text String; Equipment Segment ID: 4-byte Integer; Equipment Asset ID: 4-byte Integer; Shaft Name: Text String; Shaft Segment ID: 4-byte Integer; Shaft Asset ID: 4-byte Integer; Bearing Name: Text String; Name: Text String; Probe Segment ID: 4-byte Integer; Probe Asset ID: 4-byte Integer

Channel Level: Channel #: 4-byte Integer; Direction: 4-byte Integer (in certain examples may be text); Data Type: 4-byte Integer; Reserved Name 1: Text String; Reserved Segment ID 1: 4-byte Integer; Reserved Name 2: Text String; Reserved Segment ID 2: 4-byte Integer; Reserved Name 3: Text String; Reserved Segment ID 3: 4-byte Integer

In embodiments, files in the TDMS format may automatically use property or asset information, may create index files from specific property and asset information to facilitate database searches, may be optimized for storing binary streams of data, but may also include some minimal database structures that implement many standard SQL operations. Therefore, while the TDMS format and features discussed herein may not be as efficient as a full-blown SQL relational database, the TDMS format offers the best of both worlds in that it balances a class or format that efficiently writes and stores large streams of binary data with a fully relational database that facilitates searching, sorting, and data retrieval. In embodiments, by establishing a link between the two database methods, an optimal solution may be found in which the metadata required to extract a predefined list with analytical objectives and panel criteria for stream collection is stored in the RDS 5930. By these examples, relatively large analog data streams may be stored in the raw data stream archive 5942 primarily as binary storage for rapid stream loading, but with inherent relational SQL-type hooks, formats, conventions, etc. TDMS format files can also be configured to incorporate the DIAdem reporting functionality of LabVIEW software, providing an additional mechanism for convenient and fast access to analog and streaming data.

The methods and systems disclosed herein may include, connect to, or integrate with a virtual data acquisition instrument. In many embodiments, FIG. 27 illustrates a method and system that includes a virtual streaming DAQ instrument 6000, also known as a virtual DAQ instrument, VRDS, or VSDAQ. In contrast to the DAQ instrument 5002 (FIG. 18), the virtual DAQ instrument 6000 may be configured to include only one native application. In many examples, the one native application allowed may be a DAQ driver module 6002 that may manage all communication with the DAQ device 6004, which may include streaming functionality. In embodiments, other applications, if any, may be configured as thin-client web applications, such as RESTful web services. The one native application, or other applications or services, may be accessible through a DAQ Web API 6010. The DAQ Web API 6010 may run in or be accessible through a variety of web browsers.

In an embodiment, the storage of streaming data and the extraction and processing of the streaming data into extracted and processed data may be handled primarily by the DAQ driver service 6012 under the direction of the DAQ Web API 6010. In an embodiment, outputs from various types of sensors, including vibration, temperature, pressure, ultrasound, etc., may be provided to instrument inputs of the DAQ device 6004. In an embodiment, signals from the output sensors may be signal conditioned with respect to scaling and filtering and digitized with an analog-to-digital converter. In an embodiment, signals from the output sensors may be signals from all relevant channels simultaneously sampled at a rate sufficient to perform maximum desired frequency analysis. In an embodiment, signals from the output sensors may be sampled gap-free as one continuous stream for a relatively long time period, with enough samples to enable extensive further post-processing at a lower sampling rate. In a further example, the streaming frequency may be adjusted (re-adjusted) to record streaming data at uneven intervals. For temperature data, pressure data, and other similar data, which may be relatively slow, varying the delta time between samples can further improve data quality. Per the above example, data may be streamed from a collection of points, after which a next set of data may be collected from additional points according to a predetermined sequence, route, path, etc. In many examples, the portable sensor may move to the next location according to a predetermined order, but not necessarily to all locations, as some may be used for reference phases, etc. In further examples, multiplexer 6020 may be used to switch to the next set of points, or a mixture of the two methods may be combined.

In an embodiment, sequence and panel conditions that can be used to govern the data acquisition process using the virtual DAQ instrument 6000 may be retrieved from the MMP PCS A information store 6022. The MMP PCS A information store 6022 may include items such as the hierarchical structural relationships of the machine, i.e., the machine, where each piece of equipment contains a shaft, each shaft is associated with a bearing, and may be monitored by a particular type of transducer or probe according to a particular predefined sequence (route, path, etc.) with specific panel conditions. By way of example, the panel conditions may include hardware-specific switch settings or other acquisition parameters such as sampling rate, AC/DC coupling, voltage range and gain, integration, high-pass and low-pass filtering, anti-aliasing filtering, ICP transducers and other integrated circuit piezoelectric transducers, 4-20 mA loop sensors, etc. Information store 6022 contains other information that may be stored that may be machine-specific features important for proper analysis, including the number of gear teeth, the number of blades on a pump impeller, the number of motor rotor bars, bearing-specific parameters needed to calculate bearing frequencies, the lx rotational speeds (RPM) of all rotating elements, etc.

Under the direction of the DAQ Web API 6010 software, the digitized waveform may be uploaded using the DAQ driver service 6012 of the virtual DAQ instrument 6000. In an embodiment, the data may then be provided to the RLN data and control server 6030, which may store the stream data in the network stream data repository 6032. Unlike the DAQ instrument 5002, the server 6030 may be executed from within the DAQ driver module 6002. It will be understood in light of this disclosure that other applications may require drivers to run on the native operating system, and for this instrument, only the instrument driver may run natively. In many instances, all other applications may be configured to be browser-based. As such, the associated network variables are very similar to LabVIEW shared variables or network stream variables, which are designed to be accessible over one or more networks or via web applications.

In embodiments, the DAQ Web API 6010 may also instruct the local data control application 6034 to extract and process recently acquired streaming data, thereby converting it to the same or a lower sampling rate long enough to provide the desired resolution. This data may be converted to a spectrum, then averaged, processed in various ways, and stored as EP data, such as on the EP data repository 6040. The EP data repository 6040 may, in certain embodiments, be for temporary storage only. It will be understood in light of this disclosure that legacy data may require unique sampling rates and resolutions, particularly for order-sampled data where the sampling frequency is directly related to an external frequency, and this sampling rate is often not integer proportional to the acquired sampling rate. The external frequency may be the running speed of the machine or its internal components (e.g., Fmax values of 100, 200, 500, 1K, 2K, 5K, 10K, 20K, etc.), rather than a more standard sampling rate typically generated by the DAQ device's 5002, 6000 internal crystal, clock function, etc. In embodiments, the EP align component of the local data control application 6034 can fractionally adjust the sampling rate to a non-integer ratio rate that may be more applicable to legacy data sets and thus promote compatibility with legacy systems. In embodiments, the length of data being processed (or at least a portion thereof of a larger stream of data) is adjustable due to the depth and content of the streaming data originally acquired by the DAQ instruments 5002, 6000, so fractional rates may be more easily converted to integer ratio rates. It will be appreciated in light of this disclosure that if the data were not streamed but merely saved as a traditional snapshot of a spectrum with a typical value of Fmax, it may be highly impossible to retroactively accurately convert the acquired data to custom sampled data. In embodiments, the stream data may be converted to the appropriate sampling rate and resolution as described, specifically for legacy data purposes, and stored in the EP legacy data repository 6042. To support legacy data identification scenarios, user input 6044 may be included if there is no automated process for identification conversion. In embodiments, one such automated process for identity conversion may include importing data from a legacy system, which may contain a fully standardized format, such as the Mimosa format, and sufficient identity information to complete ID mapping table 6048. In a further example, an end user, legacy data vendor, legacy data storage facility, etc. may be able to provide sufficient information to complete (or sufficiently complete) the relevant portion of ID mapping table 6048, and thus provide a database schema for the raw data of the legacy system, so that it can be easily ingested, stored, and used for analysis by the current systems disclosed herein.

FIG. 28 illustrates further embodiments and details of the virtual DAQ instrument 6000. In these examples, the DAQ Web API 6010 may control not only the data acquisition process but also its sequencing. The DAQ Web API 6010 may provide functionality for editing this process, displaying plots of the data, controlling the processing of that data and displaying its output in myriad forms, analyzing the data, including expert analysis, communicating with external devices via the DAQ driver module 6002, and communicating with both streaming and EP data and potentially forwarding it to one or more cloud network facilities 5080. In embodiments, the virtual DAQ instrument itself and the DAQ Web API 6010 may run independently of access to the cloud network facility 5080, as local demand may require, or simply as a result of the lack of such access. The DAQ Web API 6010 enables use in industrial environments uniquely designed to prevent such signals. In embodiments, the DAQ Web API 6010 may also manage data movement, filtering, and many other housekeeping functions.

The virtual DAQ instrument 6000 may also include an expert analysis module 6052. In embodiments, the expert analysis module 6052 may be a web application or other suitable module capable of generating reports 6054 that can use machine- or measurement point-specific information from the MMP PCSA information store 6022 to analyze the stream data 6058 using the stream data analyzer module 6050. In embodiments, supervisory control of the module 6052 may be provided by the DAQ Web API 6010. Also, in embodiments, expert analysis may be provided (or supplemented) via an expert system module 5940 residing on one or more cloud network facilities accessible via the CDMS 5832. In many instances, expert analysis via the cloud may be preferred over a local system, such as the expert analysis module 6052, for a variety of reasons, including the availability and use of the latest software versions, more processing power, and a larger volume of historical data to reference. It will be appreciated in light of the present disclosure that providing expert analysis when an internet connection is unavailable may be important for seamless and time-efficient operation, providing redundancy when needed. In embodiments, this redundancy may be extended, where applicable, to all of the modular software applications and databases discussed, such that each module discussed herein is configured to provide redundancy for continued operation in the absence of an internet connection.

FIG. 29 shows further embodiments and details of multiple virtual DAQ devices present in an online system and connecting from a central DAQ device to one or more cloud network facilities via network endpoints. In an embodiment, a master DAQ device having network endpoint 6060 is provided along with additional DAQ devices, such as a DAQ device having network endpoint 6062, a DAQ device having network endpoint 6064, and a DAQ device having network endpoint 6068. The master DAQ device having network endpoint 6060 may connect to other DAQ devices having network endpoints 6062, 6064, and 6068 via LAN 6070. It will be understood that each of the instruments 6060, 6062, 6064, 6068 may include personal computers, connectivity devices, etc., including Windows, Linux, or other suitable operating systems to facilitate connection of devices utilizing a number of wired and wireless networking options, such as Ethernet, wireless 802.11g, 900 MHz wireless (e.g., to better penetrate walls, enclosures, and other structural barriers commonly encountered in industrial environments), and myriad others permitted by the use of off-the-shelf communications hardware when necessary.

FIG. 30 depicts further embodiments and details of many of the functional components of an endpoint that can be used in a variety of settings, environments, and network connectivity configurations. The endpoint includes an endpoint hardware module 6080. In embodiments, the endpoint hardware module 6080 can include one or more multiplexers 6082, a DAQ instrument 6084, and a computer 6088, computing device, PC, etc., which can include multiplexers, DAQ instruments, and computers, connected devices, etc., as disclosed herein. The endpoint software module 6090 includes a data collector application (DCA) 6092 and a raw data server (RDS) 6094. In embodiments, the DCA 6092 can be similar to the DAQ API 5052 (FIG. 18) and can be configured to retrieve and locally store stream data from the DAQ device 6084 according to a predetermined sequence or in response to user instructions. In many examples, the predetermined sequence or user instructions can be a LabVIEW software app that can control the DAQ instrument and read data. For cloud-based online systems, in many embodiments, the stored data may be accessible over a network. In many examples, this can be achieved with shared variables and network streams (or a subset of shared variables) using NI-DAQ tools. The shared variables and associated network streams may be network objects optimized for sharing data over a network. In many embodiments, the DCA 6092 may include a graphic user interface that may be configured to collect data and push it to the shared variables and their associated network streams as efficiently and quickly as possible. In embodiments, the endpoint raw data server 6094 may be configured to read raw data from a single-process shared variable and may be co-located with the master network stream. In embodiments, the raw stream of data from the portable system may be temporarily stored locally until it is pushed to the MRDS 5082 (FIG. 18). It will be understood in light of this disclosure that online system devices on a network may be referred to as endpoints, whether local or remote, or associated with a local or wide area network. For portable data collector applications that may or may not be wirelessly connected to one or more cloud network facilities, the term endpoint may be omitted to further describe devices that do not require network connectivity.

FIG. 31 illustrates further embodiments and details of multiple endpoints having respective software blocks, with at least one of the devices configured as a master block. Each of the blocks may include a data collector application ("DC A") 7000 and a raw data server ("RDS") 7002. In embodiments, each block may further include a master raw data server module ("MRDS") 7004, a master data collection and analysis module ("MDCA") 7008, and a supervisory control interface module ("SCI") 7010. The MRDS 7004 may be configured to (minimally) read network stream data from other endpoints and forward it to one or more cloud network facilities via a CDMS 5832, including cloud services 5890 and cloud data 5892. In embodiments, the CDMS 5832 may be configured to store data and provide web, data, and processing services. In these examples, this may be implemented with a LabVIEW application configured to read data from the network stream, share variables from all of the local endpoints, and write it to the local host PC, local computing device, connected devices, etc., as both a network stream and a file in TDMS format. In embodiments, the CDMS 5832 may also be configured to then post this data to the appropriate bucket using LabVIEW or similar software, where an S3 web service from Amazon Web Services ("AWS") may be supported on Amazon web servers, effectively acting as a back-end server. In many examples, different criteria may be enabled or configured for when data is posted, creating or adjusting schedules, creating or adjusting event triggers including new data events, creating buffer full messages, creating multiple alarm messages, etc.

In an embodiment, the MDCA 7008 may be configured to provide automated analysis of raw data as well as user-driven analysis, including tracking and annotating specific occurrences and, in doing so, noting where reports may be generated or alarms may be annotated. In an embodiment, the SCI 7010 may be an application configured to provide remote control of the system from the cloud as well as the ability to generate status and alarms. In an embodiment, the SCI 7010 may be configured to connect to, interface with, or integrate with a supervisory control and data acquisition ("SCADA") control system. In an embodiment, the SCI 7010 may be configured as a LabVIEW application capable of providing remote control and status alerts that may be provided to any remote device that may connect to one or more of the cloud network facilities 5870.

In embodiments, the equipment being monitored may include RFID tags that can provide important machine analysis context. RFID tags may be: associated with the entire machine or with individual components, and may be replaced when specific parts of the machine are replaced, repaired, or rebuilt; RFID tags may provide permanent information related to the life of the unit or may be reflashed to update with at least some of the new information; and in many embodiments, the DAQ device 5002 disclosed herein can interrogate one or more RFID chips to learn the hierarchical structure of the machine, its components, its service history, and how everything is connected, including drive diagrams, wiring diagrams, and hydraulic layouts. In embodiments, information that can be obtained from an RFID tag includes the manufacturer, machine type, model, serial number, model number, date of manufacture, date of installation, lot number, etc. The machine type may use a Mimosa-formatted table containing information on one or more of the following: motors, gearboxes, fans, and compressors. The machine type may also include the number of bearings, their type, location, and identification number. Information associated with one or more fans includes the type of fan, the number of blades, the number of vanes, and the number of belts. In light of this disclosure, it will be understood that other machines and their components may similarly have associated information arranged in a hierarchical manner, all of which may be available by interrogation of one or more RFID chips associated with one or more machines.

In embodiments, data collection in an industrial environment may involve routing analog signals from multiple sources, such as analog sensors, to multiple analog signal processing circuits. The routing of the analog signals may be achieved by an analog crosspoint switch that can route any of multiple analog input signals to any of multiple outputs, such as analog and/or digital outputs. The routing from input to output in an analog signal crosspoint switch in an industrial environment may be configurable, for example, by electronic signals to which the switch portions of the analog crosspoint switch respond.

In embodiments, the analog crosspoint switch may receive analog signals from multiple analog signal sources within an industrial environment. The analog signal sources may include sensors that generate analog signals. The sensors that generate analog signals that may be switched by the analog crosspoint switch may include sensors that detect a condition and convert the condition into an analog signal that may represent the condition, such as converting the condition into a corresponding voltage. Exemplary conditions that may be represented by a variable voltage may include temperature, friction, sound, light, torque, rotational speed, mechanical resistance, pressure, flow rate, etc., including any of the conditions represented by input sources and sensors disclosed throughout this disclosure and the documents incorporated herein by reference. Other forms of analog signals may include electrical signals, such as variable voltages, variable currents, variable resistances, etc.

In embodiments, an analog crosspoint switch may retain one or more aspects of an analog signal input to it in an industrial environment. Analog circuitry integrated into the switch may provide a buffered output. The analog circuitry of the analog crosspoint switch may track an input signal, such as an input voltage, to generate a buffered representation on the output. This may alternatively be accomplished by a relay (mechanical, solid-state, etc.) that propagates an analog voltage or current present at the input to a selected output of the analog switch.

In embodiments, an analog crosspoint switch in an industrial environment may be configured to switch any of multiple analog inputs to any of multiple analog outputs. Exemplary embodiments include MIMO, multiplexed configurations. The analog crosspoint switch may be dynamically configurable such that changing the configuration changes the mapping of inputs to outputs. A configuration change may be applied to one or more mappings such that the changed mapping maps one or more outputs to different inputs than before the configuration change.

In embodiments, an analog crosspoint switch may have more inputs than outputs, such that only a subset of the inputs can be routed to the outputs at the same time. In other embodiments, an analog crosspoint switch may have more outputs than inputs, such that a single input may be currently available at multiple outputs, or at least one output may not be mapped to any input.

In embodiments, an analog crosspoint switch in an industrial environment may be configured to switch any of multiple analog inputs to any of multiple digital outputs. To accomplish the conversion from analog input to digital output, analog-to-digital conversion circuitry may be configured at each input, each output, or at an intermediate point between the input(s) and output(s) of the analog crosspoint switch. Benefits of including analog signal digitization in an analog crosspoint switch, which may be located near the analog signal source, may include reduced signal transport cost and complexity that digital signal communication has over analog, reduced energy consumption, and easier detection and adjustment of abnormal conditions before they propagate throughout the industrial environment. Capturing analog signals near their source may also facilitate improved signal routing management that is more tolerant of real-world effects that require multiple signals to be routed simultaneously. In this example, a portion of the signal may be captured (and stored) locally, and another portion may be forwarded through a data collection network. If the data collection network has available bandwidth, the locally stored signal may be distributed, perhaps with a timestamp indicating the time the data was collected. This technique may be useful in applications where there is a simultaneous demand for more data collection channels than the number of available channels. Sampling control can also be based on an indication of data worth sampling. As an example, a signal source, such as a sensor in an industrial environment, can provide a data valid signal that sends an indication of when data from the sensor is available.

In an embodiment, mapping inputs to outputs of the analog crosspoint switch may be based on a signal route plan of a portion of the industrial environment that may be presented to the crosspoint switch. The signal route plan may be used in a method of data collection in an industrial environment that includes routing a plurality of analog signals along a plurality of analog signal paths. The method may include individually connecting the plurality of analog signals to inputs of the analog crosspoint switch, which may be configured with the route plan. The crosspoint switch may route a portion of the plurality of analog signals to a portion of the plurality of analog signal paths in response to the configured route plan.

In embodiments, the analog crosspoint switch may include at least one high current output driver circuit suitable for routing analog signals along paths requiring high current. In embodiments, the analog crosspoint switch may include at least one voltage-limited input that can facilitate protecting the analog crosspoint switch from damage due to excessive analog input signal voltages. In embodiments, the analog crosspoint switch may include at least one current-limited input that can facilitate protecting the analog crosspoint switch from damage due to excessive analog input currents. The analog crosspoint switch may include a plurality of interconnected relays that can facilitate routing inputs to outputs with little to no substantial signal loss.

In embodiments, an analog crosspoint switch may include signal processing or other processing functionality (e.g., a programmed processor, a special-purpose processor, a digital signal processor, etc.) capable of detecting the state of one or more analog input signals. In response to such detection, one or more actions may be performed, such as setting an alarm, sending an alarm signal to another device in the industrial environment, changing the configuration of the crosspoint switch, disabling one or more outputs, powering on or off a portion of the switch, or changing the state of an output, such as a general-purpose digital or analog output. In embodiments, the switch may be configured to process the inputs to generate signals on one or more outputs. The inputs to use, the algorithm for processing the inputs, the conditions for generating the signals, the outputs to use, etc. may be configured in a data collection template.

In embodiments, an analog crosspoint switch may be configured with more than 32 inputs and more than 32 outputs. Multiple analog crosspoint switches may be configured to facilitate switching any of the 32 inputs spread across the multiple crosspoint switches to any of the 32 outputs, even though each switch provides fewer than 32 inputs and 32 outputs.

In embodiments, an analog crosspoint switch suitable for use in an industrial environment may be configured with four or fewer inputs and four or fewer outputs. Each output may be configured to generate an analog output corresponding to a mapped analog input, or may be configured to generate a digital representation of the corresponding mapped input.

In embodiments, an analog crosspoint switch for use in an industrial environment may be configured with circuitry that facilitates replicating at least some of the attributes of the input signal, such as current, voltage range, offset, frequency, duty cycle, ramp rate, etc., while buffering (e.g., isolating) the input signal from the output signal. Additionally, the analog crosspoint switch may be configured with unbuffered inputs/outputs, effectively providing a bidirectional-based crosspoint switch.

In embodiments, analog crosspoint switches for use in industrial environments may include protected inputs that can be protected from damaging conditions, such as through the use of signal conditioning circuitry. The protected inputs can prevent damage to the switch and downstream devices to which the switch outputs are connected. As one example, the inputs of such analog crosspoint switches may include voltage clipping circuitry that prevents the voltage of the input signal from exceeding an input protection threshold. Active voltage conditioning circuitry also scales the input signal by steadily reducing the input signal so that the maximum voltage present at the input does not exceed a safe threshold. As another example, the inputs of such analog crosspoint switches may include current shunting circuitry that ensures that currents exceeding a maximum input protection current threshold are diverted through the protection circuitry rather than entering the switch. The inputs of the analog switch may be protected from static electricity and lightning strikes. Other signal conditioning features applied to the inputs of the analog crosspoint switch may include voltage scaling circuitry that attempts to facilitate the distinction between valid input signals and low-voltage noise that may be present on the input. However, in embodiments, the inputs to the analog crosspoint switch may be unbuffered and/or unprotected to minimize impacts on the signal. Signals such as alarm signals or signals that do not easily survive protection schemes such as those described herein above may be connected to unbuffered inputs of the analog crosspoint switch.

In embodiments, an analog crosspoint switch may be configured with circuitry, logic, and/or processing elements that facilitate alarm monitoring of input signals. Such an analog crosspoint switch may detect an input that satisfies an alarm condition and, in response, switch inputs, switch input-to-output mappings, disable inputs, disable outputs, issue alarm signals, activate/deactivate general-purpose outputs, etc.

In embodiments, a system for collecting data in an industrial environment may include an analog crosspoint switch adapted to selectively power up or down portions of the analog crosspoint switch or circuitry associated with the analog crosspoint switch, such as an input protector, an input conditioner, or a switch control device. Portions of the analog crosspoint switch that may be powered on or off include outputs, inputs, switch sections, etc. As an example, the analog crosspoint switch may include a modular structure that allows portions of the switch to be separated into independently powered sections. One or more modular sections may be powered on or off based on conditions such as an input signal meeting criteria or a setpoint presented to the analog crosspoint switch.

In an embodiment, a system for collecting data in an industrial environment may include an analog crosspoint switch adapted to perform signal processing, including, but not limited to, providing a voltage reference for detecting inputs crossing the voltage reference (e.g., zero volts for detecting zero-crossing signals), a phase-locked loop for facilitating the capture of low-speed frequency signals (e.g., low-speed revolutions per minute signals) and detecting their corresponding phases, deriving the phase of an input signal relative to other inputs, deriving the phase of an input signal relative to a reference (e.g., a reference clock), deriving the phase of an input signal relative to a detected alarm input condition, etc. Other signal processing functions of such an analog crosspoint switch include oversampling inputs for delta-sigma A/Ds, generating outputs with lower sampling rates, minimizing AA filter requirements, etc. Such an analog crosspoint switch may support long-block sampling at a constant sampling rate even when inputs switch, making it independent of the rate of the input signal, thereby reducing the complexity of the sampling scheme. The constant sampling rate may be selected from multiple rates that can be generated by circuitry such as a clock divider circuit that makes available multiple components of a reference clock.

In an embodiment, a system for collecting data in an industrial environment may include an analog crosspoint switch adapted to support implementation of a data collection/data routing template in the industrial environment. The analog crosspoint switch may implement the data collection/data routing template based on conditions in the industrial environment that it may detect or derive, such as an input signal that meets one or more criteria (e.g., a signal transition from a first condition to a second condition, a lack of an input signal transition within a predefined time interval (e.g., an inactive input), etc.).

In embodiments, a system for collecting data in an industrial environment may include an analog crosspoint switch that may be adapted to be configured as part of a data collection template. Configuration may occur automatically (without requiring human intervention to perform configuration actions or configuration changes) based on, for example, time parameters in the template. Configuration may occur remotely, for example, by remotely transmitting a signal detectable by a switch configuration function of the analog crosspoint switch. Configuration may occur dynamically based on a condition detectable by a configuration function of the analog crosspoint switch (e.g., a timer, an input condition, an output condition, etc.). In embodiments, information for configuring the analog crosspoint switch may be provided as a stream, a set of control lines, a data file, an indexed data set, etc. In embodiments, the configuration information for a switch's data collection template may include a list of each input and corresponding output, a list of each output function (e.g., active, inactive, analog, digital, etc.), conditions for updating the configuration (e.g., input signal that satisfies the condition, trigger signal, time (relative to another time/event/state or absolute), duration of the configuration, etc.). In embodiments, the switch's configuration may recognize the input signal protocol so that switching from a first input to a second input for a given output occurs based on the protocol. In one example, a configuration change may be initiated in the switch to switch from a first video signal to a second video signal. The configuration circuitry may detect the input signal protocol and switch to the second video signal during a synchronization phase of the video signals, such as during a horizontal or vertical refresh. In another example, switching may occur when one or more inputs are at zero volts. This could occur for a sinusoidal signal transitioning from below zero volts to above zero volts.

In an embodiment, a system for collecting data in an industrial environment may include an analog crosspoint switch adapted to provide a digital output by converting an analog signal input to the switch to a digital output. The conversion may occur after switching the analog input based on a data collection template or the like. In an embodiment, some of the outputs of the switch may be digital and some may be analog. Each output, or groups thereof, may be configurable as analog or digital based on analog crosspoint switch output configuration information included in or obtained from the data collection template. The circuitry of the analog crosspoint switch may sense the voltage range of the input signal and intelligently configure the analog-to-digital conversion function accordingly. As an example, a first input may have a voltage range of 12 volts and a second input may have a voltage range of 24 volts. The analog-to-digital conversion circuitry for these inputs is tuned so that the full range of digital values (e.g., 256 levels of an 8-bit signal) is mapped substantially linearly to 12 volts for the first input and to 24 volts for the second input.

In embodiments, the analog crosspoint switch can automatically configure the input circuitry based on the characteristics of the connected analog signal. Examples of circuit configurations may include setting a maximum voltage, a threshold based on a sensed maximum threshold, a voltage range above and/or below ground reference, an offset reference, etc. The analog crosspoint switch may also adapt the input to support voltage signals, current signals, etc. The analog crosspoint switch may detect the protocol of the input signal, such as a video signal protocol, an audio signal protocol, a digital signal protocol, or a protocol based on the input signal frequency characteristics. Other aspects of the analog crosspoint switch's input that may be adapted based on the input signal may include the signal sampling duration, comparator or differential type signals, etc.

In embodiments, analog crosspoint switches may be configured with features to counteract input signal drift and/or leakage that can occur when analog signals pass through them for extended periods without changing value (e.g., at a constant voltage). Techniques include voltage boosting, current injection, and periodic zero referencing (e.g., temporarily connecting the input to a reference signal such as ground, or applying a high-resistance path to a ground reference).

In an embodiment, a system for data collection in an industrial environment can include an analog crosspoint switch located on an assembly line consisting of conveyors and/or lifters. A powered roller conveyor system includes many rollers that transport products along a path. There may be many points along the path where the rollers can be monitored for proper operation, roller load, product accumulation, etc. Powered roller conveyor systems can also transport many products at once, facilitating the movement of products over longer distances. A system for collecting data in such an assembly environment may include sensors that detect a wide range of conditions as well as numerous locations along the transport path. As products progress along the transport path, some sensors may become active while others (such as sensors the product has passed) become inactive. The data collection system can use the analog crosspoint switch to select only sensors that are currently or are expected to become active in the future by switching inputs connected to inactive sensors to inputs connected to active sensors, thereby providing the most useful sensor signals to data detection and/or collection and/or processing equipment. In an embodiment, the analog crosspoint switch may be configured by a conveyor control system that monitors product activity and directs the analog crosspoint switch to direct different inputs to specific outputs based on a control program or data collection template associated with the assembly environment.

In an embodiment, a system for data collection in an industrial environment can include an analog crosspoint switch deployed in a factory using fans as industrial components. In an embodiment, fans in a factory environment can provide various functions, including drying, exhaust management, clean air flow, etc. When a large number of fans are installed, monitoring the fan's rotational speed, torque, etc. can be useful for early detection of potential problems with the airflow generated by the fans. However, simultaneously monitoring these factors for multiple fans can be inefficient. Therefore, sensors such as tachometers or torque meters can be placed on each fan and their analog output signals can be provided to an analog crosspoint switch. In cases where there are a limited number of outputs, or at least a limited number of systems capable of processing sensor data, an analog crosspoint switch can be used to select from multiple sensors and convey a subset of the available sensor signals to a data collection, monitoring, and processing system. As an example, sensor signals from sensors placed on a group of fans can be selected and switched to the output of the crosspoint switch. After sufficient collection and/or processing of the sensor signals for this group of fans, the analog crosspoint switch can be reconfigured to switch signals from another group of fans for processing.

In an embodiment, a system for data collection in an industrial environment can include an analog crosspoint switch deployed as an industrial component of a turbine-based power system. Vibration monitoring in turbine systems, such as hydroelectric power generation systems, has proven beneficial in reducing downtime. However, there are many vibration monitoring locations, particularly for online vibration monitoring, including relative shaft vibration, bearing absolute vibration, turbine cover vibration, thrust bearing axial vibration, stator core vibration, stator bar vibration, and stator end winding vibration. It can be beneficial to select from this list, taking several samples from sensors for each of these vibration types. A data collection system including an analog crosspoint switch can provide this functionality by connecting each vibration sensor to a separate input of the analog crosspoint switch and configuring the switch to output a subset of its inputs. A vibration data processing system, such as a computer, can determine which sensors to pass through the analog crosspoint switch and configure an algorithm to perform vibration analysis accordingly. As an example, a sensor for capturing turbine cover vibration can be selected by the analog crosspoint switch and passed to a system configured with an algorithm to determine turbine cover vibration from the sensor signals. Once the turbine cover vibration determination is complete, the thrust bearing axial vibration sensor signal may be passed to a crosspoint switch configured to apply a corresponding vibration analysis algorithm. In this way, each type of vibration can be analyzed by a single processing system operating in conjunction with an analog crosspoint switch to pass the specific sensor signal for processing.

With reference to FIG. 34, an analog crosspoint switch for collecting data in an industrial environment is depicted. The analog crosspoint switch 7022 may have multiple inputs 7024 that connect to sensors 7026 in the industrial environment. The analog crosspoint switch 7022 may also include multiple outputs 7028 that connect to data collection infrastructure, such as an analog-to-digital converter 7030, an analog comparator 7032, etc. The analog crosspoint switch 7022 may facilitate connecting one or more inputs 7024 to one or more outputs 7028 by interpreting switch control values that may be provided to it by a controller 7034, etc.

An exemplary system for data collection in an industrial environment includes analog signal sources each connected to at least one input of an analog crosspoint switch having multiple inputs and multiple outputs, the analog crosspoint switch being configurable to switch a portion of the input signal sources to the multiple outputs.

2. In certain embodiments, the analog crosspoint switch further includes an analog-to-digital converter that converts a portion of the analog signals input to the crosspoint switch into representative digital signals, with a portion of the outputs including analog outputs and a portion of the outputs including digital outputs, and/or the analog crosspoint switch is adapted to detect one or more analog input signal conditions. Any one or more of the illustrated embodiments include where the analog input signal conditions include a voltage range of the signal, and the analog crosspoint switch responsively adjusts the input circuitry to comply with the detected voltage range.

An exemplary system for data collection in an industrial environment includes a number of industrial sensors that generate analog signals representative of conditions of industrial machines in the environment being sensed by the number of industrial sensors, and a crosspoint switch that receives the analog signals and routes the analog signals to separate analog outputs of the crosspoint switch based on a signal routing plan presented to the crosspoint switch. In certain embodiments, the analog crosspoint switch further includes an analog-to-digital converter that converts a portion of the analog signals input to the crosspoint switch into representative digital signals, some of the outputs including analog outputs and some of the outputs including digital outputs, and the analog crosspoint switch is adapted to detect one or more analog input signal conditions, the one or more analog input signal conditions including a voltage range of the signal, and/or the analog crosspoint switch can responsively adjust input circuitry to comply with the detected voltage range.

An exemplary method for data collection in an industrial environment includes routing multiple analog signals along multiple analog signal paths by individually connecting the multiple analog signals to inputs of an analog crosspoint switch, configuring the analog crosspoint switch with data routing information from a data collection template for industrial environment routing, and routing portions of the multiple analog signals to portions of the multiple analog signal paths with the configured analog crosspoint switch. In certain further embodiments, at least one output of the analog crosspoint switch includes a high-current driver circuit, at least one input of the analog crosspoint switch includes a voltage-limiting circuit, and/or at least one input of the analog crosspoint switch includes a current-limiting circuit. In certain further embodiments, the analog crosspoint switch includes multiple interconnected relays that facilitate connecting any of multiple inputs to any of multiple outputs, the analog crosspoint switch further includes an analog-to-digital converter that converts a portion of the analog signals input to the crosspoint switch into a representative digital signal, and the analog crosspoint switch further includes signal processing functionality that detects the condition of one or more analog input signals and, in response, performs an action (e.g., setting an alarm, changing the switch configuration, disabling one or more outputs, powering off a portion of the switch, changing the state of a general-purpose (digital/analog) output, etc.). When some of the outputs are analog outputs and some of the outputs are digital outputs, the analog crosspoint switch is adapted to detect one or more analog input signal conditions. In response to detecting one or more analog input signal conditions, the analog crosspoint switch is adapted to take one or more actions, the one or more actions including setting an alarm, sending an alarm signal, changing the configuration of the analog crosspoint switch, disabling an output, powering off a portion of the analog crosspoint switch, powering on a portion of the analog crosspoint switch, and/or controlling a general-purpose output of the analog crosspoint switch.

An exemplary system includes a power roller of a conveyor that includes any of the described operations of an analog crosspoint switch. Further exemplary embodiments, without limitation, include sensing the condition of the power roller with sensors to determine the rotational speed of the power roller, the load being carried by the power roller, the power being consumed by the power roller, and/or the acceleration rate of the power roller. An exemplary system includes a factory-installed fan that includes any of the described operations of an analog crosspoint switch. Certain further embodiments, without limitation, include sensors positioned to sense the condition of the fan, including fan blade tip speed, torque, back pressure, RPM, and/or volume of air displaced per unit time by the fan. An exemplary system includes a turbine in a power generation environment that includes any of the described operations of an analog crosspoint switch. Certain further embodiments, without limitation, include multiple sensors positioned to sense the condition of the turbine, where the sensed condition includes relative shaft vibration, absolute bearing vibration, turbine cover vibration, thrust bearing axial vibration, stator or stator core vibration, stator bar vibration, and/or stator end winding vibration.

In embodiments, methods and systems for collecting data in an industrial environment may include multiple industrial condition sensing and acquisition modules, each of which may include at least one programmable logic component capable of controlling a portion of the sensing and acquisition functionality of that module. The programmable logic components of each module are interconnected by a dedicated logic bus including data and control channels. The dedicated logic bus may be logically and/or physically extendable to other programmable logic components on other sensing and acquisition modules. In embodiments, the programmable logic components may be programmed via the dedicated interconnect bus, via programs passed between the programmable logic components, the sensing and acquisition modules, or the entire system via dedicated programming portions of the dedicated interconnect bus. Programmable logic components for use in industrial environment data sensing and acquisition systems may be composite programmable logic devices, application-specific integrated circuits, microcontrollers, and combinations thereof.

Programmable logic components in industrial data acquisition environments can perform control functions related to data acquisition. Examples of control include power control, self-power up/down, and self-sleep/wake-up of analog channels, sensors, analog receivers, analog switches, and portions of the logic module (e.g., logic board, system, etc.) on which the programmable logic component is located. Control functions such as these may be performed in coordination with the control and operational functions of other programmable logic components, such as other components on one data acquisition module or other such modules. Other functions that programmable logic components may provide include generating voltage references, such as precision voltage references for detecting the state of input signals. Programmable logic components may generate, set, reset, adjust, calibrate, or otherwise determine the voltage of a reference, its tolerance range, etc. Other functions of programmable logic components may enable digital phase-locked loops to facilitate tracking of slowly changing input signals and to facilitate detection of the signal's phase. They may also perform phase detection relative to trigger signals, other analog inputs, or onboard references (e.g., onboard timers). The programmable logic component can be programmed to control the input signal circuitry, such as performing peak voltage detection of the input signal and auto-scaling of the input to its operating voltage range. Other functions that can be programmed into the programmable logic component may include determining an appropriate sampling frequency for sampling the input independent of its operating frequency. The programmable logic component may also be programmed to detect a maximum frequency among multiple input signals and set a sampling frequency for each input signal that is greater than the detected maximum frequency.

The programmable logic component may be programmed to configure and control data routing components, such as multiplexers, crosspoint switches, and analog-to-digital converters, to implement a data collection template for an industrial environment. The data collection template may be included in the program of the programmable logic component, and the program may include algorithms that interpret the data collection template to configure and control data routing resources in the industrial environment.

In an embodiment, one or more programmable logic components in the industrial environment may be programmed to perform signal analysis and testing of the smart band. Results of such analysis and testing may include triggering smart band data collection actions, including reconfiguring one or more data routing resources in the industrial environment. The programmable logic components may be configured to perform portions of the smart band analysis, such as collecting and verifying signal activity from one or more sensors that may be local to the programmable logic components. Smart band signal analysis results from multiple programmable logic components may be further processed by other programmable logic components, a server, a machine learning system, etc. to determine compliance of the smart band.

In embodiments, one or more programmable logic components in an industrial environment may be programmed to control data routing resources and sensors for outcomes such as reducing power consumption (e.g., powering resources on and off as needed) and implementing security within the industrial environment by managing user authentication. In embodiments, a particular data routing resource, such as a multiplexer, may be configured to support a particular input signal type. The programmable logic component may configure the resource based on the type of signal routed to the resource. In embodiments, the programmable logic component can facilitate coordination of signal type matching between sensors and data routing resources by indicating to a configurable sensor the protocol or signal type to present to the routing resource. The programmable logic component may facilitate detection of the protocol of a signal input to a data routing resource, such as an analog crosspoint switch. Based on the detected protocol, the programmable logic component may configure the routing resource to facilitate protocol support and efficient processing. As an example, a programmable logic component configuring a data collection module in an industrial environment may implement an intelligent sensor interface specification, such as the IEEE 1451.2 Intelligent Sensor Interface Specification.

In embodiments, distributing programmable logic components across multiple data sensing, collection, and/or routing modules in an industrial environment can facilitate greater functionality and local interoperability control. As an example, modules can independently perform operational functions based on programs installed in one or more programmable logic components associated with each module. Two modules may be comprised of substantially identical physical components but perform different functions in the industrial environment based on programs loaded into the programmable logic components on the modules. In this manner, if one module fails or loses power, the other modules can continue to perform their functions because they at least partially own their respective programmable logic components. In embodiments, configuring multiple programmable logic components distributed across multiple data collection modules in an industrial environment can facilitate scalability in terms of the environmental conditions sensed, the number of data routing options for routing sensed data throughout the industrial environment, the types of conditions sensed, the computing power of the environment, etc.

In embodiments, a data collection and routing system configured with a programmable logic controller can facilitate validation of external systems for use as storage nodes, such as distributed ledgers. The programmable logic component may be programmed to perform validation of protocols for communicating with such external systems, such as external storage nodes.

In embodiments, programming of programmable logic components, such as CPLDs, may be performed to accommodate a range of differences in data sensing, collection, and configuration. In embodiments, reprogramming may be performed on one or more components when adding and/or removing sensors, changing sensor types, changing sensor configurations or settings, changing data storage configurations, embedding data collection template(s) into device programs, adding and/or removing data collection modules (e.g., when scaling a system), using lower-cost devices that may have more limited functionality or resources than higher-cost devices, etc. Programmable logic components may be programmed to propagate programs for other programmable components via dedicated programmable logic device programming channels, via a daisy-chain programming architecture, through a mesh of programmable logic components, via a hub-and-spoke architecture of interconnected components, or via a ring configuration (e.g., using communication tokens).

In an embodiment, a system for data collection in an industrial environment, consisting of distributed programmable logic devices connected by a dedicated control bus, may be deployed with a drilling rig in an oil and gas production environment, such as an oil and/or gas well. The drilling rig has many active parts that may be operated, monitored, and adjusted during drilling operations. Sensors monitoring the crown block may be physically separate from sensors monitoring the blowout preventer, etc. To effectively maintain control of such a wide range of sensors, programmable logic components, such as Complex Programmable Logic Devices ("CPLDs"), may be distributed throughout the drilling rig. Each CPLD may be configured with programs that facilitate operation of a limited set of sensors, but at least some of the CPLDs may be connected by a dedicated bus to facilitate control, operation, and coordination of sensor use. As an example, a set of sensors may be deployed near a mud pump, etc., to monitor flow rate, density, mud tank level, etc. Each sensor (or group of sensors) may have one or more CPLDs to operate the sensor and sensor signal routing and collection resources. The CPLD groups on board the mud pump may be interconnected by a dedicated control bus to facilitate coordination of, for example, the control of sensors and data collection resources. This dedicated bus may extend physically and/or logically beyond the mud pump control portion of the drill machine, allowing CPLDs in other portions (e.g., crown block, etc.) to coordinate data collection and related activities across portions of the drill machine.

In an embodiment, a system for data collection in an industrial environment, consisting of distributed programmable logic devices (CPLDs) connected by a dedicated control bus, may be deployed with compressors in an oil and gas harvesting environment, such as an oil and/or gas field. Compressors are used in the oil and gas industry to compress various gases, including flash gas, gas lift, reinjection, boosting, vapor recovery, and casing head. Collecting data from sensors for these different compressor functions may require substantially different control regimes. Distributing CPLDs programmed with different control schemes is an approach to address these diverse data collection requirements. One or more CPLDs are co-located with sets of sensors for different compressor functions. A dedicated control bus can be used to coordinate the control and programming of the CPLDs within and across compressor instances. As an example, a CPLD may be configured to manage the data collection infrastructure for sensors deployed to collect compressor-related conditions for flash gas compression, while a second CPLD or group of CPLDs may be configured to manage the data collection infrastructure for sensors deployed to collect compressor-related conditions for vapor recovery gas compression. These groups of CPLDs may operate control programs.

In an embodiment, a system for data collection in an industrial environment, consisting of distributed programmable logic devices connected by a dedicated control bus, may be deployed in a refinery having turbines for oil and gas production, such as modular impulse steam turbines. A system for collecting data from an impulse steam turbine may consist of multiple condition detection and collection modules tailored to the specific functions of the impulse steam turbine. Placing a CPLD alongside these modules allows for data collection tailored to the specific installation. For example, blade conditions, such as tip speed, blade temperature rise, impulse pressure, and blade acceleration rate, may be collected by a data collection module equipped with sensors to detect these conditions. Other modules may be configured to collect data related to valves (e.g., in a multi-valve configuration, one or more modules may be configured for each valve or set of valves). Furthermore, impulse gas turbine systems may be installed alongside other systems, such as combined cycle systems, cogeneration systems, solar power generation systems, wind power generation systems, and hydroelectric power generation systems. These systems may have different data collection requirements. In a modular data acquisition system using CPLDs, the CPLD's dedicated interconnect bus allows each module to be directly programmed and/or reprogrammed in place without shutting down or physically accessing each module.

Referring to FIG. 35, an exemplary embodiment of a system for data collection in an industrial environment is depicted, including distributed CPLDs interconnected by a bus for their control and/or programming. An exemplary data collection module 7200 may include one or more CPLDs 7206 for controlling one or more data collection system resources, such as sensors 7202. Other data collection resources controlled by the CPLDs may include crosspoint switches, multiplexers, data converters, etc. The CPLDs on a module may be interconnected by a bus, such as a dedicated logic bus 7204, which may extend beyond the data collection module to CPLDs on other data collection modules. Data collection modules such as module 7200 may be configured in an environment, such as an industrial machine 7208 (e.g., an impulse gas turbine) and/or 7210 (e.g., a cogeneration system). Control and/or configuration of the CPLDs may be handled by a controller 7212 in the environment. Data collection and routing resources and interconnections (not shown) may also be configured within and between data collection modules 7200, between industrial machines 7208 and 7210 and between industrial machines 7201 and/or with external systems such as internet portals, data analysis servers, etc. to facilitate data collection, routing, storage, analysis, etc.

An exemplary system for collecting data in an industrial environment includes a plurality of industrial condition sensing and acquisition modules, each with a programmable logic component disposed on the modules, the programmable logic component controlling a portion of the sensing and acquisition functionality of the corresponding module. The system includes a dedicated communication bus interconnecting at least one programmable logic component disposed on at least one of the plurality of modules, the communication bus extending to other programmable logic components on other sensing and acquisition modules.

In certain further embodiments, the system includes a programmable logic component programmed via a communication bus, the communication bus including a portion dedicated to programming the programmable logic component, and a power control function controlling a portion of the sensing and acquisition functionality of the module, such as controlling power to sensors, multiplexers, portions of the module, and/or controlling a sleep mode of the programmable logic component. The power control function controls power to sensors, multiplexers, portions of the module, and/or controls a sleep mode of the programmable logic component, and a function controls a portion of the sensing and acquisition functionality of the module by providing a voltage reference to sensors and/or analog-to-digital converters disposed on the module and detecting the relative phase of at least two analog signals obtained from at least two sensors disposed on the module. The system also includes a power control function controlling a portion of the sensing and acquisition functionality of the module by controlling sampling of data provided by at least one sensor disposed on the module, detecting peak voltages of signals provided by sensors disposed on the module, and/or configuring at least one multiplexer disposed on the module by configuring the at least one multiplexer disposed on the module and specifying a mapping of at least one input to one output for the multiplexer. In certain embodiments, the communication bus extends to other programmable logic components on other condition sensing and/or acquisition modules. In certain embodiments, the module may be an industrial environmental condition sensing module. In certain embodiments, the module control program includes algorithms for implementing an intelligent sensor interface communication protocol, such as an IEEE 1451.2 compatible intelligent sensor interface communication protocol. In certain embodiments, the programmable logic component includes configuring the programmable logic component and/or the sensing or acquisition module to implement a smart band data collection template. Exemplary, non-limiting programmable logic components include a field programmable gate array, a complex programmable logic device, and/or a microcontroller.

An exemplary system includes an oil and gas well drilling rig with a condition sensing and/or acquisition module for monitoring aspects of the rig. Further exemplary systems include, but are not limited to, compressor monitoring and/or impulse steam engine monitoring.

In an embodiment, a system for data collection in an industrial environment may include a trigger signal and at least one data signal sharing a common output of a signal multiplexer, where the common output may be switched to propagate either the data signal or the trigger signal upon detecting a condition in the industrial environment, such as the state of the trigger signal. Sharing the data and trigger signal outputs may also reduce the number of individually wired signals in the industrial environment. Benefits of reducing individually wired signals include reducing the number of interconnections between data collection modules and reducing the complexity of the industrial environment. Trade-offs for reducing individually wired signals may include more sophisticated logic in the signal switching modules to implement signal detection and conditional switching. This added local logic complexity has the benefit of reducing the overall complexity of implementing such a data collection system in an industrial environment.

An exemplary deployment environment may include environments with limited trigger signal channels, such as existing data collection systems that do not have separate trigger support for transmitting additional trigger signals to modules with sufficient computing power to perform trigger detection. Another exemplary deployment may include systems that require at least some autonomous control to perform data collection.

In an embodiment, a system for data collection in an industrial environment may include an analog switch that switches between a first input, such as a trigger input, and a second input, such as a data input, based on the state of the first input. The trigger input may be monitored by a portion of the analog switch to detect a change in the signal, such as a change from a low voltage to a high voltage relative to a reference voltage or trigger threshold voltage. In an embodiment, a device that may receive a switched signal from the analog switch may monitor the trigger signal for a condition indicating a condition for switching from the trigger input to the data input. If a condition for the trigger input is detected, the analog switch may be reconfigured to direct the data input to the same output that was propagating the trigger output.

In an embodiment, a system for collecting data in an industrial environment may include an analog switch that routes a first input to an output of the analog switch until the output of the analog switch indicates that a second input should be routed to the output of the analog switch. The output of the analog switch may propagate a trigger signal to the output. In response to the trigger signal propagating through the switch transitioning from a first condition (e.g., a first voltage below a trigger threshold voltage value) to a second condition (e.g., a second voltage above a trigger threshold voltage value), the switch may stop propagating the trigger signal and instead propagate another input signal to the output. In an embodiment, the trigger signal and other data signals may be related; for example, the trigger signal may indicate the presence of an object placed on a conveyor and the data signal may represent a strain placed on the conveyor.

In embodiments, to facilitate timely detection of a trigger condition, the sampling rate of the analog switch output may be adjustable, e.g., a higher sampling rate during the propagation of a trigger signal and a lower sampling rate during the propagation of a data signal. Alternatively, the sampling rate may be fixed for either the trigger signal or the data signal. In embodiments, the sampling rate may be faster than the minimum sample rate required to capture a data signal based on a predetermined time between trigger occurrence and trigger detection.

In an embodiment, routing multiple hierarchically organized triggers to separate analog channels can facilitate implementation of a hierarchical data collection trigger structure in an industrial environment. A data collection template for implementing a hierarchical trigger signal architecture may include signal switch configuration and function data that may facilitate a signal switch facility, such as an analog crosspoint switch or multiplexer, to output a first input trigger in the hierarchy and, based on the detection of a first trigger condition, output a second input trigger in the hierarchy to the same output as the first input trigger by changing the internal mapping from input to output. When a second input trigger condition is detected, the output may be switched to a data signal, such as data from a sensor in the industrial environment.

In embodiments, detecting a trigger condition may cause an alarm to be generated and optionally propagated to a higher-functioning device/module, in addition to switching from a trigger signal to a data signal. Also, in addition to switching to a data signal, detecting a trigger condition may cause a disabled or powered-down sensor to be energized/activated to begin generating data for the newly selected data signal. Activation may also include sending a reset or refresh signal to the sensor.

In an embodiment, a system for data collection in an industrial environment may include a system for routing a trigger signal to a data signal path associated with a gearbox of an industrial vehicle. Combining a trigger signal with a signal path also used for data signals is useful in gearbox applications by reducing the number of signal lines required, while enabling advanced functionality such as data collection based on hydraulic fluid pressure changes. For example, a sensor may be configured to detect a hydraulic fluid pressure differential above a certain threshold, such as when hydraulic fluid flow is returned to an impeller to achieve high torque at low speeds. The output of such a sensor may be configured as a trigger to collect data related to the gearbox during low-speed operation. As an example, an industrial data collection system may include a multiplexer or switch to route either a trigger or a data channel along a single signal path. Upon detecting a trigger signal from a pressure sensor, a different signal may be routed along the same line as the trigger signal by switching a set of controls. The multiplexer may output a trigger signal until a trigger signal is detected indicating that the output should be changed to a data signal, for example. Detecting a high-pressure condition may result in data collection activity being initiated, allowing data to be collected using the same line as the trigger signal most recently used.

In an embodiment, a system for data collection in an industrial environment may include a system for routing a trigger signal onto a data signal path associated with a vehicle suspension for truck and automobile operation. Vehicle suspensions, particularly active suspensions, may include sensors for detecting road events, suspension conditions, and vehicle data such as speed, steering, etc. These conditions may not need to be detected at all times, for example, except upon detection of a trigger condition. Therefore, combining the trigger condition signal and at least one data signal onto a single physical signal routing path may be implemented. Doing so may reduce costs by requiring fewer physical connections for such a data collection system. As an example, a sensor may be configured to detect a condition to which the suspension must respond, such as a pothole. Data from the suspension may be routed along the same signal routing path as this road condition trigger signal, such that upon detection of a pothole, data may be collected that is useful for determining aspects of the suspension's response to the pothole.

In an embodiment, a system for data collection in an industrial environment may include a system for routing a trigger signal onto a data signal path associated with a power generating turbine in a power plant. Turbines used to generate electricity may be retrofitted with a data collection system that optimizes existing data signal paths to implement greater data collection capabilities. One such method involves routing new data sources onto existing lines. While signal multiplexing is typically used, combining trigger and data signals via a multiplexer or similar device can further enhance data collection efficiency. In one example, a first sensor may include a temperature sensor for measuring the temperature of a side of the power generating turbine. When that trigger is detected (e.g., by the temperature rising above a thermal threshold), a data collection system controller may transmit a different data collection signal over the same line used to detect the trigger condition. This may be accomplished by the controller or similar detecting a change in the trigger signal condition and signaling a multiplexer to switch from the trigger signal to a data signal output on the same line as the data collection trigger signal. In this example, if a portion of the turbine is detected to exceed a safety temperature threshold, a secondary safety signal may be routed onto the trigger signal path to monitor for additional safety conditions, such as overheating.

With reference to FIG. 36, one embodiment of routing a trigger signal onto a data signal path in a data collection system in an industrial environment is depicted. A signal multiplexer 7400 may receive a trigger signal on a first input from a sensor or other trigger source 7404 and a data signal on a second input from a sensor for detecting a temperature associated with industrial machinery in the environment 7402. The multiplexer 7400 may be configured to output the trigger signal onto an output signal path 7406. A data collection module 7410 may process the signal on the data path 7406, looking for a change in the signal indicative of a trigger condition provided from the trigger sensor 7404 via the multiplexer 7400. Once detected, a control output 7408 may be altered, thereby controlling the multiplexer 7400 to begin outputting data from the temperature probe 7402, such as by switching an internal switch that may control one or more of the inputs that may be routed to the output 7406. In response to a detected trigger, the data collection facility 7410 may initiate a data collection template that may include switching the multiplexer and collecting data into the triggered data store 7412. Upon completion of the data collection activity, the multiplexer control signal 7408 may return to its initial state so that the trigger sensor 7404 may again be monitored.

An exemplary system for data collection in an industrial environment includes an analog switch that directs a first input to an output of the analog switch until the output of the analog switch indicates that a second input should be directed to the output of the analog switch. In certain further embodiments, the exemplary system includes: when the output of the analog switch indicates that the second input should be directed to the output based on the output transitioning from a pending state to a triggered state, and the triggered state includes detecting the output exhibiting a voltage equal to or greater than a trigger voltage value; in response to the output of the analog switch indicating that the second input should be directed to the output, routing multiple signals using the analog switch from the input of the analog switch to the output of the analog switch; sampling the output of the analog switch at a rate that exceeds the transition rate of the multiple signals input to the analog switch; and/or generating an alarm signal when the output of the analog switch indicates that the second input should be directed to the output of the analog switch.

An exemplary system for data collection in an industrial environment includes an analog switch that switches between a first input and a second input based on a state of the first input. In certain further embodiments, the state of the first input includes the first input exhibiting a triggered state, and/or the triggered state includes detecting that the first input exhibits a voltage exceeding a trigger voltage value. In certain embodiments, the analog switch includes routing a plurality of analog signals from inputs on the analog switch to outputs on the analog switch based on the state of the first input, sampling the inputs of the analog switch at a rate that exceeds a transition rate of the plurality of signals input to the analog switch, and/or generating an alarm signal based on the state of the first input.

An exemplary system for data collection in an industrial environment includes a trigger signal and at least one data signal sharing a common output of a signal multiplexer, the common output configured to propagate the at least one data signal through the signal multiplexer upon detection of a predetermined state of the trigger signal. In certain further embodiments, the signal multiplexer is an analog multiplexer, the predefined state of the trigger signal is detected at the common output, detecting the predefined state of the trigger signal includes detecting the common output presenting a voltage equal to or greater than a trigger voltage value, the multiplexer includes routing multiple signals from inputs on the multiplexer to outputs on the multiplexer in response to detecting the predefined state of the trigger signal, also including routing multiple signals between the multiplexer and the multiple signals, sampling the output of the multiplexer at a rate exceeding a transition rate of the multiple signals input to the multiplexer, the multiplexer generating an alarm in response to detecting the predefined state of the trigger signal, and/or the multiplexer activating at least one sensor to generate the at least one data signal. Exemplary systems include, but are not limited to, monitoring a gearbox of an industrial vehicle by directing a trigger signal representing the state of the gearbox to the output of an analog switch until the output of the analog switch indicates that a second input representing the state of the gearbox associated with the trigger signal should be directed to the output of the analog switch; monitoring a suspension system of an industrial vehicle by directing a trigger signal representing the state of the suspension to the output of an analog switch until the output of the analog switch indicates that a second input representing the state of the suspension associated with the trigger signal should be directed to the output of the analog switch; and/or monitoring a power generating turbine by directing a trigger signal representing the state of the power generating turbine to the output of an analog switch until the output of the analog switch indicates that a second input representing the state of the power generating turbine associated with the trigger signal should be directed to the output of the analog switch.

In an embodiment, a system for collecting data in an industrial environment may include a data collection system that monitors at least one signal for a set of collection band parameters and, upon detection of a parameter from the set of collection band parameters in the signal, configures collection of data from a set of sensors based on the detected parameter. The selected set of sensors, the signal, and the set of collection band parameters may be part of a smart band data collection template that the system can use when collecting data in the industrial environment. Motivations for preparing a smart band data collection template may include monitoring a set of conditions of an industrial machine to facilitate improved operations, reduced downtime, preventive maintenance, breakdown prevention, etc. Based on analysis of data about the industrial machine, such as conditions that may be detected by a set of sensors, action can be taken, such as notifying a user of a change in a condition, adjusting operating parameters, scheduling preventive maintenance, triggering data collection from an additional set of sensors, etc. Examples of data that may indicate the need for some action include a detectable change through a trend in the data from the set of sensors, as well as a trend in an analytical value obtained from a group of sensors.

In embodiments, the set of collection band parameters may include values received from sensors configured to sense conditions (e.g., bearing vibration) of an industrial machine. However, the set of collection band parameters may instead be a trend of data received from a sensor (e.g., a trend of bearing vibration across multiple vibration measurements by a bearing vibration sensor). In embodiments, the set of collection band parameters may be a composite of data and/or data trends from multiple sensors (e.g., a trend of data from an on-axis vibration sensor and an off-axis vibration sensor). In embodiments, data collection activity from the set of sensors may be triggered when data values obtained from one or more sensors described herein are sufficiently close to data values within the set of collection band parameters. Alternatively, data collection activity from the set of sensors may be triggered when data values (e.g., trends, etc.) derived from one or more sensors fall outside the set of collection band parameters. As an example, the set of data collection band parameters for a motor may be a rotational speed range from 95% to 105% of a selected operating rotational speed. As long as the motor's rotational speed trend is within this range, data collection activity may be postponed. However, if a trend reaches or exceeds this range, it may trigger data collection activities, such as those defined by the smart band's data collection template.

In embodiments, triggering a data collection activity, such as that defined by a smart band's data collection template, may result in a change to the data collection system of the industrial environment that may affect aspects of the system, such as data sensing, switching, routing, storage allocation, and storage configuration. This change to the data collection system may occur near real-time upon detection of the condition, or may be scheduled to occur in the future. It may also be coordinated with other data collection activities, such as data collection activities for a different smart band data collection template, to allow completion of active data collection activities before the system is reconfigured to a smart band data collection template initiated by a sensed condition satisfying a smart band data collection trigger.

In embodiments, processing of data from sensors may be cumulative, such as over time, across a set of sensors, across machines in an industrial environment, etc. A sensed value of a condition may be sufficient to trigger a smart band's data collection template activity, but data may need to be collected and processed over time from multiple sensors to generate a data value that can be compared to a set of data collection band parameters to conditionally trigger data collection activity. Using data from multiple sensors to process the data, such as generating a trend of data values, may facilitate preventing insignificant instances of sensed data values outside of an acceptable range from triggering undue smart band data collection activity. As an example, if vibration from a bearing is detected infrequently outside of an acceptable range, trending this value over time is useful to detect whether the frequency is increasing, decreasing, substantially constant, or within a range of values. If the frequency of such values is found to be increasing, such a trend indicates a change has occurred in the operation of the industrial machine as experienced by the bearing. An acceptable range for this trended vibration value can be set as a parameter for a data collection band for monitoring the bearing's vibration data. If the trended vibration value is outside of this acceptable range, a smart band data collection activity may be initiated.

In embodiments, a system for data collection in an industrial environment supporting a smart band data collection template may be configured with data processing capabilities upon sensing one or more conditions that may trigger data collection activity of the smart band data collection template, for example, through the use of intelligent sensors that may include data processing capabilities, through the use of programmable logic components that interface with and process data from the sensors, through the use of a computer processor, such as a microprocessor, located proximate to the sensors, etc. In embodiments, the processing of data collected from one or more sensors to detect smart band template data collection activity may be performed by a remote processor, server, etc. that has access to data from multiple sensors, sensor modules, industrial machines, industrial environments, etc.

In an embodiment, a system for data collection in an industrial environment may include a data collection system that monitors the industrial environment for a set of parameters and, upon detection of at least one parameter, configures collection of data from a set of sensors and causes a data storage controller to adapt the configuration of the data storage facility to support collection of data from the set of sensors based on the detected parameter. The methods and systems described herein for conditionally altering the configuration of a data collection system in an industrial environment to implement a data collection template for a smart band may further include altering the data storage architecture. As an example, the data storage facility may be located on a data collection module that includes one or more sensors for monitoring conditions in the industrial environment. This local data storage facility may typically be configured to rapidly move sensed data from the module to a next-level sensing or processing module or server. When a data collection condition for a smart band is detected, it may be necessary to simultaneously collect sensor data from multiple sensors. To accommodate this simultaneous collection, the local memory may be reconfigured to cooperatively capture data from each of the multiple sensors, e.g., by synchronously and repeatedly sampling each sensor, thereby building a sensor data set of much larger size than would typically be captured and moved to local memory, and using known offsets, etc. A storage control facility that controls the local storage oversees the movement of sensor data to and from the local data storage, thereby enabling secure movement of data from multiple sensors to the local data storage and to destinations such as a server, network storage facility, etc. The local data storage facility may be configured such that data from a set of sensors associated with a smart band data collection template is securely stored and readily accessible as a set of smart band data to facilitate processing of the smart band-specific data. By way of example, the local storage may comprise non-volatile memory (NVM). To prepare for data collection in response to a smart band data collection template being triggered, a portion of the NVM may be erased to prepare the NVM to receive data indicated in the template.

In embodiments, multiple sensors may be arranged into sensor sets for condition-specific monitoring. Each set, which may be a logical set of sensors, may be selected to provide information about an element of the industrial environment that can provide insight into potential problems, the root cause of the problem, etc. Each set may be associated with a condition that can be monitored for compliance with a tolerance value. Sensor sets may be based on machine architecture, component hierarchy, or a hierarchy of data contributing to machine insights that can be usefully applied to maintaining or improving performance in an industrial environment. Smart band sensor sets may be configured based on expert system analysis of complex conditions, such as machine failures. Smart band sensor sets may be arranged to facilitate knowledge collection that is independent of specific failure modes or history. Smart band sensor sets may be arranged to test proposed smart band data collection templates before implementing them as part of an industrial machine's operating program. Collecting and processing data from sensor sets facilitates determining which sensors are contributing meaningful data to the set, and non-contributing sensors can be removed from the set. Smart band sensor sets may be adjusted based on external data, such as industrial surveys that indicate the types of sensor data that are most useful for reducing failures in industrial environments.

In an embodiment, a system for data collection in an industrial environment may include a data collection system that monitors at least one signal for compliance with a set of collection band conditions and configures the system upon detection of non-compliance. Data may be collected from a predetermined set of sensors associated with the monitored signal, and upon detection of non-compliance, a collection band template associated with the monitored signal may be accessed and resources identified in the template configured to perform data collection. In an embodiment, the template may identify which sensors to activate, the data from the sensors to collect, the duration of collection or the amount of data to collect, the destination (e.g., memory structure) for storing the collected data, etc. In an embodiment, a smart band method for data collection in an industrial environment may include periodic collection of data from one or more sensors configured to sense a condition of an industrial machine in the environment. The collected data may be compared against a set of criteria defining an acceptable range for the condition. If the collected data is verified to be either approaching one end of an acceptable limit or exceeding an acceptable range for the condition, data collection may be initiated from a smart band group of sensors associated with the sensed condition based on a smart band collection protocol configured as a data collection template. In an embodiment, the acceptable range for the condition is based on a history of applied analyses of the condition. In an embodiment, if an out-of-tolerance condition is verified, the data storage resources of the module where the sensed condition was detected may be configured to facilitate the capture of data from the smart band group of sensors.

In embodiments, monitoring conditions to trigger a smart band data collection template data collection operation may be in response to a regulation, such as a safety regulation, in response to an upcoming activity, such as a portion of an industrial environment being shut down for preventative maintenance, in response to sensor data being missing from a routine data collection activity, etc. In embodiments, in response to a failed sensor or missing sensor data in a smart band template data collection activity, one or more replacement sensors may be temporarily included in the sensor set to provide data that can effectively substitute for the missing data in the data processing algorithm.

In embodiments, the Smart Band data collection template may be configured to detect and collect data for Smart Band analysis covering vibration spectra such as vibration envelopes and current signatures for spectral regions or peaks, which may be a combination of absolute frequency or machine-related parameter factors, vibration time waveforms for time domain derived calculations, etc. Vibration time waveforms for time domain derived calculations include, but are not limited to, RMS overall, peak overall, true peak, crest factor, etc., vibration vectors, spectral energy humps for each region (low frequency region, high frequency region, lower order, etc.), pressure-volume analysis, etc.

In embodiments, a system for data collection applying the SmartBand data collection template may be applied to an industrial environment, such as a ball screw actuator in an automated manufacturing environment. SmartBand analysis may be applied to a ball screw actuator in an industrial environment, such as a precision manufacturing or positioning application (e.g., semiconductor photolithography machine). Because a ball screw is typically used for precise positioning, detecting variations in the positioning mechanism can prevent costly rejects. SmartBand triggering and data collection is useful in such applications, as SmartBand analysis can detect potential variations in positioning mechanisms, such as ball screw mechanisms, worm drives, and linear motors. In one example, data related to a ball screw positioning system may be collected using a system for data collection in an industrial environment as described herein. Multiple sensors may be configured to collect data such as screw torque, screw direction, screw speed, screw step, and screw origin detection. Portions of this data may be processed by the SmartBand's data analysis functionality to determine whether variances, such as the trend of screw speed as a function of torque, are approaching or exceeding acceptable thresholds. Once such a determination is made, the ball screw production system's data collection template is activated, configuring the data collection system's data sensing, routing, and collection resources to collect data to facilitate further analysis. The Smart Band's data collection template facilitates the rapid collection of data from other sensors (e.g., position, direction, acceleration) in addition to screw speed and torque by routing data from the corresponding sensors to a data collector via one or more signal paths. The Smart Band's data collection template also allows you to specify the period and order in which data is collected from these sources, effectively collecting the data required for further analysis.

In an embodiment, a system for data collection that configures and utilizes a data collection and routing infrastructure by applying the smart band data collection template can be applied to ventilation systems in mining environments. Ventilation plays a critical role in mining safety. Early detection of potential ventilation equipment problems can be supported by applying the smart band approach to data collection in such environments. Sensors may be deployed to collect information about the operation, quality, and performance of ventilation during mining operations. At each ventilation unit, ventilation-related elements such as fans, motors, belts, filters, thermometers, voltage, current, air quality, and toxic detection may be configured with corresponding sensors. While fluctuations in any one element (e.g., air volume per minute) may not necessarily indicate a problem, smart band analytics can be applied to detect trends over time that may indicate a potential ventilation equipment problem. Smart band analytics may require data from multiple sensors on which to base the analysis. Data from ventilation units can be acquired by implementing a data collection system at the ventilation unit. In one example, smart band analytics may be directed to the ventilation unit. In response to this instruction, the data collection system may be configured to collect data from sensors located at the ventilation stations by routing the data to a central monitoring facility that may collect and analyze data from multiple ventilation stations.

In embodiments, a system for data collection that applies a SmartBand data collection template to configure and utilize a data collection and routing infrastructure may be applied to drivetrain data collection and analysis in mining environments. Drivetrains, such as those for mining vehicles, may include a variety of components that can benefit from the use of the data collection methods and systems in industrial environments described herein. In particular, SmartBand-based data collection may be used to collect data from large mining vehicle drivetrains under specific conditions that may be detectable by SmartBand analysis. SmartBand-based data collection templates may be used by the drivetrain data collection and routing system to configure sensors, data paths, and data collection resources to perform data collection under specific circumstances that may indicate unacceptable trends in drivetrain performance. A data collection system for an industrial drivetrain may include sensing surfaces such as non-steered axles, planetary steered axles, driveshafts (e.g., mainshaft and wingshaft), transmissions (e.g., standard, torque converter, long drop), etc. Various data related to these operating components may be collected. However, for a thorough SmartBand analysis, data on the support and structural members that support the drivetrain may also need to be collected. Collection across this wide range of drivetrain-related components may therefore be triggered based on the smartband analysis' determination of the need for this data. As an example, smartband analysis may indicate potential slippage between the main driveshaft and wing driveshafts, which may be manifested by an increasing trend in the wing driveshaft's response delay time relative to main driveshaft operation. In response to this increasing trend, data collection modules located throughout the mining vehicle's drivetrain may be configured to route data from local sensors to be collected and analyzed by the data collector. The mining vehicle's drivetrain smart-based data collection may include various templates based on what type of trend is detected. If a trend related to the steering axis is detected, the data collection template implemented may differ in sensor content, duration, etc. from a trend related to power demand relative to normalized payload. Each template may configure data sensing, routing, and collection resources throughout the vehicle's drivetrain accordingly.

With reference to FIG. 37 , a system for data collection in an industrial environment that facilitates data collection for smart band analytics is depicted. The system for data collection in an industrial environment may include a smart band analytics data collection template repository 7600 in which smart band templates 7610 for data collection system configuration and data collection are stored and may be accessed by a data collection controller 7602. The templates 7610 may include data collection system configuration 7604 and operational information 7606, which may identify sensors, collectors, signal paths, and information for initiating and coordinating collection. The controller 7602 may receive instructions, such as commands, from a smart band analytics facility 7608 to select and implement a particular smart band template 7610. The controller 7602 may access the templates 7610 and configure data collection system resources based on the information in the templates. In an embodiment, the template may identify specific sensors, multiplexer/switch configurations, data collection trigger/start signals and/or conditions, time duration and/or data volume for collection, destination of collected data, intermediate processing, if any, and other useful information (e.g., instance identifiers, etc.). The controller 7602 can configure and operate the data collection system to perform collections for the smart band template and optionally revert the system configuration to a previous configuration.

An exemplary system for collecting data in an industrial environment includes a data collection system that monitors at least one signal for a set of collection band parameters, and when a parameter from the set of collection band parameters is detected, configures part of the system to collect data from a set of sensors based on the detected parameter. In certain further embodiments, the signal includes an output of a sensor that senses a condition in the industrial environment, the set of collection band parameters includes a value that exceeds an acceptable range of values derivable from the signal, and the at least one signal includes an output of the sensor that senses the condition in the industrial environment. Configuring part of the system includes configuring a storage device to accept data collected from the set of sensors, and configuring part of the system includes configuring a data routing portion to include at least one of the following: configuring a data routing portion to include at least one of an analog crosspoint switch, a hierarchical multiplexer, an analog-to-digital converter, an intelligent sensor, and/or a programmable logic component; detecting the parameter from the set of collection band parameters includes detecting that a trend value of the signal exceeds an acceptable range of trend values; and/or configuring part of the system includes implementing a smart band data collection template associated with the detected parameter. In certain embodiments, the data collection system monitors a signal for data values within a set of acceptable data values representing acceptable collection band conditions for the signal, and upon detecting at least one signal data value outside the set of acceptable data values, triggers a data collection activity that causes data to be collected from a predetermined set of sensors associated with the monitored signal. In certain further embodiments, the data collection system includes a signal including an output of a sensor sensing a condition of an industrial environment, the set of acceptable data values including values derivable from the signal within an acceptable range of values derivable from the signal, and includes configuring a storage device of the system to facilitate collecting data from the predetermined set of sensors in response to detecting a data value outside the set of acceptable data values; and configuring a data routing portion of the system including analog crosspoint switches, hierarchical multiplexers, analog-to-digital converters, intelligent sensors, and/or programmable logic components in response to detecting a data value outside the set of acceptable data values, wherein detecting a signal data value outside the set of acceptable data values includes detecting that a trend value of the signal exceeds an acceptable range of trend values; and/or the data collection activity is defined by a smart band data collection template associated with the detected parameter.

An exemplary method for collecting data in an industrial environment includes acts of collecting data from a sensor(s) configured to sense a condition of an industrial machine in the environment, checking the collected data against a set of criteria defining an acceptable range for the condition, and, in response to the collected data violating the acceptable range for the condition, collecting data from a smart band group of sensors associated with the sensed condition based on a smart band collection protocol configured as a smart band data collection template. In certain further embodiments, the method includes acts of violating the acceptable range for the condition when a trend in data from the sensor(s) approaches a maximum value for the acceptable range; the smart band group of sensors is defined by a smart band data collection template; the smart band data collection template includes a list of sensors to activate, data from the sensors to collect, a collection period for data from the sensors, and/or a destination for storing the collected data; collecting data from the sensors of the smart band includes configuring at least one data routing resource in the industrial environment to facilitate routing of data from the sensors of the smart band to a plurality of data collectors; and/or the set of criteria includes a range of trend values obtained by processing the data from the sensors.

Without limitation, an exemplary system monitors a ball screw actuator in an automated manufacturing environment, monitoring at least one signal from the ball screw actuator for a set of collection band parameters, and upon detecting a parameter from the set of collection band parameters, performs data collection from a set of sensors that form part of a system and are arranged to monitor the condition of the ball screw actuator based on the detected parameter. Another exemplary system monitors a ventilation system in a mining environment, monitoring at least one signal from the ventilation system for a set of collection band parameters, and upon detecting a parameter from the set of collection band parameters, performs data collection from a set of sensors that form part of a system and are arranged to monitor the condition of the ventilation system based on the detected parameter. An exemplary system monitors a drivetrain of a mining vehicle, monitoring at least one signal from the drivetrain for a set of collection band parameters, and upon detecting a parameter from the set of collection band parameters, performs data collection from a set of sensors that form part of a system and are arranged to monitor the condition of the drivetrain based on the detected parameter.

In an embodiment, a system for data collection in an industrial environment may automatically configure local and remote data collection resources and perform data collection from multiple system sensors identified as part of a sensor group that generates the data necessary to perform operational deflection shape rendering. In an embodiment, the system sensors are distributed throughout the following structural parts: industrial machinery used in an industrial environment; and system sensors sense a range of system conditions, including vibration, rotation, balance, friction, etc. In an embodiment, the automatic configuration occurs in response to a condition of the environment being detected outside an acceptable range of condition values. In an embodiment, sensors in an identified group of system sensors sense the condition.

In an embodiment, a system for data collection in an industrial environment may configure a data collection plan, such as a template, to collect data from multiple system sensors distributed throughout a machine to facilitate automatically creating an operational deflection shape visualization ("ODSV") based on the machine's structural information and the datasets used to create the machine's ODSV.

In an embodiment, a system for collecting data in an industrial environment may construct a data collection template for collecting data in the industrial environment by identifying sensors positioned to sense the condition of pre-selected structural members of the industrial machine in the environment based on the ODSV of the industrial machine. In an embodiment, the template may include an order and timing for collecting data from the identified sensors.

In embodiments, methods and systems for data collection in industrial environments may include a method for establishing acceptable sensor value ranges for a plurality of industrial machine condition sensors by verifying that operational deflection shape visualization of structural elements of the machine exhibits deflections within acceptable ranges, where data from the plurality of sensors used in the verified ODSV defines the acceptable sensor value ranges.

In an embodiment, a system for data collection in an industrial environment may include multiple data sources, such as sensors, that are grouped for coordinated data collection to provide the data necessary to generate the ODSV. Information such as which sensors to group and the coordination requirements for data collection may be obtained from an ODSV data collection template. The coordinated data collection may include simultaneous data collection. To facilitate simultaneous data collection from a subset of sensors, the sensor routing resources of the system for data collection may be configured, such as by configuring a data multiplexer to route data from the subset of sensors to which it connects to a data collector. In an embodiment, each source connected to an input of the multiplexer may be routed to a separate output within the multiplexer, such that data from all of the connected sources is routed to a data collection element in the industrial environment. In an embodiment, the multiplexer may include data storage capabilities that facilitate sharing a common output for at least some of the inputs. In an embodiment, the multiplexer may include data storage capabilities and a data bus-compatible output so that data from each source is captured in memory and transmitted over a data bus, such as a data bus common to the output of the multiplexer. In embodiments, the sensors may be smart sensors that include data storage capabilities and may transmit data from the data storage to the multiplexer in a coordinated manner that supports use of a common output of the multiplexer and/or use of a common data bus.

In an embodiment, a data collection system in an industrial environment may include templates for configuring the data collection system to collect data from multiple sensors to perform ODSV for multiple deflection geometries. Individual templates may be configured to visualize loose joints, soft joints, bends, twists, etc. Individual deflection geometry data collection templates may be configured for different parts of a machine in an industrial environment.

In embodiments, a system for data collection in an industrial environment may facilitate visualization of operational deflection shapes, which may include visualization of the locations of sensors that contributed data to the visualization. In the visualization, each sensor that contributed data to generate the visualization may be represented by a visual element. The visual element may facilitate user access to information about the sensor, such as the sensor's location, type, representative data contributed, the path of the data from the sensor to the data collector, a deflection shape template identifier, and the configuration of switches or multiplexers through which the data is routed. The visual element may be determined by associating sensor identification information received from the sensor with information relating the sensor identification to a physical location in the environment, such as a sensor map. Information may be displayed in the visualization in response to a user selecting a visual element representing a sensor, such as by hovering a cursor over the sensor visual element.

In embodiments, ODSV may benefit from data that meets the phase relationship requirements. A data collection system in the environment may be configured to facilitate collection of data that meets the phase relationship requirements. Alternatively, the data collection system may be configured to collect data from multiple sensors that includes data that meets the phase relationship requirements, but may also include data that does not. Post-processing operations that may access the phase detection data may select a subset of the collected data.

In an embodiment, a system for data collection in an industrial environment may include a multiplexer that receives data from multiple sensors and multiplexes the received data for delivery to a data collector. The data collector may process the data to facilitate ODSV. ODSV may require data from multiple different sensors, and using a reference signal, such as data from the sensors, is beneficial when processing the data from the different sensors. The multiplexer may be configured to provide data from different sensors, e.g., switch its inputs over time so that data from each sensor is received by the data collector. However, the multiplexer may include multiple outputs such that at least some of the inputs are routed to at least two of the multiple outputs. Thus, in an embodiment, a multiple-output multiplexer may be configured to facilitate data collection suitable for ODSV by routing a reference signal (e.g., data from an accelerometer) from one of its inputs to one of its outputs and multiplexing data from multiple of its outputs to one or more of its outputs while maintaining the reference signal output routing. The data collector may collect data from the reference output and use it to align multiplexed data from other sensors.

In an embodiment, a system for data collection in an industrial environment may facilitate ODSV through coordinated data collection related to conveyors for mining applications. Mining operations may rely on conveyor systems to move materials, supplies, and equipment in and out of mines. Because mining operations typically operate around the clock, conveyor downtime can significantly impact productivity and costs. Advanced analysis of conveyors and related systems may focus on secondary effects that are difficult to detect through point observations and may be more easily detected through ODSV. Acquiring operational data such as vibration and stress can facilitate ODSV. However, coordinated data acquisition can yield more reliable results. Thus, a data collection system, which may have sensors distributed throughout a conveyor system, can be configured to facilitate such coordinated data collection. As an example, the capture of data affecting structural components of a conveyor, such as landing points and the horizontal members connecting and supporting the conveyor between landing points, conveyor segment handoff points, motor mounts, and conveyor roller mounts, may need to be coordinated with data related to conveyor dynamic loads, drive systems, motors, gates, etc. A system for data collection in an industrial environment, such as a mining environment, may include data sensing and collection modules located throughout the conveyor at locations such as segment handoff points, drive systems, and the like. Each module may be configured with one or more controllers, such as a programmable logic controller, and connected via a physical or logical (e.g., wireless) communication bus to facilitate coordinated data collection. To facilitate coordination, reference signals, such as triggers, may be communicated between modules for use when collecting data. In embodiments, data collection and storage may be performed within each module, reducing the need for real-time transfer of sensed data throughout the mining environment. Data transfer from modules to an ODSV processing facility may occur after collection or as communication bandwidth between the modules and the processing facility permits. ODSV may provide insight into conveyor conditions, such as deflection of structural members. Data collection in conjunction with data collection systems used in industrial environments, such as mining, may enable ODSV to reduce operational costs by reducing downtime due to unplanned component failures.

In embodiments, a system for collecting data in industrial environments can facilitate visualization of operational deflection shapes through coordinated data collection related to fans for mining applications. Fans provide a critical function in mining operations: moving air throughout a mine to provide ventilation, equipment cooling, combustion exhaust, etc. Ensuring reliable, and often continuous, operation of fans is important for miner safety and cost-effective operations. Large mining operations may employ dozens or even hundreds of fans. Ventilation management fans include circuit, booster, and auxiliary types. High-volume auxiliary fans operate at speeds of 2500 RPM or higher. Performing ODSV can provide important reliability information for fans installed in mining environments. Collecting the range of data required for ODSV of mining fans may be performed by a system for collecting data in industrial environments as described herein. In embodiments, sensing elements, such as intelligent sensing and data collection modules, may be deployed with the fans and/or fan subsystems. These modules may exchange collection control information (e.g., via a dedicated control bus) to coordinate data collection in time and phase to facilitate ODSV.

Large auxiliary fans for use in mines may be constructed with transportability in and through the mine in mind and, as such, may include a fan body, intake and exhaust ports, dilution valves, protective cages, electrical enclosures, wheels, access panels, and other structural and/or operational elements. ODSV of such auxiliary fans may require data collection from many different elements. Systems for data collection may be configured to sense and collect data that can be combined with structural engineering data to facilitate ODSV of these types of industrial fans.

38, one embodiment of a system for collecting data in an industrial environment that performs coordinated data collection suitable for ODSV is depicted. The system for collecting data in an industrial environment may include an ODSV data collection template repository 7800 in which ODSV templates 7810 for data collection system configuration and data collection are stored and may be accessed by a system for data collection controller 7802. The templates 7810 may include data collection system configuration 7804 and operational information 7806 that may identify sensors, collectors, signal paths, reference signal information, information for initiating and adjusting collection, etc. The controller 7802 may receive instructions, such as commands, from an ODSV analysis facility 7808 to select and implement a particular ODSV template 7810. The controller 7802 may access the templates 7810 and configure data collection system resources based on the information in the templates. In an embodiment, the template may identify specific sensors, multiplexer/switch configurations, reference signals for regulating data collection, data collection trigger/start signals and/or conditions, time duration and/or data volume for collection, destination of collected data, intermediate processing, if any, and other useful information (e.g., instance identifiers, etc.). The controller 7802 may configure and operate the data collection system to perform collection for the ODSV template and optionally revert the system configuration to a previous configuration.

An exemplary method of data collection for performing ODSV in an industrial environment includes automatically configuring local and remote data collection resources and using the configured resources to collect data from a number of sensors, the number of sensors including a group of sensors that generate data necessary to perform ODSV. In certain further embodiments, the exemplary method further includes: sensors distributed throughout a structural portion of an industrial machine in the industrial environment; sensors sensing a range of system conditions including vibration, rotation, balance, and/or friction; and automatic configuration occurring in response to a condition in the environment being detected outside an acceptable range of condition values. If the condition is sensed by a sensor in a system sensor group, automatic configuration may include configuring signal switching resources to simultaneously connect some of the sensor group to the data collection resources, and/or the signal switching resources may be configured to maintain a connection between a reference sensor and the data collection resource during the period of collecting data from the sensors to perform ODSV.

An exemplary method for collecting data in an industrial environment includes configuring a data collection plan for collecting data from multiple system sensors distributed throughout machines in the industrial environment, the plan being based on structural information about the machines and an indication of data needed to generate an ODSV for the machines; configuring data sensing, routing, and collection resources in the environment based on the data collection plan; and collecting data based on the data collection plan. In certain further embodiments, the exemplary method further includes generating an ODSV, wherein configuring the data sensing, routing, and collection resources is responsive to detecting a condition in the environment outside an acceptable range of condition values, the condition being sensed by a sensor identified in the data collection plan; configuring the resources includes configuring signal switching resources to simultaneously connect multiple system sensors to the data collection resources, and/or configuring the signal switching resources to maintain a connection between a reference sensor and the data collection resource during the time period in which data is collected from the sensors to perform the ODSV.

An exemplary system for data collection in an industrial environment includes multiple sensors disposed throughout the environment, a multiplexer connecting signals from the multiple sensors to a data collection resource, and a processor for processing data collected from the multiple sensors in response to a data collection template, such that the processing results in an ODSV of a portion of a machine disposed in the environment. In certain further embodiments, the exemplary system includes: where the ODSV data collection template further identifies an environmental condition on which performance of data collection from the identified sensors depends, the condition being sensed by the sensors identified in the ODSV data collection template; where the data collection template specifies inputs of the multiplexer to simultaneously connect to the data collection resource; where the multiplexer is configured to maintain a connection between a reference sensor and the data collection resource during the period of collecting data from the sensors to perform ODSV; where the ODSV data collection template specifies data collection requirements for performing ODSV for slack, soft joints, bending, and/or twisting of a portion of a machine in the industrial environment; and/or where the ODSV collection template specifies an order and timing of data collection from the multiple identified sensors.

An exemplary method for monitoring a mining conveyor to perform ODSV of the conveyor includes automatically configuring local and remote data collection resources and using the configured resources to collect data from a number of sensors positioned to sense the mining conveyor, the number of sensors comprising a group of sensors that generate data necessary to perform visualization of the operational deflection shape of a portion of the conveyor. An exemplary method for monitoring a mining fan to perform ODSV of the fan includes automatically configuring local and remote data collection resources using the configured resources to collect data from a number of sensors positioned to sense the fan, the number of sensors comprising a group of sensors that generate data sufficient or necessary to perform ODSV of the portion of the fan.

In embodiments, a system for data collection in an industrial environment may include a hierarchical multiplexer that facilitates sequential multiplexing of input data channels according to a configurable hierarchy, such as a user-configurable hierarchy. A system for data collection in an industrial environment may include a hierarchical multiplexer that facilitates sequential multiplexing of input data channels according to a configurable hierarchy. The hierarchy may be automatically configured by a controller based on operating parameters in the industrial environment, such as parameters of machines in the industrial environment.

In an embodiment, a system for collecting data in an industrial environment may include multiple sensors that may output data at different rates. The system may also include a multiplexer module that receives sensor outputs from a first portion of the multiple sensors having similar output rates into separate inputs of a first hierarchical multiplexer of the multiplexer module. The first hierarchical multiplexer of the multiplexer module may receive sensor outputs from a second portion of the multiple sensors at similar output rates and provide at least one multiplexed output of its inputs to a second hierarchical multiplexer that provides at least one multiplexed output of its inputs. In an embodiment, the output rate of the first set of sensors may be slower than the output rate of the second set of sensors. In an embodiment, the data collection rate requirement of the first set of sensors may be lower than the data collection rate requirement of the second set of sensors. In an embodiment, the output of the first hierarchical multiplexer is a time-multiplexed combination of a portion of its inputs. In an embodiment, the second hierarchical multiplexer receives the sensor signals at an output rate similar to the output rate of the first multiplexer, and the first multiplexer generates a time-based multiplexing of a portion of its multiple inputs.

In an embodiment, a system for data collection in an industrial environment may include a hierarchical multiplexer that is dynamically configured based on a data collection template. The hierarchical multiplexer may include multiple inputs and multiple outputs, and any input can be directed to any output depending on the sensor output collection requirements of the template, and a subset of the inputs can be multiplexed at a first switching rate and output to at least one of the multiple outputs.

In an embodiment, a system for data collection in an industrial environment may include a plurality of sensors for sensing machine conditions in the environment, a hierarchical multiplexer, a plurality of analog-to-digital converters (ADCs), a processor, local storage, and an external interface. The system may perform data collection using the configured elements, including using the processor to access a data collection template of parameters for data collection from a portion of the plurality of sensors, configure the hierarchical multiplexer, the ADC, and the local storage to facilitate data collection based on the defined parameters, and store a set of data collected from the portion of the plurality of sensors in the local storage. In an embodiment, the ADC converts analog sensor data into a digital format compatible with the hierarchical multiplexer. In an embodiment, the processor monitors at least one signal generated by the sensor for a trigger condition and, upon detecting the trigger condition, responds by at least one of communicating an alert via the external interface and performing data collection according to the template corresponding to the trigger condition.

In an embodiment, a system for data collection in an industrial environment may include a hierarchical multiplexer that may be configurable based on a data collection template for the environment. The multiplexer may support simultaneous reception of multiple data signals (e.g., from sensors in the environment). In an embodiment, all sensors for a portion of industrial machines in the environment may be individually connected to inputs of a first stage of the multiplexer. The first stage of the multiplexer may provide multiple outputs that may feed a second multiplexer stage. The second stage multiplexer may provide multiple outputs that may feed a third stage, and so on. A data collection template for the environment may be configured for a specific data collection set, such as a set for determining the temperature of an entire machine or a set for determining the vibration of an entire machine. Each template may identify multiple sensors in the environment from which data should be collected, such as during a data collection event. When a template is presented to the hierarchical multiplexer, the input and output mapping of each multiplexing stage is configured, making the required data available at the output(s) of the final multiplexing hierarchical stage for data collection. As an example, a data collection template that collects a set of data to determine the temperature of an entire machine in an environment may specify many temperature sensors. A first-stage multiplexer may respond to the template by selecting all available inputs to connect to the temperature sensors. Data from these sensors may be multiplexed to multiple inputs of a second-stage sensor that performs time-based multiplexing to produce a time-multiplexed output of temperature data from a subset of the sensors. These outputs may be collected by a data collector and demultiplexed into individual sensor temperature measurements.

In embodiments, time-sensitive signals, such as triggers, can be connected to inputs that connect directly to the final multiplexer stage, thereby reducing potential delays caused by routing through multiple multiplexer stages.

In embodiments, a hierarchical multiplexer in a system for data collection in an industrial environment may be comprised of an array of relays, a programmable logic component such as a CPLD, a field programmable gate array (FPGA), etc.

In an embodiment, a system for data collection in an industrial environment, which may include a hierarchical multiplexer for routing sensor outputs to signal paths, may be used with explosive systems in mining applications. A blast initiation system and an electronic blasting system may be configured to provide a computer-aided blasting system. Effective sensing and analysis of various conditions may be required to ensure blasting is carried out safely. The system for data collection in an industrial environment may be deployed to sense and collect data related to explosive systems, such as those used in mining. The data collection system may use the hierarchical multiplexer to automatically collect data from an explosive system installation by matching the explosive system's arrangement, including, for example, layout planning, integration, interconnectivity, cascade planning, etc., to the hierarchical multiplexer. Explosive systems may be deployed in a hierarchical fashion, beginning with a primary initiator and tracing detonation connections through successive layers of electronic explosion control to sequentially detonate. The data collected from each of these layers of the blast system configuration may be associated with a stage of a hierarchical multiplexer so that data collected from the detonation of bulk explosives is captured at the layer corresponding to that blast control layer.

In an embodiment, a system for data collection in an industrial environment, which may include a hierarchical multiplexer for routing sensor outputs to signal paths, may be used with refinery blowers in oil and gas pipeline applications. Refinery blower applications include fired heater combustion air preheating systems, etc. Forced draft blowers may include various moving and dynamic components that may benefit from condition sensing and monitoring. Sensing may include detecting the status of couplings (temperature, RPM, etc.), motors (vibration, temperature, RPM, torque, power usage, etc.), louver mechanisms (actuators, louvers, etc.), and plenums (flow rate, blockages, backpressure, etc.). A system for data collection in an industrial environment, which uses a hierarchical multiplexer for routing signals from sensors, etc. to a data collector, may be configured to collect data from a refinery blower. As an example, multiple sensors may be deployed to sense air flow, bulk, and outlet to a forced draft blower used in a refinery application, such as preheating combustion air. Sensors may be grouped based on the frequency of the signals generated by the sensors. Sensors detecting louver position and control may generate data at a slower rate than sensors detecting blower RPM. Therefore, because data from the louvers changes less frequently than data from the RPM sensors, the louver position and control sensor signals may be applied lower in the multiplexer hierarchy than the blower RPM sensor. A data collection system may be able to switch between multiple louver sensors and still obtain enough information to properly detect louver position. However, properly detecting blower RPM data may require a higher bandwidth connection between the blower RPM sensor and the data collector. A hierarchical multiplexer may be able to switch between multiple louver sensor inputs, directing them to a different output than the blower RPM output, while still capturing blower RPM data at the rate required for proper detection (perhaps by outputting RPM sensor data for a longer period of time). Alternatively, the louver inputs may be time-multiplexed with the blower RPM data onto a single output and demultiplexed by a data collector configured to determine when blower RPM data is being output and when louver position data is being output.

In an embodiment, a system for data collection in an industrial environment, which may include a hierarchical multiplexer for routing sensor outputs to a signal path, can be used with pipeline-related compressors (e.g., reciprocating) in oil and gas pipeline applications. A typical use of reciprocating compressors for pipeline applications is the production of compressed air for pipeline testing. The system for data collection in an industrial environment can apply a hierarchical multiplexer while collecting data from pipeline test-based reciprocating compressors. Data from sensors located along a portion of the pipeline being tested may be input to the bottom stage of the hierarchical multiplexer because they are sampled periodically before and during the test. However, sensors that detect compressor operation, such as reciprocating links and motors, may have a lower sampling rate than compressor components that operate at higher frequencies. Sensors that provide data at frequencies that can reproduce detected movement may be input to higher stages of the hierarchical multiplexer. Time multiplexing between pipeline sensors may enable coverage of a large number of sensors while capturing events such as seal leaks. However, time multiplexing between reciprocating link sensors may require an output signal bandwidth that may exceed the bandwidth available for routing data from the multiplexer to a data collector. Therefore, in embodiments, multiple pipeline sensors may be time-multiplexed onto a single multiplexer output, with compressor sensors that detect rapidly moving parts, such as compressor motors, being routed to a separate output of the multiplexer.

Referring to FIG. 39, a system for data collection in an industrial environment is depicted that uses a hierarchical multiplexer to route sensor signals to a data collector. Outputs from multiple sensors, such as sensors monitoring conditions that change at a relatively low frequency (e.g., fan louver position sensors), may be input to the lowest hierarchical stage 8000 of a hierarchical multiplexer 8002, routed to successively higher stages in the multiplexer, and ultimately output from the multiplexer as a time-multiplexed signal, possibly including time-specific samples of each of the multiple low-frequency sensors. Outputs from a second plurality of sensors, such as sensors monitoring motor operation that may operate at 1000 RPM or more, may be input to a higher hierarchical stage 8004 of the hierarchical multiplexer and routed to an output that supports the required bandwidth.

An exemplary system for data collection in an industrial environment includes a controller that controls data collection resources in the industrial environment and a hierarchical multiplexer that facilitates continuous multiplexing of multiple input data channels according to a configurable hierarchy, where the hierarchy is automatically configured by the controller based on operating parameters of machines in the industrial environment. In certain further embodiments, the exemplary system includes: a system in which the operating parameters of the machines are identified in a data collection template; a system in which the hierarchy is automatically configured in response to smart band data collection activation; an analog-to-digital converter disposed between a source of the input data channels and the hierarchical multiplexer; and/or a system in which the operating parameters of the machines constitute at least one trigger condition for the data channels. Another example system for data collection in an industrial environment includes a plurality of sensors and a multiplexer module that receives sensor outputs from a first portion of the sensors at similar output rates into separate inputs of a first hierarchical multiplexer and provides at least one multiplexed output of the subset of inputs to a second hierarchical multiplexer, where the second hierarchical multiplexer receives sensor outputs from a second portion of the sensors and provides at least one multiplexed output of the subset of inputs. In certain further embodiments, exemplary systems include those in which the second portion of the sensors outputs data at a rate higher than the output rate of the first portion of the sensors, those in which the first and second portions of the sensors output data at different rates, those in which the output of the first hierarchical multiplexer is a time-multiplexed combination of a portion of its inputs, those in which the second multiplexer receives sensor signals at an output rate similar to the output rate of the first multiplexer, and/or those in which the first multiplexer generates a time-based multiplexing of a portion of its inputs.

An exemplary system for data collection in an industrial environment includes multiple sensors for sensing machine conditions in the environment, a hierarchical multiplexer, multiple analog-to-digital converters, a controller, local storage, and an external interface, the system including using the controller to access a data collection template that defines parameters for collecting data from a subset of the sensors. The system also includes configuring the hierarchical multiplexer, the ADC, and the local storage to facilitate data collection based on the defined parameters, and performing data collection with the configured elements, including storing a set of data collected from the subset of sensors in the local storage. In certain further embodiments, the exemplary system includes: an ADC that converts analog sensor data into a digital format compatible with the hierarchical multiplexer; a processor that monitors at least one signal generated by the sensor for a trigger condition and, upon detection of the trigger condition, responds by communicating an alert via the external interface and/or collecting data according to a template corresponding to the trigger condition; and a hierarchical multiplexer that serially multiplexes data received from the sensor according to a configurable hierarchy, the hierarchy being automatically set by the controller based on operating parameters of the machine in the industrial environment. wherein the operating parameters of the machine are identified in a data collection template and the hierarchy is automatically configured in response to data collection activation of the smart band, the system further including an ADC disposed between a source of the input data channels and the hierarchical multiplexer, the operating parameters of the machine including at least one trigger condition of the data channels, the hierarchical multiplexer sequentially multiplexing data received from the plurality of sensors according to a configurable hierarchy, and/or the hierarchy being automatically configured by the controller based on detected parameters of the industrial environment. A non-limiting example system is configured for monitoring a mining explosives system and includes a controller for controlling data collection resources associated with the explosives system and a hierarchical multiplexer that facilitates sequential multiplexing of multiple input data channels according to a configurable hierarchy, the hierarchy being automatically configured by the controller based on the configuration of the explosives system. Without limitation, an exemplary system configured for monitoring a refinery blower in an oil and gas pipeline application includes a controller for controlling data collection resources associated with the refinery blower and a hierarchical multiplexer that facilitates continuous multiplexing of multiple input data channels according to a configurable hierarchy, the hierarchy being automatically configured by the controller based on the configuration of the refinery blower. Without limitation, an exemplary system configured for monitoring a reciprocating compressor in an oil and gas pipeline application includes a controller for controlling data collection resources associated with the reciprocating compressor and a hierarchical multiplexer that facilitates continuous multiplexing of multiple input data channels according to a configurable hierarchy, the hierarchy being automatically configured by the controller based on the configuration of the reciprocating compressor.

In an embodiment, a system for data collection in an industrial environment may include an ultrasonic sensor positioned to capture ultrasonic conditions of elements within the environment. The system may be configured to collect data representing the captured ultrasonic conditions in computer memory, upon which a processor may execute an ultrasonic analysis algorithm. In an embodiment, the sensed element may be a moving element, a rotating element, a structural element, or the like. In an embodiment, the data may be streamed to computer memory. In an embodiment, the data may be streamed continuously. In an embodiment, the data may be streamed for a duration, such as an ultrasonic condition sampling period. In an embodiment, the system may include a data routing infrastructure that facilitates routing the streaming data from the ultrasonic sensor to multiple destinations, including local and remote destinations. The routing infrastructure may include a hierarchical multiplexer adapted to route the streaming data and data from at least one other sensor to a destination.

In embodiments, ultrasonic monitoring in industrial environments may be performed by a system for data collection as described herein on rotating elements (e.g., motor shafts, etc.), bearings, joints, couplings, housings, load-bearing elements, etc. The ultrasonic data may be used for pattern recognition, condition determination, time series analysis, etc., any of which may be performed by computing resources in the industrial environment, which may include local computing resources (e.g., resources located within the environment and/or within machines within the environment) and remote computing resources (e.g., cloud-based computing resources, etc.).

In embodiments, ultrasonic monitoring in an industrial environment by a data collection system may be initiated in response to a trigger (e.g., a signal from a motor indicating that the motor is running), a time scale (e.g., time since the most recent monitoring activity, time of day, time relative to a trigger, time until a future event such as a machine shutdown, etc.), or an external event (e.g., a lightning strike, etc.). Ultrasonic monitoring may be initiated in response to the performance of a smart band data collection activity. Ultrasonic monitoring may be initiated in response to the application of a data collection template in the industrial environment. The data collection template may be configured based on an analysis of previous vibration faults applicable to the monitored element, machine, environment, etc. Because continuous monitoring of ultrasonic data may require extended use of data routing resources in an industrial environment, a data collection template for continuous ultrasonic monitoring may be configured with data routing and resource utilization configuration information that a controller of the data collection system can use to configure resources to accommodate continuous ultrasonic monitoring. In one example, a data multiplexer may be configured to allocate a portion of its output to ultrasonic data for a time period specified in the template.

In embodiments, a system for data collection in an industrial environment may perform continuous ultrasonic monitoring. The system may also include processing of the ultrasonic data by a local processor located near the vibration monitoring sensor or device(s). Depending on the computing power of the local processor, functions such as peak detection may be performed. A programmable logic component may provide sufficient computing power to perform peak detection. The processing of the ultrasonic data (local or remote) may provide feedback to a controller associated with the monitored element. The feedback may be used in a control loop to adjust operating conditions, such as rotational speed, to reduce or at least mitigate potential negative effects indicated by the ultrasonic data analysis.

In embodiments, a system for data collection in an industrial environment may perform ultrasonic monitoring, particularly continuous ultrasonic monitoring. The ultrasonic monitoring data may be combined with a multi-dimensional model of the element or machine being monitored to generate a visualization of the ultrasonic data. In embodiments, an image, set of images, video, etc. may be generated that is temporally correlated with the sensed ultrasonic data. In embodiments, image recognition and/or analysis may be applied to the ultrasonic visualization to further facilitate determining the severity of conditions detected by the ultrasonic monitoring. Image analysis algorithms may be trained to detect normal and out-of-range conditions. Data from load sensors may be combined with ultrasonic data to facilitate testing of materials and systems.

In an embodiment, a system for data collection in an industrial environment may perform ultrasonic monitoring of a pipeline in an oil and gas pipeline application. The flow of oil through a pipeline can produce vibrations and other mechanical effects that can contribute to structural changes in the pipeline's liners, supports, flow boosters, regulators, diverters, and the like. Continuous ultrasonic monitoring of key sections of the pipeline can provide early detection of material changes, such as ruptured joints, that could lead to failure. A system for data collection in an industrial environment may be configured with ultrasonic sensing devices that can be connected via signal data routing resources, such as crosspoint switches and multiplexers, to data collection and analysis nodes where collected ultrasonic data can be collected and analyzed. In an embodiment, the data collection system may include a controller that references a data collection plan or template containing information to facilitate configuration of the system's data sampling, routing, and collection resources to accommodate the collection of ultrasonic sample data from multiple elements along the pipeline. The template may indicate a sequence for collecting ultrasonic data from multiple ultrasonic sensors, and the controller may configure the multiplexer to route ultrasonic sensor data from the specified ultrasonic sensors to a destination, such as a data storage controller or analysis processor, for a duration specified in the template. The controller may detect the sequence of collections in the templates or the sequence of accessed templates, and in response to each template in the detected sequence, adjust a multiplexer or the like to route the sensor data specified in each template to the collector.

In an embodiment, a system for data collection in an industrial environment may perform ultrasonic monitoring of a compressor in a power generation application. The compressor includes several critical rotating elements (e.g., shaft, motor, etc.), rotating support elements (e.g., bearings, couplings, etc.), etc. A data collection system configured to facilitate sensing, routing, collection, and analysis of ultrasonic data in a power generation application may receive ultrasonic sensor data from multiple ultrasonic sensors. Based on a configuration template, such as a template for collecting continuous ultrasonic data from one or more ultrasonic sensor devices, a controller may configure resources of the data collection system to facilitate delivery of the ultrasonic data from at least one sensor(s) via one or more signal data lines to a locally or remotely accessible data collector. In an embodiment, the template may indicate continuous acquisition of ultrasonic data from the main shaft for one minute, followed by acquisition of ultrasonic data from the secondary shaft for another minute, followed by acquisition of ultrasonic data from the compressor housing. The controller can configure a multiplexer to receive the ultrasonic data from each of these sensors and route the data from each sensor in sequence by configuring a control set to first direct input from the spindle ultrasonic sensor through the multiplexer until a time or other measure of data to be transferred is reached. The controller may then switch the multiplexer to route additional ultrasonic data needed to satisfy the second template requirements. The controller may continue to adjust data acquisition system resources along the way until all ultrasonic monitoring data acquisition templates are satisfied.

In an embodiment, a system for data collection in an industrial environment may perform ultrasonic monitoring of wind turbine gearboxes in wind energy generation applications. Wind turbine gearboxes can experience high levels of resistance during operation, due in part to the variable nature of wind, which can lead to premature failure of moving components such as gear planes, hydraulic fluid pumps, and regulators. A system for data collection in an industrial environment may be configured with ultrasonic sensors to capture information that may lead to early detection of potential failure modes in these high-strain elements. To effectively acquire ultrasonic data from multiple different ultrasonic sensors at sufficient range to facilitate the generation of a practical ultrasonic image assessment, the system may be specifically configured to deliver sufficient data at a relatively high rate from one or more of the sensors. A routing channel(s) may be dedicated to forwarding ultrasonic sensing data for a period of time, as may be specified in an ultrasonic data collection plan or template. To accomplish this, a controller, such as a programmable logic component, may configure a crosspoint switch and portions of the data collectors to distribute ultrasonic data from a first set of ultrasonic sensors (e.g., those sensing hydraulic fluid flow control elements) to multiple data collectors. Another portion of the crosspoint switch may be configured to route additional sensor data useful for evaluating the ultrasonic data (e.g., motor on/off status, sensed component thermal status, etc.) on other data channels to data collectors that can combine and analyze the data. The controller may reconfigure the data routing resources to allow collection of ultrasonic data from other elements based on corresponding data collection templates.

With reference to FIG. 40, a system for data collection in an industrial environment may include one or more ultrasonic sensors 8050 that may be connected to a data collection and routing system 8052 that may be configured by the controller 8054 based on an ultrasonic sensor-specific data collection template 8056 that may be provided to the controller 8054 by an ultrasonic data analysis facility 8058. The controller 8054 may configure the resources of the data collection system 8052 and continuously monitor the data collection flow based on the data collection requirements in the template 8056.

An exemplary system for data collection in an industrial environment includes an ultrasonic sensor positioned to capture ultrasonic conditions of elements in the environment; a controller that configures data routing resources of the data collection system to route ultrasonic data captured by the ultrasonic sensor to a destination specified by an ultrasonic monitoring data collection template; and a processor that executes an ultrasonic analysis algorithm on the data after it arrives at the destination. In certain further embodiments, the exemplary system includes: a template that defines a time interval for capturing continuous ultrasonic data from the ultrasonic sensor; a data routing infrastructure that facilitates routing streaming data from the ultrasonic sensor to multiple destinations, including local and remote destinations; a hierarchical multiplexer adapted to route the streaming data and data from at least one other sensor to the destination; elements in the environment that include rotating elements, bearings, fittings, couplings, housings, and/or load-bearing parts; a template that defines activation conditions for the continuous ultrasonic monitoring; and/or a trigger, a smart band, a template, an external event, and/or a regulatory compliance configuration.

An exemplary system for data collection in an industrial environment includes an ultrasonic sensor positioned to capture ultrasonic conditions of elements of industrial machinery within the environment; a controller that configures data routing resources of the data collection system to route ultrasonic data being captured by the ultrasonic sensor to a destination specified by an ultrasonic monitoring data collection template; and a processor that executes an ultrasonic analysis algorithm on the data after it arrives at the destination. In certain embodiments, the exemplary system further includes: where the template defines a time interval for capturing consecutive ultrasonic data from the ultrasonic sensor; where the system further includes a data routing infrastructure that facilitates routing data from the ultrasonic sensor to multiple destinations, including local and remote destinations; where the data routing infrastructure includes a hierarchical multiplexer adapted to route the ultrasonic data and data from at least one other sensor to the destination; where the elements of industrial machinery include rotating elements, bearings, joints, couplings, housings, and/or load-bearing components; and where the template activates the continuous ultrasonic monitoring, and/or where the conditions for activation include a trigger, a smart band, a template, an external event, and/or a regulatory compliance setting.

An exemplary method for continuous ultrasonic monitoring in an industrial environment includes positioning an ultrasonic monitoring device within ultrasonic monitoring range of at least one moving part of an industrial machine in the industrial environment. The ultrasonic monitoring device generates a stream of ultrasonic monitoring data and configures a data routing infrastructure that routes the stream of ultrasonic monitoring data to a destination based on an ultrasonic monitoring data collection template. The infrastructure facilitates routing data from multiple sensors via analog crosspoint switches and/or hierarchical multiplexers to multiple destinations, routing the ultrasonic monitoring device data to the destination via the routing infrastructure, processing the stored data with an ultrasonic data analysis algorithm that provides an ultrasonic analysis of at least one of a motor shaft, a bearing, a joint, a coupling, a housing, and a load-bearing component, and/or saving the data in memory accessible by a destination computer. Certain further embodiments of the exemplary method include: where the data collection template defines a time interval for continuously acquiring ultrasonic data from the ultrasonic monitoring device; where configuring the data routing infrastructure includes configuring a hierarchical multiplexer to route the ultrasonic data and data from at least one other sensor to a destination; where the ultrasonic monitoring is performed on at least one element of industrial machinery including a rotating element, a bearing, a joint, a coupling, a housing, and/or a load-bearing component; where the template defines activation conditions for the continuous ultrasonic monitoring, the activation conditions including a trigger, a smart band, a template, an external event, and/or a regulatory compliance configuration; where the ultrasonic data analysis algorithm performs pattern recognition; and/or where the routing of the ultrasonic monitoring device data is responsive to detection of a condition in the industrial environment associated with at least one moving part.

Without limitation, an exemplary system for monitoring an oil or gas pipeline includes a processor that runs an ultrasonic analysis algorithm on pipeline data after arrival at a destination; an exemplary system for monitoring a power generation compressor includes a processor that runs an ultrasonic analysis algorithm on power generation compressor data after arrival at a destination; and an exemplary system for monitoring a wind turbine gearbox includes a processor that runs an ultrasonic analysis algorithm on gearbox data after arrival at a destination.

Industrial components such as pumps, compressors, air conditioners, mixers, agitators, motors, and engines can play a critical role in the operation of equipment in a variety of environments, including as part of manufacturing equipment in industrial settings such as factories, gas processing systems, mining, and automotive systems.

Pumps include a variety of positive displacement, velocity, and impulse pumps. Velocity or centrifugal pumps typically consist of an impeller with curved blades that, when immersed in a fluid such as water or gas, rotates the fluid or gas in the same direction as the impeller. As the fluid or gas rotates, centrifugal force moves it to the outer diameter of the pump, e.g., the pump housing, where it can be collected and further processed. As the fluid or gas is removed from the outer periphery, the pressure at the pump's input orifice decreases, and new fluid or gas may be drawn into the pump.

Positive displacement pumps may include reciprocating pumps, sinusoidal pumps, gear pumps, or screw pumps. For example, a reciprocating pump typically consists of a piston that alternately generates suction by opening an inlet valve to draw liquid or gas into a cylinder, and pressure by closing the inlet valve to force any liquid or gas out of the cylinder through an outlet valve. In this way, pressurized liquid or gas is cyclically introduced into a downstream system.

Some motor vehicles, such as cars and trucks, use water-cooling systems to prevent their engines from overheating. Some vehicles use a centrifugal water pump, driven by a belt associated with the vehicle's driveshaft, to force a mixture of water and coolant through the engine to maintain an acceptable engine temperature. Engine overheating can cause significant damage, but accessing a vehicle's onboard water pump can be difficult or costly.

In an embodiment, a vehicle water pump may include multiple sensors for measuring attributes related to the water pump, such as bearing and pump housing temperature, vibration of a drive shaft associated with the pump, and fluid leakage. These sensors may be directly connected to a monitoring device or connected through an intermediary device using wired and wireless connection technologies. The monitoring device may access the sensed values corresponding to the sensors. The sensed values may correspond directly to the sensor output or a processed version of the data output, such as a digitized or sampled version of the sensor output, and/or a virtual sensor or modeled value correlated from other sensed values. The monitoring device may access and process the sensed values using methods discussed elsewhere herein to assess the health of the water pump and its various components that are prone to wear or failure (e.g., bearings or bearing sets, drive shaft, motor, etc.). The monitoring device may process the sensed values to identify twist in the pump's drive shaft. The identified twist may be evaluated against an expected twist based on the water pump's particular geometry and installation on the vehicle. Unexpected twist may place undue stress on the drive shaft and indicate a deteriorating pump health condition. The monitoring device may process the readings to identify unexpected vibrations in the shaft and unexpected temperature readings or temperature changes in the bearings or the housing proximate to the bearings. In some embodiments, the sensors may include multiple temperature sensors positioned around the water pump to identify hot spots between the bearings or throughout the pump housing that may indicate a possible bearing failure. The monitoring device may process the readings associated with the water sensors to identify liquid leaks near the pump that may indicate a seal failure. These readings can be analyzed jointly to determine the health of the pump.

In an illustrative example, measurements related to a vehicle's water pump may indicate a sudden increase in vibration at a frequency higher than the pump's operating revolutions, and a corresponding localized increase in temperature associated with a particular phase of the pump cycle, which may indicate a localized bearing failure.

Production lines may also include one or more pumps for moving a variety of materials, including acidic or corrosive materials, flammable materials, minerals, fluids containing particulates of various sizes, high viscosity fluids, variable viscosity fluids, or dense fluids. Pumps in a production line may be specially designed to meet the needs of the production line, such as pump configurations for handling various material types and the torque required to move fluids at desired speeds or pressures. Because these production lines are continuous process lines, it may be desirable to perform proactive maintenance rather than waiting for parts to fail. Fluctuations in pump speed or pressure can have a detrimental effect on the end product, and the ability to identify problems in the end product may delay actual part degradation for an unacceptably long period of time.

In embodiments, an industrial pump may include multiple sensors for measuring attributes associated with the pump, such as bearing and pump housing temperature, drive shaft vibration associated with the pump, input or output line vibration, pressure, flow rate, fluid particle counts, and pump housing vibration. These sensors may be connected to a monitoring device directly or through an intermediate device using wired and wireless connection technologies. The monitoring device may access the detected values corresponding to the sensors, which directly correspond to the sensor output of a processed version of the data output, such as a digitized or sampled version of the sensor output. The monitoring device may access and process the detected values using methods described elsewhere herein to assess the overall pump health, assess the health of pump components, predict potential downline issues resulting from atypical pump performance, or predict changes in the fluid being pumped. The monitoring device may process the detected values to identify twist in the pump's drive shaft. The identified twist is evaluated against an expected twist based on the pump's particular geometry and how it is attached to the device in relation to other components on the assembly line. Unexpected twisting can overstress the drive shaft and indicate a deteriorating pump health condition. Vibrations in the inlet and outlet piping can also be evaluated for unexpected or resonant vibrations, allowing process controls to avoid certain pump frequencies. Changes in vibration can also be caused by changes in fluid composition or density, amplifying or attenuating vibrations at certain frequencies. The monitoring system can process the readings to identify unexpected shaft vibrations, unexpected temperature values, or temperature changes in the bearings or the housing adjacent to the bearings. In some embodiments, the sensor includes multiple temperature sensors positioned around the pump, allowing for the identification of hot spots between bearings or throughout the pump housing that could indicate a possible bearing failure. For some pumps, if the fluid is corrosive or contains a large amount of particulates, cumulative exposure to the fluid can cause damage to internal pump components in contact with the fluid. This can be reflected in unexpected fluctuations in the output pressure. Additionally, if the gears in a gear pump begin to corrode and are no longer able to expel all of the trapped fluid, this can result in increased pump speed, fluid cavitation, and unexpected vibrations in the output pipe.

A compressor increases the pressure of a gas by decreasing the volume it occupies or by increasing the amount of gas in a confined volume. A positive-displacement compressor may use the motion of a piston or rotary screw to move the gas into a pressurized holding chamber. Other types of compressors use centrifugal force to accelerate the gas, converting kinetic energy into pressure. Compressors may be used to compress various gases used on assembly lines. The compressed air can power pneumatic equipment on assembly lines. In the oil and gas industry, flash gas compressors may be used to compress gases so that they remain as hydrocarbon liquids as they enter a lower-pressure environment. Compressors can be used to restore pressure in gas and oil pipelines, to blend target fluids, and/or to transfer or transport target fluids. Compressors may be used to enable underground storage of natural gas.

Similar to pumps, compressors can be equipped with multiple sensors to measure compressor-related attributes, such as bearing and compressor housing temperature, vibration of compressor-related drive shafts, transmissions, gearboxes, etc., vessel pressure, and flow rate. These sensors can be connected to a monitoring device directly or through an intermediary device using a combination of wired and wireless connection technologies. The monitoring device can access the sensed values corresponding to the sensors, which correspond directly to the sensor outputs in a processed version of the data output, such as a digitized or sampled version of the sensor output. The monitoring device can access and process the sensed values using methods described elsewhere herein to assess the overall compressor health, assess the health of compressor components, and/or predict potential downline problems resulting from atypical compressor performance. The monitoring device can process the sensed values to identify twist on the compressor drive shaft. The identified twist can then be evaluated against expected twist based on the specific geometry of the compressor and its installation relative to other components and pieces of equipment. Unexpected twist can be a sign of excessive stress on the drive shaft and a deteriorating compressor health condition. Vibrations in the suction and discharge lines can also be evaluated for unexpected or resonant vibrations and used to drive process control to avoid specific compressor frequencies. The monitoring device may process the detected values to identify unexpected vibrations in the shaft, unexpected temperature values or temperature changes in the bearings or the housing proximate to the bearings. In some embodiments, the sensors may include multiple temperature sensors positioned around the compressor to identify hot spots between the bearings or across the compressor housing that may indicate a potential bearing failure. In some embodiments, the sensors may monitor the pressure in a vessel storing compressed gas. Changes in the pressure or rate of pressure change may indicate a problem with the compressor.

Agitators and mixers are used in a variety of industrial settings. Agitators may be used to mix different components, such as liquids, solids, and gases. Agitators may be used to promote more homogeneous mixing of constituent materials. Agitators may be used to accelerate chemical reactions by increasing the exposure of different components and adding energy to a system. Agitators can be used to promote heat transfer and facilitate uniform heating or cooling of materials.

Mixers and agitators are used in a variety of industries, including chemical production, food production, and pharmaceutical production. Examples include paint and coating mixers, adhesive and sealant mixers, oil and gas mixers, water treatment mixers, and wastewater treatment mixers.

Agitators can be devices that rotate or agitate the entire tank or vessel in which the materials to be mixed are placed, similar to a concrete mixer. Effective agitation can be affected by the number and shape of baffles inside the tank. Agitation by rotation of the tank or vessel can be affected by the axis of rotation relative to the shape of the tank, the direction of rotation, and external forces such as gravity acting on the materials in the tank. Factors that affect the effectiveness of agitating a tank or vessel in agitating the materials include the axis of rotation and the amplitude and frequency of vibration along different axes. These factors can be selected based on the type of materials selected, their relative viscosities, specific gravities, particle counts, expected shear thinning or shear thickening of the constituent materials or mixtures, the flow rates of materials entering or exiting the vessel or tank, and the direction and location of the flow of materials entering or exiting the vessel.

Agitators, large tank mixers, portable tank mixers, tote tank mixers, drum mixers, and mounted mixers (of various mounting types) may include a propeller or other mechanical device, such as a blade, vane, or stator, inserted into a tank of materials to be mixed, rotating the propeller or otherwise moving the mechanical device. These include vane-type impellers, fixed-pitch blade impellers, variable-pitch blade impellers, anti-ragging impellers, fixed-radial blade impellers, marine-type propellers, folding vane-type impellers, folding pitch-blade impellers, folding radial blade impellers, and variable-pitch impellers. Agitators may be mounted so that mechanical agitation is centered in the tank. Agitators may also be mounted at an angle within the tank or offset vertically or horizontally from the center of the vessel. Agitators may enter the tank from the top, bottom, or side of the tank. A single tank may have multiple agitators to achieve uniform mixing throughout a chemical tank or vessel.

The agitator may include strategic flow or introduction of constituent materials into the vessel, including inlet location and direction, inlet velocity, inlet pressure, material viscosity, material specific gravity, etc.

Successful mixing and agitation of materials may require a combination of techniques, such as one or more propellers in a baffled tank where ingredients are introduced at different locations and at different rates.

In embodiments, an industrial mixer or agitator may include multiple sensors for measuring attributes of the industrial mixer, such as bearing or tank housing temperature, drive shaft vibration associated with a propeller or other mechanical device, such as blades, vanes, or stators, input or output line vibration, pressure, flow rate, fluid particulate control, tank housing vibration, etc. These sensors may be connected to a monitoring device directly or through an intermediary device using a combination of wired and wireless connection technologies. The monitoring device may have access to the detected values corresponding to the sensors, where the detected values correspond directly to the sensor output, such as a processed version of the data, a digitized or sampled version of the sensor output, an fusion of data from multiple sensors, etc. The monitoring device may access and process the detected values using methods discussed elsewhere herein to assess the overall health of the agitator or mixer, assess the health of agitator or mixer components, and predict potential downline issues resulting from atypical performance or changes in the composition of the material being agitated. For example, the monitoring device may process the detected values to identify twist in the agitator impeller drive shaft. The identified twist can then be evaluated against expected twist based on the agitator's particular geometry and its installation relative to other components and/or parts of the equipment. Unexpected twist can overstress the drive shaft and signal a deteriorating agitator health condition. Vibrations in the inlet and outlet pipes may be monitored for unexpected or resonant vibrations, which may be used to drive process control to avoid specific agitation frequencies. Inlet and outlet pipes may also be monitored for unexpected flow rates, unexpected particulate content, etc. Changes in vibration may be due to changes in fluid composition or density, which amplify or attenuate vibrations at specific frequencies. Monitoring devices can be equipped with sensors that collect readings that can be used to identify unexpected shaft vibrations or unexpected temperature values or changes in bearings or housings adjacent to the bearings. In some agitators, if the fluid being agitated is corrosive or contains a large amount of particulates, internal agitator components in contact with the material (e.g., baffles, propellers, blades, etc.) may suffer damage from cumulative exposure to the material.

HVAC and air conditioning systems, for example, often use a combination of compressors and fans to cool and circulate air in industrial environments. Similar to the compressor and agitator discussion, these systems may contain numerous rotating parts whose failure or poor performance can adversely affect the work environment and reduce product quality. A monitoring device can be used to monitor sensors measuring various aspects of one or more rotating parts, ventilation systems, environmental conditions, and the like. Components of an HV AC/air conditioning system may include fan motors, drive shafts, bearings, compressors, and the like. The monitoring device may access and process the sensed values corresponding to the sensor outputs according to methods described elsewhere herein to assess the overall health of air conditioning units, HVAC systems, and the like, and components of these systems, identify operating conditions, predict potential problems resulting from atypical performance, and the like. Possible assessment techniques include bearing analysis, drive shaft, rotor, and stator torsion analysis, and peak value detection. The monitoring device may process the sensed values to identify issues such as drive shaft twist, potential bearing failure, and the like.

Assembly line conveyors may consist of numerous moving and rotating parts as part of a system that moves materials through a manufacturing process. These assembly line conveyors may operate at a wide range of speeds. They may also vibrate at various frequencies as they transport material horizontally, facilitating screening, grading, lane packing, spraying, dewatering, and feeding product to the next in-line process.

The conveying system may include an engine or motor, one or more drive shafts that rotate rollers or bearings along which the conveyor belt moves. A vibrating conveyor may include a spring and multiple vibrators that vibrate the conveyor sinusoidally to propel it forward.

In embodiments, the conveyor and vibrating conveyor may include multiple sensors for measuring attributes associated with the conveyor, such as bearing temperature, drive shaft vibration, vibration of rollers on which the conveyor moves, and speed and velocity associated with the conveyor. The monitoring device may access and process the detected values using methods discussed elsewhere herein to assess the overall health of the conveyor as well as its components, predict potential problems resulting from atypical performance, and the like. Techniques for assessing the conveyor may include bearing analysis, torsion analysis, phase detection/phase-locked loops to align detected values from different parts of the conveyor, frequency conversion and frequency analysis, peak detection, and the like. The monitoring device may process the detected values to identify twisted drive shafts, potential bearing failures, uneven conveyance, and the like.

In one example, a paper mill's conveying system may include a mesh onto which paper slurry is coated. The mesh transports the slurry as the liquid evaporates and the paper dries. The paper is then wound onto a core, resulting in a roll as large as 3 meters in diameter. Paper machine conveying speeds vary from traditional equipment at 14 to 48 meters per minute to newer equipment at speeds approaching 2,000 meters per minute. On slower machines, the paper is wound onto the roll at 14 meters per minute, implying that the take-up roll rotates at a rate of 2 to 3 revolutions per minute toward the end of the roll, which is approximately 3 meters in diameter. Vibrations in the web transport and twisting of the take-up roll can cause paper damage, skewed paper on the web, and skewed rolls, resulting in equipment downtime, poor product quality, and unusable equipment. Furthermore, equipment failures can result in costly machine shutdowns and lost product. Therefore, the ability to predict problems and provide preventative maintenance is valuable.

Monitoring a truck's engine and steering system is important to ensure timely maintenance and avoid unexpected breakdowns. The health of the combustion chamber, rotating crankshaft, bearings, etc. can be monitored using a monitoring device configured to interpret readings received from multiple sensors measuring various characteristics related to engine components, including temperature, torsion, vibration, etc. As described above, the monitoring device may process the readings to identify engine bearing health, crankshaft/driveshaft torsional vibration, unexpected combustion chamber vibration, overheating of different components, etc. Processing can be performed locally or collaboratively across multiple vehicles. The monitoring device may process readings related to the engine, combustion chamber, etc. Sensors may monitor temperature, vibration, torsion, acoustics, etc. to identify problems. The monitoring device or system may use techniques such as peak detection, bearing analysis, torsional analysis, phase detection, PLL, and bandpass filtering to identify potential problems in the steering system, and bearing and torsional analysis can be used to identify potential problems in the engine's rotating components. Identifying such potential problems can be used to schedule timely maintenance, mitigate pre-maintenance actions, and influence future part designs.

Drilling machines and screwdrivers in the oil and gas industry can be subjected to significant stress. Because these machines are often located in remote locations, unexpected failures can result in extended downtime due to the lead time associated with retrieving replacement parts. Monitoring devices configured to interpret readings received from multiple sensors measuring various characteristics related to the drilling machine or driver, such as temperature, torsion, vibration, rotational speed, vertical speed, acceleration, and image sensors, can be used to monitor the health of drilling machines and drivers and associated rotating crankshafts, bearings, etc. As described above, the monitoring devices may process the readings to identify equipment health, crankshaft/driveshaft torsional vibration, unexpected component vibration, overheating of different components, etc. Processing can be performed locally or collaboratively across multiple machines. The monitoring devices may collaboratively process readings, equipment maintenance records, product records, historical data, etc. to identify correlations between readings and current and future conditions. Monitoring devices can also monitor the expected lifespan of parts and equipment. Sensors may monitor temperature, vibration, torsion, acoustics, etc. to identify issues such as unexpected twisting of the drill shaft, gear slippage, or overheating. The monitoring device or system can use techniques such as peak detection, bearing analysis, torsion analysis, phase detection, PLL, and bandpass filtering to identify potential problems. This identification of potential issues can be used to schedule timely maintenance, order new or replacement parts, reduce uptime before maintenance, and influence future part designs.

Similarly, it may be desirable to monitor the health of gearboxes operating in oil and gas fields. Monitoring equipment may be configured to interpret readings received from multiple sensors measuring various characteristics associated with the gearbox, such as temperature and vibration. The monitoring equipment can process the readings to determine the health and expected lifespan of the gears and gearbox. Processing may occur locally, or data may be collected and analyzed collaboratively across multiple gearboxes. The monitoring equipment may also collaboratively process readings, equipment maintenance records, historical data from product records, etc., to determine correlations between readings, the current and future condition of the gearbox, and the expected lifespan of the gearbox and associated components. Monitoring equipment and systems may use techniques such as peak detection, bearing analysis, torsional analysis, phase detection, PLL, and bandpass filtering to identify potential problems. Identification of such potential problems can be used to schedule timely maintenance, order new or replacement parts, reduce availability before maintenance, and influence future equipment design.

Refinery tanks in the oil and gas industry can be subject to significant stress due to chemical reactions occurring within them. Tank failures can result in the release of potentially toxic chemicals, so monitoring the condition of refinery tanks and associated components can be beneficial. By monitoring refinery tanks and collecting a variety of continuous data, it is possible to predict equipment wear, component wear, unexpected stress, and more. Predictions regarding equipment health, such as refinery tank condition, can be used to schedule timely maintenance, order new or replacement parts, reduce pre-maintenance availability, and influence future component design. Similar to the discussion above, refinery tanks can be monitored using monitoring equipment configured to interpret readings received from multiple sensors measuring various characteristics associated with the refinery tank, such as temperature, vibration, internal pressure, external pressure, and the presence of liquids or gases at seams or ports. The monitoring equipment may process the readings to identify equipment health, unexpected tank vibration, overheating of the tank, or uneven heating throughout the tank. Processing can be performed locally, or data can be collected and analyzed collaboratively across multiple tanks. The monitoring device may jointly process detected values, equipment maintenance records, historical product records, etc. to identify correlations between detected values, the current and future condition of the tank, the expected life of the tank and associated components, etc. The monitoring device or system may use techniques such as peak detection, bearing analysis, torsion analysis, phase detection, PLL, bandpass filtering, etc. to identify potential problems.

Similarly, it may be desirable to monitor the health of centrifuges operating in oil and gas refineries. A monitoring device may be configured to interpret readings received from multiple sensors measuring various characteristics associated with the centrifuge, such as temperature, vibration, and pressure. The monitoring device may process the readings to identify equipment health, unexpected centrifuge vibration, overheating, overall centrifuge pressure, and the like. Processing may be performed locally or may involve collecting and collaboratively analyzing data across multiple centrifuges. The monitoring device may also collaboratively process readings, historical data from equipment maintenance records, product records, and the like to identify correlations between readings, current and future centrifuge conditions, expected lifespans of centrifuges and associated components, and the like. The monitoring device or system may use techniques such as peak detection, bearing analysis, torsional analysis, phase detection, PLL, bandpass filtering, and the like to identify potential problems. Identification of such potential problems may be used to schedule timely maintenance, order new or replacement parts, reduce pre-maintenance operations, and influence future equipment design.

In embodiments, information regarding the health or other status of components of industrial equipment may be obtained by monitoring the condition of various components during a process. Monitoring may include monitoring the amplitude of sensor signals measuring hributes such as temperature, humidity, acceleration, and displacement. One embodiment of a data monitoring device 8100 is shown in FIG. 41 and may include multiple sensors 8106 communicatively coupled to a controller 8102. The controller 8102 includes a data acquisition circuit 8104, a data analysis circuit 8108, a MUX control circuit 8114, and a response circuit 8110. The data acquisition circuit 8104 may include a MUX 8112 whose input corresponds to a subset of the detected values. The MUX control circuit 8114 may be configured to logically control the MUX and adaptively schedule the correspondence between the MUX input and the detected values based on a subset of the detected values and/or commands from the response circuit 8110 and/or the output of the data analysis circuit 8104. The data analysis circuit 8108 may comprise one or more of a peak detection circuit, a phase difference circuit, a PLL circuit, a bandpass filter circuit, a frequency conversion circuit, a frequency analysis circuit, a torsion analysis circuit, a bearing analysis circuit, an overload detection circuit, a sensor fault detection circuit, a vibration resonance circuit for identifying undesirable interactions between machines or components, and a strain identification circuit for identifying undesirable strains such as operational deflection shapes, weight overloads, excessive forces, and stress and strain based effects. The data analysis circuit 8108 may output a component health status as a result of the analysis.

The data analysis circuit 8108 may determine the state, condition, or status of a component, part, subsystem, etc. of a machine, device, system, or equipment (collectively referred to herein as a component health status) based on the maximum value of the MUX output for a given input or the rate of change of the value of the MUX output for a given input. The data analysis circuit 8108 may determine the health status of the component based on the time integral of the MUX value for a given input. The data analysis circuit 8108 may determine the health status of the component based on the phase difference of the MUX output relative to the time of day or other sensors installed. The data analysis circuit 8108 may determine the health status of the component based on the relationship of the value, phase, phase difference, and rate of change of the MUX output to one or more input sensed values. The data analysis circuit 8108 may also determine the health status of the component based on the process stage, part specifications, or expected state of the component.

The multiplexer control circuitry 8114 may adapt the scheduling of the multiplexer logic control based on the component health state, the expected component health state, the type of component, the type of equipment being measured, the expected state of the equipment, and the stage of the process (different parameter/sensor values may be important at different stages of the process). The multiplexer control circuitry 8114 may adapt the scheduling of the multiplexer logic control based on a sequence selected by a user or a remote monitoring application, or based on a user request for a particular value. The multiplexer control circuitry 8114 may adapt the scheduling of the multiplexer logic control based on a storage profile or plan (e.g., based on the type and availability of storage elements and parameters, as described elsewhere in this disclosure and in documents incorporated by reference), network conditions or availability (also as described elsewhere in this disclosure and in documents incorporated by reference), or the value or cost of the component or equipment.

The plurality of sensors 8106 may be wired to ports of the data acquisition circuitry 8104. Alternatively, the plurality of sensors 8106 may be wirelessly connected to the data acquisition circuitry 8104. The data acquisition circuitry 8104 may have access to a sensed value corresponding to the output of at least one of the plurality of sensors 8106, where the sensor 8106 may acquire data regarding different operational aspects of the equipment or operating component.

The selection of multiple sensors 8106 for a data monitoring device 8100 designed for a particular component or piece of equipment may depend on various considerations, such as accessibility for installing new sensors, incorporation of sensors in the initial design, expected operating and fault conditions, desired resolution at various locations within the process or plant, and sensor reliability. The impact of failure, time response to failure (e.g., pre-failure warning time and abnormal modes), probability of failure, required sensitivity, and difficulty of detecting fault conditions may influence the extent to which a component or piece of equipment is monitored with more sensors or more sophisticated sensors are used in systems where unexpected or undetected failures can have costly or severe consequences.

Depending on the type of equipment, the component being measured, the environment in which the equipment operates, etc., the sensor 8106 may include one or more of the following: vibration sensors, thermometers, hygrometers, voltage and/or current sensors (for components and/or other sensors measuring components), accelerometers, speed detectors, optical or electromagnetic sensors (e.g., for temperature, composition, and/or spectral analysis, and/or determining the position or movement of an object), image sensors, structured light sensors, laser-based image sensors. Examples of sensors include, but are not limited to, image sensors, structured light sensors, laser image sensors, thermal imagers, acoustic wave sensors, displacement sensors, turbidity meters, viscometers, axial load sensors, radial load sensors, triaxial sensors, accelerometers, speedometers, tachometers, fluid pressure meters, and air flow meters. Examples of sensors include, but are not limited to, accelerometers, speedometers, tachometers, fluid pressure meters, air flow meters, horsepower meters, flow meters, fluid particle detectors, optical (laser) particle counters, ultrasonic sensors, acoustic sensors, heat flux sensors, galvanic sensors, magnetometers, and pH sensors, as well as any of the sensors described in this disclosure and references herein.

The sensor 8106 may provide a stream of data over time that has a phase component, such as that associated with acceleration or vibration, allowing for evaluation of phase or frequency analysis of different operational aspects of a portion or operating part of a device. The sensor 8106 may also provide a stream of data that does not have a traditional phase component, such as temperature, humidity, load, etc. The sensor 8106 may provide a continuous or near-continuous stream of data over time, periodic readings, event-driven readings, and/or readings according to a selected interval or schedule.

Sensor 8106 may monitor components such as bearings, bearing sets, motors, drive shafts, pistons, pumps, conveyors, vibrating conveyors, compressors, drills, etc., in vehicles, oil and gas equipment in the field, assembly line components, etc.

In an embodiment, as illustrated in FIG. 41, the sensor 8106 may be part of a data monitoring device 8100, referred to herein as a data collector, which may in some cases constitute a mobile or portable data collector. In an embodiment, as shown in FIGS. 42 and 43, one or more external sensors 8126, not explicitly part of the monitoring device 8120 but newly, previously attached to, or integrated into a device or component, may be randomly connected to or accessed by the monitoring device 8120. The monitoring device 8120 may include a controller 8122. The controller 8122 may include a data acquisition circuit 8104, a data analysis circuit 8108, a MUX control circuit 8114, and a response circuit 8110. The data acquisition circuit 8104 may include a MUX 8112 whose input corresponds to a subset of the detected values. The MUX control circuit 8114 may be configured to logically control the MUX and associate the MUX input with the detected values based on a subset of the multiple detected values and/or commands from the response circuit 8110 and/or the output of the data analysis circuit 8108. The data analysis circuit 8108 may be configured with one or more of a peak detection circuit, a phase difference circuit, a PLL circuit, a bandpass filter circuit, a frequency conversion circuit, a frequency analysis circuit, a torsion analysis circuit, a bearing analysis circuit, an overload detection circuit, a vibration resonance circuit for identifying undesirable interactions between machines or parts, a distortion identification circuit for identifying undesirable distortions such as deflection shapes during operation, stress and strain-based effects, etc.

The one or more external sensors 8126 may be directly connected to one or more input ports 8128 on the data acquisition circuit 8104 of the controller 8122, or may be accessed wirelessly by the data acquisition circuit 8104 via a reader, interrogator, or other wireless connection, such as over a short-range wireless protocol. In an embodiment, as shown in FIG. 43, the data acquisition circuit 8104 may further include a wireless communication circuit 8130. The data acquisition circuit 8104 may use the wireless communication circuit 8130 to wirelessly access the detected values corresponding to the one or more external sensors 8126, access them via another source, or some combination of these methods.

In an embodiment, as shown in FIG. 44, the controller 8134 may further include a data storage circuit 8136. The data storage circuit 8136 may be configured to store one or more of sensor specifications, component specifications, expected state information, detected values, multiplexer outputs, component models, etc. The data storage circuit 8136 may provide the specifications and expected state information to the data analysis circuit 8108.

In embodiments, the response circuit 8110 may initiate various actions based on the sensor status provided by the data analysis circuit 8108. The response circuit 8110 may adjust the sensor scaling value (e.g., from 100 mV/gram to 10 mV/gram). The response circuit 8110 may select an alternate sensor from multiple available sensors. The response circuit 8110 may acquire data from multiple sensors with different ranges. The response circuit 8110 may recommend an alternate sensor. The response circuit 8110 may issue an alarm or alert.

In embodiments, the response circuitry 8110 may cause the data acquisition circuitry 8104 to enable or disable processing of detected values corresponding to a particular sensor based on the component's condition. This may include switching to a sensor with a different response speed, sensitivity, range, etc., accessing a new sensor or sensor type, accessing data from multiple sensors, etc. The switching may be based on a model, a set of rules, etc. In embodiments, the switching is under the control of a machine learning system, where the switching is controlled based on one or more success metrics combined with input data over a series of trials, which may occur under the supervision of a human supervisor or under the control of an automated system. The switching may include switching from one input port to another input port (e.g., switching from one sensor to another). The switching may include changing the multiplexing of data, such as combining different streams under different conditions. The switching may include triggering the system to acquire additional data. For example, a mobile system (such as a robotic or drone system) may be moved to a location where different or additional data is available, e.g., an image sensor may be positioned for a different view, a sonar sensor may be positioned for a different collection direction, or a different sensor may be accessed, e.g., a collector may be moved to connect to sensors at locations in the environment via wired or wireless connections. This switching may be accomplished by instructing the multiplexer (MUX) control circuit 8114 to make changes.

In embodiments, the response circuitry 8110 may make recommendations for future replacement of a particular sensor with a sensor having a different response speed, sensitivity, range, etc. The response circuitry 8110 may also recommend design changes for future embodiments of components, pieces of equipment, operating conditions, processes, etc.

In embodiments, the response circuitry 8110 may recommend maintenance during a future process shutdown or may initiate a maintenance call, which may include replacing a sensor with the same or an alternative type of sensor having a different response speed, sensitivity, range, etc. In embodiments, the response circuitry 8110 may implement or recommend a process change, such as reducing the utilization of a component that is nearing a maintenance interval, operating informally, or has failed but is at least partially operational for its intended purpose, changing the operating speed of a component (e.g., placing it in a low-demand mode), initiating a remediation of the problem (e.g., signaling additional lubrication of a roller bearing set or signaling an alignment process for an out-of-balance system), etc.

In embodiments, the data analysis circuit 8108 and/or response circuit 8110 may periodically store data corresponding to particular sensed values and/or multiplexer outputs and/or MUX logical control in the data storage circuit 8136 to enable tracking of component performance over time. In embodiments, as described elsewhere herein, based on the sensor status, recently measured sensor data and associated operating conditions such as RPM, component load, temperature, pressure, vibration, or other sensor data of the type described throughout this disclosure in the data storage circuit 8136, enables backout of overloaded/failed sensor data. The signal evaluation circuit 8108 may store data at higher data rates to enable greater granularity in future processing, the ability to reprocess at different sampling rates, and/or diagnostics or post-processing of system information where operational data of interest has been flagged.

In embodiments, as shown in FIGS. 45, 46, 47, and 48, the data monitoring system 8138 may include at least one data monitoring device 8140. The at least one data monitoring device 8140 may include a sensor 8106 and a controller 8142 including a data acquisition circuit 8104, a data analysis circuit 8108, a data storage circuit 8136, and a communications circuit 8146 to enable transmission of data and analyses to a monitoring application 8150 on a remote server 8148. The signal evaluation circuit 8108 may include at least an overload detection circuit (e.g., see FIGS. 91 and 92) and/or a sensor fault detection circuit (e.g., see FIGS. 91 and 92). The signal evaluation circuit 8108 may periodically share data with the communications circuit 8146 for transmission to the remote server 8148 to enable tracking of component and equipment performance over time and under various conditions by the monitoring application 8150. Based on the state of the sensor, the signal evaluation circuit 8108 and/or the response circuit 8110 may share data with the communication circuit 8146 for transmission to a remote server 8148 based on the suitability of the data against one or more criteria. The data may include recent sensor data and additional data for transmission, such as RPM, component load, temperature, pressure, vibration, etc. The signal evaluation circuit 8108 may share and transmit data at a higher data rate to allow for greater granularity in processing at the remote server.

In embodiments, as shown in FIG. 45, the communications circuitry 8146 may communicate data directly to a remote server 8148. In embodiments, as shown in FIG. 46, the communications circuitry 8146 may communicate data to an intermediate computer 8152, which may include a processor 8154 executing an operating system 8156 and data storage circuitry 8158.

In embodiments such as those shown in Figures 47 and 48, the data collection system 8160 may have multiple monitoring devices 8144 collecting data for multiple components within a single piece of equipment, or may collect data for the same component across multiple pieces of equipment (both the same and different types of equipment) within the same piece of equipment. It is also possible to collect data from monitoring devices on multiple pieces of equipment within a facility. A monitoring application 8150 on the remote server 8148 may receive and store one or more of the detected values, timing signals, and data from the various monitoring devices 8144.

In embodiments, as shown in FIG. 47, the communications circuitry 8146 may communicate data directly to a remote server 8148. In embodiments, as shown in FIG. 48, the communications circuitry 8146 may communicate data to an intermediate computer 8152 including a processor 8154 executing an operating system 8156 and a data storage circuit 8158. There may be an individual intermediate computer 8152 associated with each monitoring device 8140, or an individual intermediate computer 8152 may be associated with multiple monitoring devices 8144, where the intermediate computer 8152 may collect data from multiple data monitoring devices and transmit the accumulated data to the remote server 8148. Communication to the remote server 8148 may be streaming, batch (e.g., when a connection is available), or opportunistic.

The monitoring application 8150 may select subsets of detected values to analyze jointly. The subsets for analysis may be selected based on a single type of sensor, component, or a single type of equipment on which the components are operating. The subsets for analysis may be selected or grouped based on common operating conditions, such as load size, operating state (e.g., intermittent or continuous), operating speed or tachometer output, or common ambient environmental conditions such as humidity, temperature, or air or fluid particulates. The subsets for analysis may also be selected based on the influence of other peripheral equipment, such as equipment that rotates at a similar frequency, generates electromagnetic fields, generates heat, induces motion or vibration, or emits vapors, chemicals, or particulates.

In an embodiment, the monitoring application 8150 may analyze a selected subset. In one example, data from a single sensor may be analyzed over different time periods, such as one operating cycle, multiple operating cycles, one month, one year, or the life of a component. Also, data from multiple sensors measuring the same type of part may be analyzed over different time periods. Trends in the data may be identified, such as rates of change associated with startup or different points in a process. Correlations between trends and values from different sensors may be analyzed to identify parameters that best predict the expected performance of the sensor in a short-term analysis. This information may be sent to the monitoring device for local analysis or to influence future monitoring device design, such as updating sensor models, sensor selection, sensor ranges, sensor scaling, sensor sampling frequencies, and types of data collected.

In embodiments, the monitoring application 8150 may access equipment specifications, equipment geometry, component specifications, component materials, predicted state information for multiple sensors, operational history, past detection values, sensor life models, etc., to analyze the selected subset using rule-based or model-based analysis. The monitoring application 8150 may provide recommendations regarding sensor selection, additional data to collect, data to store with sensor data, etc. The monitoring application 8150 may provide recommendations regarding scheduling repairs and/or maintenance. The monitoring application 8150 may provide recommendations regarding sensor replacement. The replacement sensor may match the sensor being replaced, or the replacement sensor may have a different range, sensitivity, sampling frequency, etc.

In embodiments, the monitoring application 8150 may include remote learning circuitry configured to analyze sensor condition data (e.g., sensor overload or sensor failure) along with data from other sensors, failure data of monitored components, equipment being monitored, outputs being generated, etc. The remote learning system may identify correlations between sensor overloads and data from other sensors.

An exemplary monitoring system for collecting data in an industrial environment includes a data acquisition circuit that interprets a plurality of sensed values, each sensed value corresponding to an input received from at least one of a plurality of input sensors; a MUX having inputs corresponding to a subset of the sensed values; a MUX control circuit that interprets the subset of the plurality of sensed values and provides logical control of the MUX and a resulting correspondence between the MUX inputs and the sensed values, where the logical control of the MUX includes adaptive scheduling of select lines; a data analysis circuit that receives an output from the MUX and data corresponding to a component health state as a result of the logical control of the MUX; and an analysis response circuit that performs an action in response to the component health state, where the plurality of sensors include at least two sensors, such as a temperature sensor, a load sensor, a vibration sensor, a sound sensor, a heat flux sensor, an infrared sensor, an accelerometer, a three-axis vibration sensor, and/or a tachometer. In certain further embodiments, the exemplary system includes: wherein at least one of the multiple sensed values may correspond to a fusion of two or more input sensors representing a virtual sensor, and the system further includes a data storage circuit that stores at least one of a component specification and expected component state information and buffers a subset of the multiple sensed values for a predetermined length of time, and the system further includes a data storage circuit that stores at least one of the component specification and expected component state information and buffers data corresponding to an output of the MUX and logic control of the MUX for a predetermined length of time, the data analysis circuit includes a peak detection circuit, a phase detection circuit, a bandpass filter circuit, a frequency conversion circuit, a frequency analysis circuit, a PLL circuit, a torsion analysis circuit, and/or a bearing analysis circuit, and the operations further include storing additional data in the data storage circuit, the operations include at least one of enabling or disabling one or more portions of the MUX circuit, and/or the operations include causing a MUX control circuit to change the logic control of the MUX and the correspondence between the input values and the sensed values of the MUX. In certain embodiments, the system includes at least two multiplexers, and controlling the correspondence between the multiplexer inputs and the detected values further includes controlling a connection between an output of a first multiplexer and an input of a second multiplexer, and controlling the correspondence between the multiplexer inputs and the detected values further includes powering down at least a portion of one of the at least two multiplexers, and/or controlling the correspondence between the MUX inputs and the detected values includes adaptive scheduling of select lines. In some embodiments, a data response circuit analyzes the stream of data from one or both MUXes and recommends an action in response to the analysis.

An exemplary test system includes a monitoring device including multiple analog and digital input sensors, data acquisition circuitry for interpreting multiple detected values, each of the multiple detected values corresponding to at least one of the input sensors; a MUX having inputs corresponding to a subset of the detected values; a MUX control circuit for interpreting the subset of detected values and for logically controlling the MUX and the resulting correspondence between the MUX inputs and the detected values, the MUX logical control including adaptive scheduling of the select lines; and a user interface capable of accepting select line scheduling inputs and displaying the output of the MUX and select line data.

In embodiments, information regarding the health or other status or condition information of a component or piece of industrial equipment may be obtained by looking at both the amplitude and phase or timing of a data signal relative to an associated data signal, timer, reference signal, or data measurement. One embodiment of a data monitoring device 8500 is shown in FIG. 49 and may include a plurality of sensors 8506 communicatively coupled to a controller 8502. The controller 8502 may include a data acquisition circuit 8504, a signal evaluation circuit 8508, and a response circuit 8510. The plurality of sensors 8506 may be hardwired to ports on the data acquisition circuit 8504 or may communicate wirelessly with the data acquisition circuit 8504. The plurality of sensors 8506 may also be wirelessly connected to the data acquisition circuit 8504. The data acquisition circuit 8504 may have access to a sensed value corresponding to the output of at least one of the plurality of sensors 8506, where the sensor 8506 may acquire data regarding different operational aspects of the equipment or operating component.

The selection of multiple sensors 8506 for a data monitoring device 8500 designed for a particular component or piece of equipment may depend on a variety of considerations, including accessibility for installing new sensors, incorporation of sensors in the initial design, anticipated operating and failure conditions, and sensor reliability. Consideration of the impact of failure may determine the extent to which a component or piece of equipment is monitored, with more sensors and/or more sophisticated sensors dedicated to systems where unexpected or undetected failures could result in expensive or severe consequences.

Depending on the type of device, the component being measured, the environment in which the device is operating, etc., the sensor 8506 may include, but is not limited to, a vibration sensor, a thermometer, a hygrometer, a voltage sensor, a current sensor, an accelerometer, a speed detector, an optical or electromagnetic sensor (e.g., measuring temperature, composition, spectral analysis, object position or movement), an image sensor, a structured light sensor, a laser-based image sensor, an acoustic wave sensor, a displacement sensor, a turbidity meter, a viscometer, a load sensor, a three-axis sensor, an accelerometer, a fluid pressure sensor, a vibration sensor, an accelerometer, a tachometer, a fluid pressure sensor, an air flow meter, a horsepower meter, a flow meter, a fluid particle detector, an acoustic sensor, a pH sensor, or any sensor described throughout this disclosure and the documents incorporated by reference.

Sensor 8506 may provide a stream of data over time having a phase component, such as that associated with acceleration or vibration, allowing for evaluation of phase or frequency analysis of different operational aspects of a portion or operating component of a device. Sensor 8506 may also provide a stream of data without a traditional phase component, such as temperature, humidity, load, etc. Sensor 8506 may provide a continuous or near-continuous stream of data over time, periodic readings, event-driven readings, and/or readings according to a selected interval or schedule.

In embodiments, as illustrated in FIG. 49, the sensor 8506 may be part of a data monitoring device 8500, referred to herein as a data collector, which may in some cases constitute a mobile or portable data collector. In embodiments, as shown in FIGS. 50 and 51, a sensor 8518, newly or previously attached to or integrated into a device or component, may be mechanically connected to or accessed by the monitoring device 8512. The sensor 8518 may be directly connected to an input port 8520 on the data acquisition circuitry 8516 of the controller 8514, or may be accessed wirelessly by the data acquisition circuitry 8516 via a reader, interrogator, or other wireless connection, such as over a short-range wireless protocol. In embodiments, the data acquisition circuitry 8516 may access the sensed values corresponding to the sensor 8518 wirelessly, via another source, or some combination of these methods. In an embodiment, the data acquisition circuit 8504 may include wireless communication circuitry 8522 capable of wirelessly receiving data from nearby sensors 8518 and routing the data to an input port 8520 of the data acquisition circuit 8516.

In embodiments, as shown in FIGS. 52 and 53, the signal evaluation circuitry 8508 may then process the detection values to obtain information about the component or portion of the device being monitored. The information extracted by the signal evaluation circuitry 8508 may include vibration data, including rotational speed, amplitude, frequency, phase, and/or acoustic data, and/or non-phase sensor data, such as temperature, humidity, image data, etc.

The signal evaluation circuit 8508 may include one or more components, such as a phase detector circuit 8528 that determines the phase difference between two time-based signals; a phase-locked loop circuit 8530 that adjusts the relative phase of a signal to align with a second signal, timer, or reference signal; and/or a bandpass filter circuit 8532 that may be used to separate signals occurring at different frequencies. An exemplary bandpass filter circuit 8532 includes any filtering operation understood in the art, including at least a lowpass filter, a highpass filter, and/or a bandpass filter—for example, used to filter out or reduce frequencies not of interest to a particular determination and/or to enhance signals at frequencies of interest. Additionally or alternatively, the bandpass filter circuit 8532 may include one or more notch filters or other filtering mechanisms to narrow a range of frequencies (e.g., frequencies from known noise sources). This may be used to filter signals of dominant frequencies, such as overall rotation, and may be useful for enabling evaluation of low-amplitude signals at frequencies associated with torsion, bearing faults, etc.

In embodiments, understanding the relative difference may be made possible by a phase detector circuit 8528 for determining the phase difference between two signals. There may be value in understanding the relative phase offset between signals, such as when periodic vibrations occur relative to the relative rotation of a piece of equipment. In embodiments, there may be value in understanding where periodic shaft vibrations occur relative to the motor's control input, in order to more balanced motor control. This may be particularly true for systems or components operating at relatively slow rotational speeds. Understanding the phase difference between two signals, or between those signals and a timer, can establish a relationship between the signal value and where it occurs in a process or rotation. Understanding the relative phase difference can be useful in assessing the relationship between different components of a system, such as when creating an Operational Deflection Shape (ODS) vibration model.

The signal evaluation circuit 8544 may perform frequency analysis using techniques such as a digital fast Fourier transform (FFT), Laplace transform, Z transform, wavelet transform, other frequency domain transform, or other digital or analog signal analysis techniques, including, but not limited to, complex analysis, including complex phase evolution analysis. The overall rotational speed or tachometer may be derived from data from sensors such as tachometers, accelerometers, and displacement meters. Additional frequencies of interest may also be identified. These may include frequencies near the overall rotational speed as well as frequencies higher than the rotational speed. These frequencies may include frequencies asynchronous with the overall rotational speed. Signals observed at frequencies that are multiples of the rotational speed may be due to vibrations from the bearings or other operations or conditions involving the bearings. In some embodiments, these frequencies may range from 1x the rotational speed, 2x the rotational speed, 3x the rotational speed, etc., up to 3.15x to 15x the rotational speed or more. In some embodiments, the signal evaluation circuit 8544 may select RC components for the bandpass filter circuit 8532 based on the overall rotational speed to create a bandpass filter circuit 8532 that rejects signals at expected frequencies, such as the overall rotational speed, to facilitate identification of small amplitude signals at other frequencies. In embodiments, variable components may be selected so that the bandpass filter may be a variable bandpass filter, adjusting for changes in rotational speed. This may occur under the control of circuit elements that automatically self-adjust, or under the control of a processor that includes automatic control based on a model of circuit operation, where a rotational speed indicator or other data is provided as the basis for control.

In embodiments, the signal evaluation circuit 8544 may utilize time-based detection values to perform transient signal analysis rather than frequency analysis. These may include identifying abrupt changes in signal amplitude, including changes in amplitude that exceed a predetermined value or that exist for a certain duration. In embodiments, the time-based sensor data may be aligned to a timer or reference signal to align the time-based sensor data to, for example, a time or location within a cycle. Additional processing to view frequency changes over time may include short-time Fourier transforms (STFTs) and wavelet transforms.

In embodiments, frequency-based techniques and time-based techniques may be combined. For example, time-based techniques may be used to determine discrete time periods during which a given operating mode or state occurs, and frequency-based techniques may be used to determine operation within one or more of the discrete time periods.

In embodiments, the signal evaluation circuitry may utilize demodulation techniques on signals obtained from equipment operating at slow speeds, such as pulp and paper machinery, mining machinery, etc. Signal evaluation circuitry employing demodulation techniques may include bandpass filter circuits, rectifier circuits, and/or lowpass circuits before converting the data to the frequency domain.

The response circuit 8510 8710 may further evaluate the results of the signal evaluation circuit 8508 8544 and initiate action based on certain criteria. Criteria may include predetermined maximum or minimum values for the detected values from a particular sensor, the value of the corresponding detected value of the sensor over time, a change in value, a rate of change in value, and/or cumulative values (e.g., time above/below a threshold, weighted time above/below one or more thresholds, and/or an area of detected values above/below one or more thresholds). Criteria may include detected values from a sensor at a particular frequency or phase, which may be based on equipment geometry, equipment control scheme, system inputs, historical data, current operating conditions, and/or expected response. Criteria may consist of a combination of data from different sensors, such as relative values, relative change in value, relative rate of change in value, or relative values over time. Relative criteria may vary depending on other data or information, such as the process stage, the type of product being processed, the type of equipment, ambient temperature and humidity, or external vibrations from other equipment. Relative criteria may include the level of synchronization with the overall rotational speed to distinguish between bearing-induced vibrations and vibrations due to the equipment design. In embodiments, the criteria may be reflected in one or more calculated statistics or metrics (including those generated by further calculations involving multiple criteria or statistics), which may in turn be used for processing (on the data collection device or by an external system), such as providing input to one or more of the machine learning capabilities described in this disclosure. They may also be used as data elements that serve as inputs to other systems, such as a control system (which may be an onboard data collector or remote, controlling data input selection, sensor data multiplexing, storage, etc.), or a data stream or data package that can be utilized by a data marketplace, SCADA system, remote control system, maintenance system, analysis system, or other system.

In illustrative and non-limiting examples, an alarm may be issued if the vibration amplitude and/or frequency exceeds a predetermined maximum value, if there is a change or rate of change that exceeds a predetermined tolerance, and/or if a cumulative value based on the vibration amplitude and/or frequency exceeds a threshold value. While certain embodiments are described herein as the detected value exceeding a threshold or predetermined value, the detected value may also be below the threshold or predetermined value—e.g., where a change in the detected value is expected to occur but the detected value indicates that the change may not have occurred. For example, but not by way of limitation, vibration data may indicate a system agitation level, properly operating equipment, etc., and vibration data below an amplitude and/or frequency threshold may be indicative of a process that is not operating as expected. Unless the context clearly indicates otherwise, any statement herein describing the determination of a value above a threshold and/or above a predetermined or expected value shall be understood to include the determination of a value below a threshold and/or below a predetermined or expected value.

The predetermined tolerances may be based on expected system response or vibration based on the equipment geometry and control scheme, such as the number of bearings, relative rotational speed, or power inflow into the system at a certain frequency. The predetermined tolerances may also be based on long-term analysis of detected values across multiple similar pieces of equipment or components, or correlation of data with equipment failures. Vibration phase information may be used to identify the physical location of a problem. Vibration phase information may be used to identify system design flaws, abnormal operation, and/or component or process failures. In some embodiments, an alert may be issued based on a change or rate of change in data over time, such as an increase in amplitude or shift in the frequency or phase at which vibrations occur. In some embodiments, an alert may be issued based on accumulated values, such as time spent above a threshold, a weighted value of time above one or more thresholds, and/or the area under the curve of values detected above one or more thresholds. In some embodiments, an alert may be issued based on a combination of data from different sensors, such as the relative change in value or the relative rate of change in amplitude, phase, or frequency, in addition to non-phase sensor values, such as temperature and humidity. For example, an increase in temperature and energy at a certain frequency may indicate a hot bearing beginning to fail. In embodiments, the relative criteria for an alarm may vary depending on other data or information, such as the process stage, the type of product being processed by the equipment, the ambient temperature and humidity, external vibrations from other equipment, etc.

In embodiments, the response circuitry 8510 can cause the data acquisition circuitry 8504 to enable or disable processing of detection values corresponding to a particular sensor based on some of the criteria described above. This may include switching to a sensor with a different response speed, sensitivity, range, etc., accessing a new sensor or sensor type, etc. The switching may be performed based on a model, a set of rules, etc. In embodiments, the switching may be under the control of a machine learning system, such that the switching is controlled based on one or more success metrics combined with input data over a series of tests that may be performed under the supervision of a human supervisor or under the control of an automated system. The switching may include switching from one input port to another (e.g., switching from one sensor to another). The switching may include changing the multiplexing of data, such as combining different streams under different circumstances. Switching may involve activating a system to acquire additional data, such as moving a mobile system (e.g., a robotic or drone system) to a location where different or additional data is available (e.g., positioning an image sensor for a different field of view or a sonar sensor for a different collection direction), or to a location where a different sensor is accessible (e.g., moving a collector to connect via a wired or wireless connection to a sensor located at a location in the environment). The response circuit 8510 may make recommendations for future replacement of a particular sensor with one having a different response speed, sensitivity, range, etc. The response circuit 8510 may recommend design changes for future embodiments of components, pieces of equipment, operating conditions, processes, etc.

In embodiments, the response circuitry 8510 may recommend maintenance during upcoming process shutdowns or may initiate a maintenance call. The response circuitry 8510 may recommend changes to process or operating parameters to remotely balance equipment. In embodiments, the response circuitry 8510 may implement or recommend process changes—for example, reducing the utilization of components that are approaching a maintenance interval, operating off-nominal, or have failed for purpose but are still at least partially operational; changing the operating speed of a component (e.g., placing it in a low-demand mode); initiating remediation of the problem (e.g., signaling additional lubrication of a roller bearing set or signaling an alignment process for an out-of-balance system); etc.

In an embodiment, as shown in FIG. 54, the data monitoring device 8540 may further include a data storage circuit 8542, memory, etc. The signal evaluation circuit 8544 may periodically store certain detected values to enable tracking of component performance over time.

In embodiments, based on associated operating conditions and/or failure modes that may occur when sensor values approach one or more criteria, the signal evaluation circuit 8544 may store data in the data storage circuit 8542 based on the data's conformance to one or more criteria as described throughout this disclosure. Based on one sensor input meeting or approaching a specified criterion or range, the signal evaluation circuit 8544 may store additional data, such as rotational speed, component load, temperature, pressure, vibration, or other sensor data of the type described throughout this disclosure. The signal evaluation circuit 8544 may store data at a higher data rate to allow for greater granularity in future processing, the ability to reprocess at a different sampling rate, and/or diagnostics or post-processing of system information where operating data of interest is flagged.

In an embodiment, as shown in FIG. 55, the data monitoring system 8546 may include at least one data monitoring device 8548. The at least one data monitoring device 8548 comprises a sensor 8506 and a controller 8550 including a data acquisition circuit 8504, a signal evaluation circuit 8538, a data storage circuit 8542, and a communications circuit 8552 that enables data and analysis to be transmitted to a monitoring application 8556 on a remote server 8554. Note that the signal evaluation circuit 8538 may comprise at least one of a phase detection circuit 8528, a phase-locked loop circuit 8530, and/or a bandpass circuit 8532. The signal evaluation circuit 8538 may periodically share data with the communications circuit 8552 for transmission to the remote server 8554, enabling the monitoring application 8556 to track the performance of components or equipment over time and under various conditions. Because sensor values approaching one or more criteria may indicate associated operating conditions and/or failure modes, the signal evaluation circuit 8538 may share data with the communications circuit 8552 for transmission to the remote server 8554 based on the data's conformance to one or more criteria. Based on one sensor input meeting or approaching a specified criterion or range, the signal evaluation circuit 8538 may share additional data for transmission, such as RPM, component load, temperature, pressure, vibration, etc. The signal evaluation circuit 8538 may also share and transmit data at a higher data rate to increase the granularity of processing at the remote server.

In an embodiment, as shown in FIG. 56, the data collection system 8560 may include multiple monitoring devices 8558 collecting data regarding multiple components within a single piece of equipment, may collect data regarding the same component across multiple pieces of equipment (both the same and different types of equipment) within the same facility, and may even collect data from monitoring devices within multiple facilities. A monitoring application on a remote server can receive and store data from multiple, diverse monitoring devices. The monitoring application can then select subsets of data that can be jointly analyzed. The subset of monitoring data may be selected based on data from a single type of component or a single type of equipment on which the component is operating. The monitoring data may be selected or grouped based on common operating conditions such as load size, operating state (e.g., intermittent, continuous), operating speed or tachometer, common ambient environmental conditions such as humidity, temperature, air or fluid particulates, etc. Monitoring data may be selected based on the influence of other nearby equipment, such as nearby machinery rotating at a similar frequency, nearby equipment that generates electromagnetic fields, nearby equipment that generates heat, nearby equipment that induces motion or vibration, nearby equipment that emits vapors, chemicals or particulates, or other potentially interfering or intervening influences.

The monitoring application may then analyze the selected data set. For example, data from one component may be analyzed over different time periods, such as one operating cycle, multiple operating cycles, one month, or one year. Data from multiple components of the same type may also be analyzed over different time periods. Trends in the data, such as changes in frequency or amplitude, may be correlated with records of failures or maintenance associated with the same part or equipment. Data trends, such as rates of change associated with startup or different points in the process, may also be identified. Additional data may be introduced into the analysis, such as data indicating the quality of the output product, the amount of output (e.g., per unit time), or the success or failure of the process. Correlations between trends and values in different types of data may be analyzed, and short-term analysis may identify parameters that may provide the best prediction of expected performance. This information may be sent to the monitoring device to update the types of data collected and analyzed locally or to influence future monitoring device design.

In an illustrative and non-limiting example, a monitoring device may be used to collect and process sensor data to measure mechanical torque. The monitoring device may communicate with or include a high-resolution, high-speed vibration sensor to collect data over a long enough period of time to measure multiple cycles of rotation. For gear-driven equipment, a sampling resolution is required such that the number of samples per cycle is at least equal to the number of gears driving the part. It should be understood that using a lower sampling resolution may result in less reliable determinations, while also allowing data to be acquired over a longer period of time to provide sufficient statistical confidence. This data can be used to generate a phase reference (relative probe) or tachometer signal for the equipment. This phase reference can be used to align phase data, such as vibration or acceleration data, from multiple sensors located at different locations on a part or on different components within a system. This information may facilitate the determination of torque on different components or the generation of an operational deflection shape (ODS), which indicates the degree of mechanical deflection of one or more components during operational modes. This ODS can be used to measure the mechanical torque of the component.

High-resolution data streams can provide additional data for detecting transient signals in slow-speed operation. Identifying transient signals can identify equipment or component defects.

In an illustrative, non-limiting example, a monitoring device can be used to identify mechanical jitter for use in failure prediction models. The monitoring device can begin acquiring data at equipment startup, ramp up to operating speed, and then acquire data while the equipment is operating. Once operating speed is reached, torsional jitter is expected to be minimal, and changes in torsion at this stage may indicate cracks, bearing failure, etc. Furthermore, removing known torsions from the signal can facilitate identification of unexpected torsions due to system design flaws or component wear. Having phase information relative to data collected at operating speed can facilitate identification of vibration sources and potential component wear. Relative phase information from multiple sensors located throughout the machine facilitates evaluation of torsional motion propagating within the equipment.

Certain further embodiments of the exemplary system include: when the signal evaluation circuit includes a phase detection circuit, or a phase detection circuit and a phase-locked loop circuit and/or a bandpass filter; and when the number of input sensors includes at least two input sensors providing phase information and at least one input sensor providing non-phase sensor information, the signal evaluation circuit further aligns the phase information provided by at least two of the input sensors; and wherein at least one operation is responsive to at least one of: a change in the magnitude of the vibration amplitude; a change in the frequency or phase of the vibration; a rate of change of at least one of the vibration amplitude, vibration frequency, and vibration phase; a relative change in at least two values of the vibration amplitude, vibration frequency, and vibration phase; and/or a relative rate of change between at least two of the vibration amplitude, vibration frequency, and vibration phase. The system further includes an alarm circuit, wherein at least one action includes providing an alarm, wherein the alarm can be one of tactile, audible, and visual; and a data storage circuit, wherein at least one of the vibration amplitude, the vibration frequency, and the vibration phase is periodically stored to create a vibration history, and wherein the at least one action includes storing additional data in the data storage circuit (e.g., as a vibration fingerprint of the component), wherein storing the additional data in the data storage circuit is responsive to at least one of a change in the magnitude of the vibration amplitude, a change in the frequency or phase of the vibration, a rate of change of the vibration amplitude, the vibration frequency, or the vibration phase, a relative change in at least two values of the vibration amplitude, frequency, and phase, and a relative rate of change of at least two values of the vibration amplitude, frequency, and phase. The system further includes at least one multiplexing (MUX) circuit by which alternative combinations of sensed values can be selected based on at least one of a user input, a sensed condition, and a selected operating parameter of the machine; the multiplexing circuit, each of a number of sensed values corresponding to at least one of the input sensors, and at least one operation including enabling or disabling a connection of one or more portions of the multiplexing circuit; a MUX control circuit that interprets a subset of the number of sensed values and provides logical control of the MUX and the resulting correspondence between MUX inputs and sensed values; and/or where the logical control of the MUX includes adaptive scheduling of select lines.

An exemplary method for monitoring a component includes receiving time-based data from at least one sensor, phase-locking the received data with a reference signal, converting the received time-based data to frequency data, filtering the frequency data to remove tachometer frequencies, identifying low-amplitude signals occurring at high frequencies, and activating an alarm if the low-amplitude signals exceed a threshold.

An exemplary system for data collection, processing, and utilization of signals in an industrial environment includes a plurality of monitoring devices, each monitoring device including a data acquisition circuit configured to interpret a plurality of detected values from a plurality of input sensors communicatively coupled to the data acquisition circuit, each of the plurality of detected values corresponding to at least one of the input sensors; a signal evaluation circuit configured to acquire at least one of a vibration amplitude, a vibration frequency, and a vibration phase position corresponding to at least one of the plurality of detected values in response to at least one corresponding one of the plurality of detected values; a data storage device for storing a subset of the plurality of detected values; a communications circuit configured to communicate at least one selected detected value to a remote server; and a monitoring application on the remote server configured to receive the at least one selected detected value, collaboratively analyze the subset of detected values received from the plurality of monitoring devices, and recommend an action.

In certain further embodiments, the exemplary system includes: for each monitoring device, the plurality of input sensors includes at least one input sensor providing phase information and at least one input sensor providing non-phase input sensor information; the joint analysis includes using the phase information from the plurality of monitoring devices to align information from the plurality of monitoring devices; the subset of detected values is selected based on data associated with the detected values including at least one of a common type of component, a common type of equipment, and a common operating condition; and the expected life of the part associated with the detected values is selected based on one of a type of equipment associated with the detected values and the operating condition under which the detected values were measured; and/or the analysis of the subset of detected values includes providing the subset of detected values and the supplemental information to a neural net to learn to recognize various operating conditions, health conditions, lifespans, and fault conditions using deep learning techniques; and the supplemental information includes one of part specifications, part performance, equipment specifications, equipment performance, maintenance records, repair records, and a predicted condition model.

An exemplary system for collecting data in an industrial environment includes: a data collection circuit configured to interpret a plurality of detected values from a plurality of input sensors communicatively coupled to the data collection circuit, each of the plurality of detected values corresponding to at least one of the input sensors; a signal evaluation circuit configured to obtain at least one of a vibration amplitude, a vibration frequency, and a vibration phase position corresponding to at least one of the plurality of detected values in response to at least one corresponding one of the plurality of detected values; a multiplexing circuit configured to select alternative combinations of the detected values based on at least one of a user input, a detected condition, and a selected operating parameter of the machine, each of the plurality of detected values corresponding to at least one of the input sensors; and a response circuit configured to perform at least one action in response to at least one of the vibration amplitude, the vibration frequency, and the vibration phase position.

An exemplary system for collecting data in an instrument includes: a data acquisition circuit configured to interpret a plurality of detected values from a plurality of input sensors communicatively coupled to the data acquisition circuit, each of the plurality of detected values corresponding to at least one of the input sensors; a timer circuit configured to generate a timing signal based on a first detected value of the plurality of detected values; a signal evaluation circuit including a phase detection circuit that determines a relative phase difference between a second detected value of the plurality of detected values and the timing signal, and that determines at least one of a vibration amplitude, a vibration frequency, and a vibration phase position corresponding to the second detected value; and a response circuit configured to perform at least one action in response to at least one of the vibration amplitude, the vibration frequency, and the vibration phase position.

An exemplary system for bearing analysis in an industrial environment includes: a data acquisition circuit configured to interpret a plurality of detected values from a plurality of input sensors communicatively coupled to the data acquisition circuit, each of the plurality of detected values corresponding to at least one of the input sensors; a data storage device that stores specifications and expected condition information for a plurality of bearing types and buffers the plurality of detected values for a predetermined period of time; a timer circuit configured to generate a timing signal based on a first detected value of the plurality of detected values; a bearing analysis circuit configured to analyze the buffered detected value in relation to the specifications and expected condition information and perform a life prediction, the bearing analysis circuit including a phase detection circuit configured to determine a relative phase difference between a second detected value of the plurality of detected values and the timing signal; and a signal evaluation circuit configured to acquire at least one of a vibration amplitude, a vibration frequency, and a vibration phase position corresponding to the second detected value; and a response circuit configured to perform at least one action in response to at least one of the vibration amplitude, the vibration frequency, and the vibration phase position.

An exemplary motor monitoring system includes a data acquisition circuit configured to interpret a plurality of sensed values from a plurality of input sensors communicatively coupled to the data acquisition circuit, each of the plurality of sensed values corresponding to at least one of the input sensors; a data storage circuit configured to store motor and motor component specifications, system geometry, and predicted state information, store past motor performance, and buffer the plurality of sensed values for a predetermined period of time; a timer circuit configured to generate a timing signal based on a first sensed value of the plurality of sensed values; and a timer circuit configured to analyze the buffered sensed values in relation to the specifications and predicted state information and calculate motor performance parameters. the motor analysis circuit includes a phase detection circuit configured to determine a relative phase difference between a second detected value of the plurality of detected values and the timing signal; a signal evaluation circuit configured to obtain at least one of a vibration amplitude, a vibration frequency, and a vibration phase position corresponding to the second detected value, and to analyze the at least one of the vibration amplitude, the vibration frequency, and the vibration phase position against buffered detected values, specifications, and predicted state information to obtain a motor performance parameter; and a response circuit configured to perform at least one action in response to the at least one of the vibration amplitude, the vibration frequency, and the vibration phase position and the motor performance parameter.

An exemplary system for estimating performance parameters of a vehicle steering system includes a data acquisition circuit configured to interpret a plurality of sensed values from a plurality of input sensors communicatively coupled to the data acquisition circuit, each of the plurality of sensed values corresponding to at least one of the input sensors; and a data storage circuit configured to store specifications, system geometry, and expected condition information for the vehicle steering system, rack, pinion, and steering column, store past steering system performance, and buffer the plurality of sensed values for a predetermined period of time.

The system further includes a timer circuit configured to generate a timing signal based on a first detected value of the plurality of detected values; a steering system analysis circuit configured to compare the buffered detected values with specifications and expected status information to analyze the detected values and generate steering system performance parameters, the steering system analysis circuit including a phase detection circuit configured to determine a relative phase difference between a second detected value of the plurality of detected values and the timing signal; and a signal evaluation circuit configured to obtain at least one of a vibration amplitude, a vibration frequency, and a vibration phase position corresponding to the second detected value and analyze the at least one of the vibration amplitude, the vibration frequency, and the vibration phase position against the buffered detected values, specifications, and expected status information to obtain the steering system performance parameters; and a response circuit configured to perform at least one action in response to the at least one position of the vibration amplitude, the vibration frequency, and the vibration phase and the steering system performance parameters.

An exemplary system for estimating a pump performance parameter and a pump performance parameter includes a data acquisition circuit configured to interpret a plurality of detected values from a plurality of input sensors communicatively coupled to the data acquisition circuit, each of the plurality of detected values corresponding to at least one of the input sensors; a data storage circuit configured to store pump and pump component specifications, system geometry, and predicted status information associated with the detected values, store past pump performance, and buffer the plurality of detected values for a predetermined period of time; a timer circuit configured to generate a timing signal based on a first detected value of the plurality of detected values; and a pump analysis circuit configured to analyze the buffered detected values against the specifications and predicted status information. The circuit includes a pump analysis circuit including a pump performance parameter, the pump analysis circuit including a phase detection circuit configured to determine a relative phase difference between a second of the plurality of detected values and the timing signal, and a signal evaluation circuit that obtains at least one of a vibration amplitude, a vibration frequency, and a vibration phase position corresponding to the second detected value, analyzes the at least one of the vibration amplitude, the vibration frequency, and the vibration phase position against the buffered detected values, specifications, and expected state information, and generates the pump performance parameter, and a response circuit configured to take at least one action in response to the at least one of the vibration amplitude, the vibration frequency, and the vibration phase and the pump performance parameter, wherein the pump is one of an automotive water pump and a mineral pump.

An exemplary system for estimating drill performance parameters of a drilling machine includes a data acquisition circuit configured to interpret a plurality of detected values from a plurality of input sensors communicatively coupled to the data acquisition circuit, each of the plurality of detected values corresponding to at least one of the input sensors; a data storage circuit configured to store drill and drill component specifications, system geometry, and predicted condition information associated with the detected values, store past drill performance, and buffer the plurality of detected values for a predetermined period of time; a timer circuit configured to generate a timing signal based on a first detected value of the plurality of detected values; and analyze the buffered detected values against the specifications and the predicted condition information to generate a drill performance parameter. the drill analysis circuit configured to: determine a relative phase difference between a second of the detected values and the timing signal; and obtain at least one of a vibration amplitude, a vibration frequency, and a vibration phase position corresponding to the second detected value; and analyze the at least one of the vibration amplitude, the vibration frequency, and the vibration phase position against the buffered detected values, specifications, and expected condition information to obtain a drill performance parameter; and a response circuit configured to perform at least one action in response to the at least one of the vibration amplitude, the vibration frequency, and the vibration phase and the drill performance parameter, wherein the drilling machine is one of an oil drilling machine and a gas drilling machine.

An exemplary system for estimating conveyor health parameters includes a data acquisition circuit configured to interpret a plurality of detected values from a plurality of input sensors communicatively coupled to the data acquisition circuit, each of the plurality of detected values corresponding to at least one of the input sensors; a data storage circuit configured to store conveyor and conveyor component specifications, system geometry, and predicted condition information associated with the detected values, store past conveyor performance, and buffer the plurality of detected values for a predetermined length of time; a timer circuit configured to generate a timing signal based on a first detected value of the plurality of detected values; and a timer circuit configured to interpret the buffered detected values against the specifications and predicted condition information. the conveyor analysis circuit includes a phase detection circuit configured to determine a relative phase difference between a second of the plurality of detected values and the timing signal; a signal evaluation circuit configured to obtain at least one of a vibration amplitude, a vibration frequency, and a vibration phase position corresponding to the second detected value, and to analyze the at least one of the vibration amplitude, the vibration frequency, and the vibration phase position against the buffered detected values, specifications, and expected state information to obtain the conveyor performance parameter; and a response circuit configured to perform at least one action in response to the at least one of the vibration amplitude, the vibration frequency, and the vibration phase position and the conveyor performance parameter.

An exemplary system for estimating agitator health parameters includes a data acquisition circuit configured to interpret a plurality of detected values from a plurality of input sensors communicatively coupled to the data acquisition circuit, each of the plurality of detected values corresponding to at least one of the input sensors; a data storage circuit configured to store agitator and agitator component specifications, system geometry, and expected state information associated with the detected values, store past agitator performance, and buffer the plurality of detected values for a predetermined period of time; a timer circuit configured to generate a timing signal based on a first detected value of the plurality of detected values; and an agitator analysis circuit configured to analyze the buffered detected values based on the specifications and expected state information to determine agitator performance parameters. the agitator analysis circuit includes a phase detection circuit configured to determine a relative phase difference between the second detection value and the timing signal; a signal evaluation circuit that obtains at least one of a vibration amplitude, a vibration frequency, and a vibration phase position corresponding to the second detection value and analyzes the at least one of the vibration amplitude, the vibration frequency, and the vibration phase position against the buffered detection values, specifications, and expected status information to determine a performance parameter of the agitator; and a response circuit configured to perform at least one action in response to the at least one of the vibration amplitude, the vibration frequency, and the vibration phase and the agitator performance parameter, wherein the agitator is one of a rotary tank mixer, a large tank mixer, a portable tank mixer, a tote tank mixer, a drum mixer, a mounted mixer, and a propeller mixer.

An exemplary system for estimating compressor health parameters includes a data acquisition circuit configured to interpret a plurality of detected values from a plurality of input sensors communicatively coupled to the data acquisition circuit, each of the plurality of detected values corresponding to at least one of the input sensors; a data storage circuit configured to store compressor and compressor component specifications, system geometry, and predicted condition information associated with the detected values, store past compressor performance, and buffer the plurality of detected values for a predetermined period of time; a timer circuit configured to generate a timing signal based on a first detected value of the plurality of detected values; a timer circuit configured to analyze the buffered detected values in relation to the specifications and predicted condition information; and a compressor health parameter estimation circuit configured to estimate the compressor health parameter. The compressor analysis circuit is configured to generate a performance parameter, the compressor analysis circuit including: a phase detection circuit configured to determine a relative phase difference between a second detected value of the plurality of detected values and the timing signal; and a signal evaluation circuit configured to obtain at least one of a vibration amplitude, a vibration frequency, and a vibration phase position corresponding to the second detected value, and to analyze the at least one of the vibration amplitude, the vibration frequency, and the vibration phase position against buffered detected values, specifications, and predicted state information to obtain a compressor performance parameter; and a response circuit configured to take at least one action in response to the at least one position of the vibration amplitude, the vibration frequency, and the vibration phase and the compressor performance parameter.

An exemplary system for estimating air conditioner health parameters includes a data acquisition circuit configured to interpret a plurality of detected values from a plurality of input sensors communicatively coupled to the data acquisition circuit, each of the plurality of detected values corresponding to at least one of the input sensors; a data storage circuit configured to store specifications, system geometry, and predicted status information for the air conditioner and air conditioner components associated with the detected values, store historical performance of the air conditioner, and buffer the plurality of detected values for a predetermined period of time; a timer circuit configured to generate a timing signal based on a first detected value of the plurality of detected values; a timer circuit configured to analyze the buffered detected values based on the specifications and predicted status information, and to estimate the air conditioner health parameters. The air conditioner analysis circuit for calculating the air conditioner performance parameters includes: a phase detection circuit configured to determine a relative phase difference between a second of the plurality of detected values and the timing signal; a signal evaluation circuit that obtains at least one of a vibration amplitude, a vibration frequency, and a vibration phase position corresponding to the second detected value, and analyzes the at least one of the vibration amplitude, the vibration frequency, and the vibration phase position against buffered detected values, specifications, and predicted state information to determine the air conditioner performance parameters; and a response circuit configured to perform at least one action in response to the at least one position of the vibration amplitude, the vibration frequency, and the vibration phase and the air conditioner performance parameters.

An exemplary system for estimating centrifuge health parameters includes a data acquisition circuit configured to interpret a plurality of detected values from a plurality of input sensors communicatively coupled to the data acquisition circuit, each of the plurality of detected values corresponding to at least one of the input sensors; a data storage circuit configured to associate the detected values with centrifuge and centrifuge component specifications, system geometry, and expected status information, store past centrifuge performance, and buffer the plurality of detected values for a predetermined period of time; a timer circuit configured to generate a timing signal based on a first detected value of the plurality of detected values; and a timer circuit configured to analyze the buffered detected values against the specifications and expected status information and to estimate the centrifuge performance. The centrifuge analysis circuit includes a phase detection circuit configured to determine a relative phase difference between a second detected value of the plurality of detected values and the timing signal; a signal evaluation circuit that obtains at least one of a vibration amplitude, a vibration frequency, and a vibration phase position corresponding to the second detected value, and analyzes the at least one of the vibration amplitude, the vibration frequency, and the vibration phase position against buffered detected values, specifications, and expected state information to determine the centrifuge performance parameter; and a response circuit configured to perform at least one action in response to the at least one of the vibration amplitude, the vibration frequency, and the vibration phase position and the centrifuge performance parameter.

In embodiments, information regarding the health of components or pieces of industrial equipment is obtained by comparing the values of multiple signals at the same point. In the process, this may be accomplished by aligning the signals with other related data signals, timers, or reference signals. One embodiment of a data monitoring device 8700, 8718 is shown in Figures 57-59 and may include controllers 8702, 8720. The controller may include data acquisition circuitry 8704, 8722, a signal evaluation circuit 8708, a data storage circuit 8716, and an optional response circuit 8710. The signal evaluation circuit 8708 may include a timer circuit 8714 and, optionally, a phase detection circuit 8712.

The data monitoring device may include multiple sensors 8706 communicatively coupled to the controller 8702. The multiple sensors 8706 may be hardwired to ports of the data acquisition circuitry 8704. The multiple sensors 8706 may be wirelessly connected to the data acquisition circuitry 8704, which can access a sensed value corresponding to the output of at least one of the multiple sensors 8706, where the sensor 8706 may capture data related to different operational aspects of a portion or operating component of the device. In embodiments, as shown in FIGS. 58 and 59, one or more external sensors 8724 not explicitly part of the monitoring device 8718 may be mechanically connected to or accessed by the monitoring device 8718. The data acquisition circuitry 8722 may include one or more input ports 8726. The multiple external sensors 8724 may be directly connected to one or more input ports 8726 provided on the data acquisition circuitry 8722 of the controller 8720. In an embodiment, as shown in FIG. 59, the data acquisition circuit 8722 may further include wireless communication circuitry 8728 for accessing detected values corresponding to one or more external sensors 8724 wirelessly or via another source, or some combination of these methods.

The selection of multiple sensors 8706 8724 for connection to a data monitoring device 8700 8718 designed for a particular component or piece of equipment may depend on a variety of considerations, including accessibility for installing new sensors, incorporation of sensors into the initial design, expected operating and fault conditions, desired resolution at various locations in the process or plant, and sensor reliability. The impact of failure, time response to failure (e.g., warning time or abnormal mode occurring before failure), probability of failure, and the sensitivity or difficulty required to detect fault conditions will determine the extent to which a component or piece of equipment is monitored.

The signal evaluation circuit 8708 may process the detected values to obtain information about the component or piece of equipment being monitored. The information extracted by the signal evaluation circuit 8708 may include information regarding what point or time in the process corresponds to the detected value, where the point in time is based on the timing signal generated by the timer circuit 8714. The initiation of the timing signal may be generated by detecting an edge of a control signal, such as a rising edge, a falling edge, or both, and the control signal may be associated with the start of the process. The initiation of the timing signal may be triggered by the initial movement of a component or equipment. The initiation of the timing signal may be triggered by the initial flow through a pipe or opening, or by flow achieving a predetermined velocity. The initiation of the timing signal may be triggered by a state value indicating that a process has started (e.g., the state of a switch, button, a data value provided to indicate that a process has started, etc.). The extracted information may consist of information regarding the phase difference between the stream of detected values and the time signal generated by the timer circuit 8714, as determined by the phase detection circuit 8712. The extracted information may include information regarding a phase difference between one stream of detected values and a second stream of detected values where the first stream of detected values is used as a basis or trigger for a timing signal generated by a timer circuit.

Depending on the type of device, the component being measured, the environment in which the device operates, etc., sensors 8706 8724 may comprise one or more of the following: thermometers, hygrometers, voltage sensors, current sensors, accelerometers, speed detectors, optical or electromagnetic sensors (e.g., to determine temperature, composition, and/or spectral analysis, and/or to measure the position or movement of an object), image sensors, displacement sensors, turbidity meters, viscometers, load sensors, triaxial sensors, tachometers, fluid pressure meters, air flow meters, horsepower meters, flow meters, fluid particle detectors, acoustic sensors, pH sensors, etc.

Sensors 8706 8724 may provide streams of data over time that have a phase component, such as acceleration or vibration, allowing for evaluation of phase or frequency analysis of different operational aspects of a portion or operating part of a device. Sensors 8706 8724 may also provide streams of data that do not have a phase, such as temperature, humidity, load, etc. Sensors 8706 8724 may provide continuous or near-continuous streams of data over time, periodic readings, event-driven readings, and/or readings according to a selected interval or schedule.

In an embodiment, as shown in Figures 60 and 61, the data acquisition circuit 8734 may further include a multiplexer circuit 8736, as described elsewhere herein. The output from the multiplexer circuit 8736 may be utilized by the signal evaluation circuit 8708. The response circuit 8710 may be capable of turning portions of the multiplexer circuit 8736 on and off. The response circuit 8710 may be capable of controlling a control channel of the multiplexer circuit 8736.

The response circuit 8710 may further evaluate the results of the signal evaluation circuit 8708 and initiate action based on certain criteria. Criteria may include a sensor's detected value at a particular frequency or phase relative to the timer signal, and the frequency or phase of interest may be based on the equipment's geometry, the equipment's control scheme, system inputs, historical data, current operating conditions, and/or expected response. Criteria may include a predetermined maximum or minimum detected value from a particular sensor, the sensor's corresponding detected value's cumulative value over time, a change in value, a rate of change in value, and/or cumulative values (e.g., time spent above/below a threshold, weighted time spent above/below one or more thresholds, and/or area of detected value spent above/below one or more thresholds). Criteria may consist of a combination of data from different sensors, such as relative values, relative change in value, relative rate of change in value, or relative values over time. Relative criteria may vary depending on other data or information, such as the stage of the process, the type of product being processed, the type of equipment, ambient temperature and humidity, or external vibrations from other equipment.

While certain embodiments are described herein as having detected values exceeding a threshold or predetermined value, detected values may also be below the threshold or predetermined value, such as when a change in detected value is expected to occur but indicates that a change in detected value may not have occurred. For example, and without limitation, vibration data may indicate a system's agitation level, properly operating equipment, etc., and vibration data below a threshold amplitude and/or frequency may be indicative of a process not operating as expected. Unless the context clearly indicates otherwise, any statement herein describing a determination of a value above a threshold and/or above a predetermined or expected value will be understood to include a determination of a value below a threshold and/or below a predetermined or expected value.

The predetermined tolerance range may be based on the expected system response or vibration based on the equipment's geometry and control method, such as the number of bearings, relative rotational speed, or power flow into the system at a certain frequency. The predetermined tolerance range may also be set by analyzing the detected values of multiple similar devices or components over a long period of time and taking into account correlations with equipment failures.

In an embodiment, an alert may be issued based on several of the criteria described above. In an illustrative example, an increase in temperature and energy at a particular frequency may indicate a hot bearing beginning to fail. In an embodiment, the relative criteria for an alert may vary depending on other data or information, such as the process stage, the type of product being processed by the equipment, ambient temperature and humidity, external vibrations from other equipment, etc. In an illustrative and non-limiting example, the response circuit 8710 may initiate an alert if the vibration amplitude and/or frequency exceeds a predetermined maximum value, if there is a change or rate of change that exceeds a predetermined tolerance, and/or if an accumulated value based on the vibration amplitude and/or frequency exceeds a threshold.

In embodiments, the response circuit 8710 may cause the data acquisition circuit 8704 to enable or disable processing of detection values corresponding to particular sensors based on some of the criteria described above. This may include switching to a sensor with a different response speed, sensitivity, range, etc., accessing a new sensor or sensor type, etc. This switching may be performed by changing the control signal of the multiplexer circuit 8736 and/or turning on or off particular inputs of the multiplexer circuit 8736. The response circuit 8710 may also recommend future replacement of a particular sensor with a sensor having a different response speed, sensitivity, range, etc. The response circuit 8710 may also recommend design changes for future embodiments of components, equipment, operating conditions, processes, etc.

In an embodiment, the response circuit 8710 may recommend maintenance or initiate a maintenance call during an upcoming process shutdown. The response circuit 8710 may recommend changes to process or operating parameters to remotely balance a piece of equipment. In an embodiment, the response circuit 8710 may implement or recommend process changes, for example, to reduce the utilization of a component that is approaching a maintenance interval, operating off-normally, or has failed but is still at least partially operational for its intended purpose. In an illustrative example, vibration phase information derived by the phase detection circuit 8712 relative to a timer signal from the timer circuit 8714 can indicate the physical location of the problem. Based on the vibration phase information, system design flaws, off-nominal operation, and/or component or process malfunctions may be identified.

In embodiments, based on associated operating conditions and/or failure modes that may occur as sensor values approach one or more criteria, the signal evaluation circuit 8708 may store data in the data storage circuit 8716 based on the data's conformance to one or more criteria. The signal evaluation circuit 8708 may store additional data, such as RPM, component load, temperature, pressure, vibration, etc., in the data storage circuit 8716 based on one sensor input meeting or approaching a specified criterion or range. The signal evaluation circuit 8708 may store data at a higher data rate to allow for greater granularity in future processing, the ability to reprocess at different sampling rates, and/or to enable diagnostics or post-processing of system information where operating data of interest has been flagged.

62 and 63 and 64 and 65, the data monitoring system 8762 may include at least one data monitoring device 8768. The at least one data monitoring device 8768 may include a sensor 8706 and a controller 8770 including a data acquisition circuit 8704, a signal evaluation circuit 8772, a data storage circuit 8742, and a communications circuit 8752 to enable transmission of data and analysis to a monitoring application 8776 on a remote server 8774. The signal evaluation circuit 8772 may include at least one of a phase detection circuit 8712 and an atimer circuit 8714. The signal evaluation circuit 8772 may periodically share data with the communications circuit 8752 for transmission to the remote server 8774 to enable the monitoring application 8776 to track performance of components and equipment over time and under changing conditions. Because sensor values approaching one or more criteria may indicate associated operating conditions and/or failure modes, the signal evaluation circuit 8708 may share data with the communications circuit 8752 for transmission to a remote server 8774 based on the data's conformance to one or more criteria. Based on one sensor input meeting or approaching a specified criterion or range, the signal evaluation circuit 8708 may share additional data for transmission, such as rotational speed, component load, temperature, pressure, vibration, etc. The signal evaluation circuit 8772 may share and transmit data at a higher data rate to allow for greater granularity in processing at the remote server.

In embodiments, as shown in FIG. 62, the communications circuitry 8752 may communicate data directly to a remote server 8774. In embodiments, as shown in FIG. 63, the communications circuitry 8752 may communicate data to an intermediate computer 8754 including a processor 8756 executing an operating system 8758 and a data storage circuit 8760. The intermediate computer 8754 may collect data from multiple data monitoring devices and transmit the accumulated data to the remote server 8774.

In embodiments such as those shown in FIGS. 64 and 65, the data collection system 8762 may have multiple monitoring devices 8768 collecting data for multiple components within a single piece of equipment, may collect data for the same component across multiple pieces of equipment (both the same and different types of equipment) within the same facility, or may collect data from monitoring devices within multiple facilities. In embodiments, as shown in FIG. 64, the communications circuitry 8752 may communicate data directly to a remote server 8774. In embodiments, as shown in FIG. 65, the communications circuitry 8752 may communicate data to an intermediate computer 8754 including a processor 8756 executing an operating system 8758 and a data storage circuitry 8760. The intermediate computer 8754 may collect data from multiple data monitoring devices and transmit the accumulated data to the remote server 8774.

In an embodiment, a monitoring application 8776 on the remote server 8774 may receive and store one or more of the detected values, timing signals, and data from multiple, various monitoring devices 8768. The monitoring application 8776 may then select subsets of the detected values, timing signals, and data to jointly analyze. The subsets for analysis may be selected based on a single type of component or a single type of equipment on which the components are operating. The subsets for analysis may also be selected or grouped based on common operating conditions, such as load magnitude, operating conditions (intermittent, continuous, process stage, etc.), operating speed or tachometer, common ambient environmental conditions such as humidity, temperature, air or fluid particulates, etc. The subsets for analysis may be selected based on the influence of other nearby equipment, such as nearby machinery rotating at a similar frequency.

The monitoring application 8776 may then analyze the selected subset. In an illustrative example, data from one component may be analyzed over different time periods, such as one operating cycle, multiple operating cycles, one month, one year, or the life of the component. Data from multiple parts of the same type may also be analyzed over different time periods. Trends in the data, such as changes in frequency or amplitude, may be correlated with records of failures or maintenance associated with the same part or related equipment. Trends in the data, such as rates of change associated with startup or different points in the process, may also be identified. Additional data may be introduced into the analysis, such as data indicating the quality of the output product or the success or failure of the process. Correlations between trends and values of different types of data may be analyzed, and short-term analysis may identify parameters that provide the best predictions regarding expected performance. This information may be sent to the monitoring device to update the types of data collected and analyzed locally and to influence future monitoring device design.

In an illustrative and non-limiting example, the monitoring device 8768 may be used to collect and process sensor data to measure mechanical torque. The monitoring device 8768 may communicate with or include a high-resolution, high-speed vibration sensor to collect data over a period of time sufficient to measure multiple cycles of rotation. For gear-driven components, the sensor's sampling resolution should be such that the number of samples per cycle is at least equal to the number of gears driving the component. It is understood that lower sampling resolution may result in less reliable determinations or that data may be acquired over a longer period of time to provide sufficient statistical reliability. This data may be used to generate an equipment phase reference (relative probe) or tachometer signal. This phase reference may be used directly or by the timer circuit 8714 to generate phase data, such as vibration or acceleration data, aligned with timing signals from multiple sensors located at different locations on the component or on different components in a system. This information may facilitate determining torque for different components or generating an operational deflection shape (ODS).

Higher resolution data streams can also provide additional data for detecting transient signals in slow-speed operation. Identifying transient signals may help identify defects in equipment or components operating at low RPMs.

In an illustrative and non-limiting example, a monitoring device can be used to identify mechanical jitter for use in failure prediction models. The monitoring device can begin acquiring data as the equipment starts up, ramps up to operating speed, and during operation. Once operating speed is reached, torsional jitter is expected to be minimal or within expected limits; changes in torsion at this stage may indicate cracks, bearing defects, etc. Additionally, known torsions can be removed from the signal to help identify unexpected torsions resulting from system design flaws, component wear, or unexpected process events. Having phase information associated with data collected at operating speed may facilitate identifying the location of vibrations and potential component wear, and/or further correlate to component failure types. Relative phase information from multiple sensors located throughout the machine can facilitate evaluation of torsion propagating within the equipment.

In embodiments, the monitoring application 8776 may access equipment specifications, equipment geometries, component specifications, component materials, predicted state information for multiple component types, operating history, past sensing values, component life models, etc., for use in analyzing the selected subset using rule-based or model-based analysis. In embodiments, the monitoring application 8776 may provide the selected subset to a neural net that learns to recognize various operating conditions, health conditions (e.g., life predictions), and fault conditions using deep learning techniques. In embodiments, a hybrid of the two techniques (model-based learning and deep learning) may be used.

By way of illustrative and non-limiting example, the health of components such as conveyors and lifters on assembly lines, water pumps on industrial vehicles, air conditioning units in factories, drilling machines, screwdrivers, compressors, pumps, gearboxes, vibrating conveyors, mixers, and motors in oil and gas fields, mineral pumps, centrifuges, refining tanks in oil and gas refinery factories, and compressors in gas processing systems can be monitored using the phase detection and adjustment techniques, data monitoring devices, and data collection systems described herein.

In an illustrative and non-limiting example, the component health of equipment facilitating chemical reactions (e.g., rotating tank/mixer agitators, mechanical/rotary agitators, and propeller agitators) deployed in chemical and pharmaceutical production lines can be assessed using the phase detection and alignment techniques, data monitoring devices, and data collection systems described herein.

In an illustrative and non-limiting example, the health of vehicle steering mechanisms and/or vehicle engine components can be assessed using the phase detection and alignment techniques, data monitoring devices, and data acquisition systems described herein.

An exemplary monitoring system for data collection includes a data acquisition circuit configured to interpret a plurality of detected values, each of the plurality of detected values corresponding to at least one of a plurality of input sensors communicatively coupled to the data acquisition circuit; a signal evaluation circuit including a timer circuit configured to generate at least one timing signal; a phase detection circuit structured to determine a relative phase difference between at least one of the plurality of detected values and at least one of the timing signals from the timer circuit; and a response circuit structured to perform at least one action in response to the relative phase difference.

In certain further embodiments, the exemplary system further includes: at least one action taken in response to at least one of a change in amplitude of at least one of the plurality of detected values; a change in frequency or relative phase of at least one of the plurality of detected values; a rate of change of both the amplitude and relative phase of at least one of the plurality of detected values; and a relative rate of change of the amplitude and relative phase of at least one of the plurality of detected values; where the at least one action issues an alarm, the alarm may be one of tactile, audible, and visual; a data storage circuit in which at least one of the relative phase difference, the detected value, and the timing signal is stored; and where the at least one action further includes storing additional data in the data storage circuit, the storing the additional data in the data storage circuit being further responsive to at least one of a change in the relative phase difference and a relative rate of change of the relative phase difference. the data acquisition circuitry further includes at least one multiplexer circuit (MUX) from which alternative combinations of sensed values can be selected based on at least one of a user input and a selected operating parameter of the machine; each of the plurality of sensed values corresponds to at least one of the input sensors, and the at least one operation comprises enabling or disabling one or more portions of the multiplexer circuit or modifying a multiplexer control line; the data acquisition circuitry includes at least two multiplexer circuits, and the at least one operation comprises modifying a connection between the at least two multiplexer circuits; and/or the system further includes a MUX control circuit configured to interpret a subset of the plurality of sensed values and provide logical control of the MUX and the resulting correspondence between the MUX inputs and the sensed values, the logical control of the MUX comprising adaptive scheduling of the selection lines.

An exemplary system for data collection includes a data acquisition circuit configured to interpret a plurality of detected values, each of the plurality of detected values corresponding to at least one of a plurality of input sensors communicatively coupled to the data acquisition circuit; a signal evaluation circuit including a timer circuit configured to generate a timing signal based on a first detected value of the plurality of detected values and a phase detection circuit configured to determine a relative phase difference between a second detected value of the plurality of detected values and the timing signal; and a phase response circuit configured to perform at least one action in response to the phase difference. In certain further embodiments, the exemplary system includes: where the at least one action is further performed in response to at least one of a change in amplitude of at least one of the plurality of detected values; a change in frequency or relative phase of at least one of the plurality of detected values; a rate of change of both the amplitude and relative phase of at least one of the plurality of detected values; and a relative rate of change of the amplitude and relative phase of at least one of the plurality of detected values; where the at least one action includes issuing an alarm, the alarm may be one of tactile, audible, and visual; where the system further includes a data storage circuit, where at least one of the relative phase difference, the detected value, and the timing signal is stored; where the at least one action further includes storing additional data in the data storage circuit, where storing the additional data in the data storage circuit is further in response to at least one of a change in the relative phase difference and a relative rate of change of the relative phase difference. the data acquisition circuitry further includes at least one multiplexer (MUX) circuit from which alternative combinations of sensed values can be selected based on at least one of a user input and a selected operating parameter of the machine; each of the plurality of sensed values corresponds to at least one of the input sensors; the at least one action includes enabling or disabling one or more portions of the multiplexer circuit or modifying a multiplexer control line; the data acquisition circuitry includes at least two multiplexer circuits and the at least one action includes modifying a connection between the at least two multiplexer circuits; the system further includes a MUX control circuit configured to interpret a subset of the plurality of sensed values and provide logical control of the MUX and the resulting correspondence between the MUX inputs and the sensed values; and/or the logical control of the MUX comprises adaptive scheduling of select lines.

An exemplary system for data collection, processing, and utilization of signals in an industrial environment includes a data acquisition circuit configured to interpret a plurality of detected values, each of the plurality of detected values corresponding to at least one of a plurality of input sensors communicatively coupled to the data acquisition circuit; a signal evaluation circuit including a timer circuit configured to generate a timing signal based on a first detected value of the plurality of detected values and a phase detection circuit configured to determine a relative phase difference between a second detected value of the plurality of detected values and the timing signal; a data storage device that stores a subset of the plurality of detected values and the timing signal; a communication circuit configured to communicate at least one selected detected value and the timing signal to a remote server; and a monitoring application on the remote server configured to receive the at least one selected detected value and the timing signal, and collaboratively analyze the subset of detected values received from the plurality of monitoring devices and recommend an action. In certain embodiments, the exemplary system includes where the collaborative analysis aligns the detection values from the multiple monitoring devices using timing signals from each of the multiple monitoring devices, and/or where the subset of detection values is selected based on data associated with the detection values including at least one of a common type of part, a common type of equipment, and a common operating condition.

An exemplary system for collecting data in an industrial environment includes: a data acquisition circuit configured to interpret a plurality of detected values, each of the plurality of detected values corresponding to at least one of a plurality of input sensors communicatively coupled to the data acquisition circuit; a multiplexer circuit capable of selecting alternative combinations of the detected values based on at least one of a user input, a detected state, and a selected operating parameter of the machine, each of the plurality of detected values corresponding to at least one of the input sensors; a signal evaluation circuit including a timer circuit configured to generate a timing signal and a phase detection circuit configured to determine a relative phase difference between at least one of the plurality of detected values and a signal from the timer circuit; and a response circuit configured to perform at least one action in response to the phase difference.

An exemplary monitoring system for collecting data in equipment includes: a data acquisition circuit configured to interpret a plurality of detected values, each of the plurality of detected values corresponding to at least one of a plurality of input sensors communicatively coupled to the data acquisition circuit; a phase detection circuit that determines a relative phase difference between a second of the plurality of detected values and the timing signal, the phase detection circuit including a timer circuit configured to generate the timing signal based on a first of the plurality of detected values; and a signal evaluation circuit configured to obtain at least one of a vibration amplitude, a vibration frequency, and a vibration phase position corresponding to the second detected value; and a response circuit that performs at least one action in response to the position of at least one of the vibration amplitude, the vibration frequency, and the vibration phase.

A monitoring device for analyzing bearings in an industrial environment includes: a data acquisition circuit configured to interpret a plurality of detected values, each of the plurality of detected values corresponding to at least one of a plurality of input sensors communicatively coupled to the data acquisition circuit; a timer circuit configured to generate a timing signal; a data storage device that stores specifications and expected condition information for a plurality of bearing types and buffers the plurality of detected values for a predetermined period of time; a timer circuit configured to generate a timing signal based on a first detected value of the plurality of detected values; a bearing analysis circuit configured to analyze the buffered detected value in relation to the specifications and expected condition information to perform a life prediction, the bearing analysis circuit including a phase detection circuit configured to determine a relative phase difference between a second detected value of the plurality of detected values and the timing signal; and a signal evaluation circuit that obtains at least one of a vibration amplitude, a vibration frequency, and a vibration phase position corresponding to the second detected value; and a response circuit that performs at least one operation in response to at least one of the vibration amplitude, the vibration frequency, and the vibration phase position.

In embodiments, information regarding the health or other status or condition of components or portions of industrial equipment can be obtained by monitoring the condition of various components throughout a process. Monitoring may include monitoring the amplitude of sensor signals measuring attributes such as temperature, humidity, acceleration, and displacement. One embodiment of a data monitoring device 9000 is shown in FIG. 66 and may include multiple sensors 9006 communicatively coupled to a controller 9002. The controller 9002, which may be part of a data collection device such as a mobile data collector or part of a system such as a network-deployed or cloud-deployed system, may include a data acquisition circuit 9004, a signal evaluation circuit 9008, and a response circuit 9010. The signal evaluation circuit 9008 may include a peak detection circuit 9012. Additionally, the signal evaluation circuit 9008 may optionally include one or more of a phase detection circuit 9016, a bandpass filter circuit 9018, a phase-locked loop circuit, a torsion analysis circuit, a bearing analysis circuit, etc. A bandpass filter 9018 may be used to filter the stream of detected values so that values, such as peaks and valleys, are detected only at or within a band of interest, such as a frequency of interest. The data acquisition circuit 9004 may include one or more analog-to-digital converter circuits 9014. The peak amplitudes detected by the peak detection circuit 9012 may be input to one or more analog-to-digital conversion circuits 9014 to provide a reference value for appropriately scaling the output of the analog-to-digital conversion circuit 9014.

The plurality of sensors 9006 may be wired to ports of the data acquisition circuitry 9004. Alternatively, the plurality of sensors 9006 may be wirelessly connected to the data acquisition circuitry 9004. The data acquisition circuitry 9004 may have access to a sensed value corresponding to the output of at least one of the plurality of sensors 9006, where the sensor 9006 may acquire data regarding different operational aspects of a portion or operating component of a device.

The selection of multiple sensors 9006 for a data monitoring device 9000 designed for a particular component or piece of equipment may depend on various considerations, such as accessibility to install new sensors, incorporation of sensors in the initial design, expected operating and fault conditions, desired resolution at various locations within the process or plant, sensor reliability, power availability, power utilization, storage utilization, etc. The impact of failure, time response of failure (e.g., warning time and/or suboptimal modes occurring prior to failure), likelihood of failure, severity of failure impact, and/or sensitivity and/or difficulty required to detect a fault condition may dictate the extent to which more sensors and/or higher performance sensors are used to monitor the component or equipment, specializing in systems where unexpected or undetected failures can be costly or severe.

The signal evaluation circuit 9008 may process the detected values to obtain information about the monitored component or equipment. The information extracted by the signal evaluation circuit 9008 may consist of information about the signal's peak values, such as peak temperature, peak acceleration, peak velocity, peak pressure, peak load capacity, peak strain, peak bending, and peak displacement. Peak detection may be performed using analog or digital circuitry. In embodiments, the peak detection circuit 9012 may be able to distinguish between "local" or short-term peaks and "global" or long-term peaks in the detected value stream. In embodiments, the peak detection circuit 9012 may be able to identify peak shapes (not just a single peak value), such as flat tops, asymptotic approaches, discrete jumps in peak values or rapid/abrupt rises in peak values, and sinusoidal behavior within a range. A flat-top peak may indicate sensor saturation. Asymptotic approaches to a peak indicate linear system behavior. Discrete jumps in value or sudden changes in peak values may indicate quantized or nonlinear behavior of the sensor or component making the measurements. In embodiments, the system may identify sinusoidal variations in peak values within an envelope, such as an envelope established by a line or curve connecting a series of peak values. Note that a "peak" should be understood to encompass one or more "valleys" representing a series of lower measured values, unless the context indicates otherwise.

In an embodiment, the peak value may be used as a reference for the analog-to-digital conversion circuit 9014.

In an illustrative and non-limiting example, a temperature probe may measure the temperature of a gear rotating within a machine. The peak temperature may be detected by peak detection circuitry 9012. The peak temperature may be provided to analog-to-digital conversion circuitry 9014 for appropriate scaling of a stream of readings corresponding to the temperature measurements of the gear rotating within the machine. The phase of the stream of readings corresponding to the temperature relative to the orientation of the gear may be determined by phase detection circuitry 9016. Knowing where the temperature peak occurs during the gear's rotation may allow identification of a faulty gear tooth.

In embodiments, two or more sets of detected values may be fused to create detected values for a virtual sensor. Peak detection circuitry may be used to verify consistency in peak timing between at least one of the two or more sets of detected values and the detected values for the virtual sensor.

In an embodiment, the signal evaluation circuit 9008 may be capable of resetting the peak detection circuit 9012 upon startup of the monitoring device 9000, upon edge detection of a control signal from the monitored system, based on user input, after a system error, etc. In an embodiment, the signal evaluation circuit 9008 may discard an initial portion of the output of the peak detection circuit 9012 before using the peak value as a reference value for the analog-to-digital conversion circuit to allow full system startup.

Depending on the type of equipment, the component being measured, the environment in which the equipment operates, etc., the sensor 9006 may comprise one or more of, but is not limited to, a vibration sensor, a thermometer, a hygrometer, a voltage sensor, a current sensor, an accelerometer, a speed detector, an optical or electromagnetic sensor (e.g., for determining temperature, composition, and/or spectral analysis, and/or the position or movement of an object), an image sensor, a structured light sensor, a laser-based image sensor, an acoustic wave sensor, a displacement sensor, a turbidity meter, a viscometer, a load sensor, a triaxial sensor, an accelerometer, a tachometer, a fluid pressure gauge, a thermometer, a hygrometer, an ammeter, an accelerometer, a speedometer, a vibration sensor, a thermometer, a hygrometer, an ammeter, an accelerometer, a speedometer, an optical sensor, an electromagnetic sensor (e.g., for determining temperature, composition, and/or spectral analysis, and/or the position or movement of an object), an image sensor, a structured light sensor, a laser-based image sensor, an acoustic wave sensor, a displacement sensor, a turbidity meter, a viscometer, a load sensor, a triaxial sensor, an accelerometer, a tachometer, a fluid pressure gauge, a thermometer, a hygrometer, an ammeter, an accelerometer, a speedometer, a vibration meter, a thermometer, a hygrometer, an ammeter, an accelerometer, a speedometer, an optical sensor, an electromagnetic sensor (e.g., for determining temperature, composition, spectral analysis, the position or movement of an object, etc.). These include, but are not limited to, any of the sensors described in this disclosure and references, such as turbidity meters, viscometers, load cells, triaxial sensors, accelerometers, tachometers, fluid pressure meters, air flow meters, horsepower meters, flow meters, fluid particle detectors, acoustic sensors, and pH sensors.

Sensor 9006 may provide a stream of data over time having a phase component, such as that associated with acceleration or vibration, allowing for evaluation of phase or frequency analysis of different operational aspects of a portion or operating part of a device. Sensor 9006 may also provide a stream of data without a traditional phase component, such as temperature, humidity, load, etc. Sensor 9006 may provide a continuous or near-continuous stream of data over time, periodic readings, event-driven readings, and/or readings according to a selected interval or schedule.

In embodiments, as illustrated in FIG. 66, the sensor 9006 may be part of a data monitoring device 9000, sometimes referred to herein as a data collector, which may sometimes constitute a mobile or portable data collector. In embodiments, as shown in FIGS. 67 and 68, one or more external sensors 9026 that are not explicitly part of the monitoring device 9020, but rather are previously attached to or integrated into a new device or component, may be opportunistically connected to or accessed by the monitoring device 9020. The monitoring device 9020 may include a controller 9022. The controller 9022 may include a response circuit 9010, a signal evaluation circuit 9008, and a data acquisition circuit 9024. The signal evaluation circuit 9008 may include a peak detection circuit 9012 and, optionally, a phase detection circuit 9016 and/or a bandpass filter circuit 9018. The data acquisition circuit 9024 may include one or more input ports 9028. The one or more external sensors 9026 may be directly connected to one or more input ports 9028 on the data acquisition circuit 9024 of the controller 9022, or may be accessed wirelessly by the data acquisition circuit 9024 via a reader, interrogator, or other wireless connection, such as over a short-range wireless protocol. In embodiments such as that shown in FIG. 68, the data acquisition circuit 9024 may further include a wireless communication circuit 9030. The data acquisition circuit 9024 may use the wireless communication circuit 9030 to access the sensed values corresponding to the one or more external sensors 9026 wirelessly, via another source, or some combination of these methods.

In an embodiment such as that shown in FIG. 69, the data acquisition circuit 9036 may further include a multiplexer circuit 9038, as described elsewhere herein. The output from the multiplexer circuit 9038 may be utilized by the signal evaluation circuit 9008. The response circuit 9010 may have the ability to turn portions of the multiplexer circuit 9038 on and off. The response circuit 9010 may also have the ability to control the control channel of the multiplexer circuit 9038.

The response circuit 9010 may evaluate the results of the signal evaluation circuit 9008 and initiate action based on certain criteria. Criteria may include a predetermined peak value of a detection value from a particular sensor, the cumulative value of the corresponding detection value of the sensor over time, the change in the peak value, the rate of change of the peak value, and/or cumulative values (e.g., time spent above/below a threshold, weighted time spent above/below one or more thresholds, and/or area of the detection value spent above/below one or more thresholds). Criteria may consist of a combination of data from different sensors, such as relative values, relative change in values, relative rate of change in values, or relative values over time. Relative criteria may vary depending on other data or information, such as the stage of the process, the type of product being processed, the type of equipment, ambient temperature and humidity, external vibrations from other equipment, etc. Relative criteria may be reflected in one or more calculated statistics or metrics (including those generated below). These data may be processed (either on-board the data collector or by an external system) and provided as input to one or more machine learning functions described in this disclosure, provided as input to a control system (e.g., on-board the data collector or remotely located, which controls data input selection, sensor data multiplexing, storage, etc.), or provided as data elements that become input to another system, such as a data stream or data package available to systems like a data marketplace, SCADA system, remote control system, maintenance system, analytics system, etc.

While certain embodiments are described herein as having detected values exceeding a threshold or predetermined value, the detected value may be below the threshold or predetermined value, e.g., indicating that a change in the detected value is expected to occur but the detected value may not have occurred. For example, without limitation, vibration data may indicate a system's agitation level, properly operating equipment, etc., and vibration data below an amplitude and/or frequency threshold may indicate a process that is not operating as expected. For example, in a process involving a blender, mixer, agitator, etc., a lack of vibration may indicate that a working element, such as a blade, fin, or vane, is not moving sufficiently. Examples include when the working material is excessively viscous or when there are gear issues (e.g., stripped gears, seized gears, etc.) (e.g., clutch). Unless the context clearly indicates otherwise, statements herein describing determining a value above a threshold and/or determining a value above a predetermined or expected value shall be understood to include determining a value below the threshold and/or determining a value below the predetermined or expected value.

The predetermined tolerance range may be based on the expected system response or vibration based on the equipment's geometry and control method, such as the number of bearings, relative rotational speed, or power flow into the system at a certain frequency. The predetermined tolerance range may also be set by analyzing the detected values of multiple similar devices or components over a long period of time and taking into account correlations with equipment failures.

In an embodiment, the response circuit 9010 may issue an alarm based on one or more of the criteria described above. In an illustrative example, an increase in peak temperature above a predetermined value may indicate a hot bearing beginning to fail. In an embodiment, the relative criteria for an alarm may vary depending on other data or information, such as the process stage, the type of product being processed by the equipment, the ambient temperature and humidity, external vibrations from other equipment, etc. In an illustrative and non-limiting example, the response circuit 9010 may initiate an alarm if the amplitude, such as vibration amplitude and/or frequency, exceeds a predetermined maximum value, if there is a change or rate of change that exceeds a predetermined tolerance, and/or if an accumulated value based on such amplitude and/or frequency exceeds a threshold.

In embodiments, the response circuitry 9010 may cause the data acquisition circuitry 9004 to enable or disable processing of a detection value corresponding to a particular sensor based on one or more of the criteria described above. This may include switching to a sensor with a different response speed, sensitivity, range, etc., accessing a new sensor or type of sensor, accessing data from multiple sensors, etc. The switching may be based on detecting a peak value from the sensor being switched to or a peak value from another sensor. The switching may be based on a model, a set of rules, etc. In embodiments, the switching is under the control of a machine learning system, where the switching is controlled based on one or more success metrics combined with input data over a series of trials, and may occur under the supervision of a human supervisor or under the control of an automated system. The switching may include switching from one input port to another input port (e.g., switching from one sensor to another). The switching may include changing the multiplexing of data, such as combining different streams under different conditions. The switching may include triggering the system to acquire additional data. For example, a mobile system (such as a robotic or drone system) may be moved to a location where different or additional data is available (such as positioning an image sensor for a different view or a sonar sensor for a different collection direction) or where different sensors are accessible (such as moving a collector to connect to sensors located at different locations in the environment via wired or wireless connections). This switching may be accomplished by changing the control signal of the multiplexer circuit 9038 and/or by turning certain inputs of the multiplexer circuit 9038 on or off.

In an embodiment, the response circuit 9010 may use the detected peak as a reference voltage to adjust the scaling value of the sensor. The response circuit 9010 may also adjust the sampling rate of the sensor so that the peak value is captured.

The response circuitry 9010 may identify sensor overloads. In embodiments, the response circuitry 9010 may make recommendations for future replacement of a particular sensor with a sensor having a different response speed, sensitivity, range, etc. The response circuitry 9010 may also recommend design changes for future embodiments of components, equipment, operating conditions, processes, etc.

In embodiments, the response circuitry 9010 may recommend maintenance or initiate a maintenance call during a future process shutdown, which may include replacing a sensor with the same or an alternative type of sensor having a different response speed, sensitivity, range, etc. In embodiments, the response circuitry 9010 may implement or recommend a process change, such as reducing the utilization of a component that is approaching a maintenance interval, operating informally, or has failed but is at least partially operational for its intended purpose, changing the operating speed of a component (e.g., placing it in a low-demand mode), initiating a remediation of the problem (e.g., signaling additional lubrication of a roller bearing set or signaling an alignment process for an out-of-balance system), etc.

In an embodiment, as shown in FIG. 70, the data monitoring device 9040 may include a sensor 9006, a data acquisition circuit 9004, and a controller 9042 that may include a signal evaluation circuit 9008. The signal evaluation circuit 9008 may include a peak detection circuit 9012 and, optionally, a phase detection circuit 9016 and/or a bandpass filter circuit 9018. The controller 9042 may further include a data storage circuit 9044, memory, etc. The controller 9042 may further include a response circuit 9010. The signal evaluation circuit 9008 may periodically store certain detected values in the data storage circuit 9044 to enable tracking of component performance over time.

In embodiments, the signal evaluation circuit 9008 may store data in the data storage circuit 9044 based on the data's conformance to one or more criteria, as described throughout this disclosure, based on associated criteria as described elsewhere herein, operating conditions and/or failure modes that may occur when sensor values approach one or more criteria. Based on one sensor input meeting or approaching a specified criterion or range, the signal evaluation circuit 9008 may store additional data in the data storage circuit 9068, such as RPM, component load, temperature, pressure, vibration, or other sensor data of the type described throughout this disclosure. The signal evaluation circuit 9008 may store data at a higher data rate to allow for greater granularity in future processing, the ability to reprocess at different sampling rates, and/or to enable diagnostics or post-processing of system information where operational data of interest has been flagged.

In embodiments, the signal evaluation circuitry 9008 may store new peaks that indicate changes in overall scaling over a long period of time (e.g., scaling the data stream based on historical peaks from months of analysis). The signal evaluation circuitry 9008 may also store data when historical peak values are approaching (e.g., when temperature, pressure, vibration, velocity, acceleration, etc., approach historical peaks).

In embodiments such as those shown in FIGS. 71 and 72 and 73 and 74, the data monitoring system 9046 may include at least one data monitoring device 9048. The at least one data monitoring device 9048 may include a sensor 9006 and a controller 9050 comprising a data acquisition circuit 9004, a signal evaluation circuit 9008, a data storage circuit 9044, and a communication circuit 9052 that enables data and analysis to be transmitted to a monitoring application 9056 on a remote server 9054. The signal evaluation circuit 9008 may include at least one peak detection circuit 9012. The signal evaluation circuit 9008 may periodically share data with the communication circuit 9052 and transmit it to the remote server 9054, enabling the monitoring application 9056 to track the performance of components or equipment over time and under various conditions. Because relevant operating conditions and/or failure modes may occur when sensor values approach one or more criteria, as described elsewhere herein, the signal evaluation circuit 9008 may share data with the communications circuit 9052 for transmission to the remote server 9054 based on the data's conformance to one or more criteria. Based on one sensor input meeting or approaching a specified criterion or range, the signal evaluation circuit 9008 may share additional data, such as RPM, component load, temperature, pressure, vibration, etc., for transmission. The signal evaluation circuit 9008 may also share and transmit data at a higher data rate to increase the granularity of processing at the remote server.

In embodiments, as shown in FIG. 71, the communications circuitry 9052 may communicate data directly to a remote server 9054. In embodiments, as shown in FIG. 72, the communications circuitry 9052 may communicate data to an intermediate computer 9058, which may include a processor 9060 executing an operating system 9062 and data storage circuitry 9064.

In embodiments, as shown in FIGS. 73 and 74, the data collection system 9066 may have multiple monitoring devices 9048 collecting data for multiple components within a single device, may collect data for the same component across multiple devices (both the same and different types) within the same facility, or may collect data from monitoring devices in multiple facilities. A monitoring application 9056 on the remote server 9054 may receive and store one or more of the sensing values, timing signals, or data from the multiple, various monitoring devices 9048.

In embodiments, as shown in FIG. 71, the communications circuitry 9052 may communicate data directly to a remote server 9054. In embodiments, as shown in FIG. 72, the communications circuitry 9052 may communicate data to an intermediate computer 9058 including a processor 9060 executing an operating system 9062 and a data storage circuit 9064. There may be an individual intermediate computer 9058 associated with each monitoring device 9048, or an individual intermediate computer 9058 may be associated with multiple monitoring devices 9048, and the intermediate computer 9058 may collect data from the multiple data monitoring devices and transmit the accumulated data to the remote server 9054.

The monitoring application 9056 may select subsets of sensed values, timing signals, and data for joint analysis. The subsets for analysis may be selected based on a single type of component or a single type of equipment on which the components are operating. The subsets for analysis may be selected or grouped based on common operating conditions, such as load size, operating conditions (e.g., intermittent, continuous), operating speed or tachometer, common ambient environmental conditions such as humidity, temperature, air or fluid particulates, etc. The subsets for analysis may also be selected based on the influence of other peripheral equipment, such as equipment rotating at a similar frequency, generating electromagnetic fields, generating heat, inducing motion or vibration, or emitting vapors, chemicals, or particulates.

The monitoring application 9056 may then analyze the selected subset. In an illustrative example, data from a single component may be analyzed over different time periods, such as one operating cycle, several operating cycles, one month, one year, or the life of the component. Data from multiple parts of the same type may also be analyzed over different time periods. Trends in the data, such as changes in frequency or amplitude, may be correlated with records of failures or maintenance associated with the same or related parts or equipment. Trends in the data may be identified, such as rates of change associated with startup or different points in the process. Additional data, such as output product quality, output volume (e.g., per unit time), or process success or failure, may also be introduced into the analysis. Trends and value correlations between different types of data may be analyzed to identify parameters for which short-term analysis may provide the best prediction of expected performance. This information may be transmitted to the monitoring device to update the types of data collected and analyzed locally or to influence future monitoring device design.

In embodiments, the monitoring application 9056 may access equipment specifications, equipment geometries, component specifications, component materials, expected state information for multiple component types, operating history, past detection values, component life models, etc., to analyze the selected subset using rule-based or model-based analysis. In embodiments, the monitoring application 9056 may feed the selected subset into a neural net that learns to recognize peaks in waveform patterns by feeding it large dataset samples of a given type of waveform behavior where the peaks have been designated (e.g., by a human analyst).

A monitoring system for collecting data in an industrial environment, the monitoring system including: a data acquisition circuit configured to interpret a plurality of detected values from a plurality of input sensors communicatively coupled to the data acquisition circuit, each of the plurality of detected values corresponding to at least one of the input sensors; a peak detection circuit configured to determine at least one peak value in response to the plurality of detected values; and a peak response circuit configured to perform at least one action in response to the at least one peak value.

An exemplary monitoring system includes: at least one action further performed in response to at least one of a change in amplitude of at least one of the plurality of detected values; a change in frequency or relative phase of at least one of the plurality of detected values; a rate of change in both the amplitude and relative phase of at least one of the plurality of detected values; and a relative rate of change in the amplitude and relative phase of at least one of the plurality of detected values; if the at least one action includes issuing an alarm, the alarm may be one of tactile, audible, or visual; and if the at least one action further includes storing additional data in the data storage circuit, the data storage circuit may store the relative phase difference and at least one of the detected values and the timing signal. The storing of the data further includes when the data acquisition circuitry is responsive to at least one of a change in the relative phase difference and a relative rate of change of the relative phase difference; when the data acquisition circuitry further has at least one multiplexer circuit capable of selecting alternative combinations of sensed values based on at least one of a user input and a selected operating parameter of the machine; when each of the plurality of sensed values corresponds to at least one of the input sensors; when the at least one operation includes enabling or disabling one or more portions of the multiplexer circuit or modifying a multiplexer control line; when the data acquisition circuitry includes at least two multiplexer circuits and when the at least one operation includes modifying a connection between the at least two multiplexer circuits.

A monitoring system for collecting data in an industrial environment configured to receive inputs corresponding to a plurality of sensors includes: a data acquisition circuit configured to interpret a plurality of detected values, each of the plurality of detected values corresponding to at least one of the input sensors; a peak detection circuit configured to determine at least one peak value in response to the plurality of detected values; and a peak response circuit configured to perform at least one action in response to the at least one peak value.

The exemplary monitoring system further includes: if at least one action is further performed in response to at least one of a change in amplitude of at least one of the plurality of detection values, a change in frequency or relative phase of at least one of the plurality of detection values, a rate of change in both the amplitude and relative phase of at least one of the plurality of detection values, and a relative rate of change in the amplitude and relative phase of at least one of the plurality of detection values; if the at least one action includes issuing an alarm, the alarm may be tactile, auditory, or visual; if the system further includes a data storage circuit, the data storage circuit stores the relative phase difference and at least one of the detection values and the timing signal; if the at least one action further includes storing additional data in the data storage circuit, the data storage circuit stores the additional data; The storing of the data further includes: when the data acquisition circuitry is responsive to at least one of a change in the relative phase difference and a relative rate of change of the relative phase difference; when the data acquisition circuitry further has at least one multiplexer circuit capable of selecting alternative combinations of detected values based on at least one of a user input and a selected operating parameter of the machine; when each of the plurality of detected values corresponds to at least one of the input sensors; when the at least one operation includes enabling or disabling one or more portions of the multiplexer circuit or modifying a multiplexer control line; when the data acquisition circuitry includes at least two multiplexer circuits and when the at least one operation includes modifying a connection between the at least two multiplexer circuits.

An exemplary system for data collection, processing, and utilization of signals in an industrial environment includes a plurality of monitoring devices, each monitoring device including a data collection circuit configured to interpret a plurality of detected values from a plurality of input sensors communicatively coupled to the data collection circuit, each of the plurality of detected values corresponding to at least one of the input sensors; a peak detection circuit configured to determine at least one peak value in response to the plurality of detected values; a peak response circuit configured to select at least one detected value in response to the at least one peak value; a communication circuit configured to communicate the at least one selected detected value to a remote server; and a monitoring application on the remote server configured to receive the at least one selected detected value, collaboratively analyze the detected values received from a subset of the plurality of monitoring devices, and recommend an action.

An exemplary system is further configured to subset the detected values based on one of an expected lifespan of a component associated with the detected values, a type of equipment associated with the detected values, and an operating condition under which the detected values were measured; if analyzing the subset of detected values, the system may provide the subset of detected values and supplemental information to a neural net to learn to recognize various operating states, health states, lifespans, and fault conditions utilizing deep learning techniques; if the supplemental information includes one of part specifications, part performance, equipment specifications, equipment performance, maintenance records, repair records, and expected condition models; and if at least one action is further taken in response to at least one of a change in amplitude of at least one of the plurality of detected values, a change in frequency or relative phase of at least one of the plurality of detected values, a rate of change of both the amplitude and relative phase of at least one of the plurality of detected values, and a relative rate of change of the amplitude and relative phase of at least one of the plurality of detected values; the at least one action may include issuing an alarm, the alarm being tactile, audible, or visual. the data acquisition circuit may be one of the above; a data storage circuit is included; at least one of the relative phase difference, the detected value, and the timing signal is stored; the at least one operation stores additional data in the data storage circuit; storing the additional data in the data storage circuit is further responsive to at least one of a change in the relative phase difference and a relative rate of change of the relative phase difference; the data acquisition circuit further includes at least one multiplexer circuit capable of selecting alternative combinations of detected values based on at least one of a user input and a selected operating parameter of the machine; each of the plurality of detected values corresponds to at least one of the input sensors; the at least one operation includes enabling or disabling one or more portions of the multiplexer circuit or changing a multiplexer control line; and/or the data acquisition circuit includes at least two multiplexer circuits and the at least one operation is changing a connection between the at least two multiplexer circuits.

An exemplary motor monitoring system includes a data acquisition circuit configured to interpret a plurality of sensed values from a plurality of input sensors communicatively coupled to the data acquisition circuit, each sensed value corresponding to at least one of the input sensors; a data storage circuit configured to store motor and motor component specifications, system geometry, and predicted state information, store past motor performance, and buffer the plurality of sensed values for a predetermined period of time; a peak detection circuit configured to determine a plurality of peak values, consisting of at least temperature peak values, speed peak values, and vibration peak values, in response to the plurality of sensed values, and analyze the peak values against the buffered sensed values, specifications, and predicted state information to obtain motor performance parameters; and a peak response circuit configured to perform at least one action in response to any of the peak values and the motor system performance parameters.

An exemplary system for estimating vehicle steering system performance parameters includes: a data acquisition circuit configured to interpret a plurality of detected values from a plurality of input sensors communicatively coupled to the data acquisition circuit, each of the plurality of detected values corresponding to at least one of the input sensors; a data storage circuit configured to store vehicle steering system, rack, pinion, and steering column specifications, system geometry, and expected state information, store past steering system performance, and buffer the plurality of detected values for a predetermined length of time; a peak detection circuit configured to determine a plurality of peak values, comprising at least a temperature peak value, a speed peak value, and a vibration peak value, in response to the plurality of detected values and analyze the peak values against the buffered detected values, the specifications, and the expected state information to obtain the vehicle steering system performance parameters; and a peak response circuit configured to perform at least one action in response to any of the peak values and the steering system performance parameters.

An exemplary system for estimating pump performance parameters includes: a data acquisition circuit configured to interpret a plurality of detected values from a plurality of input sensors communicatively coupled to the data acquisition circuit, each of the plurality of detected values corresponding to at least one of the input sensors; a data storage circuit configured to store pump and pump component specifications, system geometry, and predicted state information associated with the detected values, store past pump performance, and buffer the plurality of detected values for a predetermined length of time; a peak detection circuit configured to determine a plurality of peak values, comprising at least a temperature peak value, a speed peak value, and a vibration peak value, in response to the plurality of detected values, and analyze the peak values against the buffered detected values, the specifications, and the predicted state information to obtain the pump performance parameter; and a peak response circuit configured to perform at least one action in response to one of the peak values and the pump performance parameter. In certain further embodiments, the exemplary system includes a case where the pump is a water pump in a motor vehicle and the pump is a mineral pump.

An exemplary system for estimating drill performance parameters of a drilling machine includes: a data acquisition circuit configured to interpret a plurality of detected values from a plurality of input sensors communicatively coupled to the data acquisition circuit, each of the plurality of detected values corresponding to at least one of the input sensors; a data storage circuit configured to store drill and drill component specifications, system geometry, and predicted condition information associated with the detected values, store past drill performance, and buffer the plurality of detected values for a predetermined length; a peak detection circuit configured to determine a plurality of peak values, comprising at least a temperature peak value, a velocity peak value, and a vibration peak value, in response to the plurality of detected values, and analyze the peak values against the buffered detected values, the specifications, and the predicted condition information to obtain the drill performance parameter; and a peak response circuit configured to perform at least one action in response to one of the peak values and the drill performance parameter. The exemplary system further includes a case where the drilling machine is one of an oil drilling machine and a gas drilling machine.

An exemplary system for estimating conveyor health parameters includes: a data acquisition circuit configured to interpret a plurality of detected values from a plurality of input sensors communicatively coupled to the data acquisition circuit, each of the plurality of detected values corresponding to at least one of the input sensors; a data storage circuit configured to store conveyor and conveyor component specifications, system geometry, and predicted condition information associated with the detected values, store past conveyor performance, and buffer the plurality of detected values for a predetermined length of time; a peak detection circuit configured to determine a plurality of peak values, consisting of at least temperature peak values, speed peak values, and vibration peak values, in response to the plurality of detected values, analyze the peak values against the buffered detected values, specifications, and predicted condition information, and obtain conveyor performance parameters; and a peak response circuit configured to perform at least one action in response to one of the peak values and the conveyor performance parameters.

An exemplary system for estimating an agitator health parameter includes: a data acquisition circuit configured to interpret a plurality of sensed values from a plurality of input sensors communicatively coupled to the data acquisition circuit, each sensed value corresponding to at least one of the input sensors; a data storage circuit configured to store agitator and agitator component specifications, system geometry, and predicted state information associated with the sensed values, store past agitator performance, and buffer the plurality of sensed values for a predetermined period of time; a peak detection circuit configured to determine a plurality of peak values for the plurality of sensed values, the peak values comprising at least temperature peak values, speed peak values, and vibration peak values, analyze the peak values against the buffered sensed values, specifications, and predicted state information, and determine an agitator performance parameter; and a peak response circuit configured to perform at least one action in response to one of the peak values and the agitator performance parameter. In certain embodiments, the system further includes a case where the agitator is one of a rotary tank mixer, a large tank mixer, a portable tank mixer, a tote tank mixer, a drum mixer, a mounted mixer, and a propeller mixer.

An exemplary system for estimating compressor health parameters includes: a data acquisition circuit configured to interpret a plurality of sensed values from a plurality of input sensors communicatively coupled to the data acquisition circuit, each of the plurality of sensed values corresponding to at least one of the input sensors; a data storage circuit configured to store compressor and compressor component specifications, system geometry, and expected condition information associated with the sensed values, store past compressor performance, and buffer the plurality of sensed values for a predetermined period of time; a peak detection circuit configured to determine a plurality of peak values, comprising at least temperature peak values, speed peak values, and vibration peak values, in response to the plurality of sensed values, analyze the peak values against the buffered sensed values, the specifications, and the expected condition information, and obtain compressor performance parameters; and a peak response circuit configured to perform at least one action in response to any of the peak values and the compressor performance parameters.

An exemplary system for estimating health parameters of an air conditioner includes: a data acquisition circuit configured to interpret a plurality of sensed values from a plurality of input sensors communicatively coupled to the data acquisition circuit, each of the plurality of sensed values corresponding to at least one of the input sensors; a data storage circuit configured to store specifications, system geometry, and predicted condition information for the air conditioner and air conditioner components associated with the sensed values, store past air conditioner performance, and buffer the plurality of sensed values for a predetermined period of time; a peak detection circuit configured to determine a plurality of peak values for the plurality of sensed values, the peak values comprising at least temperature peak values, speed peak values, pressure peak values, and vibration peak values, analyze the peak values against the buffered sensed values, the specifications, and the predicted condition information, and determine air conditioner performance parameters; and a peak response circuit configured to take at least one action in response to any of the peak values and the air conditioner performance parameters.

An exemplary system for estimating centrifuge health parameters includes: a data acquisition circuit configured to interpret a plurality of detected values from a plurality of input sensors communicatively coupled to the data acquisition circuit, each of the detected values corresponding to at least one of the input sensors; a data storage circuit configured to associate centrifuge and centrifuge component specifications, system geometry, and expected status information with the detected values, store past centrifuge performance, and buffer the detected values for a predetermined period of time; a peak detection circuit configured to determine a plurality of peak values for the detected values, the peak values comprising at least temperature peak values, speed peak values, and vibration peak values, and analyze the peak values against the buffered detected values, specifications, and expected status information to determine centrifuge performance parameters; and a peak response circuit configured to perform at least one action in response to any of the peak values and the centrifuge performance parameters.

Bearings are used in a variety of equipment and applications. Bearings can be found in or support shafts, motors, rotors, stators, housings, frames, suspension systems and components, gears, various types of gear sets, other bearings, and other elements. Bearings are sometimes used as supports for high-speed vehicles such as magnetic levitation trains. Bearings are used to support rotating shafts in engines, motors, generators, fans, compressors, turbines, etc. Massive roller bearings are sometimes used to support buildings and physical infrastructure. Various types of bearings are used to support normal gears, planetary gears, and other gears. Bearings are sometimes used to support transmissions and gearboxes, such as roller thrust bearings. Bearings are sometimes used to support wheels, wheel hubs, and other rolling parts, using conical roller bearings.

There are many different types of bearings, including roller bearings, needle bearings, sleeve bearings, ball bearings, radial bearings, thrust load bearings including ball thrust bearings and roller thrust bearings used at low speeds, tapered bearings and tapered roller bearings, specialty bearings, magnetic bearings, giant roller bearings, jewel bearings (e.g., sapphire), hydrodynamic bearings, and flexure bearings that support bending element loads. References to bearings throughout this disclosure are intended to include, but are not limited to, the above terms.

In embodiments, information regarding the health of bearings or other status or condition information in a piece of industrial equipment or industrial process may be obtained by monitoring the condition of various components of the industrial equipment or industrial process. Monitoring may include monitoring the amplitude and/or frequency and/or phase of sensor signals measuring attributes such as temperature, humidity, acceleration, displacement, etc.

One embodiment of a data monitoring device 9200 is shown in FIG. 75 and may include a plurality of sensors 9206 communicatively coupled to a controller 9202. The controller 9202 may include a data acquisition circuit 9204, a data storage circuit 9216, a signal evaluation circuit 9208, and optionally a response circuit 9210. The signal evaluation circuit 9208 may include a frequency conversion circuit 9212 and a frequency evaluation circuit 9214.

The plurality of sensors 9206 may be wired to ports 9226 (see FIG. 76) of the data acquisition circuitry 9204. Alternatively, the plurality of sensors 9206 may be wirelessly connected to the data acquisition circuitry 9204. The data acquisition circuitry 9204 may have access to a sensed value corresponding to the output of at least one of the plurality of sensors 9206, where the sensor 9206 may acquire data regarding different operational aspects of a bearing or piece of equipment or infrastructure.

The selection of multiple sensors 9206 for a data monitoring device 9200 designed for a particular bearing or piece of equipment may depend on various considerations, such as accessibility for installing new sensors, sensor incorporation in the initial design, expected operating and fault conditions, and sensor reliability. The impact of failures can determine the extent of bearing or equipment monitoring. More sensors or more sophisticated sensors are used in systems where unexpected or undetected bearing failures would be costly or have severe consequences.

The signal evaluation circuitry 9208 may process the detected values to obtain information about the monitored bearing. The frequency conversion circuitry 9212 may convert one or more time-based detected values into frequency information. The conversion may be accomplished using techniques such as a digital fast Fourier transform ("FFT"), Laplace transform, Z transform, wavelet transform, other frequency domain transform, or other digital or analog signal analysis techniques, including complex analysis, including, but not limited to, complex phase unfolding analysis.

The frequency evaluation circuit 9214 (or frequency analysis circuit) may be configured to detect signals at frequencies of interest. These frequencies may include frequencies higher than the frequency at which the equipment rotates (e.g., as measured by a tachometer), various harmonic and/or resonant frequencies associated with the equipment's design and operating conditions, such as multiples of the shaft rotational speed or other rotating components for which the equipment is homed by bearings. Energy changes at frequencies close to the operating frequency may be indicative of system balance/imbalance. Energy changes at twice the operating frequency may indicate system misalignment, such as couplings or system looseness (e.g., rattle at harmonics of the operating frequency). Energy changes at frequencies close to three or four times the operating frequency, which correspond to the coupling's voltage rating, may indicate that one of the couplings is worn. Energy changes at four, five, or more times the operating frequency may be associated with a corresponding number of components, such as wear or imbalance in a five-vane pump, where there is an energy peak or activity near five times the operating frequency.

As an illustrative and non-limiting example, in the analysis of rolling element bearings, frequencies of interest include ball spin frequency, cage spin frequency, inner race frequency (since bearings often sit on races within a cage), and outer race frequency. A damaged bearing or a bearing beginning to fail may exhibit energy humps at the frequencies mentioned above and elsewhere in this disclosure. Energy at these frequencies can increase over time as the bearing wears and becomes damaged through increased fluctuations in rotational acceleration and ping.

In illustrative and non-limiting examples, bad bearings may exhibit energy humps, and as bearings wear and become defective, the intensity of high frequency measurements may begin to increase over time (greater accelerations or pings may appear in the high frequency measurement region). These measurements may be an indicator of air gaps within the bearing system. As bearings begin to wear, stronger impacts may cause the energy signal to move to higher frequencies.

In an embodiment, the signal evaluation circuit 9208 may include one or more of a phase detection circuit, a phase-locked loop circuit, a bandpass filter circuit, a peak detection circuit, etc.

In an embodiment, the signal evaluation circuit 9208 may include a transient signal analysis circuit. Transient signals can cause small-amplitude vibrations. However, a challenge in bearing analysis is the possibility of receiving signals associated with single or non-periodic impacts and exponential decay. Therefore, bearing vibrations may be represented not by a single sine wave but by a spectrum of many high-frequency sine waves. For example, a signal from a faulty bearing may only appear as a short-duration, low-amplitude spike in a time-based signal. Signals from a faulty bearing may have a smaller amplitude than signals associated with imbalance, even though the impact of the faulty bearing is more severe. Being able to identify these signals is important. Such low-amplitude transient signals may be best analyzed using transient analysis rather than traditional frequency transforms such as FFTs. Additionally, higher-resolution data streams can provide additional data for detecting transient signals during slow-speed operation. Identifying transient signals may help identify defects in equipment or components operating at low speeds.

In embodiments, the transient signal analysis circuitry for bearing analysis may include envelope modulation analysis and other transient signal analysis techniques. The signal evaluation circuitry 9208 may store long streams of detected values in the data storage circuitry 9216. The transient signal analysis circuitry may use envelope analysis techniques on those long streams of detected values to identify transient effects (such as shocks) that may not be identified using traditional sinusoidal analysis (such as FFT).

The signal evaluation circuitry 9208 may utilize transient signal analysis models optimized for the type of component being measured, such as bearings, gears, or variable speed machinery. In an illustrative and non-limiting example, a gear may resonate near its average rotational speed. In an illustrative and non-limiting example, a bearing may resonate near the bearing's rotational frequency, producing amplitude ringing around that frequency. For example, if the inner race of a shaft is worn, chatter may occur between the inner race and the shaft, producing amplitude modulation to the left and right of the bearing's frequency. Amplitude modulation may exhibit a unique sinusoidal characteristic with unique sidebands. Various signal processing techniques can be used to remove the sinusoidal components and obtain the modulation envelope for analysis.

The signal evaluation circuit 9208 may be optimized for variable-speed machinery. Historically, variable-speed machinery was expensive to build and typically used DC motors and variable sheaves with vanes to control flow. Variable-speed motors have become more common with advances in solid-state drives (SCR devices). The fundamental operating frequency of equipment can be varied from the 50-60 Hz provided by the utility, allowing the equipment to operate at different speeds, slower or faster depending on the application. Being able to operate equipment at a variety of speeds can potentially save energy. However, depending on the equipment's geometry, certain speeds can generate vibrations at resonant frequencies, shortening component life. Variable-speed motors can also discharge electricity into bearings, potentially damaging them. In embodiments, analysis of long data streams using envelope modulation analysis and other transient signal analysis techniques described herein can be useful for identifying these frequencies in order to design equipment control schemes to avoid these speeds that result in unacceptable vibrations and bearing damage.

In an illustrative, non-limiting example, heating, ventilation, and air conditioning ("HVAC") systems may be assembled on-site using variable speed motors, fans, belts, compressors, etc., whose operating speeds are not constant and whose relative relationships are unknown. In an illustrative, non-limiting example, variable speed motors may be used in fan pumps for circulating air in buildings. Variable speed motors may be used to vary the speed of conveyors, for example, in manufacturing assembly lines or steel mills. Variable speed motors may be used in fans in pharmaceutical processes, for example, where avoiding vibration is important.

In an illustrative and non-limiting example, defects in sleeve bearings can be analyzed. Sleeve bearings typically have an oil system. If the oil flow stops or becomes severely contaminated, failure can occur very quickly. Therefore, fluid particle sensors or fluid pressure sensors can be an important source of detection values.

In an illustrative and non-limiting example, the integrity of a fan can be assessed by measuring the air pulsations associated with the blade passing frequency. For example, if a fan has 12 blades, 12 air pulsations can be measured. Changes in the amplitude of the pulsations associated with different blades can indicate a change in the fan blades. Also, changes in the frequency associated with the air pulsations can indicate a bearing problem.

As an illustrative and non-limiting example, compressors used in gas processing equipment in the gas and oil sector or on assembly lines can be evaluated by measuring the periodic increase in energy/pressure in a storage vessel as gas is pumped into the storage vessel. Periodic changes in the amplitude of the energy increase may be associated with piston wear or damage to a portion of the rotating screw. Evaluating the phase of the energy signal relative to the timing signal may help identify which piston or portion of the rotating screw is damaged. Changes in frequency associated with the energy pulsations may indicate bearing problems.

As an illustrative and non-limiting example, cavitation/air pockets within a pump can create shutters in the pump housing and output flow, which can be identified through frequency conversion and frequency analysis techniques described above and elsewhere herein.

As an illustrative and non-limiting example, the frequency conversion and frequency analysis techniques described above and elsewhere herein may help identify problems with components of a building's HVAC system, such as a large fan. Poorly set dampers in the system can cause the ducts to pulsate and vibrate as air passes through the system. Monitoring vibration sensors installed in the ducts can help balance the system. Also, defective blades on a large fan can cause uneven airflow and pulsation in a building's ducts.

In an illustrative and non-limiting example, readings from an acoustic sensor placed near a bearing may help identify problems with gear meshing or faulty bearings. Based on knowledge of the gear ratios, such as the system's "in" and "out" gear ratios, and measurements of the input and output rotational speeds, readings can assess the energy generated at these ratios and, as a result, can be used to identify faulty bearings. This can be achieved with a simple, off-the-shelf motor, rather than installing a bulky sensor on the motor.

Based on the outputs of its various components, the signal evaluation circuit 9208 may perform bearing life prediction, bearing health parameter identification, bearing performance parameter identification, bearing health parameter (e.g., fault condition) determination, etc. The signal evaluation circuit 9208 may identify bearing wear, the presence of foreign matter (e.g., particulates) in a bearing, air gap or fluid loss in oiled/fluid-filled bearings, loss of lubrication in a set of bearings, loss of power in magnetic bearings, strain/stress in flexure bearings, etc. The signal evaluation circuit 9208 may identify optimal operating parameters for the equipment to extend bearing life. The signal evaluation circuit 9208 may also identify behavior (resonant wobble) at a selected operating frequency (e.g., shaft RPM).

The signal evaluation circuit 9208 may communicate with the data storage circuit 9216 to access equipment specifications, equipment geometry, bearing specifications, bearing materials, predicted state information for multiple bearing types, operating history, past detected values, etc. for use in evaluating the output of its various components. The signal evaluation circuit 9208 may buffer intermediate data, such as subsets of multiple detected values, time-based detected values converted to frequency information, filtered detected values, identified frequencies of interest, etc., for a predetermined length of time. The signal evaluation circuit 9208 may periodically store certain detected values in the data storage circuit 9216 to enable tracking of component performance over time. In embodiments, the signal evaluation circuit 908 may store data in the data storage circuit 9216 based on the conformance of the data to one or more criteria, as described throughout this disclosure, based on associated operating conditions and/or failure modes that may occur when detected values approach one or more criteria. Based on one sensor input meeting or approaching a specified criterion or range, the signal evaluation circuit 9208 may store additional data in the data storage circuit 9216, such as RPM, component load, temperature, pressure, vibration, or other sensor data of the type described throughout this disclosure. The signal evaluation circuit 9208 may store data at a higher data rate to allow for greater granularity in future processing, the ability to reprocess at different sampling rates, and/or diagnostic or post-processing of system information flagged with operating data of interest.

Depending on the type of device, the component being measured, the environment in which the device operates, etc., the sensors 9206 may include one or more of the following: vibration sensors, optical vibration sensors, thermometers, hygrometers, voltage sensors, current sensors, accelerometers, speed detectors, optical or electromagnetic sensors (e.g., for determining temperature, composition, and/or spectral analysis, and/or the position or movement of an object). Sensors 9206 may include, but are not limited to, any of the sensors described in this disclosure and the documents incorporated by reference, such as accelerometers, tachometers, fluid pressure meters, air flow meters, horsepower meters, flow meters, fluid particle detectors, acoustic sensors, pH sensors, etc. Sensors may typically consist of at least a temperature sensor, load sensor, three-axis sensor, and tachometer.

Sensor 9206 may provide a stream of data over time that has a phase component, such as that associated with acceleration or vibration, allowing for evaluation of phase or frequency analysis of different operational aspects of a piece of equipment or operating component. Sensor 9206 may also provide streams of data that are not traditionally phase-based, such as temperature, humidity, load, etc. Sensor 9206 may provide a continuous or near-continuous stream of data over time, periodic readings, event-driven readings, and/or readings according to a selected interval or schedule.

In embodiments, as illustrated in FIG. 75, the sensor 9206 may be part of a data monitoring device 9200, sometimes referred to herein as a data collector, which may sometimes constitute a mobile or portable data collector. In embodiments, as shown in FIGS. 76 and 77, one or more external sensors 9224, not explicitly part of the monitoring device 9218 but previously attached to or integrated into a device or component, may be randomly connected to or accessed by the monitoring device 9218. The monitoring device 9218 may include a controller 9220. The controller 9202 may include a data acquisition circuit 9222, a data storage circuit 9216, a signal evaluation circuit 9208, and optionally a response circuit 9210. The signal evaluation circuit 9208 may include a frequency conversion circuit 9212 and a frequency analysis circuit 9214. The data acquisition circuit 9222 may include one or more input ports 9226. The external sensors 9224 may be directly connected to one or more input ports 9226 of the data acquisition circuit 9222 of the controller 9220, or may be accessed wirelessly by a reader, interrogator, or other wireless connection, such as over a short-range wireless protocol. In embodiments such as that shown in FIG. 77, the data acquisition circuit 9222 may further include wireless communication circuitry 9262. The data acquisition circuit 9222 may use the wireless communication circuitry 9262 to access sensed values corresponding to the external sensors 9224 wirelessly, via another source, or some combination of these methods.

In an embodiment, as shown in FIG. 78, the data acquisition circuit 9222 may further include a multiplexer circuit 9236 as described elsewhere herein. The output from the multiplexer circuit 9236 may be utilized by the signal evaluation circuit 9208. The response circuit 9210 may have the ability to turn portions of the multiplexer circuit 9236 on and off. The response circuit 9210 may have the ability to control a control channel of the multiplexer circuit 9236.

The response circuit 9210 may initiate actions based on bearing performance parameters, bearing health values, bearing life prediction parameters, etc. The response circuit 9210 may evaluate the results of the signal evaluation circuit 9208 and initiate actions based on certain criteria or outputs from various components of the signal evaluation circuit 9208. Criteria may include a sensor's detected value at a particular frequency or phase relative to the timer signal, and the frequency or phase of interest may be based on equipment geometry, equipment control scheme, system inputs, historical data, current operating conditions, and/or expected response. Criteria may include a sensor's detected value at a particular frequency or phase relative to a second sensor's detected value. Criteria may include signal strength at a particular resonant frequency/harmonic compared to a detected value associated with a system tachometer or expected based on equipment geometry and operating conditions. The criteria may include a predetermined peak value of a detection value from a particular sensor, the cumulative value of the sensor's corresponding detection value over time, the change in the peak value, the rate of change of the peak value, and/or the cumulative value (e.g., time spent above/below a threshold, weighted time spent above/below one or more thresholds, and/or area of the detection value spent above/below one or more thresholds). The criteria may be comprised of a combination of data from different sensors, such as relative values, relative changes in values, relative rates of change in values, or relative values over time. The relative criteria may vary depending on other data or information, such as the stage of the process, the type of product being processed, the type of equipment, ambient temperature and humidity, external vibrations from other equipment, etc. The relative criteria may be reflected in one or more calculated statistics or metrics (including those generated by further calculations on multiple criteria or statistics), which may be used for processing (either on-board the data collector or by an external system), such as being provided as input to one or more machine learning capabilities described in this disclosure. It can also be used as a data element that serves as input to other systems, such as data streams or data packages that can be consumed by systems like data marketplaces, SCADA systems, remote control systems, maintenance systems, and analytics systems.

While certain embodiments are described herein as having detected values exceeding a threshold or predetermined value, detected values may also be below the threshold or predetermined value. For example, when a change in detected value is expected to occur, but the detected value indicates that a change may not have occurred. For example, and without limitation, vibration data may indicate a system agitation level, properly operating equipment, etc., and vibration data below a threshold amplitude and/or frequency may be indicative of a process that is not operating as expected. Unless the context clearly indicates otherwise, any statement herein describing a determination of a value above a threshold and/or above a predetermined or expected value shall be understood to include a determination of a value below a threshold and/or below a predetermined or expected value.

The predetermined tolerance range may be based on predicted system response or vibration based on the equipment's geometry and control method, such as the number of bearings, relative rotational speed, or power input to the system at a certain frequency. The predetermined tolerance range may also be set based on a long-term analysis of detected values from multiple similar pieces of equipment or components and their correlation with equipment failure.

In some embodiments, an alarm may be issued based on some of the criteria described above. In an illustrative example, an increase in temperature and energy at a particular frequency may indicate a hot bearing beginning to fail. In embodiments, the relative criteria for an alarm may vary depending on other data or information, such as the process stage, the type of product being processed by the equipment, the ambient temperature and humidity, external vibrations from other equipment, etc. In an illustrative and non-limiting example, the response circuitry 9210 may initiate an alarm if the vibration amplitude and/or frequency exceeds a predetermined maximum value, if there is a change or rate of change that exceeds a predetermined tolerance, and/or if an accumulated value based on the vibration amplitude and/or frequency exceeds a threshold.

In embodiments, the response circuitry 9210 may cause the data acquisition circuitry 9204 to enable or disable processing of detection values corresponding to a particular sensor based on some of the criteria described above. This may include switching to a sensor with a different response speed, sensitivity, range, etc., or accessing a new sensor or sensor type. The switching may be based on a model, a set of rules, etc. In embodiments, the switching is under the control of a machine learning system, controlled based on one or more success metrics combined with input data over a series of trials, which may occur under the supervision of a human supervisor or under the control of an automated system. The switching may include switching from one input port to another (e.g., switching from one sensor to another). The switching may include changing the multiplexing of data, such as combining different streams under different conditions. The switching may also include triggering the system to acquire additional data. For example, a mobile system (e.g., a robotic or drone system) may be moved to a location where different or additional data is available (e.g., an image sensor may be positioned for a different view, a sonar sensor may be positioned for a different collection direction), or a different sensor may be accessible (e.g., a collector may be moved to connect to sensors located in the environment via wired or wireless connections). This switching may be accomplished by changing the control signals of the multiplexer circuit 9236 and/or by turning on or off particular inputs of the multiplexer circuit 9236. The response circuit 9210 may also make recommendations for future replacement of particular sensors with sensors having different response speeds, sensitivity, range, etc. The response circuit 9210 may also recommend design changes for future implementations of components, equipment, operating conditions, processes, etc.

In embodiments, the response circuitry 9210 may recommend maintenance or initiate a maintenance call during an upcoming process shutdown. The response circuitry 9210 may recommend changes to process or operating parameters to remotely balance equipment. In embodiments, the response circuitry 9210 may implement or recommend process changes, such as reducing the utilization of a component that is nearing a maintenance interval, operating off-nominal, or has failed for purpose but is still at least partially operational; changing the operating speed of a component (e.g., placing it in a low-demand mode); initiating remediation of the problem (e.g., signaling additional lubrication of a roller bearing set or signaling an alignment process for an out-of-balance system), etc.

In embodiments such as those shown in FIGS. 79, 80, 81, and 82, the data monitoring system 9240 may include at least one data monitoring device 9250. The at least one data monitoring device 9250 may include a sensor 9206 and a controller 9242 including a data acquisition circuit 9204, a signal evaluation circuit 9208, a data storage circuit 9216, and a communication circuit 9246. The signal evaluation circuit 9208 may include at least one of a frequency detection circuit 9212 and a frequency analysis circuit 9214. Optional response circuitry may also be present, as described above and elsewhere herein. The signal evaluation circuit 9208 may periodically share data with the communication circuit 9246 for transmission to a remote server 9244 to enable a monitoring application 9248 to track component and equipment performance over time and under various conditions. Because sensor values approaching one or more criteria may indicate associated operating conditions and/or failure modes, the signal evaluation circuit 9208 may share data with the communication circuit 9246 for transmission to a remote server 9244 based on the data's suitability for one or more criteria. Based on one sensor input meeting or approaching a specified criterion or range, the signal evaluation circuit 9208 may share additional data for transmission, such as RPM, component load, temperature, pressure, vibration, etc. The signal evaluation circuit 9208 may also share and transmit data at a higher data rate to allow for greater granularity in processing at the remote server.

In embodiments, as shown in FIG. 79, the communications circuitry 9246 may communicate data directly to the remote server 9244. In embodiments, as shown in FIG. 80, the communications circuitry 9246 may communicate data to an intermediate computer 9252, which may include a processor 9254 executing an operating system 9256 and data storage circuitry 9258. The intermediate computer 9252 may collect data from multiple data monitoring devices and transmit the accumulated data to the remote server 9244.

In embodiments, as shown in FIGS. 81 and 82, the data collection system 9260 may have multiple monitoring devices 9250 collecting data for multiple components within a single device, may collect data for the same component across multiple devices (both the same and different types) within the same facility, or may collect data from monitoring devices within multiple facilities. A monitoring application 9248 on a remote server 9244 may receive and store one or more of the detected values, timing signals, and data from the multiple, various monitoring devices 9250. In embodiments, as shown in FIG. 81, the communications circuitry 9246 may communicate data directly to the remote server 9244. In embodiments, as shown in FIG. 82, the communications circuitry 9246 may communicate data to an intermediate computer 9252, which may include a processor 9254 executing an operating system 9256 and a data storage circuitry 9258. There may be a separate intermediate computer 9252 associated with each monitoring device 9264, or a separate intermediate computer 9252 may be associated with multiple monitoring devices 9250, and the intermediate computer 9252 may collect data from multiple data monitoring devices and send the accumulated data to the remote server 9244.

The monitoring application 9248 may select subsets of sensed values, timing signals, and data for joint analysis. The subsets for analysis may be selected based on bearing type, bearing material, or a single type of equipment on which the bearings operate. The subsets for analysis may be selected or grouped based on common operating conditions or operating history, such as load size, operating state (e.g., intermittent operation, continuous operation), operating speed or tachometer, common ambient environmental conditions such as humidity, temperature, air or fluid particulates, etc. The subsets for analysis may be selected based on common expected state information. The subsets for analysis may also be selected based on the influence of other peripheral equipment, such as machinery rotating at similar frequencies, equipment generating electromagnetic fields, equipment generating heat, equipment inducing movement or vibration, equipment emitting vapors, chemicals, or particulates, or the influence of other potential interference or disturbances.

The monitoring application 9248 may analyze the selected subset. In an illustrative example, data from one component may be analyzed over different time periods, such as one operating cycle, cycle-to-cycle comparisons, or trends over multiple operating cycles/time periods, such as one month, one year, or the life of the component. Data from multiple parts of the same type may also be analyzed over different time periods. Trends in data, such as changes in frequency or amplitude, may correlate with records of failures or maintenance associated with the same part or equipment. Data trends, such as rates of change associated with startup or different points in a process, may also be identified. Additional data may be introduced into the analysis, such as data indicating output product quality, output volume (e.g., per unit time), or process success or failure. Correlations between trends and values in different types of data may be analyzed, and short-term analysis may identify parameters that may provide the best prediction of expected performance. Analysis may identify refinements to models for expected condition information, recommendations regarding sensors to use, sensor placement, etc. Analysis may identify additional data to collect and store. Analysis may identify recommendations regarding needed maintenance or repairs and/or scheduling of preventive maintenance. The analysis may identify recommendations for purchasing replacement bearings and when to replace them. The analysis may also result in alerts about potential catastrophic failure conditions. This information may be sent to the monitoring equipment to update the types of data collected and analyzed locally or to influence the design of future monitoring equipment.

In embodiments, the monitoring application 9248 may access equipment specifications, equipment geometry, bearing specifications, bearing materials, predicted condition information for multiple bearing types, operating history, past detections, bearing life models, etc., to analyze the selected subset using rule-based or model-based analysis. In embodiments, the monitoring application 9248 may feed the selected subset to a neural net that learns to recognize various operating conditions, health conditions (e.g., life predictions), and fault conditions using deep learning techniques. In embodiments, a hybrid of the two techniques (model-based learning and deep learning) may be used.

By way of illustrative and non-limiting example, the health status of assembly line conveyor and lifter bearings, industrial vehicle water pumps, gas processing system compressors, compressors located outside gas and oil fields, factory air conditioning units, and factory mineral pumps can be monitored using the frequency conversion and frequency analysis techniques, data monitoring devices, and data collection systems described herein.

In an illustrative and non-limiting example, the health status of one or more bearings, gears, blades, screws, and associated shafts, motors, rotors, stators, gears, and other components of gearboxes, motors, pumps, vibratory conveyors, mixers, centrifuges, drilling machines, screwdrivers, and refinery tanks located in the oil and gas field can be assessed using the frequency conversion and frequency analysis techniques, data monitoring devices, and data collection systems described herein.

In an illustrative and non-limiting example, the health of bearings and associated shafts, motors, rotors, stators, gears, and other components of rotating tank/mixer agitators, mechanical/rotary agitators, and propeller agitators deployed in chemical and pharmaceutical manufacturing lines to facilitate chemical reactions can be assessed using the frequency conversion and frequency analysis techniques, data monitoring devices, and data collection systems described herein.

In an illustrative and non-limiting example, the health of bearings and associated shafts, motors, rotors, stators, gears, and other components of a vehicle system, such as a steering mechanism or engine, may be assessed using the frequency conversion and frequency analysis techniques, data monitoring devices, and data collection systems described herein.

An exemplary monitoring device for bearing analysis in an industrial environment includes a data acquisition circuit configured to interpret a plurality of sensed values, each of the plurality of sensed values corresponding to at least one of a plurality of input sensors communicatively coupled to the data acquisition circuit; a data storage device for storing specifications and predicted condition information for a plurality of bearing types and buffering the plurality of sensed values for a predetermined length of time; and a bearing analysis circuit configured to analyze the buffered sensed values in relation to the specifications and predicted condition information to obtain bearing performance parameters.

In certain further embodiments, the exemplary monitoring device includes one or more of: a response circuit that performs at least one action in response to the bearing performance parameter; where the plurality of input sensors includes at least two sensors selected from the group consisting of a temperature sensor, a load sensor, an optical vibration sensor, an acoustic wave sensor, a heat flux sensor, an infrared sensor, an acceleration sensor, a three-axis vibration sensor, and a tachometer; where the at least one action is further performed in response to at least one of a change in amplitude of at least one of the plurality of detected values, a change in frequency or relative phase of at least one of the plurality of detected values, a rate of change of both the amplitude and relative phase of at least one of the plurality of detected values, and a relative rate of change of the amplitude and relative phase of at least one of the plurality of detected values; where the at least one action includes issuing an alert, the alert may be one of tactile, audible, and visual; where the at least one action further includes storing additional data in the data storage circuit; where storing the additional data in the data storage circuit is further performed in response to at least one of a change in relative phase difference and a relative rate of change of the relative phase difference.

An exemplary monitoring device for bearing analysis in an industrial environment includes a data acquisition circuit configured to interpret a plurality of sensed values, each of the sensed values corresponding to at least one of a plurality of input sensors communicatively coupled to the data acquisition circuit; a data storage device for storing specifications and predicted condition information for a plurality of bearing types and buffering the sensed values for a predetermined length of time; and a bearing analysis circuit configured to analyze the buffered sensed values in relation to the specifications and predicted condition information to obtain a bearing health value.

In certain embodiments, the exemplary monitoring device includes one or more of: a response circuit that performs at least one action in response to the bearing health value; where the plurality of input sensors includes at least two sensors selected from the group consisting of a temperature sensor, a load sensor, an optical vibration sensor, an acoustic wave sensor, a heat flux sensor, an infrared sensor, an acceleration sensor, a three-axis vibration sensor, and a tachometer; where the at least one action is further performed in response to at least one of a change in amplitude of at least one of the plurality of detected values, a change in frequency or relative phase of at least one of the plurality of detected values, a rate of change of both the amplitude and relative phase of at least one of the plurality of detected values, and a relative rate of change of the amplitude and relative phase of at least one of the plurality of detected values; where the at least one action includes issuing an alert, the alert may be one of tactile, audible, and visual; where at least one action further includes storing additional data in a data storage circuit; where storing the additional data in the data storage circuit is further performed in response to at least one of a change in the relative phase difference and a relative rate of change of the relative phase difference.

An exemplary monitoring device for bearing analysis in an industrial environment includes a data acquisition circuit configured to interpret a plurality of sensed values, each of the sensed values corresponding to at least one of a plurality of input sensors communicatively coupled to the data acquisition circuit; a data storage device for storing specifications and expected condition information for a plurality of bearing types and buffering the sensed values for a predetermined length of time; and a bearing analysis circuit configured to analyze the buffered sensed values in relation to the specifications and expected condition information to generate bearing life prediction parameters.

In certain embodiments, the monitoring device further includes a response circuit that performs at least one action in response to the bearing life prediction parameter; if the plurality of input sensors includes at least two sensors selected from the group consisting of a temperature sensor, a load sensor, an optical vibration sensor, an acoustic wave sensor, a heat flux sensor, an infrared sensor, an acceleration sensor, a three-axis vibration sensor, and a tachometer; if the at least one action is further performed in response to at least one of a change in amplitude of at least one of the plurality of detected values, a change in frequency or relative phase of at least one of the plurality of detected values, a rate of change of both the amplitude and relative phase of at least one of the plurality of detected values, and a relative rate of change of the amplitude and relative phase of at least one of the plurality of detected values; if the at least one action includes issuing an alarm, the alarm may be one of tactile, audible, and visual; if the at least one action further includes storing additional data in a data storage circuit; if storing the additional data in the data storage circuit is further performed in response to at least one of a change in the relative phase difference and a relative rate of change of the relative phase difference.

An exemplary monitoring device for bearing analysis in an industrial environment includes a data acquisition circuit configured to interpret a plurality of detected values, each of the detected values corresponding to at least one of a plurality of input sensors communicatively coupled to the data acquisition circuit; a data storage device for storing specification and expected condition information for a plurality of bearing types and buffering the detected values for a predetermined length of time; and a bearing analysis circuit configured to analyze the buffered detected values by comparing them with the specification and expected condition information to obtain bearing performance parameters, wherein the data acquisition circuit includes a multiplexer circuit capable of selecting alternative combinations of the detected values based on at least one of user input, the detected condition, and selected operating parameters of the machine.

In certain further embodiments, an exemplary monitoring device includes a response circuit that performs at least one action in response to a bearing performance parameter, wherein the plurality of input sensors include at least two sensors selected from the group consisting of a temperature sensor, a load sensor, an optical vibration sensor, an acoustic wave sensor, a heat flux sensor, an infrared sensor, an acceleration sensor, a three-axis vibration sensor, and a tachometer; the response circuit includes one or more of: a change in amplitude of at least one of the plurality of detected values; a change in frequency or relative phase of at least one of the plurality of detected values; a rate of change of both the amplitude and relative phase of at least one of the plurality of detected values; and a relative rate of change of the amplitude and relative phase of at least one of the plurality of detected values; the at least one action includes issuing an alarm, which may be one of tactile, audible, and visual; and the at least one action further includes storing additional data in a data storage circuit, wherein storing the additional data in the data storage circuit is further performed in response to at least one of a change in the relative phase difference and a relative rate of change of the relative phase difference.

An exemplary system for data collection, processing, and bearing analysis in an industrial environment includes a plurality of monitoring devices, each monitoring device having a data acquisition circuit configured to interpret a plurality of detected values, each of the detected values corresponding to at least one of a plurality of input sensors communicatively coupled to the data acquisition circuit; a data storage device that stores specifications and predicted condition information for a plurality of bearing types and buffers the detected values for a predetermined period of time; and a bearing analysis circuit configured to analyze the buffered detected values in relation to the specifications and predicted condition information to perform a bearing life prediction.

The system further includes a communications circuit configured to communicate with a remote server that provides the bearing life prediction and a portion of the buffered detection values to the remote server.

The system further includes a monitoring application on a remote server configured to receive, store, and collaboratively analyze a subset of the detected values from the multiple monitoring devices.

In certain further embodiments, an exemplary monitoring device includes one or more of: a response circuit that performs at least one action in response to the bearing life prediction, wherein the plurality of input sensors includes at least two sensors selected from the group consisting of a temperature sensor, a load sensor, an optical vibration sensor, an acoustic wave sensor, a heat flux sensor, an infrared sensor, an acceleration sensor, a three-axis vibration sensor, and a tachometer; wherein the at least one action is further performed in response to at least one of: a change in amplitude of at least one of the plurality of detected values; a change in frequency or relative phase of at least one of the plurality of detected values; a rate of change of both the amplitude and relative phase of at least one of the plurality of detected values; and a relative rate of change of the amplitude and relative phase of at least one of the plurality of detected values; wherein the at least one action includes issuing an alert, wherein the alert may be one of tactile, audible, and visual; wherein the at least one action further includes storing additional data in the data storage circuit; and wherein storing the additional data in the data storage circuit is further performed in response to at least one of a change in the relative phase difference and a relative rate of change of the relative phase difference.

An exemplary system for data collection, processing, and bearing analysis in an industrial environment includes a plurality of monitoring devices, each having a data acquisition circuit configured to interpret a plurality of sensed values, each of the plurality of sensed values corresponding to at least one of a plurality of input sensors communicatively coupled to the data acquisition circuit, and a data storage device that stores specifications and predicted condition information for a plurality of bearing types and buffers the plurality of sensed values for a predetermined period of time.

The system further includes a bearing analysis circuit configured to analyze the buffered sensed values against specifications and predicted condition information resulting in bearing performance parameters; a communications circuit configured to communicate with a remote server and provide a life prediction and a portion of the buffered sensed values to the remote server; and a monitoring application on the remote server configured to receive, store, and collaboratively analyze a subset of the sensed values from the multiple monitoring devices.

In certain further embodiments, an exemplary monitoring device includes a response circuit that performs at least one action in response to a bearing performance parameter, wherein the plurality of input sensors includes at least two sensors selected from the group consisting of a temperature sensor, a load sensor, an optical vibration sensor, an acoustic wave sensor, a heat flux sensor, an infrared sensor, an acceleration sensor, a three-axis vibration sensor, and a tachometer; the at least one action is further performed in response to at least one of a change in amplitude of at least one of the plurality of detected values, a change in frequency or relative phase of at least one of the plurality of detected values, a rate of change of both the amplitude and relative phase of at least one of the plurality of detected values, and a relative rate of change of the amplitude and relative phase of at least one of the plurality of detected values; the at least one action includes issuing an alert, wherein the alert may be one of tactile, audible, and visual; the at least one action further includes storing additional data in the data storage circuit; and the storing of the additional data in the data storage circuit is further performed in response to at least one of a change in relative phase difference and a relative rate of change of the relative phase difference.

An exemplary system for data collection, processing, and bearing analysis in an industrial environment includes a remote learning system including: a plurality of monitoring devices, each monitoring device having a data acquisition circuit configured to interpret a plurality of sensed values, each of the plurality of sensed values corresponding to at least one of a plurality of input sensors communicatively coupled to the data acquisition circuit; a streaming circuit for streaming at least a subset of the sensed values to the remote learning system; and a bearing analysis circuit configured to analyze the sensed values in relation to a machine-based understanding of the condition of at least one bearing.

In certain further embodiments, the exemplary system further includes one or more of: the machine-based understanding is developed based on a model of the bearing that determines the state of the at least one bearing based at least in part on a relationship between bearing behavior and an operating frequency of a component of the industrial machine; the state of the at least one bearing is at least one of an operating state, a health state, a predicted life state, and a fault state; the machine-based understanding is developed based on providing input to a deep learning machine, the input consisting of multiple streams of detection values for the multiple bearings and multiple measured state values for the multiple bearings; and the state of the at least one bearing is at least one of an operating state, a health state, a predicted life state, and a fault state.

An exemplary method for analyzing bearings and sets of bearings includes receiving a plurality of detected values corresponding to data from a temperature sensor, a vibration sensor located near the bearing or set of bearings, and a tachometer for measuring rotation of a shaft associated with the bearing or set of bearings; comparing the detected values corresponding to the temperature sensors to a predetermined maximum level; filtering the detected values corresponding to the vibration sensors through a high-pass filter, the filter selected to remove vibrations associated with the detected values associated with the tachometer; identifying abrupt changes in at least one of the temperature peaks and the vibration peaks; and determining a frequency at which spikes occur in the filtered detected values corresponding to the vibration sensors; and comparing the frequency and amplitude of the spikes to expected condition information and specifications associated with the bearing or set of bearings.

The method further includes determining a bearing health parameter.

An exemplary apparatus for monitoring rolling element bearings in an industrial environment includes a data acquisition circuit configured to interpret a plurality of detected values, each of the detected values corresponding to at least one of a plurality of input sensors communicatively coupled to the data acquisition circuit; a data storage circuit configured to store specifications and expected condition information for a plurality of types of rolling element bearings and buffer the detected values for a predetermined length of time; a bearing analysis circuit configured to analyze the buffered detected values by comparing them with the specifications and expected condition information to obtain bearing performance parameters; and a response circuit configured to perform at least one action in response to the bearing performance prediction.

In this device, the multiple input sensors include at least two sensors selected from the group consisting of a temperature sensor, a load sensor, an optical vibration sensor, an acoustic wave sensor, a heat flux sensor, an infrared sensor, an acceleration sensor, a three-axis vibration sensor, and a tachometer.

An exemplary apparatus for monitoring sleeve bearings in an industrial environment includes a data acquisition circuit configured to interpret a plurality of detected values, each of the detected values corresponding to at least one of a plurality of input sensors communicatively coupled to the data acquisition circuit; a data storage device that stores sleeve bearing specifications and expected condition information for the sleeve bearing type and buffers the detected values for a predetermined length of time; and a bearing analysis circuit configured to analyze the buffered detected values against the specifications and expected condition information to yield bearing performance parameters.

The apparatus further includes a response circuit that performs at least one action in response to the bearing performance parameters, and the plurality of input sensors includes at least two sensors selected from the group consisting of a temperature sensor, a load sensor, an optical vibration sensor, an acoustic wave sensor, a heat flux sensor, an infrared sensor, an acceleration sensor, a three-axis vibration sensor, and a tachometer.

An exemplary system for monitoring pump bearings in an industrial environment includes a data acquisition circuit configured to interpret a plurality of sensed values, each of the plurality of sensed values corresponding to at least one of a plurality of input sensors communicatively coupled to the data acquisition circuit; a data storage device that stores pump specifications, bearing specifications, and predicted state information for the pump bearings and buffers the plurality of sensed values for a predetermined period of time; and a bearing analysis circuit configured to analyze the buffered sensed values against the specifications and predicted state information to yield bearing performance parameters.

The system further includes a response circuit that performs at least one action in response to the bearing performance parameters, and the plurality of input sensors includes at least two sensors selected from the group consisting of a temperature sensor, a load sensor, an optical vibration sensor, an acoustic wave sensor, a heat flux sensor, an infrared sensor, an acceleration sensor, a three-axis vibration sensor, and a tachometer.

An exemplary system for collecting, processing, and analyzing pump bearing data in an industrial environment includes a plurality of monitoring devices, each including a data acquisition circuit configured to interpret a plurality of detected values, each of the plurality of detected values corresponding to at least one of a plurality of input sensors communicatively coupled to the data acquisition circuit; a data storage device that stores pump specifications, bearing specifications, and predicted state information for the pump bearings and buffers the plurality of detected values for a predetermined period of time; a bearing analysis circuit configured to analyze the buffered detected values against the pump and bearing specifications and predicted state information to yield bearing performance parameters; a communication circuit configured to communicate with a remote server and provide the bearing performance parameters and a portion of the buffered detected values to the remote server; and a monitoring application on the remote server configured to receive, store, and collaboratively analyze a subset of the detected values from the plurality of monitoring devices.

An exemplary system for estimating conveyor health parameters includes a data acquisition circuit configured to interpret a plurality of sensed values, each of the plurality of sensed values corresponding to at least one of a plurality of input sensors, the plurality of input sensors including at least one of an angular position sensor, an angular velocity sensor, and an angular acceleration sensor positioned to measure rotating components; a data storage circuit configured to store specifications, system geometry, and expected condition information for the conveyor and associated rotating components, store past conveyor and component performance, and buffer the plurality of sensed values for a predetermined length of time; and a bearing analysis circuit configured to analyze the buffered sensed values against the specifications and expected condition information to yield bearing performance parameters.

The system further includes a system analysis circuit configured to estimate conveyor health performance using the bearing performance and at least one of predicted conditions, historical data, and system geometry.

An exemplary system for estimating an agitator health parameter includes: a data acquisition circuit configured to interpret a plurality of sensed values, each of the sensed values corresponding to at least one of a plurality of input sensors, the plurality of input sensors including at least one of an angular position sensor, an angular velocity sensor, and an angular acceleration sensor positioned to measure rotating components; a data storage circuit configured to store specifications, system geometry, and expected state information for the agitator and associated components, store past agitator and component performance, and buffer the sensed values for a predetermined length of time; a bearing analysis circuit configured to analyze the buffered sensed values in relation to the specifications and expected state information to obtain bearing performance parameters; and a system analysis circuit configured to estimate the agitator health parameter using at least one of the bearing performance, predicted state, historical data, and system geometry. In certain further embodiments, the exemplary apparatus further includes a case where the agitator is one of a rotary tank mixer, a large tank mixer, a portable tank mixer, a tote tank mixer, a drum mixer, an on-board mixer, and a propeller mixer.

An exemplary system for estimating performance parameters of a vehicle steering system includes a data acquisition circuit configured to interpret a plurality of sensed values, each of the sensed values corresponding to at least one of a plurality of input sensors, the plurality of input sensors including at least one of an angular position sensor, an angular velocity sensor, and an angular acceleration sensor arranged to measure rotational components; a data storage circuit configured to store specifications, system geometry, and expected state information for the vehicle steering system, rack, pinion, and steering column, store past steering system performance, and buffer the sensed values for a predetermined length of time; and a bearing analysis circuit configured to analyze the buffered sensed values against the specifications and expected state information to yield bearing performance parameters.

The system further includes a system analysis circuit configured to estimate vehicle steering system performance parameters using the bearing performance and at least one of predicted conditions, historical data, and system geometry.

An exemplary system for estimating pump performance parameters includes: a data acquisition circuit configured to interpret a plurality of sensed values, each of the sensed values corresponding to at least one of a plurality of input sensors, the plurality of input sensors including at least one of an angular position sensor, an angular velocity sensor, and an angular acceleration sensor arranged to measure rotating components; a data storage circuit configured to store pump and pump component specifications, system geometry, and expected condition information, store past steering system performance, and buffer the sensed values for a predetermined period of time; a bearing analysis circuit configured to analyze the buffered sensed values against the specifications and expected condition information to generate bearing performance parameters; and a system analysis circuit configured to estimate the pump performance parameters using at least one of the bearing performance, predicted condition, historical data, and system geometry. In certain embodiments, the exemplary system further includes a case where the pump is an automotive water pump and/or where the pump is an ore pump.

An exemplary system for estimating excavator performance parameters includes a data acquisition circuit configured to interpret a plurality of sensed values, each of the plurality of sensed values corresponding to at least one of a plurality of input sensors, the plurality of input sensors including at least one of an angular position sensor, an angular velocity sensor, and an angular acceleration sensor positioned to measure rotating components; a data storage circuit configured to store excavator and excavator component specifications, system geometry, and expected condition information, store past excavator performance, and buffer the plurality of sensed values for a predetermined length of time; and a bearing analysis circuit configured to analyze the buffered sensed values against the specifications and expected condition information to yield bearing performance parameters.

The system further includes a system analysis circuit configured to estimate performance parameters of the drilling machine using the bearing performance and at least one of predicted conditions, historical data, and system geometry. In certain further embodiments, the drilling machine is one of an oil drilling machine and a gas drilling machine.

An exemplary system for estimating excavator performance parameters includes a data acquisition circuit configured to interpret a plurality of sensed values, each of the sensed values corresponding to at least one of a plurality of input sensors, the plurality of input sensors including at least one of an angular position sensor, an angular velocity sensor, and an angular acceleration sensor positioned to measure rotating components; a data storage circuit configured to store specifications, system geometry, and expected condition information for the excavator and excavator components, store past excavator performance, and buffer the sensed values for a predetermined length of time; a bearing analysis circuit configured to analyze the buffered sensed values against the specifications and expected condition information to yield bearing performance parameters; and a system analysis circuit configured to estimate the excavator performance parameters using the bearing performance and at least one of the expected condition, historical data, and system geometry.

Rotating parts are used in many different types of equipment and applications. Rotating parts may include shafts, motors, rotors, stators, bearings, fins, vanes, wings, blades, fans, bearings, wheels, hubs, spokes, balls, rollers, pins, gears, and the like. In embodiments, information regarding the health or other condition or status information of a rotating part in a piece of industrial equipment or an industrial process may be obtained by monitoring the condition of the part or various other components of the industrial equipment or industrial process and identifying twists on the part. Monitoring may include monitoring the amplitude and phase of sensor signals measuring attributes such as angular position, angular velocity, and angular acceleration.

One embodiment of a data monitoring device 9400 is shown in FIG. 83 and may include a plurality of sensors 9406 communicatively coupled to a controller 9402. The controller 9402 may include a data acquisition circuit 9404, a data storage circuit 9414, a system evaluation circuit 9408, and optionally a response circuit 9410. The system evaluation circuit 9408 may include a torsion analysis circuit 9412.

The multiple sensors 9406 may be wired to ports of the data acquisition circuitry 9404. The multiple sensors 9406 may be wirelessly connected to the data acquisition circuitry 9404. The data acquisition circuitry 9404 may have access to a sensed value corresponding to the output of at least one of the multiple sensors 9406, where the sensor 9406 may capture data regarding different operational aspects of a bearing or piece of equipment or infrastructure.

The selection of multiple sensors 9406 for a data monitoring device 9400 designed to assess torsion of components such as shafts, motors, rotors, stators, bearings, gears, or other components described herein, or combinations of components within or comprising a drivetrain, equipment, or system, may depend on various considerations, such as accessibility for installing new sensors, sensor incorporation during the initial design, anticipated operating and failure conditions, and sensor reliability. The extent to which bearings or equipment are monitored may be determined by the impact of failure, such as installing more or more sophisticated sensors in systems where unexpected or undetected bearing failures would be costly or severe. To assess torsion, sensors may include angular position sensors, angular velocity sensors, angular acceleration sensors, etc.

The system evaluation circuit 9408 may process the detected values to obtain information about one or more rotating components being monitored. The torsional analysis circuit 9412 may be configured to identify torsion in a component or system based on predicted conditions, past conditions, system geometry, etc., as obtained from the data storage circuit 9414. The torsional analysis circuit 9412 may be configured to identify torsion using various techniques, such as the difference in amplitude, phase, or frequency of detected values from two linear acceleration sensors positioned at different locations on a shaft. The torsional analysis circuit 9412 may identify torsion using the difference in amplitude and phase between an angular acceleration sensor mounted on the shaft and an angular acceleration sensor mounted on a slip ring at the end of the shaft. The torsional analysis circuit 9412 may identify shear stress/elongation in a component using two strain gauges in a half-bridge configuration or four strain gauges in a full-bridge configuration. The torsional analysis circuit 9412 may use coder-based techniques, such as markers, to identify rotation of a shaft, bearing, rotor, stator, gear, or other rotating component. The markers evaluated may include visual markers such as gear teeth or stripes on a shaft that are imaged by an image sensor or photodetector. The markers evaluated may also include magnetic components located on rotating components and sensed by an electromagnetic pickup. The sensor may also be a Hall Effect sensor.

Additional input sensors may include thermometers, heat flux sensors, magnetometers, axial load sensors, radial load sensors, acceleration sensors, shear stress torque sensors, and torsion angle sensors. The torsion angle may provide rotational information or angular velocity or angular acceleration information at two locations on the shaft. In an embodiment, the sensors may be located at different ends of the shaft.

The torsional analysis circuitry 9412 may include one or more of a transient signal analysis circuitry and/or a frequency conversion circuitry and/or a frequency analysis circuitry, as described elsewhere herein.

In embodiments, the transient signal analysis circuitry for torsional analysis may include envelope modulation analysis and other transient signal analysis techniques. The system evaluation circuitry 9408 may store long streams of detected values in the data storage circuitry 9414. The transient signal analysis circuitry may use envelope analysis techniques on those long streams of detected values to identify transient effects (such as shocks) that may not be identified using traditional sinusoidal analysis (such as FFT).

In embodiments, frequencies of interest may include identifying energy in the bandwidth of relevant orders of rotating equipment. The maximum observed order may be constructed as a function of the system bandwidth and the rotational speed of the component. For varying speeds (run-up, run-down, etc.), the minimum rotational speed may determine the maximum observed order. In embodiments, torsional resonance may occur at a harmonic of the forcing frequency/frequency at which the component is being driven.

In an illustrative and non-limiting example, a monitoring device may be used to collect and process sensor data to measure the twist of a component. The monitoring device may communicate with or include a high-resolution, high-speed vibration sensor to collect data over a long enough period of time to measure multiple cycles of rotation. For gear-driven equipment, the sampling resolution should be such that the number of samples per cycle is at least equal to the number of gears driving the component. Lower sampling resolutions can be used, but they may result in less reliable determinations, and data must be acquired over a longer period of time to achieve sufficient statistical confidence. This data can be used to generate an equipment phase reference (relative probe) or tachometer signal. This phase reference can be used to align phase data, such as velocity, position, or acceleration data, from multiple sensors located at different locations on a component or on different components within a system. This information may facilitate determining the twist of different components or generating an operational deflection shape (ODS), which indicates the degree of twist of one or more components during operational modes.

High-resolution data streams can provide additional data for detecting transient signals in slow-speed operation. Identifying transient signals may help identify equipment or component defects.

In an illustrative and non-limiting example, a monitoring device can be used to identify mechanical jitter for use in failure prediction models. The monitoring device may begin acquiring data when the equipment starts up and ramps up to operating speed, or while it is operating. Once operating speed is reached, torsional jitter is expected to be minimal, and changes in torsion at this stage may indicate cracks, bearing failures, etc. Additionally, removing known torsions from the signal can facilitate identification of unexpected torsions due to system design flaws or component wear. Having phase information relative to data collected at operating speed can facilitate identification of vibration sources and potential component wear. Relative phase information from multiple sensors located throughout the machine facilitates evaluation of torsion propagating through the equipment.

The system evaluation circuit 9408 may perform component life predictions, component health parameter identification, component performance parameter identification, etc. based on the output of its various components. The system evaluation circuit 9408 may identify unexpected twisting of rotating components, or may identify strains and stresses in flexure bearings, etc. The system evaluation circuit 9408 may identify optimal operating parameters for the equipment to reduce twisting and extend component life. The system evaluation circuit 9408 may identify twisting at selected operating frequencies (e.g., shaft rotation speeds). Information regarding operating frequencies that cause twisting may facilitate future operational balancing of the equipment.

The system evaluation circuit 9408 may communicate with the data storage circuit 9414 to access equipment specifications, equipment geometry, bearing specifications, component materials, predicted state information for multiple component types, operating history, past detected values, etc., to evaluate the output of its various components. The system evaluation circuit 9408 may buffer intermediate data, such as a subset of multiple detected values, time-based detected values, time-based detected values converted to frequency information, and filtered detected values. The system evaluation circuit 9408 may also periodically save certain detected values to the data storage circuit 9414. The system evaluation circuit 9408 may periodically store certain detected values in the data storage circuit 9414 to enable tracking of component performance over time. In embodiments, the system evaluation circuit 9408 may store data in the data storage circuit 9414 based on the conformance of the data to one or more criteria, as described throughout this disclosure, based on associated operating conditions and/or failure modes that may occur when detected values approach one or more criteria. Based on one sensor input meeting or approaching a specified criterion or range, the system evaluation circuit 9408 may store additional data in the data storage circuit 9414, such as rotational speed information, component load, temperature, pressure, vibration, or other sensor data of the type described throughout this disclosure. The system evaluation circuit 9408 may store data in the data storage circuit at a higher data rate to allow for greater granularity in future processing, the ability to reprocess at different sampling rates, and/or diagnostic or post-processing of system information that flags operational data of interest.

Depending on the type of device, the component being measured, the environment in which the device is operating, etc., the sensor 9406 may comprise one or more of the following, without limitation: displacement sensors, angular velocity sensors, angular accelerometers, vibration sensors, optical vibration sensors, thermometers, hygrometers, voltage sensors, current sensors, accelerometers, speed detectors, optical or electromagnetic sensors (e.g., for determining temperature, composition and/or spectral analysis, and/or the position or movement of an object); image sensors, structured light sensors, laser image sensors, infrared sensors, acoustic wave sensors, heat flux sensors, displacement sensors, turbidity meters, viscometers, load sensors, triaxial vibration sensors, accelerometers, tachometers, thermometers, voltage sensors, current sensors, accelerometers, speed sensors, optical sensors, electromagnetic sensors (e.g., for determining temperature, composition, spectral analysis, the position or movement of an object); accelerometers, tachometers, fluid pressure meters, air flow meters, horsepower meters, flow meters, fluid particle detectors, acoustic sensors, pH sensors, etc., including, but not limited to, any of the sensors described in this disclosure and references.

Sensor 9406 may provide a stream of data over time that has a phase component, such as that related to angular velocity, angular acceleration, or vibration, allowing for evaluation of phase or frequency analysis of different operational aspects of a portion or operating part of a device. Sensor 9406 may also provide a stream of data that does not have a traditional phase component, such as temperature, humidity, load, etc. Sensor 9406 may provide a continuous or near-continuous stream of data over time, periodic readings, event-driven readings, and/or readings according to a selected interval or schedule.

As an illustrative and non-limiting example, when evaluating engine components, it may be desirable to remove vibrations due to the timing of piston vibrations or expected vibration inputs due to crankshaft geometry to help identify other torsional forces on the component. This allows the health of various components, such as automotive water pumps and positive displacement pumps, to be evaluated.

In an illustrative and non-limiting example, torsion analysis and identification of torsion variations can be useful in identifying stick-slip in gear or transmission systems. In some cases, this may only occur once per cycle, and phase information can be as important, or even more important, than signal amplitude in determining the state and behavior of the system.

In an illustrative and non-limiting example, torsion analysis can assist in identifying, predicting (e.g., timing), and evaluating drivetrain lash and subsequent torsion resulting from changes in direction or activation, which can be used to control the system, assess maintenance needs, assess the need for balancing or other component resetting, etc.

In an illustrative and non-limiting example, when evaluating a compressor, it may be desirable to filter out vibrations due to the timing of piston vibrations and expected vibration inputs associated with the technology and geometry used in the positive displacement compressor to help identify other torsional forces on the component. This may be useful in assessing the health of compressors in a variety of environments, such as factory air conditioners, gas processing system compressors in industrial environments, and oil field compressors, as described elsewhere herein.

In illustrative and non-limiting examples, torsional analysis can facilitate understanding of the health and life expectancy of various components associated with the drivetrains of vehicles such as cranes, bulldozers, tractors, transport vehicles, backhoes, forklifts, agricultural machinery, mining machinery, boring and digging machines, excavators, lifting machines, mixers (e.g., cement mixers), refrigerated trucks, and security vehicles (e.g., containing safes and similar equipment for storing valuables). Also included are drivelines for moving equipment such as assembly lines, lifts, cranes, conveyors, and material handling systems. Evaluating sensor data with a model of the system's geometry and operating conditions can be useful in identifying unexpected torsion and its transmission from the motor to the driveshaft, from the driveshaft to the universal joint, and from the universal joint to one or more wheel axles.

In an illustrative and non-limiting example, torsional analysis can facilitate understanding of the health and expected lifespan of various components associated with train/tram wheels and wheelsets. As discussed above, torsional analysis can facilitate identification of stick-slip between the wheel or wheelset and the rail. Torsional analysis that takes into account the system geometry can facilitate identification of torsional vibrations due to stick-slip, as opposed to torsional vibrations due to the drive geometry connecting the engine, drive shaft, and wheelset.

In embodiments, as illustrated in FIG. 83, the sensor 9406 may be part of a data monitoring device 9400, sometimes referred to herein as a data collector, which may sometimes constitute a mobile or portable data collector. In embodiments, as shown in FIGS. 84 and 85, one or more external sensors 9422, not explicitly part of the monitoring device 9416 but new, previously attached to, or integrated into a device or component, may be randomly connected to or accessed by the monitoring device 9416. The monitoring device 9416 may include a controller 9418. The controller 9418 may include a data acquisition circuit 9420, a data storage circuit 9414, a system evaluation circuit 9408, and optionally a response circuit 9410. The system evaluation circuit 9408 may include a torsion analysis circuit 9412. The data acquisition circuit 9420 may include one or more input ports 9424. In embodiments such as that shown in FIG. 85 , the data acquisition circuit 9420 may further include a wireless communication circuit 9426. The external sensors 9422 may be directly connected to one or more input ports 9424 of the data acquisition circuit 9420 of the controller 9418, or may be accessed wirelessly by the data acquisition circuit 9420 using the wireless communication circuit 9426 via a reader, interrogator, or other wireless connection, such as over a short-range wireless protocol. The data acquisition circuit 9420 may use the wireless communication circuit 9426 to access the sensed values corresponding to the one or more external sensors 9422 wirelessly, via another source, or some combination of these methods.

In an embodiment, as shown in FIG. 86, the data acquisition circuit 9432 may further include a multiplexer circuit 9434, as described elsewhere herein. The output from the multiplexer circuit 9434 may be utilized by the system evaluation circuit 9408. The response circuit 9410 may have the ability to turn portions of the multiplexer circuit 9434 on or off. The response circuit 9410 may have the ability to control a control channel of the multiplexer circuit 9434.

The response circuit 9410 may initiate actions based on component performance parameters, component health values, component life prediction parameters, etc. The response circuit 9410 may evaluate the results of the system evaluation circuit 9408 and initiate actions based on certain criteria or outputs from various components of the system evaluation circuit 9408. Criteria may include identification of torsion on a component by a torsion analysis circuit. Criteria may include sensor readings at specific frequencies or phases relative to a timer signal, where the frequencies or phases of interest may be based on equipment geometry, equipment control scheme, system inputs, historical data, current operating conditions, and/or expected responses. Criteria may include sensor readings at specific frequencies or phases relative to readings from a second sensor. Criteria may include signal strength at specific resonant frequencies/harmonics compared to readings associated with a system tachometer or expected based on equipment geometry and operating conditions. The criteria may include a predetermined peak value of a detection value from a particular sensor, the cumulative value of the sensor's corresponding detection value over time, the change in the peak value, the rate of change of the peak value, and/or the cumulative value (e.g., time spent above/below a threshold, weighted time spent above/below one or more thresholds, and/or area of the detection value above/below one or more thresholds). The criteria may be comprised of a combination of data from different sensors, such as relative values, relative changes in values, relative rates of change in values, or relative values over time. The relative criteria may vary depending on other data or information, such as the stage of the process, the type of product being processed, the type of equipment, ambient temperature or humidity, or external vibrations from other equipment. The relative criteria may be reflected in one or more calculated statistics or metrics (including those generated by further calculations on multiple criteria or statistics), and these metrics may be used for processing (either on-board the data collector or by an external system), such as by providing input to one or more machine learning capabilities described in this disclosure. It can also be used as a data element that serves as input to other systems, such as data streams or data packages that can be used in systems like data marketplaces, SCADA systems, remote control systems, maintenance systems, and analytics systems.

In embodiments, although the specification describes a detected value as exceeding a threshold or predetermined value, the detected value may also be below the threshold or predetermined value. For example, a change in the detected value may be expected to occur, but the detected value indicates that a change may not have occurred. Unless the context clearly indicates otherwise, any statement herein describing a determination of a value above a threshold and/or a value above a predetermined or expected value will be understood to include a determination of a value below a threshold and/or a value below a predetermined or expected value.

The predetermined tolerances may be based on expected twist based on equipment geometry, delivery system geometry, equipment configuration, or control strategies such as piston firing order. The predetermined tolerances may also be based on past or predicted performance, such as a long-term analysis of signals and performance from past runs and the past several runs. The predetermined tolerances may also be based on past or predicted performance, or on a long-term analysis of signals and performance across multiple similar pieces of equipment or components (both within a specific environment, within an individual company, within multiple companies in the same industry, and across companies in different industries). The predetermined tolerances may also be based on correlations between sensor data and actual equipment or component performance.

In some embodiments, an alarm may be issued based on some of the criteria described above. In embodiments, the relative criteria for an alarm may vary depending on other data or information, such as the process stage, the type of product being processed by the equipment, the ambient temperature and humidity, external vibrations from other equipment, etc. In illustrative and non-limiting examples, the response circuit 9410 may respond if component twist across multiple components exceeds a predetermined maximum value, exceeds a predetermined tolerance, and/or if a cumulative value based on the amplitude and frequency of twist exceeds a threshold.

In embodiments, the response circuitry 9410 may cause the data acquisition circuitry 9432 to enable or disable processing of detection values corresponding to a particular sensor based on some of the criteria described above. This may include switching to a sensor with a different response speed, sensitivity, range, etc., accessing a new sensor or sensor type, etc. The switching may be based on a model, a set of rules, etc. In embodiments, the switching is under the control of a machine learning system, where the switching is controlled based on one or more success metrics combined with input data over a series of trials, which may occur under the supervision of a human supervisor or under the control of an automated system. The switching may include switching from one input port to another input port (e.g., switching from one sensor to another). The switching may include changing the multiplexing of data, such as combining different streams under different conditions. The switching may include triggering the system to acquire additional data. For example, a mobile system (such as a robotic or drone system) may be moved to a location where different or additional data is available (such as positioning an image sensor for a different view or a sonar sensor for a different collection direction) or where different sensors are accessible (such as moving a collector to connect to sensors located at different locations in the environment via wired or wireless connections). This switching can be accomplished by changing the control signal of the multiplexer circuit 9434 and/or by turning certain inputs of the multiplexer circuit 9434 on or off.

The response circuit 9410 may calculate the transmission effect based on the difference between the measured and theoretical values of the angular position and speed of the output shaft after taking into account the gear ratio and the phase difference between the input and output.

The response circuitry 9410 may identify equipment or components that require maintenance. The response circuitry 9410 may make recommendations for future replacement of particular sensors with sensors having different response speeds, sensitivities, ranges, etc. The response circuitry 9410 may recommend design changes for future implementations of components, pieces of equipment, operating conditions, processes, etc.

In embodiments, the response circuitry 9410 may recommend maintenance during upcoming process shutdowns or may initiate a maintenance call. The response circuitry 9410 may recommend changes to process or operating parameters to remotely balance equipment. In embodiments, the response circuitry 9410 may implement or recommend process changes, such as reducing the utilization of a component that is nearing a maintenance interval, operating informally, or has failed but is at least partially operational for its intended purpose; changing the operating speed of a component (e.g., placing it in a low-demand mode); initiating remediation of the problem (e.g., signaling for additional lubrication of a roller bearing set or signaling for an alignment process for an out-of-balance system); etc.

In embodiments such as those shown in FIGS. 87, 88, 89, and 90, the data monitoring system 9460 may include at least one data monitoring device 9448. The at least one data monitoring device 9448 may include a sensor 9406 and a controller 9438 including a data acquisition circuit 9404, a system evaluation circuit 9408, a data storage circuit 9414, and a communications circuit 9442. The system evaluation circuit 9408 may include a torsion analysis circuit 9412. Optional response circuitry may also be present, as described above and elsewhere herein. The system evaluation circuit 9408 may periodically share data with the communications circuit 9442 for transmission to the remote server 9440 to enable the monitoring application 9446 to track component and equipment performance over time and under various conditions. Because sensor values approaching one or more criteria may indicate an associated operating condition and/or failure mode, the system evaluation circuit 9408 may share data with the communications circuit 9462 for transmission to the remote server 9440 based on the data's conformance to one or more criteria. Based on one sensor input meeting or approaching a specified criterion or range, the system evaluation circuit 9408 may share additional data for transmission, such as rotational speed, component load, temperature, pressure, vibration, etc. The system evaluation circuit 9408 may also share and transmit data at a higher data rate to increase the granularity of processing at the remote server. In embodiments, as shown in FIG. 87, the communications circuit 9442 may communicate data directly to the remote server 9440. In embodiments, as shown in FIG. 88, the communications circuit 9442 may communicate data to an intermediate computer 9450, which may include a processor 9452 executing an operating system 9454 and a data storage circuit 9456.

In embodiments, as shown in FIGS. 89 and 90, the data collection system 9458 may have multiple monitoring devices 9448 collecting data for multiple components within a single device, may collect data for the same component across multiple devices (both the same and different types) within the same facility, or may collect data from monitoring devices within multiple facilities. A monitoring application 9446 on the remote server 9440 may receive and store one or more of the detected values, timing signals, and data from the multiple, various monitoring devices 9448. In embodiments, as shown in FIG. 89, the communications circuitry 9442 may communicate data directly to the remote server 9440. In embodiments, as shown in FIG. 90, the communications circuitry 9442 may communicate data to an intermediate computer 9450 including a processor 9452 executing an operating system 9454 and a data storage circuitry 9456. There may be an individual intermediate computer 9450 associated with each monitoring device 9264, or an individual intermediate computer 9450 may be associated with multiple monitoring devices 9448, where the intermediate computer 9450 may collect data from multiple data monitoring devices and send the accumulated data to the remote server 9440.

The monitoring application 9446 may select subsets of sensed values, timing signals, data, product performance, etc. for joint analysis. Subsets for analysis may be selected based on component type, component material, or a single type of equipment on which the components operate. Subsets of analysis may be selected or grouped based on common operating conditions or operating history, such as load size, operating conditions (e.g., intermittent, continuous), operating speed or tachometer, common ambient environmental conditions such as humidity, temperature, or air or fluid particulates. Subsets of analysis may be selected based on common expected state information. Subsets of analysis may also be selected based on the influence of other peripheral equipment, such as machinery rotating at similar frequencies, equipment generating electromagnetic fields, equipment generating heat, equipment inducing motion or vibration, equipment emitting vapors, chemicals, or particulates, or the impact of other potential interference or disturbances.

The monitoring application 9446 may analyze a selected subset. In an illustrative example, data from a single component may be analyzed over different time periods, such as one operating cycle, cycle-to-cycle comparisons, or trends over multiple operating cycles/time periods, such as a month, a year, or the life of the component. Multiple parts of the same type may also be analyzed over different time periods. Trends in data, such as changes in frequency or amplitude, may correlate with records of failures or maintenance associated with the same component or equipment. Trends in data, such as rates of change associated with startup or different points in a process, may also be identified. Additional data may be introduced into the analysis, such as data indicating output product quality, output volume (e.g., per unit time), or process success or failure. Correlations between trends and values in different types of data may be analyzed, and short-term analysis may identify parameters that may provide the best prediction of expected performance. Analysis may identify refinements to models for expected condition information, recommendations regarding sensors to use, sensor placement, etc. Analysis may identify additional data to collect and store. Analysis may identify necessary maintenance or repairs and/or recommendations regarding scheduling preventative maintenance. The analysis may identify recommendations for purchasing replacement parts and when to replace them. The analysis may reveal recommendations for future geometry changes to reduce twisting of components. The analysis may also result in warnings about the risk of a catastrophic failure condition. This information can be sent to the monitoring device to update the types of data collected and analyzed locally and/or influence the design of future monitoring devices.

In embodiments, the monitoring application 9446 may access equipment specifications, equipment geometry, component specifications, component materials, predicted state information for multiple component types, operating history, past detection values, component life models, etc., to analyze the selected subset using rule-based or model-based analysis. In embodiments, the monitoring application 9446 may feed the selected subset to a neural net that learns to recognize various operating conditions, health conditions (e.g., life prediction), and fault conditions using deep learning techniques. In embodiments, a hybrid of the two techniques (model-based learning and deep learning) may be used.

In an illustrative and non-limiting example, the torsion analysis techniques, data monitoring devices, and data collection systems described herein can be used to monitor the health of rotating parts on assembly line conveyors and lifters.

In an illustrative and non-limiting example, the health of rotating components in a water pump on an industrial vehicle can be monitored using the torsional analysis techniques, data monitoring devices, and data collection systems described herein.

In an illustrative and non-limiting example, the data monitoring devices and data collection systems described herein can be used to monitor the health of rotating components in a compressor of a gas processing system.

In an illustrative and non-limiting example, the health of rotating components in compressors located in gas and oil fields can be monitored using the data monitoring devices and data acquisition systems described herein.

In an illustrative and non-limiting example, the techniques, data monitoring devices, and data collection systems described herein can be used to assess the health of rotating components in a factory air conditioning unit.

In an illustrative and non-limiting example, the health of rotating components in a factory mineral pump can be assessed using the techniques, data monitoring devices and data collection systems described herein.

In an illustrative and non-limiting example, the health of rotating components such as shafts, bearings, and gears in drilling machines and screwdrivers located in oil and gas fields can be assessed using the torsional analysis techniques, data monitoring devices, and data collection systems described herein.

In an illustrative and non-limiting example, the health of rotating components such as shafts, bearings, gears, and rotors of motors located in oil and gas fields can be assessed using the torsional analysis techniques, data monitoring devices, and data acquisition systems described herein.

In an illustrative and non-limiting example, the health of rotating components such as blades and screws in pumps located in oil and gas fields can be assessed using the torsional analysis techniques, data monitoring devices, and data collection systems described herein.

In an illustrative and non-limiting example, the health of rotating components such as shafts, bearings, motors, rotors, stators, and gears of vibratory conveyors located in oil and gas fields can be assessed using the torsional analysis techniques, data monitoring devices, and data collection systems described herein.

As an illustrative and non-limiting example, the health of rotating components such as bearings, shafts, motors, rotors, stators, and gears in mixers located in oil and gas fields can be assessed using the torsional analysis techniques, data monitoring devices, and data acquisition systems described herein.

In an illustrative and non-limiting example, the health of rotating components such as bearings, shafts, motors, rotors, stators, and gears in centrifuges located in oil and gas refineries can be assessed using the torsional analysis techniques, data monitoring devices, and data collection systems described herein.

In an illustrative and non-limiting example, the health of rotating components such as bearings, shafts, motors, rotors, stators, and gears in refinery tanks located in oil and gas refineries can be assessed using the torsional analysis techniques, data monitoring devices, and data collection systems described herein.

In an illustrative and non-limiting example, the health of rotating components such as bearings, shafts, motors, rotors, stators, and gears in rotating tank/mixer agitators deployed in chemical and pharmaceutical manufacturing lines to facilitate chemical reactions can be evaluated using the torsional analysis techniques, data monitoring devices, and data collection systems described herein.

In an illustrative and non-limiting example, the health of rotating components such as bearings, shafts, motors, rotors, stators, and gears in mechanical/rotary agitators deployed in chemical and pharmaceutical manufacturing lines to facilitate chemical reactions can be assessed using the torsional analysis techniques, data monitoring devices, and data acquisition systems described herein.

In an illustrative and non-limiting example, the health of rotating components such as bearings, shafts, motors, rotors, stators, and gears in propeller agitators deployed in chemical and pharmaceutical manufacturing lines to promote chemical reactions can be assessed using the torsional analysis techniques, data monitoring devices, and data collection systems described herein.

In an illustrative and non-limiting example, the health of bearings and associated shafts, motors, rotors, stators, gears, and other components of a vehicle steering mechanism can be assessed using the torsional analysis techniques, data monitoring devices, and data acquisition systems described herein.

In an illustrative and non-limiting example, the torsional analysis techniques, data monitoring devices, and data collection systems described herein can be used to assess the health of vehicle engine bearings and associated shafts, motors, rotors, stators, gears, and other components.

In an embodiment, a monitoring device for estimating the expected life of a rotating component of an industrial machine may include a data acquisition circuit configured to interpret a plurality of detected values, each of the detected values corresponding to at least one of a plurality of input sensors, the plurality of input sensors including at least one of an angular position sensor, an angular velocity sensor, and an angular acceleration sensor arranged to measure the rotating component; a data storage circuit configured to store specifications, system geometry, and expected condition information for the plurality of rotating components, store past performance of the components, and buffer the detected values for a predetermined time; a torsional analysis circuit configured to analyze the buffered detected values in relation to the specifications and expected condition information of the rotating component using transient signal analysis to identify torsional vibrations; and a system analysis circuit configured to identify the expected life of the rotating component using the identified torsional vibrations and at least one of the expected condition, past data, and system geometry. In an embodiment, the monitoring device may further include a response circuit that performs at least one action in response to the expected lifespan of the rotating component, and the plurality of input sensors include at least two sensors selected from the group consisting of a temperature sensor, a load sensor, an optical vibration sensor, an acoustic wave sensor, a heat flux sensor, an infrared sensor, an acceleration sensor, a three-axis vibration sensor, a tachometer, etc. The at least one action may include issuing at least one of a warning and an alarm, storing additional data in a data storage circuit, ordering replacement of the rotating component, scheduling replacement of the rotating component, recommending a replacement for the rotating component, etc.

In an embodiment, a monitoring device for assessing the health of a rotating component of industrial machinery may include a data acquisition circuit configured to interpret a plurality of detected values, each corresponding to at least one of a plurality of input sensors, the plurality of input sensors including at least one of an angular position sensor, an angular velocity sensor, and an angular acceleration sensor arranged to measure the rotating component. The data acquisition circuit may also include a data storage circuit configured to store a plurality of rotating equipment specification, system geometry, and expected state information, store past equipment performance, and buffer the detected values for a predetermined time. The data storage circuit may also include a torsional analysis circuit configured to utilize transient signal analysis to analyze the buffered detected values in relation to the rotating component specification and expected state information to identify torsional vibrations. The system analysis circuit may also include a system analysis circuit configured to utilize the identified torsional vibrations and at least one of the expected state, historical data, and system geometry to identify the health of the rotating component. In an embodiment, the monitoring device may further include a response circuit configured to perform at least one action in response to the health of the rotating component. The plurality of input sensors may include at least two sensors selected from the group consisting of a temperature sensor, a load sensor, an optical vibration sensor, an acoustic wave sensor, a heat flux sensor, an infrared sensor, an acceleration sensor, a three-axis vibration sensor, a tachometer, etc. The monitoring device may issue a warning or alarm as at least one action, such as storing additional data in a data storage circuit, instructing replacement of the rotating component, scheduling replacement of the rotating component, or recommending a replacement for the rotating component.

In an embodiment, a monitoring device for evaluating the operating condition of a rotating component of industrial machinery may include a data acquisition circuit configured to interpret a plurality of detected values, each of the detected values corresponding to at least one of a plurality of input sensors, the plurality of input sensors including at least one of an angular position sensor, an angular velocity sensor, and an angular acceleration sensor arranged to measure the rotating component. The data acquisition circuit may also include a data storage circuit configured to store specifications, system geometry, and predicted state information for the plurality of rotating components, store past performance of the components, and buffer the detected values for a predetermined period of time. A torsional analysis circuit configured to analyze the buffered detected values in relation to the specifications and predicted state information of the rotating components using transient signal analysis to identify torsional vibrations. A system analysis circuit configured to identify the operating condition of the rotating component using the identified torsional vibrations and at least one of the predicted state, past data, and system geometry. In an embodiment, the operating condition may be a current operating condition or a future operating condition. A response circuit may perform at least one action in response to the operating condition of the rotating component. The at least one action may include storing additional data in a data storage circuit, ordering replacement of the rotating component, scheduling replacement of the rotating component, recommending a replacement for the rotating component, etc.

In one embodiment, a monitoring device for assessing the operating condition of a rotating component of industrial machinery includes a data acquisition circuit configured to interpret a plurality of detected values, each corresponding to at least one of a plurality of input sensors, the plurality of input sensors including at least one of an angular position sensor, an angular velocity sensor, and an angular acceleration sensor arranged to measure the rotating component. The data acquisition circuit also includes a data storage circuit configured to store a plurality of rotating equipment specifications, system geometry, and expected condition information, store past equipment performance, and buffer the detected values for a predetermined period of time; a torsional analysis circuit configured to compare the buffered detected values with the rotating component specifications and expected condition information using transient signal analysis to identify torsional vibrations; and a system analysis circuit configured to identify the operating condition of the rotating component using the identified torsional vibrations and at least one of the expected condition, historical data, and system geometry. The data acquisition circuit includes a multiplexer circuit configured to select an alternative combination of the detected values based on at least one of a user input, the detected condition, and a selected operating parameter of the machine. The operating condition may be a current operating condition or a future operating condition. The at least one operation may enable or disable one or more portions of the multiplexer circuit or modify a multiplexer control line. The data acquisition circuit may include at least two multiplexer circuits, and the at least one operation may comprise modifying a connection between the at least two multiplexer circuits.

In an embodiment, a system for assessing the operating condition of a rotating component of equipment may include a data acquisition circuit configured to interpret a plurality of detected values, each of the detected values corresponding to at least one of a plurality of input sensors, the plurality of input sensors including at least one of an angular position sensor, an angular velocity sensor, and an angular acceleration sensor arranged to measure the rotating component; a data storage circuit configured to store a plurality of rotating component specifications, system geometry, and predicted state information, store past equipment performance, and buffer the detected values for a predetermined period of time; a torsional analysis circuit configured to analyze the buffered detected values in relation to the rotating component specifications and predicted state information using transient signal analysis to identify any torsional vibrations; and a system analysis circuit configured to identify the operating condition of the rotating component using at least one of the torsional vibrations, the predicted state, the past data, and the system geometry. The system includes a communications module for communicating rotating equipment operating conditions, torsional vibrations, and detected values to a remote server, the communicated detected values being based in part on the operating conditions and torsional vibrations of the rotating equipment; and a monitoring application on the remote server configured to receive, store, and collaboratively analyze a subset of detected values from the monitoring devices. Analysis of the subset of detected values may include transient signal analysis to identify the presence of high-frequency torsional vibrations. The monitoring application may be configured to subset detected values based on the operating condition, the torsional vibration, the type of rotating component, the operating condition under which the detected values were measured, and the type or equipment. Analysis of the subset of detected values may include providing the subset of detected values and supplemental information to a neural net and training it to recognize various operating, health, and fault conditions using deep learning techniques. The supplemental information may include any of component specifications, component performance, equipment specifications, equipment performance, maintenance records, repair records, predicted condition models, etc. The operational state may include a current operating state or a future operating state. The monitoring device may include a response circuit that takes at least one action in response to the operating condition of the rotating component. The at least one action may include storing additional data in a data storage circuit.

In an embodiment, a system for assessing the health of a rotating component of equipment may include a data acquisition circuit configured to interpret a plurality of detected values, each corresponding to at least one of a plurality of input sensors, the plurality of input sensors including at least one of an angular position sensor, an angular velocity sensor, and an angular acceleration sensor arranged to measure the rotating component; a data storage circuit configured to store specifications, system geometry, and expected state information for the plurality of rotating components, store past component performance, and buffer the detected values for a predetermined period of time; and a torsional analysis circuit configured to analyze the buffered detected values in relation to the specifications and expected state information for the rotating component and utilize transient signal analysis to identify torsional vibrations. The system includes a system analysis circuit configured to utilize at least one of torsional vibration, predicted state, historical data, and system geometry to identify a health state of the rotating component; a communications module configured to communicate the health state of the rotating component, the torsional vibration, and the detected values to a remote server, the communicated detected values being based in part on the health state and the torsional vibration of the rotating component; and a monitoring application on the remote server configured to receive, store, and collaboratively analyze a subset of the detected values from the monitoring devices. In an embodiment, analyzing the subset of detected values may include transient signal analysis to identify the presence of high-frequency torsional vibration. The monitoring application may be configured to subset the detected values. Analyzing the subset of detected values may include providing the subset of detected values and supplemental information to a neural net to learn to recognize various operating, health, and fault conditions using deep learning techniques. The supplemental information may include any of component specifications, component performance, equipment specifications, equipment performance, maintenance records, repair records, and predicted condition models. The operating state may be a current operating state or a future operating state. The response circuit may perform at least one action depending on the health of the rotating component.

In an embodiment, a system for estimating the expected life of a rotating component of equipment may include a data acquisition circuit configured to interpret a plurality of detected values, each of which corresponds to at least one of a plurality of input sensors, the plurality of input sensors including at least one of an angular position sensor, an angular velocity sensor, and an angular acceleration sensor arranged to measure the rotating component; a data storage circuit configured to store a plurality of rotating equipment specifications, system geometry, and expected state information, store past equipment performance, and buffer the detected values for a predetermined period of time; a torsional analysis circuit configured to analyze the buffered detected values in relation to the rotating equipment specifications and expected state information using transient signal analysis to identify torsional vibration; and a system analysis circuit configured to identify the expected life of the rotating equipment using torsional vibration and at least one of the expected state, past data, and system geometry. The communication module may communicate the expected lifespan of the rotating component, the torsional vibration, and the detected values to a remote server, the communicated detected values being based in part on the expected lifespan and the torsional vibration of the rotating component, and a monitoring application on the remote server configured to receive, store, and collaboratively analyze a subset of the detected values from the monitoring device. In an embodiment, analyzing the subset of detected values may include transient signal analysis to identify the presence of high-frequency torsional vibration. The monitoring application may be configured to subset the detected values based on one of the expected lifespan of the rotating component, the torsional vibration, the type of rotating component, the operating conditions under which the detected values were measured, and the type of equipment. Analyzing the subset of detected values may include providing the subset of detected values and supplemental information to a neural net to learn to recognize various operating, health, lifespan, and fault conditions using deep learning techniques. The supplemental information may include any of part specifications, part performance, equipment specifications, equipment performance, maintenance records, repair records, and predicted condition models. The monitoring device may include a response circuit that takes at least one action in response to the expected lifespan of the rotating component. The at least one action may include one of ordering a replacement for the rotating component, scheduling a replacement for the rotating component, and recommending a replacement for the rotating component.

In an embodiment, a system for assessing the health of a variable frequency motor in an industrial environment may include a data acquisition circuit configured to interpret a plurality of detected values, each of the detected values corresponding to at least one of a plurality of input sensors, the plurality of input sensors including at least one of an angular position sensor, an angular velocity sensor, and an angular acceleration sensor arranged to measure a rotating component; a data storage circuit configured to store a plurality of rotating equipment specifications, system geometry, and predicted state information, store past equipment performance, and buffer the detected values for a predetermined period of time; a torsional analysis circuit configured to analyze the buffered detected values in relation to the rotating equipment specifications and predicted state information using transient signal analysis to identify torsional vibrations; and a system analysis circuit configured to identify motor health parameters using at least one of the torsional vibrations, the predicted state, the past data, and the system geometry. The communications module is capable of communicating the motor health parameters, torsional vibration, and the detected values to a remote server, the communicated detected values being based in part on the motor health parameters and torsional vibration, and a monitoring application on the remote server is configured to receive, store, and collaboratively analyze a subset of the detected values from the monitoring device.

In an embodiment, a system for data collection, processing, and torsional analysis of rotating components in an industrial environment may include: a data collection circuit configured to interpret a plurality of sensed values, each of the sensed values corresponding to at least one of a plurality of input sensors, the plurality of input sensors including at least one of an angular position sensor, an angular velocity sensor, and an angular acceleration sensor positioned to measure the rotating component; a streaming circuit configured to stream at least a subset of the sensed values to a distance learning system; and a torsional analysis circuit configured to analyze the sensed values in relation to a machine-based understanding of the condition of the at least one rotating component. The machine-based understanding may be developed based on a model of the rotating component that determines a state of the at least one rotating component based at least in part on a relationship of the rotating component's behavior to an operating frequency of the component of the industrial machine. The state of the at least one rotating component may be at least one of an operating state, a health state, a predicted life state, and a fault state. The machine-based understanding may be developed based on providing input to a deep learning machine, the input consisting of a plurality of streams of detected values of a plurality of rotating components and a plurality of values of measured conditions of the plurality of rotating components. The condition of at least one rotating component may be at least one of an operating condition, a health condition, a predicted life condition, and a fault condition.

In embodiments, information regarding the health or other status or condition information of a component or piece of industrial equipment may be obtained by monitoring the condition of various components throughout a process. Monitoring may include monitoring the amplitude of sensor signals measuring attributes such as temperature, humidity, acceleration, and displacement. One embodiment of a data monitoring device 9700 is shown in FIG. 91 and may include a plurality of sensors 9706 communicatively coupled to a controller 9702. The controller 9702 may include a data acquisition circuit 9704, a signal evaluation circuit 9708, a data storage circuit 9716, and a response circuit 9710. The signal evaluation circuit 9708 may be configured with circuitry to detect failures of one or more sensors or a set of sensors, such as an overload detection circuit 9712, a sensor failure detection circuit 9714, or both. Additionally, the signal evaluation circuit 9708 may optionally include one or more of a peak detection circuit, a phase detection circuit, a bandpass filter circuit, a frequency conversion circuit, a frequency analysis circuit, a phase-locked loop circuit, a torsional analysis circuit, a bearing analysis circuit, etc.

The plurality of sensors 9706 may be wired to ports of the data acquisition circuitry 9704. Alternatively, the plurality of sensors 9706 may be wirelessly connected to the data acquisition circuitry 9704. The data acquisition circuitry 9704 may have access to a sensed value corresponding to the output of at least one of the plurality of sensors 9706, where the sensor 9706 may acquire data regarding different operational aspects of a portion or operating component of a device.

The selection of multiple sensors 9706 for a data monitoring device 9700 designed for a particular component or piece of equipment may depend on various considerations, such as the accessibility to install new sensors, the incorporation of sensors in the initial design, the expected operating and fault conditions, the desired resolution at various locations within the process or plant, and the reliability of the sensors. The impact of failure, the time response of failure (e.g., warning time and/or non-normal modes occurring prior to failure), the likelihood of failure, and/or the sensitivity and/or difficulty required to detect a fault condition may determine the extent to which a component or piece of equipment is monitored, with more sensors and/or more sophisticated sensors being used in systems where unexpected or undetected failures can be costly or have severe consequences.

Depending on the type of equipment, the component being measured, the environment in which the equipment is operating, etc., the sensor 9706 may comprise one or more of the following: vibration sensors, thermometers, hygrometers, voltage and/or current sensors (for components and/or other sensors measuring components), accelerometers, speed detectors, optical or electromagnetic sensors (e.g., for temperature, composition and/or spectral analysis, and/or to determine the position or movement of an object), image sensors, structured light sensors, laser image sensors, thermal imagers, acoustic wave sensors, displacement sensors, turbidity meters, viscometers, axial load sensors, radial load sensors, triaxial sensors, accelerometers, speedometers, tachometers, hydraulic gauges, air flow meters, etc., including, but not limited to, any of the sensors described in this disclosure and references thereto, such as fluid pressure gauges, air flow meters, horsepower meters, flow meters, fluid particle detectors, optical (laser) particle counters, ultrasonic sensors, acoustic sensors, heat flux sensors, galvanic sensors, magnetometers, pH sensors, etc.

The sensor 9706 may provide a stream of data over time that has a phase component, such as that associated with acceleration or vibration, allowing for phase or frequency analysis of different operational aspects of a portion or operating part of a device. The sensor 9706 may also provide a stream of data that does not have a traditional phase component, such as temperature, humidity, load, etc. The sensor 9706 may provide a continuous or near-continuous stream of data over time, periodic readings, event-driven readings, and/or readings according to a selected interval or schedule.

In embodiments, as illustrated in FIG. 91, the sensor 9706 may be part of a data monitoring device 9700, sometimes referred to herein as a data collector, which may sometimes constitute a mobile or portable data collector. In embodiments, as shown in FIGS. 92 and 93, one or more external sensors 9724, not explicitly part of the monitoring device 9718 but newly, previously attached to, or integrated into a device or component, may be opportunistically connected to or accessed by the monitoring device 9718. The monitoring device may include a data acquisition circuit 9722, a signal evaluation circuit 9708, a data storage circuit 9716, and a response circuit 9710. The signal evaluation circuit 9708 may comprise an overload detection circuit 9712, a sensor failure detection circuit 9714, or both. Additionally, the signal evaluation circuitry 9708 may optionally include one or more of a peak detection circuitry, a phase detection circuitry, a bandpass filter circuitry, a frequency conversion circuitry, a frequency analysis circuitry, a phase-locked loop circuitry, a torsion analysis circuitry, a bearing analysis circuitry, etc. Additionally, the data acquisition circuitry 9722 may include one or more input ports 9726.

The one or more external sensors 9724 may be directly connected to one or more input ports 9726 on the data acquisition circuit 9722 of the controller 9720, or may be accessed wirelessly by a reader or other wireless connection, such as via an interrogator or short-range wireless protocol. In an embodiment, as shown in FIG. 93, the data acquisition circuit 9722 may further include a wireless communication circuit 9730. The data acquisition circuit 9722 may use the wireless communication circuit 9730 to wirelessly access the detected values corresponding to the one or more external sensors 9724, access them via another source, or some combination of these methods.

In an embodiment, the data storage circuit 9716 may be configured to store sensor specifications, expected state information, and detected values. The data storage circuit 9716 may provide the specifications and expected state information to the signal evaluation circuit 9708.

In embodiments, the overload detection circuit 9712 may detect a sensor overload by comparing a detected value associated with a sensor to a detected value associated with a sensor having a greater range/lower resolution monitoring the same component/attribute. A discrepancy in measurements may indicate that the higher resolution sensor is likely overloaded. In embodiments, the overload detection circuit 9712 may detect a sensor overload by evaluating the consistency of the sensor's measurements with measurements from other sensor data (monitoring the same or different aspects of the component/equipment). In embodiments, the overload detection circuit 9712 may detect a sensor overload by evaluating data collected by other sensors to identify conditions that are likely to result in a sensor overload (e.g., heat flux sensor data indicating a sensor at a given location may be overloaded, accelerometer data indicating a velocity sensor may be overloaded, etc.). In embodiments, the overload detection circuit 9712 may detect a sensor overload by identifying a flat-line output followed by an upward trend. In embodiments, the overload detection circuit 9712 may detect a sensor overload by converting the sensor data to frequency data, for example, using an FFT (Fast Fourier Transform), and looking for “ski jumps” in the frequency data that may be due to data clipping due to an overloaded sensor. The sensor fault detection circuit 9714 may identify potential concerns regarding a fault in the sensor itself, the health of the sensor, or the validity of the sensor data. The rate of change of value may be used to identify a failure in the sensor itself. For example, a sudden jump to maximum output may indicate a sensor failure rather than a sensor overload. In embodiments, the overload detection circuit 9712 and/or the sensor fault detection circuit 9712 may utilize sensor specifications, expected state information (e.g., failure, error, invalid data, etc.), sensor model, etc., in identifying a sensor overload. In embodiments, the overload detection circuit 9712 or the sensor fault detection circuit 9714 may use detection values from other sensors or outputs from additional components, such as a peak detection circuit, a phase detection circuit, a bandpass filter circuit, a frequency conversion circuit, a frequency analysis circuit, and/or a phase-locked loop circuit, to identify potential sources of identified sensor overload, sensor fault, or sensor failure. Causes or contributing factors to a sensor overload include limitations in the sensor range, sensor resolution, or sensor sampling frequency. Apparent sensor overloads may result from the range, resolution, or sampling frequency of the multiplexer supplying the detection values associated with the sensor. For example, excessive heat or cold can be associated with damage to semiconductor-based sensors, resulting in erratic sensor data, a sensor's inability to generate data, or data that appears outside of normal operating ranges (e.g., large, discrete changes in temperature in a system that normally does not experience such changes). Current and voltage surges can damage sensors with sensitive electrically connected components. Excessive vibration can physically damage sensitive sensor components, such as wires and connectors. Sudden acceleration or shock indicated by acoustic data can physically damage sensors with sensitive components such as wires and connectors. A sudden increase in humidity or lack of oxygen in the environment surrounding a sensor can cause water damage to the sensor. A sudden loss of signal from a sensor can indicate a disconnection of the sensor due to vibration, shock, or other causes. A power-requiring sensor can be a dead battery or disconnected from a power source. In embodiments, the overload detection circuit 9712 or the sensor failure detection circuit 9714 can output the sensor status, which can be one of sensor overload, sensor failure, sensor health, and the like. The sensor failure detection circuit 9714 can also determine either a sensor failure state or a sensor valid state.

In an embodiment, as shown in FIG. 94, the data acquisition circuit 9722 may further include a multiplexer circuit 9731, as described elsewhere herein. The output from the multiplexer circuit 9731 may be utilized by the signal evaluation circuit 9708. The response circuit 9710 may be capable of turning on or off portions of the multiplexer. Additionally, the response circuit 9710 may be capable of controlling a control channel of the multiplexer circuit 9731.

In embodiments, the response circuit 9710 may initiate various actions based on the sensor status provided by the overload detection circuit 9712. The response circuit 9710 may continue to use the sensor if the sensor status is "sensor healthy." The response circuit 9710 may adjust the sensor's scaling value (e.g., from 100 mV/gram to 10 mV/gram). The response circuit 9710 may increase the acquisition range of an alternate sensor. The response circuit 9710 may back up sensor data from previous calculations and evaluations, such as bearing analysis, torsion analysis, etc. The response circuit 9710 may use predicted or forecast data (based on data acquired before the overload/failure) instead of actual sensor data for calculations and evaluations, such as bearing analysis, torsion analysis, etc. Additionally, the response circuit 9710 may issue an alarm. The response circuit 9710 may issue an alarm that notifies the user that the sensor is out of range and includes information about the extent of the overload, such as "Overload range - data response may not be reliable and/or linear" or "Breakdown range - sensor may be damaged." The response circuit 9710 may also issue an alert containing information about the impact of the sensor load, such as "machine health cannot be monitored" due to sensor overload/failure.

In embodiments, the response circuitry 9710 may cause the data acquisition circuitry 9704 to enable or disable processing of detection values corresponding to particular sensors based on the sensor status described above. This may include switching to a sensor with a different response speed, sensitivity, range, etc., accessing a new sensor or type of sensor, accessing data from multiple sensors, recruiting additional data collectors (e.g., routing collectors to work locations using the routing methods and systems disclosed throughout this disclosure and the documents incorporated by reference), etc. The switching may be based on a model, a set of rules, etc. In embodiments, the switching may be under the control of a machine learning system, such that the switching is controlled based on one or more indicators of success combined with input data in a series of trials that may occur under the supervision of a human supervisor or under the control of an automated system. The switching may include switching from one input port to another input port (e.g., switching from one sensor to another). The switching may include changing the multiplexing of data, such as combining different streams under different conditions. The switching may include triggering the system to obtain additional data. This may include a mobile system (such as a robotic or drone system), movement to a location where different or additional data is available (such as positioning an image sensor for a different view or a sonar sensor for a different collection direction), or movement to a location where different sensors are accessible (such as moving a collector to connect to a sensor located elsewhere in the environment via a wired or wireless connection). This switching may be accomplished by changing the control signal of the multiplexer circuit 9731 and/or by turning certain inputs of the multiplexer circuit 9731 on or off.

In embodiments, the response circuitry 9710 may make recommendations for future replacement of a particular sensor with a sensor having a different response speed, sensitivity, range, etc. The response circuitry 9710 may also recommend design changes for future embodiments of components, pieces of equipment, operating conditions, processes, etc.

In embodiments, the response circuitry 9710 may recommend maintenance or initiate a maintenance call during a future process shutdown, and maintenance may include replacing a sensor with the same or an alternative type of sensor having a different response speed, sensitivity, range, etc. In embodiments, the response circuitry 9710 may implement or recommend a process change, such as reducing the utilization of a component that is nearing a maintenance interval, operating informally, or is faulty but at least partially operational for its intended purpose, changing the operating speed of the component (e.g., placing it in a low-demand mode), initiating remediation of the problem (e.g., signaling additional lubrication of a roller bearing set or signaling an alignment process for an out-of-balance system), etc.

In embodiments, the signal evaluation circuit 9708 and/or the response circuit 9710 may periodically store certain detected values in the data storage circuit 9716 to enable tracking of component performance over time. In embodiments, based on the sensor status, as described elsewhere herein, recently measured sensor data and associated operating conditions, such as RPM, component load, temperature, pressure, vibration, or other sensor data of the type described throughout this disclosure, may be stored in the data storage circuit 9716 to enable backup of overloaded/failed sensor data. The signal evaluation circuit 9708 may store data at higher data rates to enable greater granularity in future processing, the ability to reprocess at different sampling rates, and/or diagnostics or post-processing of system information where operational data of interest has been flagged.

In embodiments such as those shown in FIGS. 95, 96, 97, and 98, the data monitoring system 9726 may include at least one data monitoring device 9728. The at least one data monitoring device 9728 may include a sensor 9706 and a controller 9730 including a data acquisition circuit 9704, a signal evaluation circuit 9708, a data storage circuit 9716, and a communications circuit 9754 that enables data and analysis to be transmitted to a monitoring application 9736 on a remote server 9734. Additionally, the signal evaluation circuit 9708 may include at least an overload detection circuit 9712. The signal evaluation circuit 9708 may periodically share data with the communications circuit 9732 to transmit to the remote server 9734, enabling the monitoring application 9736 to track component or equipment performance over time and under various conditions. Based on the state of the sensor, the signal evaluation circuit 9708 and/or the response circuit 9710 may share data with the communication circuit 9732 for transmission to a remote server 9734 based on the suitability of the data against one or more criteria. The data may include recent sensor data and additional data for transmission, such as RPM, component load, temperature, pressure, vibration, etc. The signal evaluation circuit 9708 may share and transmit data at a higher data rate to allow for increased granularity of processing at the remote server.

In embodiments such as that shown in FIG. 95, the communications circuitry 9732 may communicate data directly to a remote server 9734. In embodiments such as that shown in FIG. 96, the communications circuitry 9732 may communicate data to an intermediate computer 9738, which may include a processor 9740 executing an operating system 9742 and data storage circuitry 9744.

In embodiments, as shown in Figures 97 and 98, the data collection system 9746 may have multiple monitoring devices 9728 collecting data for multiple components within a single piece of equipment, may collect data for the same component across multiple pieces of equipment (both the same and different types of equipment) within the same facility, or may collect data from monitoring devices within multiple facilities. A monitoring application 9736 on the remote server 9734 may receive and store one or more of the sensing values, timing signals, and data from the multiple, various monitoring devices 9728.

In embodiments, as shown in FIG. 97, the communications circuitry 9732 may communicate data directly to a remote server 9734. In embodiments, as shown in FIG. 98, the communications circuitry 9732 may communicate data to an intermediate computer 9738, which may include a processor 9740 running an operating system 9742 and memory circuitry 9744. There may be a separate intermediate computer 9738 associated with each monitoring device 9728, or a separate intermediate computer 9738 may be associated with multiple monitoring devices 9728, with the intermediate computer 9738 collecting data from the multiple data monitoring devices and transmitting the accumulated data to the remote server 9734. Communication to the remote server 9734 may be streaming, batch (e.g., when a connection is available), or opportunistic.

The monitoring application 9736 may select subsets of detected values to analyze jointly. The subsets for analysis may be selected based on a single type of sensor, component, or a single type of equipment on which the components are operating. The subsets for analysis may be selected or grouped based on common operating conditions, such as load size, operating conditions (e.g., intermittent, continuous), operating speed or tachometer, common ambient environmental conditions such as humidity, temperature, air or fluid particulates, etc. The subsets for analysis may also be selected based on the influence of other peripheral equipment, such as equipment rotating at a similar frequency, generating electromagnetic fields, generating heat, inducing motion or vibration, or emitting vapors, chemicals, or particulates.

In embodiments, the monitoring application 9736 may analyze a selected subset. In an illustrative example, data from a single sensor may be analyzed over different time periods, such as one operating cycle, multiple operating cycles, one month, one year, or the life of a component. Also, data from multiple sensors of a common type measuring the same type of part may be analyzed over different time periods. Trends in the data may be identified, such as rates of change associated with start-up or different points in the process. Correlations between trends and values from different sensors may be analyzed to identify parameters that best predict the expected performance of the sensor in a short-term analysis. This information may be sent to the monitoring device to update the sensor model, sensor selection, sensor range, sensor scaling, sensor sampling frequency, the type of data collected and analyzed locally, or to influence the design of future monitoring devices.

In embodiments, the monitoring application 9736 may access equipment specifications, equipment geometry, component specifications, component materials, predicted state information for multiple sensors, operational history, past detection values, sensor life models, etc., to analyze the selected subset using rule-based or model-based analysis. The monitoring application 9736 may provide recommendations regarding sensor selection, additional data to collect, or data to store with the sensor data. The monitoring application 9736 may provide recommendations regarding scheduling repairs and/or maintenance. The monitoring application 9736 may provide recommendations regarding sensor replacement. The replacement sensor may match the sensor being replaced, or the replacement sensor may have a different range, sensitivity, sampling frequency, etc.

In embodiments, the monitoring application 9736 may include remote learning circuitry configured to analyze sensor status data (e.g., sensor overload, sensor fault, sensor failure) along with data from other sensors, fault data for the component being monitored, the equipment being monitored, the product being produced, etc. The remote learning system may identify correlations between the sensor overload and data from other sensors.

(1) In an embodiment, a monitoring system for collecting data in an industrial environment includes: a data acquisition circuit configured to interpret a plurality of detected values, each of the plurality of detected values corresponding to at least one of a plurality of input sensors; a data storage circuit configured to store sensor specifications, expected state information, and the detected values; and a signal evaluation circuit including: an overload identification circuit configured to determine a sensor overload state for at least one sensor in response to at least one of the plurality of detected values, the expected state information, and the sensor specifications; a sensor fault detection circuit configured to determine one of a sensor fault state and a sensor valid state for the at least one sensor in response to at least one of the plurality of detected values, the expected state information, and the sensor specifications; and a response circuit configured to perform at least one action in response to one of the sensor overload state, the sensor valid state, and the sensor fault state. (2) The monitoring system described in (1), further including a mobile data collector that collects data from the plurality of input sensors. (3) The monitoring system described in clause 1, wherein the at least one action includes issuing an alert or alarm. (4) The monitoring system of (1), wherein the at least one operation further comprises storing additional data in the data storage circuit. (5) The monitoring system of (1), wherein the at least one operation comprises at least one of enabling or disabling one or more portions of a multiplexer circuit and modifying multiplexer control lines. (7) The monitoring system of (5), further comprising at least two multiplexer (MUX) circuits, wherein the at least one operation comprises modifying a connection between the at least two multiplexer circuits. (8) The monitoring system of (7), further comprising a MUX control circuit configured to interpret a subset of the plurality of detected values and thereby provide logical control of a MUX and a correspondence between MUX inputs and detected values, wherein the logical control of the MUX comprises adaptive scheduling of the multiplexer control lines. (9) A system for data collection, processing, and component analysis in an industrial environment, comprising a plurality of monitoring devices, each monitoring device comprising: a data acquisition circuit configured to interpret a plurality of sensed values, each of the plurality of sensed values corresponding to at least one of a plurality of input sensors; a data storage device for storing a plurality of sensor type specifications and expected state information and for buffering the plurality of sensed values for a predetermined period of time; and a signal evaluation circuit comprising: an overload identification circuit responsive to the plurality of sensed values and at least one of the predicted state information and the sensor specifications to determine an overload state of at least one sensor; and a sensor fault detection circuit responsive to the plurality of sensed values and at least one of the predicted state information and the sensor specifications to determine one of a sensor fault state and a sensor valid state of the at least one sensor. The system includes: a response circuit that performs at least one action in response to one of a sensor overload condition, a sensor health condition, and a sensor validity condition; a communication circuit that communicates with a remote server and provides one of the sensor overload condition, the sensor health condition, and the sensor validity condition and a portion of buffered sensed values to the remote server; and a monitoring application on the remote server, configured to: receive at least one selected sensed value and one of the sensor overload condition, the sensor health condition, and the sensor validity condition; collaboratively analyze the subset of sensed values received from a plurality of monitoring devices; and recommend an action. (10) The system of (9), wherein at least one of the monitoring devices further comprises a mobile data collector that collects data from the plurality of input sensors. (11) The system of (9), wherein the at least one action includes issuing an alert or alarm. (12) The monitoring system of (9), wherein the at least one action further includes storing additional data in the data storage circuit. (13) The system of (9), wherein at least one of the monitoring devices further comprises a multiplexer (MUX) circuit. (14) The system of (13), wherein the at least one operation comprises at least one of enabling or disabling one or more portions of a multiplexer circuit and modifying a multiplexer control line. (15) The system of (9), wherein at least one of the monitoring devices further comprises at least two multiplexer (MUX) circuits, and the at least one operation comprises modifying a connection between the at least two multiplexer circuits. (16) The monitoring system of (15), further comprising a MUX control circuit configured to interpret a subset of the plurality of detected values and thereby provide logical control of a MUX and a correspondence between MUX inputs and detected values, the logical control of the MUX comprising adaptive scheduling of the multiplexer control lines. (17) The system of (9), wherein the monitoring application includes a remote learning circuit configured to analyze sensor status data along with the sensor data and identify correlations between sensor overloads and data from other systems. (18) The system of (9), wherein the monitoring application is configured to subset the sensed values based on any of a sensor overload status, a sensor health status, a sensor validity status, an expected lifespan of the sensor associated with the sensed values, an expected type of equipment associated with the sensed values, and an operating condition under which the sensed values were measured. (19) The system of (9), wherein the supplemental information comprises any of sensor specifications, past performance of the sensor, maintenance records, repair records, and an expected condition model. (20) The system of (19), wherein analyzing the subset of sensed values includes providing the subset of sensed values and the supplemental information to a neural net to learn to recognize operational states, health states, lifespans, and fault states of various sensors using deep learning techniques.

Industrial IoT data collection, monitoring, and control environments often have large and diverse sensor sets, making efficient configuration and timely modification of sensor data collection a challenge. Continuous collection from all sensors may be impossible given the large number of sensors and limited resources, such as limited power availability and limited data collection and management facilities, including various limitations on the availability and performance of sensor data collection devices, input/output interfaces, data transfer facilities, data storage, and data analysis facilities. Therefore, the number of sensors collected at any given time may vary depending on the time of initial collection setup and the handling of rapid modification of the current collection scheme based on changes in system state and operational conditions (e.g., alarm conditions, changes in operational mode, etc.). Accordingly, embodiments of the methods and systems disclosed herein may include rapid route creation and modification of routing collectors, utilizing hierarchical templates, performing smart route modifications, and monitoring and responding to changes in operational conditions.

In an embodiment, rapid route creation and modification for data collection in industrial environments can utilize hierarchical templates. Templates may be used to identify machines that can utilize the same hierarchical sensor routing scheme. For example, among the many types of machines from which data may be collected, members of a specific class of motors, such as stepper motors, may have very similar sensor routing needs, such as routine operation, periodic maintenance, and failure mode detection, which may be described in a common hierarchy of sensor collection routines. A user installing a new stepper motor can then use the "Stepper Motor Hierarchical Routing Template" for the new motor. After installation, the Stepper Motor Hierarchical Routing Template can be used to modify the routing scheme as conditions change. Users can optionally adjust the template as needed for unique motor functions, applications, environments, modes, etc. Using templates to deploy routing schemes can significantly reduce the time required to configure routing schemes for new motors or to deploy new routing techniques to existing systems that utilize traditional sensor collection methods. Introducing hierarchical routing templates allows for rapid changes to sensor collection routines based on the template. This allows for rapid route changes in response to changing conditions, such as when a stepper motor's operating mode changes necessitating a change in the subset of sensors being monitored, or when limit alerts or fault indications necessitate a more focused change in the subset of sensors used to diagnose a problem. In this way, hierarchical routing templates not only enable rapid deployment of sensor routing configurations, but also allow the sensed industrial environment to dynamically change in response to changing conditions.

The functional hierarchy of a routing template can include different hierarchical configurations for components, machines, systems, industrial environments, etc., including multiple configurations formed from all sensors and subsets of all sensors. At the system level, an "all sensors" configuration might include a connectivity map for all sensors in the system, a mapping to all onboard instrumentation sensors (e.g., monitoring points reporting within a machine or set of machines), environmental sensors (e.g., monitoring points around a machine/equipment, but not necessarily onboard), and data collection devices (e.g., data collection devices that can flexibly provide different types of specific data) to available sensors, or a unified map that combines different individual mappings. Routing configurations can provide operational routing schemes, scheduled maintenance routing schemes (e.g., collecting from a larger overall set of sensors than operational modes, but distributed across the system or focused on a specific component, function, or mode), or multiple failure mode routing schemes for multiple focused sensor collection groups targeted at different failure mode analyses (e.g., for motors, one failure mode can be collected). For example, in the case of a motor, one failure mode might be the bearings, another might be speed and torque during start-up, and different subsets of sensor data might be required depending on the failure mode (e.g., detected by abnormal readings during operation or maintenance), power saving (e.g., when the plant needs to reduce power due to weather), etc.

As previously mentioned, hierarchical templates may be conditional (e.g., rule-based), e.g., templates that conditionally route based on parameters such as sensed data during a first collection period, resulting in subsequent routing configuration changes. Within a hierarchy, nodes in a graph or tree may indicate forks where conditional logic may be used, such as selecting a predetermined subset of sensors for a given operating mode. In this manner, hierarchical templates may be associated with rule-based or model-based expert systems that facilitate automated routing based on observed conditions, such as the type of machine and its operating state, environmental conditions, etc., based on the hierarchical template. In a non-limiting example, a hierarchical template may have an initial collection configuration and a conditional hierarchy established to switch from the initial collection configuration to a second collection configuration based on sensed conditions from the initial sensor collection. Continuing with this example, a conveyor system, among various possible machines, may have multiple sensors for collection at initial collection, but once the initial data is collected and analyzed, if it is determined that the conveyor is idle (e.g., due to the lack of a signal above a minimum threshold on a motion sensor), the system may switch to a sensor data collection regime appropriate for the conveyor's idle state (e.g., using a very small subset of sensors, e.g., only using the motion sensor to detect departure from the idle state, at which point the original regime can be updated and the remainder of the sensor set can be used again). In this way, if sensor data collection detects a change in state, operating mode, environmental conditions, etc., sensor data collection can be switched to an appropriate configuration.

The hierarchical template of one collector may be based on coordination with the routing of other collectors. For example, rather than collecting all data at each machine, a collector may be configured to perform vibration analysis while another collector is configured to perform pressure or temperature at each machine in a set of similar machines. Alternatively, different sensor types may need to be set up for each collector at each machine. Factors such as the time required for sampling, the time required for sensor configuration, power consumption, the time available for collection overall, the data rates of the sensors and/or collectors, and the bandwidth of the channel (wired or wireless) available for transmitting collected data can be considered when coordinating the routing of two or more collectors, allowing for various parallel and serial configurations to be implemented for an overall effect. This may include using expert systems to optimize the coordination, such as rule-based optimization, model-based optimization, or optimization using machine learning.

The machine learning system may create a hierarchical template structure for improved routing, such as to teach the system default operating conditions (e.g., normal operating mode, system online, average production), peak operating mode (maximum capacity), slack production, etc. The machine learning system may create new hierarchical templates based on monitored conditions, such as templates based on production level profiles, production rate profiles, detected failure mode pattern analysis, etc. The application of new templates created by machine learning may be based on mode matching between current production conditions and machine learning template conditions (e.g., the machine learning system creates a new template for a new production profile and applies the new template whenever the new profile is detected).

Rapid route creation can be enabled using one or more hierarchical routing templates. For example, the routing templates may pre-establish routing schemes for different conditions, and a trigger event may trigger a sensor change to the routing scheme to accommodate the condition. In embodiments, the trigger event may be an automatic change to routing based on a trigger indicating a failure mode that may necessitate a change to the routing scheme from operational to failure mode analysis; a human change to the routing scheme based on received sensor data; or a learned change to routing. Examples include a machine learning when to trigger a change based on a set of human-initiated or human-supervised changes; manual routing changes (e.g., automatic/fast automatic change options); or human-initiated changes based on observed device performance. Routing changes may include changes from operational modes to accelerated maintenance, failure mode analysis, power-saving modes, high-performance/high-power modes (for peak power at power plants), etc.

Switching between hierarchical template configurations may be performed based on the connectivity of end device sensors. In highly automated collection routing environments (e.g., indoor networked assembly plants), different routing collection configurations may be adopted for fixed and flexible industrial layouts. In fixed industrial layouts, such as layouts with a high degree of wired connectivity between end device sensors, automated collection devices, and networks, there may be different routing configurations for the network routing hierarchy, collector sensor collection hierarchy, and storage section. In more flexible industrial layouts, with a variety of wired and wireless connections between end device sensors, automated collection devices, and networks, there may be different schemes. For example, moderately automated collection routing environments may include automated collection with periodic network connectivity, robotic-carried collectors for periodic collection (e.g., automated collection with periodic network connectivity, robotic collectors for periodic collection (e.g., terrestrial robots, drones, underwater devices, robots with network connectivity, robots with intermittent network connectivity, robots that periodically upload collections), routing methods with periodic collection and automatic routing, routing methods that only perform periodic collection but with direct routing at the time of collection, routing methods that perform periodic collection with periodic automatic routing and periodic collection, and routing methods that periodically route multiple collections over time. Less automated collection routing may include the following combinations: automated collection with human-assisted collectors (e.g., humans collecting alone, humans assisted by robots), scheduled collection with human-assisted collectors (e.g., humans initiate collection, humans assisted by robots to initiate collection, humans launch drones to collect data remotely), etc.

In an embodiment, and with reference to FIG. 99, a hierarchical template may be utilized by a local data collection system 10500 for collecting and monitoring data collected via multiple input channels 10500, such as data from sensors 10514, IoT devices 10516, etc. The local collection system 10512, also referred to herein as a data collector 10512, may include data storage 10502, data acquisition circuitry 10504, data analysis circuitry 10506, etc., and the monitoring equipment may be located locally on the data collector 10512, partially located locally on the data collector, partially located on a remote information technology infrastructure component separate from the data collector, etc. The monitoring system may include multiple input channels communicatively coupled to the data collector 10512. The data storage 10502 may be configured to store multiple collector route templates 10510 corresponding to the input channels 10500 and sensor specifications for the sensors 10514, each of which configures a different sensor collection routine. The data acquisition circuit 10504 may be configured to interpret multiple detected values, each of which corresponds to at least one of the input channels 10500. The data analysis circuit 10506 may be configured to receive output data from the multiple input channels 10500 and evaluate a current routing template collection routine based on the received output data. The data collector 10500 may be configured to switch from a current routing template collection routine to an alternative routing template collection routine based on the content of the output data. The monitoring system may further utilize a machine learning system (e.g., a neural network expert system), rule-based templates (e.g., based on machine operating conditions related to input channels providing information, input channels providing information, input channels providing information), smart route changes, alarm conditions, network connectivity, self-organization among multiple data collectors, sensor group coordination, etc.

In embodiments, the evaluation of the current routing template may be based on an operational mode routing collection scheme, such as a normal operational mode, a peak operational mode, an idle operational mode, a maintenance operational mode, or a power-save operational mode. As a result of monitoring, the data collector may switch from the current routing template collection routine because the data analysis circuitry determines a change in the operational mode, such as a change in the operational mode from an operational mode to an accelerated maintenance mode, a change in the operational mode from an operational mode to a failure mode analysis mode, a change in the operational mode from an operational mode to a power-save mode, or a change in the operational mode from an operational mode to a high-performance mode. The data collector may switch from the current routing template collection routine based on detecting a change in the operational mode, such as a fault condition, a performance condition, a power condition, a temperature condition, a vibration condition, etc. The evaluation of the current routing template collection routine may be based on a collection routine for collection parameters, such as network availability, sensor availability, a time-based collection routine (e.g., according to a schedule, over time), etc.

In an embodiment, a monitoring system for collecting data in an industrial environment may include a data collector communicatively coupled to a plurality of input channels and a data storage structured to store a plurality of collector route templates and sensor specifications for sensors corresponding to the input channels. The data collector communicatively coupled to the plurality of input channels and the data storage configured to store a plurality of collector route templates and sensor specifications for sensors corresponding to the input channels, each of the plurality of collector route templates configuring a different sensor collection routine. The data acquisition circuitry is configured to interpret a plurality of detected values, each of the detected values corresponding to at least one of the input channels. The data acquisition circuitry is configured to receive output data from the plurality of input channels and evaluate a current routing template collection routine based on the received output data. The data analysis circuitry is configured to switch from the current routing template collection routine to an alternative routing template collection routine based on the content of the output data. In an embodiment, the system is deployed in various ways, such as locally on the data collector, partially locally on the data collector, and partially on a remote information technology infrastructure component separate from the collector. Each of the input channels may correspond to a sensor located in the environment. The evaluation of the current routing template may be based on a routing collection scheme for an operational mode. The operational mode may be at least one of a normal operational mode, a peak operational mode, an idle operational mode, a maintenance operational mode, and a power-save operational mode. The data collector may switch from the current routing template collection routine because the data analysis circuit determines a change in the operational mode, such as when the operational mode changes from an operational mode to an accelerated maintenance mode, when the operational mode changes from an operational mode to a failure mode analysis mode, when the operational mode changes from an operational mode to a power-save mode, or when the operational mode changes from an operational mode to a high-performance mode. The data collector may switch from the current routing template collection routine based on a detected change in the operational mode, such as a fault condition, a performance condition, a power condition, a temperature condition, or a vibration condition. The evaluation of the current routing template collection routine may be based on the collection routine with respect to a collection parameter. For example, the parameter may be network availability, sensor availability, a time-based collection routine (e.g., when the routine collects sensor data according to a schedule and evaluates the sensor data over time), etc.

In an embodiment, a computer-implemented method for implementing a monitoring system for collecting data in an industrial environment can include: providing a data collector communicatively coupled to a plurality of input channels; providing data storage structured to store a plurality of collector route templates and sensor specifications for sensors corresponding to the input channels, each of the plurality of collector route templates including a different sensor collection routine; providing data acquisition circuitry structured to interpret a plurality of detected values, each of the plurality of detected values corresponding to at least one of the input channels; and providing data analysis circuitry structured to receive output data from the plurality of input channels and evaluate a current routing template collection routine based on the received output data, wherein the data collection device is configured to switch from the current routing template collection routine to an alternative routing template collection routine based on the content of the output data. In an embodiment, the computer-implemented method includes a method in which each of the input channels corresponds to a sensor located in the environment, some of which are deployed locally on the data collector and some of which are deployed on a remote information technology infrastructure component remote from the collector.

In an embodiment, one or more non-transitory computer-readable media are provided that include computer-executable instructions that, when executed, cause at least one processor to perform the following operations: providing a data collector communicatively coupled to a plurality of input channels; providing data storage structured to store a plurality of collector route templates and sensor specifications for sensors corresponding to the input channels, each of the plurality of collector route templates including a different sensor collection routine; providing data acquisition circuitry structured to interpret a plurality of sensed values, each of the plurality of sensed values corresponding to at least one of the input channels; and providing data analysis circuitry structured to receive output data from the plurality of input channels and evaluate a current routing template collection routine based on the received output data, wherein the data collection device is configured to switch from a current routing template collection routine to an alternative routing template collection routine based on the content of the output data. In an embodiment, the instructions are deployed partly locally on the data collector and partly remotely on a technology infrastructure component separate from the information collector, each of the input channels corresponding to a sensor in the environment.

In an embodiment, a monitoring system for collecting data in an industrial environment includes a data collector communicatively coupled to a plurality of input channels; a data storage structured to store a plurality of collector path templates and sensor specifications for sensors corresponding to the input channels, each of the plurality of collector path templates constituting a different sensor collection routine; and a data collection circuit structured to interpret a plurality of detected values, each of the plurality of detected values corresponding to at least one of the input channels. The data collection circuit also includes a machine learning data analysis circuit configured to receive output data from the plurality of input channels and evaluate a current routing template collection routine based on the received output data received over time, the machine learning data analysis circuit learning received output data patterns, and the data collection device configured to switch from the current routing template collection routine to an alternative routing template collection routine based on the learned received output data patterns. In an embodiment, the monitoring system may be deployed locally on the data collector, e.g., deployed partially on the data collector and partially on a remote information technology infrastructure component separate from the collector, and each of the input channels corresponds to a sensor located in the environment. The machine learning data analysis circuit may include a neural network expert system. The evaluation of the current routing template may be based on a routing collection scheme for the operational mode. The operational mode may be at least one of a normal operational mode, a peak operational mode, an idle operational mode, a maintenance operational mode, and a power-save operational mode. The data collector may switch from the current routing template collection routine because the data analysis circuit determines a change in the operational mode, such as when the operational mode changes from an operational mode to an accelerated maintenance mode, when the operational mode changes from an operational mode to a failure mode analysis mode, when the operational mode changes from an operational mode to a power-save mode, or when the operational mode changes from an operational mode to a high-performance mode. The data collector may switch from the current routing template collection routine based on a detected change in the operational mode, such as a fault condition, a performance condition, a power condition, a temperature condition, or a vibration condition. The evaluation of the current routing template collection routine may be based on the collection routine with respect to a collection parameter. For example, the parameter may be network availability, sensor availability, or a time-based collection routine (collecting sensor data according to a schedule and evaluating the sensor data over time).

In an embodiment, a computer-implemented method for implementing a monitoring system for collecting data in an industrial environment may include: providing a data collector communicatively coupled to a plurality of input channels; providing data storage structured to store a plurality of collector route templates, which are sensor specifications for sensors corresponding to the input channels, each of the plurality of collector route templates configuring a different sensor collection routine; and providing a data acquisition circuit structured to interpret a plurality of detected values, each of the plurality of detected values corresponding to at least one of the input channels. Providing a machine learning data analysis circuit structured to receive output data from the plurality of input channels and evaluate a current routing template collection routine based on the received output data received over time, the machine learning data analysis circuit learning received output data patterns, and the data collector configured to switch from the current routing template collection routine to an alternative routing template collection routine based on the learned received output data patterns. In an embodiment, the method may be deployed locally on the data collector, e.g., deployed partly on the data collector and partly on a remote information technology infrastructure component separate from the collector, where each of the input channels corresponds to a sensor located in the environment.

In an embodiment, one or more non-transitory computer-readable media are provided that include computer-executable instructions that, when executed, can cause at least one processor to perform the following operations: providing a data collector communicatively coupled to a plurality of input channels; providing data storage structured to store a plurality of collector route templates, which are sensor specifications for sensors corresponding to the input channels, each of the plurality of collector route templates configuring a different sensor collection routine; and providing a data acquisition circuit structured to interpret a plurality of detected values, each of the plurality of detected values corresponding to at least one of the input channels. Providing a machine learning data analysis circuit configured to receive output data from the plurality of input channels and evaluate a current routing template collection routine based on the received output data received over time, the machine learning data analysis circuit reaming received output data patterns, and the data collector configured to switch from the current routing template to an alternative routing template collection routine based on the learned received data patterns. In an embodiment, the instructions may be deployed locally on the data collector, such as partially on the data collector and partially on a remote information technology infrastructure component separate from the collector, and each of the input channels corresponds to a sensor located in the environment.

In an embodiment, a monitoring system for collecting data in an industrial environment includes a data collector communicatively coupled to a plurality of input channels; data storage structured to store collector path templates and sensor specifications for sensors corresponding to the input channels, the collector path templates configuring sensor collection routines; a data collector communicatively coupled to a plurality of input channels; data storage configured to store collector path templates and sensor specifications for sensors corresponding to the input channels, the collector path templates including sensor collection routines; a data acquisition circuit configured to interpret a plurality of detected values, each of the plurality of detected values corresponding to at least one of the input channels; and a data analysis circuit configured to receive output data from the plurality of input channels and evaluate the received output data with respect to rules, the data collector being configured to modify the sensor collection routine based on application of the rules to the received output data. In an embodiment, the system may be deployed locally on the data collector, e.g., deployed partially on the data collector and partially on a remote information technology infrastructure component separate from the collector, where each of the input channels corresponds to a sensor located in the environment. The rules may be based on the operating state of the machine for which the input channel provides information, the predicted state of the machine for which the input channel provides information, the detected fault condition of the machine for which the input channel provides information, etc. Evaluation of the received output data may be based on an operational mode routing collection scheme, where the operational mode is at least one of a normal operational mode, a peak operational mode, an idle operational mode, a maintenance operational mode, and a power-saving operational mode. The data collector may modify the sensor collection routine so that the data analysis circuit determines a change in the operational mode. For example, if the operational mode changes from an operational mode to an accelerated maintenance mode, from an operational mode to a failure mode analysis mode, from an operational mode to a power-saving mode, from an operational mode to a high performance mode, etc. The data collector may modify the sensor collection routine if it detects a change in the operational mode. For example, if the detected change is a fault condition, a performance condition, a power consumption condition, or other condition, including a temperature condition, a vibration condition, etc. Evaluation of the received output data may be based on the collection routine for collection parameters, such as network availability, sensor availability, a time-based collection routine (e.g., collecting sensor data on a schedule or over time), etc.

In an embodiment, a computer-implemented method for implementing a monitoring system for data collection in an industrial environment may include: providing a data collector communicatively coupled to a plurality of input channels; providing data storage configured to store a collector path template and sensor specifications for sensors corresponding to the input channels, the collector path template including a sensor collection routine; providing data acquisition circuitry configured to interpret a plurality of sensed values, each of the plurality of sensed values corresponding to at least one of the input channels; and providing data analysis circuitry structured to receive output data from the plurality of input channels and evaluate the received output data with respect to rules, the data collection device being configured to modify the sensor collection routine based on application of the rules to the received output data. In an embodiment, the method may be deployed locally on the data collector, such as deployed partly on the data collector and partly on a remote information technology infrastructure component separate from the collector, where each of the input channels corresponds to a sensor located in the environment.

In an embodiment, one or more non-transitory computer-readable media are provided that include computer-executable instructions that, when executed, can cause at least one processor to perform the following operations: providing a data collector communicatively coupled to a plurality of input channels; providing data storage configured to store a collector path template and sensor specifications for sensors corresponding to the input channels, the collector path template including a sensor collection routine; and providing a data acquisition circuit configured to interpret a plurality of detected values, each of the plurality of detected values corresponding to at least one of the input channels. Providing a data analysis circuit configured to receive output data from the plurality of input channels and evaluate the received output data according to rules, the data collection device being configured to modify the sensor collection routine based on application of the rules to the received output data. In an embodiment, the instructions may be deployed locally on the data collector, e.g., partially on the data collector and partially on a remote information technology infrastructure component separate from the collector, where each of the input channels corresponds to a sensor located in the environment.

Rapid routing and rerouting in industrial environments can employ smart rerouting based on incoming data or alarms, such as changes that enable dynamic selection of data collections for analysis or correlation. Smart rerouting may enable the system to change the current routing of sensor data based on incoming data or alarms. For example, a user can set a routing configuration that establishes a schedule for sensor collection for analysis, but if the analysis (or alarm) indicates a special need, the system can modify the sensor routing to address that need. For example, if a change in a motor's vibration profile, such as a sudden increase in the peak amplitude of vibration in at least one axis of a vibration sensor set, indicates the possibility of premature motor failure, the system may modify the routing to more intensively collect data for analysis. For example, starting collection on more axes of the motor, starting collection on additional bearings of the motor, or starting collection using other sensors (such as temperature or heat flow sensors) can confirm an initial hypothesis that a failure mode is occurring or aid in the analysis of the machine's condition or operating state.

Detected changes in operational modes can trigger rapid rerouting. For example, operational modes may be detected as a result of single-point sensor out-of-range detection, analytical decisions, etc., generating rerouting. Analytical decisions may be detected from sensor endpoints through single-point sensor analysis, multi-point sensor analysis, analytical domain analysis (e.g., time profile, frequency profile, correlated multi-point decision, etc.), etc. In another example, a maintenance mode may be detected during routine maintenance. In this case, a routing change increases data collection to obtain data at a higher rate during abnormal conditions. A failure mode may be detected, for example, by an alarm indicating a possible machine failure, triggering an increase in data collection rates for analysis. Performance-based modes can initiate routing changes to address various condition-related performance monitoring and metric analysis needs, such as by detecting output rate levels (e.g., peak, slack, idle). For example, if a higher peak speed of a motor, conveyor, assembly line, generator, turbine, etc. is detected compared to the past, routing can be changed accordingly. Additionally, after reviewing measurements over a period of time, additional sensors can be used to monitor for faults related to peak speed, such as overheating (measured with temperature or heat flux sensors), excessive noise (measured with acoustic or noise sensors), or excessive shaking (measured with one or more vibration sensors).

Alarm detection can trigger rapid rerouting. Alarm sources may include front-end collectors, local intelligence resources, back-end data analysis processes, ambient environment detectors, network quality detectors, power quality detectors, heat, smoke, noise, flooding, etc. Alarm types include single-instance anomaly detection, multi-instance anomaly detection, multi-sensor simultaneous detection, time-cluster sensor detection (e.g., single sensor or multi-sensor), and frequency profile detection (e.g., an increase in the anomaly detection rate, e.g., an increase in the rate of alarm occurrence over time, or a change in the frequency content of a sensor output, e.g., a change in the physical vibration profile of a motor over time).

The machine learning system may modify routing based on learned alarm pattern analysis. The machine learning system may learn the system's alarm state patterns, such as expected alarm states under normal operating conditions, expected alarm states under peak operating conditions, and component aging (e.g., new, in its operating life, in its extended life, under warranty). The machine learning system may modify routing based on changes in alarm patterns. For example, a system may be operating normally but experiencing peak operating alarm patterns (e.g., the system is operating when it should not be), or a system may be new but experiencing old profiles (e.g., infant mortality detection). The machine learning system may modify routing based on current alarm profiles and expected changes in production conditions. For example, a plant, system, or component may be experiencing above-average alarm states, is about to experience a production increase (e.g., which may foreshadow above-average failures during increased production), is about to experience a stagnation (e.g., which may be an opportunity to enhance maintenance procedures based on an increased data acquisition routing scheme), or after an unplanned event (e.g., weather, power outage, restart).

Rapid rerouting actions can include increasing the sampling rate (e.g., to a single sensor, to multiple sensors), increasing the number of sensors being sampled (e.g., simultaneous sampling of other sensors on the device, coordinated sampling of similar sensors on nearby devices), generating bursts of sampling (e.g., sampling at a high rate for a period of time), etc. Actions can be performed on a schedule, in conjunction with a trigger, or based on an operational mode. Triggering actions can include anomalous data, exceeded threshold levels, or triggered operational events (e.g., motor torque at start-up).

Rapid rerouting may switch between routing schemes, such as an operational routing scheme (e.g., a subset of sensor collections for normal operations) or a scheduled maintenance routing scheme (e.g., a larger, more focused set of sensor collections than normal operations). The distribution of sensor data may be changed to distribute sensor collections across the system, such as sensor collection sets for specific components, functions, and modes. A failure mode routing scheme may require multiple focused sensor collection groups targeted at different failure mode analyses (e.g., for a motor, one failure mode may be bearing-related, while another may be starting speed-torque-related), where different subsets of sensor data may be required based on the failure mode (e.g., detected from anomalous measurements taken during operation or maintenance). Power-saving mode routing may be performed when weather conditions require the plant to reduce power.

Dynamic adjustments to route changes may be made based on factors related to the collector or connectivity factors such as network availability and bandwidth. For example, changing the routing of a target device on the network may free up bandwidth, or routing may be changed for a device associated with alarm detection. Routing changes can have a duration, such as occurring for a predetermined period and then reverting, maintaining the change until directed by the user, or varying the duration based on network availability.

In an embodiment, and with reference to FIG. 101, smart route changes may be implemented by a local data collection system 10520 for collecting and monitoring data collected via multiple input channels 10500, such as data from sensors 10522, IoT devices 10524, etc. The local collection system 102, also referred to herein as a data collector 10520, may include data storage 10502, data acquisition circuitry 10504, data analysis circuitry 10506, response circuitry 10508, etc., and monitoring equipment may be located locally on the data collector 10520, some on the data collector, and some on a remote information technology infrastructure component separate from the data collector, etc. Smart route changes may be implemented between data collectors, such as by status messages being sent between data collectors (e.g., from an input channel attached proximate to a second input channel, from an associated set of input sensors, etc.). The monitoring system may include multiple input channels 10500 communicatively coupled to the data collector 10520. The data acquisition circuit 10504 may be configured to interpret a plurality of detected values, each of the detected values corresponding to at least one of the input channels 10500, and the data acquisition circuit 10504 acquires sensor data for the plurality of input channels from a first route of the input channels. The data store 10502 may be configured to store sensor data, sensor specifications, etc., for the sensors 10524 corresponding to the input channels 10500. The data analysis circuit 10506 may be configured to evaluate the sensor data with respect to stored expected status information, which may include an alarm threshold level, and the data analysis circuit 10506 may be configured to set an alarm condition for a first input channel in the first group of input channels if the alarm threshold level is exceeded. Further, the data analysis circuit 10506 may transmit the alarm condition to the routing control facility 10512 over the network. The response circuit 10508 may be configured to change the routing of the input channel for data collection from a first routing of the input channel to an alternate routing of the input channel upon receiving a routing change instruction from the routing control facility. In the case of network transmission, the alternate routing of the input channel may include the first input channel and a group of input channels related to the first input channel, and the data collector performs the change in routing of the input channel if communication parameters of the network between the data collector and the routing control facility (e.g., time-duration parameters, network connectivity and/or bandwidth availability parameters) are not met.

In embodiments, the alarm state may indicate a detection mode, such as an operational mode detection consisting of an out-of-range detection, a maintenance mode detection consisting of an alarm detected during maintenance, a failure mode detection (e.g., when the controller communicates a failure mode detection facility), a power mode detection indicating power-related limit data in status information that an alarm state is expected, or a performance mode detection indicating high performance limit data in status information that an alarm state is expected. The monitoring system may further include the analysis circuit setting an alarm state when an alarm threshold is exceeded for an alternate input channel of the first group of input channels. For example, if setting the alarm state for the first input channel and the alternate input channel is determined to be a multiple-instance anomaly detection, a second routing of the input channels may be configured from the first input channel and the second input channel, where sensor data from the first input channel and the second input channel contribute to simultaneous data analysis. The second routing of the input channels may include a change in routing collection parameters, such as an increase in the sampling rate, an increase in the number of channels sampled, burst sampling of at least one of the multiple input channels, etc.

In an embodiment, and with reference to FIG. 100, the collector route template 10510 may be utilized for smart route changes and may be implemented by a local data collection system 10512 for collecting and monitoring data collected via multiple input channels 10500, such as data from sensors 10514, IoT devices 10516, etc. The local collection system 10512, also referred to herein as a data collector 10512, may include data storage 10502, data acquisition circuitry 10504, data analysis circuitry 10506, response circuitry 10508, etc., and monitoring equipment may be located locally on the data collector 10512, some located on the data collector, and some located on remote information technology infrastructure components separate from the data collector, etc.

In an embodiment, a monitoring system for collecting data in an industrial environment may include: a data collector communicatively coupled to a plurality of input channels; a data acquisition circuit configured to interpret a plurality of detected values, each of the detected values corresponding to at least one of the input channels, the data acquisition circuit acquiring sensor data from a first route of the input channels for the plurality of input channels; and a data storage configured to store sensor specifications for the sensors corresponding to the input channels; a data analysis circuit configured to evaluate the sensor data with respect to stored predicted state information, the predicted state information including an alarm threshold, the data analysis circuit setting an alarm condition when the alarm threshold is exceeded for a first input channel of a first group of input channels; and a response circuit configured to change a routing of the input channels for data collection from the first routing of the input channels to an alternate routing of the input channels, the alternate routing of the input channels including the first input channel and a group of input channels associated with the first input channel. In an embodiment, the system may be deployed locally on a data collector, or partially on a data collector and partially on a remote information technology infrastructure component separate from the collector, and each of the input channels corresponds to a sensor located in the environment. The group of input channels may be associated with a first input channel and at least partially derived from multiple input channels not included in the first routing of input channels. The alarm status may indicate a detection mode, such as when the detection mode is an operational mode detection consisting of an out-of-range detection, when the detection mode is a maintenance mode detection consisting of an alarm detected during maintenance, or when the detection mode is a failure mode detection. The controller may communicate a failure mode detection facility, such as when the detection mode is a power mode detection and the alarm status indicates power-related limit data in the predicted condition information, or when the detection mode is a performance mode detection and the alarm status indicates high-performance limit data in the predicted condition information. The analysis circuit may set an alarm state for an alternate input channel in the first set of input channels when an alarm threshold is exceeded, for example, when setting an alarm state for the first input channel and the alternate input channel is determined to be a multiple-instance anomaly detection, and the alternate routing of the input channels comprises the first input channel and the second input channel, and sensor data from the first input channel and the second input channel contributes to simultaneous data analysis. The alternate routing of the input channels may include modifying routing collection parameters, such as increasing the sampling rate, increasing the number of channels sampled, or burst sampling at least one of the multiple input channels.

In an embodiment, a computer-implemented method for implementing a monitoring system for data collection in an industrial environment may include: providing a data collector communicatively coupled to a plurality of input channels; providing a data acquisition circuit configured to interpret a plurality of detected values, each of the plurality of detected values corresponding to at least one of the input channels; providing data storage configured to acquire sensor data from a first route of the input channels for the plurality of input channels and store specifications of the sensors corresponding to the input channels; and providing a data analysis circuit configured to evaluate the sensor data with respect to stored expected state information, the expected state information including an alarm threshold level, the data analysis circuit setting an alarm condition when the alarm threshold level is exceeded for a first input channel of a first group of input channels; and a response circuit configured to change routing of the input channels for data collection from the first routing of the input channels to an alternative routing of the input channels, the alternative routing of the input channels including the first input channel and a group of input channels associated with the first input channel. In an embodiment, the system may be deployed locally to the data collector, partially deployed locally to the data collector, and partially deployed in a remote information technology infrastructure component separate from the collector, with each of the input channels corresponding to a sensor located in the environment.

In an embodiment, one or more non-transitory computer-readable media containing computer-executable instructions that, when executed, can cause at least one processor to perform operations can include: providing a data collector communicatively coupled to a plurality of input channels; providing a data acquisition circuit configured to interpret a plurality of detected values, each of the plurality of detected values corresponding to at least one of the input channels, the data acquisition circuit acquiring sensor data from a first route of the input channels for the plurality of input channels; and providing data storage configured to store sensor specifications for sensors corresponding to the input channels; providing a data analysis circuit configured to evaluate the sensor data with respect to stored expected state information, the expected state information including an alarm threshold, the data analysis circuit setting an alarm condition when the alarm threshold is exceeded for a first input channel of a first group of input channels; and providing a response circuit configured to change routing of the input channels for data collection from the first routing of the input channels to an alternative routing of the input channels, the alternative routing of the input channels including the first input channel and a group of input channels associated with the first input channel. In an embodiment, the instructions are deployed locally to the data collector, some locally to the data collector, and some to a remote information technology infrastructure component separate from the collector, and each of the input channels corresponds to a sensor located in the environment.

In an embodiment, a monitoring system for collecting data in an industrial environment may include: a data collector communicatively coupled to a plurality of input channels; a data acquisition circuit configured to interpret a plurality of detected values, each of the plurality of detected values corresponding to at least one of the input channels, the data acquisition circuit acquiring sensor data from a first route of the input channels for the plurality of input channels; and a data storage configured to store sensor specifications for a sensor corresponding to the input channel. a data analysis circuit for evaluating sensor data based on accumulated predictive state information, the predictive state information including an alarm threshold, the data analysis circuit setting an alarm state when the alarm threshold is exceeded for a first input channel of a first group of input channels, and transmitting the alarm state to a routing control facility via a network; and a response circuit configured, upon receiving a routing change instruction from the routing control facility, to change the routing of the input channels for data collection from a first routing of the input channels to an alternative routing of the input channels, the alternative routing of the input channels including the first input channel and a group of input channels related to the first input channel, and the data collector automatically performs the change in routing of the input channels if communication parameters of the network between the data collector and the routing control facility are not met. In an embodiment, the instructions may be deployed locally on the data collector, or partly on a remote information technology infrastructure component separate from the collector, and each of the input channels corresponds to a sensor located in the environment. The communication parameters may be time period parameters within which the routing control facility must respond. The communication parameters may also be network availability parameters such as network connectivity parameters and bandwidth requirements. The group of input channels associated with the first input channel may be at least partially drawn from multiple input channels not included in the first routing of input channels. The alarm state may indicate a detection mode, such as an operational mode detection, which indicates an out-of-range detection, or a maintenance mode detection, which indicates an alarm detected during maintenance. The detection mode may also be a failure mode detection, in which the alarm state indicates power-related limit data in the predicted status information when the control device communicates with the failure mode detection facility. The detection mode may also be a high-performance mode detection, in which the alarm state indicates high-performance limit data in the predicted status information. The analysis circuit may set an alarm state for an alternate input channel in the first group of input channels when an alarm threshold is exceeded. For example, if setting an alarm state for the first input channel and the alternate input channel is determined to indicate multiple-instance anomaly detection, the alternate routing of input channels may consist of the first input channel and the second input channel, and sensor data from the first input channel and the second input channel contribute to simultaneous data analysis. The alternate routing of input channels may also be a change in routing collection parameters, such as an increased sampling rate, an increased number of sampled channels, or burst sampling of at least one of the multiple input channels.

In an embodiment, a computer-implemented method for implementing a monitoring system for collecting data in an industrial environment may include: providing a data collector communicatively coupled to a plurality of input channels; providing a data acquisition circuit configured to interpret a plurality of detected values, each of the plurality of detected values corresponding to at least one of the input channels, the data acquisition circuit acquiring sensor data from a first route of the input channels for the plurality of input channels; and providing data storage configured to store sensor specifications for sensors corresponding to the input channels, the data storage configured to store the sensor specifications for the sensors corresponding to the input channels. and providing a data analysis circuit for evaluating sensor data based on stored predicted state information, the predicted state information including an alarm threshold, the data analysis circuit setting an alarm state for a first input channel of a first group of the input channels when the alarm threshold is exceeded and transmitting the alarm state to a routing control facility via a network; and a response circuit structured to change routing of the input channels for data collection from a first routing of the input channels to an alternative routing of the input channels upon receiving a routing change instruction from the routing control facility, the alternative routing of the input channels including the first input channel and a group of input channels related to the first input channel, the data collector automatically performing the change in routing of the input channels if communication parameters of the network between the data collector and the routing control facility are not met. In an embodiment, the instructions are deployed locally to the data collector, and may be partially deployed locally to the data collector and partially deployed to a remote information technology infrastructure component separate from the collector, each of the input channels corresponding to a sensor located in the environment.

In an embodiment, one or more non-transitory computer-readable media are provided that include computer-executable instructions that, when executed, can cause at least one processor to perform the following operations: providing a data collector communicatively coupled to a plurality of input channels; providing a data acquisition circuit configured to interpret a plurality of detected values, each of the plurality of detected values corresponding to at least one of the input channels, the data acquisition circuit acquiring sensor data from a first route of the input channels for the plurality of input channels; and providing data storage configured to store sensor specifications for a sensor corresponding to the input channel. and providing a data analysis circuit for evaluating sensor data based on stored predicted state information, the predicted state information including an alarm threshold, the data analysis circuit setting an alarm state for a first input channel of a first group of the input channels when the alarm threshold is exceeded and transmitting the alarm state to a routing control facility via a network; and a response circuit structured to change routing of the input channels for data collection from a first routing of the input channels to an alternate routing of the input channels upon receiving a routing change instruction from the routing control facility, the alternate routing of the input channels including the first input channel and a group of input channels related to the first input channel, the data collector automatically performing the change in routing of the input channels if communication parameters of the network between the data collector and the routing control facility are not met. In an embodiment, the instructions are deployed locally to the data collector, and may be partially deployed locally to the data collector and partially deployed to a remote information technology infrastructure component separate from the collector, each of the input channels corresponding to a sensor disposed in the environment.

In an embodiment, a monitoring system for collecting data in an industrial environment may include: the second data collector transmits a status message associated with the first input channel from the first path of the input channels; and the response circuit is configured to change a path of the input channels for data collection from the first path of the input channels to an alternate path of the input channels based on the status message from the second data collector, the alternate path of the input channels including the first input channel and a group of input channels associated with the first input sensor. In an embodiment, the system may be deployed locally to a data collector, partially deployed locally to the data collector, and partially deployed in a remote information technology infrastructure component separate from the collector, with each input channel corresponding to a sensor located in the environment. The set status message transmitted from the second data collector may be from a second input channel mounted proximate to the first input channel. The set alarm transmitted from the second controller may be from a second input sensor that is part of an associated group of input sensors constituting the first input sensor. The group of input channels associated with the first input channel may be derived at least in part from multiple input channels not included in the first routing of input channels. The alarm status may indicate a detection mode, such as an operational mode detection comprising an out-of-range detection, a maintenance mode detection comprising an alarm detected during maintenance, or a failure mode detection. The controller may communicate a failure mode detection facility, such as when the detection mode is a power mode detection and the alarm status indicates power-related limit data in the predicted status information, or when the detection mode is a performance mode detection and the alarm status indicates high-performance limit data in the predicted status information. The analysis circuit may set an alarm state for an alternate input channel in the first set of input channels when the alarm threshold is exceeded. For example, if setting the alarm state for the first input channel and the alternate input channel is determined to be a multiple-instance anomaly detection, the alternate routing of the input channels may comprise the first input channel and the second input channel, and sensor data from the first input channel and the second input channel may contribute to the simultaneous data analysis. The alternate routing of the input channels may be a change in routing collection parameters, such as an increased sampling rate, an increased number of sampled channels, or burst sampling of at least one of the multiple input channels.

In an embodiment, a computer-implemented method for implementing a monitoring system for collecting data in an industrial environment may include: providing first and second data collectors communicatively coupled to a plurality of input channels; and providing data acquisition circuitry configured to interpret a plurality of detected values, each of the plurality of detected values corresponding to at least one of the input channels, the data acquisition circuitry acquiring sensor data from a first route of the input channels for the plurality of input channels. The method includes providing a data storage configured to store specifications of sensors corresponding to the input channels and a data analysis circuit configured to evaluate the sensor data based on stored expected state information, the expected state information including an alarm threshold, the data analysis circuit configured to set an alarm state for a first input channel of the first group of input channels when the alarm threshold is exceeded; providing a communication circuit configured to communicate with a second data collector, the second data collector transmitting a status message associated with the first input channel from a first path of the input channels; and providing a response circuit configured to change a path of the input channels for data collection from the first path of the input channels to an alternate path of the input channels based on the status message from the second data collector, the alternate path of the input channels consisting of the first input channel and a group of input channels associated with the first input sensor. In an embodiment, the method is deployed locally to the data collector, some of which may be deployed locally to the data collector and some of which may be deployed on a remote information technology infrastructure component separate from the collector, each of the input channels corresponding to a sensor located in the environment.

In an embodiment, one or more non-transitory computer-readable media are provided that include computer-executable instructions that, when executed, can cause at least one processor to perform the following operations: providing first and second data collectors communicatively coupled to a plurality of input channels; and providing a data acquisition circuit configured to interpret a plurality of detected values, each of the plurality of detected values corresponding to at least one of the input channels, the data acquisition circuit acquiring sensor data for the plurality of input channels from a first route of the input channel. The system includes: a data storage configured to store specifications of sensors corresponding to the input channels; and a data analysis circuit configured to evaluate the sensor data based on stored expected state information, the expected state information including an alarm threshold, the data analysis circuit configured to set an alarm state for a first input channel of the first group of input channels when the alarm threshold is exceeded; a communication circuit configured to communicate with a second data collector, the second data collector transmitting a status message associated with the first input channel from a first path of the input channels; and a response circuit configured to change a path of the input channels for data collection from the first path of the input channels to an alternate path of the input channels based on the status message from the second data collector, the alternate path of the input channels consisting of the first input channel and a group of input channels associated with the first input sensor. In an embodiment, the instructions are deployed locally to the data collector, and may be partially deployed locally to the data collector and partially deployed to a remote information technology infrastructure component separate from the collector, each of the input channels corresponding to a sensor located in the environment.

In an embodiment, a monitoring system for collecting data in an industrial environment may include: a data collector communicatively coupled to a plurality of input channels; a data acquisition circuit configured to interpret a plurality of detected values, each of the plurality of detected values corresponding to at least one of the input channels, the data acquisition circuit acquiring sensor data from a first group of input channels from the plurality of input channels; and a data storage configured to store sensor specifications for sensors corresponding to the input channels; a data analysis circuit configured to evaluate the sensor data with respect to stored expected state information, the expected state information including an alarm threshold, the data analysis circuit setting an alarm condition when the alarm threshold is exceeded for a first input channel of a first group of input channels; and a response circuit configured to change the input channels collected from the first group of input channels to an alternate group of input channels, the alternate group of input channels including the first input channel and a group of input channels associated with the first input channel and the first input sensor. In an embodiment, the system may be deployed locally to a data collector, partially locally to the data collector, and partially on a remote information technology infrastructure component separate from the collector, and each of the input channels corresponds to a sensor located in the environment. The input sensor group associated with a first input sensor may be derived at least in part from a plurality of input sensors not included in the first input sensor group. The first input channel group associated with a first input channel may be derived at least in part from a plurality of input channels not included in the first routing of input channels. The alarm state may indicate a detection mode, such as an operational mode detection comprising an out-of-range detection or a maintenance mode detection comprising an alarm detected during maintenance. The detection mode may be a failure mode detection, in which the controller communicates a failure mode detection facility. The detection mode may be a power mode detection, in which the alarm state indicates power-related limit data in the predicted status information. The detection mode may be a performance mode detection, in which the alarm state indicates high performance limit data in the predicted status information. The analysis circuit may set an alarm state for an alternate input channel of the first group of input channels when an alarm threshold is exceeded. For example, if setting the alarm state for the first input channel and the alternate input channel is determined to be a multiple-instance anomaly detection, an alternate routing of input channels may comprise the first input channel and the second input channel, and sensor data from the first input channel and the second input channel contribute to the concurrent data analysis. The alternate group of input channels may include a change in routing collection parameter, such as when the routing collection parameter is an increased sampling rate, an increased number of sampled channels, burst sampling of at least one of the multiple input channels, etc.

In an embodiment, a computer-implemented method for implementing a monitoring system for collecting data in an industrial environment may include: providing a data collector communicatively coupled to a plurality of input channels; providing data acquisition circuitry structured to interpret a plurality of detected values, each of the plurality of detected values corresponding to at least one of the input channels, the data acquisition circuitry acquiring sensor data from a first group of input channels from the plurality of input channels; providing data storage structured to store sensor specifications for sensors corresponding to the input channels; providing a data analysis circuitry configured to evaluate the sensor data with respect to stored expected state information, the expected state information including an alarm threshold level, the data analysis circuitry setting an alarm condition when the alarm threshold level is exceeded for a first input channel of a first group of input channels; and providing a response circuitry configured to change the input channels collected from the first group of input channels to an alternate group of input channels, the alternate group of input channels including the first input channel and the first input sensor. In an embodiment, the method is deployed locally to a data collector, partially deployed locally to the data collector, and partially deployed to a remote information technology infrastructure component separate from the collector, and each of the input channels corresponds to a sensor located in the environment.

In an embodiment, one or more non-transitory computer-readable media are provided that include computer-executable instructions that, when executed, cause at least one processor to perform the following operations: providing a data collector communicatively coupled to a plurality of input channels; providing data acquisition circuitry structured to interpret a plurality of detected values, each of the plurality of detected values corresponding to at least one of the input channels, the data acquisition circuitry acquiring sensor data from a first group of input channels from the plurality of input channels; providing data storage structured to store sensor specifications for sensors corresponding to the input channels; providing a data analysis circuitry configured to evaluate the sensor data with respect to stored expected state information, the expected state information including an alarm threshold, the data analysis circuitry setting an alarm condition when the alarm threshold is exceeded for a first input channel of a first group of input channels; and providing a response circuitry configured to change the input channels collected from the first group of input channels to an alternative group of input channels, the alternative group of input channels including the first input channel and a group of input channels associated with the first input channel and the first input sensor. In an embodiment, the instructions are deployed locally to the data collector, some locally to the data collector, and some to a remote information technology infrastructure component separate from the collector, and each of the input channels corresponds to a sensor located in the environment.

In an embodiment, a monitoring system for collecting data in an industrial environment may include: a data collector communicatively coupled to a plurality of input channels; a data storage configured to store a plurality of collector route templates, each of the plurality of collector route templates being sensor specifications for sensors corresponding to the input channels, the plurality of collector route templates each including a different sensor collection routine; a data acquisition circuit configured to interpret a plurality of detected values, each of the detected values corresponding to at least one of the input channels, the data acquisition circuit acquiring sensor data from a first route of the input channels; and a data analysis circuit configured to evaluate the sensor data with respect to stored expected state information, the expected state information including an alarm threshold level, the data analysis circuit setting an alarm condition when the alarm threshold level is exceeded for a first input channel of a first group of the input channels; and a data collection device configured to switch from a current routing template collection routine to an alternative routing template collection routine based on the setting of the alarm condition. In an embodiment, the system may be deployed locally on the data collector or partially deployed locally on the data collector and partially deployed on a remote information technology infrastructure component separate from the collector, and each of the input channels corresponds to a sensor located in the environment. The setting of the alarm state may be based on a routing collection scheme for the operating mode, where the operating mode is at least one of a normal operating mode, a peak operating mode, an idle operating mode, a maintenance operating mode, and a power-saving operating mode. The alarm threshold may be associated with a sensed change in one of a plurality of input channels, such as a sensed change in a fault condition, a performance condition, a power condition, a temperature condition, or a vibration condition. The alarm state may also indicate a detection mode, such as an operational mode detection comprising an out-of-range detection or a maintenance mode detection comprising an alarm detected during maintenance. The detection mode may also be a power mode detection, where the alarm state indicates power-related limit data in the expected status information. The detection mode may also be a performance mode detection, where the alarm state indicates high-performance limit data in the expected status information. The analysis circuit may set the alarm state when the alarm threshold is exceeded for an alternate input channel, such as when the setting of the alarm state is determined to be multiple instances of anomaly detection. The alternate routing template may also be a change in the routing collection parameters for the input channel. The routing collection parameter may be an increase in the number of channels sampled, an increase in the sampling rate, such as burst sampling of at least one of the multiple input channels, etc.

In an embodiment, a computer-implemented method for implementing a monitoring system for collecting data in an industrial environment includes providing a data collector communicatively coupled to a plurality of input channels; and providing a data storage structured to store a plurality of collector route templates and sensor specifications for sensors corresponding to the input channels, the plurality of collector route templates being structured to store the sensor specifications corresponding to the plurality of input channels. Each template is configured with a different sensor collection routine and includes a data acquisition circuit configured to interpret a plurality of detected values, each of the detected values corresponding to at least one of the input channels, the data acquisition circuit acquiring sensor data from a first route of the input channels. Providing a data analysis circuit structured to evaluate the sensor data with respect to stored expected state information, the expected state information including an alarm threshold level, the data analysis circuit setting an alarm condition when the alarm threshold level is exceeded for a first input channel of a first group of input channels; and configuring the data collection device to switch from a current routing template collection routine to an alternative routing template collection routine based on the setting of the alarm condition. In an embodiment, the system may be deployed locally to the data collector, partially deployed locally to the data collector, and partially deployed in a remote information technology infrastructure component separate from the collector, and each of the input channels corresponds to a sensor located in the environment.

In an embodiment, one or more non-transitory computer-readable media are provided that include computer-executable instructions that, when executed, can cause at least one processor to perform the following operations: providing a data collector communicatively coupled to a plurality of input channels; providing data storage configured to store a plurality of collector route templates, the plurality of collector route templates being sensor specifications for sensors corresponding to the input channels; providing a data acquisition circuit configured to interpret a plurality of detected values, each of the plurality of detected values corresponding to at least one of the input channels, the data acquisition circuit acquiring sensor data from a first route of the input channels; providing a data analysis circuit configured to evaluate the sensor data with respect to stored expected state information, the expected state information including an alarm threshold level, the data analysis circuit setting an alarm condition when the alarm threshold level is exceeded for a first input channel of a first group of input channels; and configuring the data collector to switch from a current routing template collection routine to an alternative routing template collection routine based on the setting of the alarm condition. In an embodiment, the instructions may be deployed locally to the data collector, or may be deployed partially to the data collector and partially to a remote information technology infrastructure component separate from the data collector. In the collector, each input channel corresponds to a sensor in the environment.

Disclosed herein are methods and systems for systems for collecting data in industrial environments using intelligent management of data collection bands (referred to herein in some cases as smart bands). The smart bands can facilitate intelligent, situational, and context-aware collection of data, such as by data collectors (such as any of the broad range of data collector embodiments described throughout this disclosure). Intelligent management of data collection via smart bands can improve various parameters of data collection, as well as parameters of processes, applications, and products that rely on data collection, such as data quality parameters, consistency parameters, efficiency parameters, comprehensiveness parameters, reliability parameters, effectiveness parameters, storage utilization parameters, yield parameters (including financial yield, output yield, and adverse event reduction), energy consumption parameters, bandwidth utilization parameters, input/output rate parameters, redundancy parameters, security parameters, safety parameters, interference parameters, signal-to-noise parameters, statistical relevance parameters, and the like. Intelligent management of smart bands can optimize across one or more such parameters, such as based on weighting the values of the parameters. For example, a smart band can provide a predetermined level of redundancy for critical data while managing energy usage to ensure it does not exceed a predetermined level. This may include using various optimization techniques described throughout this disclosure and the documents incorporated herein by reference.

In embodiments, such methods and systems for intelligent management of smart bands include an expert system and supporting technology components, services, processes, modules, applications, and interfaces (in some cases collectively referred to as a smart band platform 10722) for managing the smart bands, which may include model-based expert systems, rule-based expert systems, expert systems using artificial intelligence (such as machine learning systems, which may include neural net expert systems, self-organizing map systems, human-supervised machine learning systems, condition determination systems, classification systems, or other artificial intelligence systems), or various hybrids or combinations of any of the above. Expert systems should be understood to encompass the use of any of the above or appropriate combinations, unless the context dictates otherwise. Intelligent management may include data collection of various types of data (e.g., vibration data, noise data, and other sensor data of the type described throughout this disclosure) for event detection, condition detection, etc. Intelligent management may include the management of multiple smart bands to support a specified application, process, or workflow. Intelligent management may also include managing data collection bands to corroborate unknown variables based on the collection of other data (e.g., based on a behavioral model of the system that includes the variables), to select preferred inputs from among available inputs (including specifying input combinations, fusions, or multiplexing), and/or to specify input bands from among available input bands.

A data collection band, or smart band, may include any number of items, such as sensors, input channels, data locations, data streams, data protocols, data extraction techniques, data conversion techniques, data loading techniques, data types, sampling frequencies, sensor placement, static data points, metadata, data fusion, and data multiplexing, as described herein. Smart band settings, sometimes used interchangeably with smart band and data collection band, may describe the configuration and makeup of a smart band, such as by specifying parameters that define the smart band. For example, a data collection band, or smart band, may include one or more frequencies to measure. The frequency data may further include at least one of spectral peaks, true peak levels, crest factors derived from time waveforms, and overall waveforms derived from vibration envelopes, as well as other signal characteristics described throughout this disclosure. A smart band may include sensors or data measuring one or more wavelengths, one or more spectra, and/or one or more types of data from various sensors and metadata. A smart band may include one or more sensors, or a wide range of types of sensors, as described throughout this disclosure and the documents incorporated by reference herein. Indeed, any of the sensors described herein can be used in any of the methods or systems described throughout this disclosure. For example, one sensor may be an accelerometer, such as one that measures voltage per g of acceleration ("V/G") (e.g., 100 mV/G, 500 mV/G, 1 V/G, 5 V/G, 10 V/G, etc.). In embodiments, the data collection band circuitry may alter the configuration of a subset of sensors used in the smart band based on optimizing sensor response, such as selecting an accelerometer suitable for measuring the acceleration of a low-speed mixer versus an accelerometer suitable for measuring the acceleration of a high-speed industrial centrifuge. For example, a centrifuge may be equipped with a proximity probe and multiple accelerometers, and the smart band may intelligently select one accelerometer for measurements at low speeds and another accelerometer for measurements at high speeds. Accelerometers come in a variety of types, including piezoelectric crystal, low-frequency (e.g., 10 V/G), high-speed compressor (e.g., 10 MV/G), and MEMS. In another example, one sensor may be a proximity probe or velocity probe that can be used on a sleeve or tilt pad bearing (e.g., an oil bath). In yet another example, one sensor may be a solid-state relay (SSR) configured to automatically interface with a routed data collector (e.g., a mobile or portable data collector) to acquire or distribute data. In another example, a mobile or portable data collector may be routed to change the configuration of multiple available sensors. For example, an appropriate accelerometer can be brought to a sensing point, such as on or near a machine component. In yet another example, one sensor may be a triaxial probe (e.g., a 100 MV/G triaxial probe) used in embodiments for portable data collection. In some embodiments, a triaxial probe may have a vertically oriented element on one axis with a high frequency response, while a horizontally mounted element may affect the frequency response of all three axes. In another example, one sensor may be a temperature sensor, such as a probe with an internal temperature sensor, for example, to obtain the temperature of a bearing. In further examples, the sensor may be an ultrasonic, microphone, touch, capacitive, vibration, acoustic, pressure, strain gauge, thermography (e.g., camera), imaging (e.g., electric field detector, EMF meter measuring alternating electromagnetic fields, gaussmeter, motion detector, chemical detector, gas detector, CBRNE detector, vibration transducer, magnetometer, position detector, location information detector, speed detector, displacement detector, speed sensor, displacement sensor, tachometer, flow sensor, level sensor, proximity sensor, pH sensor, hygrometer/moisture sensor, densitometry sensor, anemometer, viscometer, or any analog and/or digital industrial sensor. In yet another example, a sensor may be for detecting or measuring ambient noise, such as a sound sensor, microphone, ultrasonic sensor, acoustic wave sensor, or optical vibration sensor (e.g., using a camera to identify vibrations generating noise). In yet another example, a sensor may be a motion detector.

A data collection band, or smart band, may be or may be configured to encompass one or more frequencies, wavelengths, or spectra for a particular sensor, a particular group of sensors, or a combined signal from multiple sensors (including multiplexing or sensor fusion).

A data collection band (smart band) may be configured to encompass one or more sensors or sensor data (including groups of sensors and their combined signals) from one or more pieces of equipment/components, areas of an installation, different but interconnected areas of an installation (e.g., a machine assembly line and a boiler room that powers that line), or locations (e.g., a building in Cambridge and a building in Boston). The settings, configuration, instructions, or specifications (collectively referred to herein using any of these terms) of a smart band include where to place sensors, how often to sample data points, the granularity at which samples are taken (e.g., number of sampling points in fractions of a second), which sensors of a set of redundant sensors to sample, the averaging sampling protocol for the redundant sensors, and any other aspects that affect data acquisition.

Within the smart band platform 10722, an expert system comprised of neural nets, model-based systems, rule-based systems, machine learning data analysis circuits, and/or hybrids of any of these can begin iterating to converge on a smart band optimized for a specific goal or outcome, such as predicting and managing the performance, health, or other characteristics of a piece of equipment, component, or system of equipment or components. Based on continuous or periodic analysis of sensor data, the expert system can intelligently modify its data collection band if a pattern/trend is identified, an outlier emerges, or a group of sensor readings begins to change. This may occur by triggering rules reflecting a model or understanding of system behavior or under the control of the neural net (either in combination with a rule-based approach or alone). The neural net receives input over time to select the appropriate collection mode based on feedback regarding successful outcomes (e.g., successful classification of system state, successful prediction, successful operation on indicators, etc.). For example, if a new pressure reactor is installed at a chemical processing facility, data from the current data collection band may not accurately predict system state or operational metrics, so the machine learning data analysis circuitry may begin iterations to determine whether the new data collection band is better at predicting state. Based on offset system data, such as from a library or other data structure, specific sensors, frequency bands, or other smart band components may initially be used with the smart band, and data may be collected to evaluate performance. As the neural net iterates, other sensors/frequency bands may be accessed to determine their relative weight in identifying performance metrics. Over time, new frequency bands (or new sets of sensors, new configurations for sensors, etc.) may be identified to better measure system performance, and the expert system may modify the data collection band based on this iteration. For example, if a slightly different or older turbine agitator is installed at a chemical reaction facility, it may be necessary to dampen one or more vibration frequencies while different frequencies exist during optimal performance, at higher amplitudes than those seen in the offset system. In this example, the smart band may be modified from that proposed with the corresponding offset system to capture the higher amplitude frequencies present in the current system.

The expert system, in embodiments including a neural net or other machine learning system, may be seeded and may iterate, such as towards convergence on the smart band, based on feedback and operating parameters as described herein. Specific feedback may include utilization metrics, efficiency metrics (e.g., power or energy utilization, storage utilization, bandwidth utilization, fresh material input/output utilization, fuel utilization, and/or financial efficiency), condition prediction or forecast success metrics (e.g., failure avoidance and mitigation), productivity metrics (e.g., workflow), yield metrics, and profit metrics. Specific parameters include storage parameters (e.g., data storage, fuel storage, inventory storage, etc.), network parameters (e.g., network bandwidth, input/output speed, network utilization, network cost, network speed, network availability, etc.), transmission parameters (e.g., data transmission quality, data transmission speed, transmission error rate, transmission cost, etc.); security parameters (e.g., number and/or type of exposure events, vulnerability to attacks, data loss, data breach, access parameters, etc.); location and positioning parameters (e.g., location of data collector, location of data collector, where data collector is, where data collector is not, etc.). location of personnel, location of machines and equipment, location of inventory units, location of parts and materials, location of network access points, location of entry and exit points, location of landing points, location of sensor sets, location of network infrastructure, location of power sources, etc.); input selection parameters, data binding parameters (e.g., input selection parameters, data binding parameters (e.g., multiplexing, extraction, conversion, loading, etc.), power parameters, state (e.g., operation mode, availability state, environmental state, failure mode, maintenance mode, expected state), events, and equipment specifications. With regard to state, operation mode can be mobility mode (direction, speed, acceleration, etc.), type of movement mode (rolling, flying, gliding, floating, hovering, floating, etc.), performance mode (gear, rotational speed, etc.), , thermal levels, assembly line speed, voltage levels, frequency levels, etc.), power modes, fuel conversion modes, resource consumption modes, and financial performance modes (yield, profitability, etc.). Availability states refer to predicting conditions under which a machine may go offline or require backup. Environmental states refer to ambient temperature, ambient humidity/moisture, ambient pressure, ambient wind/fluid flow, presence of contaminants, presence of interference elements (electrical noise, vibration, etc.), power availability, and power quality. Predicted states include achieving or not achieving desired goals such as specified/threshold power production rates, specified/threshold power generation rates, operational efficiency/failure rates, financial efficiency/profit targets, power efficiency/resource utilization, and avoiding failure conditions (e.g., , overheating, underperformance, excessive performance, etc. Avoidance of fault conditions such as overheating, underperformance, overspeed, overmotion, excessive vibration/vibration, overacceleration, expansion/contraction, electrical failure, power storage/out of fuel, overpressure, excessive radiation/meltdown, fire, freezing, fluid flow obstruction (e.g., clogged valves, frozen fluids), mechanical efficiency/failure rate, financial efficiency/profit targets, power efficiency/resource utilization, etc. Mechanical failure (e.g., component breakage, component wear, coupling failure, misalignment, asymmetry/deflection, component damage (e.g., deflection, strain, stress, cracks), imbalance, collision, stuck element, lost or slipped chain or belt), avoidance of unsafe conditions or catastrophic failure, and availability (online status).

An expert system may consist of or be seeded with a model that predicts an outcome or state given a set of data (which may consist of inputs from sensors such as data collectors, as well as other data such as system components, external systems, and external data sources). For example, the model may be an operational model of an industrial environment, machine, or workflow. In another example, the model may be for predicting conditions, predicting failures and optimizing maintenance, self-organizing storage (e.g., on-device, in a data pool, and/or in the cloud), optimizing data transport (e.g., optimizing network coding, routing depending on network conditions, etc.), optimizing a data marketplace, etc.

The expert system's iterations can result in any number of downstream actions based on the analysis of data from the smart band. In one embodiment, the expert system may cause the system to maintain or modify operating parameters or weights of a neural net model given desired goals, such as a specified/threshold power production rate, a specified/threshold power generation rate, operational efficiency/failure rate, financial efficiency/profit target, power efficiency/resource utilization, avoidance of fault conditions, avoidance of unsafe conditions or catastrophic failures, etc. In an embodiment, adjustments may be based on determining the context of the industrial system, such as the type of equipment, its purpose, typical operating mode, functional specifications of the equipment, the relationship of the equipment to other features of the environment (including other systems that provide input to or take input from the equipment), the presence and role of operators (including humans and automated control systems), and understanding the ambient or environmental conditions. For example, to achieve profit goals, a refinery pipeline may need to operate certain hours per day and/or at a certain flow rate. The expert system may be configured with a model to operate the pipeline in a manner that achieves a specified profit goal, such as indicating a predetermined flow rate of material through the pipeline based on the current market selling price of the material and the cost of getting the material into the pipeline. The model acquires data and iterates to predict whether profit goals will be achieved from the current data. Based on the results of the expert system's iterations, recommendations may be made (or control instructions may be automatically provided), such as running the pipeline at a higher flow rate or for a longer period of time. Additionally, as the system iterates, one or more additional sensors may be sampled by the model to determine whether adding them to the smart band would improve condition predictions. In another embodiment, the expert system may determine that the system should maintain or modify operating parameters, equipment, or neural net or other model weightings, taking into account operational constraints (e.g., meeting required endpoints (e.g., delivery dates, volume, cost, coordination with other systems), operating with limited resources (e.g., power, fuel, battery, etc.), storage (e.g., data storage), bandwidth (e.g., local network, P2P, WAN, Internet bandwidth, availability, input/output capacity), permissions (e.g., role-based), warranty limitations, manufacturer guidelines, maintenance guidelines, etc.). For example, a constraint for operating a boiler in an oil refinery may require the boiler to operate in conjunction with a deaerator because the aeration rate of the boiler feedwater must be reduced within the cycle. In this example, an expert system is configured with a model that ensures a predetermined overall performance when the boiler is operated in conjunction with the deaerator. As sensor data from the system is acquired, the expert system may determine that one or both aspects of the boiler and the deaerator need to be modified to continue achieving the specified overall performance. In yet another embodiment, the expert system may determine that the system should maintain or modify operating parameters, equipment, or neural network model weightings in light of identified choke points. In yet another embodiment, the expert system may determine that the system should maintain or modify operating parameters, equipment, or neural network model weightings when off-rated operation occurs. For example, a reciprocating compressor in an oil refinery that delivers high-pressure gas may be measured as operating abnormally by sensors feeding data to an expert system (optionally including a neural network or other machine learning system). If the expert system receives repeatedly abnormal data, it may predict that the refinery will not achieve its specified goals and recommend an action, such as taking a reciprocating compressor offline for maintenance. In another embodiment, the expert system may determine that the system should collect more or fewer data points from one or more sensors. For example, an anchor agitator in a pharmaceutical processing plant may be programmed to agitate the contents of a tank until a certain level of viscosity (e.g., measured in centipoise) is achieved. If the expert system collects data indicating an increase in viscosity during operation, it may recommend collecting additional data points to confirm the predicted condition as viscosity places increasing strain on the plant systems. In yet another embodiment, the expert system may determine that the system should change its data storage technique. In yet another example, the expert system may determine that the system should change its data presentation mode or method. In a further embodiment, the expert system may determine that the system should apply one or more filters (e.g., low-pass, high-pass, band-pass, etc.) to the collected data. In yet another embodiment, the expert system may determine that the system should collect data from a new smart band/a new set of sensors and/or begin measuring a new aspect identified by the neural net itself. For example, various measurements may be taken of a paddle agitator operating in a pharmaceutical factory, such as mixing time, temperature, homogeneous substrate distribution, heat or oxygen transfer rate with the internal structures or tank walls, mechanical stress, and force or torque on the agitator vessel or internal structures. The smart band monitoring these various aspects of the paddle agitator may include various sensor data streams, such as flow meters, temperature meters, etc. As the expert system iterates, perhaps seeded with minimal data from the agitator's operation, new aspects of operation may become apparent, such as the impact of pH on the operating conditions. In this manner, a new smart band containing sensor data from a pH meter is identified by the expert system. In yet a further embodiment, the expert system may determine that the system should cease collecting data from the smart band, one or more sensors, etc. In another embodiment, the expert system may determine that the system should begin collecting data from a new smart band, such as a new smart band identified by the neural net itself. In yet another embodiment, the expert system may determine that the system should adjust the weights/biases of the models used by the expert system. In yet another embodiment, the expert system may determine that the system should remove/reastask underutilized equipment. For example, an expert system may monitor multiple agitators in conjunction with pumps that blow off liquids in a pharmaceutical processing plant while the plant is operating. By iterating with data obtained from operating the plant with the agitators, the expert system can predict that a certain state will be achieved even if one or more agitators are taken out of service.

In embodiments, a monitoring system for collecting data in an industrial environment may include a plurality of input sensors, such as any of those described herein, communicatively coupled to a data collector having a controller. The monitoring system may include a data collection band circuit configured to determine at least a subset of the plurality of sensors for processing output data. The system may also include a machine learning data analysis circuit configured to receive output data from at least a subset of the plurality of sensors and ream a pattern in the received output data indicative of a condition. In some embodiments, the data collection band circuit may modify at least a subset of the plurality of sensors, or an aspect thereof, based on one or more of the learned received output data pattern and the condition. In certain embodiments, the machine learning data analysis circuit seeds a model that enables learning of the data pattern. The model may be a physical model, an operational model, a system model, or the like. In other embodiments, the machine learning data analysis circuit is structured for deep learning, where input data is provided to the circuit with no or minimal seed, and the machine learning data analysis circuit reams based on output feedback. For example, in a chemical processing plant producing polymers, a static mixer may be used to facilitate polymerization reactions. Static mixers can employ turbulent or laminar flow in their operation. Minimal data acquired during static mixer operation, such as heat transfer, mixer exit velocity, Reynolds number, and pressure drop, can be input into an expert system, which can then iterate toward a prediction based on initial feedback (polymer viscosity, polymer color, polymer reactivity, etc.).

Management of smart bands by an expert system may involve balancing multiple goals/guidelines. For example, a repair and maintenance organization (RMO) may have operating parameters designed for maintenance of a refinery's storage tanks, while the refinery owner may have specific operating parameters for the storage tanks designed to meet production targets. These goals (related to maintenance targets or production output in this example) may be tracked by different data collection bands. For example, storage tank maintenance may be tracked by sensors including vibration transducers and strain gauges, while storage tank production targets may be tracked by sensors including temperature sensors and flow meters. The expert system can intelligently manage bands aligned with different goals (optionally under the supervision of one or more supervisors (human or automated) using neural nets, machine learning systems, deep learning systems, etc.) and assign weights, parameter modifications, or recommendations based on factors such as bias toward one goal or a compromise to allow better alignment with all tracked goals. The compromise between goals delivered to the expert system may be based on one or more hierarchies or rules (e.g., regarding authority, role, importance, etc.) of the applicable goals. In embodiments, the compromise between goals may be optimized using machine learning, such as neural nets, deep learning systems, or other artificial intelligence systems as described throughout this disclosure. In one illustrative example, in a chemical processing plant operating gas-powered agitators, the expert system may manage multiple smart bands, such as one directed at detecting the operating status of the gas-powered agitators, one directed at identifying the probability of achieving production targets, and one directed at determining whether the gas-powered agitator's operation is meeting fuel efficiency targets. Each of these smart bands is equipped with a different sensor or data from different sensors (e.g., a vibration transducer indicating operating status, a flow meter indicating production targets, and a fuel gauge indicating fuel efficiency), and the output data is indicative of an aspect of the particular goal. When a single sensor or set of sensors serves multiple goals, overlapping smart bands (having some sensors in common and other sensors in common) can take input from that sensor or set of sensors, as managed by the smart band platform 10722. Rules may prioritize data-constrained collection (e.g., due to power limitations, storage limitations, bandwidth limitations, input/output processing capacity), such that smartband data collection related to that goal is maintained while other goals are paused or shut down. Goal prioritization may be managed hierarchically or through machine learning. Expert systems may seed models with current data as they iterate toward a predicted state (i.e., achieving the goal), or may not seed at all. In this example, a plant owner may decide to bias the system toward fuel efficiency during operation of a gas-powered agitator. However, as the expert system iterates, predicting that the system will not or is not achieving a particular goal and providing recommended changes to increase the likelihood of achieving the goal, the plant owner can configure the system with a bias toward fuel efficiency so that recommended changes to parameters that affect fuel efficiency are made in preference to other recommended changes.

In embodiments, an expert system can be seeded with multiple smart bands and then continue to iterate in a deep-reaching manner to arrive at a single smart band that optimizes meeting one or more goals. For example, a thermal heating system in a chemical or food processing plant may track multiple goals, such as thermal efficiency and economic efficiency. Thermal efficiency is expressed by comparing the BTUs input to the system, which is determined by knowing the quantity and quality of fuel used, with the BTUs output from the system, which is calculated using the output volume and temperature difference between materials entering and leaving the system. The economic efficiency of a thermal heating system may be expressed as the ratio of the cost (fuel, labor, materials, services, etc.) to operate the system over a period of time to the energy output from the system. Data used to track thermal efficiency may include data from flow meters, quality data points(s), and thermometers, while data used to track economic efficiency may be the energy output (e.g., kWh) and cost data from the system. These data may be used by the smart bands to predict conditions, and the expert system may iterate toward a smart band optimized to predict conditions related to both thermal and economic efficiency. The new smart band may include data previously used on the individual smart band, but may also use new data from different sensors or data sources. In an embodiment, the expert system seeds multiple smart bands and iterates to predict various conditions, but may also iterate to reduce the number of smart bands required to predict the same set of conditions.

The iterations of an expert system may, in some embodiments, be governed by rules. For example, the expert system may be configured to collect data for seeding at a predetermined frequency. The expert system may be configured to iterate at least several times when new components/equipment/fuel sources are added, when a sensor goes offline, or as standard practice. For example, if a sensor measuring the rotations of a food processing line's agitator goes offline and the expert system begins acquiring data from a new sensor measuring the same data point, the expert system may be configured to iterate multiple times before that condition is utilized or affects downstream actions. The expert system may be configured for offline training or online training. The expert system may be configured to include static and/or manually entered data in its smartband. For example, an expert system managing smartbands associated with a food processing plant's mixers may be structured to iterate to predict the mixing time until the food being processed achieves a specific viscosity, with the smartband containing data regarding the mixer's speed, the temperature of its contents, viscosity measurements, and the desired endpoints for the food's viscosity and temperature. The expert system may also be configured to include minimum/maximum numbers of variables.

In embodiments, the expert system may be overridden. In embodiments, the expert system may revert to a previous band configuration if the expert system fails, such as if the neural network fails in a neural net expert system, if there is too much uncertainty in a model-based system, if the system cannot resolve conflicting rules in a rule-based system, or if the system cannot converge on a solution in any of the above cases. For example, sensor data from an irrigation system used by a smart band's expert system may indicate a significant leak in a field, but visual inspection, such as with a drone, may indicate no such leak. In this case, the expert system reverts to the original smart band to seed the expert system. In another example, one or more point sensors on an industrial pressure cooker indicate an impending seal failure, but the data collection band on which the expert system weighted performance metrics to converge could not identify the failure. In this case, the smart band reverts to the original configuration or a version of the smart band that would have also identified the impending pressure cooker failure. A seal may be applied. In embodiments, the expert system may change the smart band configuration if a new component is added that brings the system closer to a different offset system. For example, a vacuum distillation unit has been added to an oil and gas refinery to distill naphthalene, but the expert system's current smart band configuration comes from a refinery that distills kerosene. In this example, a data structure with smart band configurations for various offset systems can be searched to find a system that more closely matches the current system. If a new offset system is identified as a closer match, such as one that also distills naphthalene, the new smart band configuration (e.g., which sensors to use, where to place them, how often to sample them, what static data points are needed, etc., as described herein) is used as the seed for the expert system to iterate to predict the state of the system. In embodiments, the expert system can change the smart band configuration when a new set of offset data becomes available from a third-party library. For example, a pharmaceutical plant might optimize a catalytic reactor to operate at high efficiency and store the smart band configuration in a data structure. The data structure can optimize the reactor's operation by continuously scanning for new smart bands that help monitor the catalytic reaction.

In embodiments, the expert system may be used to identify unknown variables. For example, the expert system may iterate to identify missing variables for use in further iterations, such as further neural net iterations. For example, an unused tank in a power plant's legacy condensate and make-up water system may have an unknown capacity because it is inaccessible and there is no documentation for the tank. A set of sensors can measure various aspects of the tank to calculate an estimated volume (such as the amount of inflow into downstream spaces or the time it takes for a dye-traced solution to pass through the system), and that volume can be input into the neural net as a new variable for the smart band.

In embodiments, the location of nodes in the expert system may be on a machine, on a data collector (or group thereof), on a network infrastructure (enterprise or other), or on the cloud. In embodiments, there may be neurons distributed across nodes (e.g., machines, data collectors, networks, clouds).

In one aspect, a monitoring system 10700 for data collection in an industrial environment includes a plurality of input sensors 10702 communicatively coupled to a data collector 10704 having a controller 10706; a data collection band circuit 10708 configured to determine at least one collection parameter for at least one of the plurality of sensors 10702 for processing output data 10710; and a machine learning data analysis circuit 10712 configured to receive the output data 10710 from at least one of the plurality of sensors 10702 and learn received output data patterns 10718 indicative of a condition. The data collection band circuit 10708 alters the at least one collection parameter for at least one of the plurality of sensors 10702 based on one or more of the learned received output data patterns 10718 and the condition. The condition may correspond to an outcome associated with a machine in the environment, an expected outcome associated with a machine in the environment, an outcome associated with a process in the environment, an expected outcome associated with a process in the environment, etc. The collection parameters may be bandwidth parameters, used to control multiplexing of multiple input sensors, timing parameters, frequency range parameters, granularity parameters for collection of sensor data, or storage parameters for collected data. The machine learning data analysis circuit may be configured to refine the received output data pattern 10718 by being seeded with a model 10720 that is a physical, operational, or system model. The machine learning data analysis circuit may be configured to refine the received output data pattern 10718 based on a state. The data collection bandwidth circuit may change a subset of the multiple sensors if the learned received output data pattern does not reliably predict the state, which may include ceasing collection of data from at least one subset.

The monitoring system 10700 may maintain or modify operating parameters of an item of equipment in the environment based on the determined condition. The controller 10706 may adjust the weighting of the machine learning data analysis circuit 10712 based on the learned received output data pattern 10718 or the condition. The controller 10706 may collect more or fewer data points from one or more members of at least one subset of the plurality of sensors 10702 based on the learned received output data pattern 10718 or the condition. The controller 10706 may change the data storage technique of the output data 10710 based on the learned received output data pattern 10718 or the condition. The controller 10706 may change the data presentation mode or manner based on the learned received output data pattern 10718 or the condition. The controller 10706 may apply one or more filters to the output data 10710. The controller 10706 may identify a new data collection bandwidth circuit 10708 based on one or more of the learned received output data patterns 10718 and the condition. The controller 10706 may adjust the weights/biases of the machine learning data analysis circuit 10712, such as in response to the learned received output data patterns 10718, the accuracy of the machine learning data analysis circuit's prediction of the expected condition, the accuracy of the machine learning data analysis circuit's classification of the condition, etc. The monitoring device 10700 may remove or retask underutilized equipment based on one or more of the learned received output data patterns 10718 and the condition. The machine learning data analysis circuit 10712 may include a neural network expert system. At least a subset of the plurality of sensors measures vibration and noise data. The machine learning data analysis circuit 10712 may be configured to ream received output data patterns 10718 indicative of progress/alignment with one or more goals/guidelines, where progress/alignment with each goal/guideline may be determined by a different subset of the plurality of sensors. The machine learning data analysis circuit 10712 may be configured to ream received output data patterns 10718 indicative of unknown variables. The machine learning data analysis circuit 10712 may be configured to ream received output data patterns 10718 indicative of preferred inputs among available inputs. The machine learning data analysis circuit 10712 may be configured to ream received output data patterns 10718 indicative of preferred input data collection bands among available input data collection bands. The machine learning data analysis circuit 10712 may be located partially on the machine, partially on one or more data collectors, partially on a network infrastructure, partially on the cloud, or any combination thereof.

In an embodiment, a monitoring device for data collection in an industrial environment includes a plurality of input sensors 10702 communicatively coupled to a controller 10706, the controller 10706 including a data collection band circuit 10708 configured to determine at least a subset of the plurality of sensors 10702 for processing output data 10710, and a machine learning data analysis circuit 10712 configured to receive output data from the at least one subset of the plurality of sensors 10702 and learn received output data patterns 10718 indicative of a condition, the data collection band circuit 10708 modifying an aspect of the at least one subset of the plurality of sensors 10702 based on one or more of the learned received output data patterns 10718 and the condition. The data collection bandwidth circuit 10708 varies the number or frequency of data points collected from one or more members of at least a subset of the plurality of sensors 10702. The data collection bandwidth circuit 10708 varies bandwidth parameters, timing parameters, frequency ranges, granularity of collection of sensor data, storage parameters of collected data, etc.

In one embodiment, a monitoring system 10700 for data collection in an industrial environment includes a plurality of input sensors 10702 communicatively coupled to a data collector 10704 having a controller 10706; a data collection band circuit 10708 configured to determine at least one collection parameter for at least one of the plurality of sensors 10702 for processing output data 10710; and a machine learning data analysis circuit 10712 configured to receive the output data 10710 from at least one of the plurality of sensors 10702 and learn received output data patterns indicative of a condition. The data collection band circuit 10708 modifies the at least one collection parameter for at least one of the plurality of sensors 10702 based on one or more of the learned received output data pattern 10718 and the condition, and the data collection band circuit 10708 modifies the at least one of the plurality of sensors 10702 if the learned received output data pattern 10718 does not reliably predict the condition.

In one embodiment, a monitoring system 10700 for data collection in an industrial environment may include a plurality of input sensors 10702 communicatively coupled to a data collector 10704 having a controller 10706; a data collection band circuit 10708 configured to determine at least one collection parameter for at least one of the plurality of sensors 10702 to process output data 10710; and a machine learning data analysis circuit 10712 configured to receive the output data 10710 from at least one of the plurality of sensors 10702 and learn a received output data pattern 10718 indicative of a condition. The data collection band circuit 10708 alters the collection parameter of at least one of the plurality of sensors 10702 based on one or more of the learned received output data pattern 10718 and the condition, and the data collector 10704 collects more or fewer data points from at least one of the plurality of sensors 10702 based on the learned received output data pattern 10718 or the condition.

In one embodiment, a monitoring system 10700 for data collection in an industrial environment may include a plurality of input sensors 10702 communicatively coupled to a data collector 10704 having a controller 10706, a data collection band circuit 10708 configured to determine collection parameters of at least one of the plurality of sensors 10702 for processing output data 10710, and a machine learning data analysis circuit 10712 configured to receive the output data 10710 from at least one of the plurality of sensors 10702 and extract patterns in the received output data 10710 indicative of a condition. and a machine learning data analysis circuit 10712 configured to receive output data 10710 from at least one sensor 10702 of the plurality of sensors and learn a pattern of the received output data 10710 indicative of a condition, wherein the data collection bandwidth circuit 10708 alters at least one collection parameter for the at least one sensor 10702 of the plurality of sensors based on one or more of the learned received output data pattern 10718 and the condition, and the controller 10706 alters a data storage technique for the output data 10710 based on the learned received output data pattern 10718 or the condition.

In one embodiment, a monitoring system 10700 for data collection in an industrial environment may include a plurality of input sensors 10702 communicatively coupled to a data collector 10704 having a controller 10706, a data collection band circuit 10708 configured to determine collection parameters of at least one of the plurality of sensors 10702 for processing output data 10710, and a machine learning data analysis circuit 10712 configured to receive the output data 10710 from at least one of the plurality of sensors 10702 and extract received output data patterns 10718 indicative of a condition. and a machine learning data analysis circuit 10712 configured to receive output data 10710 from at least one sensor 10702 of the plurality of sensors and learn a received output data pattern 10718 indicative of a condition, wherein the data collection bandwidth circuit 10708 alters at least one collection parameter for the at least one sensor 10702 of the plurality of sensors based on one or more of the learned received output data pattern 10718 and the condition, and the controller 10706 alters a data presentation mode or manner based on the learned received output data pattern 10718 or the condition.

In one embodiment, a monitoring system 10700 for data collection in an industrial environment may include a plurality of input sensors 10702 communicatively coupled to a data collector 10704 having a controller 10706, a data collection band circuit 10708 configured to determine collection parameters of at least one of the plurality of sensors 10702 for processing output data 10710, and a machine learning data analysis circuit 10712 configured to receive the output data 10710 from at least one of the plurality of sensors 10702 and extract received output data patterns 10718 indicative of a condition. and a machine learning data analysis circuit 10712 configured to receive output data 10710 from at least one of the plurality of sensors 10702 and learn a received output data pattern 10718 indicative of a condition, wherein the data collection band circuit 10708 modifies collection parameters of at least one of the plurality of sensors 10702 based on one or more of the learned received output data pattern 10718 and the condition, and the controller 10706 identifies a new data collection band circuit 10708 based on one or more of the learned received output data pattern 10718 and the condition.

In one embodiment, a monitoring system 10700 for data collection in an industrial environment may include a plurality of input sensors 10702 communicatively coupled to a data collector 10704 having a controller 10706, a data collection band circuit 10708 configured to determine collection parameters of at least one of the plurality of sensors 10702 for processing output data 10710, and a machine learning data analysis circuit 10712 configured to receive the output data 10710 from at least one of the plurality of sensors 10702 and learn received output data patterns 10718 indicative of a condition. and a machine learning data analysis circuit 10712 configured to receive output data 10710 from at least one sensor 10702 of the plurality of sensors and learn a received output data pattern 10718 indicative of a condition, wherein the data collection bandwidth circuit 10708 alters at least one collection parameter for the at least one sensor 10702 of the plurality of sensors based on one or more of the learned received output data pattern 10718 and the condition, and the controller 10706 adjusts a weight/bias of the machine learning data analysis circuit 10712. The adjustment may be in response to the learned received output data pattern, in response to an accuracy of a prediction of an expected condition by the machine learning data analysis circuit, in response to an accuracy of a classification of the condition by the machine learning data analysis circuit, etc.

In one embodiment, a monitoring system 10700 for data collection in an industrial environment may include a plurality of input sensors 10702 communicatively coupled to a data collector 10704 having a controller 10706, a data collection band circuit 10708 configured to determine collection parameters of at least one of the plurality of sensors 10702 for processing output data 10710, and a machine learning data analysis circuit 10712. The machine learning data analysis circuit is configured to receive output data 10710 from at least one of the plurality of sensors 10702 and learn a received output data pattern 10718 indicative of a condition, the data collection band circuit 10708 altering the collection parameters of at least one of the plurality of sensors 10702 based on one or more of the learned received output data pattern 10718 and the condition, and the machine learning data analysis circuit 10712 configured to recognize the received output data pattern 10718 indicative of progress or alignment with one or more goals or guidelines.

(1) In one embodiment, a monitoring system for data collection in an industrial environment includes: a plurality of input sensors communicatively coupled to a data collector having a controller; a data collection bandwidth circuit configured to process output data and determine at least one collection parameter for at least one of the plurality of sensors; and a machine learning data analysis circuit configured to receive output data from at least one of the plurality of sensors and learn a received output data pattern indicative of a condition, wherein the data collection bandwidth circuit modifies the at least one collection parameter for at least one of the plurality of sensors based on one or more of the learned received output data pattern and the condition. (2) The system of (1), wherein the condition corresponds to an outcome associated with a machine in the environment. (3) The system of (1), wherein the condition corresponds to an expected outcome associated with a machine in the environment. (4) The system of (1), wherein the condition corresponds to an outcome associated with a process in the environment. (5) The system of (1), wherein the condition corresponds to an expected outcome associated with a process in the environment. (6) The system of (1), wherein the collection parameter is a bandwidth parameter. (7) The system of (1), wherein the collection parameters are used to control multiplexing of the plurality of input sensors. (8) The system of (1), wherein the collection parameters are timing parameters. (9) The system of (1), wherein the collection parameters relate to a frequency range. (10) The system of (1), wherein the collection parameters relate to a granularity of sensor data collection. (11) The system of (1), wherein the collection parameters are storage parameters for the collected data. (12) The system of (1), wherein the machine learning data analysis circuitry is configured to seed a model and ream the received output data pattern. (13) The system of (12), wherein the model is a physical model, an operational model, or a system model. (14) The system of (1), wherein the machine learning data analysis circuitry is configured to ream the received output data pattern based on the state. (15) The system of (1), wherein the data collection bandwidth circuitry changes a subset of the plurality of sensors if the learned received output data pattern does not reliably predict the condition. (16) The system of (15), wherein changing at least one subset includes ceasing collection of data from at least one subset. (17) The system of (1), wherein the monitoring system maintains or changes operating parameters of equipment in the environment based on the determined condition. (18) The system of (1), wherein the controller adjusts weightings of the machine learning data analysis circuitry based on the learned received output data pattern or the condition. (19) The system of (1), wherein the controller collects more or fewer data points from one or more members of at least one subset of the plurality of sensors based on the learned received output data pattern or the condition. (20) The system of (1), wherein the controller changes a data storage technique for the output data based on the learned received output data pattern or the condition. (21) The system of (1), wherein the controller changes the data presentation mode or manner based on the learned received output data pattern or the state. (22) The system of (1), wherein the controller applies one or more filters to the output data. (23) The system of (1), wherein the controller identifies a new data collection band circuit based on one or more of the learned received output data pattern and the state. (24) The system of (1), wherein the controller adjusts the weights/biases of the machine learning data analysis circuit. (25) The system of (24), wherein the adjustment is made in response to the learned received output data pattern. (26) The system of (24), wherein the adjustment is made in response to the accuracy of the machine learning data analysis circuit's prediction of the expected state. (27) The system of (24), wherein the adjustment is made in response to the accuracy of the machine learning data analysis circuit's classification of the state. (28) The system of (1), wherein the monitoring device removes/reworks underutilized equipment based on one or more of learned received output data patterns and status. (29) The system of (1), wherein the machine learning data analysis circuit includes a neural network expert system. (30) The system of (1), wherein at least a subset of the plurality of sensors measures vibration and noise data. (31) The system of (1), wherein the machine learning data analysis circuit is configured to learn received output data patterns indicative of progress/alignment with one or more goals/guidelines. (32) The system of (31), wherein progress/alignment with each goal/guideline is determined by a different subset of the plurality of sensors. (33) The system of (1), wherein the machine learning data analysis circuit is configured to learn received output data patterns indicative of unknown variables. (34) The system of (1), wherein the machine learning data analysis circuit is configured to learn received output data patterns indicative of preferred inputs among available inputs. (35) The system of (1), wherein the machine learning data analysis circuit is configured to ream received output data patterns indicative of preferred input data collection bands among available input data collection bands. (36) The system of (1), wherein the machine learning data analysis circuit is located partially on the machine, on one or more data collectors, in a network infrastructure, in the cloud, or any combination thereof. (37) A monitoring device for data collection in an industrial environment, comprising: a plurality of input sensors communicatively coupled to a controller, the controller configured to determine at least a subset of the plurality of sensors for processing output data; and a machine learning data analysis circuit configured to receive output data from at least a subset of the plurality of sensors and learn received output data patterns indicative of a condition, the data collection band circuit modifying an aspect of the at least a subset of the plurality of sensors based on one or more of the learned received output data patterns and the condition. (38) The system of (37), wherein the aspect modified by the data collection band circuit is a number of data points collected from one or more members of the at least a subset of the plurality of sensors. (39) The system of (37), wherein the aspect varied by the data collection band circuitry is the frequency of data points collected from one or more members of at least a subset of the plurality of sensors. (40) The system of (37), wherein the aspect varied by the data collection band circuitry is a bandwidth parameter. (41) The system of (37), wherein the aspect varied by the data collection band circuitry is a timing parameter. (42) The system of (37), wherein the aspect varied by the data collection band circuitry relates to a frequency range. (43) The system of (37), wherein the aspect varied by the data collection band circuitry relates to the granularity of collection of sensor data. (44) The system of (37), wherein the collection parameter is a storage parameter of the collected data. (45) A monitoring system for collecting data in an industrial environment, comprising: (46) A monitoring system for collecting data in an industrial environment, comprising: a plurality of input sensors communicatively coupled to a data collector having a controller, a data collection band circuit configured to determine at least one collection parameter for at least one of the plurality of sensors to process output data, a machine learning data analysis circuit configured to receive output data from at least one of the plurality of sensors and learn received output data patterns indicative of a condition, the data collection band circuit altering the collection parameter of at least one of the plurality of sensors based on one or more of the learned received output data patterns and the condition, and the data collection band circuit altering at least one of the plurality of sensors if the learned received output data patterns do not reliably predict the condition. a plurality of input sensors communicatively coupled to a data collection device having a controller; a data collection band circuit configured to determine at least one collection parameter for at least one of the plurality of sensors to process output data; and a machine learning data analysis circuit configured to receive output data from at least one of the plurality of sensors and learn a received output data pattern indicative of a condition, wherein the data collection band circuit alters a collection parameter of at least one of the plurality of sensors based on one or more of the learned received output data pattern and the condition, and the data collection device collects more or fewer data points from at least one of the plurality of sensors based on the learned received output data pattern or the condition. (47) A monitoring system for data collection in an industrial environment, comprising: a plurality of input sensors communicatively coupled to a data collector having a controller; a data collection band circuit configured to determine at least one collection parameter for at least one of the plurality of sensors to be processed; output data; and a machine learning data analysis circuit configured to receive the output data from at least one of the plurality of sensors and learn a received output data pattern indicative of a condition, wherein the data collection band circuit alters the at least one collection parameter for at least one of the plurality of sensors based on one or more of the learned received output data pattern and the condition, and the controller alters a data storage technique for the output data based on the learned received output data pattern or the condition. (48) A monitoring system for data collection in an industrial environment, comprising: (49) A monitoring system for collecting data in an industrial environment, comprising: a plurality of input sensors communicatively coupled to a data collection device having a controller, a data collection band circuit configured to determine at least one collection parameter for at least one of the plurality of sensors to process output data, and a machine learning data analysis circuit configured to receive output data from at least one of the plurality of sensors and learn a received output data pattern indicative of a condition, wherein the data collection band circuit alters the collection parameter of at least one of the plurality of sensors based on one or more of the learned received output data pattern and the condition, and the controller alters a data presentation mode or manner based on the learned received output data pattern or the condition. (50) A monitoring system for collecting data in an industrial environment, comprising: a plurality of input sensors communicatively coupled to a data collection device having a controller, a data collection band circuit configured to determine at least one collection parameter for at least one of the plurality of sensors to process output data, and a machine learning data analysis circuit configured to receive output data from at least one of the plurality of sensors and learn a received output data pattern indicative of a condition, the data collection band circuit modifying the collection parameter of at least one of the plurality of sensors based on one or more of the learned received output data pattern and the condition, and the controller identifying a new data collection band circuit based on the learned received output data pattern and the condition. A system comprising: a plurality of input sensors communicatively coupled to a data collector having a controller; a data collection band circuit configured to determine at least one collection parameter for at least one of the plurality of sensors to process output data; and a machine learning data analysis circuit configured to receive output data from at least one of the plurality of sensors and learn received output data patterns indicative of a condition, wherein the data collection band circuit modifies the collection parameters of at least one of the plurality of sensors based on one or more of the learned received output data patterns and the condition, and the controller adjusts weights/biases of the machine learning data analysis circuit. (51) The system of (50), wherein the adjustment is made in response to the learned received output data patterns. (52) The system of (50), wherein the adjustment is made in response to an accuracy of a prediction of an expected condition by the machine learning data analysis circuit. (53) The system of (50), wherein the adjustment is made in response to an accuracy of a classification of a condition by the machine learning data analysis circuit. (54) A monitoring system for collecting data in an industrial environment, comprising: a plurality of input sensors communicatively coupled to a data collection device having a controller; a data collection band circuit configured to determine at least one collection parameter for at least one of the plurality of sensors to process output data; and a machine learning data analysis circuit configured to receive output data from at least one of the plurality of sensors and learn received output data patterns indicative of a condition; wherein the data collection band circuit alters the collection parameters of at least one of the plurality of sensors based on one or more of the learned received output data patterns and the condition; and the machine learning data analysis circuit is configured to learn received output data patterns indicative of progress or alignment with one or more goals or guidelines.

As described elsewhere herein, expert systems in industrial environments may use sensor data to make predictions regarding the outcome or condition of the environment or items within the environment. Data collection may be of various types (e.g., vibration data, noise data, and other sensor data of the types described throughout this disclosure) for event detection, condition detection, etc. For example, an expert system may utilize ambient noise, or the overall sound environment of an area and/or the overall vibration of a device of interest, optionally in combination with other sensor data, in detecting or predicting an event or condition. For example, a reciprocating compressor in an oil refinery may generate its own vibrations, but may also have ambient vibrations through contact with other aspects of the system.

In embodiments, all three types of noise (ambient noise, local noise, and vibration noise), including various subsets thereof and combinations with other types of data, along with measurements, may be organized into large datasets and processed by a "deep learning" machine/expert system aiming to predict one or more conditions (e.g., maintenance, failure, or operation) or overall outcomes, such as by learning from human oversight or from other feedback, such as feedback from one or more systems described throughout this disclosure and the documents incorporated by reference herein.

Throughout this disclosure, various examples will include machines, components, equipment, assemblies, etc., and it should be understood that the present disclosure may apply to any of the foregoing. Elements of these machines (e.g., rotating, reciprocating, swinging, bending, flowing, suspended, floating, bouncing, bearing, etc.) operating in industrial environments may generate vibrations at specific frequencies and/or amplitudes typical of the elements when the elements are in a given operating state or condition (e.g., the normal operating mode of the machine at a given speed and in a given gear). Changes in vibration parameters can indicate or predict machine conditions or outcomes. Various sensors are useful for measuring vibration, including accelerometers, velocity transducers, image sensors, acoustic sensors, and displacement probes, which are sometimes collectively referred to as vibration sensors. Vibration sensors can be permanently or temporarily attached to machines (e.g., with adhesive, hook-and-loop, or magnetic attachments) or placed on mobile or portable data collection devices. Detected conditions can be compared to historical data to identify or predict conditions or outcomes. Typical faults that can be identified using vibration analysis include: Machine imbalance, machine misalignment, resonance, bent shafts, gear mesh irregularities, blade path irregularities, vane path irregularities, recirculation and cavitation, motor failures (rotor and stator), bearing failures, etc. Also included are excessive friction, clutch slippage, belt problems, suspension and shock absorption problems, valve and other fluid leaks, lack of pressure in lubrication and other fluid systems, overheating (resulting from many of the above), blocked or frozen mechanical system engagements, interference effects, and other faults described in this disclosure and the documents incorporated by reference.

Because machines are often adjacent to or operating in coordination with other machines, measuring machine vibrations can be complicated by the presence of various noise components in the environment and associated vibrations to which the machine may be subjected. Indeed, the surrounding and/or local environment may have known vibration and/or noise patterns. In embodiments, the combined vibration data may form unique patterns due to ambient or local noise and other surrounding environmental conditions, as described in more detail herein.

In embodiments, vibration noise measurements may include one or more vibration sensors on or within the machine to measure continuous or periodic machine vibration noise. Analysis of the vibration noise may be performed, such as filtering, signal conditioning, spectral analysis, trend analysis, etc. Analysis may be performed on collective or individual sensor measurements to isolate the equipment's vibration noise to obtain the equipment's characteristic vibration, vibration pattern, or "vibration fingerprint" of the machine. The vibration fingerprints may be stored in a vibration fingerprint data structure, or library. Vibration fingerprints may include frequency, spectrum (i.e., frequency vs. amplitude), velocity, peak location, wave peak shape, waveform shape, wave envelope shape, acceleration, phase information, phase shift (including complex phase measurements), etc. Vibration fingerprints may be stored in a library in association with searchable and sortable parameters. Parameters include the brand and type of machine/component/equipment, sensor mounting and placement location, equipment/machine duty cycle, equipment/machine load distribution, dynamic interactions with other equipment, RPM, flow rate, pressure, and other vibration drive characteristics, line power voltage, equipment age, operating hours, and vibration type. Equipment age, operating hours, known adjacent equipment, associated auxiliary equipment/components, size of the space in which the equipment is installed, equipment platform material, heat flux, magnetic field, electric field, current, voltage, capacitance, inductance, product aspect, and combinations thereof (e.g., simple ratios). Vibration fingerprints can be obtained for machines during normal operation or for other periods of operation (e.g., irregular operation, breakdowns, maintenance requirements, defective components, incorrect operating parameters, and other conditions) and stored in a library for comparison with current data. A library of vibration fingerprints can be stored as indices with associated predictions, states, results, and/or events. Trend analysis data of measured vibration fingerprints can indicate the time between maintenance and failure events.

In embodiments, vibration noise may be used by an expert system to determine machine health, such as good operation, production rate, generation rate, operational efficiency, financial efficiency (e.g., output per cost), or power efficiency. In embodiments, the expert system may compare the vibration noise to stored vibration fingerprints. In other embodiments, the expert system may be seeded with initial feedback regarding the vibration noise and conditions or outcomes to learn to predict other conditions or outcomes. For example, a center-pivot irrigation system may be remotely monitored with attached vibration sensors, and the measured vibration noise may be compared to a library of vibration fingerprints to ensure the system is operating properly. If the system is not operating properly, the expert system may automatically dispatch field crews or drones to investigate. In another example, in a vacuum distillation unit at an oil refinery, the vibration noise may be compared to a library of stored vibration fingerprints by an expert system or other system to determine diesel production. Furthermore, the expert system may be fed the vibration noise of a pipeline at normal production rates, and the expert system may iterate with current data (e.g., modified vibration noise and possibly other modified parameters) to predict whether a change has resulted in increased production. In this manner, measurements may be continuously analyzed to remotely monitor operation.

In embodiments, the vibration noise may be compared, such as by an expert system, to stored vibration fingerprints in a library and associated conditions and outcomes, or alternatively, may be used as a seed for an expert system to predict when maintenance is needed (e.g., as described herein, when the vibration noise matches a condition when the equipment/component required maintenance, when the vibration noise exceeds a threshold/limit, when the vibration noise exceeds a threshold/limit, or when the vibration noise matches a vibration fingerprint in the library along with one or more additional parameters, such as an out-of-specification measurement, a signal artifact, etc.). For example, if a vibration fingerprint from a turbine agitator in a pharmaceutical processing plant matches a vibration fingerprint when the turbine agitator needed bearing replacement, the expert system may trigger an action, such as immediately shutting down the agitator or scheduling its shutdown and maintenance.

In embodiments, the vibration noise may be compared, such as by an expert system, to stored vibration fingerprints in a library and associated conditions and outcomes, or may alternatively be used as a seed for the expert system to predict failure or impending failure. For example, vibration noise from a gas agitator in a pharmaceutical plant may match a condition in which the agitator has previously failed or is about to fail. In this case, the expert system may immediately shut down the agitator, schedule a shutdown, or activate a backup agitator. In another example, if vibration noise from a pump blast fluid agitator in a chemical processing plant exceeds a threshold or limit, the expert system may investigate the cause of the excessive vibration noise and take action, such as shutting down the agitator. In another example, vibration noise from an anchor agitator in a pharmaceutical plant may exceed a threshold or limit or match a vibration fingerprint in a library along with one or more additional parameters (see parameters herein), such as a decrease in flow rate or an increase in temperature. Using the obtained vibration noise along with the parameters, the expert system may more reliably predict failure or impending failure.

In embodiments, the vibration noise may be compared, such as by an expert system, to vibration fingerprints stored in a library and associated conditions and outcomes, or alternatively may be used as a seed for an expert system to predict or diagnose problems with the equipment or external sources contributing vibration noise to the equipment (e.g., imbalance, misalignment, wear, or damage). For example, if the vibration sound of a paddle agitator matches the vibration fingerprint of a past imbalance, the expert system may immediately shut down the agitator.

In embodiments, when the expert system uses vibration noise to predict an outcome or condition, the expert system can perform or cause downstream actions to be performed. Downstream actions include triggering an alert for a failure, impending failure, or maintenance event; shutting down equipment/components; initiating maintenance/lubrication/alignment; deploying a field technician; recommending vibration absorption/damping devices; modifying the process to utilize backup equipment/components; modifying the process to preserve products/reactants; generating/modifying a maintenance schedule; and the like. The vibration fingerprint can be combined with equipment duty cycle, RPM, flow rate, pressure, temperature, and other vibration-driving characteristics to obtain and report the status of equipment and components. For example, the vibration noise of a catalytic reactor in a chemical processing plant can be matched to a condition indicating the catalytic reactor requires maintenance. Based on this predicted maintenance condition, the expert system may deploy a field technician to perform the maintenance.

In embodiments, the library may be updated if the changed parameters result in a new vibration fingerprint or if the predicted outcome or condition does not occur in the absence of mitigation. In embodiments, the library may be updated if the vibration fingerprint is associated with a different condition than predicted by the library. The update may occur after only one instance where the actual condition did not match the condition predicted from the library. In other embodiments, it may occur after a threshold number of instances. In embodiments, the library may be updated to apply one or more rules for comparison, such as rules governing how many parameters must be matched with the vibration fingerprint to accept the predicted outcome, or the standard deviation for the match.

In embodiments, the vibration noise may be compared, such as by an expert system, to stored vibration fingerprints in a library and associated conditions and outcomes, or alternatively may be used as a seed for an expert system to determine whether changes in system parameters external or internal to the machine affect its essential operation. In embodiments, changes in one or more of the temperature, flow rate, materials used, age of use, power source, installation, or other parameters (see parameters above) may change the machine's vibration fingerprint. For example, in a pressure reactor in a chemical processing plant, the flow rate or reactants may be changed. Such changes may change the machine's vibration fingerprint, rendering the normal operating vibration fingerprint stored in the library incorrect.

Ambient noise, or the overall sound environment of an area and/or the overall vibration of a target device, optionally in combination with other ambient sensed conditions, can be used to detect or predict events, outcomes, or conditions. Ambient noise may be measured by microphones, ultrasonic sensors, acoustic wave sensors, optical vibration sensors (e.g., using a camera to look at vibrations that generate noise), or "deep learning" neural networks including various sensor arrays that use large data sets to identify patterns, types of sounds, types of noise, etc. In one embodiment, the ambient sensed condition may relate to the detection of motion. For example, the motion may be the motion of a platform (e.g., a vehicle, an oil platform, an onshore suspended platform, etc.) or the motion of an object (e.g., moving equipment, a person, a robot, a part (e.g., a fan blade or turbine blade), etc.). In one embodiment, the ambient sensed condition may be sensed by imaging, such as to detect the location and nature of various machines, devices, and other objects, including those that may affect local vibrations. In one embodiment, the ambient sensed condition may be sensed by thermal detection and imaging (e.g., the presence of a person, the presence of a heat source that may affect performance parameters, etc.). In embodiments, the ambient sensed condition may be sensed by field detection (e.g., electrical, magnetic, etc.). In embodiments, the ambient sensed condition may be sensed by chemical detection (e.g., smoke, other conditions). The expert system may use any sensor data to provide the ambient sensed condition for analysis along with vibration. The fingerprint is used to predict an outcome, event, or condition. For example, an ambient condition sensed near an agitator or mixer in a food processing plant may be the operation of a space heater during the winter, and the sensed ambient condition may include ambient noise and ambient temperature.

Localized noise refers to a noise or vibration environment that is known to be ambient but occurring locally. The expert system may filter ambient noise, employ common-mode noise rejection, and/or physically separate the sensing environment.

In embodiments, a system for data collection in industrial environments may use ambient noise, local noise, and vibration noise to predict outcomes, events, and conditions. Libraries may be generated for each of three noise types for various conditions (e.g., startup, shutdown, normal operation, other operating periods as described elsewhere herein). In other embodiments, libraries may be composed of noise patterns representing aggregates of ambient noise, local noise, and/or vibration noise. Analysis (e.g., filtering, signal conditioning, spectral analysis, trend analysis) may be performed on the aggregated noise to obtain characteristic noise patterns and identify changes in noise patterns as possible indicators of altered conditions. Libraries of noise patterns may be generated using established vibration fingerprints and local and ambient noise that can be sorted by parameters (see parameters herein) or other parameters/characteristics of the local and ambient environment (e.g., company type, industry type, product, presence/absence of robotic handling units, operating environment, flow rate, production volume, brand or type of auxiliary equipment (e.g., filters, seals, bonding machines)). Libraries of noise patterns may be used, for example by expert systems with machine learning capabilities, to determine the condition of machinery, predict when maintenance is required (e.g., out-of-spec measurements, signal artifacts), predict failures or impending failures, and predict/diagnose problems.

Based on the current noise patterns, the library may reference or use an expert system that predicts an outcome, event, or condition based on the noise pattern. Based on the prediction, the expert system may do one or more of the following: issue a warning of a failure, impending failure, or maintenance event; shut down equipment/component/line; initiate maintenance/lubrication/alignment; deploy a field technician; recommend vibration absorption/damping devices; modify the process to utilize backup equipment/components; modify the process to preserve products/reactants, etc.; generate/modify maintenance schedules, etc.

For example, the noise patterns of a thermal heating system in a pharmaceutical factory or cooking system may include local noise, ambient noise, and vibration noise. Ambient noise may be the result of various pumps, for example, pumping fuel through the system. Local noise may be caused by a local security camera beeping whenever it detects motion. Vibration noise may come from combustion machinery used to heat the thermal fluid. These noise sources may create noise patterns that are associated with the state of the thermal system. The noise patterns and associated states may be stored in a library. An expert system used to monitor the state of the thermal heating system may be seeded with noise patterns and associated states from the library. When current data is received by the expert system, the expert system may predict the state based on the learned noise patterns and associated states.

In another example, the noise pattern of a boiler feedwater in an oil refinery may include local noise and ambient noise. The local noise may be due, for example, to the operation of a feed pump supplying feedwater to a steam drum, and the ambient noise may be due to a nearby fan. These noise sources may create a noise pattern associated with the condition of the boiler feedwater. This noise pattern and associated conditions may be stored in a library. An expert system used to monitor the condition of the boiler may be seeded with the noise patterns and associated conditions from the library. When current data is received by the expert system, the expert system can predict the condition based on the learned noise patterns and associated conditions.

In yet another example, the noise patterns of a storage tank in an oil refinery may include local noise, ambient noise, and vibration noise. The ambient noise may be the result of, for example, a pump pumping product into the tank. The local noise may be due to a fan for ventilating the tank room. The vibration noise may be due to line noise in the power supply supplying the storage tank. These noise sources may create a noise pattern that is associated with the condition of the storage tank. The noise patterns and associated conditions are stored in a library. An expert system used to monitor the condition of the storage tank can seed the noise patterns and associated conditions from the library. When current data is received by the expert system, the expert system can predict the condition based on the learned noise patterns and associated conditions.

In another example, the noise patterns of a power plant's condensate and makeup system may include vibration and ambient noise. The ambient noise may be due to a nearby fan. The vibration noise may be due to the operation of the power plant, such as a condenser. These noise sources can form noise patterns associated with the condition of the condenser/makeup water system. The noise patterns and associated conditions may be stored in a library. An expert system used to monitor the condition of the condenser/makeup water system may be seeded with the noise patterns and associated conditions from the library. When current data is received by the expert system, the expert system can predict the condition based on the learned noise patterns and associated conditions.

The noise pattern library may be updated if a new noise pattern results from a changed parameter, or if the predicted outcome or condition does not occur if the diagnosed problem is not alleviated. The noise pattern library may also be updated if a noise pattern results in a different condition than predicted by the library. An update may occur after only one occurrence where the actual condition does not match the condition predicted from the library. In other embodiments, it may occur after a threshold number of occurrences. In embodiments, the library may be updated to apply one or more rules for comparison, such as rules specifying how many parameters must match a noise pattern, or a standard deviation for a match, to accept the predicted outcome. For example, replacing a baffle in a static stirrer in a pharmaceutical factory may change the noise pattern. In another example, aging seals on a pressure cooker in a food processing plant may change the noise pattern associated with the pressure cooker.

In embodiments, libraries of vibration fingerprints, noise sources, and/or noise patterns may be available for subscription. The libraries may be used by offset systems to improve local system operation. Subscribers can subscribe at any level (e.g., component, machine, equipment, etc.) to access data that is not typically available, such as competitor data or data on machinery and equipment in other industries not commonly considered. Subscribers can customize the library by searching indicators/predictions based on or filtered by system conditions, and updating indicators/predictions with their own data. Libraries may further include sensors located throughout the installation, on-board diagnostic systems and instruments and sensors, ambient sensors in the environment, sensors that can be temporarily deployed such as one or more mobile data collectors (e.g., flexible sets), and sensors that can be deployed for longer-term use, such as attached to points of interest on a device or system.

In embodiments, third parties (e.g., RMOs, manufacturers) can aggregate data at the component, equipment, and plant/installation levels to provide statistically valid data sets for optimizing their systems. For example, when considering a new installation of machinery, it may be beneficial to review the library for optimal data points to capture when predicting its condition. For example, a specific sensor package may be recommended to reliably determine the presence or absence of a failure. For example, if the audible vibration of the equipment, combined with certain levels of local noise and other environmental conditions, are reliably indicators of an impending failure, a vibration transducer/temperature/microphone package that monitors those factors may be recommended for the installation. Knowing this information may be helpful when deciding whether to rent or purchase a machine, or when selecting an associated warranty or service plan, based on knowing the amount and depth of information needed to reliably maintain the machine.

In embodiments, manufacturers can use the library to quickly gather in-service machine information to create engineering specifications for new customers.

In embodiments, noise and vibration data can be used to remotely monitor installations and automatically dispatch field crews.

In embodiments, noise and vibration data can be used to audit a system. For example, equipment operating outside of its licensed duty cycle may be detected by a series of vibration sensors and/or ambient/local noise sensors. In embodiments, alerts may be issued about possible out-of-warranty violations based on data from the vibration sensors and/or ambient/local noise sensors.

In embodiments, noise and vibration data can be used for maintenance. This can be particularly useful in deployments such as power plants where there are multiple machines that may vibrate and interact with the environment, such as two large generators on the same floor or platform as each other.

In an embodiment, a monitoring system 10800 for collecting data in an industrial environment may include a plurality of sensors 10802 selected from vibration sensors, ambient environmental condition sensors, and local sensors for collecting non-vibration data in the vicinity of machines in the environment. The plurality of sensors 10802 may include a data collection circuit 10808 communicatively coupled to a data collector 10804 and configured to collect output data 10810 from the plurality of sensors 10802, and a machine learning data analysis circuit 10812 configured to receive the output data 10810 and derive a received output data pattern 10814 that predicts at least one of an outcome and a state. The state may correspond to an outcome associated with a machine in the environment, an expected outcome associated with a machine in the environment, an outcome associated with a process in the environment, or an expected outcome associated with a process in the environment. The system may be deployed on the data collector 10804 or distributed between the data collector 10804 and a remote infrastructure. The data collector 10804 may include the data collection circuit 10808. The ambient environmental condition or local sensor may include one or more of a noise sensor, a temperature sensor, a flow sensor, a pressure sensor, a chemical sensor, a vibration sensor, an acceleration sensor, an accelerometer, a pressure sensor, a force sensor, a position sensor, a location sensor, a speed sensor, a displacement sensor, a temperature sensor, a thermographic sensor, a heat flux sensor, a tachometer sensor, a motion sensor, a magnetic field sensor, an electric field sensor, a galvanic sensor, a current sensor, a tolerance sensor, a gas flow sensor, a non-gaseous fluid flow sensor, a thermal flow sensor, a particulate flow sensor, a level sensor, a proximity sensor, a toxic gas sensor, a chemical sensor, a CBRNE sensor, a pH sensor, a hygrometer, a moisture sensor, a concentration meter, an imaging sensor, a camera, an SSR, a triax probe, an ultrasonic sensor, a touch sensor, a microphone, a capacitance sensor, a strain gauge, an electromagnetic wave meter, etc.

In an embodiment, a monitoring system 10800 for collecting data in an industrial environment may include a data collection circuit 10808 configured to collect output data 10810 from a plurality of sensors 10802 selected from among vibration sensors, ambient environmental condition sensors, and local sensors for collecting non-vibration data in the vicinity of machines in the environment. The plurality of sensors 10802 are communicatively coupled to the data collection circuit 10808. The monitoring system 10800 includes a machine learning data analysis circuit 10812 configured to receive the output data 10810 and learn received output data patterns 10814 that predict at least one of an outcome and a state, the machine learning data analysis circuit 10812 being configured to determine whether the output data matches the learned received output data patterns. The machine learning data analysis circuit 10812 may be configured to learn the received output data patterns 10814 by being seeded with a model 10816. The model 10816 may be a physical model, an operational model, or a system model. The machine learning data analysis circuit 10812 may be configured to filter the received output data pattern 10814 based on the outcome or condition. The monitoring system 10700 maintains or modifies operational parameters or equipment based on the predicted outcome or condition. The data collection circuit 10808 collects more or fewer data points from one or more sensors of the plurality of sensors 10802 based on the learned received output data pattern 10814, the outcome, or the condition. The data collection circuit 10808 changes the data storage technique for the output data based on the learned received output data pattern 10814, the outcome, or the condition. The data collection device 10804 changes the data presentation mode or manner based on the learned received output data pattern 10814, the outcome, or the condition. The data collection circuit 10808 applies one or more filters (e.g., low-pass, high-pass, band-pass) to the output data. The data collection circuit 10808 adjusts weights/biases of the machine learning data analysis circuit 10812 in response to the learned received output data patterns 10814, etc. The monitoring system 10800 removes/reassigns unused equipment based on one or more of the learned received output data patterns 10814, results, or status. The machine learning data analysis circuit 10812 may include a neural network expert system. The machine learning data analysis circuit 10812 may be configured to learn received output data patterns 10814 indicative of progress/alignment with one or more goals/guidelines, where progress/alignment with each goal/guideline is determined by a different subset of the plurality of sensors 10802. The machine learning data analysis circuit 10812 may be configured to ream the received output data patterns 10814 indicative of unknown variables. The machine learning data analysis circuit 10812 may be configured to ream the received output data patterns 10814 indicative of preferred input sensors from among the available input sensors. The machine learning data analysis circuit 10812 may be located partially on the machine, partially on one or more of the data collection circuits 10808, partially on the network infrastructure, partially on the cloud, or any combination thereof. The output data 10810 from the vibration sensor forms a vibration fingerprint, which may include one or more of frequency, spectrum, velocity, peak location, wave peak shape, waveform shape, wave envelope shape, acceleration, phase information, and phase shift. The data collection circuit 10808 may apply rules regarding how many parameters of the vibration fingerprint to match or the standard deviation for a match to identify a match between the output data 10810 and the learned received output data pattern. Additionally, the status may be one of normal operation, maintenance required, failure, or impending failure. The monitoring system 10800 may take action based on the predicted outcome or condition, such as issuing an alert, shutting down equipment/components/lines, initiating maintenance/lubrication/adjustments, deploying a field technician based on the predicted outcome or condition, recommending vibration absorption/damping devices based on the predicted outcome or condition, modifying a process to utilize backup equipment/components based on the predicted outcome or condition, etc. The monitoring system 10800 may modify a process to preserve products/reactants, etc. based on the predicted outcome or condition. The monitoring system 10800 may generate or modify a maintenance schedule based on the predicted outcome or condition. The data acquisition circuit 10808 may include a data acquisition circuit 10808. The system may be deployed on the data acquisition circuit 10808 or may be distributed between the data acquisition circuit 10808 and remote infrastructure.

In an embodiment, a monitoring system 10800 for collecting data in an industrial environment may include a data collection circuit 10808 configured to collect output data 10810 from a plurality of sensors 10802 selected from among vibration sensors, ambient environmental condition sensors, and local sensors for collecting non-vibration data in the vicinity of machines in the environment, and the plurality of sensors 10802 communicatively coupled to the data collection circuit 10808. A machine learning data analysis circuit 10812 configured to receive the output data 10810 and learn received output data patterns 10814 that predict at least one of an outcome and a state, wherein the monitoring system 10800 is configured to determine whether the output data matches the learned received output data patterns and maintain or modify operating parameters or equipment based on the determination.

In an embodiment, a monitoring system 10800 for collecting data in an industrial environment may include a data collection circuit 10808 configured to collect output data 10810 from a plurality of sensors 10802 selected from vibration sensors, ambient environmental condition sensors, and local sensors for collecting non-vibration data near machines in the environment. The plurality of sensors 10802 are communicatively coupled to the data collection circuit 10808, and a machine learning data analysis circuit 10812 configured to receive the output data 10810 and learn received output data patterns 10814 that predict at least one of an outcome and a state, where the output data 10810 from the vibration sensors forms a vibration fingerprint. The vibration fingerprint may include one or more of frequency, spectrum, velocity, peak location, wave peak shape, waveform shape, wave envelope shape, acceleration, phase information, and phase shift. The data collection circuitry 10808 may apply rules regarding how many parameters of the vibration fingerprint to match or the standard deviation for a match to identify a match between the output data 10810 and the learned received output data pattern. The monitoring system 10800 may be configured to determine whether the output data matches the learned received output data pattern and maintain or modify operating parameters or equipment based on the determination.

In an embodiment, a monitoring system 10800 for collecting data in an industrial environment may include a data collection band circuit 10818 that identifies a subset of a plurality of sensors 10802 for processing output data, the subset of sensors being selected from among vibration sensors, ambient environmental condition sensors, and local sensors for collecting non-vibration data in proximity to machines in the environment, and the plurality of sensors 10802 communicatively coupled to the data collection band circuit 10818. The data collection circuit 10808 is configured to collect output data 10810 from the subset of the plurality of sensors 10802, and a machine learning data analysis circuit 10812 configured to receive the output data 10810 and learn received output data patterns 10814 that predict at least one of an outcome and a condition, wherein if the learned received output data patterns 10814 do not reliably predict the outcome or condition, the data collection band circuit 10818 alters a parameter of at least one of the plurality of sensors 10802. The controller 10806 identifies a new data collection band circuit 10818 based on one or more of the learned received output data patterns 10814 and the results or conditions. The machine learning data analysis circuit 10812 may be further configured to learn the received output data patterns 10814 that indicate preferred input data collection bands from among the available input data collection bands. The system may be deployed on the data collection circuit 10808 or may be distributed between the data collection circuit 10808 and a remote infrastructure.

In an embodiment, a monitoring system for collecting data in an industrial environment may include a data collection circuit 10808 configured to collect output data 10810 from a plurality of sensors 10802, the sensors selected from among vibration sensors, ambient environmental condition sensors, and local sensors for collecting non-vibration data in the vicinity of machines in the environment, the plurality of sensors 10802 being communicatively coupled to the data collection circuit 10808. The output data 10810 from the vibration sensors is in the form of vibration fingerprints, the data structure 10820 including the plurality of vibration fingerprints and associated results, and a machine learning data analysis circuit 10812 configured to receive the output data 10810 and generate a received output data pattern 10814 that predicts an outcome or condition based on processing of the vibration fingerprints. The machine learning data analysis circuit 10812 may be seeded with one of the plurality of vibration fingerprints from the data structure 10820. The data structure 10820 may be updated if the changed parameters result in a new vibration fingerprint or if the predicted outcome does not occur in the absence of mitigation. The data structure 10820 may be updated if the learned received output data pattern 10814 does not reliably predict the outcome or condition. The system may be deployed on the data collection circuit or distributed between the data collection circuit and remote infrastructure.

In an embodiment, a monitoring system 10800 for collecting data in an industrial environment may include a data collection circuit 10808 structured to collect output data 10810 from a plurality of sensors 10802 selected from among vibration sensors, ambient environmental condition sensors, and local sensors for collecting non-vibration data in the vicinity of machines in the environment, the plurality of sensors 10802 being communicatively coupled to the data collection circuit 10808. The output data 10810 from the plurality of sensors 10802 is in the form of noise patterns, and the monitoring system 10800 includes a data structure 10820 including the plurality of noise patterns and associated results, and a machine learning data analysis circuit 10812 structured to receive the output data 10810 and learn received output data patterns 10814 that predict an outcome or condition based on processing the noise patterns.

In an embodiment, a monitoring system for collecting data in an industrial environment may include a plurality of sensors selected from vibration sensors, ambient environmental condition sensors, and local sensors for collecting non-vibration data near machines in the environment, the plurality of sensors communicatively coupled to a data collector; data collection circuitry configured to collect output data from the plurality of sensors; and machine learning data analysis circuitry configured to receive the output data and derive a pattern in the received output data that predicts at least one of an outcome and a state. The state corresponds to an outcome, an expected outcome, an outcome related to a process, an outcome related to a machine in the environment, or the like. The system may be located at the data collector. The system may also be distributed between the data collector and a remote infrastructure. The environmental condition sensors may include a noise sensor, a temperature sensor, a flow sensor, a pressure sensor, a chemical sensor, a noise sensor, a temperature sensor, a flow sensor, a pressure sensor, a chemical sensor, a vibration sensor, an acceleration sensor, an accelerometer, a pressure sensor, a force sensor, a position sensor, a location sensor, a speed sensor, a displacement sensor, a temperature sensor, a thermography sensor, a heat flux sensor, a tachometer sensor, and a motion sensor. Local sensors may include magnetic field sensors, electric field sensors, galvanic sensors, current sensors, tolerance sensors, gas flow sensors, non-gaseous fluid flow sensors, thermal flow sensors, particulate flow sensors, level sensors, proximity sensors, toxic gas sensors, chemical sensors, CBRNE sensors, pH sensors, hygrometers, moisture sensors, concentration meters, image sensors, cameras, SSRs, triaxial probes, ultrasonic sensors, touch sensors, microphones, capacitance sensors, strain gauges, electromagnetic wave meters, etc. Local sensors may consist of one or more of vibration sensors, acceleration sensors, accelerometers, pressure sensors, force sensors, position sensors, location sensors, velocity sensors, displacement sensors, temperature sensors, thermography sensors, heat flux sensors, tachometer sensors, motion sensors, magnetic field sensors, electric field sensors, galvanic sensors, and current sensors. Flow sensors, gas flow sensors, non-gaseous fluid flow sensors, thermal flow sensors, particulate flow sensors, level sensors, proximity sensors, toxic gas sensors, chemical sensors, CBRNE sensors, pH sensors, hygrometers, moisture sensors, concentration meters, imaging sensors, cameras, SSRs, triax probes, ultrasonic sensors, touch sensors, microphones, capacitance sensors, strain gauges, electromotive force meters, etc.

In an embodiment, a monitoring system for collecting data in an industrial environment may include: a data collection circuit configured to collect output data from a plurality of sensors selected from among vibration sensors, ambient environmental condition sensors, and local sensors for collecting non-vibration data near machines in the environment, the plurality of sensors being communicatively coupled to the data collection circuit; and a machine learning data analysis circuit configured to receive the output data and train a received output data pattern that predicts at least one of an outcome and a state, the monitoring system being configured to determine whether the output data matches the trained received output data pattern. In an embodiment, the machine learning data analysis circuit may be configured to train the received output data pattern by seeding a model, such as when the model is a physical model, an operational model, or a system model. The machine learning data analysis circuit may also be configured to derive the received output data pattern based on an outcome or a state. The monitoring system may maintain or modify operational parameters or equipment based on the predicted outcome or state. The data collection circuit collects data points from one or more of the plurality of sensors based on the trained received output pattern, outcome, or state. The data collection circuitry may change the data storage technique for the output data based on the following: The data collection circuitry may change the data presentation mode or method based on the learned pattern, outcome, or condition of the received output data. The data collection circuitry may apply one or more filters (low-pass, high-pass, band-pass, etc.) to the output data. The data collection circuitry may adjust the weights/biases of the machine learning data analysis circuitry, for example, the adjustments may be in response to the learned received output data patterns. The monitoring system may remove or retask unused equipment based on one or more of the learned received output data patterns, outcomes, or conditions. The machine learning data analysis circuitry may include a neural network expert system. The machine learning data analysis circuitry may be configured to learn received output data patterns indicative of progress/alignment of one or more goals or guidelines, such as when progress or alignment of each goal or guideline is determined by a different subset of multiple sensors. The machine learning data analysis circuitry may be configured to ream received output data patterns indicative of unknown variables. The machine learning data analysis circuit may be configured to filter received output data patterns indicative of preferred input sensors among the available input sensors. The machine learning data analysis circuit may be partially located on the machine, on one or more data collectors, on the network infrastructure, on the cloud, or a combination thereof. The output data from the vibration sensor may form a vibration fingerprint, for example, where the vibration fingerprint includes one or more of frequency, spectrum, velocity, peak location, wave peak shape, waveform shape, wave envelope shape, acceleration, phase information, and phase shift. The data collection circuit may apply rules regarding how many parameters of the vibration fingerprint must match or the standard deviation for a match to identify a match between the output data and the learned received output data pattern. The status may also be normal operation, maintenance required, failure, or impending failure. The monitoring system may trigger an alert based on the predicted outcome or status. The monitoring system may shut down equipment, components, or lines based on the predicted outcome or status. The machine initiates maintenance, lubrication, or adjustments based on the predicted outcome or condition. The machine deploys on-site technicians based on the predicted outcome or condition. The machine can recommend vibration absorption or damping devices based on the predicted outcome or condition. The machine can modify processes to utilize backup equipment or parts based on the predicted outcome or condition. The monitoring system may modify the following: A process to preserve products or reactants based on the predicted outcome or condition. The monitoring system may generate or modify maintenance schedules based on the predicted outcome or condition. The system may be distributed between a data collector and remote infrastructure.

In an embodiment, a monitoring system for collecting data in an industrial environment may include: a data collection circuit configured to collect output data from a plurality of sensors selected from among vibration sensors, ambient environmental condition sensors, and local sensors for collecting non-vibration data in the vicinity of machines in the environment, the plurality of sensors being communicatively coupled to the data collection circuit; and a machine learning data analysis circuit configured to receive the output data and learn received output data patterns that predict at least one of an outcome and a state, the monitoring system being configured to determine whether the output data matches the learned received output data patterns and maintain or modify operating parameters or equipment based on the determination.

In embodiments, a monitoring system for collecting data in an industrial environment may include: a data collection circuit configured to collect output data from a plurality of sensors selected from among vibration sensors, ambient environmental condition sensors, and local sensors for collecting non-vibration data near machines in the environment, the plurality of sensors being communicatively coupled to the data collection circuit; and a machine learning data analysis circuit configured to receive the output data and derive a received output data pattern that predicts at least one of an outcome and a state, the output data from the vibration sensors forming a vibration fingerprint. In embodiments, the vibration fingerprint may include one or more of frequency, spectrum, velocity, peak location, wave peak shape, waveform shape, wave envelope shape, acceleration, phase information, and phase shift. The data collection circuit may apply rules regarding how many parameters of the vibration fingerprint to match or a standard deviation for a match to identify a match between the output data and the learned received output data pattern. The monitoring system may be configured to determine whether the output data matches the learned received output data pattern and maintain or modify operating parameters or equipment based on the determination.

In an embodiment, a monitoring system for collecting data in an industrial environment may include a data collection band circuit that identifies a subset of a plurality of sensors for processing output data, the sensors selected from among: a vibration sensor, an ambient environmental condition sensor, and a local sensor for collecting non-vibration data proximate a machine in the environment, the plurality of sensors communicatively coupled to the data collection band circuit; a data collection circuit configured to collect output data from the subset of the plurality of sensors; and a machine learning data analysis circuit configured to receive the output data and learn received output data patterns that predict at least one of an outcome and a condition, wherein the data collection band circuit alters a parameter of at least one of the plurality of sensors if the learned received output data patterns do not reliably predict the outcome or condition. In an embodiment, the controller may identify a new data collection band circuit based on the learned received output data patterns and one or more of the outcome or condition. The machine learning data analysis circuit may further be configured to learn received output data patterns that indicate a preferred input data collection band from among available input data collection bands. The system may be distributed between the data collection circuit and remote infrastructure.

In an embodiment, a monitoring system for collecting data in an industrial environment may include a data collection circuit configured to collect output data from a plurality of sensors, the sensors selected from among vibration sensors, ambient environmental condition sensors, and local sensors for collecting non-vibration data in the vicinity of machines in the environment, communicatively coupled to the data collection circuit, the output data from the vibration sensors being in the form of vibration fingerprints. The system may also include a data structure including the plurality of vibration fingerprints and associated results, and a machine learning data analysis circuit configured to receive the output data and derive a received output data pattern that predicts an outcome or condition based on processing of the vibration fingerprints. The machine learning data analysis circuit may seed one of the plurality of vibration fingerprints from the data structure. The data structure may be updated if changed parameters result in a new vibration fingerprint or if a predicted outcome does not occur in the absence of mitigation measures. The data structure may be updated if the learned received output data pattern does not reliably predict an outcome or condition. The system may be distributed between the data collection circuit and remote infrastructure.

In an embodiment, a monitoring system for collecting data in an industrial environment may include a data collection circuit configured to collect output data from a plurality of sensors selected from among vibration sensors, ambient environmental condition sensors, and local sensors for collecting non-vibration data in the vicinity of machines in the environment; a plurality of sensors communicatively coupled to the data collection circuit, the output data from the plurality of sensors being in the form of noise patterns; a data structure including the plurality of noise patterns and associated results; and a machine learning data analysis circuit configured to receive the output data and refine the received output data patterns to predict an outcome or condition based on processing the noise patterns.

An exemplary system for data collection in an industrial environment includes an industrial system having a number of components and a number of sensors, each of the sensors operably coupled to at least one of the components. The exemplary system further includes a sensor communication circuit that interprets the number of sensor data values in response to a set of sensed parameters, a pattern recognition circuit that determines a recognized pattern value in response to at least a portion of the sensor data values, and a sensor learning circuit that updates the set of sensed parameters in response to the recognized pattern value. The exemplary sensor communication circuit further adjusts the interpretation of the sensor data values in response to the updated set of sensed parameters.

Certain additional aspects of the exemplary system are described below, any one or more of which may be present in particular embodiments. The exemplary system includes the sensed parameters being a fused number of sensors, and the recognized pattern value further including a secondary value including a value determined corresponding to the fused number of sensors. The exemplary system further includes the pattern recognition circuitry and the sensor learning circuitry iteratively performing determining the recognized pattern value and updating the sensed parameters to improve the sensing performance value. The exemplary system further includes the sensing performance value including a determination of one or more of: signal-to-noise performance for detecting a value of interest in the industrial system; network utilization of sensors in the industrial system; effective sensing resolution for the value of interest in the industrial system; a power consumption value of a sensing system in the industrial system (the sensing system including the sensors); computational efficiency for determining the secondary value; accuracy and/or precision of the secondary value; redundancy capacity for determining the secondary value; and/or a lead-time value for determining the secondary value. Exemplary, non-limiting computational efficiency values include one or more determinations of the following: processor operation for determining the secondary value; Memory utilization for determining the secondary value, number of sensor inputs from the number of sensors for determining the secondary value, and/or long-term storage of supporting data to support the secondary value.

Exemplary systems include one or more or all of the sensors as analog sensors and/or remote sensors. Exemplary systems include those in which the secondary values are values such as virtual sensor output values, process prediction values, process state values, component prediction values, component state values, and/or model output values that have as input sensor data values from the fused number of sensors. Exemplary systems include those in which the fused number of sensors are one or more of the following sensor combinations: a vibration sensor and a temperature sensor, a vibration sensor and a pressure sensor, a vibration sensor and an electric field sensor, a vibration sensor and a heat flux sensor, a vibration sensor and a galvanic sensor, and/or a vibration sensor and a magnetic sensor.

The exemplary sensor learning circuit further updates the sensed parameter group by performing operations such as: updating a sensor selection for the sensed parameter group; updating a sensor sampling rate for at least one sensor from the sensed parameter group; updating a sensor resolution for at least one sensor from the sensed parameter group; updating a stored value corresponding to at least one sensor from the sensed parameter group; updating a priority corresponding to at least one sensor from the sensed parameter group; and/or updating at least one of a sampling rate, a sampling order, a sampling phase, and/or a network path configuration corresponding to at least one sensor from the sensed parameter group. The exemplary pattern recognition circuit further determines a recognized pattern value by performing operations such as: determining a signal validity of at least one sensor in the sensed parameter group and the updated sensed parameter group to a value of interest; determining a sensitivity of at least one sensor in the sensed parameter group and the updated sensed parameter group to a value of interest; and determining a predicted confidence of at least one sensor in the sensed parameter group and the updated sensed parameter group to a value of interest. Determining a predicted delay time for at least one sensor in the sensed parameter group and the updated sensed parameter group for the value of interest; determining a predicted accuracy for at least one sensor in the sensed parameter group and the updated sensed parameter group for the value of interest; determining a predicted accuracy for at least one sensor in the sensed parameter group and the updated sensed parameter group for the value of interest. Updating the recognized pattern value in response to external feedback. Exemplary, non-limiting values of interest include virtual sensor output values, process prediction values, process state values, component prediction values, component state values, and/or model output values that use fused sensor data values from multiple sensors as input.

The exemplary pattern recognition circuitry further accesses cloud-based data including a second number of sensor data values, the second number of sensor data values corresponding to at least one offset industry system. The exemplary sensor learning circuitry further accesses cloud-based data including a second set of updated sensor parameters corresponding to the at least one offset industry system.

An exemplary procedure for collecting data in an industrial environment includes operations of providing a number of sensors to an industrial system including a number of components, each of the number of sensors operably coupled to at least one of the number of components, and interpreting a number of sensor data values in response to a sensed parameter group, the sensed parameter group including a fused sensor count from the number of sensors; determining a recognized pattern value including a secondary value determined in response to the number of sensor data values; updating the sensed parameter group in response to the recognized pattern value; and adjusting an interpretation of the number of sensor data values in response to the updated sensed parameter group.

Certain further aspects of the exemplary procedure are described below, any one or more of which may be included in particular embodiments. The exemplary procedure includes iteratively performing determining a recognized pattern value and updating a set of sensed parameters to improve a sensed performance value, where determining the sensed performance value includes at least one operation for determining a value, such as determining: signal-to-noise performance for detecting a value of interest in an industrial system; network utilization of multiple sensors in an industrial system; effective detection resolution for the value of interest in an industrial system; power consumption value of a detection system in an industrial system (the detection system includes multiple sensors); computational efficiency for determining a secondary value; precision and/or accuracy of the secondary value; redundancy capacity for determining the secondary value; and/or lead time value for determining the secondary value.

An exemplary procedure includes updating a sensed parameter group by performing at least one of the following operations: updating a sensor selection for the sensored parameter group, updating a sensor sampling rate for at least one sensor in the sensored parameter group, updating a sensor resolution for at least one sensor in the sensored parameter group, updating a stored value corresponding to at least one sensor in the sensored parameter group, updating a priority corresponding to at least one sensor in the sensored parameter group, and/or updating at least one of a sampling rate, a sampling order, a sampling phase, and a network path configuration corresponding to at least one sensor in the sensored parameter group. An exemplary procedure includes determining a recognized pattern value by performing at least one of the following operations: determining a signal validity of at least one sensor in the sensed parameter group and the updated sensed parameter group to a value of interest; determining a sensitivity of at least one sensor in the sensed parameter group and the updated sensed parameter group to a value of interest; determining a predicted confidence of at least one sensor in the sensed parameter group and the updated sensed parameter group to a value of interest. Determining a predicted delay time for at least one sensor of the set of sensing parameters for the value of interest and the updated set of sensing parameters; determining a predicted accuracy for at least one sensor of the set of sensing parameters for the value of interest and the updated set of sensing parameters; determining a predicted accuracy for at least one sensor of the set of sensing parameters for the value of interest and the updated set of sensing parameters; and/or updating the recognized pattern value in response to external feedback.

The term "industrial system" (and similar terms) as used herein should be understood broadly. Without being limited to other aspects or descriptions of the present disclosure, an industrial system includes any large-scale process system, mechanical system, chemical system, assembly line, oil and gas system (including, but not limited to, production, transportation, exploration, remote operation, marine operation, and/or refining), mining system (including, but not limited to, production, exploration, transportation, remote operation, and/or underground operation), rail system (yards, trains, shipping, etc.), construction, power generation, aerospace, agriculture, food processing, and/or energy generation. Certain components may not be considered industrial individually, but may be considered industrial in an integrated system. For example, a single fan, motor, and/or engine may not be an industrial system, but may be part of a larger system and/or integrated with many other similar components, be considered an industrial system and/or part of an industrial system. For example, a large data server farm may be considered an industrial system for certain sensing operations, such as temperature detection, vibration, etc., but not for other sensing operations, such as gas composition. Furthermore, in some embodiments, other similar-looking systems may be distinguished in determining whether and/or what type of industrial system such a system is. For example, one data server farm may not have a process stream flow rate that is critical to its operation at one time, while another data server farm may have a process stream flow rate that is critical to its operation (e.g., a cooling water flow); accordingly, one data farm server may be an industrial system for data collection and/or sensing improvement processes or systems, while another data farm server may not. Thus, the benefits of the present disclosure may be applicable to a wide variety of systems, and any such system may be considered an industrial system herein, while in certain embodiments, a given system may not be considered an industrial system herein. With the benefit of the disclosure herein and knowledge of the contemplated systems typically available to that person, one of ordinary skill in the art can readily determine which aspects of the present disclosure will benefit a particular system and how to combine the processes and systems of the present disclosure to enhance the operation of the contemplated system. Particular considerations for one skilled in the art when determining whether a contemplated system is an industrial system and/or whether aspects of the present disclosure can benefit or enhance the contemplated system include, but are not limited to: the accessibility of portions of the system to location detection devices, the sensitivity of the system to capital costs (e.g., initial installation) and operational costs (e.g., process optimization, reduced power usage), the transmission environment of the system (e.g., broadband internet availability, satellite broadcast availability, etc.). The transmission environment of the system (e.g., availability of broadband internet, satellite relay, wireless cellular access, electromagnetic environment of the system, weather, temperature, environmental conditions of the system, availability of suitable locations for laying electrical wires, network lines, etc., existence and/or availability of suitable locations for network infrastructure, router positioning, wireless repeaters, etc.), availability of trained personnel to interact with computing devices, desired spatial, time, and/or frequency resolution of sensed parameters in the system, system or process characteristics (e.g., process optimization, power usage reduction), system operation turndown ratio (e.g., difference between high load and low load, difference between high flow rate and low flow rate, difference between high temperature operation and low temperature operation), operating costs, etc. These considerations may include factors such as the turndown ratio at the system (e.g., the impact of labor costs over time (day, season, etc.), the impact of variations in power consumption costs over time, throughput, etc.), the system's sensitivity to failures, downtime, etc., the expected remoteness of the system (e.g., transportation costs, time delays, etc.), and/or the extent to which the system undergoes qualitative changes over its operational cycle (e.g., the system performs multiple different processes requiring a sensing environment that changes over time, transportation costs, time delays, etc.), and/or the extent to which the system undergoes qualitative changes over its operational cycle (e.g., the system performs multiple different processes requiring a sensing environment that changes over time, the nature of the time cycle and changes, such as cyclical, event-driven, or generally available lead time). While specific examples of industrial systems and considerations are described herein for illustrative purposes, any system having the benefit of this disclosure, and any considerations understood by one of ordinary skill in the art having the benefit of this disclosure, are specifically contemplated within the scope of this disclosure.

As used herein, the term sensor (and similar terms) should be understood broadly. Without being limited to other aspects or descriptions of this disclosure, a sensor includes any device configured to provide a sensed value representative of a physical value in a system (e.g., temperature, force, pressure) or a conceptual value in a system that has at least an ancillary relationship to a physical value (e.g., work, state of charge, frequency, phase, etc.).

Exemplary, non-limiting sensors include vibration, acceleration, noise, pressure, force, position, velocity, displacement, temperature, heat flux, speed, rotational speed (e.g., tachometer), motion, accelerometer, magnetic field, electric field, galvanic, current, flow (gas, fluid, heat, particulate, particle, etc.). accelerometer, magnetic field, electric field, galvanic, current, flow (gas, fluid, heat, particulate, particle, etc.), level, proximity, gas composition, fluid composition, toxicity, corrosivity, acidity, pH, humidity, hygrometer readings, moisture, density (bulk or ratio), ultrasonic, imaging, analog, and/or digital sensors. The list of sensed values is non-limiting and examples, and while the benefits of the present disclosure in many applications can be realized regardless of sensor type, in other applications the benefits of the present disclosure may depend on sensor type.

The sensor type and detection mechanism may be any type of sensor understood in the art. Without limitation, accelerometers may be of any type and scaling, such as 500 mV/g (1 g = 9.8 m/s²), 100 mV, 1 V/g, 5 V/g, 10 V/g, or 10 MV/g, and may also support any frequency. Scaling and range may conflict with acceleration sensors and all sensor types (e.g., in fixed-bit or low-bit A/D systems). Non-limiting examples of accelerometers include piezoelectric elements, high-resolution, high-sampling-rate position-sensing elements (e.g., laser-based elements), and/or detection of other parameters (e.g., strain, force, noise) that can be correlated to acceleration and/or vibration. Exemplary, non-limiting proximity probes include electro-magnetic devices (e.g., Hall effect, variable reluctance, etc.), sleeve/oil film devices, and/or determination of other parameters that can be correlated to proximity. An example of a vibration sensor is a triaxial probe, which can have a high frequency response (e.g., 100 MV/g scaling). Exemplary, non-limiting temperature sensors include thermistors, thermocouples, and/or optical temperature determination.

Sensors may additionally or alternatively provide processed values (e.g., debounced, filtered, and/or compensated) and/or raw values for downstream processing (e.g., on a data collector, controller, plant computer, and/or cloud-based data receiver). In certain embodiments, sensors may provide voltage, current, data files (e.g., images), or other raw data outputs, and/or may provide values representative of the intended sensed measurements (e.g., a temperature sensor may communicate a voltage or temperature value). Additionally, sensors may communicate via wireless communication, wired connection, optical connection, or other mechanisms. The listed examples of sensor types and/or communication parameters are illustrative and non-limiting.

Additionally or alternatively, in certain embodiments, a sensor may be a distributed physical device, e.g., two separate sensing elements may coordinate to provide a sensed value (e.g., a position sensing element and a mass sensing element may coordinate to provide an acceleration value). In some embodiments, a single physical device may form two or more sensors and/or part of two or more sensors. For example, a position sensing element may form a position sensor and a velocity sensor, with the same physical hardware providing sensed data for both determinations.

The terms smart sensor, smart device (and similar terms) used herein should be understood broadly. Without being limited to any other aspect or description of this disclosure, smart sensors include any sensors and aspects thereof described throughout this disclosure. A smart sensor includes incremental processing reflected in the sensed value communicated by the sensor, and may include at least basic sensor processing (e.g., debouncing, filtering, compensation, normalization, and/or output limiting), more complex compensation (e.g., more complex correction (e.g., correction of temperature values based on known effects of current environmental conditions on the sensed temperature value, removal of common mode or other noise, etc.), a sensing device that provides sensed values as a network communication, and/or a sensing device that aggregates multiple sensed values for communication (e.g., multiple sensors on a connected device provide values to a single smart sensor, which then aggregates the sensed values to a data collector, controller, or other device). The use of the term smart sensor is for descriptive purposes, and whether a sensor is a smart sensor depends on the context and the intended system and may be a relative description compared to other sensors in the intended system. Thus, a given sensor with the same functionality may be a smart sensor for purposes of one intended system and just a sensor for purposes of another intended system, and/or may be a smart sensor for a intended system during certain operating conditions and just a sensor for purposes of the same intended system during other operating conditions.

As used herein, sensor fusion, fused sensor, and similar terms should be understood broadly and without limitation to other aspects or descriptions of the present disclosure, unless the context indicates otherwise. Sensor fusion includes determining secondary data from sensor data, including determining secondary data from sensor data of multiple sensors, including multiplexing streams of data from multiple sensors, combining batches of data, etc. Secondary data includes decisions about system or operating conditions beyond those directly sensed. For example, data such as temperature, pressure, and mixture ratios can be analyzed to determine which parameters are effective for a desired outcome (e.g., reaction rate). Sensor fusion may also include sensor data from multiple sources and longitudinal data (e.g., data acquired over a period of time, the course of a process, and a range of components within a plant (e.g., tracking the number of parts assembled, virtual slugs of fluid passing through a pipeline, etc.)). Sensor fusion may be performed in real time (e.g., using sensor data to make multiple sensor fusion decisions as a process progresses), offline (e.g., performed on a controller, plant computer, and/or cloud-based computing device), and/or as a post-processing operation (e.g., utilizing historical data, data from multiple plants or processes, etc.). In certain embodiments, sensor fusion includes a machine pattern recognition operation—e.g., process results are provided to and/or determined by a machine, and the machine pattern recognition operation determines outcome-effective parameters from the detected sensor value space to determine which operating conditions are likely to be the cause of the result and/or an off-nominal consequence of the result (e.g., the process was more or less effective than nominal, failed, etc.). In certain embodiments, the result may be a quantitative result (e.g., 20% more product was produced than nominal operation) or a qualitative result (e.g., product quality is unacceptable, component X of the intended system failed during the process, component X of the intended system required a maintenance or service event, etc.).

In certain embodiments, the sensor fusion operation is iterative or recursive; e.g., an estimated set of result-effective parameters is updated after a sensor fusion operation, and a subsequent sensor fusion operation is performed on the same or a different data set with the updated set of result-effective parameters. In certain embodiments, the subsequent sensor fusion operation includes adjustments to the sensing scheme—e.g., higher resolution detection (e.g., in the time, space, and/or frequency domains), larger data sets (and resulting computing and/or network resource commitments), changes to sensor capabilities and/or settings (e.g., changes to A/D scaling, range, resolution, etc.; changes to more capable sensors and/or more capable data collectors, etc.)—performed for the subsequent sensor fusion operation. In certain embodiments, the sensor fusion operation indicates improvements to the intended system (e.g., yield, quality, and/or purity, etc.) that justify the expenditure of additional resources to improve the sensing scheme. In certain embodiments, sensor fusion operations provide improvements to the sensing scheme without incremental cost, for example, by narrowing the number of resulting effective parameters, thereby freeing up system resources to provide higher resolution, sampling rates, etc., from hardware already present in the contemplated system. In certain embodiments, iterative and/or recursive sensor fusion is performed on the same data set, subsequent data sets, and/or past data sets. For example, high-resolution data may already exist in the system, and a first sensor fusion operation is performed on lower-resolution data (e.g., sampled from the high-resolution data set) so that the sensor fusion processing operation can be completed within a desired time frame, processor, memory, and/or network utilization, and/or so that a large number of variables can be checked as potential result-effective parameters. In further examples, in response to a belief that an improvement exists, a narrowing of potential result-effective variables, and/or a determination that higher-resolution data is needed to determine result-effective parameters and/or effective values for such parameters, more samples from the high-resolution data set may be utilized in subsequent sensor fusion operations.

The described operations and aspects related to sensor fusion are non-limiting examples, and one of ordinary skill in the art, with the benefit of the disclosure herein and generally available information about the contemplated systems, will be readily able to design systems that utilize and/or benefit from sensor fusion operations. Specific considerations for systems that utilize and/or benefit from sensor fusion operations include, but are not limited to, the number of components in the system, the cost of the components in the system, the cost of system maintenance and/or downtime, the value of the system improvements (e.g., production volume, quality, yield, etc.), the existence, likelihood, and/or consequences of undesirable system outcomes (e.g., by-products, heat and/or luminous phenomena, environmental benefits or consequences, hazards present in the system), the cost of providing multiple sensors for the system, the complexity between system inputs and system outputs, and the availability and cost of computing resources (e.g., processing, memory, and/or communications throughput). Whether offset systems exist (including whether data from offset systems are available and whether combining data from offset systems can produce a statistically improved data set compared to systems considered alone) and/or the cost of upgrading, improving, or modifying the sensing scheme of the contemplated system. The described considerations of contemplated systems that may benefit from or utilize sensor fusion operations are non-limiting examples.

Certain systems, processes, operations, and/or components are referred to in this disclosure as "offset systems" or the like. An offset system is a system that is different from the contemplated system but has a relationship to the contemplated system. For example, a contemplated refinery may have an "offset refinery," which may be a refinery operated by a competitor, a refinery operated by the same operator as the contemplated refinery, and/or a historically operated refinery that no longer exists. An offset refinery may have some relationship to the contemplated refinery, such as utilizing similar reactions, process flows, production volumes, feedstocks, waste materials, etc. A system that is an offset system for one purpose may not be an offset system for another purpose. For example, a manufacturing process utilizing conveyor belts and similar motors may be an offset process for the contemplated manufacturing process for purposes such as tracking product movement, understanding motor operation and failure modes, etc., but may not be an offset process for product quality if the manufactured product has different quality result parameters. Any industrial system contemplated herein may have an offset system for a specific purpose. One of ordinary skill in the art, with the benefit of this disclosure and commonly available information about the contemplated system, can readily determine what is disclosed by an offset system or offset aspects of a system.

Any one or more of the terms computer, computing device, processor, circuit, and/or server may include any type of computer that can access instructions communicably stored, such as on a non-transitory computer-readable medium, that, when executed, performs the operations of the systems or methods described herein. In some embodiments, such instructions themselves constitute a computer, computing device, processor, circuit, and/or server. Additionally or alternatively, a computer, computing device, processor, circuit, and/or server may be a discrete hardware device, one or more computing resources distributed across a hardware device, and/or may include aspects such as logic circuits, embedded circuits, sensors, actuators, input and/or output devices, network and/or communication resources, any type of memory resource, any type of processing resource, and/or hardware devices configured to respond to determined conditions to functionally perform one or more operations of the systems and methods described herein.

Certain operations described herein involve interpreting, receiving, and/or determining one or more values, parameters, inputs, data, or other information. Operations involving interpreting, receiving, and/or determining any value, parameter, input, data, and/or other information include, but are not limited to, receiving data via user input, receiving data over any type of network, reading a data value from a memory location in communication with the receiving device, utilizing a default value as the received data value, estimating, calculating, or deriving a data value based on other information available to the receiving device, and/or updating any of these in response to a later received data value. In certain embodiments, as part of receiving a data value, the data value may be received by a first operation and later updated by a second operation. For example, a first operation for interpreting, receiving, and/or determining a data value may be performed when communication is down, intermittent, or interrupted, and an updated operation for interpreting, receiving, and/or determining a data value may be performed when communication is restored.

Particular logical groupings of operations herein, such as methods or procedures of the present disclosure, are provided to explain aspects of the present disclosure. The operations described herein are generally described and/or depicted, and operations may be combined, divided, reordered, added, or deleted in a manner consistent with the disclosure herein. While the context of the description of one or more operations may require an order of one or more operations and/or may explicitly disclose an order of one or more operations, the order of operations should be understood broadly, and any equivalent grouping of operations that provides an equivalent result of the operations is specifically contemplated herein. For example, if a value is used in an operation step, determination of the value may be required prior to that operation step in certain contexts (e.g., when a time delay of data for the operation to achieve a certain effect is important), but may not be required prior to that operation step in other contexts (e.g., when use of a value from a previous execution cycle of the operation is sufficient for those purposes). Thus, in certain embodiments, the ordering of operations and grouping of operations as described are expressly contemplated herein, and in certain embodiments, reordering, subdivision, and/or different grouping of operations are expressly contemplated herein.

With reference to FIG. 104, an exemplary system 10902 for data collection in an industrial environment includes an industrial system 10904 having a number of components 10906 and a number of sensors 10908, each of the sensors 10908 operatively coupled to at least one of the components 10906. The selection, distribution, type, and communication settings of the sensors depend on the application and/or context of the system 10902.

The example system 10902 further includes a sensor communication circuit 10920 (see FIG. 105) that interprets multiple sensor data values 10948 in response to a set of sensed parameters 10928. The set of sensed parameters 10928 includes a description of which sensors 10908 were sampled at what time, including at least selected ones of the following: sampling frequency, process stage at which the particular sensor is providing a value of interest, etc. The example system includes the set of sensed parameters 10928 being a fusion of a number of sensors 10926 that may encompass detection of operating conditions of the system that affect a desired output, such as production output, quality, efficiency, profitability, purity, maintenance or service prediction for a component in the system, failure mode prediction, etc. In a further embodiment, the recognized pattern value 10930 further includes a secondary value 10932 that includes a value determined in response to the set of fused sensors 10926.

In certain embodiments, the sensor data values 10948 are provided to a data collector 10910, which may be in communication with multiple sensors 10908 and/or may be in communication with a controller 10914. In certain embodiments, a plant computer 10912 is additionally or alternatively present. In the illustrated system, the controller 10914 is configured to functionally perform the operations of the sensor communication circuitry 10920, the pattern recognition circuitry 10922, and/or the sensor learning circuitry 10924, and is depicted as a separate device for clarity of illustration. Aspects of the controller 10914 may reside on the sensor 10908, the data controller 10910, the plant computer 10912, and/or the cloud computing device 10916. In certain embodiments, all aspects of the controller 10914 may reside on separate devices depicted in the system 10902. The plant computer 10912 represents local computing resources, such as, for example, processing, memory, and/or network resources, and may be present or in communication with the industrial system 10904. In particular embodiments, the cloud computing device 10916 represents computing resources available externally to the industrial system 10904, for example, via a private network, an intranet, cellular communications, satellite communications, and/or the Internet. In particular embodiments, the data controller 10910 may be a computing device, smart sensor, MUX box, or other data collection device that can receive data from multiple sensors, pass data through, and/or store data for later transmission. An example data controller 10910 may have no storage and/or limited storage, selectively passing sensor data through, such that a subset of sensor data is communicated at a given time, depending on the data controller 10910, associated network bandwidth considerations, and/or environmental constraints. In certain embodiments, one or more sensors and/or computing devices in the system 10902 may be selectively utilized as a portable device—e.g., a plant operator walking through the industrial system may have a smartphone—to control the system 10902, the data controller 10910, the sensors 10908, etc.—for example, to improve communication throughput or sensor resolution, and/or as the primary method for communicating sensor data values 10948 to the controller 10914.

The example system 10902 further includes a pattern recognition circuit 10922 that determines a recognized pattern value 10930 in response to at least a portion of the sensor data value 10948.

The example system 10902 further includes a sensor learning circuit 10924 that updates the sensed parameters 10928 in response to the recognized pattern values 10930. The example sensor communication circuit 10920 further adjusts the interpretation of the sensor data values 10948 in response to the updated sensed parameters 10928.

The exemplary system 10902 further includes the pattern recognition circuit 10922 and the sensor learning circuit 10924 iteratively determining the recognized pattern value 10930 and updating the sensed parameter set 10928 to improve the sensed performance value 10934. For example, the pattern recognition circuit 10922 may add sensors, remove sensors, and/or change sensor settings to modify the sensed parameter set 10928 based on sensors that appear to be valid or invalid in predicting the recognized pattern value 10930, and the sensor learning circuit 10924 may direct continuous changes (e.g., while improvement is still occurring), increased or decreased rates of change (e.g., to converge more quickly to the improved sensed parameter set 10928), and/or randomized changes to the sensed parameter set 10928 (e.g., to ensure all potentially valid sensors are checked and/or to avoid converging to a local optimum).

Exemplary, non-limiting options for the sensing performance value 10934 include signal-to-noise performance for detecting a value of interest in an industrial system (e.g., a determination that the predicted signal for the value is high relative to the noise factors of one or more sensors of the sensed parameter set 10928 and/or the entire sensed parameter set 10928), network utilization of sensors in the industrial system (e.g., the sensor learning circuit 10924 may be as effective as or approximately as effective as another sensored parameter set 10928, but may value the sensored parameter set 10928 relatively higher when network utilization is low), effective sensing resolution for the value of interest in the industrial system (e.g., the sensor learning circuit 10924 may value the sensored parameter set 10928 relatively higher when it provides a more responsive prediction of the output value to smaller changes in the input value), and power consumption values of a sensing system in the industrial system, wherein the sensing system includes: The secondary values may be determined based on the sensor (e.g., the sensor learning circuitry 10924 may value a sensed parameter group 10928 relatively higher where it has the same or nearly the same effect as another sensed parameter group 10928, but at a lower power consumption), computational efficiency for determining the secondary value ... in determining the secondary value 10932), or computational efficiency for determining the secondary value (e.g., the sensor learning circuitry 10924 may value a sensed parameter group 10928 relatively higher where it has the same or nearly the same effect as another sensed parameter group 10928, but at a lower power consumption). the sensor learning circuit 10924 may score the set of sensed parameters 10928 relatively high if it provides a high accuracy and/or high precision determination of the secondary value 10932; redundancy capacity for determining the secondary value (e.g., the sensor learning circuit 10924 may score the set of sensed parameters 10928 relatively high if it provides a high accuracy and/or high precision determination of the secondary value 10932); and/or a sensed parameter set 10928 may be scored relatively higher if it provides improved or sufficient lead time in determining the secondary value 10932, such as to aid in avoiding overheating, ruining an entire production run, determining whether a component has sufficient useful life to complete a production run, etc. Exemplary, non-limiting computational efficiency values include one or more of: processor operations for determining the secondary value 10932; memory utilization for determining the secondary value 10932; number of sensor inputs from multiple sensors for determining the secondary value 10932; and/or supporting memory, such as long-term storage or buffers, to support the secondary value 10932.

An example system includes one or more, or all, of the sensors 10908 as analog sensors and/or remote sensors. An example system includes the secondary values 10932 being values such as virtual sensor output values, process prediction values (e.g., production run success values, over-temperature values, over-pressure values, product quality values, etc.), process state values (e.g., temperature at a stage of the process, time and location within the process), component prediction values (e.g., operation change predictions such as component failure predictions, component maintenance or service predictions, component response predictions, component maintenance or service predictions, component response predictions), part condition values (remaining useful life or maintenance interval of a part), and/or model output values that use as input sensor data values 10948 from the fused number of sensors 10926. Exemplary systems include where the fused number of sensors 10926 is one or more combinations of sensors such as a vibration sensor and a temperature sensor, a vibration sensor and a pressure sensor, a vibration sensor and an electric field sensor, a vibration sensor and a heat flux sensor, a vibration sensor and a galvanic sensor, and/or a vibration sensor and a magnetic sensor.

The example sensor learning circuit 10924 further updates the sensed parameter group 10928 by performing operations such as: updating the sensor selection for the sensed parameter group 10928 (e.g., which sensors are sampled); updating the sensor sampling rate for at least one sensor from the sensed parameter group (e.g., how quickly a sensor provides information and/or how quickly information passes through the network); updating the sensor resolution for at least one sensor from the sensed parameter group (e.g., changing or requesting a change in sensor resolution, utilizing additional sensors to provide greater effective resolution, etc.); updating a stored value corresponding to at least one sensor from the sensed parameter group (e.g., updating a priority corresponding to at least one sensor from the sensed parameter group (e.g., moving a sensor to a higher priority if environmental conditions prevent data from being received from all planned sensors and/or reducing the time lag between sensed data creation and receipt by the sensor learning circuit 10924), and/or updating at least one of the sampling rate, sampling order, sampling phase, and/or network path configuration corresponding to at least one sensor from the sensed parameter group.

The exemplary pattern recognition circuit 10922 further determines the recognized pattern value 10930 by performing operations such as: determining the signal validity of at least one sensor of the sensed parameter group and the updated sensed parameter group for the value of interest 10950 (e.g., determining that the sensor value is a good predictor of the value of interest 10950); determining the sensitivity of at least one sensor of the sensed parameter group 10928 and the updated sensed parameter group 10928 for the value of interest 10950 (e.g., determining the relative sensitivity of the determined value of interest to small changes in operating conditions based on the selected sensed parameter group 10928); and determining the prediction confidence of at least one sensor of the sensed parameter group 10928 and the updated sensed parameter group 10928 for the value of interest 10950. determining a predicted delay time of at least one sensor of the sensed parameter group 10928 and the updated sensed parameter group 10928 with respect to the value of interest 10950; determining a prediction accuracy of at least one sensor of the sensed parameter group 10928 and the updated sensed parameter group 10928 with respect to the value of interest 10950; determining a classification accuracy of the at least one sensor of the sensed parameter group 10928 (e.g., determining the accuracy of classification of a pattern by a machine classifier based on the use of the at least one sensor); determining a prediction accuracy of the at least one sensor of the sensed parameter group 10928 with respect to the value of interest 10950; and/or updating the recognized pattern value 10930 in response to external feedback, which may be received as external data 10952 (e.g., if the outcome of a maintenance event, product quality determination, production outcome determination, etc. is known, detection of the recognized pattern value 10930 is thereby improved depending on the condition of the system before the known outcome occurs). ) Exemplary, non-limiting values of interest 10950 include virtual sensor output values, process prediction values, process state values, component prediction values, component state values, and/or model output values having fused sensor data values from multiple sensors as inputs.

The example pattern recognition circuit 10922 further accesses cloud-based data 10954 including a second number of sensor data values, the second number of sensor data values corresponding to at least one offset industry system. The example sensor learning circuit 10924 further accesses cloud-based data 10954 including a second set of updated sensor parameters corresponding to at least one offset industry system. Thus, the pattern recognition circuit 10922 can improve pattern recognition within the system based on increased statistical data available from the offset system. Additionally, or alternatively, the sensor learning circuit 10924 can improve more quickly and with greater reliability based on data from the offset system—including determining which sensors of the offset system have proven effective in predicting system outcomes.

Exemplary systems include industrial systems, including oil refineries. Exemplary oil refineries include one or more compressors for transporting fluids throughout the plant and/or for pressurizing fluid streams (e.g., for reflux in distillation columns). Additionally or alternatively, the exemplary oil refinery includes, for example, vacuum distillation, for fractionating hydrocarbons. Furthermore, the exemplary oil refinery includes various pipelines within the system for transporting fluids, bringing in feedstocks, delivering final products, etc. For example, measurements of the temperature of various fluids, the temperature and composition of individual contact trays within the column, feed and reflux measurements, and measurements of effluents and separated products. Distillation column design is complex, and optimal designs depend on factors such as boiler and compressor size, contact conditions within the column, and feed composition, all of which can vary widely. Furthermore, optimal locations for effective sensing of conditions within the piping can vary depending on fluid flow rates, environmental conditions (e.g., causing changes in heat transfer rates), the feedstocks utilized, and other factors. Additionally, wear and tear on boilers, compressors, and other operating equipment can change the system's response and functionality, making centralized optimization of where to place sensors and how to sample data less optimal as the system ages.

This is not necessarily because sensors are expensive, but because the data they provide is costly to transmit, store, and utilize. These costs can include operational costs, such as the cost of transmitting over a network and the number of input/output operations (and the time required to perform such operations). The example system involves providing numerous sensors throughout the system and determining which sensors are effective for controlling and optimizing the distillation process. Furthermore, changes in feedstock and environmental conditions can change the optimal sensor package for both optimization and control. This example system utilizes pattern recognition circuitry to determine which sensors are effective for controlling the desired distillation parameters, including sensor fusion operations (including group selection, multiplexing and combination selection, etc.), and to determine optimal values for temperature, flow rate, feed and reflux entry trays, and/or reflux rate. Furthermore, the sensor learning circuitry can rapidly converge, over time or by utilizing an offset refinery, to various sensor packages appropriate for numerous operating conditions. In the event of an unexpected operating condition (e.g., abnormal compressor operation), the sensor learning circuitry can transition the system to sensing and operating conditions appropriate for the unexpected operating condition. This flexible use of multiple sensors allows for flexible response to changing conditions without excessive functionality in transmitting, receiving, and storing sensor data. This improves the operability of the distillation column, allowing it to be optimized for multiple operating conditions. Furthermore, distillation column alarms based on the recognition of patterns indicative of non-standard behavior can be easily prepared to adjust or shut down the process before significant product quality loss or unsafe conditions occur. Examples of sensor fusion in refineries include combining vibration information with temperature, pressure, and composition (e.g., to determine compressor performance), temperature and pressure, temperature and composition, and composition and pressure (e.g., to determine feedstock variability, contact tray performance, and component failure).

An exemplary refinery system includes a storage tank and/or boiler feedwater. Exemplary system determinations include sensor fusion to determine storage tank failures and/or abnormal operation, such as temperature and pressure fusion and/or vibration determination with non-vibration determinations (e.g., detecting leaks, air in the system, and/or feed pump issues). A specific further example system determination includes sensor fusion to determine boiler feedwater malfunctions via sensor fusion including flow rate, pressure, temperature, and/or vibration. Any one or more of these parameters can be utilized to determine system leaks, failures, feed pump wear, or scaling, and reduce pump losses while maintaining system flow. Similarly, an exemplary industrial system includes a power generation system with a condensate and/or makeup water system, where sensor fusion provides sensed parameters and predictions of failures, maintenance, etc.

An exemplary industrial system includes an irrigation system for a field or field system. Irrigation systems are subject to large system variations (e.g., inlet pressure and/or water level, component wear and maintenance) as well as environmental variations (e.g., planted crop type and distribution, weather, soil moisture, humidity, seasonal solar variations, cloud cover, and/or wind variations). Furthermore, irrigation systems are often installed in remote locations where high-bandwidth network access, maintenance facilities, and even monitoring personnel are not readily available. The example system includes multiple sensors capable of detecting the status of the irrigation system, but not all sensors need to transmit or store data; this can be done continuously. Pattern recognition circuitry can easily determine the most critical sensor groups to effectively predict system conditions (e.g., irrigation cycle, positioning, etc.) that require a pattern or response. Sensor learning circuitry responsively shifts sensed parameter groups to variations that may occur in slow cycles (e.g., seasons, climate change, etc.) or fast cycles (e.g., equipment failure, weather conditions, step-change events such as planting and harvesting, etc.). Additionally, alerts to remote facilities can be easily prepared with the confidence that the correct sensor package is installed to determine abnormal conditions (e.g., impending pump failure or need for maintenance).

Examples of industrial systems include chemical and pharmaceutical plants. Chemical plants require specific operating conditions, flow rates, temperatures, etc., to maintain the proper temperature, concentration, mixture, etc. throughout the system. Many systems have numerous process steps, and abnormal or uncoordinated operation in one part of the process can result in yield loss, process failure, and a significant reduction in production capacity due to the need for (or inability to) coordinate the coordinated process. Therefore, to minimally define the system, a significant number of systems are required, and in certain embodiments, a prohibitive number of sensors are required to maintain sensing capabilities over a wide range of operating conditions, from a data transmission and storage perspective. Furthermore, as the system becomes more complex, even with a sufficient number of sensors, optimizing and tweaking the system's operation becomes difficult. In some embodiments, pattern recognition circuitry can determine a set of sensing parameters that provides a high-resolution understanding of the system without requiring every sensor to continuously store and transmit data. Furthermore, sensor fusion can be used to abstract desired outputs, such as "maximize yield" or "minimize undesired side reactions," without the operator needing to fully understand which sensors and system conditions are most effective in achieving the abstracted desired output. Exemplary components of chemical or pharmaceutical plants that can be controlled and predicted based on sensor fusion operations include agitators, pressure reactors, catalytic reactors, and/or thermal heating systems. Examples of sensor fusion operations for determining sensed parameter groups and adjusting pattern recognition circuits include, but are not limited to, combining vibration sensors with other sensor types, combining composition sensors with other sensor types, combining temperature sensors with other sensors, and determining flow rates. The optimal sensor fusion for a particular application can be converged on by sensor learning circuits and will vary depending on the type of component being predicted and the type of output desired by the operator. For example, agitators can detect vibration, as well as composition uniformity (e.g., high-resolution temperature sensing), and predict reaction rates in well-mixed systems. Catalytic reactors can detect temperature (based on reaction thermodynamics), composition (e.g., detection of expected reactants, direct detection of catalytic materials), flow rate (e.g., critical mechanical failure, volume loss of beads, etc.), and/or pressure (e.g., indicating or linked to changes in flow rate).

An exemplary industrial system includes a food processing system. An exemplary food processing system includes pressurized vessels, agitators, mixers, and/or thermal heating systems. Process control is critical to maintaining food safety, product quality, and product consistency. However, most input parameters to food processing systems are subject to high variability. For example, basic foods, as natural products, are inherently variable, varying in moisture content, protein content, and aesthetics. Furthermore, labor cost management, power cost management, supply water variability, and the like provide complex processes in which determining process control variables, sensing parameters to determine these, and optimizing sensing in response to process variability are challenging problems. Food processing systems are often cost-conscious, and capital costs (e.g., costs for robust network and computing systems for optimization) are not readily incurred. Furthermore, food processing systems may manufacture a wide variety of products using similar or identical production equipment, for example, to support an entire product line or due to seasonal variations. As such, sensors used in one process may not be compatible with another process. In this example system, a pattern recognition circuit determines a set of sensing parameters that provides a strong signal response in the target outcome, even when there is a large variation in system conditions. The pattern recognition circuit can provide a large number of sensing group parameter options that can be used for different process conditions without requiring extensive computing or data storage resources. Furthermore, a sensor learning circuit enables the sensing system to respond quickly to changes in process conditions. This includes updating the sensing group parameter options to pursue an abstract target output without the operator needing to understand which sensing parameters best support the output target. The most appropriate sensor fusion for a particular application can be converged by the sensor learning circuit but also depends on the type of component being predicted and the type of target output being pursued by the operator. For example, sensor fusion combining temperature and non-temperature determinations, vibration and non-vibration determinations, and heat map and rate of change and non-heat map determinations is suitable for control and prediction of pressurized vessels, agitators, mixers, and heating devices. An example system includes sensor fusion of vibration and non-vibration determinations to provide predictive information for mixers and/or agitators. We will introduce an example system that provides predictive information for pressurized vessels through sensor fusion of pressure, temperature, and non-pressure determinations.

With reference to FIG. 106 , an exemplary procedure 10936 for collecting data in an industrial environment includes operation 10938 of providing a number of sensors to an industrial system including a number of components, each of the number of sensors operatively coupled to at least one of the number of components. Procedure 10936 further includes operation 10940 of interpreting the number of sensor data values responsive to a set of sensed parameters, the set of sensed parameters including a fused sensor count from the number of sensors, operation 10942 of determining a recognized pattern value including a secondary value determined responsive to the number of sensor data values, operation 10944 of updating the set of sensed parameters responsive to the recognized pattern value, and operation 10946 of adjusting an interpretation of the number of sensor data values responsive to the updated set of sensed parameters.

Exemplary procedure 10936 includes iteratively determining recognized pattern values and updating sensed parameters to improve the sensed performance value (e.g., by repeating operations 10940 through 10944 periodically, at selected intervals, and/or in response to system changes). Exemplary procedure 10936 includes determining the sensed performance value by determining signal-to-noise performance for detecting a value of interest in the industrial system, network utilization of multiple sensors in the industrial system, effective sensing resolution for the value of interest in the industrial system, power consumption values of a sensing system in the industrial system, the sensing system including multiple sensors, computational efficiency for determining the secondary value, accuracy and/or precision of the secondary value, redundancy capacity for determining the secondary value, and/or lead time values for determining the secondary value.

Exemplary procedure 10936 includes operation 10944 of updating the sensed parameter group by performing at least one operation, such as: updating a sensor selection for the sensing parameter group, updating a sensor sampling rate for at least one sensor from the sensing parameter group, updating a sensor resolution for at least one sensor from the sensing parameter group, updating a stored value corresponding to at least one sensor from the sensing parameter group, updating a priority corresponding to at least one sensor from the sensing parameter group, and/or updating at least one of a sampling rate, a sampling order, a sampling phase, and a network path configuration corresponding to at least one sensor from the sensing parameter group. Exemplary procedure 10936 includes operation 10942 of determining a recognized pattern value by performing at least one operation, such as: determining a signal validity of at least one sensor in the sensed parameter group and the updated sensed parameter group to a value of interest, determining a sensitivity of at least one sensor in the sensed parameter group and the updated sensed parameter group to a value of interest, determining a predicted confidence of at least one sensor in the sensed parameter group and the updated sensed parameter group to a value of interest. Determining a predicted delay time for at least one sensor of the set of sensing parameters for the value of interest and the updated set of sensing parameters; determining a predicted accuracy for at least one sensor of the set of sensing parameters for the value of interest and the updated set of sensing parameters; determining a predicted accuracy for at least one sensor of the set of sensing parameters for the value of interest and the updated set of sensing parameters; and/or updating the recognized pattern value in response to external feedback.

(1) In an embodiment, a system for data collection in an industrial environment includes: a plurality of components; a plurality of sensors, each operably coupled to at least one of the plurality of components; a sensor communication circuit configured to interpret a plurality of sensor data values in response to a set of sensed parameters; a pattern recognition circuit configured to determine a recognized pattern value in response to at least a portion of the plurality of sensor data values; and a sensor learning circuit configured to update the set of sensed parameters in response to the recognized pattern value, wherein the sensor communication circuit is further configured to adjust the interpretation of the plurality of sensor data values in response to the updated set of sensed parameters. (2) The system described in (1), wherein the set of sensed parameters comprises a fused set of sensors, and the recognized pattern value further includes a secondary value comprising a value determined in response to the fused set of sensors. (3) The system described in (2), wherein the pattern recognition circuit and the sensor learning circuit are further configured to iteratively determine the recognized pattern value and update the set of sensed parameters to improve a sensing performance value. (4) The system of (3), wherein the sensing performance value includes at least one performance determination selected from the group consisting of S/N performance for detecting a value of interest in an industrial system, network utilization of a plurality of sensors in the industrial system, effective sensing resolution for the value of interest in the industrial system, and power consumption value of a sensing system in the industrial system, and the sensing system includes the plurality of sensors. (5) The system of (3), wherein the sensing performance value includes signal-to-noise performance for detecting a value of interest in the industrial system. (6) The system of (3), wherein the sensing performance value comprises network utilization of the plurality of sensors in the industrial system. (7) The system of (3), wherein the sensing performance value comprises effective sensing resolution for the value of interest in the industrial system. (8) The system of (3), wherein the sensing performance value comprises power consumption value of a sensing system in the industrial system, and the sensing system includes the plurality of sensors. (9) The system of (3), wherein the sensing performance value includes computational efficiency for determining the secondary value. (10) The system of (9), wherein the computational efficiency comprises at least one of processor operations for determining the secondary value, memory utilization for determining the secondary value, number of sensor inputs from the plurality of sensors for determining the secondary value, and long-term storage of supporting data for supporting the secondary value. (11) The system of (3), wherein the sensed performance value comprises one of precision and accuracy of the secondary value. (12) The system of (3), wherein the sensed performance value comprises redundancy capacity for determining the secondary value. (13) The system of (3), wherein the sensed performance value comprises a lead time value for determining a secondary value. (14) The system of (13), wherein the secondary value comprises an over-temperature value of a component. (15) The system of (13), wherein the secondary value comprises one of maintenance time of a component, failure time of a component, and useful life of a component. (16) The system of (13), wherein the secondary value is an off-nominal operating condition that affects the quality of a product produced by operation of the industrial system. (17) The system of (1), wherein the plurality of sensors includes at least one analog sensor. (18) The system of (1), wherein at least one of the sensors is a remote sensor. (19) The system of (2), wherein the secondary value comprises at least one value selected from the group consisting of a virtual sensor output value, a process prediction value, a process state value, a component prediction value, a component state value, and a model output value that has sensor data values from the fused plurality of sensors as input. (20) The system of (2), wherein the fused plurality of sensors further comprises at least one pairing of sensor types selected from the group consisting of a vibration sensor and a temperature sensor, a vibration sensor and a pressure sensor, a vibration sensor and an electric field sensor, a vibration sensor and a heat flux sensor, a vibration sensor and a galvanic sensor, and a vibration sensor and a magnetic sensor. 21. The system of claim 1, wherein the sensor learning circuitry is further configured to update the set of sensed parameters by performing at least one operation selected from the following operations: updating a sensor selection from the set of sensor parameters, updating a sensor sampling rate for at least one sensor from the set of sensor parameters, updating a sensor resolution for at least one sensor from the set of sensor parameters, updating a stored value corresponding to at least one sensor from the set of sensor parameters, updating a priority corresponding to at least one sensor from the set of sensor parameters, and updating at least one of a sampling rate, a sampling order, a sampling phase, and a network path configuration corresponding to at least one sensor from the set of sensor parameters. (22) The pattern recognition circuit is further configured to determine a recognized pattern value by performing at least one operation selected from the following operations: determining a signal validity of at least one sensor of the sensed parameter group and the updated sensed parameter group for a value of interest; determining a sensitivity of at least one sensor of the sensed parameter group and the updated sensed parameter group for a value of interest; determining a predicted confidence of at least one sensor of the sensed parameter group and the updated sensed parameter group for a value of interest; and determining a predicted confidence of at least one sensor of the recognized parameter group and the updated sensed parameter group for a value of interest; determining a predicted delay time of at least one sensor of the sensed parameter group and the updated sensed parameter group for a value of interest; determining a predicted accuracy of at least one sensor of the sensed parameter group and the updated sensed parameter group for a value of interest; determining a predicted accuracy of at least one sensor of the sensed parameter group and the updated sensed parameter group for a value of interest; and updating the value of the recognized pattern in response to external feedback. (23) The system of (22), wherein the value of interest includes at least one value selected from the group consisting of a virtual sensor output value, a process prediction value, a process state value, a component prediction value, a component state value, and a model output value having sensor data values from the fused plurality of sensors as input. (24) The system of (2), wherein the pattern recognition circuitry is further configured to access cloud-based data including a second plurality of sensor data values, the second plurality of sensor data values corresponding to at least one offset industrial system. (25) The system of (24), wherein the sensor learning circuitry is further configured to access cloud-based data including a second set of updated sensor parameters corresponding to the at least one offset industrial system. (26) A method comprising: providing a plurality of sensors to an industrial system including a plurality of components, each of the plurality of sensors operably coupled to at least one of the plurality of components; interpreting a plurality of sensor data values in response to a sensed parameter group, the sensed parameter group including a fused plurality of sensor data values from the plurality of sensors; determining a recognized pattern value including a secondary value determined in response to the plurality of sensor data values; updating the sensed parameter group in response to the recognized pattern value; and adjusting an interpretation of the plurality of sensor data values in response to the updated sensed parameter group. (27) The method of (26), further comprising iteratively performing the determining of the recognized pattern value and the updating of the sensed parameter group to improve a sensed performance value. (28) The method of (27), further comprising determining a sensed performance value in response to determining at least one of a signal-to-noise performance for detecting a value of interest in the industrial system and a network utilization rate of a plurality of sensors in the industrial system.

An effective sensing resolution for a value of interest in an industrial system; a power consumption value of a sensing system in the industrial system, the sensing system including a plurality of sensors; and a computational efficiency for determining a secondary value, the computational efficiency including at least one of processor operations for determining the secondary value, the number of sensor inputs from the plurality of sensors for determining the secondary value, and long-term storage of support data to support the secondary value. One of processor operations for determining the secondary value, memory utilization for determining the secondary value, the number of sensor inputs from the plurality of sensors for determining the secondary value, and long-term storage of support data to support the secondary value, precision and accuracy of the secondary value, redundancy capacity for determining the secondary value, and lead time value for determining the secondary value. (29) The method of (27), wherein updating the set of sensed parameters includes performing at least one operation selected from the following operations: updating a sensor selection of the sensored parameter group, updating a sensor sampling rate of at least one sensor from the sensored parameter group, updating a sensor resolution of at least one sensor from the sensored parameter group, updating a stored value corresponding to at least one sensor from the sensored parameter group, updating a priority corresponding to at least one sensor from the sensored parameter group, and updating at least one of a sampling rate, a sampling order, a sampling phase, and a network path configuration corresponding to at least one sensor from the sensored parameter group. (30) The method of (27), wherein determining a recognized pattern value includes performing at least one operation selected from the following operations: determining signal validity of at least one sensor in the sensed parameter group and the updated sensed parameter group with respect to a value of interest; determining sensitivity of at least one sensor in the sensed parameter group and the updated sensed parameter group with respect to the value of interest; determining predicted reliability of at least one sensor in the sensed parameter group and the updated sensed parameter group with respect to the value of interest. determining a predicted delay time of at least one sensor of the sensed parameter group and the updated sensed parameter group relative to the value of interest, determining a predicted accuracy of at least one sensor of the sensed parameter group and the updated sensed parameter group relative to the value of interest, determining a predicted accuracy of at least one sensor of the sensed parameter group and the updated sensed parameter group relative to the value of interest, and updating a recognized pattern value in response to external feedback. (31) A system for data collection in an industrial environment, comprising: an industrial system including a plurality of components and a plurality of sensors, each sensor operably coupled to at least one of the plurality of components; and a sensor communication circuit configured to interpret a plurality of sensor data values in response to sensed parameters, the sensed parameters comprising fused sensor data. The system comprises a plurality of sensors, means for recognizing a pattern value in response to the sensed parameters, and means for updating the sensed parameters in response to the recognized pattern value. (32) The system of (31), further comprising means for iteratively updating the sensed parameters. (33) The system of (32), further comprising means for accessing external data and at least one of a second plurality of sensor data values corresponding to an offset industrial system, wherein the means for iteratively updating the set of sensed parameters is further responsive to the external data and at least one of the second plurality of sensor data values. (34) The system of (33), further comprising means for accessing a second set of sensed parameters corresponding to the offset industrial system, wherein the means for iteratively updating is further responsive to the second set of sensed parameters. (35) A system for data collection in an industrial environment, comprising: a plurality of components; a plurality of sensors, each sensor operatively coupled to at least one of the plurality of components; a sensor communication circuit configured to interpret a plurality of sensor data values in response to the sensed parameters; and a pattern recognition circuit configured to determine a recognized pattern value in response to at least a portion of the plurality of sensor data values, wherein the recognized pattern value comprises a secondary value consisting of values determined in response to at least a portion of the plurality of sensors. The system of claim 1, further comprising: a sensor learning circuit configured to update the sensed parameters in response to the recognized pattern value; and the sensor communications circuit further configured to adjust interpretation of the plurality of sensor data values in response to the updated sensed parameters, the pattern recognition circuit and the sensor learning circuit further configured to iteratively determine the recognized pattern value and update the sensed parameters to improve a sensed performance value, the sensed performance value comprising a signal-to-noise performance for detecting values of interest in the industrial system. (36) The system of claim 35, further comprising: a sensed parameter set comprising a fused plurality of sensors; and a secondary value determined in response to the fused plurality of sensors. (37) The system of claim 36, further comprising: a virtual sensor output value, a process prediction value, a process state value, a component prediction value, a component state value, and a model output value having sensor data values from the fused plurality of sensors as input. (38) A system for collecting data in an industrial environment, comprising: 39. The system of claim 37, wherein the sensed parameters comprise a fused set of sensors, and the secondary value comprises a value determined in response to the fused set of sensors. 39. The system of claim 37, wherein the sensed parameters comprise a fused set of sensors, and the secondary value comprises a value determined in response to the fused set of sensors. (40) The system according to (39), wherein the secondary value comprises at least one value selected from the group consisting of a virtual sensor output value, a process prediction value, a process state value, a component prediction value, a component state value, and a model output value having as input sensor data values from the fused plurality of sensors. (41) A system for data collection in an industrial environment, comprising: 42. The system of claim 41, wherein the sensed parameters comprise a fused set of sensors and the secondary value comprises a value determined in response to the fused set of sensors. (43) The system of (42), wherein the secondary value comprises at least one value selected from the group consisting of a virtual sensor output value, a process prediction value, a process state value, a component prediction value, a component state value, and a model output value having sensor data values from the fused plurality of sensors as input. (44) A system for data collection in an industrial environment, comprising: a plurality of components, a plurality of sensors, each operably coupled to at least one of the plurality of components, a sensor communication circuit configured to interpret a plurality of sensor data values in response to a set of sensed parameters, a pattern recognition circuit configured to determine a recognized pattern value in response to at least a portion of the plurality of sensor data values, the recognized pattern value comprising a secondary value determined in response to at least a portion of the plurality of sensors, and a sensor learning circuit configured to update the set of sensed parameters in response to the recognized pattern value. (45) The sensor communications circuit, wherein the sensor communications circuit is further configured to adjust interpretation of the plurality of sensor data values in response to updated sensed parameters, and the pattern recognition circuit and the sensor learning circuit are further configured to iteratively determine recognized pattern values and update the sensed parameters to improve a sensed performance value, the sensed performance value including a power consumption value of a sensing system in an industrial system, and the sensing system including a plurality of sensors. (45) The system of (44), wherein the sensed parameters include a fused plurality of sensors, and the secondary value includes a value determined in response to the fused plurality of sensors. (46) The system of (45), wherein the secondary value comprises at least one value selected from values consisting of a virtual sensor output value, a process prediction value, a process state value, a component prediction value, a component state value, and a model output value that has sensor data values from the fused plurality of sensors as input.

With reference to FIG. 107, an exemplary system 11000 for data collection in an industrial environment includes an industrial system 11002 having a number of components 11004 and a number of sensors 11006, each operably coupled to at least one of the number of components 11004. The selection, distribution, type, and communication settings of the sensors depend on the application and/or context of the system 11000.

The example system 11000 further includes a sensor communication circuit 11018 (see FIG. 108) that interprets multiple sensor data values 11034 in response to sensed parameters 11026. The sensed parameters 11026 include a description of which sensors 11006 are being sampled at what times, including at least a selected sampling frequency, the process stage at which a particular sensor may be providing a value of interest, etc. The example system includes the sensed parameters 11026 being multiple sensors provided for sensor fusion operations. In certain embodiments, the sensed parameters 11026 include a set of sensors encompassing detection of system operating conditions that predict outcomes, off-nominal operation, maintenance intervals, maintenance health states, and/or future state values for any aspect of interest to the process, component, sensor, and/or system 11000.

In certain embodiments, the sensor data values 11034 are provided to a data collector 11008, which may communicate with multiple sensors 11006 and/or with a controller 11012. In certain embodiments, a plant computer 11010 is additionally or alternatively present. In the illustrated system, the controller 11012 is configured to functionally perform the operations of the sensor communication circuitry 11018, the pattern recognition circuitry 11020, and/or the system characterization circuitry 11022, and is depicted as a separate device for clarity of illustration. Aspects of the controller 11012 may reside on the sensor 11006, the data collector 11008, the plant computer 11010, and/or the cloud computing device 11014. In certain embodiments, all aspects of the controller 11012 may reside on separate devices depicted in the system 11000. The plant computer 11010 represents local computing resources, such as processing, memory, and/or network resources, and may be present or in communication with the industrial system 11000. In certain embodiments, the cloud computing device 11014 represents computing resources available externally to the industrial system 11000, for example, via a private network, an intranet, cellular communications, satellite communications, and/or other network. The data collector may collect data via the Internet. In certain embodiments, the data collector 11008 may be a computing device, smart sensor, MUX box, or other data collection device that can receive data from multiple sensors, pass data through, and/or store data for later transmission. An example data collector 11008 may have no storage and/or limited storage, selectively pass sensor data through, and/or have a subset of sensor data communicated at a given time due to the data collector 11008, associated network bandwidth considerations, and/or environmental constraints. In certain embodiments, one or more sensors and/or computing devices in the system 11000 are portable devices; for example, a plant operator walking through the industrial system may have a smartphone, and the system 11000 may be selectively utilized as a data collector 11008, a sensor 11006, for example, to increase communication throughput, sensor resolution, and/or as the primary method for communicating sensor data values 11034 to the controller 11012.

The example system 11000 further includes a pattern recognition circuit 11020 that determines a recognized pattern value 11028 in response to at least a portion of the sensor data values 11034, and a system characterization circuit 11022 that provides a system characterization value 11030 of the industrial system in response to the recognized pattern value 11028. The system characterization value 11030 includes any value determined from the pattern recognition operations of the pattern recognition circuit 11020, including determining that a system state of interest exists, a component state of interest exists, an abstracted state of the system or component exists (e.g., product quality value, operational cost value, component health, wear, or maintenance value, component capacity value, and/or sensor saturation value), and/or is predicted to occur within a time frame of interest (e.g., calendar time, operational time, and/or process stage). Pattern recognition operations include determining operations that fit a previously known pattern, are similar to a previously known pattern, and/or are inferred from previously known pattern information (e.g., a previously known pattern may include a temperature response of a first component, and due to a known or inferred relationship between the components, it may be determined that the temperature of a second component exceeds a threshold based on pattern recognition of the first component combined with the known or inferred relationship).

Non-limiting descriptions of numerous examples of system characterization values 11030 are provided below. Exemplary system characterization values 11030 include predicted results of a process associated with an industrial system—for example, a statement regarding product quality, a statement regarding product quantity, a statement regarding product variability (e.g., the expected variability of a product parameter predicted according to the operating conditions of the system), a statement regarding product yield, a result regarding the net present value (NPV) of the process, the time to complete the process, the probability of successful completion of the process, and/or a result regarding product purity. Predicted results may include batch predictions (e.g., a single run of the process or an integer number of runs and the associated predicted results), time-based predictions (e.g., predicted results of the process for the next day, the next three weeks, until a scheduled shutdown, etc.), production definition predictions (e.g., predicted results over the next 1,000 units, the next 47 orders, etc.), and/or rate-of-change-based results (e.g., predicted three part failures per month, one emission per year, etc.). Exemplary system characteristic values 11030 include predicted future states of processes associated with an industrial system, such as operating temperatures, energy consumption values, volume in a tank, noise emissions at a school adjacent to the industrial system, and/or pump rotation speeds at a predetermined time in the future. The predicted future states can be time-based (e.g., Thursday at 4:00 PM), process state-based (e.g., during Phase 3, during a system shutdown, etc.), and/or future states of particular interest (e.g., peak energy consumption, maximum temperature, pump rotation speed, etc.), such as peak energy consumption, maximum temperature, maximum noise value, the time or process stage when the greatest number of personnel will be within 50 feet of a sensitive area, or the time or process stage when the redundancy aspect of the system is at its lowest point (e.g., to determine high-risk points in a process). ) Exemplary system characteristic values 11030 include predicted off-nominal operation of a process associated with an industrial system—e.g., when a system component capacity exceeds nominal parameters (but likely does not result in a failure), when any parameter of the system deviates three standard deviations from normal operation, when a component capacity is underutilized, etc. Exemplary system characteristic values 11030 include predicted values of the operating state of one of a number of components, e.g., at a certain time and/or process stage. Exemplary system characterization values 11030 include future state values for one of a number of components. The predicted future state of a component may be based on time, based on the state of the process, and/or based on a future state of particular interest (e.g., a predicted maximum or minimum value for the component). Exemplary system characteristic values 11030 include any of the following predicted maintenance health information: a minimum value predicted for a number of components at a particular time, process stage, until the next maintenance event, etc. The example system characteristic values 11030 include a predicted maintenance interval for at least one of the multiple components (e.g., based on current usage, forecasted usage, planned process operation, etc.). The example system characteristic values 11030 include a predicted off-nominal operation for one of the multiple components (e.g., at a selected time, process stage, and/or future state of particular interest). The example system characterization values 11030 include a predicted failure operation for one of the multiple components (e.g., any predicted failure occurrence based on a selected time, process stage, current usage, forecasted usage, planned process operation, and/or future state of particular interest). The example system characteristic values 11030 include a predicted exceedance value for one of the multiple components, the exceedance value including exceedance of a design specification and/or exceedance of a selected threshold. Exemplary system characteristic values 11030 include a predicted saturation value for one of a plurality of sensors, such as, for example, a selected time, process stage, current usage, forecasted usage, planned process operation, and/or any predicted saturation occurrences based on future conditions of particular interest.

Any of the predicted values 11030 may be raw values (e.g., temperature values), derivative values (e.g., rate of change of temperature values), cumulative values including weighted cumulative values (e.g., time spent above one or more temperature thresholds), and/or integral values (e.g., area on the temperature-time curve for a temperature value or temperature trajectory of interest). While the example provided mentions temperature, any predicted value 11030 may be utilized, including at least vibration, system throughput, pressure, etc. In certain embodiments, a combination of one or more predicted values 11030 may be utilized.

It will be appreciated in light of the present disclosure that combining predictive values 11030 can create particularly powerful combinations for system analysis, control, and risk management, as specifically contemplated herein. For example, a first predictive value may indicate a time or process stage of maximum flow through the system, and a second predictive value may determine the predicted state of one or more components of the system at that particular time or process stage. In another example, the risks of separate events can be combined to assess overall system risk using a first predictive value indicating the system's lowest margin in terms of delivery capacity (e.g., where at least one component in the process has the lowest operating margin and/or where a group of components has a statistically low operating margin due to the risk induced by multiple simultaneous low operating margins) and a second predictive value testing system risk (e.g., loss of inlet water, loss of power, increase in temperature, change in environmental conditions that reduce or increase heat transfer, or change in environmental conditions that prevent the discharge of a particular wastewater). Additionally, the predicted values can be used in conjunction with sensitivity checks (e.g., varying system conditions within a margin to determine if any failures are likely to occur) to perform sensitivity checks with higher resolution at high-risk points in the process.

The example system 11000 further includes a system interaction circuit 11024 that interprets external data 11036, such that the pattern recognition circuit 11020 further determines a recognized pattern value 11028 in response to the external data 11036. The external data 11036 includes, but is not limited to, data provided from outside the system 11000 and/or from outside the controller 11012. Non-limiting example external data 11036 includes entries from an operator (e.g., indicating a fault, failure, and/or service event). The example pattern recognition circuit 11020 further iteratively refines the pattern recognition operation in response to the external data 11036 (e.g., if the outcome of a maintenance event, product quality decision, production outcome decision, etc. is known, the detection of the recognized pattern value 11028 is thereby refined according to the state of the system prior to the occurrence of the known outcome). Exemplary, non-limiting external data 11036 includes data such as: an indicated process success value; an indicated process failure value; an indicated component maintenance event; an indicated component failure event; an indicated process result value; an indicated component wear value; an indicated process operating overvalue; an indicated component operating overvalue; an indicated fault value; and/or an indicated sensor saturation value.

The example system 11000 further includes a system collaboration circuit 11024 that interprets cloud-based data 11032 including a second number of sensor data values, the second number of sensor data values corresponding to at least one offset industrial system, and the pattern recognition circuit 11020 further determines a recognized pattern value 11028 in response to the cloud-based data 11032. The example pattern recognition circuit 11020 further iteratively refines the pattern recognition operation in response to the cloud-based data 11032. The example sensed parameter group 11026 includes a three-axis vibration sensor, a vibration sensor, and a second sensor that is not a vibration sensor, the second sensor being a digital sensor and/or multiple analog sensors.

Exemplary systems include industrial systems, including oil refineries. Exemplary oil refineries include one or more compressors for transporting fluids throughout the plant and/or for pressurizing fluid streams (e.g., for reflux in distillation columns). Additionally or alternatively, exemplary oil refineries include vacuum distillation, for example, for fractionating hydrocarbons. Furthermore, exemplary oil refineries include various pipelines within the system for transporting fluids, inputting feedstocks, and delivering final products. For example, these pipelines measure the temperature of various fluids, the temperature and composition of individual contact trays within the column, feed and reflux, and effluent and separated product measurements. Distillation column design is complex, and optimal designs depend on the size of boilers and compressors, contact conditions within the column, and the composition of the feedstock, which can vary widely. Furthermore, optimal locations for effective sensing of conditions within the piping can vary depending on fluid flow rates, environmental conditions (e.g., causing variations in heat transfer rates), the feedstock utilized, and other factors. Additionally, wear and deterioration of boilers, compressors, and other operating equipment changes the system's response and function, and single-point optimizations such as where to place sensors and how to sample data become less optimal as the system ages.

Providing multiple sensors throughout a system can be costly, not necessarily because the sensors are expensive, but because the sensors provide data that can be prohibitively expensive to transmit, store, and utilize. An example system involves providing numerous sensors throughout a system and predicting future states of system components, process variables, products, and/or emissions. This example system utilizes pattern recognition circuitry to determine not only the future predicted parameter states, but also when the future predicted parameter states are noteworthy and when they combine with other future predicted parameter states to create new risks or opportunities.

Additionally, the system characterization circuitry and system integration circuitry can improve predictions and/or system characterization over time and/or utilize offset oil refinery predictions or system characterizations to make them more robust, thereby enabling earlier detection, long-term planning for enterprise-wide optimization, and/or operating industrial systems closer to margin. When unexpected operating conditions occur (e.g., abnormal compressor operation), the sensor integration circuitry can shift system predictions and improve the ability to detect the conditions that caused the unexpected operating conditions in the system and/or offset system. Additionally, predictive distillation column alerts can be easily generated to indicate abnormal operation, marginal operation, high-risk operation, or potential upcoming maintenance or failure, providing visibility into risks that may not be apparent from a simple look at system capabilities or past experience without rigorous analysis.

Examples of sensor fusion operations in refineries include vibration information combined with temperature, pressure, and/or composition (e.g., to determine compressor performance), temperature and pressure, temperature and composition, and/or composition and pressure (e.g., to determine feedstock variations, contact tray performance, and/or component failures).

An exemplary refinery system includes a storage tank and/or boiler feedwater. Exemplary system determinations include sensor fusion to determine storage tank failures and/or abnormal operation, such as fusion of temperature and pressure, and/or vibration determination with non-vibration determinations (e.g., detection of leaks, air in the system, and/or feed pump problems). Certain further exemplary system predictions include sensor fusion to determine boiler feedwater malfunctions, such as through sensor fusion including flow rate, pressure, temperature, and/or vibration. Any one or more of these parameters can be utilized to predict system leaks, failures, feed pump wear, and scaling.

Similarly, exemplary industrial systems include power generation systems having condensate and/or makeup water systems, where sensor fusion provides sensed parameters and predictions of failures, maintenance, etc. The system characterization circuitry may utilize sensor fusion and/or continuous machine learning processes to predict failures, off-nominal operation, component health, and/or maintenance events for, but not limited to, compressors, piping, storage tanks, and/or boiler feedwater in an oil refinery.

An exemplary industrial system includes an irrigation system for a field or field system. Irrigation systems are subject to significant system fluctuations (e.g., inlet pressure and/or water level, component wear and maintenance) as well as environmental fluctuations (e.g., planted crop type and distribution, weather, soil moisture, humidity, seasonal solar variations, cloud cover, and/or wind fluctuations). Furthermore, irrigation systems are often installed in remote locations where broadband network access, maintenance facilities, and even monitoring personnel are not readily available. In the example system, the use of multiple sensors allows for prediction of irrigation system conditions without all sensors continuously transmitting or storing data. Pattern recognition circuitry can easily determine the set of sensors most critical to effectively predict patterns, thereby predicting system conditions (e.g., irrigation cycle, location, etc.) that require a response. Furthermore, alerts can be easily generated for remote facilities, with confidence that the correct sensor package is in place to predict abnormal conditions (e.g., impending pump failure or the need for maintenance). In certain embodiments, the system may determine an off-nominal process condition, such as below-normal water supply availability (e.g., based on recognized pattern conditions such as recent precipitation history, history of water production from irrigation systems or other systems competing for the same water supply), structured news alerts, or external data, and update sensed parameters, for example, to confirm water supply availability (e.g., water level sensors at relevant locations), confirm that acceptable conditions are available to allow water supply levels to be reduced (e.g., humidity sensors and/or user prompts), and/or confirm that sufficient secondary sources are available (e.g., auxiliary water level sensors).

Examples of industrial systems include chemical and pharmaceutical plants. Chemical plants require specific operating conditions, flow rates, temperatures, etc., to maintain the proper temperature, concentration, mixture, etc. throughout the system. Many systems have numerous process steps, and abnormal or uncoordinated operation in one part of the process can result in yield loss, process failure, and a significant reduction in production capacity due to the need for (or inability of) a coordinated process to accommodate. Therefore, to minimally define the system, a significant number of systems are required, and in certain embodiments, an exorbitant number of sensors are required to maintain sensing capability over a wide range of operating conditions in terms of data transmission and storage. Furthermore, system complexity makes it difficult to optimize or tune system operation, even with a sufficient number of sensors. In certain embodiments, pattern recognition circuitry can predict a set of sensing parameters that provides a high-resolution understanding of the system, even without all sensors continuously storing and transmitting data. Furthermore, pattern recognition circuitry can highlight predicted system risks and capacity limitations for upcoming process operations, where risks are buried within complex processes. This allows maintenance and system upgrades to be carried out before breakdowns or capacity limitations occur, enabling operation at lower costs and closer to margins.

Additionally, sensor fusion can be used to abstract desired predictions, such as "maximize quality" or "minimize undesired side reactions." However, operators do not need to fully understand which sensors and system conditions are most effective in achieving the abstracted desired output. Furthermore, the predictive capabilities of pattern recognition circuits can enable process changes to be implemented to support desired outcomes before the process results in suboptimal outcomes. Examples of chemical or pharmaceutical plant components that can be controlled and predicted based on pattern recognition circuit and/or sensor fusion operations include agitators, pressure reactors, catalytic reactors, and/or thermal heating systems. Examples of sensor fusion operations for determining sensed parameters and tuning pattern recognition circuits include, but are not limited to, combining vibration sensors with other sensor types, combining composition sensors with other sensor types, combining flow rate determination with other sensor types, and/or combining temperature sensors with other sensor types. For example, agitators are adapted for vibration sensing as well as composition sensing uniformity (e.g., high-resolution temperature), expected reaction rates in a well-mixed system, etc. Catalytic reactors may be temperature-sensing (based on reaction thermodynamics), composition-sensing (e.g., sensing of expected reactants and direct sensing of catalyst material), flow-sensing (e.g., severe mechanical failure, bead volume loss, etc.), and/or pressure-sensing (e.g., indicating or coupled with changes in flow rate).

An exemplary industrial system includes a food processing system. An exemplary food processing system includes pressurized vessels, agitators, mixers, and/or thermal heating systems. Process control is critical to maintaining food safety, product quality, and product consistency. However, most input parameters to food processing systems are subject to high variability. For example, basic food products, as natural products, are inherently variable, differing in moisture content, protein content, and other aesthetic variations. Furthermore, labor cost control, power cost control, supply water variability, and the like provide complex processes in which determining predictive variables, sensed parameters for determining these, and optimizing predictions in response to process variations are challenging problems. Food processing systems are often cost-conscious, and capital costs (e.g., costs for robust networks and computing systems for optimization) are not readily incurred. Furthermore, food processing systems may manufacture a wide variety of products using similar or identical production equipment, for example, to support an entire product line and/or due to seasonal variations. Accordingly, predicted behavior for one process may not support another process well. In this system, the pattern recognition circuitry can determine a set of sensing parameters that exhibit a strong signal response to a desired outcome, even when the system's conditions vary widely. The pattern recognition circuitry can provide numerous sensing group parameter options that can be utilized for different process conditions without requiring extensive computing or data storage resources, thereby achieving relevant predictions for a wide variety of operating conditions. For example, control and prediction of pressurized vessels, agitators, mixers, and/or thermal heating systems can be adapted to the operation of the pattern recognition circuitry and/or temperature determinations combined with non-temperature determinations, vibration determinations combined with non-vibration determinations, heat maps combined with rate of change of heat maps, and/or sensor fusion combined with non-heat map determinations. Examples of systems that provide predictive information for mixers and stirrers through the operation of the pattern recognition circuitry and sensor fusion of vibration determinations and non-vibration determinations, and provide predictive information for pressurized vessels through sensor fusion of pressure determinations, temperature determinations, and non-pressure determinations, are also illustrated.

Referring to FIG. 109, an example procedure 11038 includes operation 11040 of providing a number of sensors to an industrial system including a number of components, each of the number of sensors being operatively coupled to at least one of the number of components, operation 11044 of the sensed parameter group including at least one sensor of the number of sensors, operation 11046 of determining a recognized pattern value in response to at least a portion of the number of sensor data values, and operation 11046 of providing a system characteristic value of the industrial system in response to the recognized pattern value.

Example procedure 11038 further includes operation 11046 of providing a system characterization value by performing operations such as: determining a predicted outcome for a process associated with the industrial system; determining a predicted future state for a process associated with the industrial system; determining a predicted off-nominal operation for a process associated with the industrial system; determining a predicted value for one of a plurality of components; determining a future state value for one of a plurality of components; determining predicted maintenance health status information for one of a plurality of components; determining a predicted maintenance interval for at least one of the plurality of components, determining a predicted off-nominal operation for one of the plurality of components, determining a predicted fault operation for one of the plurality of components, determining a predicted exceedance value for one of the plurality of components, and/or determining a predicted saturation value for one of the plurality of sensors.

Example procedure 11038 includes operation 11050 of interpreting the external data and/or cloud-based data, and operation 11044 of determining a recognized pattern value is further performed in response to the external data and/or cloud-based data. Example procedure 11038 includes operations of iteratively improving the pattern recognition operations in response to the external data and/or cloud-based data, such as operation 11048 of adjusting operation 11042 of interpreting sensor values, e.g., by updating a set of sensed parameters, to improve the pattern recognition operations. The operations of iteratively improving the pattern recognition may further include repeating operations 11042 through 11048 periodically at selected intervals in response to changes in the system and/or in response to predicted values of the component, process, or system.

In an embodiment, a system for data collection in an industrial environment may include: an industrial system including a plurality of components; a plurality of sensors, each operably coupled to at least one of the plurality of components; a sensor communication circuit configured to interpret a plurality of sensor data values in response to a sensed parameter group, the sensed parameter group including at least one of the plurality of sensors; a pattern recognition circuit configured to determine a recognized pattern value in response to at least a portion of the plurality of sensor data values; and a system characterization circuit configured to provide a system characteristic value for the industrial system in response to the recognized pattern value. In an embodiment, the characteristic value may include at least one characteristic value selected from the following characteristic values: a predicted outcome of a process associated with the industrial system, a predicted future state of a process associated with the industrial system, and a predicted off-nominal operation of a process associated with the industrial system. The system characteristic value may include at least one characteristic value selected from the following characteristic values: a predicted value for one of a plurality of components, a future state value for one of a plurality of components, predicted maintenance health status information for one of a plurality of components, and a predicted maintenance interval for at least one of a plurality of components. The system characteristic value may include at least one characteristic value selected from the following characteristic values: predicted off-nominal operation for one of the plurality of components, predicted fault operation for one of the plurality of components, and predicted exceedance value for one of the plurality of components. The system characteristic value may include a predicted saturation value for one of the plurality of sensors. A system collaboration circuit configured to interpret external data may be included, and the pattern recognition circuit may be configured to further determine a recognized pattern value in response to the external data. The pattern recognition circuit may be further configured to iteratively improve the pattern recognition operation in response to the external data. The external data may include at least one of an indicated component maintenance event, an indicated component failure event, an indicated component wear value, an indicated component operating exceedance value, and an indicated failure value. The external data may include at least one of an indicated process failure value, an indicated process success value, an indicated process result value, and an indicated process operating exceedance value. The external data may include an indicated sensor saturation value. The system may include a system collaboration circuit configured to interpret cloud-based data including a second plurality of sensor data values, the second plurality of sensor data values corresponding to at least one offset industrial system, and the pattern recognition circuit configured to further determine recognized pattern values in response to the cloud-based data. The pattern recognition circuit may be further configured to iteratively improve the pattern recognition operation in response to the cloud-based data. The set of sensed parameters may include a triaxial vibration sensor. The set of sensed parameters may include a vibration sensor and a second sensor that is not a vibration sensor, such as when the second sensor comprises a digital sensor. The set of sensed parameters may include a plurality of analog sensors.

In an embodiment, a method may include providing a plurality of sensors to an industrial system including a plurality of components, each of the plurality of sensors operably coupled to at least one of the plurality of components; interpreting a plurality of sensor data values in response to a sensed parameter group, the sensed parameter group including at least one of the plurality of sensors; determining a recognized pattern value in response to at least a portion of the plurality of sensor data values; and providing a system characteristic value of the industrial system in response to the recognized pattern value. The system characteristic value may be provided by performing at least one operation selected from the operations consisting of: determining a predicted value for one of the plurality of components; determining a future state value for one of the plurality of components; determining expected maintenance health information for one of the plurality of components; and determining an expected maintenance interval for at least one of the plurality of components. The system characteristic value may be provided by performing at least one operation selected from the operations consisting of: determining a predicted outcome of a process associated with the industrial system; determining a predicted future state of a process associated with the industrial system; and determining a predicted off-nominal operation of a process associated with the industrial system. The system characteristic value may be provided by performing at least one operation selected from the operations consisting of: determining a predicted off-nominal operation for one of the plurality of components; determining a predicted fault operation for one of the plurality of components; and determining a predicted exceedance value for one of the plurality of components. The system characteristic value may be provided by determining a predicted saturation value for one of the plurality of sensors. The determination of the recognized pattern value may further be performed in response to external data. Iteratively improving the palm recognition operation may be provided in response to the external data. Interpreting the external data may include at least one operation selected from the operations consisting of interpreting an indicated component maintenance event, interpreting an indicated component failure event, interpreting an indicated component wear value, interpreting an indicated component operation exceedance value, and interpreting an indicated failure value. Interpreting the external data may include at least one operation selected from the operations consisting of interpreting an indicated process success value, interpreting an indicated process failure value, interpreting an indicated process result value, and interpreting an indicated process operation exceedance value. Interpreting the external data may include interpreting an indicated sensor saturation value. Interpreting the cloud-based data may include a second plurality of sensor data values, the second plurality of sensor data values corresponding to at least one offset industrial system, and determining the recognized pattern value further in response to the cloud-based data. Iterative improvements to the pattern recognition operation may be provided in response to the cloud-based data.

In an embodiment, a system for data collection in an industrial environment may include: an industrial system comprising: a plurality of components; a plurality of sensors, each operably coupled to at least one of the plurality of components; a sensor communication circuit configured to interpret a plurality of sensor data values in response to a set of sensed parameters, the set of sensed parameters including at least one of the plurality of sensors; means for determining a recognized pattern value in response to at least a portion of the plurality of sensor data values; and means for providing a system characteristic value of the industrial system in response to the recognized pattern value. The means for providing the system characteristic value may include means for performing at least one operation selected from the operations of determining a predicted outcome of a process associated with the industrial system, determining a predicted future state of a process associated with the industrial system, and determining a predicted off-nominal operation of a process associated with the industrial system. The means for providing a system characteristic value may include means for performing at least one operation selected from the group consisting of: determining a predicted value for one of the plurality of components; determining a future state value for one of the plurality of components; determining predicted maintenance health status information for one of the plurality of components; and determining a predicted maintenance interval for at least one of the plurality of components. The means for providing a system characteristic value may include means for performing at least one operation selected from the group consisting of: determining a predicted off state; and determining a predicted maintenance interval for at least one of the plurality of components. The means for providing a system characteristic value may include means for determining a predicted saturation value for one of the plurality of sensors. System interaction circuitry configured to interpret external data may be provided, and the means for determining a recognized pattern value may further determine the recognized pattern value in response to the external data. Means may be provided for iteratively improving the pattern recognition operation in response to the external data. The external data may include at least one of an indicated process success value, an indicated process failure value, and an indicated process result value. The external data may include at least one of an indicated component maintenance event, an indicated component failure event, and an indicated component wear value. The external data may include at least one of an indicated process operation exceedance value, an indicated component operation exceedance value, and an indicated fault value. The external data may include an indicated sensor saturation value. System interaction circuitry may be provided that is configured to interpret cloud-based data including a second plurality of sensor data values, the second plurality of sensor data values corresponding to at least one offset industrial system, and the means for determining a recognized pattern value further determines the recognized pattern value in response to the cloud-based data. Means for iteratively improving the pattern recognition operation may be provided in response to the cloud-based data.

In an embodiment, a system for data collection in an industrial environment may include: a distillation column including a plurality of components; a plurality of sensors, each operably coupled to at least one of the plurality of components; a sensor communication circuit configured to interpret a plurality of sensor data values in response to a set of sensed parameters, the set of sensed parameters including at least one of the plurality of sensors; a pattern recognition circuit configured to determine a recognized pattern value in response to at least a portion of the plurality of sensor data values; and a system characterization circuit configured to provide a system characteristic value of the distillation column in response to the recognized pattern value. The plurality of components may include a thermodynamic processing component, and the system characteristic value may include determining a predicted value of the thermodynamic processing component and at least one value selected from the following values: determining a future state value of the thermodynamic processing component; determining predicted maintenance health information for the thermodynamic processing component; and determining a process rate limit responsive to the capacity of the thermodynamic processing component. The thermodynamic processing component may include at least one of a compressor or a boiler.

In an embodiment, a system for data collection in an industrial environment may include: a chemical processing system comprising: a plurality of components; a plurality of sensors, each operably coupled to at least one of the plurality of components; a sensor communication circuit configured to interpret a plurality of sensor data values in response to a sensed parameter group, the sensed parameter group including at least one sensor of the plurality of sensors; a pattern recognition circuit configured to determine a recognized pattern value in response to at least a portion of the plurality of sensor data values; and a system characterization circuit configured to provide a system characteristic value of the chemical processing system in response to the recognized pattern value. The chemical processing system may include any of a chemical plant, a pharmaceutical plant, and an oil refinery. The system characteristic value may include at least one value selected from values consisting of a separation process value comprising at least one of a capacity value or a purity value; a side reaction process value comprising a side reaction rate value; and a thermodynamic process value comprising one of a capability, a capacity, and a predicted maintenance health of a thermodynamic process component.

A system for collecting data in an industrial environment, the system including:

The present invention provides an irrigation system comprising: a plurality of components, including a pump; a plurality of sensors, each operably coupled to at least one of the plurality of components; a sensor communication circuit configured to interpret a plurality of sensor data values in response to a sensed parameter group, the sensed parameter group including at least one of the plurality of sensors; a pattern recognition circuit configured to determine a recognized pattern value in response to at least a portion of the plurality of sensor data values; and a system characterization circuit configured to provide a system characterization value for the irrigation system in response to the recognized pattern value. The system characteristic value may include at least one of a predicted maintenance health value of the pump and a future state value of the pump. The pattern recognition circuit may determine an off-nominal process condition in response to at least a portion of the plurality of sensor data values, and the sensor communication circuit is further configured to modify the sensed parameter group in response to the off-nominal process condition. The off-nominal process condition may include an indication of the availability of a sub-normal water supply, and the updated sensed parameter group includes at least one sensor selected from the group consisting of a water level sensor, a humidity sensor, and an auxiliary water level sensor.

As described elsewhere herein, feedback to various intelligent and/or expert systems, control systems (including remote and local systems, autonomous systems, etc.), and the like, comprising rule-based systems, model-based systems, artificial intelligence (AI) systems (including neural nets, self-organizing systems, and others described throughout this disclosure), and various combinations and hybrids thereof, can include a wide range of information, including measurements such as utilization measures, efficiency measures (e.g., economic measures such as cost savings, power, financial measures such as cost savings), measures of success in predicting or preempting conditions (e.g., failure avoidance and mitigation), productivity measures (e.g., workflow), yield measures, profit measures, and the like, as described herein. In embodiments, feedback to expert systems may be industry-specific, domain-specific, plant-specific, machine-specific, etc.

The industry-specific feedback to the expert system may be provided by a third party, such as a repair and maintenance organization, a manufacturer, one or more consortia, or may be generated by one or more elements of the target system itself. The industry-specific feedback may be aggregated into one or more data structures, with data aggregated at the component level, the equipment level, the plant/installation level, and/or the industry level. Users of the data structure can access data at any level (e.g., component, equipment, plant, industry). Users can search the data structure for indicators/predictions based on or filtered by system conditions as needed, or update the indicators/predictions with their own data to customize the data structure for their industry. In embodiments, the expert system may seed the industry-specific feedback, such as with deep learning methods, to provide expected outcomes or conditions and/or take actions to optimize specific machines, equipment, components, processes, etc.

In embodiments, feedback provided to the expert system may be used in one or more smart bands to predict progress toward one or more goals. The expert system may use the feedback to determine modifications, changes, additions, alterations, etc. to one or more components of the system that provided the feedback, as described elsewhere herein. Based on the industry-specific feedback, the expert system may modify inputs, methods of processing or storing inputs or outputs, sensors or sensors used to provide feedback, operating parameters, equipment used in the system, or other aspects of the participants in the industrial system that provided the feedback. As described elsewhere herein, the expert system may track multiple goals, such as using one or more smart bands. The industry-specific feedback may be used in or by the smart band to predict outcomes or conditions related to one or more goals and recommend or prescribe changes directed toward increasing the likelihood of achieving the outcomes or conditions.

For example, a mixer may be used in a food processing environment or a chemical processing environment, but the feedback relevant in a food processing plant (e.g., required sterilization temperature, food viscosity, particle density (e.g., as measured by an optical sensor), cooking completion (e.g., completion of reactions involved in baking), sanitation (e.g., absence of pathogens), etc.) may be different from that relevant in a chemical processing plant (e.g., impeller speed, velocity vector, flow rate, absence of high contaminant levels, etc.). Such industry-specific feedback helps optimize the mixer's operation in that particular environment.

In another example, the expert system may use feedback from an agricultural system to train a model related to irrigation systems deployed in a field, and the industry-specific feedback may relate to one or more of the amount of water used across the industry (e.g., as measured by a flow meter), trends in water usage over a period of time (e.g., as measured by a flow meter), crop yield (e.g., as measured by a gravimetric scale), insect infestations (e.g., as identified and/or measured by drone footage), and plant mortality (e.g., as identified and/or measured by drone footage).

In another example of controlling cooling of a fluid flow system (e.g., a fan, pump, or compressor) in manufacturing, the expert system may use feedback from the production of a component containing a material (e.g., a polymer) that requires cooling during the manufacturing process, such as one or more of the following: output product quality, output product strength, output product flexibility (as measured by a series of sensors including, for example, a density meter, a viscometer, a size exclusion chromatograph, and a torque meter). If the sensors indicate that the polymer is cooling too quickly during monomer conversion, the expert system may relay instructions to one or more systems, such as reducing the operation of some of the fans, pumps, or compressors in the fluid flow system to achieve quality targets.

In another example of a reciprocating compressor operating in a refinery performing a refining process (e.g., hydrotreating, hydrocracking, isomerization, reforming), the expert system may use feedback related to one or more of the amount of sulfur, nitrogen, and/or aromatics downstream of the compressor (e.g., as measured by a near-infrared ("IR") analyzer), product cetane/octane number or smoke point (e.g., using an octane analyzer), product density, and/or smoke point. Feedback related to the product cetane/octane number or smoke point (e.g., using an octane analyzer), product density (e.g., using a density meter), by-product gas amount (e.g., using an electrochemical gas sensor), etc., may be used. In this example, when butane is isomerized to isobutene, upon receiving feedback from an in-line near-infrared analyzer measuring the quantity and/or quality of isobutene, the expert system may determine that the performance of one or more components of the isomerization system, including the reciprocating compressor, should be modified to achieve production targets.

In another example of a vacuum distillation unit operating in a refinery, the expert system may use feedback related to the amount of raw gasoline recovered (e.g., using IR to measure the volume or composition of various fractions), the boiling points of the recovered fractions (e.g., using a boiling point analyzer), the vapor cooling rate (e.g., measured with a thermometer), etc. In this example, if feedback is received during a vacuum distillation to recover diesel indicating that the recovery rate is deviating from the nominal rate of production, the expert system may instruct the vacuum distillation unit to change the source of feedstock and initiate a more detailed analysis of the preceding feedstock.

In yet another example of a refinery pipeline, the expert system may use feedback related to the type of hydrocarbon product flow (e.g., bubbly, stratified, slug, annular, transition, mist) (e.g., as measured by dye tracing), flow rate, steam velocity (e.g., using a flow meter), steam shear, etc. In this example, during operation of the pipeline, upon receiving feedback regarding the flow type and its velocity, modifications may be recommended by the expert system to improve flow through the pipeline.

In another example of a paddle or anchor type agitator in a pharmaceutical factory, the expert system may use feedback regarding the degree of mixing of high viscosity liquids, the heating of medium to low viscosity liquids, the density of the mixture, the growth rate of organisms in the mixture, etc. In this example, if feedback is received during operation of the agitator that the bacterial growth rate measured by a spectrophotometer is too high, the expert system may instruct the agitator to slow down and limit the amount of air added to the mixture or growth substrate.

In a further example of a pressure reactor in a chemical processing plant, the expert system may use feedback related to catalytic reaction rates (e.g., as measured by a mass spectrometer), particle density (e.g., as measured by a densitometer), biological growth rates (e.g., as measured by a spectrophotometer), etc. In this example, if feedback is received during operation of the pressure reactor that the particle density and biological growth rates are out of specification, the expert system may instruct the pressure reactor to modify one or more operating parameters, such as reducing pressure, increasing temperature, or increasing reaction volume.

In another example of a gas agitator operating in a chemical processing plant, the expert system may use feedback related to the effective density, viscosity, gas pressure, etc. of the gasified liquid, as measured by appropriate sensors or devices. In this example, upon receiving feedback during operation of the gas agitator, the expert system may instruct the gas agitator to modify one or more operating parameters, such as increasing or decreasing the agitation speed.

In yet another example of a pump-blast liquid-type agitator in a chemical processing plant, the expert system may use feedback related to the viscosity of the mixture, the optical density of the growing medium, and the temperature of the solution. In this example, upon receiving feedback during operation of the agitator, the expert system can instruct the agitator to modify one or more operating parameters, such as increasing or decreasing the agitation speed or injecting additional heat.

In yet another example of a turbine-type agitator in a chemical processing plant, the expert system may use feedback related to vibration noise, reaction rates of reactants, heat transfer, or suspension density. In this example, upon receiving feedback during operation of the agitator, the expert system can instruct the agitator to change one or more operating parameters, such as increasing or decreasing the agitation speed or injecting additional catalyst.

In yet another example of a static mixer mixing monomers in a chemical processing plant to produce polymers, an expert system could use feedback related to polymer viscosity, polymer color, polymer reactivity, etc. to iterate to new settings or parameters for the mixer, such as settings that change the Reynolds number, increasing the temperature, increasing the pressure, etc.

In a further example of a catalytic reactor in a chemical processing plant, the expert system may use feedback related to reaction rate, product concentration, product color, etc. In this example, when feedback is received during operation of the catalytic reactor, the expert system may instruct the reactor to modify one or more operating parameters, such as increasing or decreasing the temperature and/or injecting additional amounts of catalyst.

In a further example of a thermal heating system in a chemical processing plant or food factory, the expert system may use feedback from the system related to BTUs, flow rate, etc. In this example, when feedback is received during operation of the thermal heating system, the expert system may instruct the system to modify one or more operating parameters, such as changing the input raw materials or increasing the flow rate of the raw materials.

In a further example using boiler feedwater in an oil refinery, the expert system may use feedback related to aeration levels, temperature, etc. In this example, when feedback related to the boiler feedwater is received, the expert system may instruct the system to modify one or more operating parameters of the boiler, such as increasing aeration reduction or increasing the feedwater flow rate.

In a further example of a storage tank in an oil refinery, the expert system may use feedback related to temperature, pressure, flow rate from the tank, etc. In this example, upon receiving feedback related to the storage tank, the expert system may instruct the system to modify one or more operating parameters, such as increasing cooling or heating or initiating agitation.

In the example of a power plant condensate/make-up water system, where steam from the turbine is condensed and recirculated along with make-up water to the boiler feeder, the expert system can use feedback related to measurements of internal air leakage, heat transfer, and make-up water quality. In this example, upon receiving feedback about the condensate/make-up water system, the expert system can instruct the system to increase make-up water purification, bring a vacuum pump online, etc.

In another example of a mixer in a food factory, the expert system may use feedback related to food viscosity, food color, food temperature, etc. In this example, upon receiving the feedback, the expert system may instruct the mixer to increase or decrease speed depending on the predicted success of reaching the goal.

In another example of a pressure cooker in a food factory, the expert system may use feedback related to the viscosity of the food, the color of the food, the temperature of the food, etc. In this example, the expert system may instruct the pressure cooker to continue operating, increase the temperature, etc., depending on the predicted success of the goal.

In one embodiment, a system 11100 for data collection in an industrial environment may include a plurality of input sensors 11102 communicatively coupled to a controller 11106, a data collection circuit 11104 configured to collect output data 11108 from the input sensors 11102, and a machine learning data analysis circuit 11110 configured to receive the output data 11108 and learn received output data patterns 11112 indicative of results, wherein the machine learning data analysis circuit 11110 is configured to receive the output data 11108 and learn received output data patterns 11112 indicative of results, the machine learning data analysis circuit 11110 being configured to learn the received output data patterns 11112 by seeding a model 11114 based on industry-specific feedback 11118. The model 11114 may be a physical model, an operational model, or a system model. The industry specific feedback 11118 may be one or more of a utilization measure, an efficiency measure (e.g., power and/or financial), a measure of condition prediction or prediction success (e.g., failure avoidance and mitigation), a productivity measure (e.g., workflow), a production measure, and a profit measure. The industry specific feedback 11118 includes an amount of power generated by a machine for which the input sensors provide information during operation of the machine. The industry specific feedback 11118 includes measurements of assembly line output for which the input sensors provide information. The industry specific feedback 11118 includes a failure rate of units of a product produced by a machine for which the input sensors provide information. The industry specific feedback 11118 includes a failure rate of a machine for which the input sensors provide information. The industry-specific feedback 11118 may include a power utilization efficiency of a machine for which the input sensors provide information, where the machine is one of a turbine, a transformer, a generator, a compressor, an energy store, and a powertrain component (e.g., a material extraction rate by the machine for which the input sensors provide information, a gas production rate by the machine for which the input sensors provide information, a hydrocarbon product production rate by the machine for which the input sensors provide information, or a chemical product production rate by the machine for which the input sensors provide information). The machine learning data analysis circuit 11110 may be further configured to learn the received output data patterns 1112 based on the results. The system 11100 may maintain or modify operating parameters or equipment. The controller 11106 may adjust the weighting of the machine learning data analysis circuit 11110 based on the learned received output data patterns 1112 or results, collect more/fewer data points from the input sensors based on the learned received output data patterns 1112 or results, change the data storage technique for the output data 11108 based on the learned received output data patterns 1112 or results, change the data presentation mode or manner based on the learned received output data patterns 1112 or results, and apply one or more filters (low pass, high pass, band pass, etc.) to the output data 11108. In embodiments, the system 11100 may remove/retask unused equipment based on one or more of the learned received output data patterns 11112 and results. The machine learning data analysis circuit 11110 may include a neural network expert system. The input sensors may measure vibration and noise data. The machine learning data analysis circuit 11110 may be configured to learn received output data patterns 1112 indicative of progress/consistency with one or more goals/guidelines (e.g., which may be determined by different subsets of input sensors). The machine learning data analysis circuit 11110 may be configured to ream received output data patterns 1112 indicative of unknown variables. The machine learning data analysis circuit 11110 may be configured to ream received output data patterns 11112 indicative of preferred inputs among available inputs. The machine learning data analysis circuit 11110 may be configured to ream received output data patterns 1112 indicative of preferred input data collection bands among available input data collection bands. The machine learning data analysis circuit 11110 may be located partially on the machine, on one or more data collectors, in a network infrastructure, in the cloud, or any combination thereof. The system 11100 may be located on the data collection circuit 11104. The system 11100 may be distributed between the data collection circuit 11104 and a remote infrastructure. The data collection circuitry 11104 may include a data collector.

In an embodiment, a system 11100 for data collection in an industrial environment includes a plurality of input sensors 11102 communicatively coupled to a controller 11106, a data collection circuit 11104 structured to collect output data 11108 from the input sensors, and a machine learning data analysis circuit 11110 structured to receive the output data 11108 and learn received output data patterns 11112 indicative of the results, wherein the machine learning data analysis circuit 11110 is structured to learn the received output data patterns 11112 by being seeded with a model 11114 based on utilization measurements.

In an embodiment, a system 11100 for data collection in an industrial environment includes a plurality of input sensors 11102 communicatively coupled to a controller 11106, a data collection circuit 11104 configured to collect output data 11108 from the input sensors, and a machine learning data analysis circuit 11110 configured to receive the output data 11108 and refine a received output data pattern 11112 indicative of the results, wherein the machine learning data analysis circuit 11110 may be configured to refine the received output data pattern 11112 by being seeded with a model 11114 based on an efficiency measurement.

In an embodiment, a system 11100 for data collection in an industrial environment may include a plurality of input sensors 11102 communicatively coupled to a controller 11106, a data collection circuit 11104 configured to collect output data 11108 from the input sensors, and a machine learning data analysis circuit 11110 configured to receive the output data 11108 and reap the received output data patterns 11112 indicative of the results, wherein the machine learning data analysis circuit 11110 is configured to reap the received output data patterns 11112 by being seeded with a model 11114 based on a measure of success in predicting or forecasting a state.

In an embodiment, a system 11100 for data collection in an industrial environment includes a plurality of input sensors 11102 communicatively coupled to a controller 11106, a data collection circuit 11104 configured to collect output data 11108 from the input sensors, and a machine learning data analysis circuit 11110 configured to receive the output data 11108 and refine received output data patterns 11112 indicative of the results, wherein the machine learning data analysis circuit 11110 may be configured to refine the received output data patterns 11112 by being seeded with a model 11114 based on productivity measurements.

(1) In an embodiment, a system for data collection in an industrial environment comprises: a plurality of input sensors communicatively coupled to a controller; a data collection circuit configured to collect output data from the input sensors; and a machine learning data analysis circuit configured to receive the output data and learn patterns in the received output data indicative of results, wherein the machine learning data analysis circuit is configured to learn the received output data patterns by being seeded with a model based on industry-specific feedback. (2) The system described in (1), wherein the model is a physical model, an operational model, or a system model. (3) The system described in (1), wherein the industry-specific feedback is a utilization measurement. (4) The system described in (1), wherein the industry-specific feedback is an efficiency metric. (5) The system described in (4), wherein the efficiency metric is one of power and financial. (6) The system described in (1), wherein the industry-specific feedback is a measure of success in predicting or forecasting conditions. (7) The system described in (6), wherein the measure of success is failure avoidance and mitigation. (8) The system of (1), wherein the industry-specific feedback is a productivity indicator. (9) The system of (8), wherein the productivity indicator is a workflow. (10) The system of (1), wherein the industry-specific feedback is a yield indicator. (11) The system of (1), wherein the industry-specific feedback is a profit indicator. (12) The system of (1), wherein the machine learning data analysis circuit is further configured to learn received output data patterns based on the results. (13) The system of (1), wherein the system maintains or modifies operational parameters or equipment. (14) The system of (1), wherein the controller adjusts weightings of the machine learning data analysis circuit based on the learned received output data patterns or results. (15) The system of (1), wherein the controller collects more/fewer data points from input sensors based on the learned received output data patterns or results. (16) The system of (1), wherein the controller changes data storage techniques for output data based on learned received output data patterns or results. (17) The system of (1), wherein the control device changes data presentation modes or methods based on learned received output data patterns or results. (18) The system of (1), wherein the controller applies one or more filters (low pass, high pass, band pass, etc.) to the output data. (19) The system of (1), wherein the system eliminates/reworks underutilized equipment based on one or more learned received output data patterns and results. (20) The system of (1), wherein the machine learning data analysis circuit comprises a neural network expert system. (21) The system of (1), wherein the input sensors measure vibration and noise data. (22) The system of (1), wherein the machine learning data analysis circuit is configured to ream received output data patterns indicative of progress/alignment with one or more goals/guidelines. (23) The system of (22), wherein progress/alignment with each goal/guideline is determined by a different subset of input sensors. (24) The system of (1), wherein the machine learning data analysis circuit is configured to ream received output data patterns indicative of unknown variables. (25) The system of (1), wherein the machine learning data analysis circuit is configured to ream received output data patterns indicative of preferred inputs among available inputs. (26) The system of (1), wherein the machine learning data analysis circuit is configured to ream received output data patterns indicative of preferred input data collection bands among available input data collection bands. (27) The system of (1), wherein the machine learning data analysis circuit is located in part on a machine, on one or more data collection devices, on a network infrastructure, on a cloud, or any combination thereof. (28) The system of (1), wherein the system is located on the data collection circuit. (29) The system of (1), wherein the system is distributed between the data collection circuit and a remote infrastructure. (30) The system of (1), wherein the industry-specific feedback includes an amount of power generated by the machine for which the input sensors provide information during operation of the machine. (31) The system of (1), wherein the industry-specific feedback includes a measurement of the output of an assembly line for which the input sensors provide information. (32) The system of (1), wherein the industry-specific feedback includes a failure rate of units of a product produced by the machine for which the input sensors provide information. (33) The system of (1), wherein the industry-specific feedback includes a failure rate of the machine for which the input sensors provide information. (34) The system of (1), wherein the industry-specific feedback includes a power utilization efficiency of the machine for which the input sensors provide information. (35) The system of (34), wherein the machine is a turbine. (36) The system of (34), wherein the machine is a transformer. (37) The system of (34), wherein the machine is a generator. (38) The system of (34), wherein the machine is a compressor. (39) The system of (34), wherein the machine stores energy. (40) The system of (1), wherein the machine includes a powertrain component. (41) The system of (34), wherein the industry-specific feedback includes a material extraction rate by the machine for which the input sensors provide information. (42) The system of (34), wherein the industry-specific feedback includes a gas production rate by the machine for which the input sensors provide information. (43) The system of (34), wherein the industry-specific feedback includes a hydrocarbon product production rate by the machine for which the input sensors provide information. (44) The system of (34), wherein the industry-specific feedback includes a chemical product production rate by the machine for which the input sensors provide information. (45) The system of (1), wherein the data acquisition circuitry comprises a data collector. (46) A system for data collection in an industrial environment, comprising: a plurality of input sensors communicatively coupled to a controller; a data collection circuit configured to collect output data from the input sensors; and a machine learning data analysis circuit configured to receive the output data and derive a received output data pattern indicative of an outcome, wherein the machine learning data analysis circuit is configured to derive the received output data pattern by seeding a model based on a utilization measurement. (47) A system for data collection in an industrial environment, comprising: a plurality of input sensors communicatively coupled to a controller; a data collection circuit configured to collect output data from the input sensors; and a machine learning data analysis circuit configured to receive the output data and derive a received output data pattern indicative of an outcome, wherein the machine learning data analysis circuit is configured to derive the received output data pattern by seeding a model based on an efficiency measurement. (48) A system for data collection in an industrial environment, comprising: a plurality of input sensors communicatively coupled to a controller; a data collection circuit configured to collect output data from the input sensors; and a machine learning data analysis circuit configured to receive the output data and ream received output data patterns indicative of outcomes, wherein the machine learning data analysis circuit is configured to ream received output data patterns by seeding a model based on a measure of success in predicting or forecasting a condition. (49) A system for data collection in an industrial environment, comprising: a plurality of input sensors communicatively coupled to a controller; a data collection circuit configured to collect output data from the input sensors; and a machine learning data analysis circuit configured to receive the output data and ream received output data patterns indicative of outcomes, wherein the machine learning data analysis circuit is configured to ream received output data patterns by seeding a model based on a measure of productivity.

In an embodiment, a system for collecting data in an industrial environment may include a graphical user interface of an expert system, where a user can set parameters for a data collection band for collection by a data collector by interacting with graphical user interface elements. The parameters may relate to at least one of setting a frequency range for collection and setting a range of granularity for collection.

In embodiments, a system for data collection in an industrial environment may include an expert system graphical user interface, where a user can interact with graphical user interface elements to identify a set of sensors from a larger set of available sensors for collection by a data collector. The user interface may include a representation of available data collection devices, their capabilities, one or more corresponding smart bands, etc.

In an embodiment, a system for data collection in an industrial environment may include an expert system graphical user interface, where a user can select a set of inputs to be multiplexed from a set of available inputs by interacting with graphical user interface elements.

In an embodiment, a system for data collection in an industrial environment may include a graphical user interface of an expert system, where a user can interact with graphical user interface elements to select components of an industrial machine to be displayed in the graphical user interface for data collection, display a set of sensors available to provide data about the industrial machine, and select a subset of the sensors for data collection.

In embodiments, a system for data collection in an industrial environment may include a graphical user interface of an expert system, where a user can interact with graphical user interface elements to view a set of indicators of fault conditions for one or more industrial machines, the fault conditions being identified by application of the expert system to data collected from the set of data collectors. In embodiments, the fault conditions may be identified by a manufacturer of a portion of the one or more industrial machines. The fault conditions may be identified through analysis of industry trade data, third-party testing laboratory data, industry standards, and the like. In embodiments, the set of indicators of fault conditions for the one or more industrial machines may include indicators of stress, vibration, heat, wear, ultrasonic signatures, operational deflection geometry, and the like, and optionally include any of the widely varying conditions that can be sensed by sensors of the types described throughout this disclosure and the documents incorporated herein by reference.

In an embodiment, a system for data collection in an industrial environment may include an expert graphical user interface that allows a user to select from a list of industrial machine components to establish smart band monitoring, and in response presents the user with at least one smart band definition of an acceptable range of values for at least one sensor of the industrial machine and a list of correlated sensors from which data is collected and analyzed when an out-of-acceptable condition is detected from the at least one sensor.

In an embodiment, a system for data collection in an industrial environment may include an expert graphical user interface that allows a user to select from a list of conditions of an industrial machine for which to establish smart band monitoring, and in response presents the user with at least one smart band definition of an acceptable range of values for at least one sensor of the industrial machine and a list of correlated sensors from which data is to be collected and analyzed when an out-of-acceptable condition is detected from the at least one sensor.

In embodiments, a system for collecting data in an industrial environment may include an expert graphical user interface that allows a user to select from a list of reliability measurements of an industrial machine for establishing smart band monitoring and, in response, presents the user with at least one smart band definition of an acceptable range of values for at least one sensor of the industrial machine and a list of correlated sensors from which data is collected and analyzed when an out-of-tolerance condition is detected from the at least one sensor. In this system, the reliability measurements may include one or more of industry average data, manufacturer specifications, material specifications, recommendations, etc. In embodiments, the reliability measurements may include measurements correlated to failures, such as stress, vibration, heat, wear, ultrasonic signatures, and operational deflection shape effects. In embodiments, manufacturer specifications may include cycle counts, operating hours, maintenance recommendations, maintenance schedules, operating limits, material limits, warranty conditions, etc. In embodiments, sensors in an industrial environment may be correlated to manufacturer specifications by associating the condition being sensed by the sensor with a specification type. In embodiments, a non-limiting example of correlating a sensor to a manufacturer's specification may include a duty cycle specification correlating a sensor that detects rotation of a moving part. In an embodiment, the temperature specification may correlate to a thermal sensor positioned to sense the ambient temperature in the vicinity of the industrial machine.

In an embodiment, a system for data collection in an industrial environment may include an expert graphical user interface that automatically creates smart band groups of sensors located in the industrial environment in response to receiving a state of the industrial environment for monitoring and an acceptable range of state values.

In an embodiment, a system for data collection in an industrial environment may include an expert graphical user interface that presents on an electronic display representations of components of industrial machinery deployable in the industrial environment and, in response to a user selecting one or more of the components, performs the following: upon the user selecting one or more components, searches a database of industrial machinery failure modes for modes associated with the selected components and conditions associated with the failure modes to be monitored; and further identifies a plurality of sensors located or deployable on the presented representation of the machinery to automatically acquire data when an out-of-tolerance condition to be monitored is detected. In an embodiment, the identified plurality of sensors includes at least one sensor whose condition is to be monitored.

In an embodiment, a system for data collection in an industrial environment may include a user interface for interacting with a smart band that facilitates a user identifying sensors to include in the smart band's group of sensors by selecting sensors presented on a map of machines in the environment. The user may be guided to select from among a subset of all possible sensors based on smart band criteria, such as the type of sensor data required by the smart band. The smart band may be focused on detecting trending conditions in a portion of the industrial environment, and thus the user interface may prompt the user to select from among the identified subset of sensors, such as by making only sensors in proximity to the smart band-indicated portion of the environment selectable in the user interface.

In an embodiment, the smart band data collection configuration and deployment user interface may include a view of components of an industrial environment and associated available sensors. In an embodiment, in response to selection of a component of an industrial machine depicted in the user interface, sensors associated with smart band data collection for the component may be highlighted to allow the user to select one or more of the sensors. User selection in this context may include validation of automatic selection of sensors or manual identification of sensors for inclusion in a smart band sensor group.

In an embodiment, in response to selection of a condition on the Smart Band, such as bearing temperature trending, the user interface for configuring and using the Smart Band can automatically identify and present sensors that contribute to the Smart Band's analysis for the condition. In response to this presentation of sensors, the user can confirm or otherwise approve one or more sensors included in the Smart Band's data collection group, either individually or as a set.

In embodiments, the smart band user interface may present on a map the locations of industrial machines in an industrial environment. The locations may be annotated with indicators of smart band data collection templates configured to collect smart band data for machines at the annotated locations. The locations may be color-coded to reflect the degree of smart band coverage for machines at the locations. In embodiments, locations of machines with high smart band coverage may be colored green, while locations of machines with low smart band coverage may be colored red or another contrasting color. Other annotations, such as visual annotations, may also be used. A user may select a machine at one location and drag the selected machine to the location of the second machine, effectively configuring a smart band for a second machine to correspond to the smart band for a first machine. In this manner, a user may configure multiple smart band data collection templates, such as for newly added machines or new industrial environments.

In embodiments, various smart band configurations and selections may be stored for use across the data collection platform. For example, they may be used to select sensing templates, routing templates, device provisioning, etc., and to direct sensor placement by personnel or machines, such as autonomous or remotely controlled drones.

In an embodiment, the smart band user interface may present a map of the industrial environment, including industrial machines, machine-specific data collectors, mobile data collectors (robots and humans), etc. The user can view a list of smart band data collection actions to be performed and select a data collection resource set to perform the collection. In one example, a guided mobile robot may be equipped with a data collection system for collecting data for multiple smart band data sets. The user may view the industrial environment with which the robot is associated and assign the robot to perform a smart band data collection activity by selecting the robot, a smart band data collection template, and a location within the industrial environment, such as a machine or part of a machine. The user interface may provide the status of the collection acceptance so that the user can be informed when data collection is complete.

In embodiments, the smart band operation management user interface may include a presentation of smart band data collection activities, an analysis of the results, actions taken based on the results, suggested changes to smart band data collection (e.g., adding sensors to a smart band collection template, increasing the data collection period for a template-specific collection activity), etc. In response to a user attempting to make a change to a smart band data collection template, such as relaxing a threshold for performing smart band data collection, the user interface may facilitate "what if" analysis by presenting potential impacts on reliability, cost, resource utilization, data collection trade-offs, maintenance schedule impacts, risk of failure (increase/decrease), etc. In embodiments, a user may select or input a target budget for preventive maintenance per unit of time (e.g., month, quarter, etc.) into the user interface, and an expert system in the user interface may recommend smart band data collection templates and thresholds to adhere to the budget.

In embodiments, the smart band user interface may facilitate a user configuring the system for smart band data collection in an industrial environment. The user interface may include a display of industrial machine components, such as motors, linkages, bearings, etc., from which the user can select. In response to such selection, the expert system, in conjunction with the user interface, may present a list of potential fault conditions associated with the monitored components. The user may select one or more conditions to monitor. The user interface may present the conditions to be monitored as a set for the user's approval. The user may indicate approval of the selected conditions within the set or set monitors. Following the user's selection/approval of one or more conditions to monitor, the user interface may display a map of associated sensors available in the industrial environment for collecting data as a smart band group of sensors. The associated sensors may be associated with one or more components (e.g., the component originally selected by the user), one or more fault conditions, etc.

In embodiments, the expert system may compare relevant sensors in the environment with a set of preferred sensors for smart band monitoring of the fault condition and provide feedback to the user, such as a confidence level for performing smart band monitoring based on the available sensors for the fault condition. The user may evaluate the presented fault condition and smart band analytical information and take an action in the user interface, such as approving the relevant sensors. In response, a smart band data collection template may be created for configuring the data collection system. In embodiments, the smart band data collection template may be created independently of user approval. In such embodiments, the user may explicitly or implicitly indicate approval of the created template via their approval of the smart band analytical information.

In embodiments, the smart band's user interface, in conjunction with an expert system, may present candidate portions of industrial machinery in an industrial environment for smart band condition monitoring based on information such as manufacturer specifications, statistics derived from real-world experience with similar industrial machinery, etc. In embodiments, the user interface may allow a user to select specific aspects of the smart band's data collection and analysis process, including, for example, the degree of reliability/failure risk to monitor (e.g., near failure, best performance, industry average, etc.). In response, the expert system may adjust aspects of the smart band analysis, such as tolerance ranges to monitor, monitoring frequency, data collection frequency, data collection volume, prioritization of data collection activities (e.g., effectively prioritizing the smart band's data collection templates), weighting of data from sensors (e.g., specific sensors within a group, sensor type, etc.), etc.

In an embodiment, the user interface of the smart band may be configured to allow the expert system to recommend one or more smart bands to implement based on a set of comparison data that the user may prioritize, such as industry average data, industry best data, nearby comparable machines, or machines with the most similar configuration. Based on the weighting of the comparison data, the expert system uses the user interface to recommend one or more smart band templates to the user that are consistent with the weighting, and the user can take an action in the user interface, such as approving one or more of the recommended templates for use.

In embodiments, the user interface for configuring the placement of sensors in an industrial environment may include recommendations from an industrial environment equipment supplier (e.g., a manufacturer, wholesaler, distributor, dealer, third-party consultant, etc.) for a group of sensors to be included to perform smart band analysis of components of the industrial equipment. This information is presented to the user as a data collection template, and the user may indicate acceptance/approval, such as by placing a graphic representing the template on a portion of the industrial equipment.

In embodiments, the smart band discovery portal may facilitate the sharing of smart band-related information, such as recommendations, actual use cases, and smart band data collection and processing. The discovery portal may be embodied as a panel in the smart band's user interface.

In embodiments, a smart band evaluation portal can facilitate evaluation of smart band-based data collection and analysis. Content that may be presented in such a portal may include depictions of applications of existing smart band templates for one or more industrial machines, industrial environments, industries, etc. A smart band value may be assigned to each smart band within the portal based, for example, on past use and results. The smart band evaluation portal may also include visualizations of candidate sensors for inclusion in the smart band's data collection template based on various factors, including assigned value, preventative maintenance costs, monitored fault conditions, etc.

In an embodiment, a graphical user interface for a smart band associated with a system for data collection in an industrial environment may be deployed for an industrial component, such as a factory-based air conditioning unit. The user interface for data collection for smart band analysis of air conditioning units may facilitate graphical configuration of a smart band data collection template for a particular air conditioning system installation. In an embodiment, major components of an air conditioning system, such as a compressor, condenser, heat exchanger, ductwork, refrigerant regulator, filter, and fan, may be depicted in the user interface along with corresponding sensors for the particular air conditioning system installation. A user may select one or more of these components in the user interface to configure the system for smart band data collection. In response to a user selecting, for example, a refrigerant compressor, sensors associated with the compressor may be automatically identified in the user interface. A user may be presented with a recommended data collection template for conducting smart band data collection for the selected compressor. Alternatively, a user may request collection template suggestions from a community of smart band users, such as via a smart band template sharing panel in the user interface. Once a template is selected, the user interface can provide the user with customization options such as collection frequency, degree of reliability to monitor, etc. Once the template is finally approved, the user interface can interact with the installed air conditioning system's data collection system (if such a system is available) to implement the data collection template and show the user the results of the template implementation. The user can then finally approve the template to be used for the air conditioning device.

In an embodiment, a graphical user interface for a smart band associated with a system for data collection in an industrial environment may be deployed for an oil and gas refinery-based chiller. The user interface for the system for data collection for smart band analysis of refinery-based chillers may facilitate graphical configuration of a smart band data collection template for a particular refinery-based chiller installation. In an embodiment, the major components of a refinery-based chiller, including heat exchangers, compressors, water conditioners, etc., may be depicted in the user interface along with corresponding sensors for the particular refinery-based chiller installation. A user may select one or more of these components in the user interface to configure the system for smart band data collection. In response to a user selecting, for example, a water conditioner, sensors associated with the water conditioner may be automatically identified in the user interface. A user may be presented with a recommended data collection template to perform smart band data collection for the selected component. Alternatively, a user may request suggested collection templates from a community of smart band users, such as via a smart band template sharing panel in the user interface. Once a template is selected, the user interface may provide the user with customization options, such as frequency of collection, degree of reliability to monitor, etc. Once the template is finally approved, the user interface can interact with the installed refinery-based chiller's data collection system (if such a system is available) to implement the data collection template and present the results of the template's implementation to the user, who may then finally approve the template for use with the refinery-based chiller.

In an embodiment, a graphical user interface for a smart band associated with a system for data collection in an industrial environment may be deployed for an automotive production line robotic assembly system. The user interface for data collection for smart band analysis of a production line robotic assembly system may facilitate graphical configuration of a smart band data collection template for a particular production line robotic assembly system installation. In an embodiment, the user interface provides key components of the production line robotic assembly system, including motors, linkages, tool handlers, positioning systems, etc., along with corresponding sensors for a particular installation of the production line robotic assembly system. A user may select one or more of these components in the user interface to configure the system for smart band data collection. In response to a user selection, for example, a robot linkage sensor associated with a robot linkage may be automatically identified in the user interface. The user may be presented with a recommended data collection template for performing smart band data collection for the selected component. Alternatively, the user may request collection template suggestions from a community of smart band users, such as via a smart band template sharing panel in the user interface. Once a template is selected, the user interface may provide the user with customization options, such as collection frequency and the degree of reliability to monitor. Once the template is finally approved, the user interface can interact with a data collection system of the installed production line robotic assembly system (if such a system is available) to implement the data collection template and present the results of the implementation of the template to the user, who may then finally approve the template for use with the production line robotic assembly system.

In an embodiment, a graphical user interface for a smart band associated with a system for data collection in an industrial environment may be deployed for an automotive production line robotic assembly system. The user interface for a system for data collection for smart band analysis of a production line robotic assembly system may facilitate graphical configuration of a smart band data collection template for a particular production line robotic assembly system installation. In an embodiment, the major components of a construction site boring machine, such as a cutterhead, control system, debris handling and transport components, and precast concrete delivery and placement subsystem, which may themselves have many components, may be depicted in the user interface, along with corresponding sensors for the particular installation of the production line robotic assembly system. A user may select one or more of these components in the user interface to configure the system for smart band data collection. In response to a user selecting, for example, a debris handling component, sensors associated with the debris handling component, such as a conveyor, may be automatically identified in the user interface. A user may be presented with a recommended data collection template for performing smart band data collection for the selected component. Alternatively, a user may request collection template suggestions from a community of smart band users, such as via a smart band template sharing panel in the user interface. Once a template is selected, the user interface can provide the user with customization options such as frequency of collection, degree of reliability to monitor, etc. Once the template is finally approved, the user interface can interact with the data collection system of the installed production line robotic assembly system (if such a system is available) to implement the data collection template and present the results of the implementation of the template to the user. The user may then finally approve the template for use with the production line robotic assembly system.

Referring to FIG. 111, an exemplary user interface for smart band configuration of a system for data collection in an industrial environment is depicted. The user interface 11200 may include an industrial environment visualization portion 11202, in which one or more sensors, machines, etc. may be depicted. Each sensor, machine, or portion thereof (e.g., motor, compressor, etc.) may be selectable as part of the smart band configuration process. Similarly, each sensor, machine, or portion thereof may be visually highlighted during the smart band configuration process, such as in response to a user selection or by being automatically identified as part of a group of smart band sensors. The user interface may also include a smart band selection portion 11204 or panel in which selectable elements depict the smart band's indicators, failure modes, etc. User selection of a symptom, failure mode, etc. may highlight the corresponding component, sensor, machine, etc. in the industrial visualization portion. The user interface may also include a customization panel 11206 that allows the user to adjust attributes of the selected smart band, such as tolerance ranges, monitoring frequency, etc.

(1) In an embodiment, a system is provided that includes a selectable graphical element that facilitates selection of a representation of an industrial machine component from an industrial environment deployed with a plurality of sensors from which a data collection system collects data for a system for which a user interface enables interaction, and a selectable graphical element that represents a portion of the plurality of sensors that facilitates selection of the sensors to form a data collection subset of sensors in the industrial environment. (2) The system described in (1), wherein selection of the sensors that form the data collection subset results in a data collection template adapted to facilitate configuration of a data routing and collection system to collect data from the data collection subset of sensors. (3) The system described in (1), wherein the user interface includes an expert system that analyzes a user's selection of a graphical element that facilitates component selection and adjusts the selectable graphical element that represents a portion of the plurality of sensors to activate only sensors associated with the component associated with the selected graphical element. (4) The system described in (1), wherein the selectable graphical element that facilitates selection of an industrial machine component further facilitates presentation of a plurality of data collection templates associated with the component. (5) The system described in (1), wherein a portion of the plurality of sensors constitutes a smart band group of sensors. (6) The system of (5), wherein the sensor group of the smart band is composed of sensors for the component of the industrial machine selected by the selectable graphic element. (7) A system comprising: an expert graphical user interface including a representation of a plurality of components of an industrial machine from an industrial environment in which a plurality of sensors are located, wherein a data collection system collects data for a system with which the user interface enables interaction, and at least one representation of the plurality of components is selectable by a user in the user interface; a database of failure modes of the industrial machine; and a database search function that searches the database of failure modes for a mode corresponding to the user's selection of a component of the plurality of components. (8) The system of (7), wherein the database of conditions associated with the failure mode. (9) The system of (8), wherein the database of conditions includes a list of sensors of the industrial environment associated with the condition. (10) The system of (9), wherein the database search function further searches the database of conditions for sensors corresponding to at least one condition and displays the sensor in the graphical user interface. (11) The system of (7), wherein a user selection of a component of a plurality of components triggers a data collection template for configuring a data routing and collection system to automatically collect data from sensors associated with the selected component. (12) A method comprising the steps of: presenting, in an expert graphical user interface, a list of reliability measurements for an industrial machine; facilitating a user selection of a reliability measurement from the list; presenting a display of a smart band data collection template associated with the selected reliability measurement; and, in response to a user indication of accepting the smart band data collection template, configuring the data routing and collection system to collect data from a plurality of sensors in an industrial environment in response to detecting that a data value from one of the plurality of sensors is outside an acceptable range of data values. (13) The method of (12), wherein the reliability measurements include one or more of the following: industry average data, manufacturer specifications, manufacturer material specifications, manufacturer recommendations, etc. (14) The method of (13), wherein the manufacturer's specifications include at least one of cycle count, operating hours, maintenance recommendations, maintenance schedules, operational limits, material limits, and warranty terms. (15) The method of (12), wherein the reliability measurements are correlated to failures selected from the list consisting of stress, vibration, heat, wear, ultrasonic signatures, and operational deflection geometry effects. (16) The method of (12), further comprising relating sensors in an industrial environment to the manufacturer's specifications. (17) The method of (16), wherein correlating includes matching a duty cycle specification to a sensor that detects rotation of a moving part. (18) The method of (16), wherein the correlation includes matching a temperature specification to a thermal sensor positioned to sense an environmental temperature near the industrial machine. (19) The method of (16), further comprising dynamically setting tolerances for the data values based on the results of the correlation. (20) The method of (16), further comprising automatically determining one of the plurality of sensors for detecting the data value outside the acceptable range based on the result of the correlation.

Back-calculation, such as determining the likely root cause of a failure, can benefit from a graphical approach that facilitates visualization of an industrial environment, machine, or part thereof, with an indication of the sources providing data, such as sensors, related to the failure. A failing component, such as a bearing, may be associated with other components, such as a shaft or motor. Sensors monitoring the condition of bearings and related components can provide information on the possible causes of the failure. Such information can also be useful in suggesting indicators, such as changes in sensor output, to monitor or avoid future failures. A system that facilitates a graphical approach for back-calculation can interact with a sensor data collection and analysis system to at least partially automate aspects related to data collection and processing determined from the back-calculation process.

In an embodiment, a system for data collection in an industrial environment may include a user interface in which portions of an industrial machine associated with a condition of interest, such as a fault condition, are presented on an electronic display along with sensor data types contributing to the condition of interest, data collection points (e.g., sensors) associated with the machine portions that monitor the data types, and datasets from the data collection points that were collected and used to determine the condition of interest. The user interface displays the data collection points (e.g., sensors), the set of data collected from the data collection points and used to determine the condition of interest, and annotations of sensors that provided exceptional data, such as out-of-tolerance data, that may have been used to determine the condition of interest. The user interface may also access a machine description that facilitates determining and visualizing associated parts, such as bearings, shafts, brakes, rotors, and motor housings, that contribute to a function, such as rotating a turbine. The user interface may also access datasets that associate sensors and components located on the machine. Information included in the datasets may include sensor descriptions, their functions, the conditions sensed by each sensor, and typical or acceptable ranges for values output by the sensors. The information in the datasets may also identify multiple potential paths for sensor data to be delivered to a data collector in the system for data collection in an industrial environment. The user interface may also access datasets containing data collection templates used to configure the data collection system to collect data from sensors for a specific purpose (e.g., collecting data from a group of sensors into a sensor dataset suitable for determining a machine condition, such as the degree of shaft slippage relative to a motor).

In embodiments, a back-calculation method for determining candidate sources of data contributing to the condition of an industrial machine may include following a data collection path determined from a configuration and operational template of a data collection system for collecting data from sensors located on the industrial machine that were in place at the time the contributing data was collected. The configuration and operational template may describe signal routing, multiplexing, collection timing, etc., for data from a group of sensors. The group of sensors may be located locally on a component such as a bearing, or may be more geographically distributed, such as sensors obtaining information about a bearing and its associated components. In embodiments, the data collection template may be configured to collect and process data to detect a specific condition of the industrial machine. Thus, the template may be correlated to a condition such that performing a back-calculation of the condition of interest is guided by the correlated template. Data collected based on the template may be compared to acceptable ranges for data from various sensors. Data outside the acceptable ranges may indicate a potential root cause of the unacceptable condition. In embodiments, suspected sources of data collection may be determined from the candidate data collection sources based on a comparison of the data collected from the candidate data sources to the acceptable ranges for the data collected from each candidate data source. By visualizing signal paths, potential sensors, and suspect data sources based on these back-calculations, users can gain valuable insight into the possible root causes of failures and other issues.

In an embodiment, the back-calculation method includes visualizing paths of data contributing to a detected fault condition in an industrial environment by applying back-calculation to determine sources of the contributing data, the visualization appearing as highlighted data paths in a visual representation of a data collection system of the industrial machine. In an embodiment, determining the sources of the data may be based on a data collection and processing template for the fault condition. The template may include the configuration of the data collection system when data from the determined sources was collected by the data collection system.

When a failure occurs, or when the condition of a portion of a machine in an industrial environment reaches a critical point before failure, such as detected by preventive maintenance, reverse calculation may help determine collecting information that may be useful in preventing the failure and/or improving system performance (e.g., avoiding substantial degradation in the operation of a component). Visualizing data collection sources, components associated with a condition, algorithms that may determine the potential onset of a condition, and the like may facilitate the preparation of a data collection template for configuring data sensing, routing, and collection resources in a system for collecting data in an industrial environment. In embodiments, configuring a data collection template for a system for collecting data in an industrial environment may be based on reverse calculation applied to a machine failure, identifying candidate conditions to monitor to prevent machine failure. The resulting template may identify sensors to monitor, the configuration of sensor data collection paths, the frequency and amount of data to collect, acceptable levels of sensor data, and the like. With access to information about the machine, such as which parts are closely related to other parts and the sensors that collect data from parts within the machine, a configuration template for the data collection system may be automatically generated when parts of interest are identified.

In embodiments, a user interface may include a graphical representation of data sources as a logical arrangement of sensors that may contribute data to a calculation of the state of a machine in an industrial environment. The logical arrangement may be based on sensor type, data collection template, condition, algorithm for determining the condition, etc. As an example, a user may desire to display all temperature sensors that may contribute to a condition such as a component failure in an industrial environment. The user interface may communicate with a database of machine-related information, such as the components associated with the condition, the sensors on those components, and the types of those sensors, to determine a subset of sensors that measure temperature. The user interface highlights those sensors. The user interface may launch selectable graphical elements for those sensors, and upon user selection, may display data associated with those sensors, such as the sensor type, range of data collected, tolerance ranges, and actual data values collected under given conditions, in a pop-up panel or the like. Similar functionality of the user interface may also be applied to physically arranged sensors, such as all sensors associated with a motor, a boring machine cutting head, a wind turbine, etc.

In embodiments, third parties, such as component manufacturers, remote maintenance organizations, etc., may benefit from access to the back-calculation visualization. Granting third parties access to back-calculation information, such as visualization of sensors that contributed unacceptable data values to condition calculations and sensor locations, may be a user-executable option in a user interface for a graphical approach to back-calculation as described herein. A list of manufacturers of machines, subsystems, individual components, sensors, data collection systems, etc., along with remote maintenance organizations, etc., may be presented in one portion of the user interface. A user of the interface may select one or more of these third parties and grant them access to at least some of the available data and visualizations. Selecting one or more of these third parties may also present statistical information about the third parties, such as the occurrence and frequency of access to data to which the third party is authorized to access, access requests from the third party, etc.

In embodiments, reverse-analysis visualization can be combined with machine learning to utilize the reverse-analysis and visualization to derive potential new diagnoses for conditions, such as fault conditions, or to derive new conditions to monitor. A user may interact with the user interface to provide feedback to the machine learning technology to improve results, such as indicating the success or failure of attempts to prevent a failure via a particular data collection and processing solution (e.g., a template).

In an embodiment, a method and system for back-calculating data collected in a system for data collection in an industrial environment may be applied to a concrete pouring device in a construction site application. The concrete pouring device may be composed of several active components, including a mixer including a water and aggregate supply system, a mixing control system, a mixing motor, a directional control device, concrete sensors, etc., a concrete pump, a delivery system, flow control, and on/off control. Back-calculating failures or other conditions of active or passive components of the concrete pouring device can benefit from visualization of the device, its components, sensors, and other points where data is collected (e.g., controllers, etc.). When back-calculating a flow disturbance condition, visualization of data/conditions collected from sensors associated with the concrete pump, etc., can alert the user to pump conditions that may contribute to the flow disturbance. Flow rate may decrease simultaneously with an increase in pump temperature. This may be visualized, for example, by displaying flow sensor data and pump temperature sensor data in a user interface. This correlation may be noted by an expert system or a user observing the visualization, and corrective action may be taken.

In an embodiment, the method and system for back-calculating data collected in a system for data collection in an industrial environment may be applied to a drilling and extraction system in a mining application. The drilling and extraction system may be composed of multiple active subsystems, including a cutting head, a pneumatic drill, a jackhammer, an excavator, a transport system, etc. Back-calculating a failure or other condition of an active or passive component of the drilling and extraction system can benefit from visualization of the equipment, its components, sensors, and other points (e.g., controllers, etc.) where data is collected. When back-calculating a pneumatic line fault condition, visualization of data/conditions collected from sensors associated with the pneumatic drill, etc., can alert a user to drill conditions that may contribute to the line failure. Line pressure may increase simultaneously with a change in the drill condition. This can be visualized, for example, by displaying line pressure sensor data and data from sensors associated with the drill in a user interface. This correlation can be noted by an expert system or a user observing the visualization, and corrective action can be taken.

In embodiments, a method and system for back-calculating data collected in systems that collect data in industrial environments may be applied to cooling towers in oil and gas production environments. A cooling tower may consist of several active components, such as a water supply system, pumps, valves, temperature-controlled temperature control devices, operations, storage systems, and mixing systems. Back-calculating a failure or other condition of an active or passive component of a cooling tower can benefit from visualization of the equipment, its components, sensors, and other points from which data is collected (e.g., controllers, etc.). When back-calculating a circulating pump failure condition, visualization of data/conditions collected from sensors and other related to the cooling tower can alert a user to conditions in the cooling tower that may contribute to the pump failure. The temperature of the feedwater may increase at the same time that the output of the circulating pump decreases. This can be visualized, for example, by displaying feedwater temperature sensor data and pump output rate sensor data in a user interface. This correlation can be noted by an expert system or a user observing the visualization, allowing corrective action to be taken.

In an embodiment, a method and system for back-calculating data collected in a system for data collection in an industrial environment may be applied to a circulating water system in a power generation application. The circulating water system may consist of multiple active components, including pumps, storage systems, water chillers, etc. To back-calculate failures or other conditions in active or passive components of the circulating water system, it is useful to visualize the equipment, components, sensors, and other points (e.g., controllers) from which data is collected. When back-calculating a circulating water temperature fault condition, visualizing data/conditions collected from sensors associated with the chiller, etc., can alert a user to chiller conditions that may contribute to the temperature condition failure. The circulating water temperature may increase with an increase in core water cooler temperature. This may be visualized, for example, by displaying circulating water temperature sensor data and water chiller temperature sensor data in a user interface. This correlation may be noted by an expert system or a user observing the visualization, and corrective action may be taken.

With reference to FIG. 112, a graphical approach 11300 for back-calculation is depicted. Components of an industrial environment may be depicted on a map 11302 of the environment. Components that may have a history of failure (either in this installation or other installations) may be highlighted. In response to a selection of one of these components (e.g., by a user making the selection), sensors for the selected part and associated components may be highlighted, including signal routing paths for data from those associated sensors to a data collector. Additionally, highlighting sensors that have collected unacceptable data may indicate potential causes of failure of the selected part. The relationships between parts are based, at least in part, on machine configuration metadata. The relationship between specific sensors and fault conditions may be based, at least in part, on data collection templates associated with the part and/or fault condition.

(1) In one embodiment, a user interface for a system adapted to collect data in an industrial environment is provided, the user interface including: a plurality of graphical elements representing mechanical parts of an industrial machine, the plurality of graphical elements being associated with conditions of interest generated by a processor executing a data analysis algorithm; a plurality of graphical elements representing data collectors of the system adapted to collect data in an industrial environment, the plurality of graphical elements having collected data used in the data analysis algorithm; and a plurality of graphical elements representing sensors used to capture data used in the data analysis algorithm, the plurality of graphical elements being indicated by visual highlighting in the user interface for sensors that provided data outside an acceptable range of data values. (2) The system described in (1), wherein the conditions of interest are selected from a list of conditions of interest presented in the user interface. (3) The system described in (1), wherein the condition of interest is at least one mechanical failure of a mechanical part of the industrial machine. (4) The system described in (1), wherein the mechanical part includes at least one of a bearing, a shaft, a rotor, a housing, and a linkage of the industrial machine. (5) The system of (1), wherein an acceptable range of data values is available for each sensor. (6) The system of (1), further comprising highlighting a data collector that collected data outside the acceptable range of data values. (7) The system of (1), further comprising a data collection system configuration template that facilitates configuring the data collection system to collect data for calculating a condition of interest. (8) A method for determining potential sources of a condition of interest, comprising: identifying a data collection template for configuring data routing and collection resources in a system for collecting data in an industrial environment, the template being used to collect data that contributes to a calculation of the condition of interest; determining a route from the data collector for the collected data to a sensor that generated the collected data by analyzing the data collection template; comparing the data collected by the sensor with an acceptable range of data values for data collected by the sensor; and highlighting, in an electronic user interface depicting at least one of the industrial environment and the sensors, that at least one sensor that generated data that contributed to the calculation of the condition of interest is outside the acceptable range of data for that sensor. (9) The method of (8), wherein the condition of interest is a fault condition. (10) The method of (8), wherein the data collection template includes configuration information for at least one of an analog crosspoint switch, a multiplexer, a hierarchical multiplexer, a sensor, a collector, and a data storage device of a system adapted to collect data in an industrial environment. (11) The method of (8), wherein highlighting in the industrial environment includes highlighting at least one sensor and at least one route of data from the sensor to a data collector of the system for collecting data in the industrial environment. (12) The method of (8), wherein comparing the data collected by the sensors with an acceptable range of data values includes comparing the data collected by each sensor with an acceptable range of data values specific to each sensor. (13) The method of (8), wherein calculating the condition of interest comprises calculating a trend of data from at least one sensor. (14) The method of (8), wherein the acceptable range of values comprises a trend of data values. (15) A method for visualizing routes of data contributing to a condition of interest detected in an industrial environment, the method comprising: The method includes applying back-calculation to a condition of interest to determine a data collection system configuration template associated with the condition of interest, analyzing the template to determine a configuration of the data collection system for collecting data for detecting the condition of interest, presenting a map of the data collection configured by the template in an electronic user interface, and highlighting in the electronic user interface a path in the data collection system reflecting a path of data from at least one sensor to at least one data collection device for data contributing to the calculation of the condition of interest. (16) The method of (15), wherein the data collection system configuration template includes configuration information for at least one resource located in the data collection system selected from the list consisting of an analog crosspoint switch, a multiplexer, a hierarchical multiplexer, a data collector, and a sensor. (17) The method of (15), further comprising generating a target diagnosis for the condition of interest by applying machine learning to the back-calculation. (18) The method of (15), further comprising highlighting in the electronic user interface any sensors whose data used in the calculation of the condition of interest is outside an acceptable range of sensor data values. (19) The method of (15), wherein the condition of interest is selected from a list of conditions of interest presented on a user interface. (20) The system of (15), wherein the condition of interest is a mechanical failure of at least one mechanical part of the industrial environment. (21) The system of (15), wherein the mechanical part includes at least one of a bearing, a shaft, a rotor, a housing, and a linkage of the industrial environment.

In an embodiment, a system for data collection in an industrial environment may route data from multiple sensors in the industrial environment to a wearable tactile stimulator that presents the data from the sensors as human-detectable stimuli including at least one of touch, vibration, heat, sound, and force. In an embodiment, the tactile stimuli represent effects on machinery resulting from the sensed data. In an embodiment, a bending effect may be presented as bending a finger in a haptic glove. In an embodiment, a vibration effect may be presented as vibrating a haptic armband. In an embodiment, a heating effect may be presented as an increase in temperature in a haptic wristband. In an embodiment, an electrical effect (e.g., overvoltage, current, etc.) may be presented as a change in sound in a phasic audio system.

In embodiments, a haptic user interface for an industrial machinery operator may be adapted to provide the operator with haptic stimuli responsive to the operator's control of the machine, the stimuli indicating an effect on the machine as a result of the operator's control and a resulting interaction with objects in the environment. In embodiments, a sensed state of the machine that is out of tolerance may be presented to the operator through the haptic user interface. In embodiments, a sensed state of the machine that is within tolerance may not be presented to the operator through the haptic user interface. In embodiments, a sensed state of the machine that is within tolerance may be presented as a natural language expression of confirmation of the operator's control. In embodiments, at least a portion of the haptic user interface is worn by the operator. In embodiments, the wearable haptic user interface device may include a device that exerts a force along an outer leg portion of the device operator's uniform. As a vehicle controlled by the operator approaches an obstacle along the lateral direction of the vehicle, an inflatable bellows may inflate and apply pressure against the operator's leg closest to the side of the vehicle approaching the obstacle. The bellows may continue to inflate, thereby applying additional pressure to the operator's leg in response to the approach of the obstacle. Additionally, pressure may be pulsed if contact with an obstacle is imminent. In another example, an operator's armband may vibrate in conjunction with vibrations generated by a portion of the vehicle the operator is controlling. These are merely examples and are not intended to limit the manner in which a wearable haptic feedback user device may be controlled to indicate conditions sensed by a system for data collection in an industrial environment.

In embodiments, a tactile user interface safety system worn by a user in an industrial environment may be adapted to indicate proximity of equipment in the environment to the user by stimulating a portion of the user with at least one of pressure, heat, impact, electrical stimulation, etc., where the portion of the user that is stimulated may be closest to the equipment. In embodiments, at least one of the type, intensity, duration, and frequency of the stimulation indicates a risk of injury to the user.

In embodiments, a wearable haptic user interface device that can be worn by a user in an industrial environment can broadcast its location and associated information upon detection of an alert condition in the industrial environment. The alert condition may be proximate to the user wearing the device or may be related to the user wearing the device without being proximate. The user may be an emergency responder, and upon detection of a situation requiring an emergency response, the user's haptic device may broadcast the user's location to facilitate rapid access to or by the user to an emergency location. In embodiments, alert conditions determined from monitoring sensors on industrial machinery may be presented to the user as haptic stimuli, with the severity of the alert corresponding to the level of the stimuli. In embodiments, the level of the stimuli may be varied based on the severity of the alert, with the corresponding stimuli continuing, repeating, or escalating, optionally including activating multiple stimuli simultaneously, sending alerts to additional haptic users, etc., until an acceptable response is detected, e.g., via a haptic UI. The wearable haptic user device may be adapted to communicate with other haptic user devices to facilitate detection of an acceptable response.

In embodiments, wearable haptic user interfaces for use in industrial environments can include gloves, rings, wristbands, watches, armbands, headgear, belts, necklaces, shirts (e.g., uniform shirts), footwear, pants, ear protectors, safety glasses, vests, overalls, coveralls, and any other article of clothing or accessory that can be adapted to provide haptic stimulation.

In embodiments, the stimuli of the wearable haptic device may be correlated to sensors in the industrial environment. Non-limiting examples include vibration of the wearable haptic, such as increasing or decreasing the temperature of the wearable haptic device in response to vibrations detected in the industrial environment, or generating a sound whose pitch changes in response to changes in the sensed electrical signal. In embodiments, the severity of the stimuli of the wearable haptic device may be correlated to an aspect of the condition sensed in the industrial environment. Non-limiting examples include moderate or short-term vibrations when the degree of sensed vibration is low, strong or long-term vibration stimulation for increased sensed vibration, and aggressive, pulsed, and/or multi-modal stimulation for high amounts of sensed vibration. Stimuli of the wearable haptic device may also include lighting (e.g., flashing, color changing), sound, smell, tactile output, haptic device movement (e.g., balloon inflation/deflation, joint segment extension/contraction), force/impact, etc.

In an embodiment, a system for data collection in an industrial environment may interface with a wearable tactile feedback user device to relay data collected from a fuel processing system in a power generation application to a user via tactile stimuli. Fuel handling for power generation may involve solid fuels such as wood chips, stumps, forest residues, sticks, energy willow, peat, pellets, bark, straw, agrobiomass, coal, and solid recovered fuels. The processing system may include a receiving station where the fuel can also be sampled, a preparation station where wood-based fuels are crushed or chipped, or waste-based fuels are shredded. The fuel processing system may also include a storage and transport system, a feeding and ash removal system, and the like. A wearable tactile user interface device can be used in fuel processing systems by providing feedback to the operator on the status of an otherwise isolated processing environment. Sensors can detect the operating surface of a solid fuel feed screw system. Conditions such as screw rotation speed, fuel weight, and fuel type may be translated into tactile stimuli for the user, allowing the user to use their hands and attention to operate the fuel delivery system.

In embodiments, a system for data collection in an industrial environment may interface with a wearable haptic feedback user device to relay data collected from the suspension system of a truck and/or vehicle application to a user via haptic stimuli. The haptic simulation may be correlated to conditions being sensed by the vehicle suspension system. In embodiments, road roughness may be detected and converted into stimuli such as vibrations in a wearable haptic armband. In embodiments, suspension forces (contraction and rebound) may be converted into stimuli that present a scaled-down version of the forces to the user via a wearable haptic vest.

In embodiments, a system for data collection in an industrial environment may interface with a wearable haptic feedback user device to relay data collected from a hydroponic system in an agricultural application to a user via haptic stimuli. In embodiments, sensors in the hydroponic system, such as temperature, humidity, water level, plant size, and carbon dioxide/oxygen levels, may be converted into haptic stimuli on the wearable device. As an operator wearing haptic feedback wear walks through a hydroponic agricultural facility, sensors in proximity to the operator may signal relevant information to the haptic feedback wear, such as temperature or a measurement of actual temperature versus desired temperature, which the haptic wear can convert into haptic stimuli. As an example, a wristband may include a thermal stimulator that can rapidly change temperature to track temperature data or a derivative thereof from sensors in the agricultural environment. As a user walks through the facility, the haptic feedback wristband may change temperature to indicate the degree to which nearby temperatures conform to an expected temperature.

In embodiments, a system for data collection in an industrial environment may interface with a wearable haptic feedback user device to relay data collected from a robotic positioning system in an automated production line application to a user via haptic stimuli. The haptic feedback may include receiving a positioning system indicator of accuracy and converting it to an audible signal if the accuracy is acceptable, or to another type of stimulus if the accuracy is unacceptable.

Referring to FIG. 113, a wearable tactile user interface device is depicted for providing a user with tactile stimuli responsive to data collected in an industrial environment by a system adapted to collect data in the industrial environment. The system for data collection 11402 in the industrial environment 11400 may include multiple sensors. Data from the sensors may be collected and analyzed by a computing system. Results of the analysis may be wirelessly communicated to one or more wearable tactile feedback stimulators 11404 worn by users associated with the industrial environment. The wearable tactile feedback stimulators may interpret the results, convert them into a form of stimulation based on a mapping of the tactile stimulation to the sensed state, and generate the stimulation.

(1) In an embodiment, a system for data collection in an industrial environment includes: a plurality of wearable tactile stimulators that generate stimuli selected from a list of stimuli consisting of tactile, vibration, heat, sound, force, smell, and motion; and a plurality of sensors disposed in the industrial environment that sense environmental conditions. A processor logically disposed between the plurality of sensors and the wearable tactile stimulators receives data representing the sensed conditions from the sensors, determines at least one tactile stimulus corresponding to the received data, and sends at least one signal to instruct the wearable tactile stimulator to generate the at least one stimulus. (2) The system described in (1), wherein the tactile stimulus represents an effect on machinery in the industrial environment due to the conditions. (3) The system described in (2), wherein a bending effect is presented as bending a tactile device. (4) The system described in (2), wherein a vibration effect is presented as vibrating a haptic device. (5) The system described in (2), wherein a heating effect is presented as an increase in temperature of a haptic device. (6) The system of (2), wherein the electrical effect is presented as a change in sound generated by the haptic device. (7) The system of (2), wherein at least one of the plurality of wearable tactile stimulators is selected from the list consisting of gloves, rings, wristbands, watches, armbands, headgear, belts, necklaces, shirts, footwear, pants, overalls, coveralls, and safety goggles. (8) The system of (2), wherein the at least one signal includes a warning of a condition of interest in an industrial environment. (9) The system of (8), wherein at least one stimulus generated in response to the warning signal is repeated by at least one of the plurality of wearable tactile stimulators until an acceptable response is detected. (10) A tactile user interface for an industrial machine operator adapted to provide tactile stimuli to an operator in response to control of a machine by the operator based on at least one sensed state of the machine indicative of an impact on the machine as a result of the operator's control and a resulting interaction with an object in the environment. (11) The user interface of (10), wherein a sensed condition of the machine that exceeds an acceptable range of data values for the condition is presented to the operator through a tactile user interface. (12) The user interface of (10), wherein a sensed condition of the machine that is within an acceptable range of data values for the condition is presented as a natural language expression of confirmation of operator control via an audio-tactile stimulator. (13) The user interface of (10), wherein at least a portion of the tactile user interface is worn by the operator. (14) The system of (10), wherein a vibration-sensed condition is presented as a vibration stimulus by the tactile user interface. (15) The system of (10), wherein a temperature-sensed condition is presented as a thermal stimulus by the tactile user interface. (16) A haptic user interface safety system worn by a user in an industrial environment, the interface adapted to indicate proximity of equipment in the environment to the user by tactile stimulation via a portion of the haptic user interface closest to the equipment, at least one of type, intensity, duration, and frequency of the stimulation indicating a risk of injury to the user. (17) The haptic user interface of (16), wherein the tactile stimulation is selected from the list consisting of pressure, heat, impact, and electrical stimulation. (18) The haptic user interface of (16), further comprising a wireless transmitter that broadcasts the user's location. (19) The haptic user interface of (18), wherein the wireless transmitter broadcasts the user's location in response to the user indicating proximity to the equipment. (20) A haptic user interface as described in (16), wherein the proximity of equipment in the environment to the user is based on sensor data provided to the haptic user interface from a system adapted to collect data in an industrial environment, and the system is adapted based on a data collection template associated with a safety state of the user in the industrial environment.

In embodiments, a system for data collection in an industrial environment may facilitate presenting graphical elements depicting sensed data of an industrial machine on an augmented reality (AR) display. The graphical elements may be adapted to represent a location on a scale of acceptable values for the sensed data. The graphical elements may be positioned in the vicinity of a sensor detected within the augmented field of view that captured the sensed data on the AR display. The graphical elements may be colors, and the scale may range from cool colors (e.g., green, blue) to hot colors (e.g., yellow, red). Cool colors may represent data values near the middle of the acceptable range, and hot colors may represent data values near or outside the maximum or minimum values of the range.

In embodiments, a system for data collection in an industrial environment may present, in an AR display, data being collected from multiple sensors in the industrial environment as one of multiple graphical effects (e.g., colors within a range of colors) that correlate the data being collected from each sensor to a scale comparing acceptable values with unacceptable values. In embodiments, the multiple graphic effects may overlay a view of the industrial environment, and the placement of the multiple graphic effects may correspond to locations within the view of the environment where sensors generating corresponding sensor data are located. In embodiments, a first set of graphic effects (e.g., hot colors) represent components for which the multiple sensors indicate unacceptable values.

In embodiments, a system for data collection in an industrial environment may facilitate presenting, in an AR display, information being collected by sensors in the industrial environment as a heat map overlaid on a visualization of the environment, where areas of the environment having sensor data suggesting a greater likelihood of failure are overlaid with a different graphical effect than areas of the environment having sensor data suggesting a lesser likelihood of failure. In embodiments, the heat map is based on currently sensed data. In embodiments, the heat map is based on data of previous failures. In embodiments, the heat map is based on changes in data from a previous period, such as data suggesting an increased likelihood of machine failure. In embodiments, the heat map is based on preventive maintenance plans and records in the industrial environment.

In embodiments, a system for data collection in an industrial environment may facilitate presenting information collected by sensors in the industrial environment as a heat map overlaid on a view of the environment, such as a live view as presented on an AR display. Such a system may include presenting an overlay that promotes a call to action, the overlay being associated with an area of the heat map. The overlay may constitute a visual of a portion or subsystem of the environment where an action should be taken. In embodiments, the action to be taken may be maintenance-related and part-specific.

In embodiments, a system for data collection in an industrial environment may facilitate updating, in an AR view of the portion of the environment, a heat map of an aspect of the industrial environment based on changes in operational instructions for at least one aspect of a machine in the industrial environment. The heat map may represent compliance with operational constraints for the portion of the machine in the industrial environment. In embodiments, the heat map may represent likelihood of component failure as a result of changes to the operational instructions.

In embodiments, a system for data collection in an industrial environment may facilitate presenting the degree or measure of sensor coverage in the industrial environment for data collection as a heat map in an AR view of a portion of the environment. A template identifying sensors selected in the industrial environment for data collection activities.

In embodiments, a system for data collection in an industrial environment may facilitate displaying a heat map overlaid on a view, such as a live view of the industrial environment, of failure-related data for various parts of the environment. The failure-related data may consist of the difference between the actual failure rate of the various parts and another failure rate. The another failure rate may be the failure rate of comparable parts elsewhere in the environment and/or an average failure rate of comparable parts across multiple environments, such as an industry average, a manufacturer's failure rate estimate, etc.

In embodiments, a system for data collection in an industrial environment may facilitate displaying, in an augmented reality view of a portion of the environment, a heat map related to data collected from robotic arms and hands for robotic handling on a production line. The heat map related to data collected from the robotic arms and hands may represent data from sensors placed on the fingers of the robotic hands, for example. The sensors may collect data such as pressure when pinching an object, resistance of the object (e.g., to the robot's touch), multi-axis forces exerted on the fingers when performing a manipulation such as holding a tool, temperature of the object, total finger movement from the initial contact point to meeting a resistance threshold, and other hand position and usage. This heat map of data is displayed in the augmented reality view of the robotic production environment, allowing a user to visually assess, for example, how the relative positioning of the robotic fingers affects the object being handled.

In an embodiment, a system for data collection in an industrial environment may facilitate displaying heat maps related to data collected from linear bearings for robotic handling on a production line in an augmented reality view of a portion of the environment. Linear bearings, like most bearings, may be invisible when in use. However, to assess the operation of the bearing, it is beneficial to represent data from sensors obtaining information about the bearing in use in an augmented reality display. In an embodiment, sensors may be positioned to detect forces exerted on portions of the bearing by rotating members or elements that the bearing supports. These forces may be presented as heat maps corresponding to relative forces in a visualization of the bearing in an augmented reality view of a robotic handling machine that uses the linear bearing.

In an embodiment, a system for collecting data in an industrial environment may facilitate displaying a heat map associated with data collected from a mining drilling machine in an augmented reality view of a portion of the environment. The drilling machine, particularly a multi-tip circular drilling head, may experience various rock formations simultaneously. Sensors may be placed near each drilling tip to detect the forces experienced by the tips. The data may be collected by a system adapted to collect data in an industrial environment and provided to an augmented reality system that may display the data as a heat map or the like within the field of view of the drilling machine.

With reference to FIG. 114, an augmented reality display of a heat map based on data collected in an industrial environment by a system adapted to collect data in the environment is depicted. The augmented reality view of the industrial environment 11500 may include a heat map 11502 depicting data received from or derived from sensors 11504 in the industrial environment. The sensor data may be captured and processed by a system adapted for data collection and analysis in industrial environments. The data may be converted into a form suitable for use in the augmented reality system to display the heat map. The heat map 11502 may be aligned in the augmented reality view with the sensors from which the underlying data was sourced.

(1) In an embodiment, an augmented reality (AR) system presents sensed data of an industrial machine in a view of the industrial machine as a heat map of data collected from sensors in the view, the heat map being positioned proximate to sensors capturing the sensed data visualized on the AR display. (2) The system described in (1), wherein the heat map is based on a comparison of real-time data collected from the sensors to acceptable range values for the data. (3) The system described in (1), wherein the heat map is based on trends in the sensed data. (4) The system described in (1), wherein the heat map represents a measure of sensor coverage of the industrial environment corresponding to a condition of interest, calculated from data collected by sensors in the industrial environment. (5) The system described in (1), wherein the heat map of data collected from sensors in the view is based on data collected by a system adapted to collect data in an industrial environment by routing data from multiple sensors to multiple data collectors via at least one of an analog crosspoint switch, a multiplexer, and a hierarchical multiplexer. (6) The system of (1), wherein the heat map displays different collected data values with different colors. (7) The system of (1), wherein data collected from multiple sensors is combined to create the heat map. (8) A system for data collection in an industrial environment, comprising: an augmented reality display that presents data collected from multiple sensors in the industrial environment as one of multiple colors, the colors correlating data collected from each sensor to a color scale, with cool colors mapping to data values within an acceptable range and hot colors mapping to data values outside the acceptable range, the multiple colors overlaying a view of the industrial environment, and the arrangement of the multiple colors corresponding to locations within the view of the environment where sensors generating corresponding sensor data are located. (9) The system of (8), wherein the hot color represents a component for which multiple sensors are showing values outside a typical range. (10) The system of (8), wherein the multiple colors are based on a comparison of real-time data collected from sensors to an acceptable range for that data. (11) The system of (8), wherein the multiple colors are based on trends in sensed data. (12) The system of (8), wherein the plurality of colors represent a measure of sensor coverage in the industrial environment in response to a condition of interest, calculated from data collected by sensors in the industrial environment. (13) A method including presenting information collected by sensors in an industrial environment as a heat map overlaid on a view of the environment, such that areas of the environment having sensor data suggesting a high likelihood of failure are overlaid with a different heat map than areas of the environment having sensor data suggesting a low likelihood of failure. (14) The method of (13), wherein the heat map is based on currently sensed data. (15) The method of (13), wherein the heat map is based on previous failure data. (16) The method of (13), wherein the heat map is based on changes in data from a previous period suggesting an increased likelihood of machine failure. (17) The method of (13), wherein the heat map is based on preventive maintenance schedules and records in the industrial environment. (18) The method of (13), wherein the heat map represents an actual failure rate versus a reference failure rate. (19) The method of (18), wherein the reference failure rate is an industry average failure rate. (20) The method of (18), wherein the reference failure rate is a manufacturer's failure rate estimate.

In an embodiment, a system for data collection and visualization in an industrial environment may include augmented reality and/or virtual reality (AR/VR). Data values output from sensors positioned within the field of view of the AR/VR display are displayed along with visual attributes that indicate the sensed data's conformance to acceptable ranges or values. In an embodiment, the visual attributes may depict trends in the sensed data and/or its derivatives in near real time. In an embodiment, the visual attributes may be the actual data being captured or derived data, such as trends in the data.

In an embodiment, a system for collecting and visualizing data in an industrial environment may include an AR/VR display, where trends in data values output by sensors positioned within the AR/VR field of view may be displayed along with visual attributes indicating the severity of the trend. In an embodiment, other data or analysis that may be displayed may include data from a sensor that has exceeded a tolerance range, data from a sensor that is part of a smart band selected by a user, data from a sensor that is monitored to trigger a collection action on the smart band, and data from a sensor that senses an aspect of the environment that meets preventive maintenance criteria, such as a PM action being scheduled soon, a PM action recently performed, or a PM that is overdue. Other data for such AR/VR visualization may include data from a sensor that has recently changed, widened, or narrowed a tolerance range. Other data for such AR/VR visualization, particularly useful for operators of industrial machinery (such as drilling, perforating, etc.), may include analysis of data from sensors, such as the impact on operating elements (torque, force, strain, etc.).

In an embodiment, a system for collecting and visualizing data in an industrial environment, which may include presenting visual attributes representing data collected in an AR/VR environment, may do so for a pump in a mining application. The pump in the mining application may supply water and remove liquefied waste from a mine. Pump performance may be monitored by sensors detecting the pump motor, regulator, flow meter, etc. Pump performance monitoring data may be collected and displayed on the augmented reality display as a set of visual attributes. As an example, the pump motor's power consumption, efficiency, etc. may be displayed near the pump as viewed through the augmented reality display.

In an embodiment, a system for data collection and visualization in an industrial environment, which may include the presentation of visual attributes representing the collected data in an AR/VR environment, may be implemented for energy storage in power generation. For power generation applications, the energy storage may be monitored with sensors that capture data related to the storage and use of the stored energy. Information such as utilization of individual energy storage cells, energy storage rate (e.g., battery charge), stored energy consumption rate (e.g., kWh delivered by the energy storage system), and storage cell status may be captured and converted into augmented reality viewable attributes that may be presented in an augmented reality view of the energy storage system.

In an embodiment, a system for data collection and visualization in an industrial environment, which may include presenting visual attributes representing data collected in an AR/VR environment, may do so for a water supply system in a power generation application. Sensors may be placed in an industrial environment, such as a power generation environment, to collect data about the water supply system. Data from those sensors may be captured and processed by the data collection system. Results of this processing may include trends in data such as cooling rate, flow rate, and pressure of the water supply. These trends may be presented on an augmented reality view of the water supply system by applying a map of sensors visible to the view and retrieving data from the mapped sensors. The retrieved data (and derivatives thereof) may be displayed on the augmented reality view of the water supply system.

Referring to FIG. 115, an augmented reality display 11600 is depicted that consists of real-time data 11602 overlaid on a view of an industrial environment. Sensors 1164 within the environment may be recognized by the augmented reality system, such as by first detecting the industrial machine, system, or portion thereof with which the sensor is associated. Data from the sensors 11604 may be retrieved from a data repository, processed into trends, and presented in the augmented reality view 11600 near the sensor from which the data originated.

(1) In one embodiment, a system for collecting and visualizing data in an industrial environment is provided, in which data values output by sensors positioned within a field of view of an electronic display are displayed on the electronic display along with visual attributes that indicate the degree of compliance of the data with an acceptable range or value for the sensed data. (2) The system described in (1), in which the field of view of the electronic display is a field of view of an augmented reality display of the industrial environment. (3) The system described in (1), in which the visual attributes indicate a trend of the sensed data relative to the acceptable range over time. (4) The system described in (1), in which the data values are located on the electronic display in proximity to the sensor from which the data values are output. (5) The system described in (1), in which the visual attributes further include an indication of a sensor set on a smart band associated with the sensor from which the data values are output. (6) A system for collecting and visualizing data in an industrial environment, in which data values output by selected sensors positioned in an augmented reality view of the industrial environment are displayed along with visual attributes that indicate the degree of compliance of the data with an acceptable range or value for the sensed data. (7) The system of (6), wherein the sensor is selected based on a data collection template that facilitates configuration of sensor data routing resources in the system. (8) The system of (7), wherein the selected sensor is displayed in the template as part of a group of smart band sensors. (9) The system of (7), wherein the selected sensor is a sensor monitored to trigger a smart band data collection action. (10) The system of (6), wherein the selected sensor senses an aspect of the environment related to a preventive maintenance standard. (11) The system of (6), wherein the visual attribute further indicates whether the tolerance range has expanded or contracted within the past 72 hours. (12) A system for data collection and visualization in an industrial environment, wherein trends in data values output by selected sensors positioned within a field of view of an industrial environment depicted on an augmented reality display are displayed with visual attributes indicating the severity of the trend. (13) The system of (12), wherein a sensor is selected when data from the sensor exceeds a tolerance range. (14) The system of (14), wherein the sensor is selected based on being part of a smart band group of sensors. (15) The system of (12), wherein the visual attribute further indicates conformance of the trend to an acceptable range of data values. (16) The system of (12), wherein the system for data collection is adapted to route data from the selected sensor to a controller of an augmented reality display based on a data collection template that facilitates configuring routing resources of the system for data collection. (17) The system of (12), wherein the sensor is selected in response to the sensor data being configured in a smart band data collection template as an instruction for triggering a smart band data collection operation. (18) The system of (12), wherein the sensor is selected in response to a preventive maintenance criteria. (19) The system of (18), wherein the preventive maintenance criteria is selected from the list consisting of: a preventive maintenance action is scheduled; a preventive maintenance action has been completed within the past 72 hours; and a preventive maintenance action is overdue.

FIG. 158 illustrates a system for data collection in an industrial environment having a self-contained data collection box for capturing and analyzing data in an industrial environment, including sensor inputs 11700, 11702, 11704, and 11706 connected to a data circuit 11708 for analyzing the sensor inputs, a network communication interface 11712, a network control circuit 11710 for transmitting and receiving information related to the sensor inputs to an external system, and a data filter circuit configured to dynamically adjust which portions of the information to transmit based on instructions received via the network communication interface. Various sensor inputs X are connected to a data circuit Y, which in turn communicates with the network control circuitry connected to one or more network interfaces. These interfaces may include wired or wireless interfaces communicating with network protocols such as star, multi-hop, peer-to-peer, hub-and-spoke, mesh, ring, hierarchical, daisy-chain, and broadcast. These interfaces may be multi-pair, such as Ethernet, or single-wire, such as I2C. The network protocol can be one or more of many variations of Ethernet and other protocols for real-time communication in industrial networks, such as Modbus® over TCP, Industrial Ethernet, Ethernet Power Link, Ethermet/IP, EtherCAT, Sercos®, Profmet™, CAN bus, serial protocols, short-range communication protocols, and even home automation protocols such as ZigBee® and Z-Wave™, and wireless WWAN or WLAN protocols such as LTE ^™ , Wi-Fi, and Bluetooth™. The sensor input can be permanently or removably connected to the measurement object or can be integrated into a standalone data acquisition box. The entire system may be integrated into the equipment being measured, such as a vehicle (such as an automobile, truck, commercial vehicle, tractor, construction vehicle, or other type of vehicle), a component or item of equipment (such as a compressor, agitator, motor, fan, turbine, generator, conveyor, lift, robotic assembly, or other items described throughout this disclosure), an infrastructure element (such as a foundation, housing, wall, floor, ceiling, roof, doorway, ramp, staircase, etc.), or any other feature or aspect of an industrial environment. The entire system may be integrated into a stationary industrial system, such as a production assembly, a static component of an assembly line that is subject to wear and stress (such as a rail guide), or a moving element, such as a robot, linear actuator, gearbox, vibrator, etc.

Disclosed herein are methods and systems for data collection in industrial environments that feature self-organizing capabilities. Such data collection systems and methods can facilitate intelligent, situational, and context-aware collection, summarization, storage, processing, transmission, and/or organization of data by one or more data collectors (such as any of the broad range of data collector embodiments described throughout this disclosure), a central location, or computing system, etc. The described self-organizing capabilities of data collection in industrial environments can improve various parameters of such data collection, as well as parameters of processes, applications, and products that rely on the data collection, such as data quality parameters, consistency parameters, efficiency parameters, comprehensiveness parameters, reliability parameters, effectiveness parameters, storage utilization parameters, yield parameters (including financial yield, output yield, and adverse event reduction), energy consumption parameters, bandwidth utilization parameters, input/output rate parameters, redundancy parameters, security parameters, safety parameters, interference parameters, signal-to-noise parameters, and statistical relevance parameters. The self-organizing capabilities can be optimized across one or more such parameters, such as based on weighting the values of the parameters. For example, a group of data collectors may be managed (or self-managed) to provide a predetermined level of redundancy for critical data while not exceeding a specified level of energy usage, e.g., per data collector, group of data collectors, or entire group of data collectors. This may include using various optimization techniques described throughout this disclosure and the documents incorporated herein by reference.

In embodiments, such methods and systems for data collection in industrial environments may include one or more data collectors, arranged, for example, in a collaborative group or "swarm" of data collectors, communicating with computing systems to collect and organize data in conjunction with a data pool, as well as supporting technology components, services, processes, modules, applications, and interfaces for managing the data collection (sometimes collectively referred to as a data collection system 1204). Examples of such components include, but are not limited to, model-based expert systems, rule-based expert systems, artificial intelligence-based expert systems (such as machine learning systems, which may include neural net expert systems, self-organizing map systems, human-supervised machine learning systems, condition determination systems, classification systems, or other artificial intelligence systems), or various hybrids or combinations of any of the foregoing. References to self-organizing methods or systems should be understood to encompass the use of any of the foregoing, or any appropriate combination, unless the context indicates otherwise.

The data collection systems and methods of the present disclosure can be utilized with various types of data, including, but not limited to, vibration data, noise data, and other sensor data of the type described throughout this disclosure. Such data collection can be utilized for event detection, condition detection, and the like, which can be utilized to self-organize the data collection systems and methods, as further described herein. Self-organization capabilities include managing data collectors, either individually or in groups, to support an identified application, process, or workflow, such as tracking progress toward one or more objectives, goals, rules, policies, or guidelines. Self-organization capabilities can also include managing other objectives/guidelines, directing data collectors to determine unknown variables based on the collection of other data (e.g., based on a system behavior model that includes the variables), selecting preferred sensor inputs from among available inputs (including specifying input combinations, fusions, or multiplexing), and designating specific data collectors from among available data collectors.

A data collector may include any number of items, such as sensors, input channels, data locations, data streams, data protocols, data extraction techniques, data conversion techniques, data loading techniques, data types, sampling frequencies, sensor placement, static data points, metadata, data fusion, data multiplexing, and self-organization techniques, as described herein. A data collector configuration may describe the configuration and structure of the data collector, such as by specifying parameters that define the data collector. For example, a data collector configuration may include one or more frequencies to measure. The frequency data may further include at least one of a group of spectral peaks, a true peak level, a crest factor derived from a time waveform, and an overall waveform derived from a vibration envelope, as well as other signal characteristics described throughout this disclosure. A data collector may include sensors or data that measure one or more wavelengths, one or more spectra, and/or one or more types of data from various sensors and metadata. A data collector may include one or more sensors or a wide variety of types of sensors, as described throughout this disclosure and the documents incorporated by reference herein. Indeed, the sensors described herein may be used in any of the methods or systems described throughout this disclosure. For example, one sensor may be an accelerometer measuring voltage per g of acceleration (e.g., 100 mV/g, 500 mV/g, 1 V/g, 5 V/g, 10 V/g). In embodiments, the configuration of a subset of sensors used in a data collector may be varied based on the data, optimizing sensor response, such as selecting an accelerometer suitable for measuring the acceleration of a high-speed turbine in a power generation environment versus a low-speed gear system or drill/boring equipment. For example, proximity probes and multiple accelerometers may be placed on specific targets (e.g., gear systems, drills, turbines), intelligently selecting one accelerometer for data collector measurements at low speeds and another accelerometer for high speeds. Accelerometers come in a variety of types, including piezoelectric crystal, low-frequency (e.g., 10 V/g), high-speed compressor (10 MV/g), and MEMS. In another example, a sensor may be a proximity probe or velocity probe that can be used in a sleeve or tilt-pad bearing (e.g., oil bath). In yet another example, one sensor may be a solid-state relay (SSR) configured to automatically interface with another routed data collector (e.g., a mobile or portable data collector) to acquire or distribute data. In another example, a data collector may be routed to change the configuration of multiple available sensors. For example, an appropriate accelerometer may be located at a sensing point, such as on or near a machine component. In yet another example, one sensor may be a triaxial probe (e.g., a 100 MV/G triaxial probe) used in some embodiments for portable data collection. In some embodiments, the vertical element on one axis of a triaxial probe may have a high frequency response, while a horizontally mounted one may have a limiting effect on the frequency response of all three axes. In another example, one sensor may be a temperature sensor, such as a probe with a temperature sensor embedded within it, for example, to obtain the temperature of a bearing. In yet further examples, the sensor may be an ultrasonic, microphone, touch, capacitive, vibration, acoustic, pressure, strain gauge, thermography (e.g., camera), imaging (e.g., electric field detector, EMF meter measuring alternating electromagnetic fields, gaussmeter, motion detector, chemical detector, gas detector, CBRNE detector, vibration transducer, magnetometer, position detector, location information detector, speed detector, displacement detector, speed sensor, displacement sensor, tachometer, flow sensor, level sensor, proximity sensor, pH sensor, hygrometer/moisture sensor, densitometry sensor, anemometer, viscometer, or any analog and/or digital industrial sensor. In yet another example, a sensor may be for detecting or measuring ambient noise, such as a sound sensor, microphone, ultrasonic sensor, acoustic wave sensor, or optical vibration sensor (e.g., using a camera to identify vibrations generating noise). In yet another example, a sensor may be a motion detector.

A data collector may be configured or adapted to encompass one or more frequencies, wavelengths, or spectra for a particular sensor, a particular group of sensors, or the combined signal from multiple sensors (e.g., involving multiplexing or sensor fusion). A data collector may be configured to encompass one or more sensor or sensor data (including groups of sensors and their combined signals) from one or more pieces of equipment/components, areas of an installation, different but interconnected areas of an installation (e.g., a machine assembly line and a boiler room powering that line), or locations (e.g., a building in one geographic location and a building in another, different geographic location). Data collector settings, configurations, instructions, or specifications (collectively referred to herein using any of these terms) include where sensors are placed, how often data points or points are sampled, the granularity at which samples are taken (e.g., the number of sampling points in fractions of a second), which sensors of a set of redundant sensors are sampled, the averaging protocol for the redundant sensors, and any other aspects that affect data acquisition.

Within the data collection system 1204, the self-organization function may be implemented by neural nets, model-based systems, rule-based systems, machine learning systems, and/or hybrids of any of these systems. Furthermore, the self-organization function may be performed, in whole or in part, by individual data collectors, collections or groups of data collectors, network-based computing systems, local computing systems including one or more computing devices, remote computing systems including one or more computing devices, and combinations of one or more of these components. The self-organization function may be optimized for a specific goal or outcome, such as predicting and managing the performance, health, or other characteristics of equipment, components, or systems of equipment or components. Based on continuous or periodic analysis of sensor data, if a pattern/trend is identified, an outlier emerges, or a group of sensor readings begins to change, the self-organization function may intelligently alter the collection of data, as described herein. This may occur by triggering rules reflecting a model or understanding of system behavior (e.g., recognizing a shift in operating mode requiring a different sensor when a shaft speed increases) or may occur under the control of a neural net (either in combination with a rule-based approach or alone). For example, the system's state can be classified, predicted, or acted upon, allowing time for feedback to select an appropriate collection mode. For example, if an assembly line is reconfigured for a new product or a new assembly line is installed in a manufacturing facility, data from the current data collectors may not accurately predict the system's state or operating metrics. Therefore, the self-organizing function can begin iterations to determine whether new data collectors, sensed data types, sensed data formats, etc., are better at predicting the state or metrics. Based on offset system data, such as libraries or other data structures, specific sensors, frequency bands, or other data collectors may be initially used in the system to collect data to evaluate performance. As the self-organizing function iterates, it can access other sensors/frequency bands to determine their relative weighting in identifying performance metrics. Over time, new frequency bands (or new collections of sensors, new configurations for sensors, etc.) may be identified to better or more appropriately evaluate system performance, and the self-organizing function can modify the data collectors based on these iterations. For example, old boring tools in an energy extraction environment may dampen one or more vibration frequencies, but different frequencies have higher amplitudes than those seen in the current system and exist during optimal performance. In this example, a self-organizing function could modify the data collector from that originally proposed by the data collection system to capture the higher amplitude frequencies present in the current system.

In embodiments involving neural nets or other machine learning systems, the self-organizing function may be seeded and may iterate, for example, based on feedback and operating parameters as described herein. Specific feedback may include utilization measurements, efficiency measurements (e.g., power or energy utilization, storage utilization, bandwidth utilization, perishable input/output utilization, fuel utilization, and/or financial efficiencies such as cost savings), condition predictions or prediction success measurements (e.g., failure avoidance and mitigation), productivity measurements (e.g., workflow), yield measurements, and profit measurements. Specific parameters include storage parameters (e.g., data storage, fuel storage, inventory storage), network parameters (e.g., network bandwidth, input/output speed, network utilization, network cost, network speed, network availability), transmission parameters (e.g., data transmission quality, data transmission speed, error rate in transmission, transmission cost), security parameters (e.g., number and/or type of exposure events, vulnerability to attacks, data loss, data breach, access parameters), location and deployment parameters (e.g., location of data collectors, location of workers, location of machines and equipment, location of inventory units, location of parts and materials, location of network access points, location of entrances/exits, location of landing points, location of sensor sets, location of network infrastructure, location of power sources), input selection parameters, data combination parameters (e.g., multiple extraction, transformation, loading), power parameters (e.g., for individual data collectors or for a group of all potentially available data collectors). These include input selection parameters, data combination parameters (e.g., multiplexing, extraction, conversion, loading), power parameters (e.g., for individual data collectors, groups of data collectors, or all potentially available data collectors), state (e.g., operational mode, availability state, environmental state, failure mode, health state, maintenance mode, expected state), events, and equipment specifications. Regarding state, operational modes can include movement mode (e.g., direction, speed, acceleration), movement mode type (e.g., rolling, flying, gliding, floating, hovering, floating), performance mode (e.g., gear, rotational speed, thermal level, assembly line speed, voltage level, frequency level), power mode, fuel conversion mode, resource consumption mode, and financial performance mode (e.g., yield, profitability). Availability state refers to the prediction of conditions that may result in a machine going offline or requiring backup. Environmental state can refer to parameters such as ambient temperature, ambient humidity/moisture, ambient pressure, ambient wind/fluid flow, presence of contaminants, presence of interference (e.g., electrical noise, vibration), power availability, and power quality. Anticipated conditions include achieving or not achieving desired targets (specified/threshold power production rate, specified/threshold power generation rate, operational efficiency/failure rate, financial efficiency/profit target, power efficiency/resource utilization rate, avoidance of fault conditions (e.g., overheating, underperformance, overperformance, overload), avoidance of overheating, underperformance, overspeed, overmotion, excessive vibration/vibration, overacceleration, expansion/contraction, electrical failure, out of battery/fuel, overpressure, excessive radiation/meltdown, fire, freezing, fluid flow failure (e.g., stuck valve, frozen fluid), mechanical failure (e.g., component breakage, component wear, coupling failure, misalignment, asymmetry/deflection, component damage (e.g., deflection, strain, stress, crack), imbalance, collision, stuck element, lost or slipped chain or belt), avoidance of unsafe conditions or catastrophic failure, availability (online), etc.

This data may consist of inputs from sensors via data collectors and other data from system components, external systems, and external data sources. For example, the model may be an operational model of an industrial environment, machine, or workflow. In other examples, the model may be for predicting conditions, predicting failures, optimizing maintenance, optimizing data transport (e.g., optimizing network coding, optimizing routing depending on network conditions), optimizing a data marketplace, etc.

The self-organizing function may result in any number of downstream actions based on the analysis of data from the data collectors. In one embodiment, the self-organizing function may determine that the system should maintain or modify operational parameters, equipment, or neural net model weightings given desired goals, such as a specified/threshold power production rate, a specified/threshold power generation rate, operational efficiency/failure rate, financial efficiency/profit target, power efficiency/resource utilization, avoidance of fault conditions, avoidance of unsafe conditions or catastrophic failures, etc. In an embodiment, the adjustments may be based on determining the context of the industrial system, such as the type of equipment, purpose, typical operating mode, functional specifications of the equipment, the relationship of the equipment to other features of the environment (including other systems that provide input to or take input from the equipment), the presence and role of operators (including humans and automated control systems), and understanding the ambient or environmental conditions. For example, to achieve profit goals in a distribution environment (e.g., an electrical power distribution environment), a generator or system of generators may need to operate at a certain efficiency level. The self-organizing function may be seeded with a model for operating the system of generators in a manner that achieves a specified profit goal, such as indicating the on/off status of individual generators in the power generation system based on the time of day, the current market selling price of fuel consumed by the generators, current demand or expected future demand, etc. As the model acquires data and iterates, it predicts whether the profit goal will be achieved from the current data and determines whether the data and type of data being collected are appropriate or sufficient for the model. Based on the results of the iterations, recommendations may be made (or control instructions may be automatically provided) to collect different/additional data, organize the data differently, direct different data collectors to collect new data, etc., and/or operate a subset of generators at a higher output (but lower efficiency), power additional generators, maintain current operating conditions, etc. Additionally, as the system operates iteratively, one or more additional sensors may be sampled within the model to determine whether adding them to the self-organizing function improves state predictions or supports the goals of the data collection effort.

In embodiments, a system for data collection in an industrial environment may include multiple input sensors, such as any of those described herein, communicatively coupled to a data collector having one or more processors. The data collection system may include multiple individual data collectors configured to operate together to determine at least a subset of the multiple sensors for processing output data. The data collection system may also include a machine learning circuit configured to receive output data from at least a subset of the multiple sensors and ream a pattern in the received output data indicative of a condition. In some embodiments, the data collection system may modify at least a subset of the multiple sensors, or an aspect thereof, based on one or more of the learned received output data patterns and the condition. In certain embodiments, the machine learning circuit is seeded with a model that enables learning of the data patterns. The model may be a physical model, an operational model, a system model, etc. In other embodiments, the machine learning circuit is configured for deep learning, where input data is provided to the circuit with no or minimal seeds, and the machine learning data analysis circuit reams based on output feedback. For example, a metal tooling system in a manufacturing environment may operate to manufacture parts using machine tools such as lathes, milling machines, grinders, and boring machines. Such machines may operate at various speeds and output rates, which may affect the machine's lifespan, efficiency, accuracy, etc. The data collector may capture various parameters to evaluate the machine tool's environment, such as operating speed, heat generation, vibration, conformance to part specifications, etc. The system can utilize such parameters and iterate toward predictions of condition, output rate, etc. based on such feedback. Additionally, the system can self-organize as the data collector collects additional or different data and makes predictions from that data.

In the self-organizing function of a data collection system, there may be a balance of multiple goals/guidelines. For example, a repair and maintenance organization (RMO) may have operating parameters designed for maintenance, such as: While a manufacturing facility owner may have specific operating parameters for machinery designed to achieve production goals. These goals (in this example, related to maintenance goals or production output) may be tracked by different data collectors or sensors. For example, machine maintenance may be tracked by sensors including temperature sensors, vibration transducers, and strain gauges, while machine production goals may be tracked by sensors including speed sensors and power consumption meters. The data collection system may intelligently manage data collectors aligned with different goals (optionally under the supervision of one or more supervisors (human or automated) using neural nets, machine learning systems, deep learning systems, etc.) and assign weights, parameter modifications, or recommendations based on factors such as bias toward one goal or a compromise to allow better alignment with all goals being tracked. The compromise between goals delivered to the data collection system may be based on one or more hierarchies or rules regarding the authority, role, importance, etc. of the applicable goals. In embodiments, the trade-off between goals may be optimized using machine learning, such as neural nets, deep learning systems, or other artificial intelligence systems as described throughout this disclosure. For example, in a power plant where turbines are operating, a data collection system may manage multiple data collectors, such as one directed at detecting the operating status of the turbine, one directed at identifying the probability of achieving production targets, and one directed at determining whether the turbine's operation is meeting fuel efficiency targets. Each of these data collectors is equipped with data from a different sensor or different sensors (such as a vibration transducer indicating operating conditions, a flow meter indicating production targets, and a fuel gauge indicating fuel efficiency), and their output data indicates aspects of a particular goal. When a sensor or set of sensors serves multiple goals, overlapping data collectors (having some sensors in common and not others) can take input from that sensor or set of sensors, as managed by the data collection system. When data collection is constrained (e.g., due to power limitations, storage limitations, bandwidth limitations, input/output processing capabilities, etc.), rules may be implemented to prioritize certain goals (e.g., fuel utilization or pollution reduction goals mandated by law or regulation) and ensure that data collectors associated with those goals continue to collect data even if other goals are paused or shut down. Managing goal prioritization can occur hierarchically or through machine learning. The data collection system may seed a model based on current data acquired as it iterates toward a predicted state (e.g., achieving a goal), or it may not seed the model at all. In this example, during turbine operation, a plant owner may decide to bias the system toward fuel efficiency. However, if the self-organization function repeatedly executes and predicts that the system is not, or has not, collected enough data to determine whether the system is achieving a particular goal, the data collection system can recommend or implement changes to collect the appropriate data. Additionally, a plant owner may configure the system to bias toward a particular goal, such that recommended changes to data collection parameters that affect that goal are made in preference to other recommended changes.

In embodiments, the data collection system may be seeded with multiple data collection data types and then continue to iterate in a deep learning manner to arrive at a distribution of data collectors that optimizes meeting multiple objectives. For example, there may be multiple objectives tracked for a refining environment, such as refining efficiency and economic efficiency. The refining efficiency of a refining system may be expressed by comparing the fuel input to the system (obtained by knowing the quantity and quality of the fuel used) to the amount of refined product output from the system (calculated using the system's output). The economic efficiency of a refining system may be expressed as the ratio of the costs of running the system, such as fuel, labor, materials, and services, to the refined product output from the system over a period of time. Data used to track refining efficiency includes data from flow meters, quality data points(s), and temperature meters, while data used to track economic efficiency includes product flow and cost data output from the system. These data can be used by the data collection system to predict conditions, and the system's self-organizing capabilities can iterate toward a data collection strategy optimized to predict conditions related to both thermal efficiency and economic efficiency. The new data collection schema may include data previously used by the individual data collection devices, but may also use new data from different sensors or data sources.

The repetition of the data collection system may be governed by rules in some embodiments. For example, the data collection system may be configured to collect data for seeding at a predetermined frequency. The data collection system may be configured to repeat at least several times when new components/equipment/fuel sources are added, when a sensor goes offline, or as standard practice. For example, if a sensor measuring the rotation of a drilling tool in an offshore drilling operation goes offline and the data collection system begins acquiring data from a new sensor or data collector measuring the same data point, the data collection system may be configured to repeat multiple times before that condition is used for or allowed to affect downstream actions. The data collection system may be configured for offline training or in-situ/online training. The data collection system may be configured to include static data and/or manually entered data in the data collection device. For example, a data collection system associated with such a drilling tool may be structured to iterate toward predicting the distance drilled based on the duration of the operation, with the data collector(s) including data regarding the drilling tool's speed, distance sensors, temperature sensors, etc.

In embodiments, the data collection system may be overridden. In embodiments, the data collection system may revert to a previous configuration if the self-organization function fails, such as if insufficient or improperly collected data is collected; if there is too much uncertainty in a model-based system; if the system is unable to resolve conflicting rules in a rule-based system; or if the system is unable to converge on a solution in any of the above cases. For example, sensor data from a power generation system used by the data collection system may indicate an inoperative condition (e.g., a burned-out turbine), but output sensors or visual inspection, such as by a drone, may indicate normal operation. In such a case, the data collection system may revert to the original data collection schema used to seed the self-organization function. In another example, one or more point sensors on a refrigeration system may indicate an impending compressor failure, but the data collector self-organized to collect data relevant to determining performance indicators was unable to identify the failure. In this case, the data collector reverts to the original configuration or a version of the data collector configuration that would have identified the impending compressor failure.

In embodiments, the data collection system can change data collector settings when new components are added that bring the system closer to a different system. For example, a vacuum distillation unit is added to an oil and gas refinery to distill naphthalene, but the data collection system's current data collector settings are from a refinery that distills kerosene. In this example, a data structure with data collector settings for various systems can be searched to find one that more closely matches the current system. If a new system is identified as a closer match, the new data collector settings (such as which sensors to use, where to point them, how often to sample them, and what types of data and points are needed, as described herein), such as one that also distills naphthalene, are used as seeds to iterate the data collection system to predict the state of the system. In embodiments, the data collection system can change data collector settings when new data sets become available from a third-party library. For example, a power plant might optimize a particular turbine model to operate at high efficiency and store the data collector settings in a data structure. This data structure can be continuously scanned for new data collectors that can help monitor power generation and thereby optimize turbine operation.

In embodiments, the data collection system may utilize self-organization capabilities to uncover unknown variables. For example, the data collection system may iterate to identify missing variables to be used for further iterations. For example, an unused tank in a power plant's legacy condensate and make-up water system may have an unknown capacity because it is inaccessible and there is no documentation for the tank. Various aspects of the tank can be measured by a group of data collectors, and an estimated capacity (e.g., inflow to downstream spaces, time for dye-traced solution to pass through the system) can be calculated and entered into the data collection system as a new variable.

In embodiments, nodes in a data collection system may be on machines, on data collectors (or groups thereof), within a network infrastructure (corporate or otherwise), or within the cloud. In embodiments, there may be neurons distributed across nodes (e.g., machines, data collectors, networks, clouds).

In one aspect, and as shown in FIG. 118, a data collection system 1204 can be deployed in an industrial environment 12000 to collect data, for example, from one or more targets 1202. In the illustrated embodiment, the data collection system 1204 includes a group or "swarm" 1206 of data collectors 1208, a network 1210, a computing system 1212, and a database or data pool 1214. Each of the data collectors 1208 can include one or more input sensors and is communicatively coupled to any and all of the other components of the data collection system 1104, as illustrated in part by the connecting arrows between the components.

The target 1202 can be any form of machinery or component thereof in an industrial environment 12000. Examples of such industrial environments 12000 include, but are not limited to, factories, pipelines, construction sites, offshore oil rigs, ships, airplanes, other aircraft, mining environments, drilling environments, refineries, distribution environments, manufacturing environments, energy source extraction environments, marine exploration sites, underwater exploration sites, assembly lines, warehouses, power generation environments, hazardous waste environments, etc., each of which can contain one or more targets 1202. The target 1202 can take the form of any item or location from which a sensor can obtain data. Examples of such targets 1202 include, but are not limited to, machinery, pipelines, equipment, installations, tools, vehicles, turbines, speakers, lasers, automata, computer equipment, industrial machinery, switches, etc.

The self-organization functionality of data collection system 1204 may be performed by or on any of the components of data collection system 1204. In an embodiment, a data collector 1208 or a group 1206 of data collectors 1208 may self-organize without assistance from other components, e.g., based on data sensed by its associated sensors and other knowledge. In an embodiment, network 1210 may self-organize without assistance from other components, e.g., based on data sensed by data collector 1208 and other knowledge. Similarly, computing system 1212 and/or data pool 1214 may self-organize without assistance from other components and based on data sensed by data collector 1208 and other knowledge. It should be understood that any combination or hybrid self-organizing system may also be implemented.

By way of example only, the data collection system 1204 may implement or enable various methods or systems for data collection with self-organizing capabilities in the industrial environment 12000. These methods and systems may include analyzing multiple sensor inputs (e.g., received from or sensed by sensors at the data collector(s) 12008). These methods and systems may also include sampling the received data and self-organizing at least one of the following: (i) a data storage operation, (ii) a sensor collection operation to provide multiple sensor inputs, and (iii) a selection operation from multiple sensor inputs.

In aspects, the storing operation may include storing the data in a local database of, for example, data collector 1208, computing system 1212, and/or data pool 1214. The data may also be summarized over a predetermined period of time to reduce the size of the sensed data. The summarized data may be transmitted to one or more data collection boxes, to one or more data centers, and/or to other components of the system or other systems. Summarizing the data over a predetermined period of time to reduce the size of the data may, in some aspects, include determining a rate at which the data can be transmitted over a network (e.g., network 1210), where the size of the summarized data corresponds to a rate at which the data can be continuously transmitted over the network in real time. In such aspects, the summarized data may be continuously transmitted over the network, for example, to an external device.

In various implementations, the methods and systems may include committing the summarized data to a local ledger, identifying one or more other accessible signal acquisition devices on an accessible network, and/or synchronizing the summarized data in the local ledger with at least one of the other accessible signal acquisition devices (e.g., data collector 1208). In embodiments, the methods and systems may include receiving a remote stream of sensor data from one or more other accessible signal acquisition devices over a network. Advertising messages to potential clients may also or alternatively be sent indicating the availability of at least one of the locally stored data, summarized data, and remote stream of sensor data.

The method and system may include identifying one or more other accessible signal acquisition devices (e.g., data collector 1208) on an accessible network (e.g., 1210), designating at least one of the one or more other accessible signal acquisition devices as a logical communications hub, and providing a list of available data and their associated sources to the logical communications hub. The list of available data and their associated sources may be provided to the logical communications hub utilizing a hybrid peer-to-peer communications protocol.

In some embodiments, the storing operation may include storing the data in a local database and utilizing machine learning to automatically prune at least one parameter of the data pool. The prune may be based, at least in part, on receiving information regarding at least one of the classification accuracy and prediction accuracy of an external machine learning system that uses data from the data pool (e.g., data pool 12014).

The present disclosure describes a method for data collection in an industrial environment with self-organizing capabilities, and in one disclosed non-limiting embodiment of the present disclosure, the method can include analyzing a plurality of sensor inputs, sampling data received from the sensor inputs, and self-organizing at least one of the following: (i) a data storage operation, (ii) a sensor collection operation providing the plurality of sensor inputs, and (iii) a selection operation of the plurality of sensor inputs.

The present disclosure describes a system for data collection in an industrial environment having self-organizing capabilities, which system, in one non-limiting embodiment of the present disclosure, may include a data collector for handling multiple sensor inputs from sensors in the industrial environment and generating data related to the multiple sensor inputs, and a self-organizing system for self-organizing at least one of (i) data storage operations, (ii) data collection operations for sensors providing the multiple sensor inputs, and (iii) selection operations for the multiple sensor inputs.

The present disclosure describes a method for data collection in an industrial environment with self-organizing capabilities, and in one non-limiting embodiment of the present disclosure, the method may include analyzing multiple sensor inputs.

Sampling data received from sensor inputs and (i) a data storage operation, (ii) a sensor collection operation providing multiple sensor inputs, and (iii) a multiple sensor input selection operation, where the storage operation includes storing the data in a local database and summarizing the data over a predetermined period of time to reduce the size of the data.

In an embodiment, the method further includes transmitting the summarized data to one or more data acquisition boxes.

In an embodiment, the method further includes transmitting the summarized data to one or more data centers.

In an embodiment, summarizing the data for a predetermined period of time to reduce the size of the data includes determining a rate at which the data can be transmitted over the network, the size of the summarized data corresponding to a rate at which the data can be transmitted continuously in real time over the network.

In an embodiment, the method further includes continuously transmitting the summarized data to an external device over a network.

The present disclosure describes a method for data collection in an industrial environment with self-organizing capabilities, and the method according to one disclosed non-limiting embodiment of the present disclosure may include analyzing multiple sensor inputs, sampling data received from the sensor inputs, and self-organizing at least one of the following: (i) a data storage operation, (ii) a sensor collection operation providing multiple sensor inputs, and (iii) a multiple sensor selection operation, where the storage operation includes storing the data in a local database, summarizing the data over a predetermined period of time to reduce the size of the data, and committing the summarized data. The method may also include registering the data in a local ledger, identifying one or more other accessible signal acquisition devices on an accessible network, and synchronizing the summarized data in the local ledger with at least one of the other accessible signal acquisition devices. In an embodiment, the method further includes receiving a remote stream of sensor data from one or more other accessible signal acquisition devices over a network.

In an embodiment, the method further includes sending an advertising message to potential clients indicating the availability of at least one of the locally stored data, the summarized data, and the remote stream of sensor data.

The present disclosure describes a method for data collection in an industrial environment with self-organizing capabilities, and in one non-limiting embodiment of the present disclosure, the method may include analyzing multiple sensor inputs.

Sampling data received from sensor inputs and (i) storing the data, (ii) collecting sensors to provide multiple sensor inputs, and (iii) selecting multiple sensor inputs, wherein the storing includes storing the data in a local database and summarizing the data over a predetermined period of time to reduce the size of the data; identifying one or more other accessible signal acquisition devices on an accessible network; designating at least one of the one or more other accessible signal acquisition devices as a logical communications hub; and providing a list of available data and their associated sources to the logical communications hub.

In an embodiment, the list of available data and their associated sources is provided to a logical communication hub using a hybrid peer-to-peer communication protocol.

The present disclosure describes a method for data collection in an industrial environment with self-organizing capabilities, and in one disclosed non-limiting embodiment of the present disclosure, the method may include analyzing multiple sensor inputs, sampling data received from the sensor inputs, and self-organizing at least one of (i) a data storage operation, (ii) a sensor collection operation providing the multiple sensor inputs, and (iii) a selection operation of the multiple sensor inputs, wherein the storage operation includes storing the data in a local database, summarizing the data over a predetermined period of time to reduce the size of the data, storing the data in the local database, and automatically organizing at least one parameter of the database using machine learning, wherein the organization is based at least in part on receiving information about at least one of the classification accuracy and the prediction accuracy of an external machine learning system using the data in the database.

In an aspect, a sensor collection operation providing multiple sensor inputs can include receiving instructions directing a mobile data collector unit (e.g., data collector 12008) to operate a sensor at a target (e.g., 12002), where at least one of the multiple sensors is located on the mobile data collector unit. A communication regarding the instructions can be sent to one or more other mobile data collection units (1208). The swarm 1206, or a portion thereof, can self-organize the distribution of the mobile data collector unit and one or more other mobile data collector units (e.g., data collector 1208) at the target 1202.

In an aspect, self-organizing the distribution of mobile data collector units at target 12002 includes utilizing a machine learning algorithm to determine a respective target location for each of the mobile data collector units. The machine learning algorithm may utilize one or more of a plurality of features to determine the respective target locations. Examples of features may include the battery life of the mobile data collector unit (data collector 1208), the type of target 1202 being sensed, the type of signal being sensed, the size of the target 1202, the number of mobile data collector units (data collector 1208) required to cover the target 1202, the number of data points required for the target 1202, the success of previous signal acquisition attempts, information received from a centralized or other entity receiving instructions, historical information regarding sensors operating at the target 1202, etc.

In an implementation, self-organizing the distribution of the mobile data collector unit and one or more other mobile data collector units at the target location may include proposing a target location for the mobile data collector unit, transmitting the target location to at least one other mobile data collector unit, receiving confirmation that there is no conflict for the target location, directing one of the mobile data collector units to the target location, and collecting sensor data at the target location from the directed mobile data collector unit.

Self-organizing the distribution of the mobile data collector unit and one or more other mobile data collector units at the target location may also include, in certain embodiments, proposing a target location for the mobile data collector unit, transmitting the target location to at least one of the one or more other mobile data collector units, receiving a proposal for the new target location, directing the mobile data collector unit to the new target location, and collecting sensor data from the mobile data collector unit at the new target location.

In an additional or alternative aspect, self-organizing the distribution of the mobile data collector unit and one or more other mobile data collector units at the target location may include proposing a target location for the mobile data collector unit and determining that at least one of the one or more other mobile data collector units is at or moving to the target location. Based on at least one of the one or more other mobile data collection units being at or moving to the target location, determining a new target location, directing the mobile data collection unit to the new target location, and collecting sensor data from the mobile data collection unit at the new target location.

Self-organizing the distribution of the mobile data collector unit and one or more other mobile data collector units at the target location may further include determining a sensor type to operate at the target 1202, receiving confirmation that there is no conflict for the sensor type, instructing the mobile data collector unit to operate the sensor type at the target 1202, and collecting sensor data from the sensor type at the target 1202 from the mobile data collector unit.

In an aspect, self-organizing the distribution of the mobile data collector unit and one or more other mobile data collector units at the target location may include determining a type of sensor to operate at the target, transmitting the sensor type to at least one of the one or more other mobile data collector units, receiving a proposal for a new type of sensor, instructing the mobile data collector unit to operate the new type of sensor at the target, and collecting sensor data from the mobile data collector unit from the new type of sensor at the target.

Self-organizing the distribution of the mobile data collector unit and one or more other mobile data collector units at the target location may include determining a type of sensor operating at the target and determining that at least one of the one or more other mobile data collector units is operating or is capable of operating the type of sensor at the target. Based on whether at least one of the one or more other mobile data collector units is operating or is capable of operating the type of sensor at the target, determining a new type of sensor, instructing the mobile data collection unit to operate the new type of sensor at the target, and collecting sensor data from the new type of sensor at the target from the mobile data collection unit.

Self-organizing the distribution of the mobile data collector unit and one or more other mobile data collector units at the target location may, in some implementations, include utilizing a swarm optimization algorithm to allocate areas of sensor responsibility among the mobile data collector unit and one or more other mobile data collector units. Examples of swarm optimization algorithms include, but are not limited to, genetic algorithms (GA), ant colony optimization (ACO), particle swarm optimization (PSO), differential evolution (DE), artificial bee colony (ABC), Glowworm Swarm Optimization (GSO), and Cuckoo Search Algorithm (CSA), Genetic Programming (GP), Evolution Strategy (ES), Evolutionary Programming (EP), Firefly Algorithm (FA), Bat Algorithm (BA), Grey Wolf Optimizer (GWO), or combinations thereof.

The present disclosure describes a method for data collection in an industrial environment having self-organizing capabilities, and in one disclosed non-limiting embodiment of the present disclosure, the method may include analyzing a plurality of sensor inputs, sampling data received from the sensor inputs, and self-organizing at least one of (i) a data storage operation, (ii) a sensor collection operation providing the plurality of sensor inputs, and (iii) a selection operation of the plurality of sensor inputs.

The present disclosure describes a system for data collection in an industrial environment with automated self-organization, where the system according to one disclosed non-limiting embodiment of the present disclosure may include a data collector for handling multiple sensor inputs from sensors in the industrial environment and generating data related to the multiple sensor inputs, and a self-organizing system for self-organizing at least one of (i) data storage operations, (ii) data collection operations for sensors providing the multiple sensor inputs, and (iii) selection operations for the multiple sensor inputs.

The present disclosure describes a method for data collection in an industrial environment with self-organizing capabilities, and in one non-limiting embodiment of the present disclosure, the method may include analyzing multiple sensor inputs.

Sampling data received from the sensor inputs and self-organizing at least one of (i) a data storage operation, (ii) a sensor collection operation to provide a plurality of sensor inputs, and (iii) a selection operation of a plurality of sensor inputs, wherein the sensor collection operation to provide a plurality of sensor inputs includes receiving an instruction instructing the mobile data collector unit to operate the sensor at the target, transmitting a communication regarding the instruction to one or more other mobile data collector units, and self-organizing the distribution of the mobile data collector unit and the one or more other mobile data collector units at the target.

In an embodiment, self-organizing the distribution of the mobile data collector unit and one or more other mobile data collector units at the target includes utilizing a machine learning algorithm to determine a respective target location for each of the mobile data collector units.

In an embodiment, the machine learning algorithm determines the location of each target using one or more of a plurality of features, including the battery life of the mobile data collector unit, the type of target sensed, the type of signal sensed, the size of the target, the number of mobile data collector units required to cover the target, the number of data points required for the target, the success of previous attempts to achieve signal acquisition, information received from headquarters under instructions, and historical information regarding sensors operated at the target.

In an embodiment, self-organizing the distribution of the mobile data collector unit and one or more other mobile data collector units at the target location includes proposing a target location for the mobile data collector unit, transmitting the target location to at least one of the one or more other mobile data collector units, receiving confirmation that there is no conflict for the target location, directing the mobile data collector unit to the target location, and collecting sensor data at the target location from the mobile data collector unit.

In an embodiment, self-organizing the distribution of the mobile data collector unit and one or more other mobile data collector units at the target location includes proposing a target location for the mobile data collector unit, transmitting the target location to at least one of the one or more other mobile data collector units, receiving a proposal for the new target location, directing the mobile data collector unit to the new target location, and collecting sensor data from the mobile data collector unit at the new target location.

In an embodiment, self-organizing the distribution of the mobile data collector unit and one or more other mobile data collector units at a target location includes: proposing a target position for the mobile data collector unit; determining that at least one of the one or more other mobile data collector units is at or moving to the target position; determining a new target position based on at least one of the one or more other mobile data collector units being at or moving to the target position; directing the mobile data collector unit to the new target position; and collecting sensor data from the mobile data collector unit at the new target position.

In an embodiment, self-organizing the distribution of the mobile data collector unit and one or more other mobile data collector units at the target location includes determining a sensor type to operate at the target, receiving confirmation that there is no conflict for the sensor type, and instructing the mobile data collector unit to operate the sensor type at the target.

Collect sensor data from target sensor types from a mobile data collector unit.

The present disclosure describes a method for data collection in an industrial environment having self-organizing capabilities, and the method according to one disclosed non-limiting embodiment of the present disclosure may include analyzing a plurality of sensor inputs, sampling data received from the sensor inputs, and self-organizing at least one of: (i) a data storage operation; (ii) a sensor collection operation providing the plurality of sensor inputs; and (iii) a selection operation of the plurality of sensor inputs. The sensor collection operation providing a plurality of sensor inputs includes receiving an instruction instructing a mobile data collector unit to operate a sensor at a target, and when at least one of the plurality of sensors is located on the mobile data collector unit, the method further includes the steps of: self-organizing a selection operation of the plurality of sensor inputs; sending a communication regarding the instruction to one or more other mobile data collector units; self-organizing a distribution of the mobile data collector unit and the one or more other mobile data collector units at the target location, wherein self-organizing a distribution of the mobile data collector unit and the one or more other mobile data collector units at the target location includes determining a type of sensor to operate at the target location; sending the type of sensor to at least one of the one or more other mobile data collection units; receiving a proposal for a new type of sensor; instructing the mobile data collection unit to operate the new type of sensor at the target; and collecting sensor data from the new type of sensor at the target from the mobile data collection unit.

In an embodiment, self-organizing the distribution of the mobile data collector unit and one or more other mobile data collector units at the target location includes determining a type of sensor to operate at the target and determining that at least one of the one or more other mobile data collector units is operating or is capable of operating the type of sensor at the target. Based on whether at least one of the one or more other mobile data collection units is operating or is capable of operating the type of sensor at the target, determining a new type of sensor, instructing the mobile data collection unit to operate the new type of sensor at the target, and collecting sensor data from the new type of sensor at the target from the mobile data collection unit.

In an embodiment, self-organizing the distribution of the mobile data collector unit and one or more other mobile data collector units at the target location includes utilizing a swarm optimization algorithm to allocate sensor responsibility areas among the mobile data collector unit and one or more other mobile data collector units.

In an embodiment, the swarm optimization algorithm is one or more of the following: Genetic Algorithm (GA), Ant Colony Optimization (ACO), Particle Swarm Optimization (PSO), Differential Evolution (DE), Artificial Bee Colony (ABC), Glowworm Swarm Optimization (GSO), Cuckoo Search Algorithm (CSA), Genetic Programming (GP), Evolution Strategy (ES), Evolutionary Programming (EP), Firefly Algorithm (FA), Bat Algorithm (BA), Grey Wolf Optimizer (GWO), etc.

In an aspect, the selection operation may include receiving a signal related to at least one condition of the industrial environment 12000 and altering at least one of the analyzed sensor input and the sampling frequency based on the signal. The at least one condition of the industrial environment may be a signal-to-noise ratio of the sampled data. The selection operation may include identifying a target signal to be sensed. Additionally, the selection operation may further include identifying one or more non-target signals in the same frequency band as the target signal to be sensed and altering at least one of the analyzed sensor input and the sampling frequency based on the identified one or more non-target signals.

The selection operation may include identifying other data collectors that sense in the same signal band as the sensed target signal, and modifying at least one of the analyzed sensor input and the sampling frequency based on the identified other data collectors. In an implementation, the selection operation may further include identifying a target activity level associated with the target signal to be sensed, and modifying at least one of the analyzed sensor input and the sampling frequency based on the identified activity level.

The selection operation may further include receiving data indicative of environmental conditions near the target associated with the target signal, comparing the received environmental conditions of the target to historical environmental conditions near the target or another target similar to the target, and modifying at least one of the analyzed sensor input and the frequency of sampling based on the comparison. At least a portion of the received sampling data may be transmitted to another data collector according to a predetermined hierarchy of data collection.

In some aspects, the selection operation further includes receiving data indicative of environmental conditions near the target associated with the target signal; transmitting at least a portion of the received sampling data to another data collector according to a predetermined hierarchy of data collection; receiving feedback related to the quality or sufficiency of the transmitted data via a network connection; analyzing the received feedback; and modifying at least one of the analyzed sensor input, the frequency of sampling, the stored data, and the transmitted data based on the analysis of the received feedback.

Additionally or alternatively, the selection operation may include receiving data indicative of environmental conditions near the target associated with the target signal; transmitting at least a portion of the received sampling data to another data collector according to a predetermined hierarchy of data collection; receiving feedback related to one or more yield metrics of the transmitted data via a network connection; analyzing the received feedback; and modifying at least one of the analyzed sensor input, the frequency of sampling, the stored data, and the transmitted data based on the analysis of the received feedback.

In an implementation, the selection operations may include receiving data indicative of environmental conditions near the target associated with the target signal; transmitting at least a portion of the received sampling data to another data collector according to a predetermined hierarchy of data collection; receiving feedback related to power usage via a network connection; analyzing the received feedback; and modifying at least one of the analyzed sensor input, the sampling frequency, the stored data, and the transmitted data based on the analysis of the received feedback.

The selection operation may also include receiving data indicative of environmental conditions near the target associated with the target signal, transmitting at least a portion of the received sampling data to another data collector according to a predetermined hierarchy of data collection, receiving feedback related to the quality or sufficiency of the transmitted data via a network connection, analyzing the received feedback, and performing a dimensionality reduction algorithm on the sensed data based on the analysis of the received feedback. The dimensionality reduction algorithm may be one or more of decision trees, random forests, principal component analysis, factor analysis, linear discriminant analysis, correlation matrix-based discrimination, missing value ratio, low variance filters, random projections, non-negative matrix factorization, stacked autoencoders, chi-square or information gain, multidimensional scaling, correspondence analysis, factor analysis, clustering, and Bayesian models. The dimensionality reduction algorithm may be performed by the data collector 1208, the swarm 1206 of data collectors 1208, the network 1210, the computing system 1212, the data pool 1214, or a combination thereof. In an aspect, performing the dimensionality reduction algorithm may include transmitting the sensed data to a remote computing device.

In an aspect, a system for self-organizing the collection and storage of data collection in a power generation environment can include a data collector for processing multiple sensor inputs from various sensors. Such sensors can be components of the data collector, external to the data collector (e.g., external sensors or components of a different data collector(s)), or a combination thereof. The multiple sensor inputs can be configured to sense at least one of an operating mode, a failure mode, and a health state of at least one target system. Examples of such target systems include, but are not limited to, fuel processing systems, power sources, turbines, generators, gear systems, electrical transmission systems, transformers, fuel cells, and energy storage devices/systems. The system can also include a self-organizing system that can be configured to self-organize at least one of the following: (i) data storage operations, (ii) data collection operations for sensors providing multiple sensor inputs, and (iii) selection operations for multiple sensor inputs, as described herein.

In an aspect, the system may include a group 1206 of mobile data collectors (e.g., data collectors 1208). Additionally, in additional or alternative aspects, the self-organizing system may generate, iterate, optimize, etc., a storage specification for organizing the storage of data. The storage specification may specify, for example, which data is saved for local storage in the power generation environment and which data is output from the power generation environment for streaming over a network connection (e.g., network 1210). Other data collection, generation, and/or storage operations may be performed or enabled by the system as described herein.

In a non-limiting example, the system may include multiple sensors configured to sense various parameters in the environment of the turbine as the target system. Vibration sensors, temperature sensors, acoustic sensors, strain gauges, accelerometers, and the like may be utilized by the system to generate data regarding the operation of the turbine. As described herein, any and all of the storage, data collection, and selection operations of the multiple sensor inputs may be adapted, optimized, learned, or otherwise self-organized by the system.

In an aspect, a system for self-organizing collection and storage of data in an energy source extraction environment can include a data collector for processing multiple sensor inputs from various sensors. Examples of such energy source extraction environments include coal mining environments, metal mining environments, mineral mining environments, and oil drilling environments, although other extraction environments are also contemplated by the present disclosure. The sensors utilized can be components of the data collector, external to the data collector (e.g., external sensors or components of a different data collector(s)), or a combination thereof. The multiple sensor inputs can be configured to sense at least one of an operating mode, a failure mode, and a health state of at least one target system. Examples of such target systems include, but are not limited to, transportation systems, lifting systems, excavation systems, mining systems, digging systems, drilling systems, material handling systems, conveyor systems, pipeline systems, wastewater treatment systems, fluid pumping systems, etc.

The system may also include a self-organizing system configured to self-organize at least one of the following: (i) data storage operations, (ii) data collection operations for sensors providing multiple sensor inputs, and (iii) selection operations for multiple sensor inputs, as described herein. In an aspect, the system may include a group 1206 of mobile data collectors (e.g., data collectors 1208). Additionally, in additional or alternative aspects, the self-organizing system may generate, iterate, optimize, etc., a storage specification for organizing the storage of data. The storage specification may specify, for example, which data is saved for local storage in the power generation environment and which data is output from the power generation environment for streaming over a network connection (e.g., network 1210). Other data collection, generation, and/or storage operations may be performed or enabled by the system, as described herein.

In a non-limiting example, the system may include multiple sensors configured to sense various parameters in the environment of the fluid pump system as the target system. Vibration sensors, flow sensors, pressure sensors, temperature sensors, acoustic sensors, etc. may be utilized by the system to generate data regarding the operation of the fluid pump system. As described herein, any and all of the storage, data collection, and selection operations of the multiple sensor inputs may be adapted, optimized, learned, or otherwise self-organized by the system.

In an implementation, a system for self-organizing the collection and storage of data collection in a manufacturing environment can include a data collector for processing multiple sensor inputs from various sensors. Such sensors can be components of the data collector, external to the data collector (e.g., external sensors or components of a different data collector(s)), or a combination thereof. The multiple sensor inputs can be configured to sense at least one of an operating mode, a failure mode, and a health state of at least one target system. Examples of such target systems include, but are not limited to, power supply systems, conveyor systems, generators, assembly line systems, wafer processing systems, chemical vapor deposition systems, etching systems, printing systems, robotic handling systems, part assembly systems, inspection systems, robotic assembly systems, and semiconductor manufacturing systems. The system can also include a self-organizing system that can be configured to self-organize at least one of the following: (i) data storage operations, (ii) data collection operations for sensors providing multiple sensor inputs, and (iii) selection operations for multiple sensor inputs, as described herein.

In an aspect, the system may include a group 1206 of mobile data collectors (e.g., data collectors 1208). Additionally, in additional or alternative aspects, the self-organizing system may generate, iterate, optimize, etc., a storage specification for organizing the storage of data. The storage specification may specify, for example, which data is saved for local storage in the power generation environment and which data is output from the power generation environment for streaming over a network connection (e.g., network 1210). Other data collection, generation, and/or storage operations may be performed or enabled by the system as described herein.

In a non-limiting example, the system may include multiple sensors configured to sense various parameters in the environment of a wafer processing system as a target system. Vibration sensors, fluid flow sensors, pressure sensors, gas sensors, temperature sensors, and the like may be utilized by the system to generate data regarding the operation of the wafer handling system. As described herein, any and all of the storage, data collection, and selection operations of the multiple sensor inputs may be adapted, optimized, learned, or otherwise self-organized by the system.

Also disclosed are additional or alternative system embodiments for self-organizing the collection and storage of data collection in a refinery environment. Such system(s) may include a data collector for processing multiple sensor inputs from various sensors. Examples of such refinery environments include chemical, pharmaceutical, biological, and hydrocarbon refinery environments, although other refinery environments are also contemplated by the present disclosure. The sensors utilized may be components of the data collector, external to the data collector (e.g., external sensors or components of a different data collector(s)), or a combination thereof. The multiple sensor inputs may be configured to sense at least one of an operating mode, a failure mode, and a health state of at least one target system. Examples of such target systems include, but are not limited to, power systems, pumping systems, mixing systems, reaction systems, distillation systems, fluid processing systems, heating systems, cooling systems, evaporation systems, catalyst systems, transfer systems, and vessel systems.

The system may also include a self-organizing system that may be configured to self-organize at least one of the following: (i) data storage operations, (ii) data collection operations for sensors providing multiple sensor inputs, and (iii) selection operations for multiple sensor inputs, as described herein. In an aspect, the system may include a group 1206 of mobile data collectors (e.g., data collectors 1208). Additionally, in additional or alternative aspects, the self-organizing system may generate, iterate, optimize, etc., a storage specification for organizing the storage of data. The storage specification may specify, for example, which data is saved for local storage in the power generation environment and which data is output from the power generation environment for streaming over a network connection (e.g., network 1210). Other data collection, generation, and/or storage operations may be performed or enabled by the system, as described herein.

In a non-limiting example, the system may include multiple sensors configured to sense various parameters in the purification environment of the heating system as the target system. Temperature sensors, fluid flow sensors, pressure sensors, etc. may be utilized by the system to generate data regarding the operation of the heating system. As described herein, any and all of the storage, data collection, and selection operations of the multiple sensor inputs may be adapted, optimized, learned, or otherwise self-organized by the system.

In an aspect, a system for self-organizing the collection and storage of data collection in a distribution environment can include a data collector for processing multiple sensor inputs from various sensors. Such sensors can be components of the data collector, external to the data collector (e.g., external sensors or components of a different data collector(s)), or a combination thereof. The multiple sensor inputs can be configured to sense at least one of an operating mode, a failure mode, and a health state of at least one target system. Examples of such target systems include, but are not limited to, a power system, a conveyor system, a robotic transport system, a robotic handling system, a packaging system, a low-temperature storage system, a high-temperature storage system, a refrigeration system, a vacuum system, a transportation system, an elevator system, an inspection system, and a suspension system. The system can also include a self-organizing system that can be configured to self-organize at least one of the following (as described herein): (i) a data storage operation, (ii) a data collection operation for a sensor providing multiple sensor inputs, and (iii) a selection operation for multiple sensor inputs.

In an aspect, the system may include a group 1206 of mobile data collectors (e.g., data collectors 1208). Additionally, in additional or alternative aspects, the self-organizing system may generate, iterate, optimize, etc., a storage specification for organizing the storage of data. The storage specification may specify, for example, which data is saved for local storage in the power generation environment and which data is output from the power generation environment for streaming over a network connection (e.g., network 1210). Other data collection, generation, and/or storage operations may be performed or enabled by the system as described herein.

In a non-limiting example, the system may include multiple sensors configured to sense various parameters in the distribution environment of a target system, such as a chiller system. Power sensors, temperature sensors, vibration sensors, strain gauges, etc., may be utilized by the system to generate data regarding the operation of the system, such as a turbine. As described herein, any and all of the storage, data collection, and selection operations of the multiple sensor inputs may be adapted, optimized, learned, or otherwise self-organized by the system.

The present disclosure describes a method for data collection in an industrial environment having self-organizing capabilities, and in one disclosed non-limiting embodiment of the present disclosure, the method may include analyzing a plurality of sensor inputs, sampling data received from the sensor inputs, and self-organizing at least one of (i) a data storage operation, (ii) a sensor collection operation providing the plurality of sensor inputs, and (iii) a selection operation of the plurality of sensor inputs.

The present disclosure describes a system for data collection in an industrial environment with automated self-organization, where the system according to one disclosed non-limiting embodiment of the present disclosure may include a data collector for handling multiple sensor inputs from sensors in the industrial environment and generating data related to the multiple sensor inputs, and a self-organizing system for self-organizing at least one of (i) data storage operations, (ii) data collection operations for sensors providing the multiple sensor inputs, and (iii) selection operations for the multiple sensor inputs.

The present disclosure describes a method for data collection in an industrial environment having self-organizing capabilities, and in one disclosed non-limiting embodiment of the present disclosure, the method may include analyzing a plurality of sensor inputs, sampling data received from the sensor inputs, and self-organizing at least one of (i) a data storage operation, (ii) a sensor collection operation providing the plurality of sensor inputs, and (iii) a selection operation of the plurality of sensor inputs, wherein the selection operation includes:

The system is characterized by receiving a signal related to at least one condition of the industrial environment and, based on the signal, modifying at least one of the analyzed sensor input and the sampling frequency.

In an embodiment, at least one condition of the industrial environment is the signal-to-noise ratio of the sampled data.

In an embodiment, the selection operation includes identifying a target signal to be sensed.

In an embodiment, the selection operation further includes identifying one or more non-target signals in the same frequency band as the sensed target signal, based on which the identified one or more non-target signals modify at least one of the analyzed sensor input and the sampling frequency.

In an embodiment, the selection operation further includes identifying other data collectors that sense in the same signal band as the sensed target signal, and modifying at least one of the analyzed sensor input and the sampling frequency based on the identified other data collectors.

In an embodiment, the selecting operation further includes identifying a target activity level associated with the sensed target signal and modifying at least one of the analyzed sensor input and the sampling frequency based on the identified activity level.

In an embodiment, the selection operation further includes receiving data indicative of environmental conditions near the target associated with the target signal, comparing the received environmental conditions of the target to historical environmental conditions near the target or another target similar to the target, and altering at least one of the analyzed sensor input and the sampling frequency based on the comparison.

In an embodiment, the selection operation further includes transmitting at least a portion of the received sampling data to another data collector according to a predetermined hierarchy of data collection.

The present disclosure describes a method for data collection in an industrial environment with self-organizing capabilities. According to one non-limiting embodiment of the present disclosure, the method may include analyzing multiple sensor inputs, sampling data received from the sensor inputs, and self-organizing at least one of (i) a data storage operation, (ii) a sensor collection operation providing the multiple sensor inputs, and (iii) a selection operation of the multiple sensor inputs, where the selection operation includes identifying a target signal to be sensed. The method includes receiving a signal related to at least one condition of the industrial environment, modifying at least one of the analyzed sensor input and the sampling frequency based on the signal, receiving data indicative of a target-proximate environmental condition related to the target signal, transmitting at least a portion of the received sampled data to another data collection device according to a predetermined hierarchy of data collection, receiving feedback related to the quality or sufficiency of the transmitted data via a network connection, analyzing the received feedback, and modifying at least one of the analyzed sensor input, the sampling frequency, the stored data, and the transmitted data based on the analysis of the received feedback.

The present disclosure describes a method for data collection in an industrial environment having self-organizing capabilities. According to one disclosed, non-limiting embodiment of the present disclosure, the method can include analyzing multiple sensor inputs and sampling data received from the sensor inputs. The method self-organizes at least one of: (i) a data storage operation; (ii) a sensor collection operation providing the multiple sensor inputs; and (iii) a selection operation of the multiple sensor inputs, wherein the selection operation includes identifying a target signal to be sensed and receiving a signal associated with at least one condition of the industrial environment. The selection operation includes modifying at least one of the analyzed sensor inputs and a sampling frequency based on the signal; receiving data indicative of a target-proximate environmental condition associated with the target signal; transmitting at least a portion of the received sampling data to another data collector according to a predetermined hierarchy of data collection; receiving feedback related to one or more yield metrics of the transmitted data via a network connection; analyzing the received feedback; and modifying at least one of the analyzed sensor inputs, the sampling frequency, the stored data, and the transmitted data based on an analysis of the received feedback.

The present disclosure describes a method for data collection in an industrial environment having self-organizing capabilities. According to one disclosed, non-limiting embodiment of the present disclosure, the method can include analyzing multiple sensor inputs and sampling data received from the sensor inputs. The method self-organizes at least one of: (i) a data storage operation; (ii) a sensor collection operation providing the multiple sensor inputs; and (iii) a selection operation of the multiple sensor inputs, wherein the selection operation includes identifying a target signal to be sensed and receiving a signal associated with at least one condition of the industrial environment. The selection operation includes: modifying at least one of the analyzed sensor input and a sampling frequency based on the signal; receiving data indicative of an environmental condition near the target associated with the target signal; transmitting at least a portion of the received sampling data to another data collector according to a predetermined hierarchy of data collection; receiving feedback related to power usage via a network connection; analyzing the received feedback; and modifying at least one of the analyzed sensor input, the sampling frequency, the stored data, and the transmitted data based on an analysis of the received feedback.

The present disclosure describes a method for data collection in an industrial environment having self-organizing capabilities. According to one non-limiting embodiment of the present disclosure, the method may include analyzing a plurality of sensor inputs, sampling data received from the sensor inputs, and self-organizing at least one of (i) a data storage operation, (ii) a sensor collection operation providing the plurality of sensor inputs, and (iii) a selection operation of the plurality of sensor inputs, wherein the selection operation includes identifying a target signal to be sensed. The selection operation includes receiving a signal related to at least one condition of the industrial environment, modifying at least one of the analyzed sensor inputs and a sampling frequency based on the signal, receiving data indicative of an environmental condition near a target related to the target signal, transmitting at least a portion of the received sampled data to another data collector according to a predetermined hierarchy of data collection, receiving feedback related to the quality or sufficiency of the transmitted data via a network connection, analyzing the received feedback, and performing a dimensionality reduction algorithm on the sensed data based on the analysis of the received feedback.

In an embodiment, the dimensionality reduction algorithm is one or more of decision trees, random forests, principal component analysis, factor analysis, linear discriminant analysis, correlation matrix based classification, missing value ratio, low variance filter, random projection, non-negative matrix factorization, stacked autoencoder, chi-squared or information gain, multidimensional scaling, correspondence analysis, factor analysis, clustering, and Bayesian models.

In an embodiment, the dimensionality reduction algorithm is executed in the data collector.

In an embodiment, performing the dimensionality reduction algorithm includes transmitting the sensed data to a remote computing device.

The present disclosure describes a method for data collection in an industrial environment with self-organizing capabilities. According to one disclosed, non-limiting embodiment of the present disclosure, the method may include analyzing multiple sensor inputs and sampling data received from the sensor inputs. The method may include: (i) a data storage operation; (ii) a sensor collection operation providing multiple sensor inputs; and (iii) a selection operation of the multiple sensor inputs, wherein the selection operation includes identifying a target signal to be sensed and receiving a signal associated with at least one condition of the industrial environment. The method may further include: modifying at least one of the analyzed sensor inputs and a sampling frequency based on the signal; receiving data indicative of an environmental condition near the target associated with the target signal; transmitting at least a portion of the received sampling data to another data collection device according to a predetermined hierarchy of data collection; receiving feedback via a network connection related to at least one of the bandwidth and quality of the network connection; analyzing the received feedback; and modifying at least one of the analyzed sensor inputs, the sampling frequency, the stored data, and the transmitted data based on an analysis of the received feedback.

The present disclosure describes a system for self-organizing the collection and storage of data collection in a power generation environment. According to one disclosed, non-limiting embodiment of the present disclosure, the system may include a data collector for processing a plurality of sensor inputs from sensors in the power generation environment, the plurality of sensor inputs configured to sense at least one of an operating mode, a failure mode, and a health state of at least one target system selected from the group consisting of a fuel processing system, a power source, a turbine, a generator, a gear system, an electrical transmission system, and a transformer. The system may include the data collector configured to sense at least one of an operating mode, a failure mode, and a health state of at least one target system selected from the group consisting of a fuel processing system, a power source, a turbine, a generator, a gear system, an electrical transmission system, and a transformer, and a self-organizing system that self-organizes at least one of (i) a data storage operation, (ii) a data collection operation of sensors providing the plurality of sensor inputs, and (iii) a selection operation of the plurality of sensor inputs.

In an embodiment, the self-organizing system organizes a group of mobile data collectors to collect data from multiple target systems.

In an embodiment, the self-organizing system generates a storage specification for organizing the storage of data, the storage specification specifying data for local storage in the power generation environment and specifying data for streaming from the power generation environment over a network connection.

The present disclosure describes a system for self-organizing the collection and storage of data collection in an energy source extraction environment. According to one disclosed, non-limiting embodiment of the present disclosure, the system may include a data collector for processing a plurality of sensor inputs from sensors in the energy extraction environment, the plurality of sensor inputs configured to sense at least one of an operating mode, a failure mode, and a health status of at least one target system selected from the group consisting of a transportation system, a lifting system, an excavation system, a mining system, a drilling system, and a boring system. The system may include: (i) a data storage operation; (ii) a data collection operation of sensors providing the plurality of sensor inputs; and (iii) a self-organizing system for self-organizing at least one of the operations of selecting the plurality of sensor inputs.

In an embodiment, the self-organizing system organizes a group of mobile data collectors to collect data from multiple target systems.

In an embodiment, the self-organizing system generates a storage specification for organizing the storage of data, the storage specification specifying data for local storage in the energy extraction environment and specifying data for streaming from the energy extraction environment over a network connection.

In an embodiment, the energy source extraction environment is a coal mining environment.

In an embodiment, the energy source extraction environment is a metal mining environment.

In an embodiment, the energy source extraction environment is a mineral mining environment.

In an embodiment, the energy source extraction environment is an oil drilling environment.

The present disclosure describes a system for self-organizing the collection and storage of data collection in a manufacturing environment. According to one non-limiting embodiment of the present disclosure, the system may include a data collector for processing multiple sensor inputs from sensors in a power generation environment, the multiple sensor inputs configured to sense at least one of an operating mode, a failure mode, and a health state of at least one target system selected from the group consisting of a power system, a conveyor system, a power generator, an assembly line system, a wafer processing system, a chemical vapor deposition system, an etching system, a printing system, a robotic handling system, a component assembly system, an inspection system, a robotic assembly system, and a semiconductor manufacturing system. The system is configured to sense at least one of an operating mode, a failure mode, and a health state of a target system selected from the group consisting of a conveyor system, a power generator, an assembly line system, a wafer processing system, a chemical vapor deposition system, an etching system, a printing system, a robotic handling system, a component assembly system, an inspection system, a robotic assembly system, and a semiconductor manufacturing system. The system includes a self-organizing system that self-organizes at least one of (i) a data storage operation, (ii) a data collection operation for sensors providing the multiple sensor inputs, and (iii) a selection operation for the multiple sensor inputs.

In an embodiment, the self-organizing system organizes a group of mobile data collectors to collect data from multiple target systems.

In an embodiment, the self-organizing system generates a storage specification for organizing the storage of data, the storage specification specifying data for local storage in the manufacturing environment and specifying data for streaming from the manufacturing environment over a network connection.

The present disclosure describes a system for self-organizing the collection and storage of data collection in a refinery environment. According to one disclosed, non-limiting embodiment of the present disclosure, the system may include a data collector for processing a plurality of sensor inputs from sensors in a power generation environment, the plurality of sensor inputs configured to sense at least one of an operating mode, a failure mode, and a health state of at least one target system selected from the group consisting of a power system, a pumping system, a mixing system, a reaction system, a distillation system, and a fluid processing system. The system is configured to sense at least one of an operating mode, a failure mode, and a health state of at least one target system selected from the group consisting of a pumping system, a mixing system, a reaction system, a distillation system, a fluid processing system, a heating system, a cooling system, an evaporation system, a catalyst system, a transfer system, and a vessel system, and includes a self-organizing system that self-organizes at least one of (i) a data storage operation, (ii) a data collection operation for sensors providing the plurality of sensor inputs, and (iii) a selection operation for the plurality of sensor inputs.

In an embodiment, the self-organizing system organizes a group of mobile data collectors to collect data from multiple target systems.

In an embodiment, the self-organizing system generates a storage specification for organizing the storage of data, the storage specification specifying data for local storage within the refining environment and specifying data for streaming from the refining environment over a network connection.

In an embodiment, the purification environment is a chemical purification environment.

In an embodiment, the purification environment is a pharmaceutical purification environment.

In an embodiment, the purification environment is a biological purification environment.

In an embodiment, the refining environment is a hydrocarbon refining environment.

The present disclosure describes a system for self-organizing the collection and storage of data collection in a distribution environment. According to one non-limiting embodiment of the present disclosure, the system may include a data collector for processing a plurality of sensor inputs from sensors in the distribution environment, the plurality of sensor inputs being configured to sense at least one of an operational mode, a failure mode, and a health state of at least one target system selected from the group consisting of a power system, a conveyor system, a robotic transport system, a robotic handling system, a packaging system, a refrigerated storage system, a high-temperature storage system, and a vacuum system. The system includes: a conveyor system, a robotic transport system, a robotic handling system, a packaging system, a low-temperature storage system, a high-temperature storage system, a refrigeration system, a vacuum system, a transportation system, an elevator system, an inspection system, and a suspension system; and a self-organizing system that self-organizes at least one of (i) a data storage operation, (ii) a data collection operation of sensors providing the plurality of sensor inputs, and (iii) a selection operation of the plurality of sensor inputs.

In an embodiment, the self-organizing system organizes a group of mobile data collectors to collect data from multiple target systems.

In an embodiment, the self-organizing system generates a storage specification for organizing the storage of data, the storage specification specifying data for local storage in the delivery environment and specifying data for streaming from the delivery environment over a network connection.

With reference to FIG. 119, an exemplary system 12200 for self-organized, network-based data collection in an industrial environment is depicted. The system 12200 includes an industrial system 12202 having a number of components 12204 and a number of sensors 12206, each of the sensors 12206 operatively coupled to at least one of the components 12204. The selection, distribution, type, and communication settings of the sensors depend on the application and/or context of the system 12200.

In certain embodiments, the sensor data values 12204 are provided to a data collector 12208, which may be in communication with multiple sensors 12206 and/or with a controller 12212. In certain embodiments, a plant computer 1222 is additionally or alternatively present. In the illustrated system, the controller 12212 is configured to functionally perform the operations of the sensor communication circuitry 12224, the sensor data storage profile circuitry 12226, the sensor data storage implementation circuitry 12228, the storage planning circuitry 12230, and/or the haptic feedback circuitry 12232. The controller 12212 is depicted as a separate device for clarity of illustration. Aspects of the controller 12212 may reside on the sensors 12206, the data controller 12208, the plant computer 12210, and/or the cloud computing device 12214. In certain embodiments described throughout this disclosure, the controller 12212 or any aspect of the other controllers may reside in another device depicted in the system 12200. The plant computer 1222 represents local computing resources, such as processing, memory, and/or network resources, and may be present or in communication with the industrial system 12200. In certain embodiments, the cloud computing device 12214 represents a computing resource. The data controller 12208 is externally available to the industrial system 12202, for example, via a private network, an intranet, cellular communication, satellite communication, and/or the Internet. In certain embodiments, the data controller 12208 may be a computing device, a smart sensor, a MUX box, or other data collection device that can receive data from multiple sensors, pass the data through, and/or store the data for later transmission. An example data controller 12208 may have no storage and/or limited storage and selectively pass sensor data through, such that a subset of the sensor data is communicated at a given time, as imposed by the data controller 12208, associated network bandwidth considerations, and/or environmental constraints. In particular embodiments, one or more sensors and/or computing devices in the system 12200 are portable devices, such as a user-associated device 12216 associated with a user 12218; for example, a plant operator walking through the industrial system may have a smartphone that the system 12200 can selectively utilize as the data controller 12208, the sensors 12206—e.g., to increase communication throughput, sensor resolution, and/or as the primary method for communicating sensor data values 12244 to the controller 12212. Although the system 12200 depicts a controller 12212, a sensor 12206, a data controller 12208, a plant computer 12210, and/or a cloud computing device 12214 having memory storage thereon for storing sensor data, any one or more of these may not have memory storage thereon for storing sensor data.

The example system 12200 further includes a mesh network 12220 having multiple network nodes depicted thereon. While the mesh network 12220 is depicted in a single location for convenience of illustration, it will be understood that any network infrastructure within the system 12200 and/or in communication, even intermittently, with the system 12200 is contemplated within the system network. Additionally, any or all of the cloud server 12214, plant computer 12210, controller 12212, data controller 12208, any network-enabled sensors 12206, and/or user-associated devices 12218 may be part of a network for the system, including the mesh network 12220, during at least certain operating conditions of the system 12200. Additionally or alternatively, the system 12200 may utilize a hierarchical network, a peer-to-peer network, a peer-to-peer network with one or more supernodes, combinations thereof, hybrids thereof, and/or may include multiple networks within or in communication with the system 12200. Certain features and operations of the present disclosure may be beneficial to only one or more of these types of networks, certain features and operations of the present disclosure may be beneficial to any type of network, certain features and operations may be particularly beneficial to combinations of these networks, and/or may be beneficial to networks having multiple network options within the network, where beneficial may relate to the use of any type of option, or beneficial may relate to one or more options being a particular network type.

120, an exemplary apparatus 12222 includes a controller 12212 having a sensor communication circuit 12224 that interprets multiple sensor data values 12244 from multiple sensors 12206, and a system collaboration circuit 12228 that communicates at least a portion of the multiple sensor data values (e.g., sensor data 12244 to target storage 12252) to a storage target computing device in accordance with a sensor data transmission protocol 12232. The target computing device includes any device in the system having memory that is a target location for selected sensor data 12252, such as a cloud server 12214, a plant computer 12210, a user-associated device 12218, and/or another portion of the controller 12212 that communicates with the sensors 12206 and/or data controller 12208 via the system's network. The target computing device may be a short-term target (e.g., until a process operation is completed), a medium-term target (e.g., retain data until a specific processing operation is completed and/or until a periodic data migration occurs), and/or a long-term target (e.g., retained due to the expiration of a data retention policy and/or until a long-term data migration is planned), and/or for data storage for an unknown period of time (e.g., data is handed off to cloud server 12214, where system 12200 does not maintain control of the data in certain embodiments). In certain embodiments, the target computing device is the next computing device in the system planned to store the data. In certain embodiments, the target computing device is the next computing device in the system to which data will be moved, where such movement occurs across any aspect of the system 12200's network.

The example controller 12212 includes a transmit environment circuit 12226 that determines transmit conditions 12254 corresponding to communication of at least a portion of the number of sensor data values 12252 to a target computing device. The transmit conditions 12254 include any conditions that affect the transmission of data. For example, referring to FIG. 123, exemplary, non-limiting transmit conditions 12254 are depicted, including environmental conditions 12272 (e.g., EM noise, vibration, temperature, presence and layout of devices or components that affect transmission, such as metals, conductivity, high density, etc.). Some conditions 12272 directly affect communication, while others affect network equipment, such as routers, servers, transmitters/transceivers, etc. Example transmission conditions 12254 include network performance 12274, such as network equipment or node specifications, specified limitations of the network equipment or node (e.g., usage limits, usage authorizations, available power, etc.), estimated limitations of the network (e.g., based on equipment temperature, noise environment, etc.), and/or actual performance of the network (e.g., direct observations such as timing of messages, sending diagnostic messages, or determining throughput, and/or indirect observations by observing parameters such as memory buffers, arriving messages, etc. that tend to provide information about the performance of the network). Other example transmission conditions 12254 include network parameters 12276 such as timing parameters 12278 (e.g., clock speed, message rate, synchronous rate, asynchronous rate, etc.), protocol selection 12280 (e.g., message size including addressing information, management support bits in messages, and/or rate supported by existing or available protocols), file type selection 12282 (e.g., data transfer file type, stored file type, and network implications such as how much data must be transferred before the data is at least partially readable, how to determine that data has been transferred, likely or supported file sizes, etc.), streaming parameter selection 12284 (e.g., streaming protocol, streaming rate, priority information for streaming data, available nodes and/or computing devices for managing the streaming data, etc.), and/or compression parameters 12286 (compression algorithm and type, processing implications at each end of the message, lossy vs. lossless compression, how much information must pass before usable data is available, etc.).

With reference to FIG. 124, certain further non-limiting examples of transmission conditions 12254 corresponding to the communication of sensor data 12252 are depicted. Exemplary, non-limiting transmission conditions 12254 include the need for a mesh network 12288 (e.g., rearranging the mesh to balance throughput), a change in parent node connectivity 12290 in a hierarchically arranged network (e.g., a parent node loses connectivity, regains connectivity, and/or transitions to a different set of child nodes and/or ancestor nodes), and/or a network supernode being replaced 12292 in a hybrid peer-to-peer application layer network. As used herein, a supernode is a node that has additional capabilities from other peer-to-peer nodes. Such additional capabilities may be by design. For example, a supernode may be available to other nodes, even nodes external to the peer-to-peer node system. In certain embodiments, a supernode may additionally or alternatively have more processing power, increased network speed or throughput access, and/or more memory (e.g., for buffering, caching, and/or short-term storage), providing more capacity to fulfill the functions of the supernode.

Exemplary transmission conditions 12254 include a node in a mesh or hierarchical network being detected as malicious (e.g., from another monitoring process, heuristically, or as shown in system 12200), a peer node experiencing a change in bandwidth or connectivity 12296 (e.g., a mesh network peer that was forwarding packets lost connectivity, gained additional bandwidth, decreased available bandwidth, and/or regained connectivity). Exemplary transmission conditions 12254 include a change in the cost of transmitting information 12298 (e.g., cost increased or decreased, where cost may be a direct cost parameter such as a data transmission subscription cost or an abstracted cost parameter reflecting overall system priorities and/or the current cost of delivering information through a network hop has changed), a change in the hierarchical network layout (e.g., a network layout change 12300, such as balancing bandwidth usage in a network tree), and/or a change in the authorization scheme 12302 (e.g., a portion of the network relaying sampled data changed its permissions, authorization level, or authentication information). Specific further exemplary transmission conditions 12254 include the availability of additional connection types 12304 (e.g., a higher bandwidth network connection type becomes available and/or a lower cost network connection type becomes available), changes to the network topology 12306 (e.g., a node goes offline or online, a mesh change occurs, and/or a hierarchy change occurs), and/or a data collection client changes preferences or requirements 12308 (e.g., a data frequency requirement for at least one of the sensor value counts, a data type requirement for at least one of the sensor value counts, a sensor target for data collection, and/or a data collection client changes a storage target computing device, which may change network distribution results and routing).

The example controller 12212 includes a network management circuit 12230 that updates the sensor data transmission protocol 12232 in response to transmission conditions 12254. For example, if the transmission conditions 12254 indicate that the current routing, protocol, delivery frequency, delivery rate, and/or other parameters associated with communicating the sensor data 12252 are no longer cost-effective, feasible, suboptimal, and/or capable of improvement, the network management circuit 12230 updates the sensor data transmission protocol 12232 in response to the less cost-effective, suboptimal, and/or improved transmission conditions. The example system collaboration circuit 12228 is further responsive to the updated sensor data transmission protocol 12232, e.g., by conducting subsequent communication of the sensor data 12252 in accordance with the updated sensor data transmission protocol 12232, providing a communication to the network management circuit 12230 indicating which aspects of the updated sensor data transmission protocol 12232 cannot or are not being followed, and/or providing alerts (e.g., to an operator, network node, controller 12212, and/or network management circuit 12230) indicating that a change has been requested, that the change has been implemented, and/or that the requested change cannot or has not been implemented.

The exemplary system 12200 includes the transmission condition 12254 being an environmental condition 12272 associated with the sensor communication of the number of sensor data values 12252, the network management circuit 12230 further analyzing the environmental condition 12272, and updating the sensor data transmission protocol 12232 to modify the manner in which the number of sensor data values is transmitted from the number of sensors 12206 to the target computing device. The exemplary system further includes a data collector 12208 communicatively coupled to at least some of the number of sensors 12206 and responsive to the sensor data transmission protocol 12232, the system collaboration circuit 12228 further receiving the number of sensor data values 12244 from at least some of the number of sensors, and the transmission condition 12254 corresponding to at least one network parameter corresponding to the communication of the number of sensor data values from at least some of the number of sensors. Referring to FIG. 125, values of a number of exemplary sensor data transmission protocol 12232 are depicted. An example sensor data transmission protocol 12232 value includes a data collection rate 12310—e.g., a rate and/or frequency at which the sensors 12206 transmit, provide, or sample data, and/or a rate and/or frequency at which the data collectors 12208 receive, deliver, store, or otherwise capture sensor data. The example network management circuit 12230 further updates the sensor data transmission protocol 12232 to modify the data collectors 12208 to adjust the data collection rate 12310 for at least one of the number of sensors. Another example sensor data transmission protocol 12232 value includes a multiplexing schedule 12312, which includes data collectors 12208 and/or smart sensors configured to provide multiple sensor data values, such as in an alternating or other scheduled manner, and/or package multiple sensor values into a single message in a configured manner. The example network management circuit 12230 updates the sensor data transmission protocol 12232 to modify the multiplexing schedule of the data collectors 12208 and/or smart sensors. Another example sensor data transmission protocol 12232 value includes intermediate storage operations 12314, where intermediate storage is storage located anywhere in the system at least one network transmission prior to the target storage computing device. The intermediate storage may be implemented as an on-demand operation where a request for data (e.g., from a user, a machine learning operation, or another system component) results in subsequent transfer from the intermediate storage to the target computing device, and/or the intermediate storage may be implemented to time-shift network communications to a lower cost and/or lower network utilization time and/or to manage moment-by-moment traffic on the network. The example network management circuit 12230 updates the sensor data transmission protocol 12232 to instruct intermediate storage operations for at least a portion of a number of sensor data values, where the intermediate storage may be located at a sensor, a data collector, a node of a mesh network, a controller, a component, and/or anywhere else in the system. The exemplary sensor data transmission protocol 12232 includes commands for further data collection 12316 for at least a portion of the number of sensors—for example, because the resolution, rate, and/or frequency of sensor data provision is insufficient for some aspects of the system, to provide additional data for a machine learning algorithm, and/or because a previous resource limitation is no longer applicable and further data from one or more sensors becomes available. The exemplary sensor data transmission protocol 12232 includes commands for implementing a multiplexing schedule 12318—for example, when the data collector 12208 and/or smart sensors are capable of multiplexing sensor data but do not do so under all operating conditions, or only do so in response to the multiplexing schedule 12318 of the sensor data transmission protocol 12232.

The example network management circuit 12230 further updates the sensor data transmission protocol 12232 to adjust network transmission parameters (e.g., optional network parameters 12276) for at least a portion of the number of sensor values. For example, certain network parameters that are not control variables and/or are not currently controlled are transmission conditions 12254, certain network parameters are control variables and are subject to change in response to the data transmission protocol 12232, and/or the network management circuit 12230 can optionally control certain network parameters to become control variables. The example network management circuit 12230 further updates the sensor data transmission protocol 12232 to change any one or more of: the frequency at which data is sent; the amount of data to send; the destination (including target or intermediate destinations, and/or routing) at which the data is sent; the network protocol used to send the data; and/or the network path (e.g., providing redundant paths for transmitting the data (e.g., in cases involving high noise, high network loss, and/or critical data, the network management circuit 12230 may determine that using redundant paths for some of the data would improve system operation)). The example network management circuit 12230 can further update the sensor data transmission protocol 12232 to, for example, couple additional network paths for transmitting data (e.g., the network management circuit 12230 may have the authority to bring additional network resources online and/or selectively access additional network resources), rearrange the hierarchical network for transmitting data (e.g., add or remove hierarchical layers, change parent-child relationships, etc., to provide additional paths, fewer layers, and/or higher priority paths for critical data), rebalance the hierarchical network for transmitting data, and/or reconfigure the mesh network for transmitting data. The example network management circuit 12230 can further update the sensor data transmission protocol 12232 to delay data transmission times and/or defer data transmission times to lower-cost transmission times.

The exemplary network management circuitry further updates the sensor data transmission protocol 12232 to reduce the amount of information transmitted over the network at one time and/or updates the sensor data transmission protocol to adjust the frequency of data transmitted from a second data collector (e.g., an offset data collector within or outside the direct purview of the network management circuitry 12230, where network resource utilization from the second data collector competes with utilization from the first data collector).

The exemplary network management circuit 12230 further adjusts the external data access frequency 12234—e.g., when the expert system 12242 and/or machine learning algorithm 12248 access external data 12246 to continuously improve the system (e.g., information external to the sensor data values 12244 and/or access from an offset system or aggregated cloud-based data) and/or external data access timing (12236). Controlling the access of external data 12246 can control network utilization when system resources are low, when high fidelity and/or frequency of the sensor data values 12244 are prioritized, and/or when shifting resource utilization to lower-cost portions of the system's operating space. In particular embodiments, the system collaboration circuit 12228 accesses the external data 12246 and responds with adjusted external data access frequency 12234 and/or external data access timing values 12236. The example network management circuit 12230 further adjusts the network utilization value 12238—e.g., to maintain system utilization operation below a threshold to preserve margin and/or to avoid the need for capital-cost upgrades to the system due to capacity limitations. The example network management circuit 12230 adjusts the network utilization value 12238 to utilize bandwidth at lower cost bandwidth times—e.g., when competing traffic is low, when network utilization will not adversely impact other system processes, and/or when power consumption costs are low.

The exemplary network management circuitry further enables 12230 to utilize high-speed networks and/or request higher-cost bandwidth access when improvements in system processes are sufficient to justify the higher cost, to meet minimum data delivery requirements, and/or when aging data needs to be moved from the system before it becomes obsolete or deleted to make space for subsequent data.

The exemplary network management circuit 12230 further includes an expert system 12242, and updating the sensor data transmission protocol 12232 is further performed in response to operation of the expert system 12242. The self-organizing, network-aware data collection system can use an expert system to manage or optimize any such parameters or factors noted throughout this disclosure, individually or in combination, which expert system can include rule-based optimization, optimization based on a model of performance, and/or optimization using machine learning/artificial intelligence, optionally including deep learning approaches, or a hybrid or combination of the above. Referring to FIG. 119, numerous non-limiting examples of expert system 12242 are shown, any one or more of which may be present in an embodiment having the expert system 12242. Without being limited to any other aspects of the present disclosure relating to expert systems, machine learning operations, and/or optimization routines, example expert systems 12242 may include a rule-based system 12202 (e.g., seeded by rules based on modeling, expert input, operator experience, etc.), a model-based system 12204 (e.g., modeled responses or relationships within a system that inform specific operations of the expert system and/or coordination with other operations of the expert system), a neural net system (e.g., including rules, state machines, decision trees, conditional decisions, and/or other aspects), a Bayesian-based system 12208 (e.g., statistical modeling, managing probabilistic responses or relationships, and other decisions to manage uncertainty), a fuzzy logic-based system 12210 (e.g., determining fuzzified states of various system parameters, determining state logic for responses, and/or other decisions to manage ambiguous states of the system). Determination of fuzzification states of various system parameters, state logic for response, and de-fuzzification of truth values, and/or other decisions for managing ambiguous states of the system), and/or machine learning system 12212 (e.g., recursive, iterative, or other long-term optimization or refinement of the expert system, including searching data, resolution, sampling rate, etc. not within the scope of the expert system to determine if improved parameters not currently utilized are available), which may be added to or be an embodiment of the machine learning algorithm 12248. Any aspect of the expert system 12242 may be recalibrated, removed, and/or added during operation of the expert system 12242 in response to updated information learned by the system, information provided by a user or operator, information provided by the machine learning algorithm 12248, information from external data 12246, and/or information from an offset system.

The exemplary network management circuit 12230 further includes a machine learning algorithm 12248, and updates to the sensor data transmission protocol 12232 are further performed in response to operation of the machine learning algorithm 12248. The exemplary machine learning algorithm 12248 utilizes a machine learning optimization routine, and upon determining that an improved sensor data transmission protocol 12232 is available, the network management circuit 12230 provides the updated sensor data transmission protocol 12232 for use by the system collaboration circuit 12228. In particular embodiments, the network management circuit 12230 supplies the sensor data transmission protocol 12232 utilized by the system collaboration circuit 12228 to produce real-world results; applies modeling to the system (either first-principles modeling based on the characteristics of the system or a model utilizing actual operational data of the system) to determine what the results of a given sensor data transmission protocol 12232 would be or could have been (e.g., including obtaining extra sensor data beyond that utilized to support the process in which the system operates and/or utilizing external data 12246 and/or benchmark data 12240); and/or makes random changes to the sensor data transmission protocol 12232 to prevent the optimization routine from falling into local optima or non-optimum states.

The exemplary machine learning algorithm 12248 further utilizes feedback data including at least a portion of the transmission conditions 12254, the number of sensor values 12244, and/or where the feedback data includes benchmark data 12240. Referring to FIG. 126, non-limiting examples of benchmark data 12240 are depicted. Benchmark data 12240 may generally refer to expected data (e.g., from an expert system 12242, user input, prior experience, and/or modeling output), data from offset systems (including adjusted for variances in the intended system 12200), aggregated data of similar systems (e.g., as external data 12246, which may be cloud-based), etc. Benchmarking data may be for an entire system, a network, a node on the network, a data collector, and/or a single sensor or a selected group of sensors. Exemplary, non-limiting benchmark data may include network efficiency 12320 (e.g., throughput capability, power utilization, quality and/or integrity of communications relative to the system's 12200 infrastructure, duty cycle, and/or environmental conditions), data efficiency 12322 (e.g., data efficiency 12322 (which may include, for example, a percentage of overall successful data captured relative to a target value, a description of data gaps relative to a target value, and/or focus on important or prioritized data), comparison with offset data collector 12324 (e.g., a comparison of data collectors in systems with similar environments, data collection responsibilities, or other characteristics that make the comparison meaningful), throughput efficiency 12326 (e.g., Throughput Efficiency 12326 (e.g., utilization of available throughput, variability indicators (e.g., high variability indicates the network is oversized or has additional transmission capacity, or high variability indicates the network is responding to cost avoidance opportunities), or both depending on further context in which other information can be viewed and understood, such as why utilization differences occur), Data Validity 12328 (e.g., a determination that the captured parameters are consequently valid, are strong control parameters, and/or are highly predictive parameters, and that valid data is being acquired with acceptable resolution, sampling rate, etc.), Data Quality 12330 (e.g., data degradation due to noise, deconvolution errors, multiple operations and rounding, compression, packet loss, etc.), data precision 12342 (e.g., a determination that sufficiently accurate data is being captured, transmitted, and stored in storage), data accuracy 12340 (e.g., a determination that corrupted data, degradation due to transmission and/or storage, and/or time lags result in inaccurate data taken alone or inaccurate data when applied in a time series or other configuration), data frequency 12338 (e.g., a determination that the communicated data has sufficient time and/or frequency domain resolution to determine a response of interest), environmental response 12336 (e.g., a determination that whether environmental influences on the network are sufficiently managed to preserve other aspects of the data); signal diversity 12332 (e.g., whether there are systematic gaps that increase the consequences of degradation, e.g., 1% of the data is missing, but is it systematically a single critical sensor, or are there multiple potential sources of critical sensed parameters); critical responses (is there enough data to detect critical responses, such as supporting sensor fusion and/or pattern recognition operations); and/or mesh network coherence 12334 (e.g., keeping processors, nodes, and other aspects of the network together in a single view of applicable memory state).

Referring to Figure 127, further specific, non-limiting examples of benchmarking data 12240 are depicted. Exemplary and non-limiting benchmark data 12240 may include data coverage 12346 (e.g., what portions of desired data, critical data, etc. were successfully communicated and captured, and how is the data distributed throughout the system?), target coverage 12344 (e.g., do system components or processes have sufficient temporal and spatial resolution of sensed values?), operational efficiency 12348 (e.g., reflecting the amount of time, number of steps, or range of operations required to achieve a given result, such as if a human operator, robotic element, drone, etc. is required to accomplish the operation?), service quality commitments 12358 (e.g., service quality commitments 12358 (e.g., agreements, formal or informal commitments, and/or best practice service qualities such as maximum data gaps, minimum uptime, minimum coverage, etc.), service quality guarantees 12360 (e.g., formal agreements of service quality with known or modeled outcomes that can act on a cost function, etc.), service level agreements (SLAs, etc.), and so forth. 12362 (e.g., minimum uptime, data rate, data resolution, etc., which may be driven by industry practice, regulatory requirements, and/or formal agreements that a particular parameter, detection of a particular component, or detection of a particular process in a system meets data delivery requirements such as type, resolution, sample rate, etc.), predetermined quality of service values (e.g., user-defined values, the system's operator's policies, etc.), and/or network impairment values 12364. Exemplary and non-limiting network impairment values 12364 include network interference values (e.g., environmental noise, traffic on the network, collisions, etc.), network impairment values (e.g., components, actions, and/or objects that disrupt wireless or wired communications in areas of the network or across the network), and/or areas where network connectivity is impaired (e.g., areas where network connectivity is impaired for some reason). Loss of connectivity due to a network fault (which may be normal at least intermittently during operation), loss of power, movement of an object within the area, movement of a network node within the area (e.g., a smartphone utilized as a node), etc. In certain embodiments, the network impairment value 12364 may be caused by interference from components of the system, interference caused by one or more sensors (e.g., due to a malfunction, failure, or operation outside of expected range), interference caused by metal (or other conductive) objects, interference caused by physical obstructions (e.g., signal attenuation due to low power conditions (e.g., brownouts, scheduled power reductions, low battery, etc.), and signal attenuation due to network traffic demands on portions of the network (e.g., high traffic demands on a node or nodes during system operation).

Yet another exemplary system includes an industrial system including a number of components and a number of sensors, each operably coupled to at least one of the number of components; a sensor communication circuit that interprets a number of sensor data values from the number of sensors; and a system collaboration circuit that communicates at least a portion of the number of sensor data values over a network having a number of nodes according to a sensor data transmission protocol to a computing device to store the sensor data values. The system also includes a transmission environment circuit that determines transmission feedback corresponding to the communication of at least a portion of the number of sensor data values; and a network management circuit that updates the sensor data transmission protocol in response to the transmission feedback. The example system collaboration circuit is further responsive to the updated sensor data transmission protocol.

121, an exemplary apparatus 12256 for self-organized, network-dependent data collection in an industrial environment is depicted for an industrial system having a network with a large number of nodes. In addition to the aspects of the apparatus 1222, the apparatus 12256 further includes the system collaboration circuit 1228 transmitting an alert (e.g., as a node communication 12258) to at least one of the large number of nodes in response to the updated sensor data transmission protocol 12232. In particular embodiments, updating the sensor data transmission protocol 12232 includes the network management circuit 12230 providing node control instructions, e.g., instructions to rearrange nodes, such as providing instructions to rearrange a mesh network including the number of nodes, rearranging a hierarchical data network including the number of nodes, rearranging a peer-to-peer data network including the number of nodes, or rearranging a hybrid peer-to-peer data network including the number of nodes. In particular embodiments, the system collaboration circuit 12228 provides the node control instructions as one or more node communications 12258.

In this embodiment, updating the sensor data transmission protocol 12232 includes the network management circuit 12230 providing instructions to reduce the amount of data transmitted over the network, providing instructions to adjust the frequency of data capture transmitted over the network, providing instructions to time-shift and deliver at least a portion of the number of sensor values transmitted over the network (e.g., providing instructions to modify a network protocol corresponding to the network, providing instructions to reduce the throughput of at least one device connected to the network, providing instructions to reduce network bandwidth usage, providing instructions to compress data corresponding to at least a portion of the number of sensor values transmitted over the network, providing instructions to condense data corresponding to at least a portion of the number of sensor values transmitted over the network (e.g., providing a relevant subset, providing data with a reduced sample rate, etc.), providing instructions to summarize data (e.g., providing instructions to synchronize the network). The methods include providing instructions for summarizing (e.g., statistical descriptions, aggregated values, etc.) data corresponding to at least a portion of the number of sensor values transmitted over the network, providing instructions for encrypting data corresponding to at least a portion of the number of sensor values transmitted over the network (e.g., to enable the use of alternative, less secure network paths and/or to access alternative network paths that require encryption), providing instructions for distributing data corresponding to at least a portion of the number of sensor values to a distributed ledger, providing instructions for distributing data corresponding to at least a portion of the number of sensor values to a central server (e.g., plant computer 12210 and/or cloud server 12214), providing instructions for distributing data corresponding to at least a portion of the number of sensor values to a supernode, and providing instructions for redundantly distributing data corresponding to at least a portion of the number of sensor values across multiple network connections. In certain embodiments, updating the sensor data transmission includes providing instructions to deliver data corresponding to at least a portion of the number of sensor values to one of the components (e.g., where one or more components 12204 in the system have memory storage and communicative access to the sensors 12206, the data collectors 12208, and/or a network), and/or where one of the components is communicatively coupled to a sensor providing data corresponding to at least a portion of the number of sensor values (e.g., where the data stored on the component 12204 is the component where the data was measured or is in proximity to the sensor 12206 that took the data).

An example network includes a mesh network, and the network management circuit 12230 further updates the sensor data transmission protocol 12232 to provide instructions to eject one of the nodes from the mesh network (e.g., remove it from a mesh map, take it out of service, etc.). An example network includes a peer-to-peer network, and the network management circuit 12230 further updates the sensor data transmission protocol 12232 to provide instructions to eject one of the nodes from the peer-to-peer network.

The exemplary network management circuit 12230 further updates the sensor data transmission protocol 12232 to cache at least a portion of the number of sensor values 12252 (e.g., as a sensor data cache 12260). In certain further embodiments, the network management circuit 12230 further updates the sensor data transmission protocol 12232 to communicate the cached sensor values 12260 in response to at least one of the following: a user, a model, a machine learning algorithm, an expert system, etc. has requested the data; network feedback indicates that communication of the cached data is available (e.g., prior network restrictions that prompted the network management circuit 12230 to cache have now been lifted or improved); and/or higher priority data exists that requires utilization of cache resources to hold the cached data 12260.

An exemplary system 12200 for self-organized, network-dependent data collection in an industrial environment includes an industrial system 12202 having a number of components 12204 and a number of sensors 12206, each operably coupled to at least one of the number of components 12204. A sensor communication circuit 12224 interprets a number of sensor data values 12244 from the number of sensors at a predetermined frequency. A system collaboration circuit 12228 communicates at least a portion of the number of sensor data values 12252 over a network having a number of nodes to a computing device for storage in accordance with a sensor data transmission protocol 12232, the sensor data transmission protocol 12232 including a predetermined hierarchy of data collection and a predetermined frequency. An exemplary data management circuit 12230 adjusts the predetermined frequency in response to transmission conditions 12254 and/or benchmark data 12240.

An exemplary system 12200 for self-organized, network-dependent data collection in an industrial environment includes an industrial system 12202 having a number of components 12204 and a number of sensors 12206, each operably coupled to at least one of the number of components 12204. A sensor communication circuit 12224 interprets a number of sensor data values 12244 from the number of sensors 12206 at a predetermined frequency, and a system collaboration circuit 12228 communicates at least a portion of the number of sensor data values 12252 over a network having a number of nodes to a computing device for storage according to a sensor data transmission protocol. A transmission environment circuit 12226 determines transmission feedback (e.g., transmission conditions 12254) corresponding to communication of at least a portion of the number of sensor data values 12252 over the network. The network management circuit 12230 updates the sensor data transmission protocol 12232 in response to the transmission feedback 12254, and the network notification circuit 12268 provides an alert value 12264 in response to the updated sensor data transmission protocol 12232. Example alert values 12264 include notifying an operator, notifying a user, notifying a portable device associated with the user, notifying a node in the network, notifying a cloud computing device, notifying a plant computing device, and/or providing an alert as external data to an offset system. Example, non-limiting, warning conditions include a component of the system operating in a fault state, a process of the system operating in a fault state, network communication limitations triggering the use of cache and/or intermediate storage for sensor values, a change in the sensor data transmission protocol (including a change in the type selected), and/or a change in the sensor data transmission protocol that may result in a loss of data fidelity or resolution (e.g., data compression, data condensation, and/or data summarization).

Exemplary transmission feedback includes feedback values such as: a change in transmission price, a change in storage price, a loss of connectivity, a decrease in bandwidth, a change in connectivity, a change in network availability, a change in network range, a change in wide area network (WAN) connectivity, and/or a change in wireless local area network (WLAN) connectivity.

An exemplary system includes an assembly line industrial system having multiple vibrating components, such as motors, conveyors, fans, and/or compressors. The system includes multiple sensors that determine various parameters associated with the vibrating components, including determining one or more diagnostic and/or process-related information for the components (e.g., proper operation, abnormal operation, operating speed, impending service or failure, etc.). Examples of sensors include, but are not limited to, noise, vibration, acceleration, temperature, shaft speed, etc. The sensor information is communicated, at least in part, to a target storage system via a network communicatively coupled to the assembly line industrial system. The example system includes a network management circuit that determines a sensor data transmission protocol for controlling the flow of data from the sensors to the target storage system. The network management circuit, associated expert system, and/or associated machine learning algorithms update the sensor data transmission protocol to ensure efficient network utilization, sufficient delivery of data to support system control, diagnostic, and/or other decisions planned for the data outside the system, reduced resource utilization of data transmission, and/or to accommodate changes in system or related aspects, such as system noise factors, variability, and/or costs or environmental parameters. The illustrated systems include improvements to system operations to ensure the completion of diagnostic, control, or other data-dependent operations, to reduce costs while maintaining performance, and/or to increase system capabilities over time or process cycles.

An exemplary system includes an automated robotic handling system that includes numerous components, such as actuators, gearboxes, and/or rail guides. The system includes numerous sensors that determine various parameters related to the components, including, but not limited to, actuator position and/or feedback sensors, vibration, acceleration, temperature, imaging sensors, and/or spatial position sensors (e.g., within the handling system, associated plant, and/or GPS-type positioning). The sensor information is communicated to a target storage system at least in part via a network communicatively coupled to the automated robotic handling system. The exemplary system includes a network management circuit that determines a sensor data transmission protocol for controlling the flow of data from the sensors to the target storage system. The network management circuit, associated expert systems, and/or associated machine learning algorithms update the sensor data transmission protocol to ensure efficient network utilization, sufficient delivery of data to support system control, diagnosis, improvement, and/or control. The system also performs processing efficiency updates and/or other planned decisions on data external to the system to address changes in system noise factors, variability, and related aspects, such as system costs and environmental parameters, to reduce data transmission resource usage. Exemplary systems include improvements to system operations to ensure the completion of diagnostic, control, or other data-dependent operations, to reduce costs while maintaining performance, and/or to increase system capacity over time or process cycles.

An exemplary system includes a mining operation, including surface and/or underground mining operations. The exemplary mining operation includes components such as underground inspection systems, pumps, ventilation, generators and/or power generation, gas composition or quality systems, and/or process stream composition systems (e.g., determining desired material composition and/or waste stream composition for pollution and/or regulatory control). Various sensors are present in the illustrated system to control operations, determine component status, support safe operation, and/or support regulatory compliance. Sensor information is communicated, at least in part, to a target storage system via a network communicatively coupled to the mining operation. In certain embodiments, the mining operation's network infrastructure exhibits high variability due to, but not limited to, significant environmental fluctuations (e.g., fluctuations in pit or shaft conditions) and/or intermittent availability (e.g., shutting down electronic equipment during certain mining operations, difficulty in providing network access to portions of the mining operation, and/or the desirability of including mobile or intermittently available devices within the network infrastructure). The example system includes a network management circuit that determines a sensor data transmission protocol for controlling the flow of data from the sensors to the target storage system. The network management circuit, associated expert system, and/or associated machine learning algorithms update the sensor data transmission protocol for efficient network utilization, adequate distribution of data to support system control, diagnostics, improved and/or updated processing efficiency, support for financial and/or regulatory compliance, and/or other decisions designed for data outside the system, reduced resource utilization for data transmission, and/or to accommodate changes in system or related aspects, such as system noise factors, variability, network infrastructure challenges, and/or costs or environmental parameters.

Examples of systems include aerospace systems, such as airplanes, helicopters, satellites, spacecraft or launchers, orbital platforms, and/or missiles. Aerospace systems have numerous systems supported by sensors, such as those monitoring engine operation, control surface status and vibration, environmental conditions (internal and external), and telemetry support. Furthermore, aerospace systems vary widely in both the number of different types of sensors (e.g., few fuel pressure sensors, many control surface sensors) and the sampling rates for relevant decisions across different types of sensors (e.g., cabin pressure may require one second of data, while weather radar and engine speed sensors may require much higher time resolution). Computing power in aerospace applications is at a premium due to power consumption and weight considerations. Accordingly, iterative, recursive, deep learning, expert systems, and/or machine learning operations to improve any system on the aerospace system, including sensor data acquisition and transmission of sensor information, are, in many embodiments, driven to a computing device external to the system's aerospace vehicle (e.g., through offline learning, post-processing, etc.). Storage capacity in aerospace applications is similarly expensive, and long-term storage of sensor data onboard aerospace vehicles is not a cost-effective solution in many embodiments. Furthermore, network communications from aircraft can experience high variability and bandwidth limitations as the aircraft rapidly moves through the environment or enters areas where direct communication with ground resources is impractical. Furthermore, certain aerospace applications experience significant competition for available network resources. For example, in environments with a large number of passengers, passenger use of the network infrastructure consumes significant bandwidth. Therefore, operating network management circuitry, associated expert systems, and/or associated machine learning algorithms to update sensor data transmission protocols can significantly improve sensing operations in various aerospace systems. Furthermore, the large number of offset systems in certain aerospace applications can improve the capabilities of expert systems or machine learning algorithms to improve sensor data acquisition and transmission operations and manage the high variability of system sensing parameters (frequency, data rate, and/or data resolution) regardless of operating conditions.

Exemplary systems include oil or gas production systems such as production platforms (onshore or offshore), pumps, rigs, drilling equipment, blenders, etc. Oil and gas production systems exhibit high variability in sensed variable types and parameters, such as vibrations (e.g., pumps, rotating shafts, fluid flow through piping, etc.), gas composition (e.g., near wellhead areas, personnel zones, storage tanks, etc.) (data may be acquired infrequently or may not be acquired at certain times, such as when personnel are not present), and pressure values (both the required resolution and frequency or sampling rate can vary widely depending on the operations currently occurring in the system). Furthermore, oil and gas production systems exhibit significant variability in network infrastructure depending on the system (e.g., offshore platforms versus long-term land-based production facilities) and depending on the operations being performed on the system (e.g., a wellhead during production may have limited network access, while a drilling or fracturing operation may have a large network infrastructure at the operating site). Thus, it can be seen that the operation of network management circuits, associated expert systems, and/or associated machine learning algorithms to update sensor data transmission protocols can significantly improve sensing operations in various oil or gas production systems.

The present disclosure describes a system for self-organized, network-dependent data collection in an industrial environment. According to one non-limiting embodiment of the present disclosure, the system may include an industrial system including a plurality of components, a plurality of sensors, each operably coupled to at least one of the plurality of components, and a sensor communication circuit configured to interpret a plurality of sensor data values from the plurality of sensors. The system may also include a system collaboration circuit configured to communicate at least a portion of the plurality of sensor data values to a storage target computing device according to a sensor data transmission protocol, a transmission environment circuit configured to determine transmission conditions corresponding to the communication of at least a portion of the plurality of sensor data values to the storage target computing device, and a network management circuit configured to update the sensor data transmission protocol in response to the transmission conditions, wherein the system collaboration circuit is further responsive to the updated sensor data transmission protocol.

In an embodiment, the transmission conditions include environmental conditions associated with sensor communication of the plurality of sensor data values, the network management circuitry is further configured to analyze the environmental conditions, and updating the sensor data transmission protocol includes modifying how the plurality of sensor data values are transmitted from the plurality of sensors to the target computing device.

In an embodiment, a data collector is communicatively coupled to at least some of the plurality of sensors and responsive to a sensor data transmission protocol, wherein the system interaction circuitry is configured to receive a plurality of sensor data values from at least some of the plurality of sensors, and the transmission conditions correspond to at least one network parameter corresponding to communication of the plurality of sensor data values from at least some of the plurality of sensors.

In an embodiment, the network management circuitry is further configured to update the sensor data transmission protocol to modify the data collector to adjust the data collection rate of at least one of the plurality of sensors.

In an embodiment, the network management circuitry is further configured to update the sensor data transmission protocol to modify the multiplexing schedule of the data collector.

In an embodiment, the network management circuitry is further configured to update the sensor data transmission protocol to instruct intermediate storage operations for at least a portion of the plurality of sensor data values.

In an embodiment, the network management circuitry is further configured to update a sensor data transmission protocol to instruct at least some of the plurality of sensors to collect additional data.

In an embodiment, the network management circuitry is further configured to update the sensor data transmission protocol to modify the data collectors to implement the multiplexing schedule.

In an embodiment, the network management circuitry is further configured to update the sensor data transmission protocol to adjust network transmission parameters for at least some of the plurality of sensor values.

In an embodiment, the adjusted network transmission parameters include at least one parameter selected from the following parameters: timing parameters, protocol selection, file type selection, streaming parameter selection, and compression parameters.

In an embodiment, the network management circuitry is further configured to update the sensor data transmission protocol to change the frequency of the transmitted data.

In an embodiment, the network management circuitry is further configured to update the sensor data transmission protocol to change the amount of data transmitted.

In an embodiment, the network management circuitry is further configured to update the sensor data transmission protocol to change the destination of the transmitted data.

In an embodiment, the network management circuitry is further configured to update the sensor data transmission protocol to change the network protocol used to transmit the data.

In an embodiment, the network management circuitry is further configured to update the sensor data transmission protocol to add redundant network paths for transmitting data.

In an embodiment, the network management circuitry is further configured to update the sensor data transmission protocol to couple additional network paths for transmitting data.

In an embodiment, the network management circuitry is further configured to update the sensor data transmission protocol to rearrange the hierarchical network for transmitting data.

In an embodiment, the network management circuitry is further configured to update the sensor data transmission protocol to rebalance the hierarchical network for transmitting data.

In an embodiment, the network management circuitry is further configured to update the sensor data transmission protocol to reconfigure the mesh network for transmitting data.

In an embodiment, the network management circuitry is further configured to update the sensor data transmission protocol to delay the data transmission time.

In an embodiment, the network management circuitry is further configured to update the sensor data transmission protocol to delay the data transmission time to a lower-cost transmission time.

In an embodiment, the network management circuitry is further configured to update the sensor data transmission protocol to reduce the amount of information transmitted over the network at one time.

In an embodiment, the network management circuitry is further configured to update the sensor data transmission protocol to adjust the frequency of data transmitted from the second data collector.

In an embodiment, the network management circuitry is further configured to adjust the external data access frequency, and the system interaction circuitry is responsive to the adjusted external data access frequency.

In an embodiment, the network management circuitry is further configured to adjust the external data access timing value, and the system collaboration circuitry is responsive to the adjusted external data access timing value.

In an embodiment, the network management circuitry is further configured to adjust the network utilization value.

In an embodiment, the network management circuitry is further configured to adjust the network utilization value to utilize bandwidth at lower cost bandwidth times.

In an embodiment, the network management circuitry is further configured to enable utilization of high-speed networks.

In an embodiment, the network management circuitry is further configured to request higher cost bandwidth access and update the sensor transmission protocol in response to the higher cost bandwidth access.

In an embodiment, the network management circuitry further includes an expert system, and updating the sensor data transmission protocol is further responsive to operation of the expert system.

In an embodiment, the network management circuitry further includes a machine learning algorithm, and updating the sensor data transmission protocol is further performed in response to operation of the machine learning algorithm.

In an embodiment, the machine learning algorithm is further configured to utilize feedback data including transmission conditions.

In an embodiment, the feedback data further includes at least a portion of the plurality of sensor values.

In an embodiment, the feedback data further includes benchmark data.

In an embodiment, the benchmark data further includes data selected from the list consisting of network efficiency, data efficiency, comparison with offset data collectors, throughput efficiency, data availability, data quality, data precision, data accuracy, and data frequency.

In an embodiment, the benchmark data further includes data selected from the list consisting of environmental response, mesh networking coherence, data coverage, target coverage, signal diversity, critical response, and operational efficiency.

In an embodiment, the transmission conditions corresponding to the communication include at least one condition selected from the following: a mesh network needs to reorganize to balance throughput; connectivity of a parent node in a hierarchically arranged network has changed; a network supernode in a hybrid peer-to-peer application layer network has been replaced; or a node in the mesh network or hierarchical network has been detected as malicious.

In an embodiment, the transmission conditions corresponding to the communication include at least one condition selected from the following: a mesh network peer forwarding the packet has lost connectivity; a mesh network peer forwarding the packet has gained additional bandwidth; a mesh network peer forwarding the packet has reduced bandwidth; and a mesh network peer forwarding the packet has regained connectivity.

In an embodiment, the transmission conditions corresponding to the communication include at least one condition selected from the following conditions: a change in the permissions, authentication level, or entitlements of a portion of the network relaying the sampling data; a change in the current cost of delivering information over a network hop; the availability of a higher bandwidth network connection type; the availability of a lower cost network connection type; and a change in the network topology.

In an embodiment, the transmission conditions corresponding to the communication include at least one condition selected from the following conditions: the data collection client has changed the data frequency requirement of at least one of the plurality of sensor values; the data collection client has changed the data type requirement of at least one of the plurality of sensor values; the data collection client has changed the sensor target for data collection; and the data collection client has changed the computing device of the storage target.

The present disclosure describes a system for self-organized, network-dependent data collection in an industrial environment. According to one disclosed, non-limiting embodiment of the present disclosure, the system may include an industrial system including a plurality of components; a plurality of sensors, each operably coupled to at least one of the plurality of components; a sensor communication circuit configured to interpret a plurality of sensor data values from the plurality of sensors; and a system collaboration circuit configured to communicate at least some of the plurality of sensor data values over a network. The system collaboration circuit includes a plurality of nodes on a storage target computing device according to a sensor data transmission protocol; a transmission environment circuit configured to determine transmission feedback corresponding to the communication of at least some of the plurality of sensor data values over the network; and a network management circuit configured to update the sensor data transmission protocol in response to the transmission feedback, wherein the system collaboration circuit is further responsive to the updated sensor data transmission protocol.

In an embodiment, the system integration circuitry is further configured to send an alert to at least one of the plurality of nodes in response to the updated sensor data transmission protocol.

In an embodiment, updating the sensor data transmission includes at least one operation selected from the following: providing instructions to reorganize a mesh network including a plurality of nodes; providing instructions to reorganize a hierarchical data network including a plurality of nodes; reorganizing a peer-to-peer data network including a plurality of nodes; and reorganizing a hybrid peer-to-peer data network including a plurality of nodes.

In an embodiment, updating the sensor data transmission includes at least one operation selected from the following: providing instructions to reduce the amount of data transmitted over the network; providing instructions to adjust the frequency of data capture transmitted over the network; providing instructions to time-shift delivery of at least a portion of the plurality of sensor values transmitted over the network; and providing instructions to modify a network protocol corresponding to the network.

In an embodiment, updating the sensor data transmission includes at least one operation selected from the following: providing instructions to reduce the throughput of at least one device coupled to the network; providing instructions to reduce bandwidth usage of the network; and providing instructions to compress data corresponding to at least some of the plurality of sensor values transmitted over the network. Examples of operations include providing instructions to condense data corresponding to at least some of the plurality of sensor values transmitted over the network; providing instructions to summarize data corresponding to at least some of the plurality of sensor values transmitted over the network; and providing instructions to encrypt data corresponding to at least some of the plurality of sensor values transmitted over the network.

In an embodiment, updating the sensor data transmission includes at least one operation selected from the following: providing instructions to distribute data corresponding to at least some of the plurality of sensor values to a distributed ledger; providing instructions to distribute data corresponding to at least some of the plurality of sensor values to a central server; providing instructions to distribute data corresponding to at least some of the plurality of sensor values to a supernode; and providing instructions to redundantly distribute data corresponding to at least some of the plurality of sensor values over multiple network connections.

In an embodiment, updating the sensor data transmission includes providing instructions to deliver data corresponding to at least a portion of the plurality of sensor values to one of the plurality of components.

In an embodiment, one of the plurality of components is communicatively coupled to a sensor that provides data corresponding to at least a portion of the plurality of sensor values.

In an embodiment, the system collaboration circuitry is further configured to interpret the quality of service commitment, and the network management circuitry is further configured to further update the sensor data transmission protocol in response to the quality of service commitment.

In an embodiment, the system collaboration circuitry is further configured to interpret a service level agreement, and the network management circuitry is further configured to further update the sensor data transmission protocol in response to the service level agreement.

In an embodiment, the network management circuitry is further configured to update the sensor data transmission protocol to provide instructions to improve the quality of service value.

In an embodiment, the network includes a mesh network, and the network management circuitry is further configured to update the sensor data transmission protocol to provide instructions to eject one of the plurality of nodes from the mesh network.

In an embodiment, the network includes a peer-to-peer network, and the network management circuitry is further configured to update the sensor data transmission protocol to provide instructions to eject one of the plurality of nodes from the peer-to-peer network.

In an embodiment, the network management circuitry is further configured to update the sensor data transmission protocol to cache at least a portion of the plurality of sensor values.

In an embodiment, the network management circuitry is further configured to update the sensor data transmission protocol to communicate at least a cached portion of the plurality of sensor values in response to at least one of a determination that the cached data has been requested, a determination that there is network feedback indicating that the cached data is available for communication, and a determination that there is higher priority data requiring utilization of the cache resources that hold the cached data.

In an embodiment, the system further includes a data collector configured to receive at least a portion of the plurality of sensor data values, wherein at least a portion of the plurality of sensor data values includes data provided by a plurality of sensors, and the transmitted feedback includes network performance information corresponding to the data collector.

In an embodiment, the system further includes a data collector configured to receive at least a portion of a plurality of sensor data values, where at least a portion of the plurality of sensor data values includes data provided by a plurality of sensors, and a second data collector communicatively coupled to the network, where the transmitted feedback includes network performance information corresponding to the second data collector.

The present disclosure describes a system for data collection relying on a self-organizing network in an industrial environment. According to one non-limiting embodiment of the present disclosure, the system may include an industrial system including a plurality of components, a plurality of sensors, each operably coupled to at least one of the plurality of components, and a sensor communication circuit configured to interpret a plurality of sensor data values from the plurality of sensors at a predetermined frequency. The system collaboration circuit is configured to communicate at least a portion of the plurality of sensor data values to a computing device for storage according to a sensor data transmission protocol over a network having a plurality of nodes, the sensor data transmission protocol including a predetermined hierarchy of data collection and a predetermined frequency; a transmission environment circuit configured to determine transmission feedback corresponding to communication of at least a portion of the plurality of sensor data values over the network; and a network management circuit configured to update the sensor data. The system collaboration circuit updates the data transmission protocol in response to the transmission feedback and further in response to the benchmark data, and the system collaboration circuit is further responsive to the updated sensor data transmission protocol.

In an embodiment, updating the transmission of sensor data includes at least one operation selected from the operations of: providing instructions to change the sensor of a plurality of sensors; providing instructions to adjust a predetermined frequency; and providing instructions to adjust the amount of stored sensor data values. Also, the operations include issuing instructions to adjust a data transmission rate for communication of at least some of the plurality of sensor data values; issuing instructions to adjust a data transmission time for communication of at least some of the plurality of sensor data values; and issuing instructions to adjust a network method for communication over a network.

In an embodiment, the benchmark data further includes data selected from the list consisting of network efficiency, data efficiency, comparison with offset data collectors, throughput efficiency, data availability, data quality, data precision, data accuracy, and data frequency.

In an embodiment, the benchmark data further includes data selected from the list consisting of environmental response, mesh networking coherence, data coverage, target coverage, signal diversity, critical response, and motion.

In an embodiment, the benchmark data further includes data selected from the list consisting of network interference values, network impairment values, and areas of impaired network connectivity.

In an embodiment, the transmission feedback includes a communications interference value selected from the following values: interference due to components of the system, interference due to one of the sensors, interference due to metal objects, interference due to physical obstructions, attenuated signals due to low power conditions, and attenuated signals due to network traffic demands in a portion of the network.

The present disclosure describes a system for self-organized, network-dependent data collection in an industrial environment. According to one non-limiting embodiment of the present disclosure, the system may include an industrial system including a plurality of components and a plurality of sensors, each operably coupled to at least one of the plurality of components. The system may include: a sensor communication circuit configured to interpret a plurality of sensor data values from the plurality of sensors at a predetermined frequency; a system interaction circuit configured to communicate at least some of the plurality of sensor data values over a network having a plurality of nodes according to a sensor data transmission protocol to a computing device to store the sensor data values; a transmission environment circuit configured to determine transmission feedback corresponding to the communication of at least some of the plurality of sensor data values over the network; a network management circuit configured to update the sensor data transmission protocol in response to the transmission feedback; and a network notification circuit configured to provide an alert value in response to the updated sensor data transmission protocol, wherein the system interaction circuit is further responsive to the updated sensor data transmission protocol.

In an embodiment, the transmission feedback includes at least one feedback value selected from the following values: a change in transmission price, a change in storage price, a loss of connectivity, a reduction in bandwidth, a change in connectivity, a change in network availability, a change in network range, a change in wide area network (WAN) connectivity, and a change in wireless local area network (WLAN) connectivity.

In an embodiment, the network management circuit further includes an expert system, and updating the sensor data transmission protocol is further performed in response to operation of the expert system.

In an embodiment, the expert system includes at least one system selected from the group consisting of a rule-based system, a model-based system, a neural net system, a Bayesian-based system, a fuzzy logic-based system, and a machine learning system.

In an embodiment, the network management circuitry further includes a machine learning algorithm, and updating the sensor data transmission protocol is further performed in response to operation of the machine learning algorithm.

In an embodiment, the machine learning algorithm is further configured to utilize feedback data including transmission conditions.

In an embodiment, the feedback data further includes at least a portion of the plurality of sensor values.

In an embodiment, the feedback data further includes benchmarking data.

In an embodiment, the benchmark data further includes data selected from the list consisting of network efficiency, data efficiency, comparison with offset data collectors, throughput efficiency, data availability, data quality, data precision, data accuracy, and data frequency.

In an embodiment, the benchmark data further includes data selected from the list consisting of environmental response, mesh networking coherence, data coverage, target coverage, signal diversity, critical response, and operational efficiency.

With reference to FIG. 128, an exemplary system 12500 for data collection in an industrial environment includes an industrial system 12502 having a number of components 12504 and a number of sensors 12506, each of the sensors 12506 operatively coupled to at least one of the components 12504. The selection, distribution, type, and communication settings of the sensors depend on the application and/or context of the system 12500.

The exemplary system 12500 further includes a sensor communication circuit 12522 (see FIG. 129) that interprets multiple sensor data values 12542. The exemplary system may include a set of sensors that may be considered to support sensor fusion operations, such as detecting system operating conditions that affect a desired output, to control a process or portion of the industrial system 12502, or to diagnose or predict aspects of the industrial system 12502 or processes associated with the industrial system 12502.

In certain embodiments, the sensor data values 12542 are provided to a data collector 12508, which may be in communication with multiple sensors 12506 and/or with a controller 12512. In certain embodiments, a plant computer 12510 is additionally or alternatively present. In the illustrated system, the controller 12512 is configured to functionally perform the operations of the sensor communication circuitry 12522, the sensor data storage profile circuitry 12524, the sensor data storage implementation circuitry 12526, the storage planning circuitry 12528, and/or the haptic feedback circuitry 12530. The controller 12512 is depicted as a separate device for clarity of illustration. Aspects of the controller 12512 may reside on the sensors 12506, the data controller 12508, the plant computer 12510, and/or the cloud computing device 12514. In certain embodiments described throughout this disclosure, the controller 12512, or any aspect of the other controller, may reside in another device depicted on the system 12500. The plant computer 12510 represents local computing resources, e.g., processing, memory, and/or network resources, that may reside on and/or be in communication with the industrial system 12500. In certain embodiments, the cloud computing device 12514 represents computing resources available externally to the industrial system 12502, e.g., via a private network, an intranet, cellular communications, satellite communications, and/or the Internet. In certain embodiments, the data controller 12508 may be a computing device, smart sensor, MUX box, or other data collection device that can receive data from multiple sensors, pass the data through, and/or store the data for later transmission. An example data controller 12508 may have no storage and/or limited storage and selectively pass sensor data through, communicating a subset of the sensor data at a given time, as imposed by the data controller 12508, associated network bandwidth considerations, and/or environmental constraints. In certain embodiments, one or more sensors and/or computing devices in the system 12500 are portable devices; for example, a plant operator walking through the industrial system may have a smartphone, which the system 12500 can selectively utilize as the data controller 12508, sensors 12506, for example, to increase communication throughput, sensor resolution, and/or as the primary method for communicating sensor data values 12542 to the controller 12512. The system 12500 depicts the controller 12512, sensors 12506, data controller 12508, plant computer 12510, and/or cloud computing device 12514 having memory storage thereon for storing sensor data, any one or more of which may not have memory storage thereon for storing sensor data. In particular embodiments, the sensor data storage profile circuit 12524 prepares a data storage profile 12532 that directs the sensor data to memory storage, including moving the sensor data from one memory storage device to another in a controlled manner. Sensor data stored in various devices consumes memory on the devices, transferring stored data between devices consumes network and/or communication bandwidth in the system 12500, and/or operations on the sensor data, such as processing, compression, statistical analysis, summarizing, and/or providing alerts, consumes processor cycles and memory to support operations, such as buffer files, intermediate data, etc. Thus, improved or optimal configuration and/or updates of the data storage profile 12532 may provide lower utilization of system resources and/or allow for storage of sensor data at higher resolution, over longer time frames, and/or from a larger number of sensors.

129, an exemplary apparatus 12520 for self-organizing data storage for a data collector of an industrial system is depicted. The exemplary apparatus 12520 includes a controller, such as the controller 12512. The exemplary controller includes a sensor communication circuit 12522 that interprets a number of sensor data values 12542 and a sensor data storage profile circuit 12524 that determines a data storage profile 12532. The data storage profile 12532 includes a data storage plan for the number of sensor data values 12542. The data storage plan includes how many of the sensor data values 12542 to initially store (e.g., when the data is sampled and/or after initial transmission to the data controller 12508, the plant computer 12510, the controller 12512, and/or the cloud computing device 12514). An example data storage profile 12532 includes a schedule for the transmission of data, which may be according to time, process stage, operating conditions of the system 12500 and/or a network associated with the system, and communication conditions of devices within the system 12500.

For example, data from a temperature sensor can be stored locally on the sensor with storage capacity and scheduled to be transmitted in bursts to a data controller. The data controller may be instructed to transmit the sensor data to a cloud computing device on a scheduled basis, such as when the data controller's memory reaches a threshold, when network communication capacity becomes available, at the end of a process, and/or on demand. Additionally or alternatively, data from the sensor may be modified on the device or as the data is transferred (e.g., immediately before transfer, immediately after transfer, or on a scheduled basis). For example, the data retention profile 12532 may describe storing high-resolution, high-accuracy, and/or high-sampling-rate data and reducing the retention of the data set for a period of time, after a selected event and/or confirmation of a successful process, or after confirmation that the high-resolution data is no longer needed. Thus, high-resolution data and/or data from multiple sensors can be made available for sensor fusion operations, etc., while also managing long-term memory utilization. Each sensor data set may be processed separately due to memory storage characteristics, or sensors may be grouped for similar processing (e.g., sensors with similar data characteristics and/or impact on the system, sensors that cooperate in a sensor fusion operation, a group of sensors utilized in a model or virtual sensor, etc.). In particular embodiments, sensor data from a single sensor may be treated differently depending on updates to the data storage profile 12532, the time or process stage at which the data was acquired, and/or system conditions such as network issues, fault conditions, etc. Additionally or alternatively, a single set of sensor data may be stored in multiple locations within the system, for example, if the same data is utilized in multiple separate sensor fusion operations, with resource consumption from storing multiple sets of the same data being lower than processor or network utilization for utilizing a single stored data set in multiple separate processes.

Referring to FIG. 133, various aspects of an exemplary data storage profile 12532 are depicted. The exemplary data storage profile 12532 includes aspects of the data storage profile 12532 that may be included as additional or alternative aspects of the data storage profile 12532 to, and/or include as, a storage location definition 12534, a storage time definition, and/or a storage time definition 12536, a data resolution description 12540. Any one or more of the storage-related factors or parameters depicted in FIG. 133 may be included in the data storage profile 12532 and/or managed by the self-organizing storage system (e.g., system 12500 and/or controller 12532). The self-organizing storage system may manage or optimize any such parameters or factors noted throughout this disclosure, individually or in combination, using an expert system that may include rule-based optimization, optimization based on models of performance, and/or optimization using machine learning/artificial intelligence, optionally including deep learning approaches, or a hybrid or combination thereof. In embodiments, the exemplary data storage profile 12532 includes a storage type plan 12576 or profile that describes or specifies a type of storage based on the underlying physical media type of the storage, the type of device or system on which the storage resides, the mechanism by which the storage can be accessed to read or write data, etc. For example, the storage media plan 12578 may specify or consider the use of tape media, hard disk drive media, flash memory media, non-volatile memory, optical media, one-time programmable memory, etc. The storage media plan may describe or specify parameters related to the media, including storage duration, power usage, reliability, redundancy, thermal performance factors, robustness to environmental conditions (such as radiation and extreme temperatures), capabilities such as input/output speeds and capabilities, write speeds, read speeds, or other media-specific parameters such as data file organization, operating system, read/write lifecycle, data error rates, and/or data compression aspects associated with or inherent to the media or media controller. The storage access plan 12580 or profile may specify or consider the nature of the interface to the available storage, such as database storage (including relational databases, object-oriented databases, and other databases, as well as distributed databases, virtual machines, cloud-based databases, etc.), cloud storage (such as S3 ^™ buckets and other simple storage formats), stream-based storage, cache storage, edge storage (e.g., in edge-based network nodes), on-device storage, server-based storage, network-attached storage, etc. The storage access plan or profile may specify or consider factors such as cost, I/O performance, reliability, complexity, size, etc. of different storage types. The storage protocol plan 12582 or profile may specify or consider the protocol over which data is transmitted or written, such as a streaming protocol, an IP-based protocol, a non-volatile memory representation protocol, a SATA protocol or other network-attached storage protocol, a disk-attached storage protocol, an Ethernet protocol, a peered storage protocol, a distributed storage protocol, etc. Examples of storage protocols include peered storage protocols, distributed ledger protocols, packet-based storage protocols, batch-based storage protocols, metadata storage protocols, and compressed storage protocols (using various compression types, such as packet-based media, streaming media, lossy compression types, and lossless compression types). A storage protocol plan may describe or specify factors related to the storage protocol, such as input/output performance, compatibility with available network resources, cost, complexity, data processing required to implement the protocol, network utilization to support the protocol, robustness of the protocol to support system noise (e.g., EM, competing network traffic, frequency of interruptions in network availability), and memory utilization to implement the protocol (e.g., utilization of stored memory and/or utilization of intermediate memory when creating or transferring data). A storage write protocol 12584 plan or profile may specify or consider how data is written to storage, such as in file format, streaming format, batch format, discrete chunks, partitions, stripes or bands across different storage locations, streams, or packets. A storage write protocol may describe or specify parameters and factors related to writes, such as input speed, reliability, redundancy, and security. A storage security plan 12586 or profile may describe or specify how storage will be secured, such as password protection, authentication, authorization, rights management, encryption (of data, storage media, and/or network traffic on the system), physical isolation, network isolation, geographic placement, etc. A storage location plan 12588 or profile may describe or specify the location of storage, such as geolocation, network location (e.g., at the edge, at a given server), location on a data collector, location on a handheld device (such as an operator's smartphone, tablet, or personal computer in the environment), location within or among device groups (such as a mesh, peer-to-peer group, ring, hub-and-spoke group, set of parallel devices, swage, etc.), location within an industrial environment (such as within the storage elements of an instrumentation system of or for a machine, location on an information technology system for the environment), or dedicated storage systems such as disks, dongles, USB devices, etc. The storage backup plan 12590 or profile may describe or specify a plan for backup or redundancy of stored data, such as indicating redundant locations for backup storage locations and managing any or all of the above factors. In particular embodiments, the storage security plan 12586 and/or storage backup plan 12590 may specify parameters such as data retention, long-term storage planning (e.g., migrating stored data to another storage medium after a certain period of time and/or after certain operations in the system have been performed on the data), physical risk management of the data and/or storage media (e.g., providing data in multiple geographic regions with different physical risk parameters, moving data when a storage location experiences physical risk, refreshing data according to the expected lifecycle of the long-term storage media, etc.).

The example controller 12512 further includes a sensor data storage implementation circuit 12526 that stores at least a portion of the multiple sensor data values in response to the data storage profile 12532. The example controller 12512 includes a data storage profile 12532 having storage location definitions 12534 corresponding to at least one of a number of sensor data values 12542, including at least one location such as: a sensor storage location (e.g., data stored for a period of time on a sensor and/or data stored on a portable device for a user 12518 in proximity to an industrial system 12502 where the portable device is adapted by the system as a sensor); a sensor communication device storage location (e.g., on a data controller 12508, a MUX device, a smart sensor in communication with other sensors, and/or on a portable device for a user 12518 in proximity to an industrial system 12502 or a network of industrial systems 12502 where the portable device is adapted by the system as a communication device to transfer sensor data between components within the system); a regional network storage location (e.g., on a plant computer 12510 and/or controller 12512); and/or a global network storage location (e.g., on a cloud computing device 12514).

The exemplary controller 12512 includes a data storage profile 12532 including a storage time definition 12536 corresponding to at least one of the multiple sensor data values 12542, including at least one time value, such as: a description of the time domain in which the corresponding at least one of the multiple sensor data values is to be stored (e.g., the time and location of the data, which may include a time relative to some aspect such as the time of data sampling, the start or stop time of a process stage, or an absolute time such as midnight, Saturday, or the first day of the month); a time domain storage trajectory (e.g., multiple locations) including multiple time values corresponding to multiple storage locations in which the corresponding at least one of the multiple sensor data values is to be stored; a flow of sensor data through a system across devices, including a relative or absolute time description of the time of each storage transfer); a process description value in which at least one corresponding one of the multiple sensor data values is stored (e.g., the process description may include an identification of a process stage and which process is associated with the storage plan); and/or a trajectory of a process description including multiple process stages corresponding to multiple storage locations in which at least one corresponding one of the multiple sensor data values is stored (e.g., the flow of sensor data through a system across multiple devices, including an identification of a process stage and/or process for each storage transfer).

The exemplary controller 12512 includes a data storage profile 12532 including a data resolution description 12540 corresponding to at least one of the multiple sensor data values 12544, the data resolution description 12540 including values such as: a detection density value corresponding to at least one of the multiple sensor data values (e.g., the detection density may be a temporal sampling resolution, a spatial sampling resolution, the accuracy of the sampled data, and/or an applied processing operation that may affect the available resolution, such as filtering and/or lossy compression of the data); a detection density value corresponding to at least one of the number of sensor data values (e.g., including values such as: a group of sensors having similar detection density values, secondary data values determined from a group of sensors having a specified detection density value, etc.); a detection density trajectory including a number of detection density values of at least one of the multiple sensor data values, each of the multiple detection density values corresponding to a time value (e.g., one such as: a combination of any of the concepts of detection density and any of the concepts of time domain), a detection density trajectory including a number of detection density values of at least one of a number of sensor data values, each of the number of detection density values corresponding to a process stage value (e.g., a combination of any of the concepts of detection density and any of the concepts of process description or stage), and/or a detection density trajectory including a number of detection density values of at least one of a number of sensor data values, each of the number of detection density values corresponding to a value of a storage location (e.g., the detection density can be varied depending on the device storing the data).

The example sensor data storage profile circuit 12524 further updates the data storage profile 12532 after operation of the sensor data storage implementation circuit 12526, and the sensor data storage implementation circuit 12526 further stores a portion of the number of sensor data values 12544 in response to the updated data storage profile 12532. For example, during operation of the system at a first time, the sensor data storage implementation circuit 12526 utilizes a currently existing data storage profile sensor data storage implementation circuit 12526, which may be based on an initial estimate of system performance, desired data from an operator of the system, and/or data from a previous operation of the sensor data storage profile circuit 12524. During system operation, the sensor data storage implementation circuit 12526 stores data according to the data storage profile 12532, and the sensor data storage profile circuit 12524 determines parameters of the data storage profile 12532 that may result in improved system performance. The example sensor data storage profile circuit 12524 may, for example, utilize a machine learning optimization routine to test various parameters for the data storage profile 12532, and upon determining that an improved data storage profile 12532 is available, the sensor data storage profile circuit 12524 provides an updated data storage profile 12532 for use by the sensor data storage implementation circuit 12526. In particular embodiments, the sensor data storage profile circuit 12524 may perform various operations, such as supplying an intermediate data storage profile 12532 for use by the sensor data storage implementation circuit 12526 to produce real-world results, applying modeling to the system (either first-principles modeling based on the characteristics of the system, a model utilizing actual operational data of the system, a model utilizing actual operational data of the offset system, and/or a combination thereof) to determine what the results of a given data storage profile 12532 would be or would have been, and/or applying random changes to the data storage profile 12532 to prevent the optimization routine from settling into local optima or non-optimum states.

The exemplary sensor data storage profile circuit 12524 further updates the data storage profile 12532 in response to external data 12544 and/or cloud-based data 12538, including data such as: enhanced data demand values (e.g., an operator, model, optimization routine, and/or other process requests enhanced data resolution for one or more parameters); process success values (e.g., indicating that the current storage method provides sufficient data availability and/or system performance, and/or indicating that the current storage method may be overcapacity and one or more changes to reduce system utilization are possible); and/or indicates that the current storage usage may not provide sufficient data availability and/or system performance and/or that the current storage usage may be over capacity and one or more changes can be made to reduce system utilization); process failure values (e.g., indicates that the current storage usage may not provide sufficient data availability and/or system performance and may include additional actions or operator alerts to determine whether data transmission and/or availability caused the process failure); component service values (e.g., actions to adjust data storage so that higher resolution data is available to improve learning algorithms that predict future service events and/or actions to determine which factors caused the early service); component maintenance values (e.g., actions to adjust data storage so that higher resolution data is available to improve learning algorithms that predict future maintenance events and/or actions to determine which factors caused the early maintenance); network description values (e.g., device identification, protocol determination, and/or network changes entered by a user or operator that result in a change in capacity, potentially resulting in a personalized optimal storage plan for sensor data); process feedback values (e.g., detected process conditions or one or more process conditions); network feedback values (e.g., one or more network changes determined by the actual operation of the network (e.g., loss or reduction in communication of one or more devices, changes in network traffic, changes in transmission noise values on the network, etc.)); sensor feedback values (e.g., metadata such as sensor failures, changes in capabilities, and/or abnormal readings, rates of change, or off-nominal conditions that indicate a retention plan should be modified, e.g., enhanced or reduced resolution, sampling time, etc., based on detected data from the system); and/or a second data retention profile, where the second data retention profile was generated for the offset system.

The exemplary storage planning circuit 12528 determines a data configuration plan 12546 and updates the data storage profile 12532 in response to the data configuration plan 12546, and the sensor data storage implementation circuit 12526 further stores at least a portion of the number of sensor data values in response to the updated data storage profile 12532. An exemplary data configuration plan 12546 includes values such as: data storage structure values (e.g., data type, such as integer, string, comma-separated file, etc., how many bits to commit to a value, etc.); data compression values (e.g., whether to compress data, what compression model to use, and/or whether to replace segments of data with summary information, curve-fit summaries such as polynomials, etc.); data writing strategy values (e.g., whether to store values distributedly or on a single device, what network communication and/or operating system protocols to utilize, etc.); data tier values (e.g., which data to prioritize over other data when storage or communication constraints limit the data stored); data tier values (e.g., which data to prioritize over other data when the data is intended to be used, etc.); The data may be temporary, such as not being in the intended location during processing, or permanent, such as some data needing to be compressed in a lossy manner), extended access values determined for the data (e.g., the type the data is for reporting; extended access values determined for the data (e.g., the type the data is for reporting, searching, modeled access, and/or tagging, where extended access includes where the data is stored for availability, data indexing, data summarization, data current events reporting, which may be stored in addition to raw or processed sensor data), and/or indicators corresponding to the data (e.g., placeholders indicating where the data is located, interfaces for accessing the data, units, precision, time frame, metadata indicating the process in operation, defects present, results, etc.).

In this manner, controlling the flow and storage of data within the system can generally improve and optimize data management throughout the system over time. Thus, for a given utilization of resources such as storage space, communications bandwidth, power consumption, and/or processor execution cycles, higher resolution data can be accumulated in a more readily accessible manner than conventional systems with fixed or manually configurable data storage and flow. Furthermore, the system can accommodate process variations that affect optimal or beneficial parameters for controlling data flow and storage. Those skilled in the art, having the benefit of the disclosure herein, will recognize that the combination of control over data storage methodology with control over data type and knowledge of the system's process operations creates a powerful combination in certain areas. In contemplated embodiments, for example, higher resolution data can be maintained for extended periods and made available when the need for the data arises, without incurring the full costs of permanently storing the data or communicating the data through all layers of the system.

In one embodiment, an underground mine inspection system may need to capture and store specific, detailed data regarding toxic gas concentrations, temperature, noise, etc. for regulatory purposes, but perhaps only a single data point regarding one or more toxic gases is needed periodically for ongoing operational purposes. In this embodiment, the system's data storage profile indicates that only specific sensor data aligned with regulatory needs is stored in a specific manner that is available long-term and optionally only when needed, while other sensor data required for operational purposes is stored in a more accessible manner.

In another embodiment relating to vehicle brakes, data relating to brake use and performance may be captured in high resolution and stored in a first data storage that is not transmitted across the network, while lower resolution data may be transmitted periodically and/or in near real time to a vehicle control and maintenance application. When the application or other users require the higher resolution data, it may be accessed from the first data storage.

In a further embodiment manufacturing truck and automobile body and frame parts, certain detailed data regarding paint color, surface curvature, and other quality control measures may be captured and stored at high resolution, but only low-resolution data related to throughput is transmitted for ongoing operational purposes. In this embodiment, the system's data storage profile may dictate that only certain sensor data aligned with quality control needs be stored in a specific manner that is available long-term and only when needed, while other sensor data required for operation is stored in a more accessible manner.

In another example, data type, resolution, etc. can be configured and changed as it flows through the system depending on the value useful to the individual components processing the data, depending on the network resources utilized for the data, and/or depending on the accompanying data (e.g., models, virtual sensors, and/or sensor fusion operations) if higher capacity data does not improve the accuracy of the process utilizing the accompanying data.

In one embodiment, in a rail condition monitoring system, as rail condition data is acquired, each component of the system may require different resolutions of the same data. Continuing with this example, as real-time rail traffic data is acquired, it may be stored and/or transmitted at a lower resolution for rapid dissemination of data throughout the system, while utilization and load data may be stored and utilized at a higher resolution to track rail usage and rail maintenance needs at a more detailed level.

In another embodiment of a tractor-operated hydraulic pump, when the tractor is in the field and does not have access to a network, data from the onboard sensors can be acquired in low resolution and stored locally on the tractor, but when the tractor regains access, the data can be acquired and transmitted in high resolution.

In another embodiment of an actuator for a robotic handling unit in an automotive factory, data about the actuator may flow to multiple downstream systems, such as a production tracking system that uses the actuator data alone and an energy efficiency tracking system that uses the data in sensor fusion with data from environmental sensors. These systems may have different resolutions for the actuator data to suit their respective applications.

In yet another embodiment of a mine generator, data may be captured regarding generator performance, carbon monoxide levels near the generator, and the cost of operating the generator. Each component of the control system overseeing the mine may require different resolutions of the same data. Continuing with this example, as carbon monoxide data is captured, it may be stored and/or transmitted at a lower resolution for rapid dissemination throughout the system to appropriately alert workers. Performance and cost data may be stored and used at a higher resolution to track economics and lifetime maintenance needs.

In an additional embodiment, sensors on the truck's wheel ends can monitor lubrication, noise (e.g., grinding, vibration), and temperature. In the field, sensor data may be transmitted remotely at low resolution for remote monitoring, while within a threshold distance from a fleet maintenance facility, the data may be transmitted at high resolution.

In another example, accompanying information about the data enables efficient downstream processing (e.g., by downstream devices or processes that access the data), including unpackaging the data, easily determining where related high-performance data may reside within the system, and/or streamlining operations that utilize the data (e.g., performing reporting, modeling, alerting, and/or sensor fusion or other system analysis). One embodiment includes storing high-capability (e.g., high sampling rate, high accuracy, indexed, etc.) data in a first storage device within the system (e.g., near the sensor in a network layer to conserve network communication resources) and transmitting low-capability data up the network layer (e.g., to a cloud computing device), where the low-capability data includes ancillary information for accessing the stored high-capability data, including user-accessible ancillary data (e.g., user-accessible ancillary data (e.g., headers, message boxes, or other organically interfaceable ancillary data) and/or automated process-accessible ancillary data (e.g., structured data, XML, populated fields, etc.) that can be utilized by a process to automatically request, retrieve, or access the high-capability data. In certain embodiments, the ancillary data further includes information regarding content, accuracy, sampling time, calibration (e.g., debouncing, filtering, or other processing applied), allowing an accessing component or user to determine whether the data meets desired parameters without retrieving the high-capability data.

In one embodiment, vibration noise from vibration sensors attached to assembly line vibrators may be stored locally in a high-resolution format, while a lower-resolution version of the same data, including accompanying information about the availability of ambient and local noise data for sensor fusion, may be transmitted to a cloud-based server. If a resident process on the server requires the high-resolution data, such as a machine learning process, the server may retrieve the data at that time.

In another embodiment of an airplane engine, aggregated performance data from multiple sensors may be transmitted to a remote site during flight along with accompanying information. The accompanying information, such as a header with metadata related to historical airplane information, may allow the remote site to efficiently analyze the performance data in the context of the historical data without accessing additional databases.

In a further embodiment of a coal pulverizer at a power plant, data accompanying low-quality sensor data regarding the size of the coal exiting the pulverizer may include information regarding the accuracy of the size measurement so that a technician can determine whether higher resolution data is needed to confirm a determination that the pulverizer needs to be taken offline for maintenance.

In a further embodiment of a drilling rig or production platform employed in oil and gas production, high-capacity data regarding drill and platform operating parameters may be acquired and stored locally, while only low-capacity data is transmitted off-site to conserve bandwidth. Along with the low-capacity data, accompanying information may include instructions on how an off-site automated process can automatically access the high-capacity data if it becomes necessary.

In yet another embodiment, temperature sensors on pumps used in oil and gas production and extraction may be stored locally in high-resolution format, while a lower-resolution version of the same data, including accompanying information about the availability of noise and energy usage data for sensor fusion, may be transmitted to a cloud-based server. If a resident process on the server requires the high-resolution data, such as a machine learning process, the server may retrieve the data at that time.

In another embodiment of a gearbox in an automated robotic processing device or agricultural environment, aggregated performance data from multiple sensors may be transmitted to a remote site during use along with accompanying information. The accompanying information, such as a header with metadata relating to historical gearbox information, may allow the remote site to efficiently analyze the performance data in the context of historical data without accessing additional databases.

In a further embodiment of a mine ventilation system, data accompanying low-quality sensor data regarding the size of airborne particulates may include information regarding the accuracy of the size measurement so that a technician can determine whether higher-resolution data is needed to confirm a determination that the ventilation system requires maintenance.

In a further embodiment of a rolling bearing used in agriculture, high-capacity data may be acquired and stored locally regarding the operating parameters of the rolling bearing, while only low-capacity data is transmitted off-site to conserve bandwidth. Along with the low-capacity data, accompanying information may include instructions on how to automatically access the high-capacity data if an automated off-site process is required.

In a further embodiment of a mining stamp mill, data accompanying the low-quality sensor data regarding the size of the ore deposit exiting the stamp mill may include information regarding the accuracy of the size measurement, allowing an engineer to determine whether higher resolution data is needed to confirm a determination that the stamp mill requires a change in operating parameters.

With reference to FIG. 130, an exemplary storage time definition 12536 is depicted. The exemplary storage time definition 12536 depicts multiple storage locations 12556 corresponding to multiple time values 12558. It is understood that any values, such as storage type, storage medium, storage access, storage protocol, storage write value, storage security, and/or storage backup value, may be included in the storage time definition 12536. Additionally or alternatively, the exemplary storage time definition 12536 may include process operations, events, and/or other values in addition to or as an alternative to the time values 12558. The exemplary storage time definition 12536 depicts the movement of associated sensor data to a first storage location 12550 over a first time interval, to a second storage location 12552 over a second time interval, and to a third storage location 12554 over a third time interval. While the storage location values 12550, 12552, 12554 are depicted as integral selections corresponding to planned storage locations, additionally or alternatively, the values may be continuous or discrete, but not necessarily integral. For example, a storage location value 12550 of "1" may be associated with a first storage location, a storage location value 12550 of "2" may be associated with a second storage location, and values between "1" and "2" may have understood meanings, such as a priority for moving data (e.g., "1.1" indicates that data should be moved from "2" to "1" with a relatively high priority compared to "1.4"), a rate of data to be moved (e.g., to control network utilization, memory utilization, etc. during transfer operations), and/or storage location prioritization with alternative options (e.g., to be able to dictate storage location and include it in a cost function so that storage location can be balanced with other system constraints). Additionally or alternatively, the storage time definition 12536 may include additional dimensions (e.g., protocol, media, security plan changes, etc.) and/or may include multiple options for storage planning (e.g., providing weighted values between two, three, four, or more storage locations, protocols, media, etc. in a triangulated or multi-dimensional definition space).

With reference to FIG. 131, an exemplary data resolution description 12540 is depicted. The exemplary data resolution description 12540 depicts a number of data resolution values 12562 corresponding to a number of time values 12564. It is understood that any values, such as storage type, storage medium, storage access, storage protocol, storage write value, storage security, and/or storage backup value, may be included in the data resolution description 12540. Additionally or alternatively, the exemplary data resolution description 12540 may include process operations, events, and/or other values in addition to or as an alternative to the time value 12558. The exemplary data resolution description 12540 depicts changes in the resolution of the stored associated sensor data resolution values 12560 over time intervals, such as initially operating at a low resolution, stepping up to a high resolution (e.g., corresponding to a process start time), stepping up to a high resolution value (e.g., during a process time where the process is significantly improved by the high resolution of the associated sensor data), and stepping up to a low resolution value (e.g., after the process is completed). While this example depicts a higher resolution before the process begins than after the process ends as an illustrative example, data resolution description 12540 may include any data resolution trajectory. Data resolution value 12560 is depicted as an integral selection value corresponding to the planned data resolution, but may additionally or alternatively be a continuous or discrete value, and not necessarily an integral value. For example, a data resolution value 12560 of "1" may be associated with a first data resolution (e.g., a particular sampling time, byte resolution, etc.), a data resolution value 12560 of "2" may be associated with a second data resolution, and values between "1" and "2" may have an understood meaning, such as a priority for sampling at a defined resolution (e.g., "1.1" may indicate that data should be acquired at a sampling rate corresponding to "1" with a relatively high priority compared to "1.3", and/or that data should be acquired at a sampling rate that is 10% of a rate between "1" and "2"), and/or alternative options (e.g., sensor or network limitations, available sensor communication devices such as data controllers, smart sensors, or portable devices acquiring data from sensors, and/or inclusion in a cost function such that data resolution can be balanced with other constraints in the system). Additionally or alternatively, the data resolution description 12540 may include additional dimensions (e.g., protocol, media, security plan variations, etc.) and/or multiple options for data resolution planning (e.g., providing weighted values among two, three, four, or more data resolution values, protocols, media, etc. in a triangulated or multi-dimensional definition space).

The example system 12500 further includes a haptic feedback circuit 12530 that determines haptic feedback instructions 12548 in response to at least one of the number of sensor values 12542 and/or the data storage profile 12532, and a haptic feedback device 12516 that responds to the haptic feedback instructions 12548. Example and non-limiting haptic feedback instructions 12548 include instructions such as: vibration instructions; temperature instructions; sound instructions; electrical instructions; and/or light instructions. An exemplary, non-limiting operation of the haptic feedback circuit 12530 includes feedback that data has been or is being stored on the haptic feedback device 12516 and/or a mobile device associated with the user 12518 communicating with the haptic feedback device 12516 (e.g., as follows: the user 12518 passes by the system 12500 with a smartphone that the system 12500 utilizes to store sensor data, and the smartphone provides haptic feedback instructions 12548 to notify the user 12518 that the smartphone is currently being utilized by the system 12500, e.g., allowing the user 12518 to maintain communication with a sensor, data controller, or other transmitting device, and/or allowing the user to actively cancel or enable data transfer). Additionally or alternatively, the haptic feedback device 12516 may be a smartphone (e.g., utilizing vibration, sound, light, or other haptic aspects of the smartphone) and/or the haptic feedback device 12516 may include data storage and/or communication capabilities.

In certain embodiments, the haptic feedback circuit 12530 provides haptic feedback instructions 12548 as a warning or notification to the user 12518, for example, to alert or notify the user f25f8 that a process has been started or is about to be started, that abnormal operation has been detected or predicted, that a component of the system requires maintenance or is predicted to require maintenance, or that an aspect of the system is in a condition that the user 12518 may want to pay attention to (e.g., a component is still powered, has any type of high potential energy, and/or is hot to which the user 12518 may be in proximity to the component). In certain embodiments, the haptic feedback circuit 12530 configures haptic feedback instructions 12548 to provide intuitive feedback to the user 12518. For example, an alert value may provide more immediate, urgent, and/or intermittent vibration modes for informational notifications, a temperature-based alert or notification may utilize temperature-based haptic feedback (e.g., an over-temperature container notification may provide warm or cold haptic feedback), and/or flash a color related to the temperature (e.g., an over-temperature container notification may provide warm or cold haptic feedback), or The electrical notification may provide electrical-related haptic feedback (e.g., an electrical-related sound such as a buzzer or spark, or a light electrical feedback such as when a user opens a panel on a component that is still powered on) or may provide vibration. For example, a vibration profile similar to that detected on the requested component may be sent to the haptic feedback device to allow a technician to diagnose the component without physical contact, or haptic feedback on the requested component may be provided when a user double-checks lockout/tagout operations before entering the component, opening a panel, and/or entering a potentially hazardous area. The provided examples of the operation of the haptic feedback circuit 12530 are illustrative and non-limiting.

132, an exemplary apparatus 12566 for data collection in an industrial environment includes a controller 12512, a sensor communication circuit 12522 that interprets a number of sensor data values 12542, and a sensor data storage profile circuit 12524 that determines a data storage profile 12532, the data storage profile 12532 including a data storage plan for the number of sensor data values 12542, and a network coding circuit 12568 that provides a network coding value 12570 in response to the number of sensor data values 12542 and the data storage profile 12532. The controller 12512 further includes a sensor data storage implementation circuit 12526 that stores at least a portion of the number of sensor data values 12542 in response to the data storage profile 12532 and the network coding value 12570. The network coding values 12570 include, but are not limited to, network encoding for data transmission, such as packet sizing, distribution, combining sensor data within packets, encoding and decoding algorithms for network data and communications, and/or any other aspect for controlling network communications throughout the system. In particular embodiments, the network coding values 12570 include linear network coding algorithms, random linear network coding algorithms, and/or convolutional codes. Additionally or alternatively, the network coding circuit 12568 provides scheduling and/or synchronization of network communication devices in the system, and may include separate scheduling and/or synchronization for different networks within the system. The network coding circuit 12568 schedules the network coding values 12570 throughout the system according to data volume, transfer rates, and network utilization, and alternatively or additionally performs self-learning and/or machine learning operations to improve or optimize the network coding. For example, a sensor with a single, low-volume data transfer to a data controller may utilize TCP/IP packet communication to the data controller without linear network coding, while a sensor with a higher-volume data transfer may utilize TCP/IP packet communication to the data controller without linear network coding. Aggregated data transfers from the data controller to another system component (e.g., controller 12532) may utilize linear network coding. The exemplary network coding circuit 12568 adjusts network coding values 12570 in real time for components in the system to optimize or improve transfer speed, power utilization, error and packet loss, and/or any other desired parameters. For example, a given component may result in a low transfer rate but large available memory, while a downstream component may have low available memory (potentially relative to that component's data storage expectations). Accordingly, a complex network coding value 12570 for the given component may not result in improved data throughput for the overall system, while a network coding value 12570 that improves the throughput of the downstream component may justify the processing overhead for the more complex network coding value 12570.

The exemplary system includes the network coding circuit 12568 further determining a network definition value 12572 and further providing a network coding value 12570 in response to the network definition value 12572. Exemplary network definition values 12572 include values such as: network feedback values (e.g., transfer rate, uptime, synchronization availability, etc.), network condition values (e.g., presence of noise, transmit/receive capabilities, dropouts, etc.), network topology values (e.g., device communication flow and connectivity, device operating system, protocol, and storage type, available computing resources on a device, location and function of a device within the system), intermittently available network device values (e.g., known or observed availability of a device at a time or process stage, predicted availability of a device, prediction of known noise factors for a device, etc. process operations that reduce device availability), and/or network cost description values (e.g., device resource utilization (e.g., relative cost or impact of processing, memory, and/or communication resources), device power utilization and cost of power consumption, device available power, and cost descriptions of externalities associated with power consumption (power itself may not be expensive, but power at a particular location has costs associated with replacing batteries, including device availability or access during operation).

The exemplary system further includes providing a network coding value 12570 such that the sensor data storage implementation circuitry stores a first portion of the number of sensor data values 12542 utilizing the first network coding value 12570 and stores a second portion of the number of sensor data values 12542 utilizing the second network coding value 12570 (e.g., the network coding value 12570 can vary depending on the data being transmitted, the transmitting device, and/or the time or process stage). Exemplary, non-limiting network coding values include a network type selection (e.g., public, private, wireless, wired, intranet, external, internet, cellular, etc.), a network selection (e.g., which one or more of a number of available networks are utilized), a network coding selection (e.g., packet definition, coding technique, linear, random linear, convolutional, triangular, etc.), a network timing selection (e.g., synchronization and ordering of data transmissions between devices), and a network feature selection (e.g., on/off of a network-supported device or devices). The exemplary network coding circuit 12568 may further adjust the network coding value 12570 to provide intermediate network coding values (e.g., as test coding values on the system and/or as modeled coding values performed offline), compare performance indicators 12574 corresponding to the network coding value 12570 and the intermediate network coding value, and provide updated network coding values (e.g., as the network coding value 12570) in response to the comparison of the performance indicators 12574.

An exemplary system includes an industrial system having multiple components and multiple sensors, each operably coupled to at least one of the multiple components. The multiple sensors provide multiple sensor values, and the system further includes multiple organizational structures, such as controllers, data collectors, plant computers, cloud-based servers and/or global computing devices, and/or network layers, configured to self-organize and store at least some of the multiple sensor values. For example, operation of the controller 12512 provides for the storage and distribution of sensor data values to reduce resource (processor, network, and/or memory) consumption for storing the sensor data. The self-organizing operation includes managing the stored sensor data over time and therefore providing sensor information to system components in time to complete operations (e.g., process control, improvement, modeling, and/or machine learning, system operation). Furthermore, data security, including long-term security due to storage media, geography, and/or unauthorized access, is considered throughout the data storage lifecycle. The exemplary system further includes an organizational structure that provides enhanced resolution of the number of sensor values in response to at least one of enhanced data request values or alert values corresponding to the industrial system. The system controls the storage process with consideration for system impacts, keeping lower-resolution data, summary data, or other accessibility data available, while enhancing resolution by storing higher-resolution data in a less resource-intensive manner that is available upon request and/or at a time appropriate for system operation. Examples of enhanced resolution include enhanced spatial resolution, enhanced time-domain resolution, a greater number of sensor values than a standard resolution, and/or a higher accuracy of at least one sensor value than a standard resolution. The exemplary system further includes a network layer, wherein the organizational structure is configured for self-organizing network coding for communication of the number of sensor values on the network layer. The exemplary system further includes a user haptic feedback device proximate to at least one of the industrial system or the network layer, wherein the organizational structure is configured for providing haptic feedback to the haptic feedback device and/or configuring the haptic feedback to provide an intuitive alert to the user.

In an embodiment, a system for data collection in an industrial environment may include a sensor communication circuit configured to interpret a plurality of sensor data values; a sensor data storage profile circuit configured to determine a data storage profile, the data storage profile including a data storage plan for the plurality of sensor data values; and a sensor data storage implementation circuit configured to store at least a portion of the plurality of sensor data values in response to the data storage profile. In an embodiment, the data storage profile may include a storage location definition corresponding to at least one of the plurality of sensor data values, the storage location definition including at least one location selected from the group consisting of a sensor storage location, a sensor communication device storage location, a regional network storage location, and a global network storage location. The data storage profile may include a storage time definition corresponding to at least one of the plurality of sensor data values, the storage time definition including at least one time value selected from the group consisting of: a time domain description in which at least one of the corresponding plurality of sensor data values is stored, a time domain storage trajectory consisting of a plurality of time values corresponding to a plurality of storage locations in which at least one of the corresponding plurality of sensor data values is stored, a process description value in which at least one of the corresponding plurality of sensor data values is stored, and a process description trajectory consisting of a plurality of process stages corresponding to the plurality of storage locations in which at least one of the corresponding plurality of sensor data values is stored. The data storage profile may include a data resolution description corresponding to at least one of the plurality of sensor data values, the data resolution description including at least one of the following: a detected density value corresponding to at least one of the plurality of sensor data values, a detected density value corresponding to at least one of the plurality of sensor data values, a detected density trajectory consisting of a plurality of detected density values of at least one of the plurality of sensor data values, wherein each of the plurality of detected density values corresponds to a time value. and a detected density trajectory comprising a plurality of detected density values for at least one sensor data value of the plurality of sensor data values, each of the plurality of detected density values corresponding to a process stage value, and a detected density trajectory comprising a plurality of detected density values for at least one sensor data value of the plurality of sensor data values, each of the plurality of detected density values corresponding to a stored position value. The sensor data storage profile circuit may further comprise structure for updating the data storage profile after operation of the sensor data storage implementation circuit, the sensor data storage implementation circuit further comprising structure for storing a portion of the plurality of sensor data values in response to the updated data storage profile. The sensor data storage profile circuit may be further configured to update the data storage profile in response to external data, the external data including at least one data value selected from an extended data request value, a process success value, a process failure value, a component service value, a component maintenance value, a network description value, a process feedback value, a network feedback value, a sensor feedback value, and a second data storage profile, the second data storage profile being generated for an offset system. The storage plan circuit may be further configured to determine a data organization plan and update the data storage profile in response to the data organization plan, and the sensor data storage implementation circuit may be further configured to store at least a portion of the plurality of sensor data values in response to the updated data storage profile. The data organization plan may include at least one value selected from the group consisting of a data storage structure value, a data compression value, a data write strategy value, a data hierarchy value, an extended access value determined for the data, and an instruction value corresponding to the data. The haptic feedback circuit may be configured to determine a haptic feedback instruction in response to at least one of the plurality of sensor values or the data storage profile, and includes a haptic feedback device responsive to the haptic feedback instruction. The haptic feedback instruction may include at least one instruction selected from the group consisting of a vibration instruction, a temperature instruction, a sound instruction, an electrical instruction, and a light instruction. The data storage plan may be generated by a rule-based expert system utilizing feedback, the feedback relating to one or more aspects of the industrial environment or the plurality of sensor data values. The data retention plan may be generated by a model-based expert system utilizing feedback, the feedback relating to one or more of an aspect of the industrial environment or a plurality of sensor data values. The data retention plan may be generated by an iterative expert system utilizing feedback, the feedback relating to one or more of an aspect of the industrial environment or a plurality of sensor data values. The data retention plan may be generated by a deep learning machine system utilizing feedback, the feedback relating to one or more of an aspect of the industrial environment or a plurality of sensor data values. The data retention plan may be based on one or more of the type of physical media underlying the storage, the type of device or system on which the storage resides, and the mechanism by which the storage is accessed to read and write data. The underlying physical media may be one of tape media, hard disk drive media, flash memory media, non-volatile memory, optical media, and one-time programmable memory. The data storage plan may consider or specify parameters related to the underlying physical media, including one or more of the following aspects related to or inherent in the underlying physical media or media controller: retention time, power usage, reliability, redundancy, thermal coefficient of performance, robustness to environmental conditions, input/output speed and capacity, write speed, read speed, data file organization, operating system, read/write lifecycle, data error rate, and data compression. The data storage plan may include one or more of a storage type plan, a storage media plan, a storage access plan, a storage protocol plan, a storage write protocol plan, a storage security plan, a storage location plan, and a storage backup plan.

In an embodiment, a system for data collection in an industrial environment may include a sensor communication circuit configured to interpret a plurality of sensor data values; a sensor data storage profile circuit configured to determine a data storage profile, the data storage profile including a data storage plan for the plurality of sensor data values; a network coding circuit configured to provide a network coding value in response to the plurality of sensor data values and the data storage profile; and a sensor data storage implementation circuit configured to store at least a portion of the plurality of sensor data values in response to the data storage profile and the network coding value. The network coding circuit may be configured to determine a network definition value and further provide the network coding value in response to the network definition value, the network definition value including at least one value selected from the group consisting of a network feedback value, a network condition value, a network topology value, an intermittently available network device value, and a network cost description value. The network coding circuit may be configured to provide the network coding value such that the sensor data storage implementation circuit stores a first portion of the plurality of sensor data values using a first network coding value and stores a second portion of the plurality of sensor data values using a second network coding value. The network coding value may include at least one value selected from the following values: network type selection, network selection, network coding selection, network timing selection, network feature selection, network protocol selection, packet size selection, and packet order selection. The network coding circuit may be further configured to adjust the network coding value to provide an intermediate network coding value, compare performance metrics corresponding to each of the network coding value and the intermediate network coding value, and provide an updated network coding value in response to comparing the performance metrics.

In an embodiment, a system may include an industrial system including a plurality of components and a plurality of sensors, each operably coupled to at least one of the plurality of components; the plurality of sensors providing a plurality of sensor values; and means for self-organizing and storing at least a portion of the plurality of sensor values. In an embodiment, means for enhancing the resolution of the plurality of sensor values in response to at least one of an enhanced data request value or an alert value corresponding to the industrial system may be provided, the enhanced resolution comprising at least one of enhanced spatial resolution, enhanced time domain, and enhanced temporal domain. The enhanced resolution may be characterized by a greater number of the plurality of sensor values than a standard resolution of the plurality of sensor values, and a greater accuracy of at least one of the plurality of sensor values than a standard resolution of the plurality of sensor values. The system may include a network layer and means for self-organizing network coding for communication of the plurality of sensor values over the network layer. The system may include means for providing haptic feedback to a user's haptic feedback device proximate to at least one of the industrial system or the network layer. The system may include means for configuring the haptic feedback to provide an intuitive alert to the user.

In an embodiment, a system for self-organizing data storage for data collected from a mine may include a sensor communication circuit structured to interpret a plurality of sensor data values; a sensor data storage profile circuit structured to determine a data storage profile, the data storage profile including a data storage plan for the plurality of sensor data values; and a sensor data storage implementation circuit structured to store at least a portion of the plurality of sensor data values in response to the data storage profile. In an embodiment, a system for self-organizing data storage for data collected from an assembly line may include a sensor communication circuit structured to interpret a plurality of sensor data values; a sensor data storage profile circuit structured to determine a data storage profile, the data storage profile including a data storage plan for the plurality of sensor data values; and a sensor data storage implementation circuit structured to store at least a portion of the plurality of sensor data values in response to the data storage profile.

In an embodiment, a system for self-organizing data storage for data collected from an agricultural system may include: a sensor communication circuit configured to interpret a plurality of sensor data values; a sensor data storage profile circuit configured to determine a data storage profile, the data storage profile including a data storage plan for the plurality of sensor data values; and a sensor data storage implementation circuit configured to store at least a portion of the plurality of sensor data values in response to the data storage profile.

In an embodiment, a system for self-organizing data storage for data collected from a robotic handling unit of a motor vehicle may include a sensor communication circuit configured to interpret a plurality of sensor data values; a sensor data storage profile circuit configured to determine a data storage profile, the data storage profile including a data storage plan for the plurality of sensor data values; and a sensor data storage implementation circuit structured to store at least a portion of the plurality of sensor data values in response to the data storage profile.

In an embodiment, a system for self-organizing data storage for data collected from an automotive system may include a sensor communication circuit configured to interpret a plurality of sensor data values; a sensor data storage profile circuit configured to determine a data storage profile, the data storage profile including a data storage plan for the plurality of sensor data values; and a sensor data storage implementation circuit structured to store at least a portion of the plurality of sensor data values in response to the data storage profile.

In an embodiment, a system for self-organizing data storage for data collected from a robotic handling unit of a motor vehicle may include a sensor communication circuit structured to interpret a plurality of sensor data values; a sensor data storage profile circuit structured to determine a data storage profile, the data storage profile including a data storage plan for the plurality of sensor data values; and a sensor data storage implementation circuit structured to store at least a portion of the plurality of sensor data values in response to the data storage profile.

In an embodiment, a system for self-organizing data storage for data collected from an aerospace system may include a sensor communication circuit configured to interpret a plurality of sensor data values; a sensor data storage profile circuit configured to determine a data storage profile, the data storage profile including a data storage plan for the plurality of sensor data values; and a sensor data storage implementation circuit configured to store at least a portion of the plurality of sensor data values in response to the data storage profile.

In an embodiment, a self-organizing data storage system for data collected from a railway may include a sensor communication circuit configured to interpret a plurality of sensor data values; a sensor data storage profile circuit configured to determine a data storage profile, the data storage profile including a data storage plan for the plurality of sensor data values; and a sensor data storage implementation circuit configured to store at least a portion of the plurality of sensor data values in response to the data storage profile.

In an embodiment, a system for self-organizing data storage for data collected from an oil and gas production system may include: a sensor communication circuit structured to interpret a plurality of sensor data values; a sensor data storage profile circuit structured to determine a data storage profile, the data storage profile including a data storage plan for the plurality of sensor data values; and a sensor data storage implementation circuit structured to store at least a portion of the plurality of sensor data values in response to the data storage profile.

In an embodiment, a system for self-organizing data storage for data collected from a power generation system includes: a sensor communication circuit configured to interpret a plurality of sensor data values; a sensor data storage profile circuit configured to determine a data storage profile, the data storage profile including a data storage plan for the plurality of sensor data values; and a sensor data storage implementation circuit configured to store at least a portion of the plurality of sensor data values in response to the data storage profile.

In embodiments, methods and systems are provided for data collection at or associated with one or more machines deployed in an industrial environment using self-organizing network coding for network transmission of sensor data across the network. In embodiments, network coding can be used to specify and manage how packets (including streams of packets described in various embodiments throughout this disclosure and the documents incorporated by reference) are relayed from a sender (e.g., a data collector, an instrumentation system, a computer, etc.) in the industrial environment where the data is collected to a receiver (e.g., another data collector (e.g., a swarm or collaborative group), an instrumentation system, a computer, storage, etc.) in the industrial environment, or to a remote computer, server, cloud platform, database, data pool, data marketplace, mobile device (e.g., a network-connected device (e.g., a mobile phone, personal computer, tablet, etc.) via one or more network infrastructure elements (sometimes referred to herein as nodes), such as access points, switches, routers, servers, gateways, bridges, connectors, physical interfaces, etc.). Network coding can be used to specify and manage how packets (including streams of packets described in various embodiments throughout this disclosure and the documents incorporated by reference) are relayed across the network. ... from a sender (e.g., a data collector, an instrumentation system, a computer, etc.) in the industrial environment where the data is collected to a receiver (e.g., another data collector (e.g., a swarm or collaborative group), an instrumentation system, a computer, storage, etc.) in the industrial environment to a remote computer, server, cloud platform, database, data pool, data marketplace, mobile device (e.g., a network-connect Using one or more network protocols, such as Energy, cellular protocols, LTE, 2G, 3G, 4G, 5G, CDMA, TDSM, packet-based protocols, streaming protocols, file transfer protocols, broadcast protocols, multicast protocols, and unicast protocols. In situations involving two-way communication, any of the devices and systems described above, or others mentioned throughout this disclosure, may act as a sender, a receiver, or both. Network coding also takes into account network availability (including the availability of multiple alternative networks) and allows transmissions to occur over different networks, such as by dividing different components or redundantly transmitting the same components. Network coding may take into account bandwidth and spectrum availability. For example, a given spectrum may be divided (e.g., by subdividing the spectrum by frequency, time division multiplexing, and other techniques). A network or its components may be virtualized for purposes such as network resource provisioning, specification of network coding for virtualized networks, etc. Network coding includes various approaches, such as those described herein and in the incorporated documents.

In embodiments, one or more network coding systems or methods of the present disclosure may employ self-organization, such as configuring network coding parameters for one or more transmissions over one or more networks using an expert system capable of configuring a model-based system (e.g., automatically selecting network coding parameters or configurations based on one or more defined or measured parameters related to a transmission, such as parameters of the data or content being transmitted, the sender, the receiver, available network infrastructure components, network infrastructure conditions, industrial environment conditions, etc.). The model may consider parameters related to, for example, file size, number of packets, stream size, importance of the data packet or stream, value of the packet or stream, transmission cost, transmission reliability, quality of service, transmission quality, quality of user experience, financial yield, spectrum availability, input/output speeds, storage availability, storage reliability, and many others mentioned throughout this disclosure. In embodiments, the expert system may be a rule-based system, where one or more rules are executed based on detecting conditions or parameters, calculating variables, etc. In embodiments, the expert system may be a machine learning system, such as a deep learning system, based on neural networks, self-organizing maps, or other artificial intelligence approaches (including those described throughout this disclosure or the documents incorporated by reference). The machine learning system in any of the embodiments of the present disclosure may configure one or more inputs, weights, connections, functions (including functions of individual neurons or groups of neurons within a neural net), or other parameters of the artificial intelligence system. Such configuration may be performed through iteration and feedback, optionally with human oversight, such as by providing feedback on various indicators of success or failure. In the case of network coding, configuration may include setting one or more coding parameters for a network coding specification or plan. For example, configuration may include selecting a network, selecting one or more nodes, selecting a data path, setting timers or timing parameters, setting redundancy parameters, setting a coding type (including the use of regenerative codes, such as using network coding for distributed storage, such as in a peer-to-peer network), etc. The configuration may include coefficients for coding (including linear algebraic coefficients), parameters for random or near-random linear network coding (including the generation of near-random coefficients for coding), session configuration parameters, or other parameters described in the network coding embodiments described below, throughout this disclosure, and in documents incorporated by reference herein. For example, the machine learning system may select a protocol for transmission, select a network(s) to be used, select one or more senders, select one or more routes, configure one or more network infrastructure nodes, select a destination receiver, configure a receiver, etc. In embodiments, each one of these may be configured by an individual machine learning system, or the same system may configure an overall configuration by iteratively adjusting one or more of the various parameters listed above through a series of trials, optionally seeded by a training set that may be based on human configuration of the parameters or through model- and/or rule-based configuration. Feedback to the machine learning system may consist of various measurements, such as transmission success or failure, reliability, efficiency (including cost-based, energy-based, and other efficiency measures, such as measures of energy per transmitted bit and energy per saved bit), transmission quality, quality of service, financial yield, operational effectiveness, prediction success, classification success, etc. In embodiments, the machine learning system may configure the network coding parameters by predicting network behavior or characteristics and may learn to improve the prediction using any of the techniques described above. In embodiments, the machine learning system may configure the network coding parameters by classification of one or more network elements and/or one or more network behaviors and may improve the classification, such as through training and iteration over time. Such machine-based prediction and/or classification, including model-based, rule-based, and machine learning-based, may be used or configured for self-organization. In this way, network coding self-organization can use or comprise various combinations or permutations of model-based systems, rule-based systems, and a variety of different machine learning systems (including classification systems, prediction systems, and deep learning systems, among others).

As described in U.S. Patent Application Publication No. 2017/0013065, entitled "Cross-Session Network Communication Configuration," network coding may include methods and systems for data communication over a data channel on a data path between a first node and a second node, including maintaining data characterizing one or more current or previous data communication connections passing through the data channel, and initiating a new data communication connection between the first node and the second node, including configuring the new data communication connection at least in part in response to the maintained data. The maintained data may characterize one or more data channels on one or more data paths between the first node and the second node through which the one or more current or previous data communication connections pass. The maintained data may characterize an error rate of the one or more data channels. The maintained data may characterize a bandwidth of the one or more data channels. The maintained data may characterize a round-trip time of the one or more data channels. The maintained data may characterize communication protocol parameters of one or more current or previous data communication connections.

The communication protocol parameters may include one or more of a congestion window size, a block size, an interleaving factor, a port number, a pacing interval, a round trip time, and a timing variation. The communication protocol parameters may include two or more of a congestion window size, a block size, an interleaving factor, a port number, a pacing interval, a round trip time, and a timing variation.

The maintained data may characterize forward error correction parameters associated with one or more current or previous data communication connections. The forward error correction parameters may include a code rate. Initiating the new data communication connection may include configuring the new data communication connection according to first data in the maintained data, the first data being maintained at the first node, and initiating the new data communication connection includes providing the first data from the first node to the second node to configure the new data communication connection.

Initiating the new data communication connection may include configuring the new data communication connection according to first data in the maintained data, the first data being maintained at the first node, and initiating the new data communication connection including accessing the first data at the first node to configure the new data communication connection. Any of these elements of the maintained data, including various parameters of a communication protocol, error correction parameters, connection parameters, etc., may be provided to an expert system to support self-organization of network coding, including for execution of rules for setting network coding parameters based on the maintained data, for population of models, or for configuration of parameters of a neural net or other artificial intelligence system.

Initiating a new data communication connection may include configuring the new data communication connection according to first data of the maintained data, the first data being maintained at the first node, and initiating the new data communication connection includes accepting a request from the first node to establish a new data communication connection between the first node and a second node, and receiving at the second node at least one message from the first node including first data for configuring the connection. The method for maintaining a new data communication connection between the first node and the second node may include maintaining communication parameters, including initializing the communication parameters according to first data received in at least one message from the first node.

Maintaining the new data communication connection may include adapting communication parameters in response to feedback from the first node. The feedback from the first node may include a feedback message received from the first node. The feedback may include feedback derived from multiple feedback messages received from the first node. The feedback may relate to any of the types of feedback described above and may be used to self-organize the data communication connection using an expert system.

In some examples, prior to establishing a data communication connection via a data channel on the data path, one or more training communication connections via a data channel on the data path are employed. The training communication connection is used to gather information about the data channel, which is used in establishing the data communication connection. In other examples, no training communication connection is performed, and information about the data channel is obtained from one or more previous or current data communication connections via a data channel on the data path.

The present disclosure describes a method for data communication over a data channel on a data path between a first node and a second node, and in one disclosed non-limiting embodiment of the present disclosure, the method may include: maintaining data characterizing one or more current or previous data communication connections traversing the data channel; and initiating a new data communication connection between the first node and the second node, the new data communication connection including configuring the new data communication connection at least in part according to the maintained data, wherein the configuration of the new data communication connection is configured by an expert system.

In an embodiment, the expert system uses at least one of rules and models to set parameters for the configuration.

In an embodiment, the expert system is a machine learning system that iteratively configures at least one of a set of inputs, a set of weights, and a set of functions based on feedback associated with a data channel.

In an embodiment, the expert system receives multiple inputs from a data collector who accepts data regarding machines operating in an industrial environment.

As described in U.S. Patent Application Publication No. 2017/0012861, entitled "Multipath Network Communications," self-organizing network coding under expert system control may include a method and system for communicating data between a first node and a second node via multiple data paths coupling the first node and the second node, and may include transmitting messages between the first node and the second node via the multiple data paths, including transmitting a first subset of the messages via a first data path of the multiple data paths and transmitting a second subset of the messages via a second data path of the multiple data paths, wherein the first data path has a first latency and the second data path has a second latency substantially greater than the first latency, and wherein messages of the first subset of messages are selected to have first message characteristics and messages of the second subset are selected to have second message characteristics different from the first message characteristics.

For example, in an industrial environment, messages may be designated as time-critical, such as messages related to a critical machine fault condition (e.g., overheating, excessive vibration, or any of the other fault conditions described throughout this disclosure), messages related to a safety hazard, or messages related to a time-critical operational step on which other processes depend (e.g., completion of a catalytic reaction in a high-value, high-speed manufacturing process, completion of a subassembly in a high-value, high-speed manufacturing process, refining process, etc.). Completion of a catalytic reaction, completion of a subassembly in a high-value, high-speed manufacturing process, refining process, etc.) may be designated as time-critical (e.g., by rules analyzed or processed by a rules engine) or may be learned as time-critical by an expert system based on feedback regarding time-critical results, including results of similar machines with similar data in a similar industrial environment. The first subset of messages and the second subset of messages may be determined from a portion of messages available at the first node at the time of transmission. At subsequent transmissions, additional messages available at the first node may be divided into the first and second subsets based on message characteristics associated with the additional messages. The division into subsets and the selection of which subsets target which data paths may be performed by an expert system. Messages having a first message characteristic may be associated with an initial subset of the data set, and messages having a second message characteristic may be associated with subsequent subsets of the data set. The methods and systems described herein for selecting inputs for data collection and multiplexing data may be orchestrated, such as by an expert system, to configure inputs for alternate channels, such as providing streaming elements with real-time importance to a first data path and other elements, such as for long-term predictive maintenance, to other data paths. In an embodiment, the messages in the second subset may include messages that precede the last acknowledged message in a sequential transmission order associated with the messages by up to n messages, where n is determined based on a buffer size at one of the first and second nodes.

The message having the first message characteristic may include an acknowledgment message, and the message having the second message characteristic may include a data message. The message having the first message characteristic may include a supplemental data message. The supplemental data message may include a data message including redundant data, and the message having the second message characteristic may include an original data message. The first data path may include a terrestrial data path, and the second data path may include a satellite data path. The terrestrial data path may include one or more of a cellular data path, a digital subscriber line (DSL) data path, a fiber optic data path, a cable Internet-based data path, and a wireless local area network data path. The satellite data path may include one or more of a low Earth orbit satellite data path, a medium Earth orbit satellite data path, and a geostationary Earth orbit satellite data path. The first data path may include a medium Earth orbit satellite data path or a low Earth orbit satellite data path, and the second data path may include a geostationary Earth orbit satellite data path.

The method may further include, for each path of the multiple data paths, maintaining an indication of success and failure of messages over the data path and adjusting the congestion window of the data path based on the indication, which may occur under expert system control, such as based on feedback of results of a series of transmissions. The method may further include, for each path of the multiple data paths, maintaining, at the first node, an indication of whether a number of messages received at the second node is sufficient to decode data associated with the messages, the indication being based on feedback received at the first node across the multiple data paths.

In another general aspect, a system for communicating data between multiple nodes via multiple data paths coupling the multiple nodes includes a first node configured to transmit messages to a second node via the multiple data paths, including transmitting a first subset of messages via a first data path of the multiple data paths and transmitting a second subset of messages via a second data path of the multiple data paths.

In an embodiment, the first subset of messages and the second subset of messages for each data path may be determined from a portion of messages available at the first node at the time of transmission. At subsequent transmissions, additional messages available at the first node may be divided into the first and second subsets based on message characteristics associated with the additional messages. Messages having the first message characteristic may be associated with an initial subset of the data set, and messages having the second message characteristic may be associated with a subsequent subset of the data set.

In an embodiment, the second subset of messages may include messages that precede the last acknowledged message by up to n messages in a sequential transmission order associated with the messages, where n is determined based on a receive buffer size at the second node. The messages having the first message characteristic may include acknowledgement messages, and the messages having the second message characteristic may include data messages. The messages having the first message characteristic may include supplemental data messages. The supplemental data messages may include data messages containing redundant data, and the messages having the second message characteristic may include original data messages.

The first node may be further configured to maintain, for each of the multiple data paths, an indication of successful and unsuccessful delivery of messages on the data path and adjust the congestion window of the data path based on the indication. The first node may be further configured to maintain an aggregate indication of whether a number of messages received at the second node across the multiple data paths is sufficient to decode data associated with the messages and to send supplemental messages based on the aggregate indication, the aggregate indication being based on feedback from the second nodes received at the first node across the multiple data paths.

The present disclosure describes a method for communicating data between a first node and a second node via a plurality of data paths coupling the first node and the second node. According to one non-limiting embodiment of the present disclosure, the method may include transmitting messages between the first node and the second node via a plurality of data paths, including transmitting a first subset of messages via a first data path of the plurality of data paths and transmitting a second subset of messages via a second data path of the plurality of data paths. The first data path has a first latency, the second data path has a second latency that is substantially greater than the first latency, messages of the first subset are selected to have first message characteristics, messages of the second subset are selected to have second message characteristics that are different from the first message characteristics, and selection of the message characteristics of the first and second subsets is performed automatically under the control of an expert system.

In an embodiment, the expert system uses at least one of rules and models to set the parameters of the selection.

In an embodiment, the expert system is a machine learning system that iteratively configures at least one of a set of inputs, a set of weights, and a set of functions based on feedback associated with at least one of the data paths.

In an embodiment, the expert system receives multiple inputs from a data collector that accepts data about machines operating in an industrial environment.

As described in U.S. Patent Application Publication No. 2017/0012868, entitled "Multiple protocol network communication," a self-organized network coding system under expert control may include a method and system for communicating data between a first node and a second node over one or more data paths coupling the first node and the second node, the method including transmitting at least some of the messages over the first data path using a first communication protocol and transmitting at least some of the messages over the second data path using a second communication protocol. The method also includes determining that the first data path is altering the flow of messages on the first data path due to transmitting the messages using the first communication protocol, and adjusting the number of messages transmitted over the data paths in response to the determination, the adjusting step including reducing the number of messages transmitted over the first data path and increasing the number of messages transmitted over the second data path. The determination that the first data path is altering the flow of messages and/or adjusting the number of messages sent over the data path may be performed under the control of an expert system, such as a rule-based system, a model-based system, a machine learning system (including deep learning), or a hybrid of any of these, which takes inputs related to one or more of the data path, the node, the communication protocol used, etc. The data path may be between devices and systems in an industrial environment, such as instrumentation systems of industrial machines, one or more mobile data collectors (optionally coordinated in groups), data storage systems (including network-attached storage), servers, and other information technology elements, any of which may have or be associated with one or more network nodes. The data path may be between any such devices and systems within any type of network (e.g., switches, routers, etc.) or between them and devices and systems in remote environments, such as enterprise information technology systems, cloud platforms, etc.

Determining that a first data path is altering the flow of messages on the first data path may include determining that the first data path is limiting the rate of messages transmitted using a first communication protocol. Determining that a first data path is altering the flow of messages on the first data path may include determining that the first data path is dropping messages transmitted using the first communication protocol at a rate that is higher than the rate at which the second data path is dropping messages transmitted using a second communication protocol. The first communication protocol may be User Datagram Protocol (UDP), and the second communication protocol may use User Datagram Protocol (UDP) or Transmission Control Protocol (TCP), or vice versa. Other protocols described in this disclosure may also be used.

Messages may be initially divided evenly or according to some predetermined allocation (e.g., by type, as described in connection with other embodiments) across the first and second data paths, such as using load balancing techniques. Messages may be initially divided across the first and second data paths according to the division of messages across the first and second data paths in one or more prior data communication connections. Messages may also be initially divided between the first and second data paths based on the probability that messages transmitted using the first communication protocol will cause the first data path to change the flow of messages on the first data path.

Messages may be divided between the first data path and the second data path based on message type. Message types may include one or more of acknowledgement messages, forward error correction messages, retransmission messages, and original data messages. Reducing the number of messages sent over the first data path and increasing the number of messages sent over the second data path may include sending all messages over the second path and not sending all messages over the first path.

At least some of the multiple data paths may share a common physical data path. The first data path and the second data path may share a common physical data path. The adjustment of the number of messages sent across the multiple data paths may occur at an early stage of the transmission of the messages. The adjustment of the number of messages sent across the number of data paths may occur repeatedly during the duration of the transmission of the messages. The adjustment of the number of messages sent across the multiple data paths may include increasing the number of messages sent via the first data path and decreasing the number of messages sent via the second data path.

This is because TCP and UDP both share the same low-level data path, yet have very different protocol characteristics.

In some examples, approaches learn the network's data processing policies and state by responding to momentary network behavior and probing for changes. For example, a SCADA system may allow only a limited number of authorized users, services, and applications to use its data paths due to concerns about the confidentiality of the underlying machines and processes controlled (including remotely) through the SCADA system and the potential for cyberattacks. While traditional load balancers assume that each data path is unique and does not affect others, some approaches recognize that TCP and UDP share low-level data paths and directly affect each other. Furthermore, TCP provides in-order delivery and data retransmission (including flow control, congestion control, etc.), while UDP does not. This uniqueness necessitates additional logic provided by the methods and systems disclosed herein. This logic may include mapping specific message types to each communication protocol based, at least in part, on the different characteristics of the protocols (e.g., expecting longer jitter with TCP and out-of-order delivery with UDP). For example, because TCP is more reliable, systems can forgo coding on packets sent over TCP, while UDP can send forward error correction to add redundancy and save bandwidth. In some instances, a larger ACK interval is used to ACK TCP data.

Employing the techniques described herein, the approach distributes data over TCP and UDP data paths to achieve optimal or near-optimal throughput, even in situations where network provider policies disfavor UDP (compared to traditional systems that use UDP when possible and fall back to TCP otherwise).

A method for communicating data between a first node and a second node via multiple data paths connecting the first node and the second node, the method including:

Transmitting a message between a first node and a second node via multiple data paths, including transmitting at least a portion of the message via a first data path of the multiple data paths using a first communication protocol and transmitting at least a portion of the message via a second data path of the multiple data paths using a second communication protocol.

Adjusting the number of messages transmitted on the multiple data paths includes determining that a first data path is altering the flow of messages on the first data path due to the messages being transmitted using a first communications protocol, and, in response to the determination, decreasing the number of messages transmitted on the first data path and increasing the number of messages transmitted on the second data path, wherein the alteration of the message flow is performed automatically under the control of an expert system.

In an embodiment, the expert system uses at least one of rules and models to set parameters for the flow changes.

In an embodiment, the expert system is a machine learning system that iteratively configures at least one of a set of inputs, a set of weights, and a set of functions based on feedback associated with at least one of the data paths.

In an embodiment, the expert system receives multiple inputs from a data collector that accepts data about machines operating in an industrial environment.

In this embodiment, the first communication protocol is UDP (User Datagram Protocol).

In this embodiment, the second communication protocol is TCP (Transmission Control Protocol).

In an embodiment, the message is initially split across the first and second data paths using a load balancing technique.

In an embodiment, the message is initially split across the first and second data paths according to the splitting of the message across the first and second data paths in one or more preceding data communication connections.

In an embodiment, messages are initially divided between a first data path and a second data path based on the probability that the first data path will alter the flow of messages on the first data path due to the messages being transmitted using the first communications protocol.

In an embodiment, the probabilities are determined by an expert system.

As described in U.S. Patent Application Publication No. 2017/0012884, entitled "Message Reordering Timers," self-organizing network coding under expert system control may include a method and system for data communication from a first node to a second node via a data channel coupling the first node and the second node, the method and system including receiving a data message at the second node, the message belonging to a set of data messages being sequentially transmitted from the first node; transmitting a feedback message from the second node to the first node, the feedback message characterizing a delivery status of the set of data messages at the second node, the method including maintaining a set of one or more timers responsive to the occurrence of a number of delivery order events, the maintaining including changing a state of one or more timers in the set of timers based on the occurrence of the number of delivery order events, and postponing transmission of the feedback message until expiration of one or more of the set of one or more timers. Data channels may be between devices, such as instrumentation systems on industrial machines, one or more mobile data collection devices (optionally coordinated in groups), data storage systems (including network-attached storage), servers, and other information technology elements, which may have or be associated with one or more network nodes. Data channels may be between any such devices and systems and devices and systems (e.g., switches, routers, etc.) in any type of network, or between them and those located in remote environments, such as enterprise information technology systems, cloud platforms, etc. The determination that a timer is needed, the setting of the timer, and the initiation of the timer user may occur under the control of an expert system, such as a rule-based system, a model-based system, a machine learning system (including deep learning), or a hybrid thereof, which receives input regarding one or more of the type of communication occurring, the data channel, the node, the communication protocol being used, etc.

The set of one or more timers may include a first timer, which may be initiated upon detection of a first delivery order event, the first delivery order event associated with receipt of a first data message associated with a first position in the sequential order before receipt of one or more missing messages associated with a position preceding the first position in the sequential order. The method may include transmitting a feedback message indicating successful delivery of the set of data messages at the second node upon detection of a second delivery order event, the second delivery order event associated with receipt of one or more missing messages before expiration of the first timer. The method may include transmitting the feedback message indicating unsuccessful delivery of the set of data messages at the second node upon expiration of the first timer before any of the one or more missing messages are received. The set of one or more timers may include a second timer, which may be initiated upon detection of a second delivery command event, the second delivery command event associated with receipt of some, but not all, of the missing messages before expiration of the first timer. The method may include transmitting a feedback message indicating unsuccessful delivery of the set of data messages at the second node upon expiration of a second timer prior to receiving the missing messages. The method may also include transmitting a feedback message indicating successful delivery of the set of data messages at the second node upon detection of a third delivery command event, the third delivery command event being associated with receiving the missing messages prior to expiration of the second timer.

In another general aspect, a method for communicating data from a first node to a second node over a data channel between the first node and the second node includes receiving, at the first node, feedback messages indicating delivery status of a set of data messages sequentially transmitted from the second node to the second node. At the first node, maintaining a congestion window size includes maintaining a set of one or more timers in response to the occurrence of a number of feedback events, the maintaining including modifying the state of one or more timers in the set of timers based on the occurrence of the number of feedback events, and delaying modification of the congestion window size until expiration of one or more of the set of one or more timers.

The set of one or more timers may include a first timer, which may be initiated upon detection of a first feedback event, the first feedback event associated with receipt of a first feedback message indicating successful delivery of a first data message having a first position in the sequential order prior to receipt of one or more feedback messages indicating successful delivery of one or more other data messages having a position prior to the first position in the sequential order. The method may include canceling modification of the congestion window upon detection of a second feedback event, the second feedback event associated with receipt of one or more feedback messages indicating successful delivery of the one or more other data messages before expiration of the first timer. The method may include modifying the congestion window upon expiration of the first timer before receipt of any feedback messages indicating successful delivery of the one or more other data messages.

The set of one or more timers may include a second timer, which may be initiated upon detection of a third feedback event, the third feedback event being associated with receipt of one or more feedback messages indicating successful delivery of some, but not all, of the one or more other data messages before expiration of the first timer. The method may include modifying the size of the congestion window upon expiration of the second timer before receiving one or more feedback messages indicating successful delivery of the one or more other data messages. The method may include canceling the change in the size of the congestion window upon detection of a fourth feedback event, the fourth feedback event being associated with receipt of one or more feedback messages indicating successful delivery of the one or more other data messages before expiration of the second timer.

In another general aspect, a system for communicating data between multiple nodes over a data channel includes a first node among the multiple nodes configured to receive feedback messages indicating delivery status of a set of data messages sequentially transmitted from a second node to the first node. Maintaining a congestion window size at the first node includes maintaining a set of one or more timers in response to occurrences of multiple feedback events, the maintaining including modifying the state of one or more timers in the set of timers based on the occurrences of the multiple feedback events and delaying modification of the congestion window size until expiration of one or more of the set of one or more timers.

The present disclosure describes a method for communicating data from a first node to a second node over a data channel coupling the first node and the second node, and the method according to one disclosed non-limiting embodiment of the present disclosure may include: using an expert system to determine, based on at least one condition of the data channel, whether one or more timers will be used to manage the data communication; and, based on such determination, receiving a data message at the second node, the message belonging to a set of data messages being transmitted sequentially from the first node. The method also includes: transmitting a feedback message from the second node to the first node, the feedback message characterizing a delivery status of the set of data messages at the second node, and maintaining a set of one or more timers in response to occurrences of a plurality of delivery order events, the maintaining including changing a state of one or more timers in the set of timers in response to occurrences of the plurality of delivery order events, and postponing transmission of the feedback message until expiration of one or more of the set of one or more timers.

In an embodiment, the expert system uses at least one of rules and models to set parameters for determining whether to use one or more timers.

In an embodiment, the expert system is a machine learning system that iteratively configures at least one of a set of inputs, a set of weights, and a set of functions based on feedback associated with at least one of the data paths.

In an embodiment, the expert system receives multiple inputs from a data collector that accepts data about machines operating in an industrial environment.

In an embodiment, the set of one or more timers includes a first timer that is initiated upon detection of a first delivery order event, the first delivery order event being associated with receipt of a first data message associated with a first position in the sequential order prior to receipt of one or more missing messages associated with a position prior to the first position in the sequential order.

As described in U.S. Patent Application Publication No. 2017/0012885, entitled "Network Communication Recoding Nodes," self-organizing network coding under expert system control may include a method and system for modifying redundancy information associated with coded data passing from a first node to a second node via a data path, and may include receiving first coded data including first redundancy information from a first node at an intermediate node via a first channel connecting the first node and an intermediate node, the first channel having first channel characteristics, and transmitting second coded data including second redundancy information from the intermediate node to the second node via a second channel connecting the intermediate node and the second node. A degree of redundancy associated with the second redundancy information may be determined by modifying the first redundancy information based on one or both of the first channel characteristics and the second channel characteristics, without decoding the first coded data. Data paths may be between devices and systems in an industrial environment (each operating as one or more nodes for sending, receiving, or transmitting data), such as instrumentation systems on industrial machines, one or more mobile data collectors (optionally coordinated in groups), data storage systems (including network-attached storage), servers, and other information technology elements, any of which may have or be associated with one or more network nodes. Data paths may be between any such devices and systems and devices and systems in any type of network (e.g., switches, routers, etc.), or between them and those in remote environments, such as enterprise information technology systems or cloud platforms. Modification of redundancy information may be performed by or under the control of an expert system, such as a rule-based system, a model-based system, a machine learning system (including deep learning), or a hybrid thereof, which receives inputs related to one or more of the data path, the node, the communication protocol used, etc. Redundancy may result from (and may be identified, at least in part, based on) the combination or multiplexing of data from a series of data inputs, as described throughout this disclosure.

Modifying the first redundancy information may include adding redundancy information to the first redundancy information. Modifying the first redundancy information may include removing redundancy information from the first redundancy information. The second redundancy information may be further formed by modifying the first redundancy information based on feedback from the second node indicating success or failure of delivery of the encoded data to the second node. The first encoded data and the second encoded data may be encoded, for example, using a random linear network code or a substantially random linear network code. Modifying the first redundancy information based on one or both of the first channel characteristics and the second channel characteristics may include modifying the first redundancy information based on one or more of a block size, a congestion window size, and a pacing rate associated with the first channel characteristics and/or the second channel characteristics.

The method may include transmitting a feedback message from the intermediate node to the first node, acknowledging receipt of the one or more messages at the intermediate node. The method may also include receiving the feedback message from the second node at the intermediate node, and transmitting additional redundancy information to the second node in response to receiving the feedback message.

In another general aspect, a system for modifying redundancy information associated with coded data passing from a first node to a second node via multiple data paths includes an intermediate node configured to receive first coded data including first redundancy information from the first node via a first channel connecting the first node and an intermediate node, the first channel having first channel characteristics, and transmit second coded data including second redundancy information from the intermediate node to the second node via a second channel connecting the intermediate node and the second node, the second channel having second channel characteristics. Redundancy associated with the second redundancy information is determined by modifying the first redundancy information based on one or both of the first channel characteristics and the second channel characteristics without decoding the first coded data.

The present disclosure describes a method for modifying redundancy information associated with coded data passed from a first node to a second node via multiple data paths, and a method according to one disclosed non-limiting embodiment of the present disclosure may include receiving first coded data including first redundancy information from a first node at an intermediate node via a first channel connecting the first node and an intermediate node, the first channel having first channel characteristics, and transmitting second coded data including second redundancy information from the intermediate node to the second node via a second channel connecting the intermediate node and the second node. The second channel has second channel characteristics, and the redundancy associated with the second redundant information is determined by modifying the first redundant information based on one or both of the first channel characteristics and the second channel characteristics without decoding the first encoded data, and the modification of the first redundant information is performed based on one or more of a block size, a congestion window size, and a pacing rate associated with the first channel characteristics and/or the second channel characteristics, and the modification of the first redundant information is performed under the control of an expert system.

In an embodiment, the expert system uses at least one of rules and models to set parameters for modifying the redundancy information.

In an embodiment, the expert system is a machine learning system that iteratively configures at least one of a set of inputs, a set of weights, and a set of functions based on feedback associated with at least one of the data paths.

In an embodiment, the expert system receives multiple inputs from a data collector that accepts data about machines operating in an industrial environment.

In an embodiment, modifying the first redundancy information includes adding redundancy information to the first redundancy information.

In an embodiment, modifying the first redundancy information includes deleting the redundancy information from the first redundancy information.

In an embodiment, the second redundancy information is further formed by modifying the first redundancy information based on feedback from the second node indicating success or failure of delivery of the encoded data to the second node.

In an embodiment, the first encoded data and the second encoded data are encoded using a random linear network code.

As described in U.S. Patent Application Publication No. 2017/0012905, entitled "Error Correction Optimization," self-organizing network coding under expert system control may include a method and system for data communication between a first node and a second node via a data path coupling the first node and the second node, and may include transmitting segments of data from the first node to the second node via the data path as multiple messages, the multiple messages being transmitted in a transmission order. A degree of redundancy associated with each message is determined based on the position of the message in the transmission order. The data path may be between devices and systems in an industrial environment (each operating as one or more nodes for sending, receiving, or transmitting data), such as instrumentation systems for industrial machines, one or more mobile data collectors (optionally coordinated in groups), data storage systems (including network-attached storage), servers, and other information technology elements, any of which may have or be associated with one or more network nodes. The data paths may be between any such devices and systems and devices and systems (e.g., switches, routers, etc.) within any type of network, or between them and those in remote environments such as enterprise information technology systems or cloud platforms. The transmission order determination is made by or under the control of an expert system, such as a rule-based system, a model-based system, a machine learning system (including deep learning), or a hybrid thereof, which takes inputs related to one or more of the data path, the nodes, the communication protocol used, etc. Redundancy may result from (and may be identified at least in part based on) the combination or multiplexing of data from a series of data inputs, as described throughout this disclosure.

The degree of redundancy associated with each message in the number of messages may increase because the message's position in the transmission order is non-decreasing. Determining the degree of redundancy associated with each message in the number of messages based on the message's position (i) in the transmission order is further based on one or more of the delay requirements for the application at the second node, the round-trip time associated with the data path, and the smoothed loss rate (P) associated with the channel. It is also based on an increasing function (g(i)) based on the size of the data associated with the number of messages (N), the number of acknowledgment messages (ai) received from the second node corresponding to the message from the number of messages, the number of in-flight messages (fi) in the number of messages, and an index of the data associated with the number of messages.

The redundancy associated with each message in the message count may be defined as: (N + g(i) - ai)/(l - p) - fi. g(i) may be defined as the maximum of parameters m and N - i, and g(i) may be defined as N - p(i), with integer rounding necessary, where P is a polynomial. The method may include, at a first node, receiving a feedback message from a second node indicating a missing message at the second node, and in response to receiving the feedback message, transmitting a redundancy message to the second node to increase the degree of redundancy associated with the missing message. The method may also include, at the first node, maintaining a queue of preemptively computed redundancy messages, and in response to receiving the feedback message, removing some or all of the preemptively computed redundancy messages from the queue and adding redundancy messages to the queue for transmission. The redundancy messages may be generated and transmitted on the fly in response to receiving the feedback message.

The method may include, at the first node, maintaining a queue of pre-emptively computed redundancy messages for a number of messages; and, in response to receiving a feedback message indicating successful delivery of the number of messages, removing the pre-emptively computed redundancy message associated with the number of messages from the queue of pre-emptively computed redundancy messages. A degree of redundancy associated with each of the messages may characterize a probability of correctability of erasure of the message. The probability of correctness may depend on a comparison of the degree of redundancy to the loss probability.

The present disclosure describes a method for communicating data between a first node and a second node over a data path coupling the first node and the second node, and in one disclosed non-limiting embodiment of the present disclosure, the method includes transmitting segments of data as multiple messages from the first node to the second node over the data path. The multiple messages are transmitted according to a transmission order, a degree of redundancy associated with each message of the multiple messages is determined based on the position of the message in the transmission order, and the transmission order is determined under the control of an expert system.

In an embodiment, the expert system uses at least one of rules and models to set transmission order parameters.

In an embodiment, the expert system is a machine learning system that iteratively configures at least one of a set of inputs, a set of weights, and a set of functions based on feedback associated with at least one of the data paths.

In an embodiment, the expert system receives multiple inputs from a data collector that accepts data about machines operating in an industrial environment.

In an embodiment, the degree of redundancy associated with each message of the plurality of messages increases as the message's position in the transmission order becomes non-decreasing.

In an embodiment, determining the degree of redundancy associated with each message of the plurality of messages based on the position (i) of the message in the transmission order is further based on one or more of the delay requirements of the application, the round-trip time associated with the data path, the smoothed loss rate (P) associated with the channel, the size (N) of the data associated with the plurality of messages, the number (ai) of acknowledgment messages received from the second node corresponding to the message from the plurality of messages, the number (fi) of in-flight messages of the plurality of messages, and an increasing function (g(i)) based on an index of the data associated with the plurality of messages.

As described in U.S. patent application Ser. No. 14/935,885, entitled "Packet Coding-Based Network Communications," self-organizing network coding under expert system control may include a method and system for data communication between a first node and a second node on a path, and may include estimating a rate at which loss events occur, where a loss event is either a failure to deliver a single packet to the second data node or a failure to deliver multiple consecutively transmitted packets to the second data node, and may include transmitting redundancy messages at the estimated rate at which loss events occur. An expert system may be used to estimate the rate at which loss events occur.

A method of communicating data from a first node to a second node over a data channel coupling the first node and the second node, such as in an industrial environment, comprising: receiving, at the first node, a message from the second node (including receiving the message including data that depends at least in part on characteristics of the channel coupling the first node and the second node); and transmitting the message from the first node to the second node (including applying forward error correction according to parameters determined from the received message), wherein the parameters determined from the received message include at least two of a block size, an interleaving factor, and a code rate. The method may be performed under the control of an expert system.

The present disclosure describes a method for communicating data from a first node in an industrial environment to a second node over a data channel coupling the first node and the second node, the method according to one disclosed non-limiting embodiment of the present disclosure including: receiving a message at the first node from the second node, the message including data that depends at least in part on characteristics of the channel coupling the first node and the second node; and transmitting the message from the first node to the second node, applying error correction according to parameters determined from the received message, the parameters determined from the received message including at least two of a block size, an interleaving factor, and a code rate, and the application of the error correction is performed under the control of an expert system.

In an embodiment, the expert system uses at least one of rules and models to set parameters for error correction.

In an embodiment, the expert system is a machine learning system that iteratively configures at least one of a set of inputs, a set of weights, and a set of functions based on feedback associated with at least one of the data paths.

As depicted in FIG. 134, a cloud platform for supporting the deployment of devices in the Internet of Things (IoT), such as in an industrial environment, may include various components, modules, services, elements, applications, interfaces, and other elements (collectively referred to as "cloud platform 13000"), which may include a policy automation engine 13002 and a data marketplace 13008. The cloud platform 13000 may include, integrate with, or connect to various devices 13006, cloud computing environments 13068, data pools 13070, data collectors 13020, and sensors 13024. The cloud platform 13000 may also include systems and functionality for self-organization 13012, machine learning 13014, and rights management 13016.

Within the cloud platform 13000, various components may be deployed in a wide variety of architectures and configurations. In embodiments, the device 13006 may be connected to, integrated with, or deployed within a cloud computing environment 13068, a policy automation engine 13002, a data marketplace 13008, a data collector 13020, and systems and capabilities for self-organization 13012, machine learning 13014, and rights management 13016. The device 13006 may be connected to or integrated with the policy automation engine 13002, the data marketplace 13008, the data collector 13020, and systems or capabilities for self-organization 13012, machine learning 13014, and rights management 13016, either directly or through the cloud computing environment 13068.

Devices 13006 may be IoT devices, such as those for collecting, exchanging, and managing information related to machines, personnel, equipment, infrastructure elements, components, parts, inventory, assets, and other characteristics of a wide range of industrial environments as described throughout this disclosure. Devices 13006 may also connect via various protocols 13004, such as networking protocols, streaming protocols, file transfer protocols, data exchange protocols, software operating system protocols, and the like. Devices 13006 may also connect to policy automation engine 13002 to execute policies that may be deployed within cloud platform 13000, such as to govern activities, permissions, rules, and the like within platform 13000. Devices 13006 may also connect to data streams 13010 within data marketplace 13008.

The data pool 13070 may be connected to or integrated with the functionality of the cloud computing environment 13068, the data collector 13020, and the data marketplace 13008, the policy automation engine 13002, the self-organization 13012, the machine learning 13014, and the rights management 13016. The data pool 13070 may be included within the cloud computing environment 13068 or may be external to the cloud computing environment 13068. As a result, the connection to the data pool 13070 may be made by a direct connection to the data pool 13070, a cloud connection to the data pool 13070, or a combination of a direct connection to the data pool 13070 and a cloud connection. Additionally, the data pool 13070 may be included within the data marketplace 13008 or may be external to the data marketplace 13008.

Data pool 13070 may include a multiplexer (MUX) 13022 and may also be connected to self-organization 13012, machine learning 13014, and rights management functions. MUX 13022 may connect to sensors 13024, collect data from the sensors 13024, and consolidate the data collected from the sensors 13024 into a single data set. In an exemplary and non-limiting embodiment, data pool 13070, data collector 13020, and sensors 13024 may be included within industrial environment 13018.

The policy automation engine 13002 and data marketplace 13008 may be used in a variety of industrial environments 13018. Industrial environments 13018 may include aerospace environments, agricultural environments, assembly line environments, automotive environments, and chemical and pharmaceutical environments. Industrial environments 13018 may also include food processing environments, industrial parts environments, mining environments, oil and gas environments, particularly oil and gas production environments, truck and automotive environments, and the like.

Similarly, devices 13006 may include a variety of devices that may operate within an industrial environment or that may collect data regarding other such devices. Among many examples, devices 13006 may include agitators, including turbine agitators, airframe control surface vibrators, catalytic reactors, and compressors. Devices 13006 may also include conveyors and lifters, disposal systems, drivetrains, fans, irrigation systems, motors, and the like. Devices 13006 may also include pipelines, electric powertrains, production platforms, pumps, such as water pumps, robotic assembly systems, hot wire heating systems, trucks, transmission systems, and turbines. Devices 13006 may operate within a single industrial environment 13018 or multiple industrial environments 13018. For example, a pipeline device may operate within an oil and gas environment, while a catalytic reactor may operate in either an oil and gas production environment or a pharmaceutical environment.

The policy automation engine 13002 may be a cloud-based policy automation engine 13002. The policy automation engine 13002 may be used to create, deploy, and/or manage an interconnected set of policies 13030, rules 13028, and protocols 13004, such as policies related to security, authorization, permissions, etc. For example, the policies may dictate which users, applications, services, systems, devices, etc. may access an IoT device, read data from an IoT device, subscribe to streams from an IoT device, write data to an IoT device, establish a network connection with an IoT device, provision an IoT device, collaborate with an IoT device, etc.

The policy automation engine 13002 may generate and manage policies 13030. The policy generation engine may be a centralized policy management system in the cloud platform 13000.

Policies 13030 generated and managed by policy automation engine 13002 may deploy numerous rules 13028 to allow access to and use of various aspects of IoT devices. Policies 13030 may include IoT device creation policies 13032, IoT device deployment policies 13034, IoT device management policies 13036, etc. Policies 13030 may be communicated to devices 13006 through protocols 13004 or directly from policy automation engine 13002.

For example, in an exemplary and non-limiting embodiment, the policy automation engine 13002 may manage policies 13030 and create protocols 13004 that specify and enforce roles 13026 and permissions 13074 for workers related to how the workers can use data provided by IoT devices. The workers may be human workers or machine workers.

In an additional exemplary and non-limiting embodiment, policy 13030 may be used to automate a remediation process. The remediation process may be performed when a system is partially disabled, when equipment fails, and when the entire system may be disabled. The remediation process may include instructions such as initiating a system restart, bypassing or replacing equipment, notifying appropriate stakeholders of the condition, etc. The policy automation engine 13002 may also include policy 13030 that specifies the roles 13026 and permissions 13074 required for a user 13072 to initiate a remediation or other process or to otherwise act.

The policy automation engine 13002 can also specify and detect conditions. Conditions may determine when a policy 13030 is distributed or otherwise acted upon. Conditions may include individual conditions, sets of conditions, independent conditions, interdependent conditions, etc.

In an exemplary, non-limiting embodiment of an independent condition, the policy automation engine 13002 may determine that a failure of a non-critical device 13006 does not require notification of a system operator. In an exemplary, non-limiting embodiment of an interdependent condition, the policy automation engine 13002 may determine that a failure of two non-critical system devices 13006 requires notification of a system operator because the failure of two non-critical system devices 13006 may be an early indicator of a possible system-wide failure.

As depicted in FIG. 135, the policy automation engine 13002 may include compliance policies 13050 and fault, configuration, accounting, provisioning, and security (FCAPS) policies 13052. Policies 13030 may connect to rules 13028, protocols 13004, and policy inputs 13048.

Policy 13030 may provide input to rules 13028 and provide information related to how roles 13026, permissions 13074, and uses 130280 are defined. Policy 13030 may receive policy input 13048 and incorporate policy input 13048 as policy parameters included within policy 13030. Policy 13030 may provide input to protocol 13004 and be included within protocol 13004 used to create, deploy, and manage device 13006.

Compliance policies 13050 may include data ownership policies, data analysis policies, data usage policies, data formatting policies, data transmission policies, data security policies, data privacy policies, information sharing policies, jurisdiction policies, etc. Data transmission policies may include policies for transmitting data across jurisdictions.

Data ownership policies may indicate policies 13030 governing who manages the data, who can use the data, and how the data can be used. Data analysis policies may indicate what data owners can do with the data they are authorized to access and may determine what data they can see and what data they can combine with other data. For example, a data owner may be able to see aggregated user data but not individual user data. Data usage policies indicate how data may be used and under what circumstances. Data format policies may indicate standard and mandated formats that are permitted for handling data. Data transmission policies, including inter-jurisdictional data transmission policies, may determine policies 13030 governing how inter- and intra-jurisdictional transmission of data is handled. Data security policies may determine how data at rest, such as stored data, and transmitted data must be protected.

Data privacy policies can determine how data may or may not be shared, for example, within and outside an organization. Information sharing policies can determine how data may be sold or shared, and under what circumstances. Jurisdiction policies can determine who controls data, when, and where it is transmitted within and across borders.

FCAPS policies 13052 may include fault management policies, configuration management policies, accounting management policies, provisioning management policies, and security management policies. Fault management policies may specify policies 13030 used to handle device faults. Configuration management policies may specify policies used to configure devices 13006. Accounting management policies may specify policies 13030 used for device accounting purposes such as reporting, billing, etc. Provisioning management policies may specify policies 13030 used to provision services to devices 13006. Security management policies may specify policies 13030 used to ensure the security of devices 13006.

Policy input 13048 may be received from policy input interface 13046. Policy input 13048 may include standards-based policy input 13044 and other policy input 13048. Standards-based policy input 13044 may include, for example, input related to standard data formats, standard rule sets, and other standards-related information established by standards bodies.

Other policy inputs 13048 may include a wide range of information related to industry-specific policies, cross-industry policies, manufacturer-specific policies, device-specific policies 13030, etc. Policy inputs 13048 may be provided via a policy input interface 13046 connected to the cloud computing environment 13068, or may be human-entered. Policy input interface 13046 may also collect machine-provided policy inputs 13048.

As depicted in FIG. 134, the data marketplace 13008 may include data streams 13010, a data marketplace input interface, a data marketplace input 13056, a data payment allocation engine 13038, a marketplace value assessment engine 13040, a data brokerage engine 13042, a marketplace self-organization engine 13076, and one or more data pools 13070. The data marketplace 13008 may be contained within the cloud networking environment 13068 or may be externally connected to the cloud networking environment 13068. Additionally, the data pools 13070 may be contained within the cloud networking environment 13068 or may be externally connected to the cloud networking environment 13068.

The data marketplace 13008 may connect directly to the data pool 13070, for example, if the data marketplace 13008 and the data pool 13070 are located in the same physical location. The data marketplace 13008 may connect to the data pool 13070 via the cloud networking environment 30, for example, if the data marketplace 13008 and the data pool 13070 are located in different physical locations.

The data marketplace 13008 may connect to and receive inputs. The data marketplace 13008 may receive marketplace inputs via a data interface, such as one or more data collectors 13020. The data collectors 13020 may be multiplexed data collectors. Inputs received via the data collectors 13020 may be received as one or more data streams 13010 from one or more data collectors 13020 and combined into additional data streams 13010 by a multiplexer (MUX) 13022.

Data stream 13010 may also include data from data pool 60. Data marketplace inputs, data stream 13010 and data pool 13070, may include metrics and measurements of the success of data marketplace 13008. The metrics and measurements of the success of data marketplace 13008 may then be used by machine learning capabilities 13014 to configure one or more parameters of data marketplace 13008.

The input may be a consorter input 13054. The consorter input 13054 may be received from a consortia. The consortia may include an energy consortia, a healthcare consortia, a manufacturing consortia, a smart city consortia, a transportation consortia, etc. The consortia may be an existing consortia or a new consortia.

In an exemplary and non-limiting embodiment, new consortia may form as a result of the data marketplace 13008 making certain data types and combinations of data available. The data brokering engine 13042 may enable members of the consortium to trade information. The data brokering engine 13042 may enable consortium members to trade information they provide based on the value of the information, for example, as calculated by the market value assessment engine 13040.

The data marketplace 13008 can also connect to self-organization 13012, machine learning 13014, and rights management 13016 capabilities. Rights management capabilities 13016 may include rights.

Rights may include business strategy and solution rights, liaison rights 13058, marketing rights 13078, security rights 13060, technology rights 13062, testbed rights 13064, etc. Business strategy and solution lifecycle rights may include business strategy and planning rights, industrial internet system design rights, project management rights, solution evaluation rights, contractual rights, etc. Liaison rights 13058 may include standards body rights, open source community rights, certification and testing organization rights, government agency rights, etc. Marketing rights 13078 may include communications rights, energy rights, healthcare rights, marketing and security rights, retail store operations rights, smart factory rights, and thought leadership rights. Security rights 13060 may include promotion rights to drive industry consensus, promote security best practices, and accelerate the adoption of security best practices.

Technology rights 13062 may include architecture rights, connectivity rights, distributed data management and interoperability rights, industrial analysis rights, innovation rights, IT/OT rights, safety rights, vocabulary rights, use case rights, and liaison rights 13058. Testbed rights 13064 may include, for example, the right to implement specific use cases and scenarios and the right to generate testable results to verify that the implementation meets expected results. Testbed rights 13064 may also include the right to explore collaborations between unproven and existing technologies, for example, interoperability testing, the right to create potentially disruptive new products and services, and the right to generate requirements and priorities for stakeholder groups such as standards bodies and consortia.

The rights management capability may assign different rights to different participants in the data marketplace 13008. In an exemplary and non-limiting embodiment, a manufacturer or remote maintenance organization (RMO). Participants may be assigned rights to information based on their device or proprietary methodology. The data marketplace 13008 may then ensure that only appropriate data streams 13010 are offered to the marketplace based on the assigned rights.

Rights management capability 13016 can manage permissions for access. One or more parameters of rights management capability 13016 can be automatically configured by machine learning capability 13014 or can be based on metrics of success of data marketplace 13008. Machine learning engine 13014 can also use the metrics and measures of success to configure a user interface. The user interface can present data elements for users of data marketplace 13008. The user interface can also present one or more mechanisms by which users of data marketplace 13008 can gain access to one or more data elements.

The data payment allocation engine 13038 may allocate data marketplace payments. The data payment allocation engine 13038 may allocate data marketplace payments according to the value of the data stream 13010, the value of contributions to the data stream 13010, etc. Such payment allocation may enable the data marketplace 13008 to allocate payments to data contributors based on the value of their data contributions.

For example, data contributors to higher value data streams 13010 may receive higher payments than data contributors to lower value data streams 13010. Similarly, data marketplace participants, such as IoT device manufacturers and system integrators, may be rated or ranked by the value of their data and the strength of the configurations they provide and support.

The data marketplace 13008 may be a self-organizing data marketplace. The self-organizing data marketplace may self-organize using self-organization capabilities 13012. The self-organization capabilities 13012 may learn, develop, and optimize using artificial intelligence (AI) capabilities. The AI capabilities may be provided, for example, by machine learning 13014 capabilities. Self-organization may occur via expert systems and may be based on the application of a model, one or more rules, etc. Self-organization may occur via neural networks or deep learning systems, for example, by optimizing variations in the organization of the data pool over time based on feedback to one or more measures of success. Self-organization may occur via a hybrid or combination of rule-based systems, model-based systems, and neural networks or other AI systems. Various capabilities may be self-organized, such as how data elements are presented in the marketplace user interface, what data elements are presented, what data streams are obtained as input to the marketplace, how the data elements are described, what metadata is provided with the data elements, how the data elements are stored (e.g., in "hot" storage such as a cache or in slower but cheaper storage locations), where the data elements are stored (e.g., at the edge of the network), how the data elements are combined, fused, or multiplexed, etc. Feedback to the self-organization may include various metrics and success measures as described throughout this disclosure, such as profit measures, yield measures, ratings (by users, purchasers, licensees, reviewers, etc.), and interest measures (e.g., clickstream activity, time spent on a page, time spent reviewing an element or link to a data element, etc.).

Data marketplace inputs 13056, data streams 13010, and data pools 13070 may be organized based on metrics and measures of success for the data marketplace 13056. Data marketplace inputs 13056, data streams 13010, and data pools 13070 may be organized by self-organization capabilities 13012, which can automatically organize the marketplace inputs 13056, data streams 13010, and data pools 13070 without requiring interaction by a user of the data marketplace 13008.

The success metrics and measures may also be used to configure the data brokering engine 13042 to execute transactions between at least two market participants. The machine learning engine 13014 may use the success metrics to automatically configure the data brokering engine 13042 without requiring user intervention. The success metrics may also be used by a pricing engine, such as the marketplace valuation engine 13040, to set prices for one or more data elements within the data marketplace 13008.

In an exemplary and non-limiting embodiment, the self-organizing data marketplace may determine which types of data streams 13010 are most valuable and self-organize to offer for sale the other most valuable data streams 13010. Calculation of the value of the data streams may be performed by the marketplace valuation engine 13040.

In an embodiment, a policy automation system for a data collection system in an industrial environment may include: a policy input interface configured to receive policy input related to the definition of at least one parameter of rules, policies, and protocols, where the at least one parameter defines at least one of a configuration of a data collection device, an access policy for accessing data from the data collection device, and a collection policy for collection of data by the device; and a policy automation engine configured to receive the input and automatically configure and deploy the at least one rule, policy, and protocol within the system for data collection. In an embodiment, the at least one parameter may define at least one of an energy usage policy, a cost-based policy, a data write policy, and a data retention policy. The parameter may relate to a policy selected from a compliance policy, a fault policy, a configuration policy, an accounting policy, a provisioning policy, and a security policy for defining how devices are created, deployed, and managed. The compliance policy may include a data ownership policy. The data ownership policy specifies who owns the data. The data ownership policy may specify how the owner may use the data. The compliance policy may include a data analysis policy. A data analysis policy may specify what data a data owner can access, how the data owner can use the data, and how the data owner can combine the data with other data. A compliance policy may include a data usage policy, a data format policy, etc. A data format policy may include a standard data format policy, a mandatory data format policy, etc. A compliance policy may include a data transmission policy. A data transmission policy may include an inter-jurisdiction data transmission policy. A compliance policy may include a data security policy, a data privacy policy, an information sharing policy, etc. A data security policy may include an at-rest data security policy, a transmitted data security policy, etc. An information sharing policy may include policies specifying when information may be sold, when information may be shared, etc. A compliance policy may include a jurisdiction policy. A jurisdiction policy may include policies specifying who controls data. A jurisdiction policy may include policies specifying when data may be controlled. A jurisdiction policy may include policies specifying how data transmitted across boundaries is controlled.

In an embodiment, a policy automation system for a data collection system in an industrial environment may include: a policy automation engine that enables configuration of multiple policies that apply to the collection and utilization of data processed by multiple network-connected devices located in multiple industrial environments, the policy automation engine being hosted on an information technology infrastructure element located separately from the industrial environments; and, once configured in the policy automation engine, the policies are automatically deployed to multiple devices in the multiple industrial environments, the policies setting configuration parameters related to the types of data collected by the data collection system and access permissions for the collected data. The policies may include multiple policies selected from among compliance policies, fault policies, configuration policies, accounting policies, provisioning policies, and security policies, and multiple policies communicatively coupled to the policies, for defining how devices are created, deployed, and managed. The policy input interface may be configured to receive policy inputs that are used as inputs to at least one of the rules, policies, and protocol definitions, such as in the case where the policy automation system is a centralized source of policies for creating, deploying, and managing policies for devices in the industrial environment.

In an embodiment, a policy automation system for a data collection system in an industrial environment can include: a policy automation engine that enables configuration of multiple policies that apply to the collection and utilization of data processed by multiple network-connected devices located in multiple industrial environments, the policy automation engine hosted on an information technology infrastructure element located separately from the industrial environments, and configuring policies in the policy automation engine that set configuration parameters related to data collected by the data collection system and access permissions for the collected data, the policy automation system communicatively coupled to the multiple devices via a cloud network connection. The cloud network connection can be a private cloud connection, a publicly offered cloud connection, a primary connection between the policy automation system and the devices, an intranet cloud connection connecting devices within a single enterprise, an extranet cloud connection connecting devices across multiple enterprises, a secure cloud network connection protected by a virtual private network (VPN) connection, etc.

In embodiments, a data marketplace for data collection systems in an industrial environment may include an input interface structured to receive marketplace input, at least one of a data pool and a data stream for providing data collected within the marketplace, and a data stream including data from the data pool. In embodiments, at least one parameter of the marketplace may be automatically configured by a machine learning function based on indicators of success of the marketplace. The input may include multiple data streams from multiple industrial data collectors. The collector may be a multiplexed data collector. The input may include consortium input. The consortium may be an existing consortium, a new consortium, a new consortium related to the data stream through a common interest, etc. The indicators and measures of success may include profit measures, yield measures, ratings, indicators of interest, etc. Ratings may include user ratings, buyer ratings, licensee ratings, reviewer ratings, etc. Indicators of interest include clickstream activity, time on page, time spent on review elements, links to data elements, etc.

In embodiments, a data marketplace for data collection systems in an industrial environment may include an input system structured to receive multiple data inputs related to data sensed from or about one or more industrial machines; at least one of a data pool and a data stream for providing the collected data within the marketplace; and a self-organizing system for organizing at least one of the data inputs and the data pool based on marketplace success metrics. In embodiments, the self-organizing system may optimize variations in the organization of the data pool over time. The optimized variations may be based on feedback to one or more success metrics. The self-organizing system may organize how data elements are displayed in the marketplace user interface. The self-organizing system may select which data elements to present, which data streams to obtain as input to the marketplace, how to describe the data elements, what metadata to provide with the data elements, how the data elements are stored, the location of the storage elements within a communication network (e.g., in an edge element of the network), how the data elements are combined, etc. The storage method may include a cache or other "hot" storage method. The storage means may include slower but less expensive storage locations. The method for combining data elements may be a data fusion method, a data multiplexing method, or the like. The self-organizing system may receive feedback data, for example, where the feedback data includes success metrics and measurements. The success metrics and measures may include profit metrics, yield metrics, ratings, metrics of interest, or the like. Ratings may be provided by users, buyers, licensees, or reviewers. The success metrics and measures may include metrics of interest. Metrics of interest may include clickstream activity, time spent on page activity, time spent reviewing elements, links to data elements, or the like. The self-organizing system may determine a value for the data stream. The value of the data stream may determine which data streams are offered for sale by the data marketplace. Ratings may include user ratings. Ratings may include buyer ratings, licensee ratings, reviewer ratings, or the like.

In embodiments, a data marketplace for data collection systems in an industrial environment may include: an input interface structured to receive data input from, or relating to, one or more of a plurality of industrial machines; at least one of a data pool and a data stream for providing the collected data within the marketplace; and a rights management engine for managing permissions to access the data within the marketplace. In embodiments, at least one parameter of the rights management engine may be automatically configured by machine learning functionality based on metrics of success for the marketplace. The rights management engine may assign rights to participants in the data marketplace. The rights may include business strategy and solution rights, liaison rights, marketing rights, security rights, technology rights, testbed rights, etc. Success metrics or measures may include profit metrics, yield metrics, ratings, etc. Ratings may include user ratings, buyer ratings, inclusive licensee ratings, reviewer ratings, etc. Success metrics may include interest metrics. For example, interest may include clickstream activity, time spent on a page, time spent reviewing elements, and links to data elements.

In embodiments, a data marketplace for data collection systems in an industrial environment may include an input interface structured to receive data input from or regarding one or more of a plurality of industrial machines; at least one of a data pool and a data stream for providing data collected within the marketplace; and a data brokering engine configured to execute data transactions between at least two marketplace participants. In embodiments, at least one parameter of the data brokering engine may be automatically configured by a machine learning facility based on metrics of marketplace success. The data transaction input may include a market value rating. The marketplace value rating may be assigned to a marketplace participant. The market value rating may be assigned to a market participant based on the value of the input the market participant provided to the marketplace. The data transaction may be a trade, a sales transaction, a payment transaction, or the like. The metrics and measures of success may include a profit measure, a yield measure, a rating, etc. The rating may include a user rating. The rating may include a buyer rating, a licensee rating, a reviewer rating, etc. The metrics and measures of success may include a rating of interest. Metrics of interest may include clickstream activity, time spent on page, time spent on review elements, links to data elements, etc.

In embodiments, a data marketplace for data collection systems in an industrial environment may include an input interface structured to receive data input from or regarding one or more of a plurality of industrial machines; at least one of a data pool and a data stream for providing the collected data within the marketplace; and a pricing engine for setting a price for at least one data element within the marketplace. In embodiments, pricing may be automatically set for the pricing engine by machine learning functionality based on metrics of success for the marketplace. Success metrics and measures may include profit measures, yield measures, ratings, etc. Ratings may include user ratings. Ratings may include buyer ratings, licensee ratings, reviewer ratings, etc. Metrics and success measures may include metrics of interest. Metrics of interest may include clickstream activity, time spent on page, time spent on review elements, links to data elements, etc.

In embodiments, a data marketplace for data collection systems in an industrial environment may include an input interface structured to receive data input from or regarding one or more of a plurality of industrial machines; at least one of a data pool and a data stream for providing data collected within the marketplace; and a user interface for presenting data elements and at least one mechanism by which parties using the marketplace can gain access to the at least one data stream or data pool. In embodiments, pricing may be automatically set for the pricing engine by machine learning functionality based on metrics of success for the marketplace. Success metrics and measures may include profit measures, yield measures, ratings, etc. Ratings may include user ratings. Ratings may include buyer ratings, licensee ratings, reviewer ratings, etc. Metrics and success measures may include metrics of interest. Metrics of interest may include clickstream activity, time spent on page, time spent on review elements, links to data elements, etc.

In an embodiment, a data collection system in an industrial environment may include a policy automation system for a data collection system in an industrial environment, the system including: a plurality of rules selected from among roles, permissions, and usages, the plurality of rules communicatively coupled to policies, protocols, and policy inputs; a plurality of policies selected from among compliance, fault, configuration, accounting, provisioning, and security policies for defining how devices are created, deployed, and managed, the plurality of policies communicatively coupled to policies, protocols, and policy inputs; and a policy input interface structured to receive policy inputs for use as inputs to at least one of the rule, policy, and protocol definitions.

In embodiments, the data marketplace may include an input interface structured to receive marketplace input, a plurality of data pools that store collected data including the marketplace input and make the collected data available for use by the marketplace, and a data stream that includes data from the data pools.

As described herein and in the attached Appendix B, intelligent industrial equipment and systems may be configured into various networks, including self-forming networks, private networks, internet-based networks, and the like. One or more smart heating systems, such as those described in Appendix B, which may incorporate hydrogen production, storage, and use, may be configured as nodes in such a network. In embodiments, a smart heating system may be configured with one or more network ports, such as a wireless network port facilitating connectivity via Wi-Fi and other wired and/or wireless communication protocols as described. Smart heating systems, such as smart hydrogen production systems and smart hydrogen storage systems described in Appendix B, may be configured individually or as integrated systems connected as one or more nodes in a network of industrial equipment and systems. In this example, a smart heating system may be deployed in an on-site industrial equipment operations center, such as a portable trailer equipped with communications capabilities. Such deployed smart heating systems may be manually, automatically, or semi-automatically configured to join a network of devices, such as industrial data collection, control, and monitoring nodes, and participate in network management, communications, data collection, data monitoring, control, and the like.

In another example of a smart heating system participating in a network of industrial equipment monitoring, control, and data collection devices, multiple smart heating systems may be configured into a smart heating system sub-network. In an embodiment, data generated by the sub-network of devices may be communicated over the industrial equipment network using the methods and systems described herein.

In embodiments, the smart heating system may participate in a network of industrial equipment as described herein. As an example of this, as depicted in FIG. 136, one or more of the smart heating systems may be configured as IoT devices, such as IoT device 13500, as described herein. In embodiments, the smart heating system 13502 may communicate via access points, via a mobile ad-hoc network or connectivity mechanisms described herein for devices and system elements, and/or via network elements described herein.

In embodiments, one or more of the smart heating systems described in Appendix B may incorporate, integrate, use, or interface with equipment, platforms, modules, etc. that enable the smart heating systems to perform functions such as analytics, self-organizing storage, data collection, etc. that improve data collection and deploy increased intelligence. Various data analysis techniques described herein, such as machine pattern recognition of data, collection, generation, storage, and communication of fused data from analog industrial sensors, multi-sensor data collection and multiplexing, self-organizing data pools, and self-organizing swarms of industrial data collectors, may be embodied in, enabled by, used in conjunction with, or derived from data collected by one or more of the smart heating systems.

In an embodiment, a smart heating system may be configured with local data collection functionality to acquire long blocks of data (i.e., long data acquisition periods) from multiple sensors, etc., at a single, relatively high sampling rate, as opposed to multiple data sets acquired at different sampling rates. In this example, the local data collection functionality may include planning data collection routes based on historical templates, etc. In an embodiment, the local data collection functionality may include managing data collection bands, such as specific frequency bands and bands defining at least one of spectral peaks, true peak levels, crest factors, etc.

In embodiments, one or more smart heating systems may participate as a self-organizing swarm of IoT devices that may facilitate industrial data collection. Smart heating systems, along with other smart heating systems, IoT devices, industrial data collectors, etc., may organize among themselves to optimize data collection based on the capabilities and conditions of the smart heating system, and the need to sense, record, and acquire information from the smart heating system and its surroundings. In embodiments, one or more smart heating systems may be configured with processing intelligence and capabilities that can facilitate coordination with other members, devices, etc. of the swarm. In embodiments, members of a smart heating system in a swarm may track information about what other smart heating systems in the swarm are processing and collecting to facilitate allocating data collection activities, data storage, data processing, and data publication among members of the swarm.

In embodiments, multiple smart heating systems, even if configured with different burners, provide a common hydrogen production system and/or a common hydrogen storage system. In embodiments, multiple smart heating systems may coordinate data collection associated with the common hydrogen production and/or storage system so that data collection is not unnecessarily duplicated by multiple smart heating systems. In embodiments, smart heating systems that may consume hydrogen may coordinate their hydrogen production and/or storage data collection with other smart heating systems so that a smart heating system that may be preparing to consume hydrogen is tracked even if another smart heating system is performing the data collection, processing, etc. In embodiments, smart heating systems in a group may communicate with each other to determine which smart heating system will collect and process hydrogen consumption data when each smart heating system prepares to stop consuming hydrogen, such as when heating, cooking, or other use of heat nears completion. However, when multiple smart heating systems are actively consuming hydrogen, data collection may be performed by a first smart heating system, data analysis may be performed by a second smart heating system, and recording or reporting of the data and data analysis may be performed by a third smart heating system; in this example, recording or reporting of the data and data analysis may be performed by the third smart heating system. By assigning specific data collection, processing, storage, and reporting functions to different smart heating systems, appropriate roles may be assigned to specific smart heating systems that have sufficient storage, processing bandwidth, communication bandwidth, available energy supply, etc. A smart heating system may notify the group that it will soon enter a power save mode when a heating time, cooking time, etc. is nearing the end, so that it is not assigned to perform tasks such as data analysis that would need to be interrupted by the power save mode.

In embodiments, another advantage of using a group of smart heating systems as disclosed herein is that the data storage capabilities of the group can be utilized to store more information than can be stored in a single smart heating system by sharing the responsibility of storing data for the group.

In an embodiment, a self-organizing swarm of smart heating systems includes one of the systems being designated as a master swarm participant that can drive decision-making regarding the allocation of resources of individual smart heating systems within the swarm for activities such as data collection, processing, storage, and reporting.

In embodiments, the methods and systems for self-organizing swarms of industrial data collectors may include multiple additional functions, capabilities, features, modes of operation, etc., as described herein. In embodiments, the smart heating system may be configured to perform any or all of these additional functions, capabilities, features, etc., without limitation.

The methods and systems described herein may be deployed, in part or in whole, via a machine executing computer software, program code, and/or instructions on a processor. The present disclosure may be implemented as a method on a machine, as a system or apparatus that is part of or associated with a machine, or as a computer program product embodied in a computer-readable medium that executes on one or more machines. In embodiments, the processor may be part of a server, cloud server, client, network infrastructure, mobile computing platform, stationary computing platform, or other computing platform. The processor may be any type of computing or processing device capable of executing program instructions, code, binary instructions, etc. The processor may be or include any variant, such as a signal processor, digital processor, embedded processor, microprocessor, or coprocessor (e.g., mathematical coprocessor, graphics coprocessor, communication coprocessor, etc.), that can directly or indirectly facilitate the execution of program code or program instructions stored thereon. Furthermore, the processor may enable the execution of multiple programs, threads, and code. Threads may execute simultaneously to increase processor performance and facilitate simultaneous operation of applications. As a method of implementation, the methods, program codes, program instructions, etc. described herein may be implemented with one or more threads. A thread may spawn other threads, which may have associated priorities, and the processor may execute these threads based on priorities or other ordering based on instructions provided in the program code. The processor, or any machine utilizing it, may include non-transitory memory that stores the methods, codes, instructions, and programs described herein. The processor may access non-transitory storage media via an interface that can store the methods, codes, and instructions described herein. Storage media associated with the processor for storing methods, programs, codes, program instructions, or other types of instructions executable by a computing or processing device may include, but are not limited to, one or more of a CD-ROM, DVD, memory, hard disk, flash drive, RAM, ROM, cache, etc.

A processor may include one or more cores, which can increase the speed and performance of a multiprocessor. In embodiments, the process may be a dual-core processor, a quad-core processor, or a chip-level multiprocessor that combines two or more independent cores (called dies).

The methods and systems described herein may be deployed, in part or in whole, via machines executing computer software on servers, clients, firewalls, gateways, hubs, routers, or other computer and/or network hardware. Software programs may be associated with servers, including file servers, print servers, domain servers, Internet servers, intranet servers, cloud servers, and other variations such as secondary servers, host servers, and distributed servers. A server may include one or more of the following: memory, a processor, computer-readable ephemeral and/or non-ephemeral media, storage media, ports (physical and virtual), communication devices, and interfaces accessible to other servers, clients, machines, and devices via wired or wireless media. The methods, programs, or code described herein may be executed by a server. Additionally, other equipment necessary to execute the methods described herein may be considered part of the infrastructure associated with the server.

The server may provide an interface to other devices, including, but not limited to, clients, other servers, printers, database servers, print servers, file servers, communication servers, distributed servers, social networks, etc. Furthermore, this coupling or connection may facilitate remote execution of programs over a network. Networking some or all of these devices may facilitate parallel processing of a program or method at one or more locations without departing from the scope of this disclosure. Furthermore, any of the devices connected to the server via an interface may include at least one storage medium capable of storing methods, programs, code, and/or instructions. A central repository may provide program instructions for execution on different devices. In this embodiment, the remote repository may function as a storage medium for program code, instructions, and programs.

Software programs may be associated with clients, including file clients, print clients, domain clients, Internet clients, intranet clients, and other variations such as secondary clients, host clients, and distributed clients. A client may include one or more of the following: memory, a processor, computer-readable transient and/or non-transitory media, storage media, ports (physical and virtual), communication devices, and interfaces that can access other clients, servers, machines, and devices via wired or wireless media. The methods, programs, or codes described herein may be executed by a client. Additionally, other devices necessary for execution of the methods described herein may be considered part of the infrastructure associated with the client.

Clients may provide interfaces to other devices, including, but not limited to, servers, other clients, printers, database servers, print servers, file servers, communication servers, distributed servers, etc. Furthermore, this coupling and/or connection may facilitate remote execution of programs over a network. Networking some or all of these devices may facilitate parallel processing of a program or method at one or more locations without departing from the scope of this disclosure. Furthermore, any of the devices connected to a client via an interface may include at least one storage medium capable of storing methods, programs, applications, code, and/or instructions. A central repository may provide program instructions for execution on different devices. In this embodiment, remote repositories may function as storage media for program code, instructions, and programs.

Figure 286 provides a schematic diagram of the architecture, its components, and functional relationships for an Industrial Internet of Things solution. The data processing platform 13700 may include a series of data processing layers, such as intelligent storage systems and capabilities 13724, monitoring and collection systems and capabilities 13728, and processing and intelligence capabilities 13730, as described in various embodiments throughout this disclosure and the documents incorporated by reference herein, which can serve a series of applications 13732, such as where the various capabilities, microservices, etc. of the platform 13700 can serve multiple applications 13732 in a unified or integrated manner. The platform 13700 may be deployed in a cloud computing environment, such as on cloud computing infrastructure and services, and may connect to the industrial environment 13704, such as via monitoring and collection systems and capabilities 13728, and edge systems 13718 may provide connectivity (using any of the networks and/or software systems, services, protocols, or capabilities described throughout this disclosure and the documents incorporated by reference herein, or using cellular connectivity (including 5G capabilities), Wi-Fi, Bluetooth, and other network protocols, and many others, such as application programming interfaces, ports, connectors, brokers, and other software systems, as will be understood by those skilled in the art), computation (such as data processing, signal processing, data transformation, data normalization), and intelligence (such as application of decision rules or models, computation and manipulation of inputs to generate analyses, alerts, reports, and/or control instructions, application of one or more artificial intelligence systems (such as machine learning systems, neural networks, expert systems, deep learning systems, or other systems disclosed throughout this disclosure or the documents incorporated by reference herein), etc.

In an embodiment, the platform 13700 may generate, host, integrate, link, contain, integrate, or otherwise interact with a set of industrial entity digital twins 13734, which may constitute a digital representation or replica of the real-world state of a set of industrial entities 13736, such as workers 13712, fixed assets 13712 (machines, systems, equipment, furniture, etc.), infrastructure 13710 (floors, walls, ceilings, loading docks, foundations, etc.), and many others that reside in or around the industrial environment 13704, such as fixed assets 13712 (machines, systems, equipment, furniture, etc.), infrastructure 13710 (floors, walls, ceilings, loading docks, foundations, etc.), and moving assets 13708 (vehicles, forklifts, autonomous vehicles, drones, assembly lines, fans, rotors, turbines, pumps, valves, fluids, etc.).

In an embodiment, the edge system 13718 may interface with each of the mobile data collectors 13702 (including on-board intelligence (e.g., data storage and processing, power utilization optimization, etc.), such as having any of the functionality described throughout this disclosure and the documents incorporated herein by reference). For example, functionality such as a crosspoint switch for selecting and routing a subset of sensor channels, a reader such as an RFID reader for obtaining data from the entities 13736, such as asset tags, or the ability to connect to and read from the sensors 13722 and/or on-board diagnostic systems. Also, SLAM (Simultaneous Location and Address Management) may be used. The mobile data collector 13702 may be a mobile data collector (e.g., a mobile data collector (e.g., a mobile data collector) 13702 or a mobile data collector (e.g., a mobile data collector) 13702. The mobile data collector 13702 may be ... Thus, the location, position, orientation, etc. of the data collection point by the mobile data collector 13702 may be automatically registered to or by the SLAM system 114, and a unified data set may be provided to the edge system 13718 for further communication, calculation, or processing. For example, a series of vibration data readings taken by the three-axis mobile data collector 13702 may be registered to a specific location in a mapped point cloud of data created by or within the SLAM system 13714, allowing the vibration information to be linked to those portions of the point cloud and subsequently linked to machines or other entities 13730 represented by that portion of the point cloud or by other mapping systems.

In embodiments, the SLAM system 13714 and the mobile data collector 13702 are integrated into a single portable device, allowing data collection routes to be executed (e.g., by a worker, drone, or autonomous vehicle) while the space is being mapped by the SLAM system 13714. This may thus constitute a simultaneous location mapping data collection system (SLAMDC) 13740. In embodiments, the mobile data collector 13702 may collect data from sensors 13722 (such as onboard triaxial vibration sensors, ultrasonic sensors, acoustic sensors, thermal sensors, and many other sensors) included in or integrated with the data collector 13702. In embodiments, the mobile data collector 13702 may collect data from sensors 13722 positioned in or around the environment 13704, such as cameras, analog sensors, digital sensors, or many other sensors. In an embodiment, a data collector, such as a worker, drone, or autonomous vehicle, may direct additional sensors to be placed on or in proximity to a set of industrial entities 13736, such as where intelligence indicates a benefit from collecting additional information, such as where a problem is detected or predicted, such as by onboard intelligence, intelligence of edge systems 13718, or intelligent systems 13730 of platform 13700.

In an embodiment, edge system 13718 may include, link or connect to, and integrate with control system 13742, for example, to provide control of one or more industrial entities 13736, such as to control machines (CNC machines, additive manufacturing machines, energy systems (e.g., generators or turbines), assembly lines, etc.) in a factory, control workflows (production workflows, inspection workflows, data collection workflows, maintenance workflows, service workflows, etc.), control of a subsystem, system, or operation of an entire factory or set of factories, etc. The processing, computation, and intelligence capabilities of the edge systems 13718 (and the platform 13700, by virtue of connectivity between the edge systems 13718, the processing, computation, and intelligence capabilities 13730 of the platform 13700) can thus benefit from input from and provide input to (including control signals for) the set of control systems 13742. Data from the mobile data collectors 13702 (including data from sensors 13722, onboard information of entities 13736, and other information), data from the edge systems 13718, data from the SLAM system 13714, data from the composite SLAMDC system 13740, data from one or more applications 13732, or data from the platform 13700 (including any of the layers therein) may be represented in a set of industrial digital twins 13734. For example, industrial digital twin 13734 may show a point cloud view of a mapped industrial environment (which in embodiments may be augmented, e.g., using 3D mapping, AR, or VR systems), with associated data collection elements presented in the point cloud view. Many examples are available, such as highlighting (e.g., by color, motion, etc.) areas of the point cloud where a system is vibrating in a manner that is out of normal range (e.g., exceeding a threshold severity level as discussed elsewhere herein) in digital twin 13734. Industrial entity digital twin 13734 may include, link, connect, or integrate with various interfaces and dashboards 13738, such as those configured for specific workflows, roles, and users. For example, dashboards and interfaces may be used by operators interacting with a particular machine (e.g., if the digital twin is used for training, workflow guidance, diagnosing problems, etc.), managers of factory floor operations (e.g., if the digital twin 13734 shows the layout of machines on the floor, traffic patterns (e.g., asset movements, moving assets 13708 and operators 13712 involved in a workflow), status information (including operating status, maintenance status, inspection status, etc.) for operators, machines, processes, etc.), analytical information (e.g., showing operational metrics, potential problems, etc.), inspectors (e.g., if the digital twin 13734 shows areas indicated by the data collector 13702 as requiring or beneficial for additional inspection (e.g., an inspector can check off items that have already been inspected or highlight items for further inspection by interacting with the digital twin interface or dashboard 13738), maintenance and service workers (e.g., if the digital twin 13734 shows a schematic highlighting the location of items needing maintenance and directing service workers appropriately), and These include users who may be presenting information and guidance (e.g., in alternate views) on how to navigate to the appropriate location and/or machine and perform service or maintenance (from checklists or workflows to virtual, mixed, or augmented reality training or guidance sessions that may be presented on the machine); front office managers (e.g., finance personnel who may be presenting financial information (including current and forecasted) such as ROI metrics, output metrics, and cost metrics); legal personnel (e.g., where the digital twin 13734 may present compliance information and highlight legal risks (e.g., safety violations, or where status information about operations indicates a potential breach of a company's contract (e.g., inability to produce contractually required output)); inventory managers; procurement personnel; and the like. Additionally, business executives, such as CEOs, CTOs, COOs, CIOs, CDOs, and CMOs, may interact with the digital twin 13734 representing an entire factory or set of factories to identify potential risks and opportunities, including understanding the interactions and/or contributions of elements of the industrial entity 13736 to the overall operations, strategy, etc. of the company.

In various embodiments, the interface and dashboard 13738 may display sensor information collected from sensors 13722, from mobile data collectors 13702, from the SLAM system 13714 (or composite SLAMDC system 13740), mapping information from the SLAM system 13714 or the SLAMDC system 13740, representations of the shape and location of the entity 13736 (e.g., point clouds, CAD drawings, photographs, 3D representations, blueprints, or abstract representations (e.g., topologies or hierarchies showing relationships), calculations, metrics, calculations, statistics, analyses, etc. (e.g., calculated by the edge system 13718, the processing and intelligence system 13730, or other systems), state or status information (e.g., showing the operational state or status of a workflow involving the industrial entity 13736), and the like.

Information elements from the industrial environment 13704 or information elements related to the industrial entities 13736 can be presented in an overlay (e.g., indicators or symbols are presented on top of a point cloud, photograph, or 3D representation of a unit in a 3D interface), in their native form (e.g., a point cloud is represented), in a 3D visualization (e.g., the interface treats the elements as 3D geometric elements), etc.

Interfaces and dashboards 13738 may include graphical interfaces (e.g., for laptops, tablets, mobile devices), touchscreen interfaces, voice-activated interfaces, augmented reality interfaces, virtual reality interfaces, mixed reality interfaces, application programming interfaces (APIs), etc.

Examples include component digital twins, which represent individual parts of a component; machine digital twins, which represent an entire machine; system digital twins, which represent a system including multiple components, parts, machines, etc. and their interactions; worker digital twins, which represent one or more attributes or states of a set of workers 13712; and deployment digital twins, which represent the layout or arrangement of entities 13736 (such as, but not limited to, the arrangement of components, assets, machines, workers, or other elements on a factory floor). Augmented reality, virtual reality, and mixed reality digital twins provide a realistic experience to a user, such as by simulating or mimicking interactions with assets, other workers, workflows, etc. (e.g., when training a worker or group of workers on how to operate or maintain a machine or system or how to perform a workflow involving a machine or system); and abstract digital twins, such as topologies, hierarchies, and flow diagrams, which represent elements and relationships.

In embodiments, interfaces and dashboards 13738 may be provided that facilitate drilling down and/or zooming up on the digital twin 13734 (whether under user control or automated based on understanding status information, contextual information, user interactions, etc.), moving to a broader view encompassing more components and/or their interactions, obtaining additional information (such as viewing additional metrics related to metrics represented in the digital twin 13734, more granular data, source data used to determine the metrics, etc.), etc.

In embodiments, the interface and dashboard 13738 may be configured to facilitate switching between views or types of digital twins of the same entity 13736 (whether under user control or through automation, such as based on understanding status information, contextual information, user interaction, or other factors related to the digital twin 13734). For example, a user may switch from an overall schematic view showing current status information of machines and workflows on the factory floor to a 3D view showing a realistic representation of one of the machines (e.g., one that highlights a problem, such as if the data collector 13702 determines that the machine is operating outside of normal parameters such as temperature, vibration, pressure, etc.).

In various embodiments, an end-to-end system is provided in which the industrial digital twin 13734 maintains continuous or periodically updated data connections to the mobile data collector 13702, the SLAM system 13714 and/or the SLAMDC system 13740 through one or more tiers of the platform 100 and connections to edge systems, such that the industrial digital twin 13734 provides real-time or periodically updated information regarding the current attributes, state, status, etc. of the entities 13736 within the industrial environment 13704. This may include representing, as described above, sensor data from sensors 13722, onboard data from entities 13736, control information from control system 13742, various data collected by data collector 13702, mapping information, information computed by edge intelligence of edge system 13718 and/or processing and intelligence system 13730, etc., to allow a manager, executive, or other user to create a highly interactive visualization and interaction of elements under the user's purview or that are otherwise of interest to the user.

In embodiments, data collection by the mobile data collectors 13702 and/or analytics derived from sensors 13722, control systems 13742, and/or on-board sensing or diagnostics of the industrial entities 13736 may be calculated by the edge systems 13718 and/or the processing and intelligence systems 13730 may include metrics indicative of the probability of an unplanned shutdown occurring during a period of time based on current information from these various data sources, and optionally based on historical data from results involving similar entities 13736. Unplanned shutdown metrics may be calculated for various entities 13736, such as machines, systems, workflows, factories, or sets of factories, and may be represented in the industrial digital twin 13734, such as by representing the metrics as overlay elements on the digital twin providing a schematic representation of the factory floor.

In embodiments, contributing factors to the probability of an unplanned shutdown of an industrial entity 13736, workflow, or operation, etc., may be analyzed and represented in an interface or dashboard 13738 of the industrial digital twin 13734. These components may include the probability of occurrence of known failure modes of a component or machine (e.g., calculated by physical models, historical models, predictive maintenance models using historical models, etc.), such as mechanical stress, overload, wear, bearing issues, coupling issues, unbalanced rotating parts, overheating, freezing, excessive viscosity, lubrication issues, clogging-based failures, cavitation, vacuum failure, leaks, low fluid levels, low pressure, electrical failures, power failures, part supply failures, tool absence, part absence, part damage, shutdown of another entity 13736, traffic congestion, information technology issues, calculation errors, cyber attacks, and many other issues.

In embodiments, the probability of an unplanned shutdown may be determined by a predictive machine, such as a neural network, trained on a historical data set of failures. In embodiments, the probability of an entity's unplanned shutdown may be determined by a combination of a model-based approach and a neural network. For example, a neural network may determine the probability of a particular type of failure and/or a particular component of a system, which may then be used in a model to calculate the probability of a system shutdown involving that type of failure or component, or vice versa.

In embodiments, the unplanned shutdown probability may be calculated by edge systems 13718, by platform 100's processing and intelligence capabilities 13730, or by a combination of these or other intelligence systems. The unplanned shutdown probability metrics may be represented in a set of industrial digital twins 13734, such as to provide managers, maintenance workers, executives, inspectors, etc. with a visual representation of the overall risk of unplanned shutdown and the components or entities 13736 that are at risk or contributing to an increased probability of unplanned shutdown of a factory, plant, system, process, line, machine, workflow, etc. This allows managers and executives to drill down to obtain more detailed information and take action to reduce risk. As an example, an executive may be presented with a view of a set of factories, with one factory represented in a different color (e.g., bright red) in the industrial digital twins 13734 based on its probability of unplanned shutdown exceeding a threshold (or simply having the highest probability among the set of factories). This allows management to focus on the factory and gain additional insight into operational choices that may have been overlooked if they were simply presented with raw data or spreadsheets that require them to calculate or estimate the probability of an unplanned shutdown. Similarly, the plant manager of a highlighted factory might have an industrial digital twin 13734 that displays the probability of unplanned shutdowns for various components of machinery and processes, such as pumps that maintain vacuum in critical semiconductor manufacturing equipment or parts used in the semiconductor manufacturing process. A process in the factory (or biological production process, for example) may be identified as being at high risk of failure based on vibration analysis that indicates cavitation, combined with other data sources such as the age of the pump and its maintenance and operating history. The pump may be highlighted in the configured view for the factory manager in the industrial digital twin 13734, for example, by highlighting it in a bright color and animating the pump with movement (e.g., shaking visual elements) that indicates the vibration issue is likely a contributing factor to the risk of an unplanned shutdown of the pump (leading to vacuum failure, critical production process failure, and factory-wide shutdown). Compared to a spreadsheet or raw data output, visual cues in a digital twin direct attention, allowing a plant manager to direct attention to a pump for maintenance or replacement (including interactions such as touching the pump in the digital twin). Instructions or messages provided by one user (e.g., a plant manager or executive) can result in a message or highlighting in another digital twin 13734 or user interface or dashboard 13738 configured for another user. For example, a pump, if flagged by a plant manager in the plant view, may appear in a service worker's digital twin 13734, showing a route to the pump and then switching to a view that guides the worker through inspection, maintenance, service, and/or replacement. In this way, a set of digital twins 13734 can highlight unplanned shutdown risks based on real-time or periodic connections to data collection systems via edge intelligence, optionally using guidance and instructions from additional views of the set of digital twins to facilitate workflows (enabled within the digital twin) in which attention is directed (by highlighting visual elements) to issues that various workers can address.

In an embodiment, there is end-to-end real-time or periodic connectivity between a set of industrial digital twins 13734 and industrial entities 13736 and their various on-board sensors via platform 13700, edge systems 13718, control systems 13742, data collectors 13702, SLAM systems 13714, SLAMDC systems 13740, and sensors 13722. Data collection systems, diagnostic systems, buses, etc. can facilitate control over various elements of these systems through manipulation of elements within the interfaces and dashboards 13738 of the digital twins 13734, including those that are linked to, included in, or integrated with one or more applications 13732, such as via APIs. For example, manipulating an element of the industrial digital twin 13734 may be used to configure or change data collection by the mobile data collector 13702, such as by having the mobile data collector 13702 switch channels (where multiple sensor channels are available and the data collector 13702 is instructed (via a crosspoint switch) to switch from collecting, for example, one axis of vibration channel, temperature and pressure, to collecting three axes of vibration data). This could occur, for example, if a manager sees a potential vibration problem in the machine's digital twin 13734 and touches an element to drill down, automatically or under user control, switching data collection modes to collect different sensor data, more granular data (e.g., much more). The digital twin 13734 may provide a variety of intelligence or computational capabilities, such as collecting data at short time intervals or collecting data in a streaming format. As another example, manipulating user interface or dashboard elements 13738 or providing instructions via an API to the digital twin 13734 may configure or change the configuration of intelligence or computational capabilities, such as the edge system 13718, the processing and intelligence system 13730 of the platform 13700, or other intelligence systems. For example, a user (or an automated system) may reconfigure an edge system to access different data sources, such as pruning data sources that are deemed to have less impact, or to use different data sources to generate results, such as those involving classification, predictive, or control activities. New data sources can be added that may improve the overall system performance. For example, a factory may have a predictive maintenance system (or multiple such systems). Once the factory is scanned to generate a point cloud representing various physical entities in the environment, such as during a data collection and mapping session in the SLAMDC system 13740, and the factory is displayed on the user's industrial digital twin 13734, the user may be presented with a set of additional data sources available for the factory, including predictive maintenance data, and the user may select a data source and link it (e.g., by drag and drop) to a portion of the digital twin (e.g., as shown below). As a result, the predictive maintenance data becomes available as a data source to any intelligence systems operating on the machines. To facilitate augmenting intelligence systems as in this example, or for other purposes, the platform 13700 may facilitate connectivity between the end-to-end industrial digital twin system 13734 (and elements that exchange information with and/or are controlled by it) and other information technology systems of an enterprise. For example, the platform 13700 may link to, provide input from, receive output from, and/or integrate with those other systems, including, but not limited to, enterprise resource planning systems, control systems, predictive maintenance systems, inventory management systems, procurement systems, inspection systems, compliance systems, quality management systems, operational planning systems, and a variety of other systems.

In an embodiment, the digital twin can provide a direct control interface to one or more industrial entities 13736 by manipulating user interface elements, dashboard elements 13738, or by providing instructions to the digital twin 13734 via an API to set or change the configuration of the control system 13742 or provide control signals to the control system 13736.

In embodiments, the industrial digital twin 13734 and associated end-to-end system of data collection and intelligence may be used in connection with supporting a service ecosystem, such as understanding maintenance and service needs, particularly when intelligence indicates a high probability of unplanned shutdown of a critical entity 13736, as represented in a set of industrial digital twins 13734 configured for use by users and applications (including those providing robotic process automation) involved in the service ecosystem, such as identifying risks, alerting to service issues, identifying and ordering needed parts, tools, or components, identifying qualified personnel with required expertise, scheduling personnel, parts, components, etc., scheduling required shutdowns of dependent processes and operations, routing personnel and assets to service locations (off and within the factory or plant floor), guiding personnel (including automated personnel) through procedures and protocols, facilitating data collection and reporting, and many other uses. This support includes providing real-time and/or periodic updates from data collection, providing visualization of elements (automatically and/or under user control) by zooming, drilling down, switching views, etc., allowing interaction to obtain or configure intelligence and/or control, and other features described throughout this disclosure and in the documents incorporated herein by reference.

FIG. 287 is a schematic diagram illustrating an industrial setting 28720 in which a sensor kit 28700 is installed. In embodiments, the sensor kit 28700 may refer to a fully deployable, purpose-configured industrial IoT system provided in a unified kit and ready for deployment in the industrial setting 28720 by a consumer entity (e.g., an owner or operator of the industrial setting 28720). In embodiments, the sensor kit 28700 allows the owner or operator to install and deploy the sensor kit with no or minimal configuration (e.g., setting user permissions, setting passwords, and/or setting notification and/or display preferences). The term "sensor kit" 28700 may refer to a collection of devices installed in an industrial environment 28720 (e.g., a factory, amine, oil field, oil pipeline, refinery, commercial kitchen, industrial park, storage facility, construction site, etc.). The collection of devices comprising sensor kit 28700 includes a collection of one or more Internet of Things (IoT) sensors 28702 and a collection of one or more edge devices 28704. For purposes of discussion, references to "sensors" or "sensor devices" should be understood to mean IoT sensors unless specifically stated otherwise.

In embodiments, sensor kit 28700 includes an industrial component, a type of industrial component (e.g., a turbine, a generator, a fan, a pump, a valve, an assembly line, a pipe or pipeline, a food inspection line, a server rack, etc.), an industrial setting 28720, and/or a type of industrial setting 28720 (e.g., indoor, outdoor, manufacturing, mining, drilling, resource extraction, underground, underwater, etc.), and a set of edge devices capable of processing input from sensors and providing network-based communications. In embodiments, edge device 28704 may include or communicate with a local data processing system (e.g., a device configured to compress sensor data, filter sensor data, analyze sensor data, issue notifications based on sensor data, etc.) capable of providing local output, such as signals and analytical results resulting from the local processing. In embodiments, the edge device 28704 may include or communicate with a communication system (e.g., a Wi-Fi chipset, a cellular chipset, a satellite transceiver, a cognitive radio, one or more Bluetooth® chips, and/or other networking devices) capable of communicating data (e.g., raw and/or processed sensor data, notifications, command instructions, etc.) within and outside the industrial environment. In embodiments, the communication system is configured to operate independently of the primary data or communication network of the industrial environment 28720. In embodiments, the communication system includes security features and instructions that maintain complete physical and data separation from the primary data or communication network of the industrial setting 28720. For example, in embodiments, a Bluetooth® enabled edge device may be configured to allow pairing only with pre-registered components of the kit, and not with other Bluetooth® enabled devices within the industrial environment 28720.

In embodiments, the IoT sensor 28702 is a sensor device configured to collect sensor data and can communicate the sensor data to another device using at least one communication protocol. In embodiments, the IoT sensor 28702 is configured to be deployed in, on, or around an industrial entity of a defined type. The term industrial entity may refer to any object that can be monitored in an industrial environment 28720. In embodiments, the industrial entity may include industrial components (e.g., turbines, generators, fans, pumps, valves, assembly lines, pipes or conduits, food inspection lines, server racks, etc.). In embodiments, the industrial entity may include living things associated with the industrial setting 28720 (e.g., humans working in the industrial setting 28720 or livestock monitored in the industrial setting 28720). Depending on the intended use, setting, or purpose of the sensor kit 28700, the IoT sensor 28702 may have different configurations and form factors. Examples of different types of sensors include vibration sensors, inertial sensors, temperature sensors, humidity sensors, motion sensors, LIDAR sensors, smoke/fire sensors, current sensors, pressure sensors, pH sensors, light sensors, radiation sensors, etc.

In an embodiment, edge device 28704 may be a computing device configured to receive sensor data from one or more IoT sensors 28702 and perform one or more edge-related processes related to the sensor data. Edge-related processes may refer to processes performed on edge device 28704 to store sensor data, reduce communication network bandwidth, and/or reduce computational resources required in back-end systems. Examples of edge processes may include data filtering, signal filtering, data processing, compression, encoding, quick prediction, quick notification, emergency alerts, etc.

In embodiments, the sensor kit 28700 is pre-configured such that devices within the sensor kit 28700 (e.g., sensors 28702, edge devices 28704, collection devices, gateways, etc.) are configured to communicate with each other via the sensor kit network without the user having to configure the sensor kit network. A sensor kit network may refer to a closed communication network established among various devices of the sensor kit and utilizing two or more different communication protocols and/or communication media to enable communication of data between the devices and to a broader communication network, such as a public communication network 28790 (e.g., the Internet, a satellite network, and/or one or more cellular networks). For example, some devices within the sensor kit network may communicate using a Bluetooth® communication protocol, while other devices may communicate with each other using a short-range wireless communication protocol, a Zigbee protocol, and/or a Wi-Fi communication protocol. In some implementations, the sensor kit 28700 may be configured to establish a mesh network with various devices acting as routing nodes within the sensor kit network. For example, the sensor 28702 may be configured to collect data and transmit the collected data to the edge device 28704 via the sensor kit network, but may also be configured to receive and route data packets from other sensors 28702 in the sensor kit network toward the edge device 28704.

In embodiments, the sensor kit network may include additional types of devices. In embodiments, the sensor kit 28700 may include one or more collection devices (not shown in FIG. 138) that function as routing nodes for the sensor network, such that the collection devices are part of a mesh network. In embodiments, the sensor kit 28700 may include a gateway device (not shown in FIG. 138) that enables communication with a wider network, whereby the gateway device may communicate with the edge device 28704 via a wired or wireless communication medium in industrial settings 28720 that prevent the edge device 28704 from communicating with the public communication network 28790 (e.g., in factories with very thick concrete walls). Embodiments of the sensor kit 28700 may include additional devices without departing from the scope of this disclosure.

In an embodiment, the sensor kit 28700 is configured to communicate with the backend system 28750 over a communications network, such as the public communications network 28790. In an embodiment, the backend system 28750 is configured to receive sensor data from the sensor kit 28700 and perform one or more backend operations on the received sensor data. Examples of backend operations may include storing the sensor data in a database, performing analytical tasks on the sensor data, providing results of the analysis and/or visualizations of the sensor data to a user via a portal and/or dashboard, training one or more machine learning models using the sensor data, determining predictions and/or classifications regarding the operation of the industrial setting 28720 and/or industrial devices in the industrial setting 28720 based on the sensor data, controlling aspects of the industrial setting 28720 and/or industrial devices based on the predictions and/or classifications, issuing notifications to users via a portal and/or dashboard based on the predictions and/or classifications, etc.

It will be appreciated that in some embodiments, the sensor kit 28700 may provide additional types of data to the backend system 28750. For example, the sensor kit 28700 may provide additional types of data to the backend system 28750 regarding any detected issues (e.g., malfunction, low battery level, etc.) or potential issues with the sensor 28702 or other devices in the sensor kit 28700.

In embodiments, the sensor kit 28700 is configured to self-monitor for faulty components (e.g., a faulty sensor 28702) and report the faulty component to an operator. For example, in some embodiments, the edge device 28704 may be configured to detect a sensor 28702 failure based on a lack of reports from the sensor, a lack of response to a request (e.g., a "ping"), and/or unreliable data (e.g., data that regularly deviates from expected sensor readings). In some embodiments, the edge device 28704 maintains a sensor kit network map showing where each device in the sensor kit network is located and can provide a user with the approximate location and/or identifier of a faulty sensor.

In embodiments, the sensor kit 28700 may be implemented to allow post-installation configuration. Post-installation configuration may refer to updating the sensor kit 28700 by adding devices and/or services to the sensor kit 28700 after the sensor kit 28700 has been installed. In some of these embodiments, a user of the system (e.g., an operator of the industrial setting 28720) may subscribe to or purchase specific edge "services." For example, the sensor kit 28700 may be configured to execute particular programs installed on one or more devices of the sensor kit 28700 only if the user has valid subscription or ownership permissions to access the edge services supported by the programs. If the user no longer has valid subscription and/or ownership permissions, the sensor kit 28700 may prevent the execution of those programs. For example, a user may subscribe to unlocked AI-based edge services, mesh network functionality, self-monitoring services, compression services, in-house notifications, etc.

In some embodiments, a user can add a new sensor 28702 to the sensor kit after installation in a plug-and-play-like manner. In some of these embodiments, the edge device 28704 and the sensor 28702 (or other devices being added to the sensor kit 28700) may include respective short-range communication capabilities (e.g., a near-field communication (NFC) chip, an RFID chip, a Bluetooth chip, a Wi-Fi adapter, etc.). In these embodiments, the sensor 28702 may include persistent storage for storing identification data (e.g., a sensor identifier value) and other data that will be used to add the sensor 28702 to the sensor kit 28700 (e.g., industrial device type, supported communication protocols, etc.). In some embodiments, a user can initiate the post-installation addition to the sensor kit 28700 by pressing a button on the edge device 28704 and/or by bringing the sensor 28702 into proximity with the edge device 28704. In some embodiments, the edge device 28704 may emit a signal (e.g., radio frequency) in response to a user initiating a post-installation addition to the sensor kit. The edge device 28704 may emit the signal, for example, as a result of a human user pressing a button or at predetermined time intervals. The emitted signal may trigger a sensor 28702 that is close enough to receive the signal to transmit the sensor's 28702 sensor ID and any other appropriate configuration data (e.g., device type, communication protocol, etc.). In response to the sensor 28702 transmitting its configuration data (e.g., sensor ID and other associated configuration data) to the edge device 28704, the edge device 28704 may add the sensor 28702 to the sensor kit 28702. Adding the sensor 28702 to the sensor kit 28704 may include updating a data store or manifest stored on the edge device 28704 that identifies the sensor kit 28700 device and its associated data. Non-limiting examples of data that may be stored in a manifest associated with each sensor 28702 may include the communication protocol used by the sensor 28702 to communicate with the edge device 28704 (or intermediate device), the type of sensor data provided by the sensor 28702 (e.g., vibration sensor data, temperature data, humidity data, etc.), the model used to analyze the sensor data from the sensor 28702 (e.g., model identifier), alarm limits associated with the sensor 28702, etc.

In embodiments, sensor kit 28700 (e.g., edge device 28704) may be configured to update distributed ledger 28762 with sensor data captured by sensor kit 28700. In embodiments, distributed ledger 28762 is a blockchain or any other suitable distributed ledger 28762. Distributed ledger 28762 may be a public ledger or a private ledger. A private ledger reduces the power consumption requirements for maintaining the distributed ledger 28762, while a public ledger consumes more power but provides greater security. In embodiments, distributed ledger 28762 may be distributed across multiple node computing devices 28760. Node computing devices 28760 may be any suitable computing devices, including physical servers, virtual servers, personal computing devices, etc. In some embodiments, node computing devices 28760 are approved (e.g., via a consensus mechanism) before the node computing devices 28760 participate in the distributed ledger. In some embodiments, the distributed ledger 28762 may be stored privately. For example, the distributed ledger may be stored among a pre-approved set of node computing devices such that the distributed ledger 28762 cannot be accessed by unauthorized devices. In some embodiments, the node computing devices 28760 are sensor kits 28702 and edge devices 28704 of other sensor kits 28702.

In an embodiment, the distributed ledger 28762 is composed of a set of linked data structures (e.g., blocks, data records, etc.), where the linked data structures form an acyclic graph. For ease of explanation, the data structures will be referred to as blocks. In an embodiment, each block may include a header containing the block's unique ID, a body containing the data stored in the block, and a pointer. In an embodiment, the pointer is the block ID of the block's parent block, where the parent block is the block created before the block was written. The data stored in each block may be sensor data captured by each sensor kit 28700. Depending on the implementation, the type and amount of sensor data stored in each body of the block may vary. For example, a block may store a set of sensor measurements from one or more types of sensors 28702 of the sensor kit 28700 captured over a period of time (e.g., sensor data 28702 captured from all sensors 28702 of the sensor kit 28700 over a period of one hour or one day) and associated metadata (e.g., a sensor identifier for each sensor measurement and a timestamp for each sensor measurement or group of sensor measurements). In some embodiments, a block may store sensor measurements determined to be anomalous (e.g., outside the standard deviation of expected sensor measurements or a delta of a sensor measurement above a threshold) and/or sensor measurements indicating a problem or potential problem, and associated metadata (e.g., a sensor ID for each sensor measurement and a timestamp for each sensor measurement or group of sensor measurements). In some embodiments, the sensor data stored in a block may be compressed and/or encoded sensor data, such that the edge device 28704 compresses/encodes the sensor data into a more compact format. In embodiments, edge device 28704 may generate a hash of the body such that the contents of the body (e.g., the block ID and sensor data of the parent block) are hashed and cannot be changed without changing the value of the hash. In embodiments, edge device 28704 may encrypt the content within the block to prevent the content from being read by unauthorized devices.

As mentioned above, distributed ledger 28762 may be used for different purposes. In some embodiments, distributed ledger 28762 may further include one or more smart contracts. A smart contract is a self-executing digital contract. A smart contract may include code (e.g., executable instructions) that defines one or more conditions that trigger one or more actions. A smart contract may be written by a developer in a scripting language (e.g., JavaScript), an object code language (e.g., Java), or a compiled language (e.g., C++ or C). The written smart contract may be encoded into blocks and deployed to distributed ledger 28762. In embodiments, backend system 28750 is configured to receive smart contracts from users and write the smart contracts to the respective distributed ledger 28762. In embodiments, the address of the smart contract (e.g., the block ID of the block containing the smart contract) may be provided to one or more parties to the smart contract so that each party can invoke the smart contract using the address. In some embodiments, the smart contract may include an API that allows the parties to provide data (e.g., the address of the block) and/or send data (e.g., instructions to transfer funds to an account).

In an example implementation, an insurance company may allow insured owners and/or operators of industrial environments 28720 to agree to share sensor data with the insurance company to demonstrate that equipment within the facility is functioning properly. In return, the insurance company may issue a rebate or refund to the owner and/or operator if the owner and/or operator complies with the agreement with the insurance company. Compliance with the contract may be verified electronically by the distributed ledger participant nodes and/or sensor kits 28700 via a smart contract. In an embodiment, the insurance company may deploy a smart contract (e.g., by adding the smart contract to the distributed ledger 28762) that triggers the issuance of a rebate or refund of a portion of the insurance premium when the sensor kits 28700 provide the insurance company via the distributed ledger with sufficient sensor data indicating that the facility is operating without issue. In some of these embodiments, the smart contract may include a first condition requiring a certain amount of sensor data to be reported from the facility and a second condition that each instance of the sensor data equals a value (e.g., no classified or predicted issues) or a range of values (e.g., all sensor readings within a predefined range of values). In some embodiments, the action taken in response to one or more conditions being met may be depositing funds (e.g., wire transfer or cryptocurrency) into an account. In this example, the edge device 28704 may write blocks containing the sensor data to the distributed ledger. The edge device 28704 may also provide the addresses of these blocks to the smart contract (e.g., using the smart contract's API). Once the smart contract verifies the first and second conditions of the agreement, the smart contract may initiate the transfer of funds from the insurer's account to the insured's account.

In another example, a regulatory agency (e.g., a state, local, or federal regulatory agency) may require facility operators to report sensor data to ensure compliance with one or more regulations. For example, the regulatory agency may regulate food inspection facilities, pharmaceutical manufacturing facilities, e.g., manufacturing facility 1700, indoor agriculture facilities, e.g., indoor agriculture facility 1800, offshore oil drilling facilities, e.g., underwater industrial facility 1900, etc. In embodiments, the regulatory agency may deploy a smart contract configured to receive and validate sensor data from the industrial setting 28720 and, in response to validating the sensor data, issue a compliance token (or certificate) to the facility owner's account. In some of these embodiments, the smart contract may include a condition requiring a certain amount of sensor data to be reported from the facility and a second condition requiring the sensor data to comply with reporting regulations. In this example, the edge device 28704 may write a block including the sensor data to the distributed ledger 28762. The edge device 28704 may also provide the addresses of these blocks to the smart contract (e.g., using the smart contract's API). Once the smart contract verifies the first and second terms of the agreement, the smart contract may generate a token indicating compliance by the venue operator and initiate the transfer of funds to an account (e.g., a digital wallet) associated with the venue.

Distributed ledger 28762 may be adapted for additional or alternative applications without departing from the scope of this disclosure.

Figures 139, 140, and 141 show example configurations of a sensor kit network 28800. Depending on the sensor kit 28700 and the industrial environment 28720 in which the sensor kit 28700 is installed, the sensor kit network 28800 can communicate in different ways.

139 shows an exemplary sensor kit network 28800A that is a star network. In these embodiments, the sensors 28702 communicate directly with the edge devices 28704. In these embodiments, the communication protocol(s) utilized by the sensor devices 28702 and the edge devices 28704 to communicate are based on one or more of the physical area of the sensor kit network 28702, the available power source, and the type of sensors 28702 in the sensor kit 28700. For example, in settings where the area to be monitored is a relatively small area and the sensor 28702 cannot be connected to a power source, the sensor 28702 may be fabricated with a Bluetooth®, Low Energy (BLE) microchip that communicates using a Bluetooth®, Low Energy protocol (e.g., the Bluetooth®, 5 protocol maintained by the Special Interest Group). In another example, in a relatively small area where many sensors 28702 are to be deployed, the sensor 28702 may be fabricated with a Wi-Fi microchip that communicates using the IEEE 802.11 protocol. In the embodiment of FIG. 139, the sensor 28702 may be configured for one-way or two-way communication. In embodiments where edge device 28704 does not need to communicate data and/or instructions to sensor 28702, sensor 28702 may be configured for one-way communication. In embodiments where edge device 28704 communicates data and/or instructions to sensor 28702, sensor 28702 may be configured with a transceiver for two-way communication. A star network may be configured with devices having other suitable communication devices without departing from the scope of this disclosure.

FIG. 140 illustrates an exemplary sensor kit network 28800B, which is a mesh network in which nodes (e.g., sensors 28702) connect to each other directly, dynamically, and/or non-hierarchically to cooperate with each other to efficiently route data to and from edge device 28704. In some embodiments, devices in the mesh network (e.g., sensors 28702, edge device 28704, and/or any other devices in sensor kit network 28800B) may be configured to self-organize and self-configure the mesh network such that sensors 28702 and/or edge device 28704 determine which devices route data on behalf of other devices and/or provide redundancy for transmission in the event of a routing node (e.g., sensor 28702) failing. In embodiments, the sensor kit 28700 may be configured to implement a mesh network in an industrial setting 28720 where the area to be monitored is relatively large (e.g., greater than 28700 meters in radius from the edge device 28704) and/or where the sensors 28702 in the sensor kit 28700 are intended to be installed in close proximity to one another. In the latter scenario, the power consumption of the individual sensors 28702 may be reduced because the distance each individual sensor 28702 needs to transmit is relatively small compared to sensors 28702 in a star network. In embodiments, the sensors 28702 may be manufactured with ZigBee® microchips, Digi XBee® microchips, Bluetooth®, Low Energy microchips, and/or other suitable communication devices configured to participate in a mesh network.

FIG. 141 illustrates an example of a sensor kit network 28800C that is a hierarchical network. In these embodiments, the sensor kit 28700 includes a set of collection devices 28806. A collection device 28806 may refer to an on-sensor device that receives sensor data from a sensor device 28704 and routes the sensor data to an edge device 28704, either directly or via another collection device 28806. In embodiments, a hierarchical network may refer to a network topography in which one or more intermediate devices (e.g., collection device 28806) route data from one or more respective peripheral devices (e.g., sensor device 28702) to a central device (e.g., edge device 28704). A hierarchical network may include wired and/or wireless connections. In embodiments, the sensor devices 28702 may be configured to communicate with the collection devices 28806 via any suitable communication device (e.g., Bluetooth, Low Energy microchips, Wi-Fi microchips, ZigBee microchips, etc.). In embodiments, the hierarchical sensor kit network may be implemented in industrial environments 28720 where a power source is available to power the collection devices 28806 and/or where the sensors 28702 are likely to be too far apart to support a reliable mesh network.

The examples in Figures 139 through 141 are provided for examples of different sensor kit network topologies. These examples are not intended to limit the types of sensor kit networks 28800 that can be formed by the sensor kits 28700. Additionally, the sensor kit networks 28800 may be configured as a hybrid of star networks, hierarchical networks, and/or mesh networks, depending on the industrial environment 28720 in which each sensor kit 28800 is deployed.

FIG. 289A illustrates an exemplary IoT sensor 28702 (or sensor) according to an embodiment of the present disclosure. An embodiment of the IoT sensor 28702 may include, but is not limited to, one or more sensing components 28902, one or more storage devices 28904, one or more power sources 28906, one or more communication devices 28908, and a processing device 28910. In an embodiment, the processing device 28910 may execute an edge reporting module 28912.

The sensor 28702 includes at least one sensing component 28902. The sensing component 28902 may be any digital, analog, chemical, and/or mechanical component that outputs raw sensor data to the processing unit 28910. It is understood that different types of sensors 28702 are manufactured with different types of sensing components. In embodiments, the sensing component 28902 of an inertial sensor may include one or more accelerometers and/or one or more gyroscopes. In embodiments, the sensing component 28902 of a temperature sensor may include one or more thermistors or other temperature sensing mechanisms. In embodiments, the sensing component 28902 of a heat flux sensor may include, for example, a thin film sensor, a surface mount sensor, a polymer-based sensor, a chemical sensor, etc. In embodiments, the sensing component 28902 of a motion sensor may include a LIDAR device, a radar device, a sonar device, etc. In embodiments, the sensing component 28902 of an occupancy sensor may include a surface monitored for occupancy, a pressure-activated switch embedded under the surface of the occupancy sensor, and/or a piezoelectric element integrated into the surface of the occupancy sensor, such that an electrical signal is generated when an object occupies the surface monitored for occupancy. In embodiments, the sensing component 28902 of a humidity sensor may include a capacitive element (e.g., a metal oxide between electrodes) that outputs a capacitance value corresponding to ambient humidity, a resistive element including a salt medium with electrodes on two sides of the medium whereby a variable resistance measured by the electrodes corresponds to ambient humidity, and/or a thermal element including a first thermal sensor that outputs the temperature of a dry medium (e.g., dry nitrogen). The thermal element may include a first thermal sensor that outputs the temperature of the dry medium (e.g., dry nitrogen) and a second thermal sensor that outputs the ambient temperature of the sensor's environment, such that humidity is determined based on the change (delta) between the temperature of the dry medium and the ambient temperature. In embodiments, the sensing component 28902 of a vibration sensor may include an accelerometer component, a position-sensing component, a torque-sensing component, etc. It is understood that the list of sensor types and their sensing components is provided by way of example. Additional or alternative types of sensors and sensing components may be integrated into the sensor 28702 without departing from the scope of the present disclosure. Furthermore, in some embodiments, the sensor 28702 of the sensor kit 28700 may include audio, visual, or audio/visual sensors in addition to non-audio/visual sensors 28702 (i.e., sensors that do not capture video or audio). In these embodiments, the sensing component 28992 may include a camera and/or one or more microphones. In some embodiments, the microphones may be directional microphones such that the direction of the source of the audio can be determined.

The storage device 28904 may be any suitable medium for storing data to be transmitted to the edge device 28704. In embodiments, the storage device 28904 may be a persistent storage medium, such as a flash memory device. In embodiments, the storage device 28904 may be a transient storage medium, such as a random access memory device. In embodiments, the storage device 28904 may be a circuit configured to store a charge, whereby the magnitude of the charge stored by the component indicates a sensed value, or an incremental count. In these embodiments, this type of storage device 28904 may be used when power availability and size are concerns and/or when the sensor data is count-based (e.g., number of detected events). It is understood that any other suitable storage device 28904 may be used. In embodiments, the storage device 28904 may include a cache 28914, which is adapted to store sensor data that has not yet been reported to the edge device 28704. In these embodiments, the edge reporting module 28912 may clear the cache 28914 after the sensor data stored in the cache 28914 has been transmitted to the edge device 28704.

The power source 28906 is any suitable component that provides power to the other components of the sensor 28902, including the sensing component 28902, the storage device 28904, the communication device 28906, and/or the processing device 28908. In embodiments, the power source 28906 includes a wired connection to an external power source (e.g., alternating current from a power outlet or direct current from a battery or solar power source). In embodiments, the power source 28906 may include a power inverter that converts alternating current to direct current (or vice versa). In embodiments, the power source 28906 may include an integrated power source, such as a rechargeable lithium-ion battery or a solar element. In embodiments, the power source 28906 may include a self-generating element, such as a piezoelectric element. In these embodiments, the piezoelectric element may output a voltage when sufficient mechanical stress or force is applied to the element. This voltage may be stored in a capacitor or may power the sensing element 28902. In embodiments, the power source may include an antenna (e.g., a receiver or transceiver) that receives radio frequencies that energize the sensor 28702. In these embodiments, the radio frequencies may "wake up" the sensor 28702 and trigger an action by the sensor 28702, such as taking a sensor measurement and/or reporting sensor data to the edge device 28704. The power source 28906 may include additional or alternative components as well.

In embodiments, the communication device 28908 is a device that enables wired or wireless communication with another device in the sensor kit network 28800. In most sensor kit configurations 28700, the sensor 28702 is configured to communicate wirelessly. In these embodiments, the communication device 28908 may include a transmitter or transceiver that transmits data to other devices in the sensor kit network 28800. Additionally, in some of these embodiments, the communication device 28908 having a transceiver may receive data from other devices in the sensor kit network 28800. In wireless embodiments, the transceiver may be integrated into a chip configured to perform communications using the respective communication protocol. In some embodiments, the communication device 28908 is a ZigBee® microchip, a Digi XBee® microchip, a Bluetooth® microchip, a Bluetooth Low Energy microchip, a Wi-Fi microchip, or any other suitable short-range communication microchip. In embodiments in which the sensor kit 200 supports mesh networking, the communication device 28908 may be a microchip implementing a communication protocol that supports mesh networking (e.g., ZigBee PRO mesh networking protocol, Bluetooth®, Mesh, 802.IIA/B/g/n/AC, etc.). In these embodiments, the communication device 28908 may be configured to establish a mesh network and handle routing of data packets received from other devices according to the communication protocol implemented by the communication device 28908. In some embodiments, the sensor 28702 may be configured with two or more communication devices 28908. In these embodiments, the sensors 28702 may be added to different sensor kit 28700 configurations and/or allow for flexible configuration of the sensor kit 28702 depending on the industry setting 28720.

In an embodiment, the processing device 28910 may be a microprocessor. The microprocessor may include memory (e.g., read-only memory (ROM)) that stores computer-executable instructions and one or more processors that execute the computer-executable instructions. In an embodiment, the processing device 28910 executes an edge reporting module 28912. In an embodiment, the edge reporting module 28912 is configured to transmit data to the edge device 28704. Depending on the configuration of the sensor kit network 28800 and the location of the sensor 28702 relative to the edge device 28704, the edge reporting module 28912 can transmit data (e.g., sensor data) directly to the edge device 28704 or to an intermediate device (e.g., a collection device 206 or another sensor device 28702) that routes the data toward the edge device 28704. In an embodiment, the edge reporting module 28912 obtains raw sensor data from the sensing component 28902 or from the storage device 28904 and packetizes the raw sensor data into report packets 28920.

Figure 289B illustrates an exemplary report packet 28920 according to some embodiments of the present disclosure. In some of these embodiments, the edge reporting module 28912 may populate a report packet template to obtain the report packet 28920. In an embodiment, the report packet 28920 may include a first field 28922 indicating a sensor ID of the sensor 28702 and a second field 28926 indicating sensor data. Additionally, the report packet 28920 may include a routing data field 28924 indicating the packet's destination (e.g., the address or identifier of the edge device 28704), a timestamp field 28928 indicating a timestamp, and/or additional fields such as: a checksum field 28930 indicating a checksum (e.g., a hash value of the contents of the report packet). The report packet may include additional or alternative fields (e.g., an error code) without departing from the scope of the present disclosure.

Returning to FIG. 142, in an embodiment, edge reporting module 28912 may generate a report packet 28920 for each instance of sensor data. Alternatively, edge reporting module 28912 may generate a report packet 28920 that includes a batch of sensor data (e.g., the previous N sensor readings, or all sensor readings held in cache 28914 for sensor 28702 since cache 28914 was last purged). Upon generating report packet 28920, edge reporting module 28912 may output report packet 28920 to communication device 28908, which transmits report packet 28920 to edge device 28704 (either directly or via one or more intermediate devices). The edge reporting module 28912 may generate and transmit reporting packets 28920 at predetermined intervals (e.g., every second, every minute, every hour), continuously, or when triggered (e.g., when activated via a power source or when commanded by the edge device 28704).

In an embodiment, the edge reporting module 28912 instructs the sensing component(s) 28902 to capture sensor data. In an embodiment, the edge reporting module 28912 may instruct the sensing component 28902 to capture sensor data at predetermined intervals. For example, the edge reporting module 28912 may instruct the sensing component 28902 to capture sensor data every second, every minute, or every hour. In an embodiment, the edge reporting module 28912 may instruct the sensing component 28902 to capture sensor data when the power source 28906 is energized. For example, the power source 28906 may be energized by radio frequency or when a pressure switch is activated to close a circuit. In an embodiment, the edge reporting module 28912 may instruct the sensing component 28902 to capture sensor data in response to receiving a command to report sensor data from the edge device 28704 or a human user (e.g., in response to the user pressing a button).

In an embodiment, the sensor 28702 includes a housing (not shown). The sensor housing may have any suitable form factor. In embodiments in which the sensor 28702 is used outdoors, the sensor may have a housing that is waterproof and/or resistant to extreme cold and/or heat. In an embodiment, the housing may have a suitable coupling mechanism for removably coupling to an industrial component.

The above is one example of sensor 28702. Sensor 28702 may have additional or alternative components without departing from the scope of this disclosure.

Figure 290 illustrates an example of an edge device 28704. In an embodiment, edge device 28704 may include a storage system 29002, a communication system 29004, and a processing system 29006. Edge device 28704 may also include additional components not shown, such as a power source, a user interface, etc.

Storage system 29002 includes one or more storage devices. The storage may include persistent storage media (e.g., flash memory drive, hard disk drive) and/or transient storage (e.g., RAM). Storage system 29002 may store one or more data stores. The data stores may include one or more databases, tables, indexes, records, file systems, folders, and/or files. In the illustrated embodiment, the storage stores a configuration data store 29010, a sensor data store 29012, and a model data store 29014. Storage system 29002 may store additional or alternative data stores without departing from the scope of this disclosure.

In embodiments, the configuration data store 29010 stores data related to the configuration of the sensor kit 28700, including the devices in the sensor kit 28700. In some embodiments, the configuration data store 29010 may maintain a set of device records. The device record may indicate a device identifier that uniquely identifies a device in the sensor kit 28700. The device record may also indicate the type of device (e.g., sensor, collection device, gateway device, etc.). In embodiments in which the network path from each device to the edge device 28704 does not change, the device record may also indicate the device's network path to the edge device 28704 (e.g., any intermediate devices in the device's network path). In addition, if the device record corresponds to a sensor 28702, the device record may also indicate the type of sensor (e.g., a sensor type identifier) and/or the type of data provided by the sensor 28702.

In an embodiment, the configuration data store 29010 may maintain a set of sensor type records, each record corresponding to a different type of sensor 28702 in the sensor kit 28700. The sensor type record may indicate a type identifier that identifies the type of sensor and/or the type of sensor data provided by the sensor. In an embodiment, the sensor type record may further indicate associated information related to the sensor data, including maximum or minimum values of the sensor data, error codes output by sensors 28702 of the sensor type, etc.

In embodiments, the configuration data store 29010 may maintain a map of the sensor kit network 200. The map of the sensor kit network 200 may show the network topology of the sensor kit network 200, including the network paths of the collection of devices in the sensor kit 28700. In some embodiments, the map may also include the physical locations of the sensors. The physical location of a sensor 28702 may be defined as the room or area in which the sensor 28702 is located, the particular industrial component that the sensor 28702 is monitoring, a set of coordinates relative to the edge device 28704 (e.g., x, y, z coordinates relative to the edge device 28704, or the angle and distance of the sensor 28702 relative to the edge device 28704), the estimated longitude and latitude of the sensor 28702, or any other suitable format of relative or absolute position determination and/or measurement.

In embodiments, the sensor data store 29012 stores sensor data collected from the sensors 28702 of the sensor kit 28700. In embodiments, the sensor data store 29012 maintains the collected sensor data over a period of time. In some of these embodiments, the sensor data store 29012 may be a cache that stores the sensor data until it is reported and backed up in the backend system 28750. In these embodiments, the cache may clear once the sensor data is reported to the backend system 28750. In some embodiments, the sensor data store 29012 stores all sensor data collected by the sensor kit 29012. In these embodiments, the sensor data store 29012 may provide a backup of all sensor data collected by the sensor kit 28700 over time, thereby ensuring that the owner of the sensor kit 28700 maintains ownership of that data.

In embodiments, the model data store 29014 stores machine-learned models. The machine-learned models may include any suitable type of model, including neural networks, deep neural networks, recurrent neural networks, Bayesian neural networks, regression-based models, decision trees, prediction trees, classification trees, hidden Markov models, and/or any other suitable type of model. The machine-learned models may be trained with training data that is expert-generated data, historical data, and/or outcome-based data. Outcome-based data may be data collected after a prediction or classification has been made and indicates whether the prediction or classification was correct or incorrect and the results achieved. A training data instance may refer to a unit of training data that includes a set of features and a label. In embodiments, the label of a training data instance may indicate the state of an industrial component or industrial setting 28720 at a given time. Example conditions vary widely depending on the industrial setting 28720 and the conditions the machine-learned model is trained to predict or classify. Examples of labels in a manufacturing facility include, but are not limited to, no problem detected, mechanical failure of a component, electrical failure of a component, chemical leak detected, etc. Examples of labels in a mining facility include, but are not limited to, no problem detected, oxygen deficiency, presence of toxic gas, structural component failure, etc. Examples of labels in an oil and gas facility (e.g., oil field, gas well, oil refinery, pipeline) include, but are not limited to, no problem detected, mechanical component failure (e.g., failed valve or failed O-ring), leak, etc. Examples of labels in an indoor farming facility include, but are not limited to, no problem detected, plant withered, plant wilted, plant turned a particular color (e.g., brown, purple, orange, or yellow), mold found, etc. In these examples, there are certain features that may be relevant to the condition and some features that may have little to do with the condition. Through a machine learning process (which may be performed in the backend system 28750 or another system), a model is trained to determine a prediction or classification based on a set of features. Thus, the set of features for the training data instances may include sensor data that is temporally proximate to the time at which a condition of the industrial component or industrial setting 28720 occurred (e.g., a label associated with the industrial component or industrial setting 28720).

In embodiments, the machine-learned model may include a predictive model used to predict potential problems associated with an industrial component being monitored. In some of these embodiments, the machine-learned model may be trained with training data (expert-generated data and/or historical data) corresponding to one or more conditions associated with a particular component. In some of these embodiments, the training data set may include sensor data corresponding to scenarios in which maintenance or some other intervention was subsequently required and sensor data corresponding to scenarios in which maintenance or some other intervention ultimately was not required. In these example embodiments, the machine-learned model may be used to determine a prediction of one or more potential problems that may occur with one or more industrial components being monitored and/or the industrial setting 28720 being monitored.

In embodiments, the machine-learned model may include a classification model that classifies the condition of the industrial component and/or industrial setting 28720 being monitored. In some of these embodiments, the machine-learned model may be trained with: training data (e.g., expert-generated data and/or historical data) corresponding to one or more conditions associated with a particular component. In some of these embodiments, the training data set may include sensor data corresponding to scenarios in which the respective industrial component and/or respective industrial setting 28720 was operating in a normal condition and sensor data in which the respective industrial component and/or respective industrial setting 28720 was operating in an abnormal condition. In training data instances in which an abnormal condition was present, the training data instance may include a label indicating the type of abnormal condition. For example, a training data instance corresponding to an indoor agriculture facility determined to be too humid for ideal growing conditions may include a label indicating that the facility was too humid.

In an embodiment, the communication system 29004 includes two or more communication devices, including at least one internal communication device that communicates with the sensor kit network 200 and at least one external communication device that communicates with a public communication network (e.g., the Internet) directly or through a gateway device. The at least one internal communication device may include a Bluetooth® chip, a ZigBee chip, an XBee chip, a Wi-Fi chip, etc. The selection of the internal communication device may depend on the environment of the industrial setting 28720 and its impact on the sensors 28702 installed therein (e.g., whether the sensors 28702 have a reliable power source, whether the sensors 28702 are spaced closely together, whether the sensors 28702 need to transmit through walls, etc.). The external communication device may provide wired or wireless communication. In an embodiment, the external communication device may include a cellular chipset (e.g., a 4G or 5G chipset), an Ethernet card, a satellite communication card, or other suitable communication device. The external communication device(s) of edge device 28704 may be selected based on the environment of the industrial setting 28720 (e.g., indoors vs. outdoors, thick walls that prevent wireless communication vs. thin walls that allow wireless communication, located near a cell phone tower vs. located in a remote location) and/or the preferences of the operator of the industrial setting 28720 (e.g., whether the operator has allowed edge device 28704 to access the private network of the industrial setting 28720 or whether the operator has not allowed edge device 28704 to access the private network of the industrial setting 28720).

In an embodiment, processing system 29006 includes one or more memory devices (e.g., ROM and/or RAM) that store computer-executable instructions and multiple processors that execute one or more computer-executable instructions. Processing system 29006 may execute one or more of data processing module 29020, encoding module 29022, instant decision AI module 29024, notification module 29026, configuration module 29028, and distributed ledger module 29030. Processing system 29006 may execute additional or alternative modules without departing from the scope of this disclosure. Additionally, modules described herein may include sub-modules that perform one or more functions of the respective module.

In embodiments, the data processing module 29020 receives sensor data from the sensor kit network 200 and performs one or more data processing operations on the received sensor data. In embodiments, the data processing module 29020 receives report packets 320 containing sensor data. In some of these embodiments, the data processing module 29020 may filter duplicate data records (e.g., filtering one of two report packets 320 received from two respective sensors monitoring the same component for redundancy). The data processing module 29020 may additionally or alternatively filter and/or flag report packets 320 containing clearly erroneous sensor data (e.g., a sensor whose sensor 28702 type is not within a given tolerance range or a sensor containing an error code). In embodiments, the data processing module 29020 may store and/or index the sensor data in a sensor data store.

In embodiments, the data processing module 29020 may aggregate sensor data received from the sensors 28702 of the sensor kit 28700, or a subset thereof, over a period of time and transmit the sensor data to the backend system 28750. When transmitting the sensor data to the backend system 28750, the data processing module 29020 may generate a sensor kit report packet including one or more instances of the sensor data. The sensor data in the sensor kit report packet may be compressed or uncompressed. In embodiments, the sensor kit report packet may indicate a sensor kit identifier that identifies the source of the data packet to the backend system 28750. In embodiments, the data processing module 29020 may transmit the sensor data upon receiving sensor data from the sensors 28702, at a predetermined interval (e.g., every second, every minute, every hour, every day), or in response to a trigger condition (e.g., a prediction or classification that there is a problem with the industrial component or industrial setting 28720 based on the received sensor data). In some embodiments, sensor data may be encoded/compressed to allow for more efficient transmission of sensor data collected from multiple sensors 28702 and/or over a period of time. In embodiments, the data processing module 29020 may utilize a rapid decision AI module 29024 to determine whether an industrial component of the industrial setting 28720 and/or the industrial setting 28720 itself is likely in a healthy state. If the rapid decision AI module 29024 determines that the industrial component and/or industrial setting 28720 is in a healthy state with a high degree of certainty, the data processing module 29020 may delay or forgo transmitting the sensor data used to perform the classification to the backend system 28750. Additionally or alternatively, if the rapid decision AI module 29024 determines that the industrial component and/or industrial setting 28720 is in a healthy state with a high degree of certainty, the data processing module 29020 may compress the sensor data, or may compress it at a greater rate. Data processing module 29020 may perform additional or alternative functions without departing from the scope of this disclosure.

In embodiments, the encoding module 29022 may receive the sensor data and encode, compress, and/or encrypt the sensor data. The encoding module 29022 may employ other techniques to compress the sensor data. In embodiments, the encoding module 29022 may employ horizontal or compression techniques to compress the sensor data. For example, the encoding module 29022 may use the Lempel-Zev-WelCh algorithm or variations thereof. In some embodiments, the encoding module 29022 may represent the sensor data in its original integer or "count form" and with associated calibration coefficients and offsets at the time of collection. In these embodiments, the coefficients and offsets may be combined at the time of collection when the exact signal path is known, such that one floating-point coefficient and one integer offset are stored for each channel.

In embodiments, the encoding module 29022 may employ one or more codecs to compress the sensor data. The codecs may be proprietary and/or publicly available codecs. In some embodiments, the encoding module 29022 may compress the sensor data using a media compression codec (e.g., a video compression codec). For example, the encoding module 29022 may normalize the sensor data to values that fall within the range and format of a media frame (e.g., normalize the sensor data to acceptable pixel values for inclusion in a video frame) and embed the normalized sensor data in the media frame. The encoding module 29022 may embed the normalized sensor data collected from the sensors 28702 of the sensor kit 28700 into the media frame according to a predefined mapping (e.g., a mapping of each sensor 28702 to one or more respective pixels in the media frame). The encoding module 29022 may generate a set of contiguous media. In this manner, the media frames may be compressed using a media codec (e.g., H.264/MPEG-4 codec, H.265/MPEG-H codec, H.263/MPEG-4 codec, proprietary codec, etc.) to obtain a sensor data encoding. The encoding module 29022 then sends the sensor data encoding to a backend system, which may decompress and recalculate the sensor data based on the normalized values. In these embodiments, the codec used for compression and the mapping of sensors to pixels may be selected to reduce lossiness or increase compression ratios. Furthermore, the aforementioned techniques may be applied to sensor data that tends to be more static and change less between samples, and/or where sensor data collected from different sensors tends to change less when sampled simultaneously. The encoding module 29022 may employ additional or alternative encoding/compression techniques without departing from the scope of this disclosure.

In embodiments, the rapid decision AI module 29024 may utilize a limited set of machine-learned models to generate a prediction and/or classification of the condition of the monitored industrial component and/or the condition of the monitored industrial setting 28720. In embodiments, the rapid decision AI module 29024 may receive a set of features (e.g., one or more sensor data values) and request a particular type of prediction or classification based thereon. In embodiments, the rapid decision AI module 29024 may utilize a machine-learned model corresponding to the requested prediction or classification. The rapid decision AI module 29024 may generate a feature vector based on the received features, where the feature vector includes one or more sensor data values obtained from one or more sensors 28702 of the sensor kit 28700. The rapid decision AI module 29024 may feed the feature vector to the machine-learned model. The machine-learned model may output a prediction or classification and a confidence level for the prediction or classification. In embodiments, the prompt decision AI module 29024 may output the prediction or classification to the data processing module 29020 (or another module that requested the prediction or classification). For example, in embodiments, the data processing module 29020 may use the classification that the industrial component and/or industrial setting 28720 is healthy to delay or postpone transmission of sensor data and/or compress the sensor data. In embodiments, the data processing module 29020 may use the prediction or classification that the industrial component and/or industrial setting 28720 is likely to experience a failure to send uncompressed sensor data to the backend system 28750, which may further analyze the sensor data and/or notify a human user of the potential problem.

In embodiments, the notification module 29026 may provide a notification or alarm to a user based on the sensor data. In some of these embodiments, the notification module 29026 may apply a set of rules that trigger a notification or alarm when certain conditions are met. The conditions may define sensor data values that are highly correlated with an undesirable (e.g., emergency) condition. Upon receiving sensor data from the data processing module 29020, the notification module 29026 may apply one or more rules to the sensor data. If the conditions for triggering an alarm or notification are met, the notification module 29026 may issue an alarm or notification to a human user. The manner in which the alarm or notification is provided to a human user (e.g., provided to a user device or triggering an audible alarm) may be predefined or, in some embodiments, defined by an operator of the industrial configuration 28720.

In embodiments, the configuration module 29028 configures the sensor kit network 200. In embodiments, the configuration module 29028 may send configuration requests to other devices in the sensor kit 28700 depending on the sensors 28702, edge devices 28704, and any other devices installed in the industrial setting 28720. In some of these embodiments, the sensors 28702 and/or other devices may establish a mesh network or a hierarchical network in response to the configuration request. In embodiments, the sensors 28702 and other devices in the sensor kit network may respond to the configuration request. In embodiments, the configuration module 29028 may generate device records corresponding to the responding devices based on the device IDs of those devices and any additional data provided in the response to the configuration request.

In embodiments, the configuration module 29028 adds new devices to the sensor kit 28700. In these embodiments, the configuration module 29028 adds new sensors 28702 to the sensor kit 28700 after installation in a plug-and-play-like manner. In some of these embodiments, the communication devices 29004, 308 of the edge device 28704 and the sensor 28702 (or other devices being added to the sensor kit 28700) may each include short-range communication capabilities (e.g., a near-field communication (NFC) chip). In these embodiments, the sensor 28702 may include persistent storage to store identification data (e.g., a sensor ID value) and other data (e.g., device type, supported communication protocols, etc.) that will be used to add the sensor to the sensor kit. In response to a user initiating a post-installation addition to the sensor kit 28700 (e.g., the user pressing a button on the edge device 28704 and/or bringing a sensor 28702 into proximity with the edge device 28704), the configuration module 29028 may cause the communication system 29004 to emit a signal (e.g., radio frequency). The emitted signal may trigger sensors 28702 that are close enough to receive the signal to transmit their sensor ID and any other appropriate configuration data (e.g., device type, communication protocol, etc.). In response to the sensor 28702 transmitting its configuration data (sensor ID and other associated configuration data) to the edge device 28704, the configuration module 29028 may add the new sensor 28702 to the sensor kit 28702. In embodiments, adding the sensor 28702 to the sensor kit 28704 may include generating a new device record corresponding to the new sensor 28702 based on the sensor ID and updating the configuration data store 29010 with the new device record. The configuration module 29028 may add the new sensor 28702 to the sensor kit 28700 in any other suitable manner.

In an embodiment, edge device 28704 may include a distributed ledger module 29030. In an embodiment, distributed ledger module 29030 may be configured to update distributed ledger 28762 with sensor data captured by sensor kit 28700. In an embodiment, the distributed ledger may be distributed among multiple node computing devices 28760. As described, in an embodiment, distributed ledger 28762 is comprised of a set of linked data structures (e.g., blocks, data records, etc.). For ease of description, the data structures will be referred to as blocks.

As described, each block may include a header containing the block's unique ID and a body containing the data stored in the block and a pointer to the parent block. In embodiments, the block pointer is the block ID of the block's parent block. The data stored in each block may be sensor data captured by the respective sensor kit 28700. In some embodiments, the types and amounts of sensor data stored in each body of a block may vary. For example, a block may store a set of sensor measurements from one or more types of sensors 28702 in the sensor kit 28700 captured over a period of time (e.g., sensor data 28702 captured from all sensors 28702 in the sensor kit 28700 over a period of one hour or one day) and associated metadata (e.g., the sensor ID for each sensor measurement and the timestamp for each sensor measurement or group of sensor measurements). In some embodiments, a block may store sensor measurements determined to be anomalous (e.g., outside the standard deviation of expected sensor measurements, or where the delta of the sensor measurements is: A block may include sensor readings that exceed thresholds and/or indicate a problem or potential problem, and associated metadata (e.g., a sensor ID for each sensor reading and a timestamp for each sensor reading or group of sensor readings). In some embodiments, the sensor data stored in the block may be compressed and/or encoded, such that the encoding module 29022 compresses/encodes the sensor data into a more compact format. In embodiments, the distributed ledger module 29030 may generate a hash of the body such that the contents of the body (e.g., the block ID and sensor data of the parent block) are hashed and cannot be changed without changing the value of the hash. In embodiments, the distributed ledger module 29030 may encrypt the content within the block to prevent the content from being read by unauthorized devices.

In embodiments, the distributed ledger module 29030 generates blocks in response to a trigger event. Examples of trigger events may include at predetermined times (e.g., every minute, hour, daily), when a potential problem is classified or predicted, when one or more sensor readings are outside of tolerance thresholds, etc. In response to a trigger event, the distributed ledger module 29030 may generate a block based on the sensor data to be reported. Depending on the configuration of the server kit 28700 and the intended use of the distributed ledger 28762, the amount and type of data contained in the block may vary. For example, in a manufacturing or resource mining setting, such as a manufacturing facility 1700 or an underwater industrial setting 1800, the distributed ledger 28762 may be used to demonstrate functional machinery and/or predict maintenance needs. In this example, the distributed ledger module 29030 may be accessed by an insurance carrier to set insurance premiums and/or issue refunds. Thus, in this example, the distributed ledger module 29030 may include any sensor readings (and associated metadata) that fall outside of tolerance thresholds or instances where a problem is classified or predicted. In another example, the distributed ledger may be accessible by a regulatory agency to ensure that the facility is operating in accordance with one or more regulations. In these embodiments, the distributed ledger module 29030 may store a set of one or more sensor readings (and associated metadata) in a block so that the sensor readings can be analyzed by the regulatory agency. In some of these embodiments, the sensor readings may be compressed to store more sensor data in a single block. In response to generating the block, the distributed ledger module 29030 may transmit the block to one or more node computing devices 28760. Once the block is validated (e.g., using a consensus mechanism), each node computing device 28760 may update the distributed ledger 28762 with the new block.

As discussed, in some embodiments, the distributed ledger may further include a smart contract. Once written, the smart contract may be encoded into a block and deployed to the distributed ledger 28762. The address of the smart contract (e.g., the block ID of the block containing the smart contract) may be provided to one or more parties to the smart contract, and each party may invoke the smart contract using the address. In some of these embodiments, the address of the smart contract may be provided to the distributed ledger module 29030, such that the distributed ledger module 29030 reports items to the smart contract. In some embodiments, the distributed ledger module 29030 may leverage the smart contract's API to report items to the smart contract.

In the example implementation described above, an insurance company may utilize a smart contract to allow owners and/or operators of insured facilities to demonstrate that equipment within the facility is functioning properly. In some embodiments, the smart contract may trigger the issuance of a rebate or refund on a portion of insurance premiums if the facility owner and/or operator provides sufficient sensor data indicating the facility is operating without problems. In some of these embodiments, the smart contract may include a first condition requiring a certain amount of sensor data to be reported from the facility and a second condition that each instance of the sensor data equals a value (e.g., no classified or predicted problems) or a range of values (e.g., all sensor readings within a predefined range of values). In some embodiments, the action may be to deposit funds (e.g., a wire transfer or cryptocurrency) into an account in response to the first and second conditions being met. In this example, distributed ledger module 29030 may write a block including the sensor data to distributed ledger 28762. The distributed ledger module 29030 may also provide the addresses of these blocks to the smart contract (e.g., via the smart contract's API). Once the smart contract verifies the first and second conditions of the agreement, the smart contract may initiate the transfer of funds from the insurer's account to the insured's account.

In another example described above, a regulatory agency (e.g., a state, local, or federal regulatory agency) may utilize a smart contract to monitor facilities (e.g., food inspection facilities, pharmaceutical manufacturing facilities, indoor agriculture facilities, offshore oil drilling facilities, etc.) based on reported sensor data to ensure compliance with one or more regulations. In embodiments, the smart contract may be configured to: receive and validate sensor data from the facility (e.g., via the smart contract's API); and, in response to validating the sensor data, issue a compliance token (or certificate) to the facility owner's account. In some of these embodiments, the smart contract may include a first condition requiring a certain amount of sensor data to be reported from the facility and a second condition requiring the sensor data to comply with reporting regulations. In this example, the distributed ledger module 29030 may write blocks containing the sensor data to the distributed ledger. The sensor kit 28700 may also provide addresses of these blocks to the smart contract (e.g., using the smart contract's API). Once the smart contract verifies the first and second terms of the agreement, the smart contract may generate a token indicating compliance by the facility operator and initiate the transfer of funds to an account (e.g., a digital wallet) associated with the facility.

Figure 291 illustrates an exemplary backend system 28750 according to some embodiments of the present disclosure. In embodiments, backend system 28750 may be implemented as a cloud service running on one or more physical server devices. In embodiments, backend system 28750 may include a storage system 29102, a communication system 29104, and a processing system 29106. Backend system 28750 may include additional components not shown.

Storage system 29102 includes one or more storage devices. The storage may include persistent storage media (e.g., flash memory drive, hard disk drive) and/or transient storage (e.g., RAM). Storage system 29102 may store one or more data stores. The data stores may include one or more databases, tables, indexes, records, file systems, folders, and/or files. In the illustrated embodiment, storage system 29102 stores sensor kit data store 29110 and model data store 29112. Storage system 29102 may store additional or alternative data stores without departing from the scope of this disclosure.

In embodiments, the sensor kit data store 29110 stores data associated with each sensor kit 28700. In embodiments, the sensor kit data store 29110 may store sensor kit data corresponding to each installed sensor kit 28700. In embodiments, the sensor kit data may indicate the devices in the sensor kit 28700, including each sensor 28702 (e.g., a sensor ID) in the sensor kit 28700. In some embodiments, the sensor kit data may indicate sensor data captured by the sensor kit 28700. In some of these embodiments, the sensor kit data may identify each instance of sensor data captured by the sensor kit 28700, and for each instance of sensor data, the sensor kit data may indicate the sensor 28702 that captured the sensor data, and in some embodiments, a timestamp corresponding to the sensor data.

In embodiments, the model data store 29112 stores machine-learned models trained by the AI system 29124 based on the training data. The machine-learned models may include predictive models and classification models. In embodiments, the training data used to train a particular model includes data collected from one or more sensor kits 28700 monitoring the same type of industrial environment 28720. The training data may additionally or alternatively include historical data and/or expert-generated data. In embodiments, each machine-learned model may be associated with a respective type of industrial setting 28720. In some of these embodiments, the AI system 29124 may periodically update the machine-learned models for a type of industrial setting 28720 based on the sensor data collected from and results obtained from the sensor kits 28700 monitoring those types of industrial settings 28720. In embodiments, the machine-learned models for a type of industrial setting 28720 may be provided to the edge devices 28704 of the sensor kits 28700 monitoring that type of industrial setting 28720.

In an embodiment, the communication system 29104 includes one or more communication devices, including at least one external communication device that communicates with a public communication network (e.g., the Internet). The external communication device may communicate via wired or wireless communication. In an embodiment, the external communication device may include a cellular chipset (e.g., a 4G or 5G chipset), an Ethernet card and/or a Wi-Fi card, or other suitable communication device.

In embodiments, the processing system 29106 may include one or more memory devices (e.g., ROM and/or RAM) that store computer-executable instructions and one or more processors that execute the computer-executable instructions. The processors may execute in a parallel or distributed manner. The processors may be located on the same physical server device or on different server devices. The processing system 29106 may execute one or more of the decoding module 29120, data processing module 29122, AI module 29124, notification module 29126, analysis module 29128, control module 29130, dashboard module 29132, configuration module 29134, and distributed ledger management module 29136. The processing system 406 may execute additional or alternative modules without departing from the scope of this disclosure. Furthermore, the modules described herein may include sub-modules that perform one or more functions of the respective module.

In embodiments, the sensor kit 28700 may transmit an encoded sensor kit packet containing sensor data to the backend system 28750. In these embodiments, the decoding module 29120 may receive the encoded sensor data from the edge device 28704 and may decode, decode, and/or decompress the encoded sensor kit packet to obtain the sensor data and metadata associated with the received sensor data (e.g., the sensor kit ID and one or more sensor IDs for the sensors that captured the sensor data). The decoding module 29120 may output the sensor data and other metadata to the data processing module 29122.

In embodiments, the data processing module 29122 may process sensor data received from the sensor kit 28700. In some embodiments, the data processing module 29122 may receive the sensor data and store the sensor data in the sensor kit data store 29110 in association with the sensor kit 28700 that provided the sensor data. In embodiments, the data processing system 29122 may provide AI-related requests to the AI module 29124. In these embodiments, the data processing system 29122 may extract relevant sensor data instances from the received sensor data and provide the extracted sensor data instances to the AI module 29124 in a request indicating the type of request (e.g., what type of prediction or classification) and the sensor data to use. If a potential problem is predicted or classified, the data processing module 29122 may execute a workflow associated with the potential problem. The workflow may define how the potential problem is to be handled. For example, the workflow may indicate that a notification should be sent to a human user, that corrective action should be initiated, and/or other appropriate action. Data processing module 29122 may perform additional or alternative processing tasks without departing from the scope of this disclosure.

In embodiments, the AI module 29124 trains a machine-learned model used to make the prediction or classification. The machine-learned model may include any suitable type of model, including a neural network, a deep neural network, a recurrent neural network, a Bayesian neural network, a regression-based model, a decision tree, a prediction tree, a classification tree, a hidden Markov model, and/or any other suitable type of model. The AI module 29124 may train the machine-learned model with a training dataset. The training dataset may include expert-generated data, historical data, and/or outcome-based data. Outcome-based data may be data collected after a prediction or classification has been made and may indicate whether the prediction or classification was correct or incorrect and/or the results achieved. A training data instance may refer to a unit of training data that includes a set of features and a label. In embodiments, the label of a training data instance may indicate the state of the industrial component or industrial setting 28720 at a given time. Example conditions vary greatly depending on the industrial setting 28720 and the condition the machine learning model is trained to predict or classify. Example labels in a manufacturing facility include, but are not limited to, no problem detected, mechanical failure of a component, electrical failure of a component, chemical leak detected, etc. Example labels in a mining facility include, but are not limited to, no problem detected, oxygen deficiency, presence of toxic gas, structural component failure, etc. Example labels in an oil and gas facility (e.g., oil field, gas well, oil refinery, pipeline) include, but are not limited to, no problem detected, mechanical component failure (e.g., failed valve or failed O-ring), leak, etc. Example labels in an indoor farming facility include, but are not limited to, no problem detected, plants withered, plants wilted, plants turned a particular color (e.g., brown, purple, orange, or yellow), mold was found, etc. In each of these examples, there are certain features that may be relevant to the condition and several features that may have little or no relevance to the condition. In embodiments, the AI module 29124 may enhance the machine-learned models as more sensor data and results associated with the machine-learned models are received. In embodiments, the machine-learned models may be stored in the model data store 29112. Each model may be stored with a model identifier, which may indicate (e.g., map to) the type of industrial setting 28720 the model operates in, the type of prediction or classification the model performs, and the features the model receives. In some embodiments, one or more machine-learned models (and subsequent updates) may be pushed to each sensor kit 28700, such that the edge device 28704 of each sensor kit 28700 may use one or more machine-learned models to perform predictions and/or classifications without relying on the backend system 28750.

In embodiments, AI module 29124 receives a request for prediction and/or classification and determines a prediction and/or classification based on the request. In embodiments, the request may indicate the type of prediction or classification requested and may include a set of features for making the prediction or classification. In response to the request, AI module 29124 may select a machine learning model to utilize based on the type of prediction or classification requested, such that: The selected model receives the specified set of features. AI module 29124 may then generate a feature vector including one or more instances of the sensor data and provide the feature vector to the selected model. In response to the feature vector, the selected model may output a prediction or classification and a confidence level (e.g., a confidence score) for the prediction or classification. AI module 29124 may output the prediction or classification and the confidence level therein to the module that provided the request.

In embodiments, the notification module 29126 may issue a notification to a user and/or a respective industrial setting 28720 when an issue is detected in the respective setting. In embodiments, the notification may be sent to a user device of the user indicating the nature of the issue. The notification module 29126 may implement an API (e.g., a REST API) whereby a user device of a user associated with the industrial setting 28720 may request a notification from the backend system 28750. In response to the request, the notification module 29126 may provide any notification (if any) to the user device. In embodiments, the notification may be sent to a device located in the industrial setting 28720 whereby the device may generate an alarm in the industrial setting 28720 in response to the industrial setting 28720.

In embodiments, the analytics module 29128 may perform analytics-related tasks on sensor data collected by the backend system 28750 and stored in the sensor kit data store 29110. In embodiments, analytics tasks may be performed on sensor data received from individual sensor kits. Additionally, or alternatively, analytics tasks may be performed on sensor data. Examples of analytics tasks that may be performed on sensor data obtained from various sensor kits 28700 monitoring different industrial settings 28720 include energy usage analysis, quality analysis, process optimization analysis, financial analysis, predictive analysis, yield optimization analysis, failure prediction analysis, scenario planning analysis, and many others.

In an embodiment, the control module 29130 may control one or more aspects of the industrial setting 28720 based on decisions made by the AI system 29124. In an embodiment, the control module 29130 may be configured to provide commands to devices or systems of the industrial setting 28720 to take corrective action in response to detecting a particular problem. For example, the control module 29130 may issue a command to a manufacturing facility to stop an assembly line in response to determining that a critical component on the assembly line is likely to have failed or is likely to have failed. In another example, the control module 29130 may issue a command to an agricultural facility to turn on a dehumidifier in response to determining that humidity levels in the facility are too high. In another example, the control module 29130 may issue a command to close a valve in an oil pipeline in response to determining that a component in the oil pipeline downstream of the valve is likely to have failed or is likely to have failed. For a particular industry setting 28720, the control module 29130 may execute remedial actions defined by a human user associated with the industry setting 28720, where the human user may define what conditions may trigger the remedial action.

In embodiments, the dashboard module 29132 presents a dashboard to a human user via a user device 28740 associated with the human user. In embodiments, the dashboard provides a graphical user interface through which the human user can view things related to the sensor kit 28700 with which the human user is associated (e.g., an employee of the industrial setting 28720). In these embodiments, the dashboard module 29132 may retrieve and display raw sensor data provided by the sensor kit, analytical data related to the sensor data provided by the sensor kit 28700, predictions or classifications made by the backend system 28750 based on the sensor data, etc.

In embodiments, the dashboard module 29132 allows a human user to configure aspects of the sensor kit 28700. In embodiments, the dashboard module 29132 may present a graphical user interface that allows a human user to configure one or more aspects of the associated sensor kit 28700. In embodiments, the dashboard may allow a user to configure alarm limits for one or more sensor types and/or conditions. For example, a user may define a temperature value at which a notification will be sent to a human user. In another example, a user may define a set of conditions that, if predicted by the AI module and/or edge device, will activate an alarm. In embodiments, the dashboard may allow a user to define which users receive notifications when an alarm is triggered. In embodiments, the dashboard may allow a user to subscribe to additional functionality of the backend system 28750 and/or edge device 28704.

In embodiments, the dashboard may allow a user to add one or more subscriptions to the sensor kit 28700. The subscriptions may include access to backend services and/or edge services. The user may select the services to add to the sensor kit 28700 and may provide payment information to pay for the services. Upon verification of the payment information, the backend system 28750 may provide the sensor kit 28700 with access to their functionality. Examples of services that may be subscribed to include analytics services, AI services, notification services, etc. The dashboard may allow a user to perform additional or alternative configurations.

In embodiments, the configuration module 29134 maintains the configuration of each sensor kit 28700. Initially, when a new sensor kit 28700 is deployed to the industrial environment 28720, the configuration module 29134 may update the sensor kit data store 29110 with the device ID of each device in the newly installed sensor kit 28700. Once the sensor kit data store 29110 has been updated to reflect the newly installed sensor kit 28700, the backend system 28750 may begin storing sensor data from the sensor kit 28700. In embodiments, a new sensor 28702 may be added to each sensor kit 28700. In these embodiments, the edge device 28704 may provide an add request to the backend system 28750 when attempting to add a device to the sensor kit 28700. In embodiments, the request may indicate the sensor ID of the new sensor. In response to the request, the configuration module 29134 may add the sensor ID of the new sensor to the sensor kit data for the requesting sensor kit 28700 in the sensor kit data store 29110.

In embodiments, backend system 28750 includes a distributed ledger management module 29136. In some of these embodiments, the distributed ledger management module 29136 allows a user to update and/or configure the distributed ledger. In some of these embodiments, the distributed ledger management module 29136 allows a user to define or upload smart contracts. As discussed, a smart contract may include one or more conditions to be verified by the smart contract and one or more actions to be triggered when the condition is verified. In embodiments, a user may provide one or more conditions to be verified to distributed ledger management module 29136 via a user interface. In some of these embodiments, the user may provide code (e.g., JavaScript code, Java code, C code, C++ code, etc.) that defines the condition. The user may also provide an action to be performed in response to a particular condition being met. In response to the smart contract being uploaded/created, distributed ledger management module 29136 may deploy the smart contract. In embodiments, distributed ledger management module 29136 may generate a block that includes the smart contract. The block may include a header that defines the block's address and a body that includes an address to the previous block and the smart contract. In some embodiments, distributed ledger management module 29136 may determine a hash value based on the following: Distributed ledger management module 29136 may send the block to one or more node computing devices 28760, which update the distributed ledger with the block that includes the smart contract. Distributed ledger management module 29136 may further provide the block's address to one or more parties that may access the smart contract. Distributed ledger management module 29136 may perform additional or alternative functions without departing from the scope of this disclosure.

Backend system 28750 may include additional or alternative components, data stores, and/or modules not discussed.

FIG. 292 illustrates an example of the operation of a method 29200 for compressing sensor data obtained by a sensor kit 28700. In an embodiment, the method 29200 may be performed by an edge device 28704 of the sensor kit 28700.

At 29210, edge device 28704 receives sensor data from one or more sensors 28702 of sensor kit 28700 via sensor kit network 200. In an embodiment, the sensor data from each sensor 28702 may be received in a report packet. Each report packet may include a device identifier for the sensor 28702 that generated the report packet and one or more instances of sensor data captured by the sensor 28702. The report packet may include additional data, such as a timestamp or other metadata.

In 29212, edge device 28704 processes sensor data. In embodiments, edge device 28704 may deduplicate any duplicate report packets. In embodiments, edge device 28704 may filter sensor data that is obviously erroneous (e.g., outside of an acceptable range). In embodiments, edge device 28704 may aggregate sensor data obtained from multiple sensors 28702. In embodiments, edge device 28704 may perform one or more AI-related tasks, such as determining a prediction or classification related to the condition of one or more industrial components of industrial setting 28720. In some of these embodiments, the decision to compress the sensor data may depend on whether edge device 28704 determines that there is a potential problem with the industrial component. For example, edge device 28704 may compress sensor data if no problem was predicted or classified. In other embodiments, edge device 28704 may compress any sensor data or a particular type of sensor data (e.g., sensor data obtained from a temperature sensor) being sent to a backend system.

At 29214, the edge device 28704 may compress the sensor data. The edge device 28704 may employ any suitable compression technique to compress the sensor data. For example, the edge device 28704 may employ a vertical or horizontal compression technique. The edge device 28704 may be configured with a codec to compress the sensor data. The codec may be a proprietary codec or an "off-the-shelf" codec.

At 29216, edge device 28704 may send the compressed sensor data to backend system 28750. In an embodiment, edge device 28704 may generate a sensor kit packet including the compressed data. The sensor kit packet may specify the source of the sensor kit packet (e.g., a sensor kit ID or an edge device ID) and may include additional metadata (e.g., a timestamp). In an embodiment, edge device 28704 may encrypt the sensor kit packet before sending it to backend system 28750. In an embodiment, edge device 28704 sends the sensor kit packet directly to backend system 28750 (e.g., via a cellular connection, a network connection, or a satellite uplink). In other embodiments, edge device 28704 sends the sensor kit packet to backend system 28750 via a gateway device, and the gateway device sends the sensor kit packet directly to backend system 28750 (e.g., via a cellular connection or a satellite uplink).

FIG. 293 illustrates an example of the operation of method 29300 for processing compressed sensor data received from sensor kit 28700. In an embodiment, method 29300 is performed by backend system 28750.

At 29310, the backend system 28750 receives the compressed sensor data from the sensor kit. In an embodiment, the compressed sensor data may be received in a sensor kit packet.

At 29312, backend system 28750 decompresses the received sensor data. In embodiments, the backend system may utilize a codec to decompress the received sensor data. Prior to decompressing the received sensor data, backend system 28750 may decode the sensor kit packet containing the compressed sensor data.

At 29314, backend system 28750 performs one or more backend operations on the decompressed sensor data. The backend operations may include storing the data, filtering the data, performing AI-related tasks on the sensor data, issuing one or more notifications related to the results of the AI-related tasks, performing one or more analytics-related tasks, controlling industrial components of industrial configuration 28720, etc.

FIG. 294 illustrates an example of the operation of a method 29400 for streaming sensor data from a sensor kit 28700 to a backend system 28750. In an embodiment, method 29400 may be performed by an edge device 28704 of the sensor kit 28700.

At 29410, edge device 28704 receives sensor data from one or more sensors 28702 of sensor kit 28700 via sensor kit network 28800. In embodiments, sensor data from each sensor 28702 may be received in a report packet. Each report packet may include a device identifier for the sensor 28702 that generated the report packet and one or more instances of sensor data captured by the sensor 28702. The report packet may include additional data, such as a timestamp or other metadata. In embodiments, edge device 28704 may process the sensor data. For example, edge device 28704 may deduplicate any duplicate report packets and/or filter sensor data that is obviously erroneous (e.g., outside of acceptable ranges). In embodiments, edge device 28704 may aggregate sensor data obtained from multiple sensors 28702.

At 29412, edge device 28704 may normalize and/or convert the sensor data into a media frame-compliant format. In embodiments, edge device 28704 may normalize and/or convert each sensor data instance into a value that conforms to the constraints of the media frame that will contain the sensor data. For example, in embodiments in which the media frames are video frames, edge device 28704 may normalize and/or convert the sensor data instance into an acceptable pixel frame. Edge device 28704 may employ one or more mapping and/or normalization functions to convert and/or normalize the sensor data.

At 29414, the edge device 28704 may generate blocks of media frames based on the transformed and/or normalized sensor data. For example, in embodiments where the media frames are video frames, the edge device 28704 may assign each instance of the transformed and/or normalized sensor data to a respective pixel of the video frame. The manner in which the edge device 28704 assigns an instance of the transformed and/or normalized sensor data to each pixel may be defined by a mapping that maps each sensor to a respective pixel value. In embodiments, the mapping may be defined to minimize variance between values of adjacent pixels. In embodiments, the edge device 28704 may generate a series of time-sequenced media frames, with each successive media frame corresponding to a subsequent set of sensor data instances.

At 29416, edge device 28704 may encode the block of media frames. In an embodiment, edge device 28704 may employ a media codec (e.g., a video codec) encoder to compress the block of media frames. The codec may be a proprietary codec or an "off-the-shelf" codec. For example, the media codec may be an H.264/MPEG-4 codec, an H.265/MPEG-H codec, an H.263/MPEG-4 codec, a proprietary codec, etc. The codec receives the block of media frames and generates an encoded media block based thereon.

At 29418, edge device 28704 may transmit the encoded media blocks to backend system 28750. In embodiments, edge device 28704 may stream the encoded media blocks to backend system 28750. Each encoded block may specify the source of the block (e.g., a sensor kit ID or an edge device ID) and may include additional metadata (e.g., a timestamp and/or a block identifier). In embodiments, edge device 28704 may encrypt the encoded media blocks before transmitting them to backend system 28750. Edge device 28704 may transmit the encoded media blocks directly to backend system 28750 (e.g., via a cellular connection, a network connection, or a satellite uplink) or may transmit the encoded media blocks directly to backend system 28750 (e.g., via a cellular connection or a satellite uplink) via a gateway device.

The edge device 28704 may continue to perform the method 29400 described above to deliver a stream of live sensor data from the sensor kit. The method 29400 described above may be performed in a setting where many sensors are deployed and where the sensors are sampled frequently or continuously. In this manner, the bandwidth required to provide sensor data to a backend system is reduced.

Figure 295 illustrates an example of the operation of method 29500 for capturing a sensor data stream from an edge device 28704. In an embodiment, method 29500 is performed by a backend system.

At 29510, backend system 28750 receives the encoded media blocks from the sensor kit. Backend system 28750 may receive the encoded media blocks as part of the sensor data stream.

At 29512, the backend system 28750 decodes the encoded blocks using a decoder corresponding to the codec used to encode the media blocks to obtain a set of consecutive media frames. As described with respect to the encoding operation, the codec may be a proprietary codec or an "off-the-shelf" codec. For example, the media codec may be an H.264/MPEG-4 codec, an H.265/MPEG-H codec, an H.263/MPEG-4 codec, a proprietary codec, etc. The codec receives the encoded blocks of media frames and decodes the encoded blocks to obtain a series of consecutive media frames.

At 29514, the backend system 28750 recreates the sensor data based on the media frames. In embodiments, the backend system 28750 determines normalized and/or transformed sensor values embedded in each respective media frame. For example, in embodiments where the media frames are video frames, the backend system 28750 may determine a pixel value for each pixel in the media frame. The pixel value may correspond to each sensor 28702 of the sensor kit 28700, and the value may represent a normalized and/or transformed instance of the sensor data. In embodiments, the backend system 28750 may recreate the sensor data by reversing the normalization and/or transformation of the pixel values. In embodiments, the backend system 28750 may utilize an inverse transform and/or inverse normalization function to obtain each recreated sensor data instance.

In method 29518, backend system 28750 performs one or more backend operations based on the recreated sensor data. The backend operations may include storing the data, filtering the data, performing AI-related tasks on the sensor data, issuing one or more notifications related to results of the AI-related tasks, performing one or more analytics-related tasks, controlling industrial components of industrial configuration 28720, etc.

FIG. 296 illustrates a series of operations of a method 29600 for determining a transmission strategy and/or storage strategy for sensor data collected by the sensor kit 28700 based on the sensor data. The transmission strategy may define how the sensor data (if any) is transmitted to a backend system. For example, the sensor data may be compressed using an aggressive lossy codec, a lossless codec, and/or transmitted without compression. The storage strategy may define how the sensor data is stored on the edge device 28704. For example, the sensor data may be stored permanently (or until a human deletes the sensor data), stored for a set period of time (e.g., one year), or discarded. The method 29600 may be performed by the edge device 28704. The method 29600 may be performed to reduce network bandwidth consumed by the sensor kit 28700 and/or to reduce storage constraints on the edge device 28704.

In method 29610, edge device 28704 receives sensor data from sensor 28702 of sensor kit 28700. The data may be received continuously or intermittently. In embodiments, sensor 28702 may push the sensor data to edge device 28704 and/or edge device 28704 may periodically request sensor data 28702 from sensor 28702. In embodiments, edge device 28704 may process the sensor data as it is received, including deduplicating the sensor data.

In embodiments, the edge device 28704 may be configured to perform one or more AI-related tasks prior to transmission via the satellite uplink. In some of these embodiments, the edge device 28704 may be configured to determine, based on the sensor data and one or more machine-learned models, whether there is a high likelihood of an issue associated with either the component and/or the industrial setting 28720.

In method 29612, the edge device 28704 may generate one or more feature vectors based on the sensor data. The feature vector may include sensor data from a single sensor 28702, a subset of the sensors 28702, or all of the sensors 28702 in the sensor kit 28700. In scenarios where a single sensor or a subset of the sensors 28702 is included in the feature vector, the machine-learned model may be trained to identify one or more issues associated with the industrial component or industrial setting 28720, but may not be sufficient to fully determine the entire setting as likely clean/safe. Additionally or alternatively, the feature vector may correspond to a single snapshot in time (e.g., all sensor data in the feature vector corresponds to the same sampling event) or a period of time (e.g., sensor data samples from the most recent sampling event and sensor data samples from previous sampling events). In embodiments where the feature vector defines sensor data from a single snapshot, the machine-learned model may be trained to identify potential issues without temporal context. In embodiments where the feature vector defines sensor data over a period of time, the machine-learned model may learn to identify potential issues in the context of what the sensor(s) 28702 have/were previously reporting. In these embodiments, the edge device 28704 may maintain a cache of sensor data sampled over a predetermined period of time (e.g., the previous hour, the previous day, the previous N days), such that the cache is cleared on a first-in, first-out basis. In these embodiments, the edge device 28704 may retrieve previous sensor data samples from the cache for use in generating a feature vector having data samples over a period of time.

In method 29614, the edge device 28704 may input one or more feature vectors into one or more respective machine learning models. Each model may output a prediction or classification associated with the industrial component and/or industrial setting 28720, as well as a confidence score associated with the prediction or classification.

At 29616, the edge device 28704 may determine a transmission strategy and/or a storage strategy based on the output of the machine-learned model. In some embodiments, the edge device 28704 may make decisions related to the manner in which sensor data is transmitted to the backend system 28750. In some embodiments, the edge device 28704 may make decisions related to how the sensor data is transmitted to the backend system 28750 and/or stored on the edge device. In some of these embodiments, the edge device 28704 may compress the sensor data if there is a high probability that there are no issues across the industrial setting 28720 as a whole and across individual components of the industrial setting 28720. For example, if the machine-learned model predicts that there is a high probability that there are no issues and classifies that there are currently no issues with a high confidence (e.g., a confidence score greater than 0.98), the edge device 28704 may compress the sensor data. Alternatively, in a scenario where the machine-learned model predicts that there is likely no problem and classifies with high confidence that there is no current problem, the edge device 28704 may forgo transmission but may store the sensor data on the edge device 28704 for a predetermined period of time (e.g., a one-year expiration). In a scenario where the machine-learned model predicts a potential problem or classifies a current problem, the edge device 28704 may transmit the sensor data uncompressed or using a lossless compression codec. Additionally or alternatively, in a scenario where the machine-learned model predicts a potential problem or classifies a current problem, the edge device 28704 may store the sensor data used to make the prediction or classification indefinitely, as well as data collected before and/or after the condition is predicted or classified.

FIG. 297 illustrates an example configuration of a sensor kit 29700 according to some embodiments of the present disclosure. In the illustrated example, the sensor kit 29700 is configured to communicate with a communications network 28780 via an uplink 29708 to a satellite 29710. In an embodiment, the sensor kit 29700 of FIG. 151 is configured for use in an industrial setting 28720 located in a remote location where cellular coverage is unreliable or non-existent. In an embodiment, the sensor kit 29700 may be installed in natural resource extraction, natural resource transportation systems, power generation facilities, and the like. For example, the sensor kit 29700 may be deployed in an oil or natural gas field, an offshore oil rig, a mine, an oil or gas pipeline, a solar field, a wind farm, a hydroelectric power plant, and the like.

In the example of FIG. 151, the sensor kit 29700 includes an edge device 28704 and a set of sensors 28702. The sensors 28702 may include various types of sensors 28702, depending on the industrial setting 28720. In the illustrated example, the sensors 28702 communicate with the edge device 28704 via a mesh network. In these embodiments, the sensors 28702 may communicate sensor data to nearby sensors, which may then propagate the sensor data to edge devices 28704 located in remote/peripheral areas of the industrial setting 28720. While a mesh network is shown, the sensor kit 29700 of FIG. 151 may include alternative network topologies, such as a hierarchical topology (e.g., some or all of the sensors 28702 communicate with the edge devices 28704 through their respective collection devices) or a star topology (e.g., the sensors 28702 communicate directly with the edge devices).

In the embodiment of FIG. 151, edge device 28704 includes a satellite terminal having a directional antenna for communicating with a satellite. The satellite terminal may be pre-configured to communicate with a geosynchronous satellite or a low-Earth orbit satellite. Edge device 28704 may receive sensor data from the sensor kit network established by sensor kit 29700. Edge device 28704 may then transmit the sensor data to backend system 28750 via satellite 29710.

In embodiments, the configuration of sensor kit 29700 is suitable for industrial settings 28720 covering remote locations where external power sources are not abundant. In embodiments, sensor kit 29700 may include an external power source, such as a battery, a rechargeable battery, a generator, and/or a solar panel. In these embodiments, the external power source may be deployed to power sensor 28702, edge device 28704, and any other devices within sensor kit 29700.

In embodiments, the configuration of sensor kit 29700 is suitable for an outdoor industrial setting 28720. In embodiments, sensor 28702, edge device 28704, and other devices of sensor kit 28700 (e.g., collection device) may be configured in a weather-resistant housing. In these embodiments, sensor kit 29700 may be deployed in an outdoor setting.

In embodiments, the edge device 28704 may be configured to perform one or more AI-related tasks prior to transmission via satellite uplink. In some of these embodiments, the edge device 28704 may be configured to determine whether there is a high likelihood of a problem associated with any of the components and/or industrial setting 28720 based on the sensor data and one or more machine-learned models. In embodiments, the edge device 28704 may receive sensor data from various sensors and generate one or more feature vectors based thereon. The feature vector may include sensor data from a single sensor 28702, a subset of the sensors 28702, or all of the sensors 28702 in the sensor kit 29700. In scenarios where a single sensor or a subset of the sensors 28702 is included in the feature vector, the machine-learned model may be trained to identify one or more problems associated with the industrial component or industrial setting 28720, but may not be sufficient to fully determine that the entire setting is likely to be problem-free/safe. Additionally or alternatively, the feature vector may correspond to a single snapshot in time (e.g., all sensor data in the feature vector corresponds to the same sampling event) or a period of time (sensor data samples from the most recent sampling event and sensor data samples from previous sampling events). In embodiments where the feature vector defines sensor data from a single snapshot, the machine-learned model may be trained to identify potential issues without temporal context. In embodiments where the feature vector defines sensor data over a period of time, the machine-learned model may be trained to identify potential issues in the context of what the sensor(s) 28702 have/were previously reporting. In these embodiments, the edge device 28704 may maintain a cache of sensor data sampled over a predetermined period of time (e.g., the previous hour, the previous day, the previous N days), such that the cache is cleared on a first-in, first-out basis. In these embodiments, the edge device 28704 may retrieve previous sensor data samples from the cache for use in generating a feature vector having data samples over a period of time.

In embodiments, the edge device 28704 may feed one or more feature vectors to one or more respective machine learning models. Each model may output a prediction or classification associated with the industrial component and/or industrial setting 28720, as well as a confidence score associated with the prediction or classification. In some embodiments, the edge device 28704 may make decisions related to how the sensor data is transmitted to the backend system 28750 and/or stored on the edge device. For example, in some embodiments, the edge device 28704 may compress the sensor data based on the prediction or classification. In some of these embodiments, the edge device 28704 may compress the sensor data if a problem is unlikely to occur across the industrial setting 28720 as a whole and across individual components of the industrial setting 28720. For example, if the machine learning model predicts that there is likely no problem and classifies that there is currently no problem with a high degree of confidence (e.g., a confidence score greater than 0.98), the edge device 28704 may compress the sensor data. Alternatively, in a scenario where the machine-learned model predicts that there is likely no problem and classifies with high confidence that there is no current problem, the edge device 28704 may forgo transmission but may store the sensor data on the edge device 28704 for a predetermined period of time (e.g., one year). In a scenario where the machine-learned model predicts a potential problem or classifies a current problem, the edge device 28704 may transmit the sensor data without compression or using a lossless compression codec. In this manner, the amount of bandwidth transmitted over the satellite uplink may be reduced, as the sensor data is compressed or not transmitted in most cases.

In embodiments, the edge device 28704 may apply one or more rules to determine whether a trigger condition exists. In embodiments, the one or more rules may be tailored to identify potential hazards and/or emergency situations. In these embodiments, the edge device 28704 may trigger one or more notifications or alarms when a trigger condition exists. Additionally or alternatively, the edge device 28704 may transmit sensor data without compression when a trigger condition exists.

FIG. 298 illustrates an example configuration of a sensor kit 29800 according to some embodiments of the present disclosure. In the illustrated example, sensor kit 29800 is configured to include a gateway device 29806 that communicates with a communications network 28780 via an uplink 29708 to a satellite 29710. In an embodiment, sensor kit 29800 of FIG. 152 is configured for use in an industrial setting 28720 located in a remote area where cellular coverage is unreliable or non-existent, and edge device 28704 is located where physical transmission to a satellite is unreliable or impossible. In an embodiment, sensor kit 29700 may be installed in an underground or underwater facility, or in a facility with very thick walls. For example, sensor kit 29700 may be deployed in an underground mine, an underwater oil or gas pipeline, an underwater hydroelectric power plant, etc.

In the example of FIG. 152, sensor kit 29800 includes edge device 28704, a set of sensors 28702, and gateway device 29806. In an embodiment, gateway device 29806 is a communications device including a satellite terminal having a directional antenna for communicating with a satellite. The satellite terminal may be pre-configured to communicate with a geosynchronous satellite or a low-Earth orbit satellite. In an embodiment, gateway device 29806 may communicate with edge device 28704 via wired communications link 29808 (e.g., Ethernet). Edge device 28704 may receive sensor data from the sensor kit network established by sensor kit 29800. Edge device 28704 may then transmit the sensor data to gateway device 29806 via wired communications link 29808. Gateway device 29806 may then communicate the sensor data to backend system 28750 via satellite uplink 29708.

The sensors 28702 may include various types of sensors 28702, which may vary depending on the industrial setting 28720. In the illustrated example, the sensors 28702 communicate with the edge devices 28704 via a mesh network. In these embodiments, the sensors 28702 may communicate sensor data to nearby sensors 28702, which then propagate the sensor data to edge devices 28704 located in remote/peripheral portions of the industrial setting 28720. While a mesh network is shown, the sensor kit 29800 of FIG. 152 may include alternative network topologies, such as a hierarchical topology (e.g., some or all of the sensors 28702 communicate with the edge devices 28704 through their respective collection devices) or a star topology (e.g., the sensors 28702 communicate directly with the edge devices).

In embodiments, the configuration of the server kit 29800 is suitable for industrial settings 28720 covering remote locations where external power sources are not abundant. In embodiments, the sensor kit 29800 may include an external power source, such as a battery, a rechargeable battery, a generator, and/or a solar panel. In these embodiments, the external power source may be deployed to power the sensor 28702, the edge device 28704, and any other devices within the sensor kit 29800.

In an embodiment, the configuration of server kit 29800 is suitable for underground or underwater industrial settings 28720. In an embodiment, sensor 28702, edge device 28704, and other devices (e.g., collection devices) of sensor kit 28700 may be configured in a waterproof or other airtight housing (to prevent dust from entering edge device 28704 and/or sensor device 28702). Additionally, because gateway device 29808 is likely to be installed outdoors, gateway device 29808 may include a weatherproof housing.

In embodiments, the edge device 28704 may be configured to perform one or more AI-related tasks prior to transmission via satellite uplink. In some of these embodiments, the edge device 28704 may be configured to determine whether there is a high probability that there is no problem associated with any of the components and/or industrial setting 28720 based on the sensor data and one or more machine-learned models. In embodiments, the edge device 28704 may receive sensor data from various sensors and generate one or more feature vectors based thereon. The feature vector may include sensor data from a single sensor 28702, a subset of the sensors 28702, or all of the sensors 28702 in the sensor kit 29800. In scenarios where a single sensor or a subset of the sensors 28702 is included in the feature vector, the machine-learned model may be trained to identify one or more problems associated with the industrial component or industrial setting 28720, but may not be sufficient to fully determine that the entire setting is likely to be problem-free/safe. Additionally or alternatively, the feature vector may correspond to a single snapshot in time (e.g., all sensor data in the feature vector corresponds to the same sampling event) or a period of time (sensor data samples from the most recent sampling event and sensor data samples from previous sampling events). In embodiments where the feature vector defines sensor data from a single snapshot, the machine-learned model may be trained to identify potential issues without temporal context. In embodiments where the feature vector defines sensor data over a period of time, the machine-learned model may be trained to identify potential issues in the context of what the sensor(s) 28702 have/were previously reporting. In these embodiments, the edge device 28704 may maintain a cache of sensor data sampled over a predetermined period of time (e.g., the previous hour, the previous day, the previous N days), such that the cache is cleared on a first-in, first-out basis. In these embodiments, the edge device 28704 may retrieve previous sensor data samples from the cache for use in generating a feature vector having data samples over a period of time.

In embodiments, the edge device 28704 may feed one or more feature vectors to one or more respective machine learning models. Each model may output a prediction or classification associated with the industrial component and/or industrial setting 28720, as well as a confidence score associated with the prediction or classification. In some embodiments, the edge device 28704 may make decisions related to how the sensor data is transmitted to the backend system 28750 and/or stored on the edge device. For example, in some embodiments, the edge device 28704 may compress the sensor data based on the prediction or classification. In some of these embodiments, the edge device 28704 may compress the sensor data if a problem is unlikely to occur across the industrial setting 28720 as a whole and across individual components of the industrial setting 28720. For example, if the machine learning model predicts that there is likely no problem and classifies that there is currently no problem with a high degree of confidence (e.g., a confidence score greater than 0.98), the edge device 28704 may compress the sensor data. Alternatively, in a scenario where the machine-learned model predicts that there is likely no problem and classifies with high confidence that there is no current problem, the edge device 28704 may forgo transmission but may store the sensor data on the edge device 28704 for a predefined period of time (e.g., one year). In such a scenario, once the machine-learned model predicts a potential problem or classifies a current problem, the edge device 28704 may transmit the sensor data without compression or using a lossless compression codec. In this manner, the amount of bandwidth transmitted over the satellite uplink may be reduced, as the sensor data is compressed or not transmitted in most cases.

In embodiments, the edge device 28704 may apply one or more rules to determine whether a trigger condition exists. In embodiments, the one or more rules may be tailored to identify potential hazards and/or emergency situations. In these embodiments, the edge device 28704 may trigger one or more notifications or alarms when a trigger condition exists. Additionally or alternatively, the edge device 28704 may transmit the sensor data (via the gateway device 29806) without compression when a trigger condition exists.

FIG. 153 illustrates an example configuration of a sensor kit 29900 according to some embodiments of the present disclosure. In the example of FIG. 153, the sensor kit 29900 includes an edge device 28704, a set of sensors, and a set of collection devices. In an embodiment, the sensor kit 29900 configuration is suitable for an industrial setting 28720 that covers a large area and has abundant power sources, but where the industrial operator does not want to connect the sensor kit 29900 to the industrial setting's 28720 private network. In an embodiment, the edge device 28704 includes a cellular communication device (e.g., a 4G LTE chipset or a 5G LTE chipset) with a transceiver that communicates with a cellular tower 29910. The cellular communication may be pre-configured to communicate with a cellular data provider. For example, in an embodiment, the edge device 28704 may include a SIM card registered with a cellular provider that has a cellular tower 29910 proximate to the industrial setting 28720. The edge device 28704 may receive sensor data from the sensor kit network established by the sensor kit 29900. After processing the sensor data, the edge device 28704 may transmit the sensor data to the backend system 28750 via the cellular tower 29910.

The sensors 28702 may include various types of sensors 28702, which may vary depending on the industrial setting 28720. In the illustrated example, the sensors 28702 communicate with the edge device 28704 via a hierarchical network. In these embodiments, the sensors 28702 may communicate sensor data to the collector 206, which may communicate the sensor data to the edge device 28704 via a wired or wireless communication link. The hierarchical network may be deployed anywhere in an area, such as a factory, power plant, food testing facility, indoor cultivation facility, or other facility that is larger (e.g., 40,000 square feet or larger) and where power sources are abundant. While a hierarchical network is shown, the sensor kit 29900 of FIG. 153 may include alternative network topologies, such as a mesh topology or a star topology (e.g., the sensors 28702 communicate directly to the edge device).

In embodiments, the edge device 28704 may be configured to perform one or more AI-related tasks prior to transmission via satellite uplink. In some of these embodiments, the edge device 28704 may be configured to determine whether there is a high likelihood of a problem associated with any of the components and/or industrial setting 28720 based on the sensor data and one or more machine-learned models. In embodiments, the edge device 28704 may receive sensor data from various sensors and generate one or more feature vectors based thereon. The feature vector may include sensor data from a single sensor 28702, a subset of the sensors 28702, or all of the sensors 28702 in the sensor kit 29900. In scenarios where a single sensor or a subset of the sensors 28702 is included in the feature vector, the machine-learned model may be trained to identify one or more problems associated with the industrial component or industrial setting 28720, but may not be sufficient to fully determine that the entire setting is likely to be problem-free/safe. Additionally or alternatively, the feature vector may correspond to a single snapshot in time (e.g., all sensor data in the feature vector corresponds to the same sampling event) or a period of time (sensor data samples from the most recent sampling event and sensor data samples from a previous sampling event). In embodiments where the feature vector defines sensor data from a single snapshot, the machine-learned model may be trained to identify potential issues without temporal context. In embodiments where the feature vector defines sensor data over a period of time, the machine-learned model may be trained to identify potential issues in the context of what the sensor(s) 28702 have/were previously reporting. In these embodiments, the edge device 28704 may maintain a cache of sensor data sampled over a predetermined period of time (e.g., the previous hour, the previous day, the previous N days), such that the cache is cleared on a first-in, first-out basis. In these embodiments, the edge device 28704 may retrieve previous sensor data samples from the cache for use in generating a feature vector having data samples over a period of time.

In embodiments, the edge device 28704 may feed one or more feature vectors to one or more respective machine learning models. Each model may output the following: a prediction or classification regarding the industrial component and/or industrial environment 28720 and a confidence score for the prediction or classification. In some embodiments, the edge device 28704 may make decisions related to how sensor data is transmitted to the backend system 28750 and/or stored on the edge device. For example, in some embodiments, the edge device 28704 may compress the sensor data based on the prediction or classification. In some of these embodiments, the edge device 28704 may compress the sensor data if problems are unlikely to occur across the industrial setting 28720 as a whole and across individual components of the industrial setting 28720. For example, if the machine learning model predicts that there is likely no problem and classifies that there is currently no problem with a high degree of confidence (e.g., a confidence score greater than 0.98), the edge device 28704 may compress the sensor data. Alternatively, in a scenario where the machine-learned model predicts that there is likely no problem and classifies with high confidence that there is no current problem, the edge device 28704 may forgo transmission but may store the sensor data at the edge device 28704 for a predetermined period of time (e.g., one year). In a scenario where the machine-learned model predicts a potential problem or classifies a current problem, the edge device 28704 may transmit the sensor data without compression or using a lossless compression codec. In this way, the amount of bandwidth transmitted over cellular towers may be reduced, as the sensor data is compressed or not transmitted in most cases.

In embodiments, the edge device 28704 may apply one or more rules to determine whether a trigger condition exists. In embodiments, the one or more rules may be tailored to identify potential hazards and/or emergency situations. In these embodiments, the edge device 28704 may trigger one or more notifications or alarms when a trigger condition exists. Additionally or alternatively, the edge device 28704 may transmit sensor data without compression when a trigger condition exists.

FIG. 154 illustrates an example configuration of a sensor kit 30000 according to some embodiments of the present disclosure. In the example of FIG. 154, the sensor kit 30000 includes an edge device 28704, a set of sensors 28702, a set of collection devices 206, and a gateway device 30006. In an embodiment, the sensor kit 30000 configuration is suitable for an industrial setting 28720 that covers a large area and has abundant power sources, but where wireless communication (e.g., cellular communication) is unreliable or impossible in the industrial environment 28720 and the industrial operator does not want to connect the sensor kit 30000 to the industrial setting's 28720 private network. In an embodiment, the gateway device 30006 is a cellular network gateway device that includes a cellular communication device (e.g., a 4G, 5G chipset) with a transceiver that communicates with a cellular tower 29910. The cellular communication may be pre-configured to communicate with a cellular data provider. For example, in an embodiment, the gateway device 30006 may include a SIM card registered with a cellular provider having a tower 29910 proximate to the industrial setting 28720. In an embodiment, the gateway device 30006 may communicate with the edge device 28704 via a wired communication link 30008 (e.g., Ethernet). The edge device 28704 may receive sensor data from the sensor kit network established by the sensor kit 30000. The edge device 28704 may then transmit the sensor data to the gateway device 30006 via the wired communication link 30008. The gateway device 30006 may then communicate the sensor data to the backend system 28750 via the cellular tower 29910.

The sensors 28702 may include various types of sensors 28702, which vary depending on the industrial setting 28720. In the illustrated example, the sensors 28702 communicate with the edge device 28704 via a hierarchical network. In these embodiments, the sensors 28702 may communicate sensor data to the collector 206, which may communicate the sensor data to the edge device 28704 via a wired or wireless communication link. Hierarchical networks may be deployed in locations where the monitored area is rather large (e.g., 40,000 square feet or more) and power sources are plentiful, such as factories, power plants, food testing facilities, indoor cultivation facilities, etc. Although a hierarchical network is shown, the sensor kit 30000 of FIG. 154 may include alternative network topologies, such as a mesh topology or a star topology (e.g., where the sensors 28702 communicate directly to the edge device).

In embodiments, the edge device 28704 may be configured to perform one or more AI-related tasks prior to transmission via satellite uplink. In some of these embodiments, the edge device 28704 may be configured to determine whether there is a high likelihood of a problem associated with any of the components and/or industrial setting 28720 based on the sensor data and one or more machine-learned models. In embodiments, the edge device 28704 may receive sensor data from various sensors and generate one or more feature vectors based thereon. The feature vector may include sensor data from a single sensor 28702, a subset of the sensors 28702, or all of the sensors 28702 in the sensor kit 30000. In scenarios where a single sensor or a subset of the sensors 28702 is included in the feature vector, the machine-learned model may be trained to identify one or more problems associated with the industrial component or industrial setting 28720, but may not be sufficient to fully determine that the entire setting is likely to be problem-free/safe. Additionally or alternatively, the feature vector may correspond to a single snapshot in time (e.g., all sensor data in the feature vector corresponds to the same sampling event) or a period of time (sensor data samples from the most recent sampling event and sensor data samples from previous sampling events). In embodiments where the feature vector defines sensor data from a single snapshot, the machine-learned model may be trained to identify potential issues without temporal context. In embodiments where the feature vector defines sensor data over a period of time, the machine-learned model may be trained to identify potential issues in the context of what the sensor(s) 28702 have/were previously reporting. In these embodiments, the edge device 28704 may maintain a cache of sensor data sampled over a predetermined period of time (e.g., the previous hour, the previous day, the previous N days), such that the cache is cleared on a first-in, first-out basis. In these embodiments, the edge device 28704 may retrieve previous sensor data samples from the cache for use in generating a feature vector having data samples over a period of time.

In embodiments, the edge device 28704 may feed one or more feature vectors to one or more respective machine learning models. Each model may output a prediction or classification associated with the industrial component and/or industrial setting 28720, as well as a confidence score associated with the prediction or classification. In some embodiments, the edge device 28704 may make decisions related to how the sensor data is transmitted to the backend system 28750 and/or stored at the edge device. For example, in some embodiments, the edge device 28704 may compress the sensor data based on the prediction or classification. In some of these embodiments, the edge device 28704 may compress the sensor data if problems are unlikely to occur across the industrial setting 28720 as a whole and across individual components of the industrial setting 28720. For example, if the machine learning model predicts that there is likely no problem and classifies that there is currently no problem with a high degree of confidence (e.g., a confidence score greater than 0.98), the edge device 28704 may compress the sensor data. Alternatively, in a scenario where the machine learning model predicts that there is likely no problem and classifies with high confidence that there is no current problem, the edge device 28704 may forgo transmission but may store and transmit the sensor data to the edge device 28704 for a predefined period of time (e.g., one year). In a scenario where the machine learning model predicts a potential problem or classifies a current problem, the edge device 28704 may transmit the sensor data without compression or using a lossless compression codec. In this way, the amount of bandwidth transmitted over cellular towers may be reduced, as the sensor data is compressed or not transmitted in most cases.

In embodiments, the edge device 28704 may apply one or more rules to determine whether a trigger condition exists. In embodiments, the one or more rules may be tailored to identify potentially dangerous and/or emergency situations. In these embodiments, the edge device 28704 may trigger one or more notifications or alarms when a trigger condition exists. Additionally or alternatively, the edge device 28704 may transmit sensor data without compression when a trigger condition exists.

FIG. 155 illustrates an example configuration of a sensor kit 30100 for installation in an agricultural setting 30120, according to some embodiments of the present disclosure. In the example of FIG. 155, the sensor kit 30100 is configured for installation in an indoor agricultural setting 30120, which may include, but is not limited to, a control system 30122, an HVAC system 30124, a lighting system 30126, a power system 30128, and/or an irrigation system 30130. In this example, various features and components of the agricultural setting include components that are monitored by a set of sensors 28702. In an embodiment, the sensors 28702 capture instances of sensor data and provide each instance of the sensor data to an edge device 28704. In the exemplary embodiment of FIG. 155, the sensor kit 30100 includes a set of collection devices 206 that route the sensor data from the sensors 28702 to the edge device 28704. A sensor kit 30100 for deployment in an agricultural environment may also have different sensor kit network topologies. For example, in facilities with no more than two or three monitored rooms, the sensor kit network may be a mesh or star network, depending on the distance between the edge device 28704 and the farthest potential sensor location. For example, if the distance between the edge device 28704 and the farthest potential sensor location is greater than 150 meters, the sensor kit network may be configured as a mesh network. In the embodiments of FIG. 155, the edge device 28704 transmits sensor data directly to the backend system 28750. In these embodiments, the edge device 28704 includes a cellular communication device that communicates with a cellular tower 29910 of a pre-configured cellular provider via a pre-configured cellular connection. In other embodiments of the present disclosure, the edge device 28704 transmits sensor data to the backend system 28750 via a gateway device (e.g., gateway device 30006) that includes a cellular communication device that communicates with a cellular tower 29910 of a pre-configured cellular provider.

In embodiments, the sensor kit 30100 may include any suitable combination of a light sensor 30102, a weight sensor 30104, a temperature sensor 30106, a CO2 sensor 30108, a humidity sensor 30110, a fan speed sensor 30112, and/or an audio/visual (AV) sensor 30114 (e.g., a camera). The sensor kit 30100 may also include additional or alternative sensors 28702. In embodiments, the sensor data collected by the edge device 28704 may include ambient light measurements indicative of the amount of ambient light detected in the area of the light sensor 30102. In embodiments, the sensor data collected by the edge device 28704 may include weight or mass measurements indicative of the weight or mass of an object (e.g., a pot or tray containing one or more plants) placed on the weight sensor 30104. In embodiments, the sensor data collected by the edge device 28704 may include temperature measurements indicative of the ambient temperature in the vicinity of the temperature sensor 30106. In an embodiment, the sensor data collected by edge device 28704 may include humidity measurements indicative of ambient humidity in the vicinity of humidity sensor 30110, or moisture measurements indicative of the relative amount of moisture in a medium (e.g., soil) monitored by humidity sensor 30110. In an embodiment, the sensor data collected by edge device 28704 may include CO2 measurements indicative of ambient levels of CO2 in the vicinity of CO2 sensor 30108. In an embodiment, the sensor data collected by edge device 28704 may include temperature measurements indicative of ambient temperature in the vicinity of temperature sensor 30106. In an embodiment, the sensor data collected by edge device 28704 may include fan speed measurements indicative of the measured speed of a fan (e.g., a fan of HVAC system 30124) measured by fan speed sensor 30112. In an embodiment, the sensor data collected by edge device 28704 may include a video signal captured by AV sensor 30116. The sensor data captured by sensor 28702 and collected by edge device 28704 may include additional or alternative types of sensor data without departing from the scope of this disclosure.

In embodiments, edge device 28704 is configured to perform one or more edge operations on the sensor data. For example, edge device 28704 may preprocess the received sensor data. In embodiments, edge device 28704 may predict or classify potential problems with one or more components of HVAC system 30124, lighting system 30126, power system 30128, irrigation system 30130, plants growing in the agricultural facility, and/or the facility itself. In embodiments, edge device 28704 may analyze the sensor data with respect to a set of rules that define trigger conditions. In these embodiments, edge device 28704 may trigger an alarm or notification in response to a trigger condition being met. In embodiments, edge device 28704 may encode, compress, and/or encrypt the sensor data before transmitting it to backend system 28750. In some of these embodiments, the edge device 28704 may selectively compress the sensor data based on a prediction or classification made by the edge device 28704 and/or based on one or more trigger conditions being met.

In embodiments, the edge device 28704 may be configured to perform one or more AI-related tasks prior to transmission via satellite uplink. In some of these embodiments, the edge device 28704 may be configured to determine whether there is a high likelihood of a problem associated with any of the components and/or industrial setting 28720 based on the sensor data and one or more machine-learned models. In embodiments, the edge device 28704 may receive sensor data from various sensors and generate one or more feature vectors based thereon. The feature vector may include sensor data from a single sensor 28702, a subset of the sensors 28702, or all of the sensors 28702 in the sensor kit 29900. In scenarios where a single sensor or a subset of the sensors 28702 is included in the feature vector, the machine-learned model may be trained to identify one or more problems associated with the industrial component or industrial setting 28720, but may not be sufficient to fully determine that the entire setting is likely to be problem-free/safe. Additionally or alternatively, the feature vector may correspond to a single snapshot in time (e.g., all sensor data in the feature vector corresponds to the same sampling event) or a period of time (sensor data samples from the most recent sampling event and sensor data samples from previous sampling events). In embodiments where the feature vector defines sensor data from a single snapshot, the machine-learned model may be trained to identify potential issues without temporal context. In embodiments where the feature vector defines sensor data over a period of time, the machine-learned model may be trained to identify potential issues in the context of what the sensor(s) 28702 have/were previously reporting. In these embodiments, the edge device 28704 may maintain a cache of sensor data sampled over a predetermined period of time (e.g., the previous hour, the previous day, the previous N days), such that the cache is cleared on a first-in, first-out basis. In these embodiments, the edge device 28704 uses the cache to generate the feature vector with data samples over a period of time.

In embodiments, the edge device 28704 may feed one or more feature vectors to one or more respective machine learning models. Each model may output a prediction or classification associated with the industrial component and/or industrial setting 28720, as well as a confidence score associated with the prediction or classification. In some embodiments, the edge device 28704 may make decisions related to how the sensor data is transmitted to the backend system 28750 and/or stored at the edge device. For example, in some embodiments, the edge device 28704 may compress the sensor data based on the prediction or classification. In some of these embodiments, the edge device 28704 may compress the sensor data if problems are unlikely to occur across the industrial setting 28720 as a whole and across individual components of the industrial setting 28720. For example, if the machine learning model predicts that there is likely no problem and classifies that there is currently no problem with a high degree of confidence (e.g., a confidence score greater than 0.98), the edge device 28704 may compress the sensor data. Alternatively, in a scenario where the machine learning model predicts that there is likely no problem and classifies with high confidence that there is no current problem, the edge device 28704 may forgo transmission but may store the sensor data on the edge device 28704 for a predetermined period of time (e.g., one year). In a scenario where the machine learning model predicts a potential problem or classifies a current problem, the edge device 28704 may transmit the sensor data without compression or using a lossless compression codec. In this way, the amount of bandwidth transmitted over cellular towers may be reduced, as the sensor data is compressed or not transmitted in most cases.

In embodiments, the edge device 28704 may apply one or more rules to the sensor data to determine whether a trigger condition exists. In embodiments, the one or more rules may be tailored to identify potential hazards and/or emergency situations. In these embodiments, the edge device 28704 may trigger one or more notifications or alarms when a trigger condition exists. Additionally or alternatively, the edge device 28704 may transmit the sensor data without compression when a trigger condition exists. In some embodiments, the edge device 28704 may selectively compress and/or transmit the sensor data based on the application of one or more rules to the sensor data.

In embodiments, backend system 28750 may perform one or more backend operations based on the received sensor data. In embodiments, backend system 28750 may decode/decompress/decrypt the sensor data received from each sensor kit 30100. In embodiments, backend system 28750 may preprocess the received sensor data. In embodiments, backend system 28750 may preprocess the sensor data received from each sensor kit 30100. For example, backend system 28750 may filter, deduplicate, and/or structure the sensor data. In embodiments, backend system 28750 may perform one or more AI-related tasks using the sensor data. In some of these embodiments, backend system 28750 may extract features from the sensor data and use them to predict or classify specific conditions or events related to the agricultural environment. For example, backend system 28750 may develop a model used to predict crop yield based on weight measurements, temperature measurements, CO2 measurements, light measurements, and/or other extracted features. In another example, backend system 28750 may develop models used to predict or classify mold-conducive conditions in rooms or areas of an agricultural facility based on temperature measurements, humidity measurements, video signals or images, and/or other extracted features. In embodiments, backend system 28750 may perform one or more analytical tasks on sensor data and display the results to a human user via a dashboard. In some embodiments, backend system 28750 may receive control commands from a human user via a dashboard. For example, a human resource with sufficient login credentials may control an HVAC system 30124, a lighting system 30126, a power system 30128, and/or an irrigation system 30130 in an industrial setting 28720. In some of these embodiments, backend system 28750 may telemetrically monitor the actions of the human users and train one or more machine learning models (e.g., neural networks) on actions to take in response to displaying the analytical results to the human user. In other embodiments, the backend system 28750 may execute one or more workflows related to the HVAC system 30f24, the lighting system 30126, the power system 30128, and/or the irrigation system 30130 to control one or more of the systems of the agricultural setting 30120 based on predictions or classifications made by the backend system in response to sensor data. In embodiments, the backend system 28750 may provide one or more control commands to the control system 30122 of the agricultural setting 30120, which may control the HVAC system 30124, the lighting system 30126, the power system 30128, and/or the irrigation system 30130 based on the received control commands. In embodiments, the backend system 28750 may provide or utilize an API to provide the control commands to the agricultural setting 30120.

FIG. 156 illustrates an example operation of a method 30200 for monitoring an industrial setting 28720 using an automatically configured backend system 28750. In an embodiment, the method 30200 may be performed by the backend system 28750, the sensor kit 28700, and the dashboard module 532.

In 30202, the backend system 28750 registers the sensor kit 28700 with a respective industrial setting 28720. In some embodiments, the backend system 28750 registers multiple sensor kits 28700 and registers each sensor kit 28700 of the multiple sensor kits 28700 with a respective industrial setting 28720. In embodiments, the backend system 28750 provides an interface for specifying the type of entity or industrial setting 28720 to be monitored. In some embodiments, a user may select a set of parameters for monitoring each industrial setting 28720 of the sensor kit 28700. The backend system 28750 may automatically provide a set of services and capabilities of the backend system 28750 based on the selected parameters.

In 30204, backend system 28750 configures sensor kit 28700 to monitor physical characteristics of each industrial setting 28720 in which sensor kit 28700 is registered. For example, if each industrial setting 28720 is a natural resource extraction setting, backend system 28750 may configure one or more of an infrared sensor, a ground penetration sensor, a light sensor, a humidity sensor, a temperature sensor, a chemical sensor, a fan speed sensor, a rotational speed sensor, a weight sensor, and a camera sensor to monitor and collect sensor data related to metrics and parameters of the natural resource extraction setting and the equipment used therein.

At 30206, the sensor kit 28700 transmits the instance of the sensor data to the backend system 28750. In some embodiments, the sensor kit 28700 transmits the instance of the sensor data to the backend system 28750 via a gateway device. The gateway device may provide a virtual container for the instance of the sensor data so that only registered owners or operators of the respective industrial settings 28720 can access the sensor data via the backend system 28750.

In 30208, backend system 28750 processes the instances of sensor data received from sensor kit 28700. In some embodiments, backend system 28750 includes an analytics facility and/or a machine learning facility. The analytics facility and/or machine learning facility may be configured based on the type of industrial setting 28720 and may process the instances of sensor data received from sensor kit 28700. In some embodiments, backend system 28750 updates and/or configures the distributed ledger based on the instances of processed sensor data.

At 30210, backend system 28750 configures and populates a dashboard. In embodiments, backend system 28750 configures the dashboard to retrieve and display one or more of raw sensor data provided by the sensor kit, analytical data related to the sensor data provided by sensor kit 28700, predictions or classifications made by backend system 28750 based on the sensor data, etc. In some embodiments, backend system 28750 configures alarm limits for one or more sensor types and/or conditions based on industrial settings 28720. Backend system 28750 may define which users receive notifications when alarms are triggered. In embodiments, backend system 28750 may subscribe to additional capabilities of backend system 28750 and/or edge device 28704 based on industrial settings 28720.

At 30212, the dashboard provides the monitoring information to a human user. In an embodiment, the dashboard provides the monitoring information to the user by displaying the monitoring information on a device, such as a computer terminal, a smartphone, a monitor, or any other suitable device for displaying information. The monitoring information may be provided via a graphical user interface.

FIG. 157 illustrates an exemplary manufacturing facility 30300, according to some embodiments of the present disclosure. The manufacturing facility 30300 may include a plurality of industrial machines 30302, illustratively including conveyor belts, assembly machines, die machines, turbines, and power systems. The manufacturing facility 30300 may further include a plurality of products 30304. The manufacturing facility may have a sensor kit 28700 installed therein, the sensor kit 28700 including a plurality of sensors 28702 and edge devices 28704. As an example, one or more sensors 28702 may be installed on some or all of the industrial machines 30302 and products 30304.

FIG. 158 illustrates a surface portion of an exemplary underwater industrial facility 30400, according to some embodiments of the present disclosure. The underwater industrial facility 30400 may include a transport and communication platform 30402, a storage platform 30404, and a pump platform 30406. The underwater industrial facility 30400 may have a sensor kit 28700 installed therein, the sensor kit 28700 including a plurality of sensors 28702 and an edge device 28704. By way of example, one or more sensors 28702 may be installed in some or all of the transport and communication platform 30402, the storage platform 30404, and the pumping platform 30406, as well as their individual components and machinery.

FIG. 159 illustrates an exemplary indoor farming facility 30500 according to some embodiments of the present disclosure. The indoor farming facility 30500 may include a greenhouse 30502 and multiple wind turbines 30504. The indoor farming facility 30500 may have a sensor kit 28700 installed therein, the sensor kit 28700 including multiple sensors 28702 and an edge device 28704. By way of example, one or more sensors 28702 may be installed in some or all components of the greenhouse 30504 and some or all components of the wind turbines 30504.

160, in embodiments, the edge device 28704 can include, link or connect, integrate, or be integrated with a control system 13742 and/or a data processing platform 13700 to provide control of one or more industry entities 13736, such as controlling machines in a factory (CNC machines, additive manufacturing machines, energy systems (e.g., generators or turbines), assembly lines, etc.), control of workflows (production workflows, inspection workflows, data collection workflows, maintenance workflows, service workflows, etc.), or control of subsystems, systems, or operations of an entire factory or set of factories. In some embodiments, the edge device 28704 may be linked or connected to the control system 13742 via a network 28780. In some embodiments, the edge device 28704 may integrate with the control system 13742 via a processing device 29006. In some embodiments, the control system 13742 may be integrated with a backend system 28750. The processing, computational, and intelligence capabilities of the edge device 28704 may thus benefit from input from, and may provide input to, (including control signals therefor) the set of control systems 13742. Data from the sensor kit 28700 (including report packets, sensor kit packets, and/or other data from the sensors 28702), and/or the data processing module 29020, encoding module 29022, decision AI module 29024, notification module 29026, configuration module 29028, and distributed ledger module 29030), and/or data from the edge device 28704 may be represented in a set of industrial digital twins 13734. For example, the industrial digital twin 13734 may show a point cloud view (which in embodiments may be augmented, such as using 3D mapping, AR, or VR systems) of the industrial setting 28720, with associated data collection elements presented in the point cloud view along with the point cloud. Many examples are available, such as highlighting (e.g., by color or movement) areas of the point cloud where the system is vibrating in a way that is outside of normal ranges (such as exceeding a threshold of severity units as discussed elsewhere herein) in the digital twin 13734. The industrial entity digital twin 13734 may include, link or connect to, or integrate with various interfaces and dashboards 13738, such as those configured for specific workflows, roles, and users. For example, dashboards and interfaces may be used to inform workers interacting with a particular machine (such as when the digital twin is used for training, workflow guidance, diagnosing problems, etc.), managers of factory floor operations (such as when the digital twin 13734 shows the layout of machines on the floor, traffic patterns (e.g., asset movement; moving assets 13708 and workers 13712 involved in a workflow), status information (including operation status, maintenance status, inspection status, etc.) for workers, machines, processes, etc.), analytical information (such as showing metrics about operations, potential problems, etc.), inspectors (such as when the digital twin 13734 shows areas indicated by the data collector 13702 as needing or beneficial for additional inspection (e.g., an inspector can check off items that have already been inspected or highlight items for further inspection by interacting with the digital twin interface or dashboard 13738)), maintenance and service workers (such as when the digital twin 13734 shows a schematic highlighting the location of items needing maintenance and directing service workers to the appropriate location and/or machine, providing information on how to perform the service or maintenance, and Examples of relevant audiences include those presenting guidance (e.g., in separate views) (from checklists or workflows to machine-presentable virtual, mixed, or augmented reality training or guidance sessions); front office managers (e.g., finance personnel who can present financial information (including current and forecasted) such as ROI metrics, output metrics, and cost metrics); legal personnel (e.g., where the digital twin 13734 can present compliance information and highlight legal risks (e.g., safety violations, or where status information about operations indicates a potential breach of the company's contracts (e.g., inability to deliver contractually required output)); inventory managers; procurement personnel; and the like. Additionally, business executives, such as CEOs, CTOs, COOs, CIOs, CDOs, and CMOs, can interact with the digital twin 13734 representing an entire factory or set of factories to identify potential risks and opportunities, including understanding the interaction of elements and/or the contribution of elements involving the industry entity 13736 to the overall operations, strategy, etc. of the enterprise. The digital twin 13734 may be updated based on data from the sensor kit 28700 so that the digital twin 13734 is maintained in substantially real time.

In various embodiments, the interface and dashboard 13738 can display sensor information collected from the sensor kit 28700. Information elements about the industrial environment 13704 or industrial setting 28720 can be presented as an overlay (e.g., metrics or symbols are presented on top of a point cloud, photograph, or 3D representation of a unit in a 3D interface), in their native form (e.g., a point cloud is represented), in a 3D visualization (e.g., the interface treats the elements as 3D geometric elements), etc.

Provided herein is a system including: a set of industrial digital twins of a set of industrial entities supported by a set of data processing platforms having intelligent processing capabilities; a set of mobile data collection systems that facilitate collection of data from and regarding the set of industrial entities; a set of simultaneous location and mapping systems that provide a set of scans of a set of industrial environments in which the set of industrial entities are located; and an edge computing system that provides connectivity among the set of mobile data collection systems, the set of simultaneous location and mapping systems, the data processing platforms, and the control systems of the set of industrial entities. The edge computing system provides connectivity among the set of mobile data collection systems, the set of simultaneous location and mapping systems, the data processing platforms, and the control systems of the set of industrial entities, wherein information collected by the mobile data collection systems is automatically associated with a set of visual representations of the industrial entities obtained via the simultaneous location and mapping systems in the set of industrial digital twins. In an embodiment, the system provides real-time updates of the digital twins based on data collected for the industrial entities. In an embodiment, the set of digital twins includes a digital twin of a single machine. In an embodiment, the set of digital twins includes a system digital twin. In an embodiment, the set of digital twins includes a workflow digital twin.

In an embodiment, the set of digital twins includes a worker digital twin. In an embodiment, the set of digital twins includes a configuration digital twin that displays the configuration of industrial entities in an industrial environment. In an embodiment, the set of digital twins includes a logical digital twin that represents entities and relationships in the industrial environment. In an embodiment, the digital twin includes a set of interfaces. In an embodiment, the set of interfaces includes an application programming interface. In an embodiment, the set of interfaces includes a touchscreen interface. In an embodiment, the set of interfaces includes a graphical user interface. In an embodiment, the set of interfaces includes an analytics dashboard interface.

In an embodiment, the interface presents a metric of the probability of an unplanned shutdown of at least one of a machine, a process, a system, a factory, and a workflow. In an embodiment, interacting with the set of interfaces of the industrial digital twin results in configuring data collection. In an embodiment, interacting with the set of interfaces of the industrial digital twin results in configuring intelligence by an edge system. In an embodiment, interacting with the set of interfaces of the industrial digital twin results in configuring intelligence by a set of intelligence systems of a data processing platform. In an embodiment, interacting with the set of interfaces of the industrial digital twin results in configuring control of a set of industrial entities. In an embodiment, the system is configured to interoperate with an enterprise resource planning system. In an embodiment, the system is configured to interoperate with a maintenance and service system.

The methods and systems described herein may be used to provide hydrogen directly from a hydrolysis device for certain applications, including those that do not require the introduction of oxygen. In such embodiments, where only hydrogen gas may be required, hydrogen may be produced and delivered directly for real-time use, such as for heating burners, industrial heating processes such as welding and brazing, and any other use case requiring direct-use hydrogen. Other applications include coating, tooling, extrusion, and drying. The methods and systems described herein can produce high-quality hydrogen gas for applications requiring high-quality hydrogen gas, such as laser cutting. Other applications include producing hydrogen gas in combination with other combustible gases for operations such as generating a flame suitable for welding or supplying an oxygen-hydrogen torch.

In applications where both separated hydrogen and separated oxygen may be needed for different purposes, such as generation, storage, distribution, and/or heating, e.g., cooking systems, can independently direct both gases to the appropriate process application. For example, in a submarine electrolyzer, hydrogen may be used to power the burners and oxygen may be used to power the submarine's air circulation system. In yet other embodiments, the oxygen and hydrogen separated during the hydrolysis process may need to be recombined under a protocol that produces the desired combination and rate of oxygen and hydrogen combination. One such example is oxygen-hydrogen welding.

In embodiments, other examples of time-shifted uses of electrolyzer products that benefit from and/or include hydrogen storage can include storing hydrogen in an uncompressed state, a gaseous state, a compressed liquid state, or a combination thereof in small tanks that are part of the cooking system or other industrial system, in larger tanks on or near the cooking system, or transporting it to a very large holding tank at an unlocated facility. A further example of a hydrogen storage technique involves absorption of hydrogen by a substrate. The substrate can then be transported to a small tank or other substrate storage facility that is part of the cooking system, a larger tank on or near the cooking system, a very large holding tank at an unlocated facility, or distributed storage across multiple small, medium, and large storage facilities that facilitate localized access to the stored energy. At the appropriate time, the substrate can be heated to convert the hydrogen back to its original gaseous state.

Cooking and other heating systems that may use hydrogen as one of multiple fuel sources may participate in automatically selecting among the fuel sources. These systems may include processing capabilities connected to various sources that can provide data on factors useful to consider when deciding which energy source to select. The decision on which energy source to select may be based on a single factor, such as the current price of one or more energy sources. The energy source that provides sufficient energy at the lowest current price may be selected. In embodiments, the cooking or other heating system may automatically configure itself to the selected energy source under computer control. For example, if hydrogen is selected, the connection to the hydrogen source may be enabled and connections to other sources may be disabled. Similarly, burners, heater controls, heat and safety profiles, cooking times, and various other factors may automatically adjust based on the selected energy source. If, during cooking or heating, a different energy source (e.g., electricity) is found to be less expensive, the system may automatically reconfigure to use the other energy source. By using an electric heater instead of a gas heater, cooking or heating operations can continue with minimal interruption. Cooking/heating processes using such hybrid energy sources may require different protocols to complete the cooking/heating process based on the new energy source.

Alternatively, the automated selection of a fuel source may be based on multiple factors. These factors may be applied to a fuel source selection algorithm that can process some of the factors individually, as a group, or in combination. Examples of factors include the energy sources available to the cooking/heating system and the prices of other energy sources, including those not directly available. As such, the selection of an energy source may be driven by other considerations, such as which energy source is environmentally beneficial. In embodiments, the automated selection of an energy source may be based, at least in part, on the expected availability of the energy source. In embodiments, predictions of energy outages, such as brownouts, may be based on various factors, including direct knowledge of scheduled brownouts. Such predictions may also be based on prior experience regarding the availability of energy sources, which may be applied to machine learning algorithms to provide predictions of future energy availability. Other factors that may be applied to an algorithm for automatically determining an energy source may include the availability of water sources for producing hydrogen, the availability of renewable energy (e.g., based on forecasts of solar, wind, etc.), the level and/or intensity of energy need, predictions of the level of need for a future period, such as the next 24 hours, etc. If the projection of future needs includes large fluctuations in demand over that period, each peak in demand can be analyzed separately, and average demand values or other derivatives can be used to determine the weighting of various energy sources.

In addition to selecting energy for direct cooking and heating applications, the selection of energy for operating a hydrolysis device to produce hydrogen may be automated. Energy sources that may be included in such an automated selection process may include solar energy, wind energy, hydrogen energy, sulfur dioxide, electricity (e.g., from the power grid), natural gas, etc. In embodiments, an algorithm that may facilitate the automated energy selection may receive information about each energy source, such as availability, cost, and efficiency, and process it by, for example, comparing the information to determine which energy source is best suited to operate the hydrolysis device for a given period of time. In this example, the algorithm may favor energy sources that are highly reliable, highly available, and low cost over energy sources that are less reliable, less available, and more costly. In embodiments, a combination of these three factors may result in the selection of a particular source. For example, if the demand for reliable energy at a particular time is weighted higher than price, a more costly energy source may be automatically selected because it is more reliably available. The automated fuel selection algorithm may also generate recommendations for fuel selection, with a human or other automated process making the selection. As an example, an automated fuel selection algorithm may recommend a fuel that is lower in cost but somewhat less reliable than other sources. However, when considering weighting or other aspects of the available information about the source, such a recommendation may meet the algorithm's acceptance criteria.

The methods and systems described herein may also relate to methods and systems for automatically selecting an energy source, such as methods for determining optimal use of renewable energy (e.g., solar, wind, geothermal, hydroelectric, etc.) or non-renewable fuels. In embodiments, the selection of an energy source to power an on-site standalone cooking or heating system may be based on various factors, including access to and distance to a renewable energy source as a direct, primary source of supply to the cooking system. For example, data on the production costs of hydroelectric renewable energy may support the selection, but hydroelectric renewable energy may not be the optimal use because the distribution network may not be in place or a substantial premium may be charged for access to that particular renewable energy source.

In embodiments, other factors include the price and quantity of electricity required to power the cooking system and/or electrolyzer, and the ability of the energy source to match the demand and availability of generated power needed for both sustained and short-term periods of use. In embodiments, other factors that may influence the automated energy source selection process include the availability and recycle of excess heat from the cooking system and/or other nearby industrial facilities. In embodiments, excess heat may include waste heat, sulfur dioxide by-product, etc., that can be used to generate heat via a heat exchange process. In embodiments, another set of criteria for determining the optimal energy source for use by a cooking system such as those described herein may include comparing the need for short-term access to electricity at any time of day with the timing and availability of power sources, such as nearby power sources, to limit the timing of demand for electricity. The waste heat by-product sulfur dioxide may be used in a heat transfer process to recover heat from sulfur dioxide gas, or may be applied directly to the hydrolyzer system to produce hydrogen. In embodiments, sulfur dioxide gas can be applied directly to a hydroriser system to generate hydrogen, which can be used as an environmental conservation tool by reducing the amount of sulfur dioxide gas, or the hydrogen generated can be used to fume and remove garbage, or to generate electricity.

In embodiments, external systems, such as information systems, may be associated with or connected to the hydrogen production, storage, distribution, and usage systems described herein. The information system may receive information from all aspects and system processes, including energy selection (e.g., automated energy selection), including actual results compared to predicted results; energy consumption; hydrogen production by energy source type (e.g., solar, hydroelectric, wind, flue gas, including use of sulfur dioxide); hydrogen purification processes; hydrogen storage (including compression, natural storage, substrate injection-based, etc.); hydrogen distribution; uses; combinations with other fuel sources (e.g., hydrogen with other combustible energy media); and hydrogen applications, including timing, cost, application environment, etc.

In embodiments, communication with external systems may occur via the exchange of messages, which may facilitate remote monitoring, remote control, etc. By way of example, the messages may include information regarding the source, destination, and purpose of the message (e.g., control, monitoring, etc.), recommended actions to be taken, alternative actions to be taken, actions to avoid, etc.

In embodiments, methods and systems related to hydrogen production, storage, distribution, and use may include, associate with, or integrate improvement capabilities that provide continuous improvement to system performance, quality, and the like. In embodiments, improvement capabilities include process and output quality, including process control and heat recovery, flow control and precision control, improved safety, reliability, service availability, and output consistency. Other features that may be provided and/or integrated into the hydrogen-based systems described herein may include data collection, analysis, and modeling for improvement; data security, cybersecurity, network security to prevent external attacks on control systems, etc.; and monitoring and analysis to facilitate preventive maintenance and repair.

In embodiments, the methods and systems described herein may include integration with and/or access to data processing systems that may also have access to third-party data. By monitoring data collected from sensors, time of day, weather conditions, and other data sources may be used in conjunction with specific rule sets to trigger activation and/or deactivation of hydrogen-using (e.g., cooking) operations. In embodiments, data may be accumulated in a continuous feedback loop that captures various metrics related to operations such as cooking operations. In embodiments, analysis and control of such system activation may take into account the actual requirements and timing of when the cooking system needs to be used (e.g., when preparing a meal such as breakfast, or when heating is required for an industrial operation such as the start of a new job).

In embodiments, data collection, monitoring, process improvement, quality improvement, and the like may also be performed during operation of such a system. In one example, when a cooking system is activated, the system may be able to determine the best way to receive the heat needed to run the process at hand at that particular moment. Receiving the heat needed to run the process may be selected from a variety of heat sources, including in-line hydrogen generation, stored hydrogen consumption, combined energy utilization, and the like. In embodiments, cooking elements that mix hydrogen and non-hydrogen heat burners may be automatically controllable, such that the system can automatically decide to use one or the other heat source, or a combination thereof, using, for example, machine learning and continuous monitoring.

Further, in this example, the smart cooktop may include burners for hydrogen and liquid propane. In embodiments, methods and systems for cooking operations may automatically activate the appropriate burner (e.g., hydrogen burner or liquid propane burner) based on the fuel selection. Operation of such a cooking or heating system may be performed by a computer-enabled controller that can process factors including time of day, energy costs at spot prices for each alternative, the length of the process involved, meeting 100% environmental protection requirements, potentially hazardous use of flames depending on the location of the cooking system, and other security features. Data analysis can be performed on all aspects of the system for continuous improvement of operational control. As an example, if the electrolyzer is not operating, a sensor can capture information about the liquid propane burner being used. In embodiments, this single data acquisition example illustrates that while it is desirable to collect information on all operational aspects to avoid missing information, practical considerations allow for more focused data collection and analysis. In embodiments, all activity and behavior by the cooking system and heating elements can be captured, recorded, measured, and used to inform actions such as quality improvements.

In embodiments, information may be provided about one or more deployments of the cooking system to facilitate self-improvement and real-time decision-making. In embodiments, captured information may also be stored and used, such as for time series analysis, to determine patterns that may indicate opportunities for improvement. In embodiments, data obtained over multiple deployments may be used to create and update models that may be used, such as for computer-generated simulations. These models may be applied to design processes, etc. In embodiments, continuous improvement modifications may be stimulated by machine-to-machine learning programs, human improvement efforts, improved and/or modified instructions, etc.

Systems and methods for using wearable devices for mobile data collection within an industrial IoT data collection environment will now be described with reference to the figures. See FIGS. 161 through 164. Referring first to FIG. 161, a data collection system may include one or more wearable devices configured to operate as mobile data collectors within an industrial IoT data collection environment. For example, the one or more wearable devices may transmit data, receive data, transmit commands, receive commands, be under control, communicate control, or otherwise communicate with the industrial IoT data collection, monitoring, and control system 10. Disclosed herein are methods and systems for data collection using wearable devices, including a single wearable device having a single sensor for recording condition-related measurements (alternatively, "condition measurements" or "condition measurements," as described below) within an industrial IoT data collection environment. A single wearable device having multiple sensors for recording condition-related measurements within an environment for industrial IoT data collection, multiple wearable devices each having a single sensor for recording condition-related measurements within an environment for industrial IoT data collection, and multiple wearable devices each having one or more sensors for recording condition-related measurements within an environment for industrial IoT data collection. For example, the wearable device may be a wearable haptic or multi-sensor user interface for an industrial sensor data collection apparatus with vibration, heat, electricity, and/or sound outputs, as well as any other suitable output. In another example, the wearable device may be any other suitable device, component, unit, or other computational surface having a tangible form and configured for or otherwise usable for placement on a person in an industrial environment, regardless of the duration of such use. For example, the wearable device may be a garment or a device included in a garment. In another example, the wearable device may be an accessory item or a device included in an accessory item. Examples of apparel to which a wearable device can be attached include, but are not limited to, shirts, vests, jackets, pants, shorts, gloves, socks, shoes, protective outerwear, underwear, undershirts, tank tops, etc. Examples of accessories to which a wearable device can be attached include, but are not limited to, hats, helmets, glasses, goggles, visual safety accessories, masks, chest bands, belts, lift support wear, antennas, wristbands, rings, necklaces, bracelets, watches, brooches, neck straps, backpacks, front packs, arm packs, leg packs, lanyards, key rings, headphones, hearing safety accessories, earphones, earpieces, etc. Regardless of the specific form, a wearable device according to the present disclosure includes one or more sensors for recording environmental condition-related measurements for industrial IoT data collection. For example, one or more sensors of a wearable device described herein can measure conditions related to equipment in an industrial IoT environment or can measure conditions related to the industrial IoT environment itself. As used herein, condition measurements recorded using sensors (e.g., of a wearable device or other suitable data collector) refer to information related to a subject in an environment for Industrial IoT data collection. That is, the information is directly or indirectly indicative of the subject's condition or may be used to otherwise indicate the subject's condition. For example, the information may indirectly indicate the subject's condition where it is processed or otherwise used to identify or determine the subject's condition. As used herein, recording a measurement using a sensor (e.g., of a wearable device or other suitable data collector) refers to the use of the sensor to make the measurement available for further processing. For example, recording a measurement using a sensor may refer to one or more of generating data indicative of the measurement, transmitting a signal indicative of the measurement, or obtaining the measurement.

A number of wearable devices 14000 are deployed within the industrial IoT data collection environment. In some scenarios, the wearable devices 14000 may be wearable devices issued by an operator of the industrial IoT data collection environment. Alternatively, the wearable devices 14000 may be wearable devices owned by workers selected to perform tasks within the industrial IoT data collection environment. As shown in FIG. 161 , the wearable devices 14000 may include any combination of a single wearable device with a single sensor 14002, a single wearable device with multiple sensors 14004, a combination of wearable devices each with a single sensor 14006, and a combination of wearable devices each with one or more sensors 14008. However, in embodiments, the wearable devices 14000 may include different wearable devices. For example, in embodiments, wearable device 14000 may omit combinations of wearable devices that include a single sensor 14006 and/or combinations of wearable devices that include one or more sensors 14008. For example, wearable device 14000 may be limited to individual wearable devices rather than combinations of wearable devices that provide combined, improved, or otherwise different functionality compared to each of the constituent wearable devices taken individually. In another example, in embodiments, wearable device 14000 may omit a single wearable device having a single sensor 14002 and/or a single wearable device having multiple sensors 14004. For example, wearable device 14000 may be limited to combinations of wearable devices rather than individual devices (e.g., if a particular combination of wearable devices is identified as valuable in a particular context, such as for recording measurements related to specific conditions within an environment for industrial IoT data collection). Communication and other transfer of data between the wearable device 14000 and devices receiving output from the wearable device, or otherwise between sensors within the wearable device 14000 and devices receiving output from those sensors, may be wireless or wired and may include standard communication technologies such as 802.11 and 900 MHz wireless systems, Ethernet, USB, Firewire, etc.

In embodiments, different wearable devices 14000 may be configured to record status-related measurements of some or all of the targets (e.g., devices or equipment). For example, some of the wearable devices 14000 may be configured to record status-related measurements of the targets based on vibrations measured for some or all of the targets. The vibrations measured for the targets may refer to, but are not limited to, the frequency at which all or some of the targets vibrate, waveforms obtained from vibration envelopes associated with the targets, changes in vibration levels, etc. In another example, some of the wearable devices 14000 may be configured to record status-related measurements of the targets based on temperatures measured for some or all of the targets. The temperatures measured for the targets may refer to, but are not limited to, the internal or external temperatures of all or some of the targets, the operating temperatures of the targets, temperatures measured within an area surrounding the targets, etc. In another example, some of the wearable devices 14000 may be configured to perform status-related recordings of the targets based on electrical or magnetic outputs measured for some or all of the targets. The measured electrical or magnetic output for a target may refer to, but is not limited to, the level or change of an electromagnetic field associated with the target, the amount of electricity or magnetic material output from or otherwise emitted by the target, etc. In another example, a portion of the wearable device 14000 may be configured to record a condition-related measurement for a target based on an acoustic output measured for some or all of the targets. The measured acoustic output for a target may refer to, but is not limited to, audible or inaudible frequencies corresponding to sound waves generated by or associated with the target, sound waves emitted due to changes in the target's motion, etc. In another example, a portion of the wearable device 14000 may be configured to record a condition-related measurement for a target based on vibration, temperature, electrical or magnetic, or non-acoustic output measured for some or all of the targets.

Alternatively, or in addition, different wearable devices 14000 may be configured to record some or all condition-related measurements of particular types of targets within an environment for industrial IoT data collection. For example, some of the wearable devices 14000 may be configured to record some or all condition-related measurements from agitators (e.g., turbine agitators), airframe control surface vibrators, catalytic reactors, compressors, etc. In another example, some of the wearable devices 14000 may be configured to record some or all condition-related measurements from conveyors and lifters, waste systems, drive trains, fans, irrigation systems, motors, etc. In another example, some of the wearable devices 14000 may be configured to record some or all condition-related measurements from pipelines, electric powertrains, production platforms, pumps (e.g., water pumps), robotic assembly systems, thermal heating systems, trucks, transmission systems, turbines, etc. In an embodiment, the wearable devices 14000 may be configured to record some or all condition-related measurements of a particular type of industrial environment. For example, industrial environments having targets whose conditions are measured using the wearable device 14000 may include, but are not limited to, manufacturing environments, fossil fuel energy production environments, aerospace environments, mining environments, construction environments, marine environments, maritime environments, submarine environments, wind energy production environments, hydroelectric energy production environments, nuclear energy production environments, etc., oil drilling environments, oil pipeline environments, other suitable energy product environments, other suitable energy pathway or transmission environments, other suitable industrial environments, factories, aircraft such as airplanes, distribution environments, energy source extraction environments, marine exploration sites, underwater exploration sites, assembly lines, warehouses, power generation environments, hazardous waste environments, etc.

A combination of wearable devices each having a single sensor 14006 and/or a combination of wearable devices each having one or more sensors 14008 may represent a combination of wearable devices selected for use together in an industrial IoT data collection environment. For example, a combination of wearable devices each having a single sensor 14006 and/or a combination of wearable devices each having one or more sensors 14008 may represent all or part of an industrial uniform worn by a worker performing one or more tasks in an industrial IoT data collection environment. For example, each combination of wearable devices each having a single sensor 14006 and/or a combination of wearable devices each having one or more sensors 14008 may include each one of multiple wearable devices worn by a user (e.g., one hat, one shirt, one pair of pants, one shoe, one vest, one necklace, one bracelet, one backpack, or more or fewer wearable devices). Embodiments of the present disclosure may contemplate industrial uniforms that include other possible combinations of wearable devices, such as combinations of wearable devices each having a single sensor 14006 and/or combinations of wearable devices each having one or more sensors 14008.

In embodiments, the use of multiple sensors in combination, either as a combination of wearable devices each equipped with a single sensor 14006 and/or as a combination of wearable devices each equipped with one or more sensors 14008, can introduce expanded or additional functionality for Industrial IoT data collection. Accordingly, in some of these embodiments, the industrial uniform may include functionality beyond that provided by the individual sensors integrated within the industrial uniform. For example, the outputs of wearable devices having sensors for recording measurements related to the condition of the same target may be preprocessed by central processing software or hardware aspects integrated within or otherwise associated with the industrial uniform (e.g., a collective processing heart, as described below). For example, the central processing software or hardware aspects integrated within or otherwise associated with the industrial uniform may process the outputs of multiple wearable devices to determine whether the outputs are the same for a particular observed measurement of the target. If one of the outputs deviates from the other outputs by more than a threshold value, the deviating output may be discarded. For example, the discarded output may represent output generated using a sensor that experienced interference or other problems while recording measurements related to the target's condition. In another example, central processing software or hardware integrated within or otherwise associated with an industrial uniform may process different types of output from multiple wearable devices (e.g., recorded based on different targets or different condition-related measurement types (e.g., vibration vs. temperature)) to determine or identify the target's condition. For example, a condition may be indicated by a combination of multiple outputs. In such a scenario, a first output from a first wearable device may be combined or otherwise processed with a second output from a second wearable device to determine or identify the target's condition. Different combinations of wearable devices may be identified as different industrial uniforms, each of which may have the same or different capabilities with respect to recording types of condition-related measurements for the target. In yet another example, the integration of multiple wearable devices within an industrial uniform enables simultaneous or substantially simultaneous processing of condition-related measurements recorded using the wearable devices.

Condition-related measurements taken using the wearable device 14000 may be available via the network 14010 (e.g., without the need for an external network). The network 14010 may be a MANET (e.g., MANET 20 shown in FIG. 2 or any other suitable MANET), the Internet (e.g., Internet 110 shown in FIG. 3 or any other suitable Internet), or any other suitable type of network, or any combination thereof. For example, the network 14010 may be used to receive condition-related measurements recorded using the wearable device 14000. The network 14010 may then be used to transmit some or all of those received condition-related measurements to other components of the data collection system 102. For example, the network 14010 may be used to transmit some or all of those received condition-related measurements to a data pool 14012 (e.g., data pool 60 shown in FIG. 2 or any other suitable data pool) for storage of those received condition-related measurements. In another example, the network 14010 may be used to transmit some or all of the received condition-related measurements to one or more servers 14014 corresponding to the environment for industrial IoT data collection. The server 14014 may include aspects of one or more hardware or software servers. For example, the server 14014 to which the received condition-related measurements are transmitted may include an intelligent system 14016 that processes the received condition-related measurements. The intelligent system 14016 may process the received condition-related measurements in any suitable manner, including using artificial intelligence processes, machine learning processes, and/or other cognitive processes to identify information within or otherwise related to the received condition-related measurements. In an embodiment, after processing the received condition-related measurements, the server 14014 to which the received condition-related measurements are transmitted may transmit the processed information or data indicative of the processed information to another system (e.g., for storage or analysis). The data indicative of the processed information from the server 14014 may include, for example, the output or other results of the artificial intelligence processes, machine learning processes, and/or other cognitive processes.

In embodiments, some or all of the wearable devices 14000 may include an intelligent system 14018 for processing condition-related measurements recorded using those wearable devices 14000 before transmitting those recorded condition-related measurements (e.g., via the network 14010) or any other suitable communication mechanism. For example, some or all of the wearable devices 14000 may integrate artificial intelligence processes, machine learning processes, and/or other cognitive processes to analyze the condition-related measurements recorded thereby. Processing by the intelligent system 14018 of the wearable devices 14000 may be within or represent a pre-processing step of the industrial IoT data collection, monitoring, and control system 10. For example, pre-processing may be selectively performed by certain types of wearable devices 14000 to pre-process the recorded condition-related measurements, e.g., to identify redundant, irrelevant, or unimportant information. In another example, preprocessing may be automated for a particular type of wearable device 14000, e.g., to preprocess the recorded condition-related measurements to identify redundant, irrelevant, or unimportant information. In another example, preprocessing may be selectively performed for a particular type of condition-related measurements recorded by any of the wearable devices 14000, e.g., to preprocess the recorded condition-related measurements to identify redundant, irrelevant, or unimportant information. In another example, preprocessing may be automated for a particular type of condition-related measurements recorded by any of the wearable devices 14000, e.g., to preprocess the recorded condition-related measurements to identify redundant, irrelevant, or unimportant information.

In an embodiment, some or all of the wearable device 14000 may include sensor fusion functionality. For example, the sensor fusion functionality may be embodied as on-device sensor fusion 80. For example, condition-related measurements recorded using one or more analog sensors of the wearable device 14000 (e.g., the analog sensors 82 shown in FIG. 4 or any other suitable sensors) may be processed locally or remotely (e.g., using artificial intelligence, machine learning, and/or other cognitive processes), which may be embodied within the wearable device 14000 itself, within the server 14014, within both, or within any other suitable hardware or software. For example, the output of sensors integrated within the wearable device 14000 may be provided directly to the on-device sensor fusion aspect 80. The sensor fusion functionality may be embodied by a pre-processing step performed prior to the artificial intelligence, machine learning, and/or other cognitive processes. In an embodiment, the sensor fusion functionality may be performed using a MUX. For example, each of a single wearable device having multiple sensors 14004 may include its own MUX for combining condition-related measurements recorded using different individual sensors of the multiple sensors. In another example, some or all of the individual wearable devices in a set of wearable devices, each having one or more sensors 14008, may include their own MUX for combining condition-related measurements recorded using different individual sensors of the multiple sensors. In some such embodiments, the MUX may be internal to the wearable devices. In some such embodiments, the MUX may be external to the wearable devices.

In embodiments, the wearable device 14000 may be controlled within or otherwise connected to and used by the host processing system 112 shown in FIG. 6 (or any other suitable host system). The host processing system 112 may be locally accessible via the network 14010. Alternatively, the host processing system 112 may be remote (e.g., embodied in a cloud computing system) and may be accessible using one or more network infrastructure elements (e.g., access points, switches, routers, servers, gateways, bridges, connectors, physical interfaces, etc.) and/or may use one or more network protocols (e.g., IP-based protocols, TCP/IP, UDP, HTTP, Bluetooth, Bluetooth Low Energy, cellular protocols, LTE, 2G, 3G, 4G, 5G, CDMA, TDSM, packet-based protocols, streaming protocols, file transfer protocols, broadcast protocols, multicast protocols, unicast protocols, etc.). In embodiments, condition-related measurements recorded using wearable device 14000 may be processed using a network coding system or method, which may be embodied internally or externally with respect to host processing system 112. For example, the network coding system may process measurements recorded using wearable device 14000 based on the availability of a network for communicating those recorded condition-related measurements, based on the availability of bandwidth and spectrum for communicating those recorded condition-related measurements, based on other network characteristics, or based on some combination thereof.

In embodiments, condition-related measurements recorded using wearable device 14000 may be retrieved from wearable device 14000 by an upstream device (e.g., a client device or other software or hardware aspect used to review, analyze, or otherwise view the condition-related measurements). For example, wearable device 14000 may not actively transmit the received condition-related measurements (e.g., to server 14014, data pool 14012, or other suitable hardware or software component that receives condition-related measurements recorded using wearable device 14000). Rather, transmission of condition-related measurements from wearable device 14000 may be triggered by a command received at wearable device 14000 (e.g., from server 14014 or from other hardware or software in data collection system 102). For example, a data collection device, which may be fixed within a particular location in the environment or may be movable relative to the environment, may be configured to retrieve condition-related measurements recorded by various wearable devices 14000. For example, the wearable devices 14000 may record condition-related measurements in an environment continuously, periodically, or at other multiple times for industrial IoT data collection. A data collector may send one or more commands at fixed intervals, random times, or otherwise to some or all of the wearable devices 14000 (e.g., to retrieve some or all of the condition-related measurements recorded by those wearable devices 14000 since the last time condition-related measurements were retrieved therefrom). Alternatively, the data collector may send one or more commands at those fixed intervals, random times, or otherwise to a collective processing heart 14020 associated with the wearable devices 14000. For example, the collective processing heart 14020 may be or include a hub for receiving condition-related measurements recorded using some or all of the wearable devices 14000. In another example, the command, when used and processed, causes an individual wearable device 14000 or the collective processing heart 14020 of the wearable devices 14000 to transmit recorded condition-related measurements, or data representative thereof, from the wearable devices 14000. For example, the collective processing heart 14020 may be configured to pull condition-related measurements from some or all of the wearable devices 14000 (e.g., at regular intervals, at random times, or in other manners). The collective processing heart 14020 may then transmit the pulled condition-related measurements from the wearable devices 14000 (e.g., to the server 14014, the data pool 14012, or other hardware or software component selected or otherwise configured to receive the condition-related measurements).

In an embodiment, condition-related measurements recorded using the wearable device 14000 may be transmitted from the wearable device 14000 in response to a request for those condition-related measurements. For example, the collective processing heart 14020 may send requests for recorded condition-related measurements to some or all of the wearable devices 14000 at regular intervals, at random times, or in other ways. The processors of some or all of the wearable devices 14000 to which the request was sent may process the request to determine which condition-related measurements to transmit. For example, data indicating the time of the most recent request for recorded condition-related measurements may be accessed by those processors. The processors may then compare that time with the time a new request is received from the collective processing heart 14020. The processors may then query a data store for condition-related measurements recorded between the two times. The processors may then transmit those condition-related measurements in response to the request. In another example, the processor may identify the most recent set of condition-related measurements recorded using the corresponding wearable device 14000 and transmit those condition-related measurements in response to the request. In another example, a data collector within the data collection system 10 may send the request directly to the wearable device 14000. In yet another example, the data collector may send the request to the collective processing mind 14020. The collective processing mind 14020 may process the request to determine which selected individual wearable devices 14000 were used to record the requested condition-related measurements. The collective processing mind 14020 may then transmit the particular condition-related measurements in response to the request, for example, by querying storage for some or all of the condition-related measurements recorded using those selected individual wearable devices 14000. Alternatively, the collective processing mind 14020 may process the request to determine which condition-related measurements recorded by some or all of the wearable devices 14000 to transmit in response to the request (e.g., based on the time of the request). For example, the collective processing heart 14020 can compare the time of the request with the time of the most recent request for recorded condition-related measurements. The collective processing heart 14020 can then retrieve the condition-related measurements recorded during those times and transmit the retrieved condition-related measurements in response to the request.

In embodiments, condition-related measurements may be pushed from wearable device 14000 to an upstream device (e.g., a client device or other software or hardware aspect used to review, analyze, or otherwise view the condition-related measurements). For example, wearable device 14000 may proactively transmit received condition-related measurements (e.g., to server 14014, data pool 14012, or any other suitable hardware or software component that receives condition-related measurements recorded using wearable device 14000) without such receiving hardware or software component requesting them or causing the wearable device to transmit them upon command. For example, some or all of wearable devices 14000 may transmit condition-related measurements at regular intervals, at random times, immediately upon recording those condition-related measurements, some time after recording those measurements, when it is determined that a threshold number of condition-related measurements have been recorded, or at other suitable times. In some such embodiments, the wearable device 14000 may push recorded condition-related measurements in response to detecting the proximity of the data collection router 14014, either by itself or using a collective processing heart 14020.

For example, referring now to FIG. 162, the collective processing heart 14020 may include a detector 14022 configured to detect the proximity of a target 14024 (e.g., one of the devices 13006 shown in FIG. 134 or any other suitable target) with respect to one or more of the wearable devices 14000. For example, upon such detection, the collective processing heart 14020 may send a signal to one or more of the wearable devices 14000 to record and transmit received state-related measurements at the data collection router 14026. Alternatively, upon such detection, the collective processing heart 14020 may query a data store to obtain state-related measurements and then transmit those received state-related measurements at the data collection router 14026. In either case, the data collection router 14026 forwards the received state-related measurements to the server 14014, the data pool 14012, or any other suitable hardware or software component. In another example, upon such detection, the aggregate processing core 14020 may, for example, send a signal directly to the server 14014, the data pool 14012, or other hardware or software component to bypass the data collection router 14026, or if the data collection router 14026 is omitted.

163, in embodiments, the collective processing heart 14020 may be omitted. In some of these embodiments, the wearable device 14000 may detect the proximity of a target 14024. Upon such detection, the wearable device 14000 may record condition-related measurements (e.g., vibration, temperature, electrical or magnetic output, sound output, etc.) of the target 14024. The recorded condition-related measurements may be transmitted over the network 14010 (e.g., to a data pool 14012, a server 14014, or other suitable hardware or software component). Alternatively, the recorded condition-related measurements may be transmitted to a data collection router 14026, for example, if the network 14010 is unavailable or if the data collection router 14026 is configured to receive and/or preprocess the recorded condition-related measurements from the wearable device 14000. The data collection router 14026 may be one of many data collection routers 14026 deployed throughout the environment for Industrial IoT data collection. For example, the data collection router 14026 may be a data collection router 14026 configured to transmit condition-related measurements recorded specifically for the target 14024.

164, various aspects of the functionality of the intelligent system 14028 used to process the output of the wearable device 14000 are disclosed. In embodiments, the intelligent system 14028 includes a cognitive learning module 14030, an artificial intelligence module 14032, and a machine learning module 14034. The intelligent system 14028 may include additional or fewer modules. The intelligent system 14028 may be, for example, the intelligent system 14018 or the intelligent system 14016 shown in FIG. 161, or may be another intelligent system. Although shown as separate modules, in embodiments, there may be overlap between some or all of the cognitive learning module 14030, the artificial intelligence module 14032, and the machine learning module 14034. For example, the artificial intelligence module 14032 may include the machine learning module 14034. In another example, the cognitive learning module 14030 may include the artificial intelligence module 14032. In embodiments, there is therefore a machine learning module 14034. Wearable device 14000 may include any number of wearable devices. For example, as shown, wearable device 14000 includes a first wearable device 14000A, a second wearable device 14000B, and an Nth wearable device 14000N, where N is a number greater than 2. Intelligent system 14028 receives the outputs of wearable devices 14000A, 14000B, ... 14000N. In particular, one or more of modules 14030, 14032, and 14034 of intelligent system 14028 receive data generated by and output from one or more of wearable devices 14000A, 14000B, ... 14000N. Output from wearable devices 14000A, 14000B, ... 14000N may include, for example, condition-related measurements recorded using wearable devices 14000A, 14000B, ... 14000N (e.g., condition-related measurements of equipment in an environment for industrial IoT data collection). In an embodiment, output from wearable devices 14000A, 14000B, ... 14000N may be processed by all three of modules 14030, 14032, and 14034 of intelligent system 14028. In an embodiment, output from wearable devices 14000A, 14000B, ... 14000N may include, for example, condition-related measurements recorded using wearable devices 14000A, 14000B, ... 14000N (e.g., condition-related measurements of equipment in an environment for industrial IoT data collection). In an embodiment, output from wearable devices 14000A, 14000B, ... 14000N may be processed by all three of modules 14030, 14032, and 14034 of intelligent system 14028. 14000N may be processed by only one of modules 14030, 14032, and 14034 of intelligent system 14028. For example, the particular one of modules 14030, 14032, and 14034 of intelligent system 14028 to use to process the output from wearable devices 14000A, 14000B, ... 14000N may be selected based on the output from wearable devices 14000A, 14000B, ... 14000N. 14000N may be selected based on the wearable device used to generate the output, the equipment measured in generating the output, the value of the output, other selection criteria, etc.

Knowledge base 14036 may be updated based on output from intelligent system 14028. Knowledge base 14036 represents a library or other set or collection of knowledge related to the industrial IoT data collection environment, including equipment in that environment, tasks performed in that environment, personnel skilled in performing tasks in that environment, etc. Intelligent system 14028 may process condition-related measurements recorded using wearable devices 14000A, 14000B, ..., 14000N to facilitate knowledge collection to expand knowledge base 14036. For example, modules 14030, 14032, and 14034 of intelligent system 14028 may process those condition-related measurements against existing knowledge in knowledge base 14036 to update or otherwise modify the information in knowledge base 14036. The intelligent system 14028 can use intelligence and machine learning capabilities (e.g., of the machine learning module 14034 or described elsewhere in this disclosure) to process condition-related measurements and related information based on detected conditions (e.g., conditions reported by the wearable device 14000 and/or conditions provided as training data) and/or condition information (e.g., condition information determined by a machine condition recognition system capable of determining a condition, e.g., information related to an operational condition, an environmental condition, a condition within a known process or workflow, a condition including a fault or diagnostic condition, etc.). This may include optimizing input selection and configuration based on learning feedback from a learning feedback system, which may include providing training data (e.g., from a host processing system or from other data collection systems directly or from the host processing system) and may include providing feedback metrics (e.g., success metrics calculated within an analysis system of the host processing system). Examples of host processing systems, learning feedback systems, data collection systems, and analysis systems are described elsewhere in this disclosure. Thus, the intelligent system 14028 can be used to update the workflow of tasks assigned and performed within the industrial IoT environment based on the output from the wearable devices 14000A, 14000B, ... 14000N.

In embodiments, intelligent system 14028 may include other intelligence or machine learning aspects within any of modules 14030, 14032, and 14034, or otherwise. For example, the intelligent system 14028 may be a YOLO (YOU OnLY LOOK ONCE) neural network, a YOLO Convolutional Neural Network (CNN), a set of neural networks configured to run on or from an FPGA, a set of neural networks configured to run on or from an FPGA and GPU (GRAPHICS PROCESSING UniT) hybrid component, user-configurable serial and parallel flows for hybrid neural networks (e.g., configuring serial and/or parallel flows between neural networks as outputs that can be communicated between the neural networks), a machine learning system for automatically configuring a topology or workflow for a set of hybrid neural networks (e.g., sequential, parallel, dataflow, etc.), a deep learning system for automatically configuring a topology or workflow for a set of hybrid neural networks (e.g., sequential, parallel, dataflow, etc.) based on a training dataset that may or may not use manual configuration (e.g., by a human user). for configuring networks (serial, parallel, data flow, etc.) based on training datasets of outcomes from Industrial IoT processes (e.g., maintenance, repair, service, failure prediction, optimization of the operation of machines, systems of equipment, etc.), or other intelligence or machine learning aspects.

Thus, in embodiments, the output of the wearable device 14000 may be processed using the intelligent system 14028 to add to, remove from, or otherwise modify the knowledge base 14036. For example, the knowledge base 14036 may reflect the following information: The wearable device 14000 may be used to perform one or more tasks within an industrial environment in which targets are located and in which the wearable device 14000 is used. The output from the wearable device 14000 may be used to increase knowledge regarding the nature of an emerging problem with the industrial environment by describing, for example, information regarding the target for which a measurement was recorded, the time and/or date the measurement was recorded, existing or other condition information regarding the target, information regarding the time required to resolve the problem with the target, information regarding how to resolve the problem with the target, information indicating the amount of downtime for the target and other aspects of the respective industrial environment as a result of resolving the problem, an indication of whether the problem should be resolved now, later (or not at all), etc. The intelligent system 14028 may process the output to update existing training data. For example, existing training data can be used to update machine learning, artificial intelligence, and/or other cognitive functions to identify target conditions based on the output of the wearable device 14000.

For example, knowledge base 14036 may include a series of databases or other tables or graphs arranged hierarchically based on the subject or the area of the industrial environment that contains the subject. For example, a first tier of knowledge base 14036 may reference the industrial environment (e.g., a power plant, a manufacturing facility, a mining facility, etc.). A second tier of knowledge base 14036 may reference zones within the industrial environment (e.g., Zone 1, Zone 2, etc., possibly named zones). A third tier of knowledge base 14036 may reference targets within those zones (e.g., within a first zone of a power plant that includes electrical equipment, this may include alternators, circuit breakers, transformers, batteries, exciters, etc., and within a second zone of a power plant that includes turbines, generators, generator magnets, etc., this may include alternators, circuit breakers, transformers, batteries, exciters, etc.). Knowledge base 14036 may be updated based on the output of intelligent system 14028, by manual data entry by a user, or both. For example, workers in a power plant may be given one or more wearable devices (e.g., wearable device 14000). Upon approaching a turbine, one of the wearable devices 14000, which has a sensor for recording vibration measurements, may determine that the turbine is vibrating at a particular rate. The output of the wearable device is processed by the intelligent system 14028, such as by comparing the output to a set of known data for the turbine. For example, the intelligent system 14028 may query data from a knowledge base 14036 that indicates: past measurements recorded regarding the vibration of that turbine in that particular power plant; the intelligent system 14028 may then determine whether the new output from the wearable device is consistent with or deviates from the data in the knowledge base 14036; if the new output deviates from the data in the knowledge base, the intelligent system 14028 may update the data in that portion of the knowledge base 14036 to reflect the new output. Alternatively, updating of knowledge base 14036 may be delayed until, for example, after a threshold number of deviant power measurements have been recorded to prevent erroneous power outputs from being used to correct the understanding of the turbine's operation.

Disclosed herein is a system for data collection in an industrial environment that integrates wearable devices. As used herein, wearable device integration refers to the use of a wearable device for a specific or general purpose. For example, wearable device integration described with respect to the functionality or configuration of a system may refer to the use by that system of a wearable device 14000 and/or the hardware and/or software used in conjunction with the wearable device 14000 for data collection within an industrial IoT environment, as shown, for example, in FIGS. 161 through 164. Such wearable device integration refers to the use of one or more wearable devices 14000. For example, a system disclosed herein as including wearable device integration may include the integration of one or more of a shirt, a vest, a jacket, a pair of pants, a pair of shorts, gloves, socks, shoes, protective outerwear, underwear, an undershirt, a tank top, a hat, a helmet, eyeglasses, goggles, and a visual safety accessory. Examples of articles (e.g., clothing and/or accessory articles) that include such other types of wearable devices include masks, chest bands, belts, lift support wear, antennas, wristbands, rings, necklaces, bracelets, watches, brooches, neck straps, backpacks, front packs, arm packs, leg packs, lanyards, key chains, headphones, hearing protection accessories, earbuds, earphones, or other types of wearable devices or articles.

In an embodiment, a system for data collection in an industrial environment is disclosed that integrates a wearable device and uses an analog crosspoint switch to collect a variable group of analog sensor inputs.

In an embodiment, a system for data collection in industrial environments is disclosed that has IP front-end signal conditioning on a multiplexer to integrate wearable devices and improve signal-to-noise ratio.

In an embodiment, a system for data collection in an industrial environment with multiplexer continuous monitoring alarm functionality integrated with a wearable device is disclosed.

In one embodiment, a data collection system for industrial environments that integrates wearable devices is disclosed, using a distributed CPLD chip with multiple MUXs and a dedicated bus for logical control of the data collection units.

In an embodiment, a system for data collection in an industrial environment is disclosed that has high amperage input capability using solid-state relays and a design topology that integrates wearable devices.

In an embodiment, a system for data collection in an industrial environment is disclosed that has the ability to power down at least one of an analog sensor channel and a component board that integrates a wearable device.

In an embodiment, a system for data collection in industrial environments is disclosed that integrates a wearable device with triggers and unique electrostatic protection for vibration inputs.

In an embodiment, a system for data collection in an industrial environment is disclosed that has an accurate voltage reference for A/D zero reference integrated into a wearable device.

In an embodiment, a system for data collection in industrial environments is disclosed that integrates a wearable device with a phase-locked loop bandpass tracking filter to obtain low-speed RPM and phase information.

In one embodiment, a data collection system for industrial environments is disclosed that uses an on-board timer integrated with a wearable device to digitally derive phase for input and trigger channels.

In an embodiment, a system for data collection in an industrial environment is disclosed that has a peak detector for autoscaling that is routed to a separate analog-to-digital converter for peak detection integrated into a wearable device.

In an embodiment, a system for data collection in an industrial environment is disclosed that has the routing of raw or buffered trigger channels to other analog channels integrating a wearable device.

In an embodiment, a system for data collection in industrial environments is disclosed that uses higher input oversampling for a delta-sigma A/D for a lower sampling rate output to integrate with wearable devices and minimize AA filter requirements.

In one embodiment, a data collection system for industrial environments is disclosed that uses a CPLD as a clock distributor for a delta-sigma analog-to-digital converter to achieve lower sampling rates without the need for digital resampling associated with integration into wearable devices.

In an embodiment, a system is disclosed for data collection in industrial environments with long blocks of data at a high sampling rate, as opposed to multiple data sets captured at different sampling rates, integrating wearable devices.

In one embodiment, a data collection system for industrial environments is disclosed that stores calibration data with maintenance history on-board in a card set integrated with a wearable device.

In an embodiment, a system for data collection in industrial environments is disclosed that has rapid route creation capabilities using hierarchical templates that integrate wearable devices.

In an embodiment, a system for data collection in an industrial environment is disclosed that has intelligent management of a data collection band integrated with a wearable device.

In an embodiment, a system for data collection in an industrial environment is disclosed that uses a neural net expert system for intelligent management of a data collection band integrated with a wearable device.

In an embodiment, a system for data collection in an industrial environment is disclosed that integrates wearable devices and uses a database hierarchy for sensor data analysis.

In an embodiment, a system for data collection in an industrial environment is disclosed that includes an expert system with intelligent data collection bands integrated with wearable devices and an expert system GUI graphical approach for defining diagnostics.

In an embodiment, a system for data collection in an industrial environment is disclosed that has a graphical approach for back-calculation definition that integrates wearable devices.

In an embodiment, a system for data collection in an industrial environment is disclosed that includes a proposed bearing analysis method involving the integration of wearable devices.

In an embodiment, a system for data collection in industrial environments is disclosed that incorporates wearable device integration and transient signal analysis to detect and analyze torsional vibrations.

In embodiments, a system for data collection in industrial environments is disclosed that has improved integration using both analog and digital methods, along with the integration of wearable devices.

In an embodiment, a system for data collection in industrial environments is disclosed that has adaptive scheduling technology for continuous monitoring of analog data in local environments integrating wearable devices.

In an embodiment, a system for data collection in an industrial environment with data acquisition parking functionality involving the integration of wearable devices is disclosed.

In an embodiment, a data collection system for industrial environments is disclosed that has a self-sufficient data collection box that integrates a wearable device.

In an embodiment, a system for data collection in an industrial environment with SD card storage integrated into a wearable device is disclosed.

In an embodiment, a system for data collection in industrial environments is disclosed that has enhanced on-board statistical capabilities for continuous monitoring integrating wearable devices.

In an embodiment, a system for data collection in industrial environments is disclosed that uses ambient noise, local noise, and vibration noise for prediction, integrating wearable devices.

In an embodiment, a system for data collection in an industrial environment is disclosed that has a smart route that changes route based on input data or alarms, simultaneously obtaining dynamic data for analysis or correlation through the integration of wearable devices.

In an embodiment, a system for data collection in an industrial environment with smart ODS and transfer capabilities that integrates wearable devices is disclosed.

In an embodiment, a system for data collection in an industrial environment is disclosed that has a hierarchical multiplexer that integrates a wearable device.

In an embodiment, a system for data collection in an industrial environment with discriminatory sensory overload integrating a wearable device is disclosed.

In an embodiment, a system for data collection in an industrial environment is disclosed that includes RF identification and an inclinometer integrated with a wearable device.

In an embodiment, a system for data collection in industrial environments with continuous ultrasound monitoring integrated with a wearable device is disclosed.

In an embodiment, a system for data collection in industrial environments with cloud-based machine pattern recognition based on the fusion of remote analog industrial sensors integrated with wearable devices is disclosed.

In an embodiment, a system for data collection in an industrial environment is disclosed that has cloud-based machine pattern analysis of status information from multiple analog industrial sensors to provide predictive status information for an industrial system integrating wearable devices.

In an embodiment, a system for data collection in an industrial environment is disclosed that has a cloud-based policy automation engine for IoT, with the creation, deployment, and management of IoT devices integrating wearable devices.

In an embodiment, a system for data collection in an industrial environment with on-device sensor fusion and data storage for industrial IoT devices integrating wearable devices is disclosed.

In an embodiment, a system for data collection in an industrial environment is disclosed that has a self-organizing data marketplace for industrial IoT data that integrates wearable devices.

In an embodiment, a system for data collection in an industrial environment is disclosed that integrates wearable devices and has self-organization of a data pool based on utilization and/or yield metrics.

In an embodiment, a system for data collection in industrial environments is disclosed that integrates wearable devices and trains AI models based on industry-specific feedback.

In an embodiment, a system for data collection in an industrial environment is disclosed that has a self-organized swarm of industrial data collectors that integrate wearable devices.

In an embodiment, a system for data collection in an industrial environment with an IoT distributed ledger that integrates wearable devices is disclosed.

In an embodiment, a system for data collection in an industrial environment is disclosed that has a self-organizing collector that integrates a wearable device.

In an embodiment, a system for data collection in an industrial environment is disclosed that has a network-sensitive collector that integrates a wearable device.

In an embodiment, a system for data collection in an industrial environment is disclosed that has a remotely organized collector that integrates wearable devices.

In an embodiment, a system for data collection in an industrial environment is disclosed that has self-organizing storage for a multi-sensor data collector that integrates wearable devices.

In an embodiment, a system for data collection in industrial environments is disclosed that has self-organizing network coding for a multi-sensor data network integrating wearable devices.

In an embodiment, a system for data collection in an industrial environment is disclosed having a wearable tactile user interface for an industrial sensor data collector with vibration, heat, electricity, and/or sound outputs integrated with a wearable device.

A system for data collection in industrial environments is disclosed that includes a heat map displaying collected data for AR/VR through the integration of wearable devices.

In an embodiment, a system for data collection in an industrial environment is disclosed that has automatically adjusted AR/VR visualization of data collected by a data collector integrating a wearable device.

In an embodiment, an intelligent cooking system is disclosed that has processing, communication, and other IT components for remote monitoring and control that integrates wearable devices.

In an embodiment, an intelligent cooking system is disclosed that integrates a wearable device and has a hydrogen fuel-producing electrolyzer that operates on a water source to separate the hydrogen and oxygen components.

In one embodiment, an intelligent cooking system is disclosed that includes a low-pressure hydrogen storage system that stores hydrogen produced in an electrolyzer integrated with a wearable device.

In an embodiment, an intelligent cooking system is disclosed that has a fuel control module that integrates a wearable device to automatically control a fuel procurement or blending device based on some measure of past, current, planned, and/or projected consumption or availability.

In one embodiment, an intelligent cooking system is disclosed that includes a solar-powered hydrogen electrolyzer integrated with a wearable device.

In one embodiment, an intelligent cooking system is disclosed that includes a wind-powered hydrogen electrolyzer integrated with a wearable device.

In one embodiment, an intelligent cooking system is disclosed that includes a hydroelectric hydrogen electrolyzer integrated with a wearable device.

In an embodiment, an intelligent cooking system is disclosed that includes an on-demand gas-LPG hybrid burner that dynamically supplies LPG, hydrogen, or other fuels without user input or oversight through the integration of a wearable device.

In an embodiment, an intelligent cooking system is disclosed having a sealed burner chamber that provides heat to a targeted heat zone as a thermal plane integrated with a wearable device.

In an embodiment, an intelligent cooking system is disclosed that has a smart knob with connectivity and local and remote controls for controlling an intelligent cooktop device or other IoT device that integrates a wearable device.

In an embodiment, an intelligent cooking system is disclosed that has a mobile docking facility with integrated power, data communication, and thermal protection for charging mobile devices and wearable devices.

In an embodiment, an intelligent cooking system is disclosed having distributed modules or components located in a cooktop subsystem that integrates a wearable device.

In an embodiment, an intelligent cooking system is disclosed that has a centralized control facility that manages the operation of the cooktop subsystems that integrate wearable devices.

In one embodiment, an intelligent cooking system with remote control functionality that integrates a wearable device is disclosed.

In an embodiment, an intelligent cooking system with automation that integrates wearable devices is disclosed.

In an embodiment, an intelligent cooking system is disclosed that integrates wearable devices and has detectors and sensors for monitoring the status of the cooking system.

In an embodiment, an intelligent cooking system is disclosed that has machine learning to optimize the operation of a cooking system that integrates a wearable device.

In an embodiment, an intelligent cooking system having a mobile application integrated with a wearable device is disclosed.

In one embodiment, an intelligent cooking system is disclosed that has a cloud-based platform that interacts with electronic devices and related ecosystem participants, such as suppliers, content providers, service providers, and regulators, to provide wearable device-integrated value-added services to users of the intelligent cooking system, users of the hydrogen production system, and other ecosystem participants.

In an embodiment, an intelligent cooking system is disclosed that has a recommendation engine for providing recommendations to a user that integrates a wearable device.

In an embodiment, an intelligent cooking system is disclosed that has a notification engine that integrates a wearable device to provide notifications to a user.

In an embodiment, an intelligent cooking system is disclosed having an advertising engine for providing location-based offers to users integrating wearable devices.

In an embodiment, an intelligent cooking system is disclosed that has an interface that enables machine-to-machine or user-to-machine communication with other devices and the cloud to provide data for analysis, monitoring, control, and operation of other devices and systems that integrate with the wearable device.

In an embodiment, an intelligent cooking system is disclosed that has a user interface that facilitates a context- and intelligence-driven personalized experience for computing devices connected to a network centered around the intelligent cooking system that integrates wearable devices.

In embodiments, an intelligent cooking system is disclosed that includes profiling, recording, or analysis of user usage, equipment usage, maintenance and repair history, patterns, or patterns related to malfunctions, energy usage patterns, cooking patterns, and analytics for the deployment, use, and servicing of electrolyzers that integrate wearable devices.

In an embodiment, an intelligent cooking system is disclosed that integrates a wearable device and has a commerce utility for ordering ingredients, components, and materials.

In an embodiment, an intelligent cooking system is disclosed that integrates a wearable device and has a cooking assistance utility to assist a user with cooking tasks.

In an embodiment, an intelligent cooking system is disclosed that integrates wearable devices with health utilities to provide food health indicators, nutritional information, nutritional search functionality, nutritional assistance, and personalized suggestions and recommendations.

In an embodiment, an intelligent cooking system is disclosed that integrates wearable devices and has infotainment utilities for playing music, videos, and/or podcasts.

In an embodiment, an intelligent cooking system is disclosed that has a broadcast utility to enable a personalized cooking channel broadcast from a cooking system that integrates a wearable device.

In an embodiment, an intelligent cooking system is disclosed that includes a smart cooktop and a food survey utility for gathering information from user activity regarding recipes used by users of a region-wide smart cooktop system that integrates wearable devices.

In an embodiment, a system for data collection in an industrial environment is disclosed that has an IoT platform that integrates wearable devices.

In an embodiment, a system for data collection in an industrial environment is disclosed having an IoT data adapter for receiving data input and establishing a connection with one or more available IoT cloud platforms for publishing data for wearable device integration.

In an embodiment, a system for data collection in an industrial environment is disclosed having a condition detector for detecting conditions associated with connection attempts by an IoT data adapter to one or more IoT cloud platforms that integrate wearable devices.

In an embodiment, a system for data collection in an industrial environment is disclosed that has an IoT data adapter with an adaptation engine that integrates a wearable device.

In an embodiment, a system for data collection in an industrial environment is disclosed that integrates wearable devices and uses machine learning to prepare data packets or streams.

In an embodiment, a system for data collection in an industrial environment is disclosed that has a data marketplace that provides a pool of available cloud networking platforms that integrate with wearable devices.

In embodiments, a system for data collection in an industrial environment is disclosed that has a messaging utility that provides messages to a cloud platform user interface indicating the availability of new data sources, and data source integration and usage instructions with wearable device integration.

In an embodiment, a system for data communication between nodes capable of maintaining first and second transmission limits based on received arrival rates and delivery success feedback messages is disclosed, where the system limits the transmission of messages based on the transmission limits integrated with wearable devices.

In an embodiment, a system for data communication between nodes is disclosed that has the ability to restrict the transmission of further messages that have not yet been acknowledged as successfully delivered according to a window size integrated with wearable devices.

In an embodiment, a system for data communication between nodes is disclosed that has the ability to maintain an estimate of the rate of loss events and use it to adjust the rate of redundancy messages through the integration of wearable devices.

In an embodiment, a system for data communication between nodes having an estimated rate of loss events is disclosed, in which the error correction code used to determine the selected redundant message is based on the estimated rate of loss events integrated with wearable devices.

In an embodiment, a system for data communication between nodes that integrates wearable devices and has the ability to apply forward error correction based on received messages describing channel characteristics is disclosed.

In an embodiment, a system for data communication between nodes is disclosed that has the ability to maintain/set a timer based on the occurrence of a broadcast command event and delay the transmission of feedback messages using a timer integrated into a wearable device.

In an embodiment, a system for data communication between nodes is disclosed that maintains/sets a timer based on the occurrence of a delivery command event and has the ability to integrate a wearable device to delay changes to the congestion window size based on the timer.

In an embodiment, a data communication system between nodes is disclosed that maintains/sets a timer based on the occurrence of a delivery order event, delays changes to the congestion window size based on the timer, and integrates a wearable device to cancel changes to the congestion window size when a feedback message indicating successful delivery is received.

In an embodiment, a system for data communication between nodes integrating wearable devices is disclosed that has the ability to configure new connections using maintained data characterizing current/previous connections.

In an embodiment, a data communication system between nodes that integrates wearable devices and has the ability to configure new connections using maintenance data that characterizes the error rates of current/previous connections is disclosed.

In an embodiment, a data communication system between nodes that integrates wearable devices and has the ability to configure new connections using maintained data that characterizes timing variations of current/previous connections is disclosed.

In an embodiment, a data communication system between nodes that integrates wearable devices and has the ability to configure new connections using maintained data characterizing the bandwidth of current/previous connections is disclosed.

In an embodiment, a data communication system between nodes is disclosed that integrates wearable devices and has the ability to configure new connections using persistence data that characterizes the round-trip times of current/previous connections.

In an embodiment, a data communication system between nodes is disclosed that has the ability to configure new connections using maintained data that characterizes communication control parameters of current/previous connections that integrate wearable devices.

In an embodiment, a data communication system between nodes is disclosed that integrates wearable devices and has the ability to configure new connections using maintained data that characterizes forward error correction parameters of current/previous connections.

In an embodiment, a system for data communication between nodes is disclosed having a data store for maintaining data characterizing one or more current or previous data communication connections, and a connection initiation module for initiating new data communication connections based on the maintained data through integration of a wearable device.

In an embodiment, a system for data communication between nodes is disclosed that integrates wearable devices and has the capability to transmit a first subset of data messages over a low-latency data path and a second subset of messages over a high-latency data path.

In an embodiment, a system for data communication between nodes is disclosed that integrates wearable devices and has the capability to transmit a first subset of time-critical data messages over a low-latency data path and a second subset of messages over a high-latency data path.

In an embodiment, a system for data communication between nodes is disclosed that has the capability to transmit a first initial subset of data messages over a low-latency data path and subsequently transmit a second subset of available messages over a high-latency data path through the integration of a wearable device.

In an embodiment, a system for data communication between nodes is disclosed that integrates a wearable device and has the capability to transmit a first subset of acknowledgement messages over a low-latency data path and a second subset of data messages over a high-latency data path.

In an embodiment, a system for data communication between nodes is disclosed that has the capability to transmit a first subset of supplemental/redundant data messages over a low-latency data path and a second subset of data messages over a high-latency data path through the integration of a wearable device.

In an embodiment, a data communication system between nodes is disclosed in which each message has a degree of redundancy associated with it based on the message's position in a transmission order that integrates wearable devices.

In an embodiment, a system for data communication between nodes is disclosed in which the degree of redundancy associated with each message increases as the location of the message decreases with the integration of wearable devices.

In an embodiment, a system is disclosed for data communication between nodes with redundancy associated with each message in response to receiving feedback messages from integrated wearable devices based on the message's position in a transmission order.

In an embodiment, a system for data communication between nodes with a degree of redundancy associated with each message in response to receiving a feedback message based on the message's position in a transmission order is disclosed, where the system adds or removes redundancy messages from a queue based on the feedback messages with wearable device integration.

In an embodiment, a data communication system between nodes is disclosed that has the ability to adjust the number of messages sent on each of multiple different data paths with different communication protocols when it is determined that a data path is changing the flow of messages due to the integration of wearable devices.

In an embodiment, a data communication system between nodes is disclosed that has the ability to adjust the number of messages sent on each of multiple different data paths having different communication protocols when it is determined that the data paths are changing the initial division flow of messages based on previous communication connections for wearable device integration.

In an embodiment, a data communication system between nodes is disclosed that has the ability to modify/add/delete redundancy information associated with encoded data as it travels from node to node over a channel based on channel characteristics integrated with wearable devices.

In an embodiment, a system for data communication between nodes is disclosed that integrates wearable devices and has the ability to transmit FEC packets at an estimated rate of loss events (isolated packet losses or bursts of consecutive packets).

In an embodiment, a system for data communication between nodes with hybrid coding, TCP, and pacing of packet transmissions with integration of wearable devices is disclosed.

In an embodiment, a system for data communication between nodes is disclosed that has a forward error correction code structure that interleaves groups of message packets with parity packets and has coding across overlapping groups of message packets with integration of wearable devices.

In an embodiment, a data communication system between nodes having a variant of TCP that combines delay-based backoff and stable window growth functionality is disclosed, along with the integration of wearable devices.

Systems and methods for using mobile robots and/or mobile vehicles for mobile data collection within an environment for industrial IoT data collection will now be described with reference to FIGS. 165 through 167. Referring initially to FIG. 165, a data collection system may include one or more mobile robots and/or mobile vehicles configured to operate as mobile data collectors within an environment for industrial IoT data collection. For example, the one or more mobile robots and/or mobile vehicles may transmit data, receive data, transmit commands, receive commands, be under control of, communicate control to, or otherwise communicate with the industrial IoT data collection, monitoring, and control system 10. Disclosed herein are methods and systems for data collection using mobile robots and/or mobile vehicles, including mobile robots having one or more mobile data collectors integrated therein, mobile vehicles having one or more mobile data collectors integrated therein, mobile robots having one or more mobile data collectors coupled thereto, and mobile vehicles having one or more mobile data collectors coupled thereto. As used herein, the term "mobile robot" may refer to, but is not limited to, a robotic arm, an android robot, a small or large autonomous robot, a remotely operated robot, a programmably configured robot, or other robotic mechanism. Examples of mobile robots incorporating or coupled with a mobile data collector include, but are not limited to, any of the aforementioned types of mobile robots. As used herein, the term "mobile object" refers to large machinery (e.g., earthmoving machinery), large on-road industrial vehicles, large off-road industrial vehicles, industrial machinery deployed in various environments (e.g., turbines, turbomachinery, generators, pumps, pulley systems, manifolds, valve systems, etc.), earthmoving machinery, ground compaction machinery, transport machinery, hoisting machinery, conveying machinery, aggregate manufacturing machinery, machinery used in concrete construction, piling machinery, construction machinery (e.g., excavators, backhoes, loaders, bulldozers, skid steer loaders, trenchers, motor graders, motor scrapers, etc.), and the like. Examples of mobile vehicles that may be integrated with or coupled to a mobile data collector include crawler loaders, wheel loading shovels, dump trucks, tanker trucks, tippers, trailers, tunnel handling equipment, road rollers, concrete mixers, hot mix plants, road making machines (e.g., compactors), stone crushers, hot mix plants, etc.; road rollers, concrete mixers, hot mix plants, road making machines (e.g., compactors), stone crushers, pavers, slurry sealers, sprayers, plastering machines, large pumps, etc.; material handling equipment (e.g., cranes, conveyors, forklifts, etc.); people transport vehicles (e.g., cars, trucks, carts, personal watercraft, aircraft, etc.); unmanned vehicles (e.g., autonomous air vehicles such as drones, autonomous personal watercraft, autonomous cars and trucks, etc.); and other vehicles (e.g., regardless of size, purpose, and whether or not they use a motor). Examples of mobile vehicles that a mobile data collector may integrate with or to which a mobile data collector may be coupled include, but are not limited to, any suitable mobile vehicle. Regardless of the particular configuration, a mobile robot or vehicle according to the present disclosure includes one or more mobile data collectors that are or include sensors for recording environmental state-related measurements for Industrial IoT data collection. For example, one or more sensors of a mobile data collector described in this disclosure can measure states related to equipment within the Industrial IoT environment or can measure states related to the Industrial IoT environment itself. Examples of mobile data collectors that can be integrated into and/or coupled to a mobile robot or vehicle include, but are not limited to, mobile phones, laptop computers, tablet computers, personal digital assistants, walkie-talkies, radios, long-range or short-range communication devices, flashlights, etc. Sensors of a mobile data collector integrated into and/or coupled to a mobile robot or vehicle may measure one or more of vibration, temperature, electrical output, magnetic output, sound output, or other output of or related to a target within the Industrial IoT environment.

In an embodiment, the fleet 14038 of mobile data collectors includes a number of mobile robots and/or mobile vehicles. The mobile robots and/or mobile vehicles of the fleet 14038 may be mobile robots and/or mobile vehicles native to the Industrial IoT environment or may be mobile robots and/or mobile vehicles brought into the Industrial IoT environment from a different location. As shown in FIG. 165, the fleet 14038 may include different types of mobile robots and/or mobile vehicles, including a mobile robot 14040 having one or more mobile data collectors integrated therein, a mobile vehicle 14042 having one or more mobile data collectors integrated therein, a mobile robot 14044 having one or more mobile data collectors coupled thereto, and a mobile vehicle 14046 having one or more mobile data collectors coupled thereto. In an embodiment, a mobile data collector is integrated into the mobile robot or mobile vehicle in cases where removing the mobile data collector from the mobile robot or mobile vehicle during typical operation of the mobile robot or mobile vehicle would interfere with the normal operation of the mobile robot or mobile vehicle. In an embodiment, a mobile data collector is coupled to a mobile robot or mobile vehicle if the mobile data collector can be detached or otherwise separated from the mobile robot or mobile vehicle without significant disruption to the normal operation of the mobile robot or mobile vehicle.

The mobile robots and mobile vehicles of the mobile data collector group 14038 collect data from targets 14048 (e.g., targets 1202 shown in FIG. 118, or any other suitable targets). In an embodiment, the data collected by the mobile data collectors from targets 14048 may be stored in a data pool 14050 (e.g., data pool 14012 shown in FIG. 118). For example, targets 14048 may be or may include one or more of a machine, a pipeline, equipment, an installation, a tool, a vehicle, a turbine, a speaker, a laser, an automaton, computer equipment, industrial equipment, a switch, etc.

Different mobile robots and/or mobile vehicles in the group 14038 may be configured to record particular types of condition-related measurements for some or all of the targets 14048. For example, some of the mobile robots and/or mobile vehicles in the group 14038 may be configured to record condition-related measurements based on vibrations measured for some or all of the targets 14048. In another example, some of the mobile robots and/or mobile vehicles in the group 14038 may be configured to record condition-related measurements based on temperatures measured for some or all of the targets 14048. In another example, some of the mobile robots and/or mobile vehicles in the group 14038 may be configured to record condition-related measurements based on electrical or magnetic outputs measured for some or all of the targets 14048. In another example, some of the mobile robots and/or mobile vehicles in the group 14038 may be configured to record condition-related measurements based on sound outputs measured for some or all of the targets 14048. In another example, some of the mobile robots and/or mobile vehicles of the group 14038 may be configured to record condition-related measurements based on vibration, temperature, electrical or magnetic, or non-acoustic outputs measured for some or all of the targets 14048.

Alternatively, or in addition, different mobile robots and/or mobile vehicles of the group 14038 may be configured to record some or all status-related measurements of a particular type of target 14048. For example, some of the mobile robots and/or mobile vehicles of the group 14038 may be configured to record some or all status-related measurements of agitators (e.g., turbine agitators), airframe control surface vibrators, catalytic reactors, compressors, etc. In another example, some of the mobile robots and/or mobile vehicles of the group 14038 may be configured to record some or all status-related measurements from conveyors and lifters, waste systems, drive trains, fans, irrigation systems, motors, etc. In another example, some of the mobile robots and/or mobile vehicles of the group 14038 may be configured to record some or all status-related measurements from pipelines, electric powertrains, production platforms, pumps (e.g., water pumps), robotic assembly systems, thermal heating systems, trucks, transmission systems, turbines, etc. In embodiments, the mobile robots and/or mobile vehicles of the fleet 14038 may be configured to record condition-related measurements for some or all of a particular type of industrial environment. For example, industrial environments having targets whose conditions are measured using the mobile robots and/or mobile vehicles of the fleet 14038 may include, but are not limited to, manufacturing environments, fossil fuel energy production environments, aerospace environments, mining environments, construction environments, marine environments, shipping environments, submarine environments, wind energy production environments, hydroelectric energy production environments, nuclear energy production environments, oil drilling environments, oil pipeline environments, other suitable energy product environments, other suitable energy routing or transmission environments, other suitable industrial environments, factories, aircraft such as airplanes, distribution environments, energy source extraction environments, marine exploration sites, underwater exploration sites, assembly lines, warehouses, power generation environments, hazardous waste environments, etc.

The fleet 14038 includes a self-organization system 14052 for causing the mobile robots or mobile vehicles in the fleet 14038 to self-organize (e.g., during data collection operations within an Industrial IoT environment). In embodiments, the data collection system (e.g., data collection system 1204 or any other suitable data collection system) comprising the fleet 14038 may include self-organization functionality that may be performed by or on any of the components of the data collection system. In embodiments, the mobile robots or mobile vehicles of the fleet 14038 may self-organize without assistance from other components, e.g., based on data sensed by their associated sensors and other knowledge. In embodiments, the network 14010 may be accessed for self-organization without assistance from other components and, e.g., based on data sensed by the mobile robots and/or mobile vehicles or other knowledge. It should be understood that any combination or hybrid self-organizing system may also be embodied. For example, the data collection system may implement or enable various methods or systems for data collection with self-organizing functionality in an Industrial IoT environment. These methods and systems may include, for example, analyzing multiple sensor inputs received from or sensed by sensors on the mobile robots and/or mobile vehicles of the fleet 14038. These methods and systems may also include sampling the received data and self-organizing at least one of the following: (i) a data storage operation (e.g., for the data pool 14050), (ii) a sensor collection operation providing multiple sensor inputs, and (iii) a selection operation from multiple sensor inputs.

In embodiments, the self-organizing system 14052 may be used to collectively organize two or more mobile robots and/or mobile vehicles of the group 14038. Alternatively, the self-organizing system 14052 may be used to organize individual mobile robots and/or mobile vehicles of the group 14038. For example, the self-organizing system 14052 may control the traversal of each of the mobile robots and mobile vehicles of the group 14038 through different areas, sections, or otherwise. In embodiments, there may be other mobile robots having one or more mobile data collectors integrated thereto, other mobile vehicles having one or more mobile data collectors integrated thereto, other mobile robots having one or more mobile data collectors coupled thereto, and/or other mobile vehicles having one or more mobile data collectors coupled thereto that collect data for some or all of the target 14048 but that are not included in the group 14038. Such other mobile robots and/or other mobile vehicles may be controlled individually (e.g., outside of the self-organizing system 14052).

In embodiments, the fleet 14038 may include an intelligent system 14054 that processes condition-related measurements recorded using the mobile robots and/or mobile vehicles of the fleet 14038 prior to transmitting those recorded condition-related measurements over the network 14010 or any other suitable communication mechanism. For example, some or all of the mobile robots and/or mobile vehicles of the fleet 14038 may integrate artificial intelligence processes, machine learning processes, and/or other cognitive processes to analyze the condition-related measurements recorded thereby. In embodiments, processing by the intelligent system 14054 of the mobile robots and/or mobile vehicles of the fleet 14038 may be within or represent a pre-processing step of the industrial IoT data collection, monitoring, and control system 10. For example, certain types of mobile robots and/or mobile vehicles of the fleet 14038 may selectively perform pre-processing of recorded condition-related measurements to identify redundant, irrelevant, or unimportant information. In another example, a particular type of mobile robot and/or mobile vehicle in the fleet 14038 may pre-process recorded condition-related measurements in an automated manner to identify redundant, irrelevant, or unimportant information. In another example, pre-processing may be selectively performed on a particular type of condition-related measurement recorded by any of the mobile robots and/or mobile vehicles in the fleet 14038 to pre-process the recorded condition-related measurements (e.g., to identify redundant, irrelevant, or unimportant information). In another example, pre-processing may be automated on a particular type of condition-related measurement recorded by any of the mobile robots and/or mobile vehicles in the fleet 14038 to pre-process the recorded condition-related measurements (e.g., to identify redundant, irrelevant, or unimportant information).

In embodiments, condition-related measurements recorded using the mobile robots and/or mobile vehicles of the group 14038 may be made available via the network 14010 (e.g., as described with respect to FIG. 307) without the need for an external network. The network 14010 may be a MANET (e.g., MANET 20 shown in the figure or any other suitable MANET), the Internet (e.g., Internet 110 shown in FIG. 3 or any other suitable Internet), or any other suitable type of network, or any combination thereof. For example, the network 14010 may be used to receive condition-related measurements recorded using the mobile robots and/or mobile vehicles of the group 14038. The network 14010 may then be used to transmit some or all of those received condition-related measurements to other components of the data collection system 102. For example, the network 14010 may be used to transmit some or all of those received condition-related measurements to a data pool 14050 (e.g., data pool 60 shown in FIG. 2 or any other suitable data pool) for storage of those received condition-related measurements. In another example, the network 14010 may be used to transmit some or all of the received condition-related measurements to a server 14056 (e.g., server 14014 shown in FIG. 161 or any other suitable server) in the environment for industrial IoT data collection. The server 14056 may include aspects of one or more hardware or software servers. For example, the server 14056 to which the received condition-related measurements are transmitted may include an intelligent system 14058 for processing the received condition-related measurements. The intelligent system 14058 may process the received condition-related measurements using artificial intelligence processes, machine learning processes, and/or other cognitive processes to identify information within or otherwise related to the received condition-related measurements. In an embodiment, after processing the received condition-related measurements, the server 14056 to which the received condition-related measurements are transmitted may transmit the processed information or data indicative of the processed information to another system (e.g., for storage or analysis). In an embodiment, the data indicative of the processed information from the server 14056 may include, for example, the output or other results of the artificial intelligence processes, machine learning processes, and/or other cognitive processes.

In an embodiment, a mobile robot or mobile vehicle of fleet 14038 may include a computer vision system or other computer vision capability. For example, the computer vision capability of the mobile robot or mobile vehicle may include hardware and software configured to identify objects in multi-axis space using image sensing. In an embodiment, the computer vision functionality in the mobile robot or mobile vehicle may include functionality for observing the visibility of target 14048 during normal operation of the mobile robot or mobile vehicle. In an embodiment, data processed by the computer vision capability of the mobile robot or mobile vehicle may be input to intelligent system 14054 (e.g., for further processing and learning of target 14048 and/or the environment including target 14048).

In an embodiment, some or all of the mobile robots and/or mobile vehicles of the group 14038 may include sensor fusion functionality. For example, the sensor fusion functionality may be embodied as on-device sensor fusion 80. For example, condition-related measurements recorded using one or more analog sensors (e.g., the analog sensors 82 shown in FIG. 4 or any other suitable sensors) of the mobile robots and/or mobile vehicles of the group 14038 may be processed locally or remotely using artificial intelligence, machine learning, and/or other cognitive processes, which may be embodied within the mobile robots and/or mobile vehicles of the group 14038 themselves, the server 14056, or both. In an embodiment, the sensor fusion functionality may be embodied by a pre-processing step performed prior to the artificial intelligence, machine learning, and/or other cognitive processes. In an embodiment, the sensor fusion functionality may be performed using a MUX. For example, each of the mobile robots and/or mobile vehicles of the group 14038 may include its own MUX for combining condition-related measurements recorded using individual sensors of its multiple sensors. In some such embodiments, the MUX may be internal to the mobile robots and/or mobile vehicles of group 14038. In some such embodiments, the MUX may be external to the mobile robots and/or mobile vehicles of group 14038.

In embodiments, condition-related measurements recorded using the mobile robots and/or mobile vehicles of the group 14038 may be retrieved from the mobile robots and/or mobile vehicles by an upstream device (e.g., a client device or other software or hardware aspect used to review, analyze, or otherwise display the condition-related measurements). For example, the mobile robots and/or mobile vehicles of the group 14038 may not actively transmit the received condition-related measurements (e.g., to the server 14056, the data pool 14050, or other suitable hardware or software component that receives the condition-related measurements recorded using the mobile robots and/or mobile vehicles of the group 14038). Rather, transmission of condition-related measurements from the mobile robots and/or mobile vehicles of the group 14038 may be triggered by a command received at the mobile robots and/or mobile vehicles of the group 14038 (e.g., from the server 14056 or from other hardware or software in the data collection system 102). For example, a data collection device on any of the mobile robots and/or mobile vehicles of the group 14038 may be configured to retrieve condition-related measurements recorded using that mobile robot or mobile vehicle. For example, the mobile robots and/or mobile vehicles of the group 14038 may continuously, periodically, or otherwise record condition-related measurements within an environment for Industrial IoT data collection. The data collector may send one or more commands to some or all of the mobile robots and/or mobile vehicles of the group 14038 to retrieve therefrom some or all of the condition-related measurements recorded using the mobile robots and/or mobile vehicles of the group 14038 at regular intervals, random times, or otherwise, e.g., since the last time a condition-related measurement was retrieved. In another example, the commands, when processed using an individual mobile robot and/or mobile vehicle of the group 14038, cause the recorded condition-related measurements, or data representative thereof, to be transmitted from the mobile robot and/or mobile vehicle of the group 14038.

In an embodiment, state-related measurements recorded using the mobile robots and/or mobile vehicles of the group 14038 may be transmitted from the mobile robots and/or mobile vehicles of the group 14038 in response to a request for those state-related measurements. For example, the self-organizing system 14052 may send a request for recorded state-related measurements to some or all of the mobile robots and/or mobile vehicles of the group 14038 at regular intervals, random times, or otherwise. Processors of some or all of the mobile robots and/or mobile vehicles of the group 14038 to which the request was sent may process the request to determine which state-related measurements to transmit. For example, data indicating the time of the most recent request for recorded state-related measurements may be accessed by those processors. The processor may then compare that time with the time it received a new request from the self-organizing system 14052. The processor may then query a data store for state-related measurements recorded between the two times. The processor may then transmit those state-related measurements in response to a request. In another example, the processor may identify the most recent set of condition-related measurements and transmit those condition-related measurements recorded using the corresponding mobile robots and/or mobile vehicles of the fleet 14038 in response to the request. In another example, a data collector within the data collection system 10 may send a request directly to the mobile robots and/or mobile vehicles of the fleet 14038. In yet another example, a mobile robot and/or mobile vehicle of the fleet 14038 may send a request to the self-organizing system 14052. The self-organizing system 14052 may process the request to determine a selection of individual mobile robots and/or mobile vehicles of the fleet 14038 that were used to record the requested condition-related measurements. In an embodiment, the collective processing mind 14020 may then transmit the particular condition-related measurements in response to the request, for example, by querying storage for some or all of the condition-related measurements recorded using those selected individual mobile robots and/or mobile vehicles of the fleet 14038. Alternatively, the self-organizing system 14052 may process the request and determine which state-related measurements recorded by some or all of the mobile robots and/or mobile vehicles of the fleet 14038 to transmit in response to the request (e.g., based on the time of the request). For example, the self-organizing system 14052 may compare the time of the request with the time of the most recent request for recorded state-related measurements. The self-organizing system 14052 may then retrieve state-related measurements recorded during those times and transmit the retrieved state-related measurements in response to the request.

In embodiments, condition-related measurements recorded using the mobile robots and/or mobile vehicles of the group 14038 may be pushed to an upstream device (e.g., a client device or other software or hardware aspect used to review, analyze, or otherwise view the condition-related measurements). For example, the mobile robots and/or mobile vehicles of the group 14038 may proactively transmit the condition-related measurements they receive (e.g., at the server 14056, data pool 14050, or other suitable hardware or software component that receives the condition-related measurements recorded using the mobile robots and/or mobile vehicles of the group 14038) without such receiving hardware or software component requesting or otherwise causing the mobile robots or mobile vehicles to transmit their condition-related measurements upon command. For example, some or all of the mobile robots and/or mobile vehicles of the group 14038 may transmit their condition-related measurements at regular intervals, at random times, immediately upon recording their condition-related measurements, some time after recording their measurements, when it is determined that a threshold number of condition-related measurements have been recorded, or at other suitable times. In some such embodiments, mobile robots and/or mobile vehicles of the fleet 14038 may push recorded condition-related measurements, either by themselves or using a self-organizing system 14052, in response to detecting the proximity of a data collection router 14062.

For example, referring now to FIG. 166, upon detection of target 14048 by a mobile robot or mobile vehicle 14060 (e.g., one or more of a mobile robot 14040 having one or more mobile data collectors integrated thereto, a mobile vehicle 14042 having one or more mobile data collectors integrated thereto, a mobile robot 14044 having one or more mobile data collectors coupled thereto, or a mobile vehicle 14046 having one or more mobile data collectors coupled thereto) of the group 14038, when the target 14048 is detected, the mobile robot or mobile vehicle 14060 records status-related measurements (e.g., vibration, temperature, electrical or magnetic output, sound output, etc.) of the target 14048. The recorded condition-related measurements can be transmitted over the network 14010 (e.g., to the data pool 14050, the server 14056, or another hardware or software component). Alternatively, the recorded condition-related measurements can be transmitted to the data collection router 14062, for example, if the network 14010 is unavailable or if the data collection router 14062 is configured to receive and/or preprocess the recorded condition-related measurements from the mobile robot or vehicle 14060. The data collection router 14062 may be one of many data collection routers 14062 deployed throughout the environment for industrial IoT data collection. For example, the data collection router 14062 may be a data collection router 14062 configured to transmit the recorded condition-related measurements specifically to the target 14048.

167, various aspects of the functionality of an intelligent system 14064 used to process the output of the mobile robots and/or mobile vehicles of the fleet 14038 are disclosed. In embodiments, the intelligent system 14064 may include a cognitive learning module 14066, an artificial intelligence module 14068, and a machine learning module 14070. The intelligent system 14064 may include additional or fewer modules. The intelligent system 14064 may be, for example, the intelligent system 14054 or the intelligent system 14058 shown in FIG. 165, or any other suitable intelligent system. Although shown as separate modules, in embodiments, there may be overlap between some or all of the cognitive learning module 14066, including the artificial intelligence module 14068 and the machine learning module 14070. For example, the artificial intelligence module 14068 may include the machine learning module 14070. In another example, the cognitive learning module 14066 may include an artificial intelligence module 14068 (and, in embodiments, therefore, a machine learning module 14070). The swarm 14038 may include any number of mobile robots and/or mobile vehicles. For example, as shown, the swarm 14038 includes a first mobile robot or vehicle 14060A, a second mobile robot or vehicle 14060B, and an Nth mobile robot or vehicle 14060N, where N is a number greater than two. The intelligent system 14064 receives the outputs of the mobile robots or vehicles 14060A, 14060B, ... 14060N. In particular, one or more of the modules 14066, 14068, and 14070 of the intelligent system 14064 receive data generated by and output from one or more of the mobile robots or vehicles 14060A, 14060B, ... 14060N. The outputs from the mobile robots or vehicles 14060A, 14060B, ..., are, for example, outputs from the mobile robots or vehicles 14060A, 14060B, ..., 14060N. The outputs may include, for example, state-related measurements recorded using the mobile robots or vehicles 14060A, 14060B, ..., 14060N (e.g., state-related measurements of equipment in an environment for industrial IoT data collection). In an embodiment, the outputs from the mobile robots or vehicles 14060A, 14060B, ..., 14060N may be processed by all three of the modules 14066, 14068, and 14070 of the intelligent system 14064. In embodiments, outputs from mobile robots or vehicles 14060A, 14060B, ..., 14060N may be processed by all of modules 14066, 14068, 14070 of intelligent system 14064. 14060N may also be processed by only one of modules 14066, 14068, and 14070 of intelligent system 14064. For example, the particular one of modules 14066, 14068, and 14070 of intelligent system 14064 used to process outputs from mobile robots or vehicles 14060A, 14060B, ..., may be selected based on the mobile robot and/or vehicle, equipment used to generate the output, the mobile robot and/or vehicle used to generate the output, equipment measured in generating the output, the value of the output, other selection criteria, etc.

Knowledge base 14036 (e.g., as described with respect to FIG. 164) may be updated based on output from intelligent system 14064. Knowledge base 14036 represents a library or other set or collection of knowledge related to the industrial IoT data collection environment, including equipment in that environment, tasks performed in that environment, personnel skilled in performing tasks in that environment, etc. Intelligent system 14064 can process condition-related measurements recorded using mobile robots or mobile vehicles 14060A, 14060B, ... 14060N to facilitate knowledge collection to expand knowledge base 14036. For example, modules 14066, 14068, and 14070 of intelligent system 14064 can process those condition-related measurements against existing knowledge in knowledge base 14036 to update or otherwise modify the information in knowledge base 14036. The intelligent system 14064 uses intelligence and machine learning capabilities (e.g., of the machine learning module 14070 or described elsewhere in this disclosure) to detect conditions (e.g., conditions communicated by the mobile robots and/or mobile vehicles of the fleet 14038 and/or conditions provided as training data) and/or state information (e.g., state information determined by a machine state recognition system that can determine conditions related to operational conditions, environmental conditions, conditions within a known process or workflow, conditions involving faults or diagnostic conditions, etc.). This may include optimizing input selection and configuration based on learning feedback from a learning feedback system, may include providing learning data (e.g., from the host processing system or from other data collection systems directly or from the host processing system), and may include providing feedback metrics (e.g., success metrics calculated within an analytics system of the host processing system). Examples of learning feedback systems, data collection systems, and analytics systems are described elsewhere in this disclosure. Thus, the intelligent system 14064 can be used to update the workflow of tasks assigned and performed within the industrial IoT environment based on outputs from the mobile robots or mobile vehicles 14060A, 14060B, ... 14060N.

In an embodiment, intelligent system 14064 may include other intelligence or machine learning aspects within any of modules 14066, 14068, and 14070, or otherwise. For example, the intelligent system 14064 may be a YOLO neural network, a YOLO CNN, a set of neural networks configured to operate on or from an FPGA, a set of neural networks configured to operate on or from a hybrid FPGA and GPU component, user configurable serial and parallel flows for hybrid neural networks (e.g., configuring serial and/or parallel flows between neural networks as outputs that can be communicated between the neural networks), a machine learning system for automatically configuring a topology or workflow for a set of hybrid neural networks (e.g., sequential, parallel, dataflow, etc.), a deep learning system for automatically configuring a topology or workflow for a set of hybrid neural networks (e.g., sequential, parallel, dataflow, etc.) based on a training dataset that may or may not use manual configuration (e.g., by a human user). for configuring networks (serial, parallel, data flow, etc.) based on training datasets of outcomes from Industrial IoT processes (e.g., maintenance, repair, service, failure prediction, optimization of the operation of machines, systems of equipment, etc.), or other intelligence or machine learning aspects.

Thus, in embodiments, output from the mobile robots and/or mobile vehicles of the fleet 14038 may be processed using the intelligent system 14054 to add to, remove from, or otherwise modify the knowledge base 14036. For example, the knowledge base 14036 may reflect information used to perform one or more tasks within an industrial environment in which targets are located and in which the mobile robots and/or mobile vehicles of the fleet 14038 are employed. Thus, output from the mobile robots and/or mobile vehicles of the fleet 14038 may be used to increase knowledge regarding the nature of problems that arise with respect to the industrial environment, for example, by describing information regarding the target for which a measurement was recorded, the time and/or date the measurement was recorded, existing or other condition information regarding the target, information regarding the time required to resolve a problem with the target, information regarding how to resolve a problem with the target, information indicating the amount of downtime for the target and other aspects of the respective industrial environment as a result of resolving the problem, an indication of whether the problem should be resolved now, later (or not at all), etc. The intelligent system 14054 may process the output to update existing training data. For example, existing training data may be used to update machine learning, artificial intelligence, and/or other cognitive functions to identify target conditions based on the outputs of the mobile robots and/or mobile vehicles of fleet 14038.

For example, knowledge base 14036 may include a series of databases or other tables or graphs arranged hierarchically based on targets or areas of the industrial environment that contain targets. For example, a first tier of knowledge base 14036 may reference the industrial environment (e.g., a power plant, a manufacturing facility, a mining facility, etc.). A second tier of knowledge base 14036 may reference zones within the industrial environment (e.g., Zone 1, Zone 2, etc., possibly named zones). A third tier of knowledge base 14036 may reference targets within those zones (e.g., within a first zone of a power plant that includes electrical equipment, this may include alternators, circuit breakers, transformers, batteries, exciters, etc., and within a second zone of a power plant that includes turbines, generators, generator magnets, etc., this may include alternators, circuit breakers, transformers, batteries, exciters, etc.). Knowledge base 14036 may be updated based on the output of intelligent system 14054, by manual user data entry, or both.

For example, mobile robots and/or mobile vehicles of fleet 14038 may be deployed to monitor or otherwise traverse different locations (e.g., zones) within a mining facility used to mine and/or process fuel materials (e.g., coal, natural gas, etc.) and/or non-fuel materials (e.g., stone, sand, gravel, gold, silver, etc.). The mobile robot may be deployed to traverse a first zone in which mineral crushing machinery is operating, and the mobile vehicle may be deployed to traverse a second zone in which underground mining machinery is operating. The mobile robot may measure the operating temperature of an ore crusher in the first zone, the temperature surrounding the ore crusher in the first zone, etc. The mobile robot may further measure sounds output from the mineral crushing machinery, for example, by recording sound measurements output from some or all of the mineral crushing machinery. The mobile robot may detect an overheating issue with one of the mineral crushing machines if it records temperature measurements that, when processed by intelligent system 14054 against data stored in knowledge base 14036, indicate that the temperature is at a dangerous level. The mobile robot may be instructed to remain at the machine's location and record new temperature measurements over a period of time (e.g., at regular intervals) to determine whether the machine is indeed operating at a dangerously high temperature. If the intelligent system 14054 detects that the initial high temperature measurement is not representative of the machine's operating temperature, the intelligent system 14054 may not update the knowledge base 14036 to reflect the erroneous measurement, or may instead update the knowledge base 14036 to reflect that such temperature measurement may not represent a dangerous condition.

The mobile vehicle may measure vibration output associated with the underground mining equipment. The mobile output may be processed using intelligent system 14054 to determine whether it is consistent with or deviates from the data in knowledge base 14036. If the mobile output deviates from the data in the knowledge base, intelligent system 14054 may update the data in that portion of knowledge base 14036 to reflect the mobile output. Intelligent system 14054 may also, or instead, cause the mobile vehicle to sound an alarm (e.g., using light, sound, or both) to alert personnel located in that zone. For example, intelligent system 14054 may obtain information from knowledge base 14036 that suggests the mobile output reflects a dangerous condition, e.g., associated with a potential underground cave-in. In some scenarios, intelligent system 14054 may send a notification directly to the operator of the underground machine to alert them to the dangerous condition.

Disclosed herein is a system for using mobile robots and/or mobile vehicles for data collection in an industrial environment. As used herein, using a mobile robot and/or mobile vehicle means using a mobile robot and/or mobile vehicle for a specific or general purpose. For example, use of a mobile robot and/or mobile vehicle described with respect to the functionality or configuration of a system refers to the use by that system of a fleet 14038 of mobile robots and/or mobile vehicles, and the hardware and/or software used in connection with the fleet 14038 of mobile robots and/or mobile vehicles, for data collection within an industrial IoT environment, as shown in FIGS. 165 through 167. Such use of a mobile robot and/or mobile vehicle refers to the use of one or more of the fleet 14038 of mobile robots and/or mobile vehicles. For example, the systems disclosed herein as using mobile robots and/or mobile vehicles may be used with robotic arms, android robots, small or large autonomous robots, remotely operated robots, programmably configured robots, other robotic mechanisms, large machinery (e.g., earth moving machinery), large on-road industrial vehicles, large off-road industrial vehicles, industrial machinery deployed in various situations (e.g., turbines, turbo machinery, generators, pumps, pulley systems, manifolds, valve systems, etc.), earth moving machinery, ground compaction machinery, transport machinery, hoisting machinery, conveying machinery, aggregate manufacturing machinery, machinery used in concrete construction, piling machinery, construction machinery (e.g., excavators, backhoes, loaders, etc.), and the like. These include bulldozers, skid steer loaders, trenchers, motor graders, motor scrapers, crawler loaders, wheel loading shovels, dump trucks, tank trucks, tippers, trailers, tunnel handling equipment, road rollers, concrete mixers, hot mix plants, road construction machines (compactors, etc.), stone crushers, hot mix plants, etc. Road rollers, concrete mixers, hot mix plants, road construction machines (compactors, etc.), stone crushers, pavers, slurry sealers, spraying machines, plastering machines, large pumps, etc. Material handling equipment (cranes, conveyors, forklifts, etc.), people transport vehicles (cars, trucks, carts, personal watercraft, aircraft, etc.), unmanned vehicles (autonomous aircraft such as drones, autonomous personal watercraft, autonomous cars and trucks, etc.), other vehicles (regardless of size, purpose, whether or not they use a motor).

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments, including the use of analog crosspoint switches to collect a variable group of analog sensor inputs integrated with wearable devices.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments, with IP front-end signal conditioning on a multiplexer to integrate wearable devices and improve signal-to-noise ratio.

In an embodiment, a system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection in industrial environments with multiplexer continuous monitoring alarm functionality integrated with wearable devices.

In one embodiment, a system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection in industrial environments, integrating wearable devices, using a distributed CPLD chip with multiple MUXes and a dedicated bus for logical control of the data collection section.

In an embodiment, a system for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments is disclosed, having high amperage input capability using solid-state relays and a design topology that integrates wearable devices.

In an embodiment, a system for using a mobile robot and/or a mobile vehicle for mobile data collection in an industrial environment is disclosed, having the ability to power down at least one of the component boards that integrate the analog sensor channels and the wearable device.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments with unique electrostatic protection for triggers and vibration inputs integrated with wearable devices.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments with an accurate voltage reference for A/D zero reference that integrates a wearable device.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments that integrates a wearable device with a phase-locked loop bandpass tracking filter to obtain low-speed RPM and phase information.

In an embodiment, a system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection in industrial environments, using an on-board timer integrated with a wearable device to digitally derive phase for input and trigger channels.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments with a peak detector for autoscaling that is routed to another analog-to-digital converter for peak detection with wearable device integration.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments with routing of raw or buffered trigger channels to other analog channels integrating wearable devices.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments, with the use of higher input oversampling for delta-sigma A/Ds for lower sampling rate outputs to minimize AA filter requirements with wearable device integration.

In an embodiment, a system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection in industrial environments, employing a CPLD as a clock divider for a delta-sigma analog-to-digital converter to achieve low sampling rates without the need for digital resampling associated with integrating a wearable device.

In embodiments, a system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection in industrial environments with long blocks of data at high sampling rates, as opposed to integrating wearable devices to capture multiple data sets at different sampling rates.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments, including storing calibration data with maintenance history on an onboard card set with wearable device integration.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments with rapid route planning capabilities using hierarchical templates integrating wearable devices.

In an embodiment, a system for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments is disclosed, having intelligent management of data collection bands with the integration of wearable devices.

In an embodiment, a system for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments is disclosed, having a neural net expert system that uses intelligent management of data collection bands with the integration of wearable devices.

In an embodiment, a system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection in industrial environments with the use of a database hierarchy for sensor data analysis integrating wearable devices.

In an embodiment, a system for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments is disclosed, having an expert system GUI graphical approach for defining intelligent data collection bands and diagnostics of the expert system with integration of wearable devices.

In an embodiment, a system for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments is disclosed that has a graphical approach for back-calculation definition with the integration of wearable devices.

In an embodiment, a system for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments is disclosed, with the proposed bearing analysis method involving the integration of wearable devices.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments with torsional vibration detection/analysis utilizing transient signal analysis with the integration of wearable devices.

In embodiments, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments, with improved integration using both analog and digital methods with the integration of wearable devices.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments, with adaptive scheduling techniques for continuous monitoring of analog data in the local environment integrating wearable devices.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments with data acquisition parking capabilities with the integration of wearable devices.

In an embodiment, a system for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments is disclosed that has a self-sufficient data collection box that integrates a wearable device.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments with SD card storage integrated with a wearable device.

In embodiments, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments with enhanced on-board statistical capabilities for continuous monitoring through the integration of wearable devices.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments with the use of ambient noise, local noise, and vibration noise for prediction through the integration of wearable devices.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments with smart routes that change route based on incoming data or alarms, enabling simultaneous dynamic data for analysis or correlation through the integration of wearable devices.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments with smart ODS and transfer capabilities with the integration of wearable devices.

In an embodiment, a system for using mobile robots and/or mobile vehicles for mobile data collection in an industrial environment is disclosed that has a hierarchical multiplexer that integrates wearable devices.

In an embodiment, a system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection in industrial environments with a hyper-sensory identity that integrates wearable devices.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments with RF identification and an inclinometer integrated with a wearable device.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments with continuous ultrasound monitoring integrating wearable devices.

In an embodiment, a system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection in industrial environments with cloud-based machine pattern recognition based on the fusion of remote analog industrial sensors integrated with wearable devices.

In an embodiment, a system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection in industrial environments with cloud-based machine pattern analysis of status information from multiple analog industrial sensors to provide predictive status information for industrial systems integrating wearable devices.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments with a cloud-based policy automation engine for IoT, along with the creation, deployment, and management of IoT devices with the integration of wearable devices.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments with on-device sensor fusion and data storage for industrial IoT devices with the integration of wearable devices.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in an industrial environment with a self-organizing data marketplace for industrial IoT data with the integration of wearable devices.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments with self-organization of data pools based on utilization and/or yield metrics integrating wearable devices.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments with training AI models based on industry-specific feedback with the integration of wearable devices.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in an industrial environment with a self-organized swarm of industrial data collectors with the integration of wearable devices.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in an industrial environment with an IoT distributed ledger that integrates wearable devices.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments with self-organizing collectors with the integration of wearable devices.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in an industrial environment with network-sensitive collectors with the integration of wearable devices.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in an industrial environment with remotely organized collectors with the integration of wearable devices.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments with self-organizing storage for multi-sensor data collectors with the integration of wearable devices.

In an embodiment, a system for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments is disclosed, with self-organizing network coding for a multi-sensor data network integrating wearable devices.

In an embodiment, a system for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments is disclosed, having a wearable tactile user interface for industrial sensor data collectors with vibration, heat, electrical and/or sound outputs with the integration of a wearable device.

A system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments with heat maps displaying collected data for AR/VR integration with wearable device integration.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments with automatically coordinated AR/VR visualization of data collected by the data collector with the integration of wearable devices.

In embodiments, an intelligent cooking system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection and has processing, communication, and other IT components for remote monitoring and control that integrate wearable devices.

In an embodiment, an intelligent cooking system is disclosed that uses a mobile robot and/or mobile vehicle for mobile data collection and has a hydrogen fuel generating electrolyzer that operates on a water source to separate the hydrogen and oxygen components, integrating a wearable device.

In an embodiment, an intelligent cooking system is disclosed that uses a mobile robot and/or mobile vehicle for mobile data collection and has a low-pressure hydrogen storage system for storing hydrogen produced by an electrolyzer with the integration of wearable devices.

In embodiments, an intelligent cooking system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection, integrates wearable devices, and has a fuel control module that automatically controls fuel procurement or blending devices based on some measure of past, current, planned, and/or predicted consumption or availability.

In one embodiment, an intelligent cooking system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection and has a solar-powered hydrogen electrolyzer integrated with wearable devices.

In one embodiment, an intelligent cooking system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection and has a wind-powered hydrogen electrolyzer integrated with wearable devices.

In one embodiment, an intelligent cooking system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection and has a hydroelectric hydrogen electrolyzer integrated with wearable devices.

In embodiments, an intelligent cooking system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection and integrates wearable devices to have an on-demand gas-LPG hybrid burner that dynamically supplies LPG, hydrogen, or other fuels without requiring user input or supervision.

In an embodiment, an intelligent cooking system is disclosed that uses a mobile robot and/or mobile vehicle for mobile data collection and has an enclosed burner chamber that provides heat at a target heat zone as a thermal plane with the integration of wearable devices.

In embodiments, an intelligent cooking system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection and has smart knobs with connectivity and local and remote controls for controlling intelligent cooktop devices or other IoT devices with wearable device integration.

In embodiments, an intelligent cooking system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection and has a mobile docking facility with power for charging mobile devices, data communication, and integrated thermal protection for wearable devices.

In embodiments, an intelligent cooking system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection and has distributed modules or components located in a cooktop subsystem that integrates wearable devices.

In an embodiment, an intelligent cooking system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection and has a centralized control facility that manages the operation of cooktop subsystems that integrate wearable devices.

In one embodiment, an intelligent cooking system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection and has remote control functionality that integrates wearable devices.

In an embodiment, an intelligent cooking system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection and has automation through the integration of wearable devices.

In embodiments, an intelligent cooking system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection and integrates wearable devices with detectors and sensors to monitor the status of the cooking system.

In embodiments, an intelligent cooking system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection and has machine learning to optimize the operation of the cooking system, integrating wearable devices.

In an embodiment, an intelligent cooking system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection and has a mobile application that integrates wearable devices.

In an embodiment, an intelligent cooking system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection, has a cloud-based platform that interacts with electronic devices and related ecosystem participants of suppliers, content providers, service providers, and regulators, and integrates wearable devices to provide value-added services to users of the intelligent cooking system, users of the hydrogen production system, and other ecosystem participants.

In an embodiment, an intelligent cooking system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection and integrates wearable devices with a recommendation engine to provide recommendations to users.

In an embodiment, an intelligent cooking system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection and has a notification engine that integrates wearable devices to provide notifications to users.

In an embodiment, an intelligent cooking system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection and has an advertising engine that integrates wearable devices to provide location-based offers to users.

In embodiments, an intelligent cooking system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection and has interfaces that enable machine-to-machine or user-to-machine communication with other devices and the cloud to provide data for analysis, monitoring, control, and operation of other devices and systems, integrating wearable devices.

In an embodiment, an intelligent cooking system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection and has a user interface that facilitates a context- and intelligence-driven personalized experience for computing devices connected to a network centered around the intelligent cooking system that integrates wearable devices.

In embodiments, an intelligent cooking system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection and has analytics to profile, record, or analyze users, equipment usage, maintenance and repair history, patterns, or patterns associated with malfunctions, energy usage patterns, cooking patterns, and electrolyzer deployment, usage, and service that integrates wearable devices.

In embodiments, an intelligent cooking system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection and integrates wearable devices with commerce utilities for ordering ingredients, components, and materials.

In an embodiment, an intelligent cooking system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection and has a cooking assistance utility that integrates wearable devices to assist users with cooking tasks.

In an embodiment, an intelligent cooking system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection and integrates wearable devices to provide food health metrics, nutritional information, nutritional search capabilities, nutritional assistance, and health utilities for personalized suggestions and recommendations.

In embodiments, an intelligent cooking system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection and has infotainment utilities that integrate wearable devices to play music, videos, and/or podcasts.

In an embodiment, an intelligent cooking system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection and has broadcast utilities to enable personalized cooking channels broadcast from a cooking system that integrates wearable devices.

In an embodiment, an intelligent cooking system is disclosed that uses mobile robots and/or mobile vehicles for mobile data collection and has a food survey utility to gather information from smart cooktops and user activity regarding recipes used by users of the smart cooktop system across a region with wearable device integration.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in an industrial environment with an IoT platform that integrates wearable devices.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments, having an IoT data adapter for receiving data input and establishing a connection with one or more available IoT cloud platforms for integrating wearable devices and publishing data.

In an embodiment, a system for using mobile robots and/or mobile vehicles for mobile data collection in an industrial environment is disclosed having a condition detector for detecting conditions associated with connection attempts by an IoT data adapter to one or more IoT cloud platforms involving the integration of wearable devices.

In an embodiment, a system for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments is disclosed that includes an IoT data adapter with an adaptation engine that integrates a wearable device.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in industrial environments, with the use of machine learning to prepare data packets or streams with the integration of wearable devices.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data collection in an industrial environment with a data marketplace that provides a pool of available cloud networking platforms integrating wearable devices.

In an embodiment, a system for using mobile robots and/or mobile vehicles for mobile data collection in an industrial environment is disclosed, including a messaging utility that provides messages to a cloud platform user interface indicating the availability of new data sources, and data source integration and usage instructions involving the integration of wearable devices.

In an embodiment, a system is provided for using mobile robots and/or mobile vehicles for mobile data communication between nodes capable of maintaining first and second nodes.
A second sending limit based on received arrival rate and delivery success rate, and a sending limit based on integration with wearable devices are disclosed for messages.

In an embodiment, a system is disclosed that uses mobile robots and/or mobile vehicles for mobile data communication between nodes with the ability to restrict the transmission of further messages that have not yet been acknowledged as successfully delivered according to a window size integrated with wearable devices.

In an embodiment, a system is disclosed that uses mobile robots and/or mobile vehicles for mobile data communication between nodes with the ability to maintain an estimate of the rate of loss events and use it to adjust the rate of redundancy messages through the integration of wearable devices.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data communication between nodes having an estimated rate of loss events, in which the error correction code used to determine the selected redundant message is based on the estimated rate of loss events involving the integration of wearable devices.

In an embodiment, a system is disclosed that uses mobile robots and/or mobile vehicles for mobile data communications between nodes that have the capability to apply forward error correction based on received messages describing channel characteristics, integrating wearable devices.

In an embodiment, a system is disclosed that uses mobile robots and/or mobile vehicles for mobile data communication between nodes with the ability to maintain/set timers based on the occurrence of broadcast command events and delay the transmission of feedback messages using timers integrated with wearable devices.

In an embodiment, a system is disclosed that uses mobile robots and/or mobile vehicles for mobile data communication between nodes with the ability to maintain/set a timer based on the occurrence of a broadcast command event and integrate wearable devices to delay changes to congestion window sizes based on the timer.

In an embodiment, a system is disclosed that uses mobile robots and/or mobile vehicles for mobile data communication between nodes, with the ability to maintain/set a timer based on the occurrence of a delivery command event, delay changes to the congestion window size based on the timer, and integrate a wearable device to cancel changes to the congestion window size upon receiving a feedback message indicating successful delivery.

In an embodiment, a system is disclosed that uses mobile robots and/or mobile vehicles for mobile data communication between nodes that integrates wearable devices and has the ability to configure new connections using maintained data characterizing current/previous connections.

In an embodiment, a system is disclosed that uses mobile robots and/or mobile vehicles for mobile data communication between nodes that integrates wearable devices and has the ability to configure new connections using maintenance data that characterizes the error rates of current/previous connections.

In an embodiment, a system is disclosed that uses mobile robots and/or mobile vehicles for mobile data communication between nodes that integrates wearable devices and has the ability to form new connections using maintenance data that characterizes timing variations of current/previous connections.

In an embodiment, a system for using mobile robots and/or mobile vehicles for mobile data communication between nodes is disclosed that has the ability to configure new connections using maintained data characterizing the bandwidth of current/previous connections that integrate wearable devices.

In an embodiment, a system for using mobile robots and/or mobile vehicles for mobile data communication between nodes is disclosed that has the ability to configure new connections using persistence data characterizing round-trip times of current/previous connections integrating wearable devices.

In an embodiment, a system is disclosed that uses mobile robots and/or mobile vehicles for mobile data communication between nodes that integrates wearable devices and has the ability to configure new connections using maintained data that characterizes communication control parameters of current/previous connections.

In an embodiment, a system for using mobile robots and/or mobile vehicles for mobile data communication between nodes is disclosed that has the ability to configure new connections using maintained data characterizing forward error correction parameters of current/previous connections integrating wearable devices.

In an embodiment, a system for using mobile robots and/or mobile vehicles for mobile data communication between nodes is disclosed, having a data store for maintaining data characterizing one or more current or previous data communication connections, and a connection initiation module for initiating new data communication connections based on the data maintained through integration of a wearable device.

In an embodiment, a system is disclosed that integrates wearable devices and uses mobile robots and/or mobile vehicles for mobile data communications between nodes capable of transmitting a first subset of data messages over a low-latency data path and a second subset of messages over a high-latency data path.

In an embodiment, a system is disclosed that uses mobile robots and/or mobile vehicles for mobile data communications between nodes capable of transmitting a first subset of time-critical data messages over a low-latency data path and a second subset of messages over a high-latency data path that integrates wearable devices.

In an embodiment, a system is disclosed that uses mobile robots and/or mobile vehicles for mobile data communication between nodes that have the capability to transmit a first initial subset of data messages over a low-latency data path and a second subset of messages that is later available over a high-latency data path that integrates wearable devices.

In an embodiment, a system is disclosed for using a mobile robot and/or a mobile vehicle for mobile data communications between nodes that have the capability to transmit a first subset of acknowledgement messages over a low-latency data path and a second subset of data messages over a high-latency data path through the integration of a wearable device.

In an embodiment, a system is disclosed that uses mobile robots and/or mobile vehicles for mobile data communications between nodes capable of transmitting a first subset of supplemental/redundant data messages over a low-latency data path and a second subset of data messages over a high-latency data path with the integration of wearable devices.

In an embodiment, a system is disclosed that uses mobile robots and/or mobile vehicles for mobile data communication between nodes with redundancy associated with each message based on the message's position in a transmission order that integrates wearable devices.

In an embodiment, a system is disclosed that uses mobile robots and/or mobile vehicles for mobile data communication between nodes, with a degree of redundancy associated with each message increasing as the location of the message decreases with the integration of wearable devices.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data communication between nodes with a degree of redundancy associated with each message based on the message's position in a transmission order, and responsive to receiving feedback messages through the integration of wearable devices.

In an embodiment, a system is disclosed that uses mobile robots and/or mobile vehicles for mobile data communication between nodes, with a degree of redundancy associated with each message, in response to receiving feedback messages based on the message's position in a transmission order, and adds or removes redundant messages from a queue based on the feedback messages with wearable device integration.

In an embodiment, a system is disclosed that uses mobile robots and/or mobile vehicles for mobile data communication between nodes with the ability to adjust the number of messages sent over each of multiple different data paths with different communication protocols when it is determined that the data paths are altering the flow of messages, along with the integration of wearable devices.

In an embodiment, a system is disclosed for using a mobile robot and/or mobile vehicle for mobile data communication between nodes that has the ability to adjust the number of messages sent on each of multiple different data paths having different communication protocols when it is determined that the data paths are changing the initial division flow of messages based on a previous communication connection with a wearable device integration.

In an embodiment, a system is disclosed that uses mobile robots and/or mobile vehicles for mobile data communication between nodes with the ability to modify/add/delete redundancy information associated with encoded data as the wearable device moves from node to node over a channel based on integrated channel characteristics.

In an embodiment, a system is disclosed that uses mobile robots and/or mobile vehicles for mobile data communication between nodes with the capability to transmit FEC packets at an estimated rate for loss events (isolated packet losses or bursts of consecutive packets) through the integration of wearable devices.

In an embodiment, a system is disclosed for using mobile robots and/or mobile vehicles for mobile data communication between nodes with combined coding, TCP, and pacing of packet transmissions with the integration of wearable devices.

In an embodiment, a system is disclosed that uses mobile robots and/or mobile vehicles for mobile data communication between nodes with a forward error correction code structure that interleaves groups of message packets with parity packets and has coding that traverses overlapping groups of message packets with the integration of wearable devices.

In an embodiment, a system is disclosed that uses mobile robots and/or mobile vehicles for mobile data communication between nodes using a variant of TCP that combines delay-based backoff with a stable window increase function with the integration of wearable devices.

Systems and methods for using handheld devices for mobile data collection within an industrial IoT data collection environment will now be described with reference to the figures. See FIGS. 168 through 171. Referring first to FIG. 168, a data collection system may include one or more handheld devices configured to operate as mobile data collectors within an industrial IoT data collection environment. For example, the one or more handheld devices may transmit data, receive data, transmit commands, receive commands, be under control, communicate control, or otherwise communicate with the industrial IoT data collection, monitoring, and control system 10. Disclosed herein are methods and systems for data collection using handheld devices, including a single handheld device having a single sensor for recording condition-related measurements within an environment for industrial IoT data collection, a single handheld device having multiple sensors for recording condition-related measurements within an environment for industrial IoT data collection, multiple handheld devices each having a single sensor for recording condition-related measurements within an environment for industrial IoT data collection, and multiple handheld devices each having one or more sensors for recording condition-related measurements within an environment for industrial IoT data collection. For example, the handheld device may be a wearable tactile or multi-sensor user interface for an industrial sensor data collection apparatus with vibration, heat, electricity, and/or sound outputs. In another example, the handheld device may be any other suitable device, component, unit, or other computational surface having a tangible form that is configured or otherwise usable for placement on a person within an industrial environment, regardless of the duration of such use. Examples of portable devices include, but are not limited to, mobile phones, laptop computers, tablet computers, personal digital assistants, walkie-talkies, radios, long-range or short-range communication devices, flashlights, or other suitable portable devices with sensors built in or coupled to them. Regardless of the particular form, handheld devices according to the present disclosure include one or more sensors for recording environmental condition-related measurements for industrial IoT data collection. For example, one or more sensors of handheld devices described herein may measure conditions related to equipment within the industrial IoT environment or may measure conditions related to the industrial IoT environment itself.

A number of handheld devices 14072 are deployed within the industrial IoT data collection environment. The handheld devices 14072 may be handheld devices issued by an operator of the industrial IoT data collection environment. Alternatively, the handheld devices 14072 may be handheld devices owned by workers selected to perform tasks within the industrial IoT data collection environment. As shown in FIG. 168, the handheld devices 14072 include a single handheld device with a single sensor 14074, a single handheld device with multiple sensors 14076, a combination of handheld devices each with a single sensor 14078, and a combination of handheld devices each with one or more sensors 14080. However, in embodiments, the handheld devices 14072 may include different handheld devices. For example, in an embodiment, handheld device 14072 may omit each combination of handheld devices having a single sensor 14078 and/or each combination of handheld devices having one or more sensors 14080. For example, portable device 14072 may be limited to individual portable devices rather than a combination of portable devices that provide combined, improved, or otherwise different functionality compared to each of the portable devices taken individually. In another example, in an embodiment, portable device 14072 may omit a single portable device having a single sensor 14074 and/or a single portable device having multiple sensors 14076. For example, handheld device 14072 may be limited to a combination of handheld devices rather than individual devices (e.g., if a particular combination of handheld devices is identified as valuable in a particular context, such as for recording measurements related to specific conditions within an environment for industrial IoT data collection).

In an embodiment, different handheld devices 14072 may be configured to record specific types of condition-related measurements for some or all of the targets (e.g., devices or equipment) in the environment for Industrial IoT data collection. For example, some of the handheld devices 14072 may be configured to record condition-related measurements based on vibrations measured for some or all of the targets. In another example, some of the handheld devices 14072 may be configured to record condition-related measurements based on temperatures measured for some or all of the targets. In another example, some of the handheld devices 14072 may be configured to record condition-related measurements based on electrical or magnetic outputs measured for some or all of the targets. In another example, some of the handheld devices 14072 may be configured to record condition-related measurements based on sound outputs measured for some or all of the targets. In another example, some of the handheld devices 14072 may be configured to record condition-related measurements based on vibrations, temperature, electrical or magnetic, or non-sound outputs measured for some or all of the targets.

Alternatively, or in addition, different handheld devices 14072 may be configured to record some or all status-related measurements of particular types of targets within an environment for industrial IoT data collection. For example, some of the handheld devices 14072 may be configured to record some or all status-related measurements from agitators (e.g., turbine agitators), airframe control surface vibrators, catalytic reactors, compressors, etc. In another example, some of the handheld devices 14072 may be configured to record some or all status-related measurements from conveyors and lifters, waste systems, drive trains, fans, irrigation systems, motors, etc. In another example, some of the handheld devices 14072 may be configured to record some or all status-related measurements from pipelines, electric powertrains, production platforms, pumps (e.g., water pumps), robotic assembly systems, thermal heating systems, trucks, transmission systems, turbines, etc. In an embodiment, the handheld devices 14072 may be configured to record some or all status-related measurements of a particular type of industrial environment. For example, industrial environments having targets having conditions measured using handheld device 14072 may include, but are not limited to, manufacturing environments, fossil fuel energy production environments, aerospace environments, mining environments, construction environments, marine environments, maritime environments, submarine environments, wind energy production environments, hydroelectric energy production environments, nuclear energy production environments, etc., oil drilling environments, oil pipeline environments, other suitable energy product environments, other suitable energy pathway or transmission environments, other suitable industrial environments, factories, aircraft such as airplanes, distribution environments, energy source extraction environments, marine exploration sites, underwater exploration sites, assembly lines, warehouses, power generation environments, hazardous waste environments, etc.

In embodiments, condition-related measurements taken using the handheld device 14072 may be made available via the network 14010 (e.g., as described with respect to FIG. 161) without the need for an external network. The network 14010 may be a MANET (e.g., MANET 20 shown in FIG. 2 or any other suitable MANET), the Internet (e.g., Internet 110 shown in FIG. 3 or any other suitable Internet), or any other suitable type of network, or any combination thereof. For example, the network 14010 may be used to receive condition-related measurements recorded using the handheld device 14072. The network 14010 may then be used to transmit some or all of those received condition-related measurements to other components of the data collection system 102. For example, the network 14010 may be used to transmit some or all of those received condition-related measurements to a data pool 14084 (e.g., data pool 60 shown in FIG. 2 or any other suitable data pool) for storage of those received condition-related measurements. In another example, the network 14010 may be used to transmit some or all of the received condition-related measurements to a server 14086 (e.g., server 14014 shown in FIG. 161 or any other suitable server) in the environment for industrial IoT data collection. The server 14086 may include aspects of one or more hardware or software servers. For example, the server 14086 to which the received condition-related measurements are transmitted may include an intelligent system 14088 for processing the received condition-related measurements. The intelligent system 14088 may process the received condition-related measurements using artificial intelligence processes, machine learning processes, and/or other cognitive processes to identify information within or otherwise related to the received condition-related measurements. In an embodiment, after processing the received condition-related measurements, the server 14086 to which the received condition-related measurements are transmitted may transmit the processed information or data indicative of the processed information to another system (e.g., for storage or analysis). The data indicative of the processed information from the server 14086 may include, for example, the output or other results of the artificial intelligence processes, machine learning processes, and/or other cognitive processes.

In an embodiment, some or all of the handheld devices 14072 may include an intelligent system 14082 for processing condition-related measurements recorded using those handheld devices 14072 prior to transmitting those recorded condition-related measurements (e.g., via the network 14010 or any other suitable communication mechanism). For example, some or all of the handheld devices 14072 may integrate artificial intelligence processes, machine learning processes, and/or other cognitive processes to analyze the condition-related measurements recorded thereby. Processing by the intelligent system 14082 of the handheld devices 14072 may be within or represent a pre-processing step of the industrial IoT data collection, monitoring, and control system 10. For example, pre-processing may be selectively performed by certain types of handheld devices 14072 to pre-process the recorded condition-related measurements (e.g., identify redundant, irrelevant, or unimportant information). In another example, preprocessing may be automated for a particular type of handheld device 14072 to preprocess the recorded condition-related measurements (e.g., to identify redundant, irrelevant, or unimportant information). In another example, preprocessing may be selectively performed for a particular type of condition-related measurements recorded by any of the handheld devices 14072 to preprocess the recorded condition-related measurements (e.g., to identify redundant, irrelevant, or unimportant information). In another example, preprocessing may be automated for a particular type of condition-related measurements recorded by any of the handheld devices 14072 to preprocess the recorded condition-related measurements (e.g., to identify redundant, irrelevant, or unimportant information).

In an embodiment, some or all of the handheld devices 14072 may include sensor fusion functionality. For example, the sensor fusion functionality may be embodied as on-device sensor fusion 80. For example, condition-related measurements recorded using one or more of the handheld device 14072's multiple analog sensors (e.g., the multiple analog sensors 82 shown in FIG. 4 or any other suitable sensors) may be processed locally or remotely using artificial intelligence, machine learning, and/or other cognitive processes that may be embodied within the handheld device 14072 itself, the server 14086, or both. The sensor fusion functionality may be embodied by a pre-processing step performed prior to the artificial intelligence, machine learning, and/or other cognitive processes. In an embodiment, the sensor fusion functionality may be performed using a MUX. For example, each of a single handheld device having multiple sensors 14076 may include its own MUX for combining condition-related measurements recorded using different individual sensors of the multiple sensors. In another example, some or all of the individual handheld devices in a combination of handheld devices each having one or more sensors 14080 may include their own MUX for combining condition-related measurements recorded with different individual sensors of the plurality of sensors. In some such embodiments of the plurality of sensors, the MUX may be internal to the handheld device. In some such embodiments, the MUX may be external to the handheld device.

The handheld device 14072 may be controlled within or otherwise connected to and used by the host processing system 112 shown in FIG. 6 (or any other suitable host system). The host processing system 112 may be locally accessible via the network 14010. Alternatively, the host processing system 112 may be remote (e.g., as embodied in a cloud computing system) and may be accessible using one or more network infrastructure elements (e.g., access points, switches, routers, servers, gateways, bridges, connectors, physical interfaces, etc.) and/or one or more network protocols (e.g., IP-based protocols, TCP/IP, UDP, HTTP, Bluetooth, Bluetooth Low Energy, cellular protocols, LTE, 2G, 3G, 4G, 5G, CDMA, TDSM, packet-based protocols, streaming protocols, file transfer protocols, broadcast protocols, multicast protocols, unicast protocols, etc.). In an embodiment, the condition-related measurements recorded using handheld device 14072 may be processed using a network coding system or method, which may be embodied internally or externally with respect to host processing system 112. For example, the network coding system may process the measurements recorded using handheld device 14072 based on the availability of a network for communicating those recorded condition-related measurements, based on the availability of bandwidth and spectrum for communicating those recorded condition-related measurements, based on other network characteristics, or based on some combination thereof.

In embodiments, condition-related measurements recorded using the handheld device 14072 may be retrieved from the handheld device 14072 by an upstream device (e.g., a client device or other software or hardware aspect used to review, analyze, or otherwise display the condition-related measurements). For example, the handheld device 14072 may not actively transmit the received condition-related measurements (e.g., to the server 14086, the data pool 14084, or any other suitable hardware or software component that receives the condition-related measurements recorded using the handheld device 14072). Rather, transmission of the condition-related measurements from the handheld device 14072 may be triggered by a command received at the handheld device 14072 (e.g., from the server 14086 or from other hardware or software in the data collection system 102). For example, a data collection device, which may be fixed within a particular location in an industrial IoT data collection environment or may be mobile therein, may be configured to retrieve condition-related measurements recorded using various handheld devices 14072. For example, the handheld devices 14072 may record condition-related measurements continuously, periodically, or otherwise multiple times within an industrial IoT data collection environment. A data collector may, at fixed intervals, random times, or otherwise, send one or more commands to some or all of the handheld devices 14072 to retrieve some or all of the condition-related measurements recorded using those handheld devices 14072 since the last time condition-related measurements were retrieved therefrom. Alternatively, the data collector may, at those fixed intervals, those random times, or otherwise, send one or more commands to a collective processing heart 14090 associated with the handheld devices 14072. For example, the collective processing heart 14090 may be or include a hub for receiving condition-related measurements recorded using some or all of the handheld devices 14072. In another example, the command, when processed by an individual handheld device 14072 or by the collective processing heart 14090 of the handheld devices 14072, causes recorded condition-related measurements, or data representative thereof, to be transmitted from the handheld devices 14072. For example, the collective processing heart 14090 may be configured to pull condition-related measurements from some or all of the handheld devices 14072 (e.g., at regular intervals, at random times, or otherwise). The collective processing heart 14090 may then transmit the pulled condition-related measurements from the handheld devices 14072 (e.g., to the server 14086, the data pool 14084, or other hardware or software component selected or otherwise configured to receive the condition-related measurements).

In an embodiment, condition-related measurements recorded using the handheld device 14072 may be transmitted from the handheld device 14072 in response to a request for those condition-related measurements. For example, the collective processing core 14090 may send a request for recorded condition-related measurements to some or all of the handheld devices 14072 at regular intervals, random times, or otherwise. The processors of some or all of the handheld devices 14072 to which the request was sent may process the request to determine which condition-related measurements to transmit. For example, data indicating the time of the most recent request for recorded condition-related measurements may be accessed by those processors. The processors may then compare that time with the time a new request is received from the collective processing core 14090. The processors may then query a data store for condition-related measurements recorded between the two times. The processors may then transmit those condition-related measurements in response to the request. In another example, the processor may identify the most recent set of condition-related measurements recorded using the corresponding handheld device 14072 and transmit those condition-related measurements in response to the request. In another example, a data collector within the data collection system 10 may send the request directly to the handheld device 14072. In yet another example, the data collector may send the request to the collective processing mind 14090. The collective processing mind 14090 may process the request to determine which selected individual handheld devices 14072 were used to record the requested condition-related measurements. The collective processing mind 14090 may then transmit the particular condition-related measurements in response to the request, for example, by querying storage for some or all of the condition-related measurements recorded using those selected individual handheld devices 14072. Alternatively, the collective processing mind 14090 may process the request to determine which condition-related measurements recorded by some or all of the handheld devices 14072 to transmit in response to the request (e.g., based on the time of the request). For example, the collective processing heart 14090 can compare the time of the request with the time of the most recent request for recorded condition-related measurements. The collective processing heart 14090 can then retrieve the condition-related measurements recorded during those times and transmit the retrieved condition-related measurements in response to the request.

In embodiments, condition-related measurements recorded using handheld device 14072 may be pushed from handheld device 14072 to an upstream device (e.g., a client device or other software or hardware aspect used to review, analyze, or otherwise display the condition-related measurements). For example, handheld device 14072 may proactively transmit received condition-related measurements (e.g., at server 14086, data pool 14084, or other suitable hardware or software component that receives condition-related measurements recorded using handheld device 14072) without such receiving hardware or software component requesting them or causing the handheld device to transmit them upon command. For example, some or all of handheld devices 14072 may transmit condition-related measurements at regular intervals, at random times, immediately upon recording those condition-related measurements, some time after recording those measurements, when it is determined that a threshold number of condition-related measurements have been recorded, or at other suitable times. In an embodiment, the handheld device 14072 may push recorded condition-related measurements in response to detecting the proximity of the data collection router 14092, either by itself or using the collective processing heart 14090.

For example, referring now to FIG. 169, the collective processing heart 14090 may include a detector 14094 configured to detect the proximity of a target 14096 (e.g., one of the devices 13006 shown in FIG. 134, or any other suitable target) with respect to one or more of the handheld devices 14072. For example, upon such detection, the collective processing heart 14090 may send a signal to one or more of the handheld devices 14072 to record and transmit received state-related measurements at the data collection router 14092. Alternatively, upon such detection, the collective processing heart 14090 may query a data store to obtain state-related measurements and then transmit those state-related measurements received at the data collection router 14092. In either case, the data collection router 14092 forwards the received state-related measurements to the server 14086, the data pool 14084, or any other suitable hardware or software component. In another example, upon such detection, the aggregate processing core 14090 may send a signal directly to the server 14086, the data pool 14084, or other hardware or software component, for example, to bypass the data collection router 14092 or if the data collection router 14092 is omitted.

170, in an embodiment, the collective processing core 14090 may be omitted. Instead, the handheld device 14072 detects the proximity of the target 14096. Upon such detection using the handheld device 14072 (e.g., one or more of a single handheld device with a single sensor 14074, a single handheld device with multiple sensors 14076, a combination of handheld devices each with a single sensor 14078, or a combination of handheld devices each with one or more sensors 14080), the handheld device 14072 records condition-related measurements (e.g., vibration, temperature, electrical or magnetic output, sound output, etc.) of the target 14096. The recorded condition-related measurements may be transmitted via the network 14010 (e.g., to a data pool 14084, a server 14086, or other suitable hardware or software component). Alternatively, the recorded condition-related measurements can be transmitted to the data collection router 14092, for example, if the network 14010 is unavailable or if the data collection router 14092 is configured to receive and/or pre-process the recorded condition-related measurements from the handheld device 14072. The data collection router 14092 may be one of many data collection routers 14092 located throughout an environment for industrial IoT data collection. For example, the data collection router 14092 may be a data collection router 14092 configured to transmit recorded condition-related measurements specifically for the target 14096.

171, various aspects of the functionality of intelligent system 14098 used to process the output of handheld device 14072 are disclosed. Intelligent system 14098 includes a cognitive learning module 14100, an artificial intelligence module 14102, and a machine learning module 14104. In embodiments, intelligent system 14098 may include additional or fewer modules. Intelligent system 14098 may be, for example, intelligent system 14082 or intelligent system 14088 shown in FIG. 161, or any other suitable intelligent system. Although shown as separate modules, in embodiments, there may be overlap between some or all of cognitive learning module 14100, artificial intelligence module 14102, and machine learning module 14104. For example, artificial intelligence module 14102 may include machine learning module 14104. In another example, cognitive learning module 14100 may include artificial intelligence module 14102 (and, in embodiments, therefore, machine learning module 14104). The handheld devices 14072 may include any number of handheld devices. For example, as shown, the handheld devices 14072 include a first handheld device 14072A, a second handheld device 14072B, and an Nth handheld device 14072N, where N is a number greater than two. The intelligent system 14098 receives the output of the handheld devices 14072A, 14072B, .... 14072N, and in particular one or more of the modules 14100, 14102, and 14104 of the intelligent system 14098, receive data generated by and output from one or more of the handheld devices 14072A, 14072B, .... 14072N may include, for example, condition-related measurements recorded using the handheld devices 14072A, 14072B, .... 14072N may be state-related measurements of equipment in the environment, for example, for industrial IoT data collection. In an embodiment, the outputs from handheld devices 14072A, 14072B, ... 14072N may be processed by all three of modules 14100, 14102, and 14104 of intelligent system 14098. In an embodiment, the outputs from handheld devices 14072A, 14072B, ... 14072N may be processed by all three of modules 14100, 14102, and 14104 of intelligent system 14098. 14072N may be processed by only one of modules 14100, 14102, and 14104 of intelligent system 14098. For example, the particular one of modules 14100, 14102, and 14104 of intelligent system 14098 to use to process the output from handheld devices 14072A, 14072B, ... may be selected based on the output from handheld devices 14072A, 14072B, .... Module 14072N may be selected based on the handheld device used to generate that output, the equipment measured in generating that output, the value of the output, other selection criteria, etc.

Knowledge base 14036 (e.g., as shown in FIG. 164) may be updated based on output from intelligent system 14098. Knowledge base 14036 represents a library or other set or collection of knowledge related to the industrial IoT data collection environment, including equipment in that environment, tasks performed in that environment, personnel skilled in performing tasks in that environment, etc. Intelligent system 14098 can process condition-related measurements recorded using handheld devices 14072A, 14072B, .... 14072N facilitates knowledge collection to expand knowledge base 14036. For example, modules 14100, 14102, and 14104 of intelligent system 14098 can process those condition-related measurements against existing knowledge in knowledge base 14036 to update or otherwise modify the information in knowledge base 14036. The intelligent system 14098 can use intelligence and machine learning capabilities (e.g., of the machine learning module 14104 or described elsewhere in this disclosure) to process condition-related measurements and associated information based on detected conditions (e.g., conditions reported by the handheld device 14072 and/or conditions provided as training data) and/or condition information (e.g., condition information determined by a machine condition recognition system that can determine conditions related to operational conditions, environmental conditions, conditions within a known process or workflow, conditions including faults or diagnostic conditions, etc.). This may include optimizing input selection and configuration based on learning feedback from a learning feedback system, providing learning data (e.g., from the host processing system or from other data collection systems directly or from the host processing system), and providing feedback metrics (e.g., success metrics calculated within an analytics system of the host processing system). Examples of host processing systems, learning feedback systems, data collection systems, and analytics systems are described elsewhere in this disclosure. Thus, the intelligent system 14098 can be used to update the workflow of tasks assigned and performed within the industrial IoT environment based on the output from the handheld devices 14072A, 14072B, ... 14072N.

In embodiments, intelligent system 14098 may include other intelligence or machine learning aspects within any of modules 14100, 14102, and 14104, or otherwise. For example, intelligent system 14098 may include one or more of YOLO. Neural networks, YOLO CNN, sets of neural networks configured to operate on or from FPGAs, sets of neural networks configured to operate on or from hybrid FPGA and GPU components, user-configurable serial and parallel flows for hybrid neural networks (e.g., configuring serial and/or parallel flows between neural networks as outputs that can be communicated between the neural networks), machine learning systems for automatically configuring topologies or workflows for sets of hybrid neural networks (e.g., serial, parallel, dataflow, etc.), based on a training dataset that may or may not use manual configuration (e.g., by a human user), deep learning systems for automatically configuring topologies or workflows for sets of hybrid neural networks (e.g., serial, parallel, dataflow, etc.), based on a training dataset of outcomes from industrial IoT processes (e.g., maintenance, repair, service, failure prediction, optimization of the operation of machines, systems of equipment, etc.), or other intelligence or machine learning aspects.

Thus, in embodiments, the output of the handheld device 14072 may be processed using the intelligent system 14088 to add to, remove from, or otherwise modify the knowledge base 14036. For example, the knowledge base 14036 may reflect information used to perform one or more tasks within an industrial environment in which targets are located and in which the handheld device 14072 is used. Thus, the output from the handheld device 14072 may be used to increase knowledge regarding the nature of an emerging problem with the industrial environment by describing, for example, information regarding the target for which a measurement was recorded, the time and/or date the measurement was recorded, existing or other condition information regarding the target, information regarding the time required to resolve the problem with the target, information regarding how to resolve the problem with the target, information indicating the amount of downtime for the target and other aspects of the respective industrial environment as a result of resolving the problem, an indication of whether the problem should be resolved now, later (or not at all), etc. The intelligent system 14088 may process the output to update existing training data. For example, existing training data may be used to update machine learning, artificial intelligence, and/or other cognitive functions to identify target conditions based on the output of the handheld device 14072.

For example, knowledge base 14036 may include a series of databases or other tables or graphs arranged hierarchically based on the subject or areas of the industrial environment that contain the subject, e.g., a first tier of the knowledge base may reference the industrial environment (e.g., a power plant, a manufacturing facility, a mining facility, etc.) - a second tier of knowledge base 14036 may reference zones within the industrial environment (e.g., Zone 1, Zone 2, etc., or possibly named zones). A third tier of knowledge base 14036 may reference targets within those zones (e.g., within a first zone of a power plant that includes electrical equipment, this may include alternators, circuit breakers, transformers, batteries, exciters, etc., and within a second zone of a power plant that includes turbines, generators, generator magnets, etc., this may include alternators, circuit breakers, transformers, batteries, exciters, etc.). Knowledge base 14036 may be updated based on the output of intelligent system 14088, by manual data entry by a user, or both. For example, a worker within a manufacturing facility may be provided with one or more handheld devices (e.g., handheld device 14072). The worker may walk around the manufacturing facility and approach multiple machines in different zones, such as a hydraulic press in a first zone, a thermoforming machine in a second zone, and a conveyor in a third zone. As the worker approaches the first zone, the handheld device may record measurements related to the hydraulic press that indicate vibrations resulting from the operation of the hydraulic press. The measurements are processed using intelligent system 14088 against data stored in a database related to the hydraulic press, for example, in knowledge base 14036. If the measurements do not match the data stored in that database, intelligent system 14088 may determine that the hydraulic press is not operating properly. For example, if the vibrations resulting from the operation of the hydraulic press are less than those recorded in knowledge base 14036, it may be determined that the hydraulic press is not functioning at an optimal speed. The data in knowledge base 14036 may then be referenced to determine the likely cause of this problem, including the amount of time required to resolve the problem. For example, knowledge base 14036 may indicate that a low vibration output is due to a failure of a particular component on a hydraulic press.

The worker may then walk up to the thermoforming machine and measure the ambient temperature around the machine using a handheld device. This measurement may be processed using the intelligent system 14088 to determine that the thermoforming machine is outputting the expected temperature. The worker may then walk up to the conveyor and measure the speed of the conveyor using the handheld device. For example, a camera vision system built into the handheld device may be used to detect the conveyor's operating speed. The operating speed may then be compared to the expected temperature. The expected operating speed of the conveyor is measured as indicated in the appropriate section of the knowledge base 14036. If it is determined that the conveyor is operating at an unexpected speed, the intelligent system 14088 may alert the worker in the area of the conveyor, for example, via the handheld device or via a collective processing center in communication with the handheld device (e.g., a collective processing center located in the third zone of the manufacturing facility), that the conveyor may not be functioning as intended. The alert may be expressed as a warning notification to prevent sudden emergency action from being taken. In such a scenario, an operator can view the alert and update the knowledge base 14036 to reflect the unexpected speed measurement.

Disclosed herein is a system for using handheld devices for data collection in an industrial environment. As used herein, handheld device integration refers to the use of a handheld device for a specific or general purpose. For example, handheld device integration described with respect to a system's functionality or configuration refers to the use by that system of a handheld device 14072 and/or the hardware and/or software used in connection with the handheld device 14072 for data collection within an industrial IoT environment, as shown in FIGS. 168 through 171. Such use of a handheld device refers to one or more uses of the handheld device 14072. For example, a system disclosed herein as using a handheld device may include the use of one or more of a mobile phone, laptop computer, tablet computer, personal digital assistant, walkie-talkie, walkie-talkie, long-range or short-range communication device, flashlight, or other type of handheld device.

In an embodiment, a system for using a handheld device for data collection in an industrial environment is disclosed that includes the use of an analog crosspoint switch to collect a variable group of analog sensor inputs.

In an embodiment, a system for using handheld devices for data collection in industrial environments with IP front-end signal conditioning on a multiplexer for improved signal-to-noise ratio is disclosed.

In an embodiment, a system for using a handheld device for data collection in an industrial environment with multiplexed continuous monitoring alarm functionality is disclosed.

In one embodiment, a data acquisition system for an industrial environment is disclosed that uses a distributed CPLD chip with multiple MUXes and a dedicated bus for logical control of the data acquisition units.

In an embodiment, a system is disclosed for using a handheld device for data collection in an industrial environment with high amperage input capabilities using solid-state relays and a design topology.

In an embodiment, a system is disclosed for using a handheld device for data collection in an industrial environment having the ability to power down at least one of an analog sensor channel and a component board.

In an embodiment, a system is disclosed for using a handheld device for data collection in an industrial environment with unique electrostatic protection for triggers and vibration inputs.

In an embodiment, a system is disclosed for using a handheld device for data collection in an industrial environment with an accurate voltage reference for the A/D zero reference.

In an embodiment, a system is disclosed for using a handheld device for data collection in an industrial environment with a phase-locked loop bandpass tracking filter to obtain low-speed RPM and phase information.

In an embodiment, a system is disclosed that uses a handheld device for data collection in an industrial environment, using an on-board timer to digitally derive phase for input and trigger channels.

In an embodiment, a system is disclosed for using a handheld device for data collection in an industrial environment having a peak detector for autoscaling that is routed to a separate analog-to-digital converter for peak detection.

In an embodiment, a system is disclosed for using a handheld device for data collection in an industrial environment with routing of a buffered trigger channel to raw or other analog channels.

In an embodiment, a system for using handheld devices for data collection in industrial environments is disclosed that has the use of higher input oversampling for delta-sigma A/Ds for lower sampling rate outputs to minimize AA filter requirements.

In an embodiment, a system for using handheld devices for data collection in an industrial environment is disclosed that includes using a CPLD as a clock distributor for a delta-sigma analog-to-digital converter to achieve low sampling rates without the need for digital resampling.

In an embodiment, a system is disclosed for using a handheld device for data collection in an industrial environment with long blocks of data at a high sampling rate, as opposed to multiple sets of data acquired at different sampling rates.

In an embodiment, a system is disclosed for using a handheld device for data collection in an industrial environment with storage of calibration data with maintenance history on a board card set.

In an embodiment, a system for using handheld devices for data collection in industrial environments with rapid route creation capabilities using hierarchical templates is disclosed.

In an embodiment, a system for using handheld devices for data collection in an industrial environment with intelligent management of data collection bands is disclosed.

In an embodiment, a system for using handheld devices for data collection in an industrial environment is disclosed that has a neural net expert system that uses intelligent management of data collection bands.

In an embodiment, a system is disclosed for using handheld devices for data collection in an industrial environment with the use of a database hierarchy in sensor data analysis.

In an embodiment, a system for using handheld devices for data collection in an industrial environment is disclosed that has an intelligent data collection band and an expert system GUI graphical approach for defining expert system diagnostics.

In an embodiment, a system for using handheld devices for data collection in industrial environments with a graphical approach for back-calculation definition is disclosed.

In an embodiment, a system for using a handheld device for data collection in an industrial environment with the proposed bearing analysis method is disclosed.

In an embodiment, a system for using a handheld device for data collection in an industrial environment with torsional vibration detection/analysis using transient signal analysis is disclosed.

In an embodiment, a system is disclosed for using handheld devices for data collection in industrial environments with improved integration using both analog and digital methods.

In an embodiment, a system for using handheld devices for data collection in industrial environments is disclosed that has adaptive scheduling techniques for continuous monitoring of analog data in the local environment.

In an embodiment, a system for using handheld devices for data collection in an industrial environment with data acquisition parking capabilities is disclosed.

In an embodiment, a system for using a handheld device for data collection in an industrial environment having a self-contained data collection box is disclosed.

In an embodiment, a system for using a handheld device for data collection in an industrial environment with SD card storage is disclosed.

In an embodiment, a system is disclosed for using handheld devices for data collection in industrial environments with enhanced on-board statistical capabilities for continuous monitoring.

In an embodiment, a system is disclosed for using handheld devices for data collection in industrial environments with the use of ambient noise, local noise, and vibration noise for prediction.

In an embodiment, a system is disclosed for using handheld devices for data collection in an industrial environment with smart routes that change routes based on input data or alarms, simultaneously providing dynamic data for analysis or correlation.

In an embodiment, a system for using handheld devices for data collection in an industrial environment with smart ODS and transfer capabilities is disclosed.

In an embodiment, a system for using handheld devices for data collection in an industrial environment having a hierarchical multiplexer is disclosed.

In an embodiment, a system for using a handheld device for data collection in an industrial environment with sensory overload is disclosed.

In an embodiment, a system for using a handheld device for data collection in an industrial environment having RF identification and an inclinometer is disclosed.

In an embodiment, a system for using a handheld device for data collection in an industrial environment with continuous ultrasound monitoring is disclosed.

In an embodiment, a system is disclosed for using handheld devices for data collection in industrial environments with cloud-based machine pattern recognition based on the fusion of remote analog industrial sensors.

In an embodiment, a system is disclosed for using handheld devices for data collection in an industrial environment with cloud-based machine pattern analysis of status information from multiple analog industrial sensors to provide predictive status information for the industrial system.

In an embodiment, a system for using handheld devices for data collection in an industrial environment is disclosed that includes a cloud-based policy automation engine for IoT, along with the creation, deployment, and management of IoT devices.

In an embodiment, a system for using handheld devices for data collection in industrial environments with on-device sensor fusion and data storage for industrial IoT devices is disclosed.

In an embodiment, a system for using handheld devices for data collection in an industrial environment with a self-organizing data marketplace for industrial IoT data is disclosed.

In an embodiment, a system is disclosed for using handheld devices for data collection in an industrial environment with self-organization of data pools based on utilization and/or yield metrics.

In an embodiment, a system is disclosed for using handheld devices for data collection in industrial environments with training AI models based on industry-specific feedback.

In an embodiment, a system for using handheld devices for data collection in an industrial environment with a self-organized group of industrial data collectors is disclosed.

In an embodiment, a system for using handheld devices for data collection in an industrial environment with an IoT distributed ledger is disclosed.

In an embodiment, a system for using a handheld device for data collection in an industrial environment having a self-organizing collector is disclosed.

In an embodiment, a system for using handheld devices for data collection in an industrial environment with network-sensitive collectors is disclosed.

In an embodiment, a system for using handheld devices for data collection in an industrial environment with remotely organized collectors is disclosed.

In an embodiment, a system for using handheld devices for data collection in an industrial environment with self-organizing storage for a multi-sensor data collector is disclosed.

In an embodiment, a system for using handheld devices for data collection in an industrial environment with self-organizing network coding for multi-sensor data networks is disclosed.

In an embodiment, a system for using a handheld device for data collection in an industrial environment is disclosed, having a wearable haptic user interface for an industrial sensor data collector with vibration, heat, electrical, and/or acoustic outputs.

In this integration, a system for using handheld devices for data collection in industrial environments is disclosed that has a heat map that displays the collected data for AR/VR.

In an embodiment, a system is disclosed for using handheld devices for data collection in an industrial environment with automatically adjusted AR/VR visualization of data collected by the data collector.

In an embodiment, an intelligent system for use with a handheld device is disclosed that has processing, communication, and other IT components for remote monitoring and control.

In one embodiment, an intelligent system is disclosed that uses a handheld device and has a hydrogen fuel production electrolyzer that operates on a water source and separates hydrogen and oxygen components.

In an embodiment, an intelligent system for use with a handheld device is disclosed, the intelligent system having a low-pressure hydrogen storage system for storing hydrogen produced in an electrolyzer.

In an embodiment, an intelligent system for use with a handheld device is disclosed that has a fuel control module that automatically controls a fuel procurement or blending device based on some measure of past, current, planned, and/or forecasted consumption or availability.

In one embodiment, an intelligent system using a handheld device and having a solar-powered hydrogen electrolyzer is disclosed.

In one embodiment, an intelligent system using a handheld device and including a wind-powered hydrogen electrolyzer is disclosed.

In one embodiment, an intelligent system using a handheld device and including a hydroelectric hydrogen electrolyzer is disclosed.

In an embodiment, an intelligent system is disclosed having an on-demand gas-LPG hybrid burner that uses a handheld device to dynamically supply LPG, hydrogen, or other fuels without requiring user input or oversight.

In an embodiment, an intelligent system for use with a handheld device is disclosed that has an enclosed burner chamber that provides heat to a target heat zone as a thermal plane.

In an embodiment, an intelligent system for using a handheld device is disclosed that has a smart knob with connectivity and local and remote controls for controlling an intelligent cooktop device or other IoT device.

In an embodiment, an intelligent system for using a handheld device is disclosed, the intelligent system having a mobile docking facility with power, data communication, and thermal protection for charging the mobile device.

In an embodiment, an intelligent system is disclosed that uses a handheld device and has distributed modules or components located in the cooktop subsystem.

In an embodiment, an intelligent system is disclosed that uses a handheld device and has a centralized control facility that manages the operation of the cooktop's subsystems.

In an embodiment, an intelligent system is disclosed that uses a handheld device and has remote control capabilities.

In an embodiment, an intelligent system for using a handheld device and having automation is disclosed.

In an embodiment, an intelligent system is disclosed that uses a handheld device and has detectors and sensors for monitoring the status of a cooking system.

In an embodiment, an intelligent system using a handheld device and machine learning to optimize the operation of a cooking system is disclosed.

In an embodiment, an intelligent system for using a handheld device and having a mobile application is disclosed.

In an embodiment, an intelligent system for use with handheld devices is disclosed that has a cloud-based platform that interacts with electronic devices and related ecosystem participants of suppliers, content providers, service providers, and regulators to provide value-added services to users of the intelligent cooking system, users of the hydrogen production system, and other ecosystem participants.

In an embodiment, an intelligent system for using a handheld device is disclosed, the intelligent system having a recommendation engine for providing recommendations to a user.

In an embodiment, an intelligent system for using a handheld device is disclosed, the intelligent system having a notification engine for providing notifications to a user.

In an embodiment, an intelligent system for use with a handheld device is disclosed, the intelligent system having an advertising engine for providing location-based offers to a user.

In an embodiment, an intelligent system is disclosed that uses a handheld device and has an interface that enables machine-to-machine or user-to-machine communication with other devices and the cloud to provide data for analysis, monitoring, control, and operation of other devices and systems.

In an embodiment, an intelligent system for using a handheld device is disclosed having a user interface that facilitates a context- and intelligence-driven personalized experience for computing devices that connect to a network based around the intelligent cooking system.

In an embodiment, an intelligent system for using a handheld device is disclosed that has analytical capabilities for profiling, recording, or analyzing the user, device usage, maintenance and repair history, patterns, or patterns associated with malfunctions, energy usage patterns, cooking patterns, and electrolyzer deployment, use, and service.

In an embodiment, an intelligent system is disclosed for using a handheld device and having a commerce utility for ordering ingredients, components, and materials.

In an embodiment, an intelligent system for using a handheld device is disclosed, the intelligent system having a cooking assistance utility for assisting a user with cooking tasks.

In an embodiment, an intelligent system is disclosed that uses a handheld device and has a health utility for providing food health indicators, nutritional information, nutritional search functionality, nutritional assistance, and personalized suggestions and recommendations.

In one embodiment, an intelligent system for using a handheld device is disclosed, the intelligent system having an infotainment utility for playing music, videos, and/or podcasts.

In an embodiment, an intelligent system for use with a handheld device is disclosed that has a broadcast utility for enabling a personalized cooking channel to be broadcast from the cooking system.

In an embodiment, an intelligent system for using handheld devices is disclosed that includes recipes used by users of a region-wide smart cooktop system that includes a smart cooktop and a food survey utility for collecting information from user activity.

In an embodiment, a system for using handheld devices for data collection in an industrial environment having an IoT platform is disclosed.

In an embodiment, a system is disclosed for using handheld devices for data collection in an industrial environment, having an IoT data adapter for receiving data input and establishing a connection with one or more available IoT cloud platforms for publishing the data.

In an embodiment, a system for using a handheld device for data collection in an industrial environment is disclosed that has a condition detector for detecting conditions associated with connection attempts made by an IoT data adapter to one or more IoT cloud platforms.

In an embodiment, a system for using a handheld device for data collection in an industrial environment is disclosed that has an IoT data adapter with an adaptation engine.

In an embodiment, a system for using handheld devices for data collection in industrial environments is disclosed that includes the use of machine learning to prepare data packets or streams.

In an embodiment, a system is disclosed for using handheld devices for data collection in an industrial environment having a data marketplace that provides a pool of available cloud networking platforms.

In an embodiment, a system for using handheld devices for data collection in an industrial environment is disclosed that has a messaging utility that provides messages to a cloud platform user interface indicating the availability of new data sources and instructions for integrating and using the data sources.

In an embodiment, a system is disclosed that uses handheld devices for data communication between nodes capable of maintaining first and second transmission limits based on received arrival rates and delivery success feedback messages, and that limits the transmission of messages based on the transmission limits.

In an embodiment, a system is disclosed for using handheld devices for data communication between nodes that has the ability to limit the transmission of further messages that have not yet been confirmed as successfully delivered, depending on a window size.

In an embodiment, a system is disclosed for using handheld devices for data communication between nodes that has the ability to maintain an estimate of the rate of loss events and use it to adjust the rate of redundancy messages.

In an embodiment, a system is disclosed for using handheld devices for data communication between nodes having an estimated rate of loss events, in which the error correction code used to determine the selected redundancy message is based on the estimated rate of loss events.

In an embodiment, a system is disclosed for using handheld devices for data communication between nodes that has the capability to apply forward error correction based on received messages describing channel characteristics.

In an embodiment, a system for using handheld devices for data communication between nodes is disclosed that has the ability to maintain/set a timer based on the occurrence of a broadcast command event and to use the timer to delay the transmission of a feedback message.

In an embodiment, a system is disclosed for using a handheld device for data communication between nodes that has the ability to maintain/set a timer based on the occurrence of a delivery command event and delay modification of a congestion window size based on the timer.

In an embodiment, a system is disclosed that uses handheld devices for data communication between nodes that has the ability to maintain/set a timer based on the occurrence of a delivery order event, delay a change in congestion window size based on the timer, and cancel the change in congestion window size upon receiving a feedback message indicating successful delivery.

In an embodiment, a system is disclosed for using handheld devices for data communication between nodes with the ability to configure new connections using maintained data characterizing current/previous connections.

In an embodiment, a system is disclosed for using handheld devices for data communication between nodes that has the ability to configure new connections using maintained data characterizing the error rates of current/previous connections.

In an embodiment, a system is disclosed that uses handheld devices for data communication between nodes with the ability to configure new connections using maintained data that characterizes timing variations of current/previous connections.

In an embodiment, a system is disclosed that uses handheld devices for data communication between nodes with the ability to configure new connections using maintained data that characterizes the bandwidth of current/previous connections.

In an embodiment, a system is disclosed for using handheld devices for data communication between nodes that has the ability to configure new connections using maintained data characterizing the round-trip times of current/previous connections.

In an embodiment, a system is disclosed for using handheld devices for data communication between nodes with the ability to configure new connections using maintained data characterizing communication control parameters of current/previous connections.

In an embodiment, a system for using handheld devices for data communication between nodes is disclosed that has the ability to configure new connections using maintained data characterizing forward error correction parameters of current/previous connections.

In an embodiment, a system for using handheld devices for data communication between nodes is disclosed having a data store for maintaining data characterizing one or more current or previous data communication connections, and a connection initiation module for initiating new data communication connections based on the maintained data.

In an embodiment, a system is disclosed for using handheld devices for data communication between nodes that have the capability to transmit a first subset of data messages over a low-latency data path and a second subset of messages over a high-latency data path.

In an embodiment, a system is disclosed for using handheld devices for data communication between nodes that have the capability to transmit a first subset of time-critical data messages over a low-latency data path and a second subset of messages over a high-latency data path.

In an embodiment, a system is disclosed for using a handheld device for data communication between nodes having the ability to transmit a first initial subset of data messages over a low-latency data path and a second subset of messages later available over a high-latency data path.

In an embodiment, a system is disclosed for using handheld devices for data communication between nodes that have the capability to transmit a first subset of acknowledgement messages over a low-latency data path and a second subset of data messages over a high-latency data path.

In an embodiment, a system is disclosed for using handheld devices for data communication between nodes that have the capability to transmit a first subset of supplemental/redundant data messages over a low-latency data path and a second subset of data messages over a high-latency data path.

In an embodiment, a system is disclosed that uses handheld devices for data communication between nodes with a degree of redundancy associated with each message that is based on the message's position in the transmission order.

In an embodiment, a system is disclosed that uses handheld devices for data communication between nodes with a degree of redundancy associated with each message that increases as the message's position decreases.

In an embodiment, a system is disclosed that uses handheld devices for data communication between nodes with a degree of redundancy associated with each message in response to receiving feedback messages based on the message's position in the transmission order.

In an embodiment, a system is disclosed that uses handheld devices for data communication between nodes with a degree of redundancy associated with each message based on the message's position in the transmission order, and that, in response to receiving a feedback message, adds or removes redundant messages from a queue based on the feedback message.

In one embodiment, a system is disclosed that uses handheld devices for data communication between nodes and has the ability to adjust the number of messages sent over each of multiple different data paths having different communication protocols when it is determined that the data path is altering the flow of messages.

In an embodiment, a system is disclosed for using a handheld device for data communication between nodes that has the ability to adjust the number of messages sent on each of multiple different data paths having different communication protocols when it is determined that the data paths are changing the initial division flow of messages based on previous communication connections.

In an embodiment, a system for using handheld devices for data communication between nodes having the ability to modify/add/delete redundancy information is disclosed that is related to encoded data as it travels over a channel from node to node based on characteristics of the channel.

In an embodiment, a system is disclosed for using handheld devices for data communication between nodes that have the capability to transmit FEC packets at an estimated rate of loss events (isolated packet losses or bursts of consecutive packets).

In an embodiment, a system is disclosed for using handheld devices for data communication between nodes with hybrid coding, TCP, and pacing for packet transmission.

In an embodiment, a system is disclosed that uses handheld devices for data communication between nodes having a forward error correcting code configuration that interleaves groups of message packets with parity packets and encodes across overlapping groups of message packets.

In an embodiment, a system is disclosed for using handheld devices for data communication between nodes that has a variation of TCP that combines a delay-based backoff with a stable window growth function.

Systems and methods for using imagery datasets to identify operational characteristics, such as vibration, of one or more targets, sometimes referred to herein as devices, within an Industrial IoT environment are described with reference to the figures. Reference is first made to FIGS. 172 through 174. In an embodiment, a system, such as computer vision system 15000, as generally shown in the figures, is provided. FIG. 172 is configured to use one or more imagery datasets to detect vibration or other operational characteristics (e.g., vibration, heat, electromagnetic emissions, or other suitable operational characteristics) of one or more targets in an Industrial IoT environment (e.g., as described above). The one or more targets may include devices 13006, as described above. Devices 13006 may include agitators, including turbine agitators, airframe control surface vibrators, catalytic reactors, and compressors. Devices 13006 may also include conveyors and lifters, waste systems, drivetrains, fans, irrigation systems, and motors.

The devices 13006 may also include pipelines, electric powertrains, production platforms, pumps (e.g., water pumps), robotic assembly systems, thermal heating systems, trucks, transmission systems, and turbines. The devices 13006 may operate in a single industrial environment 13018 or in multiple industrial environments 13018. For example, a pipeline device may operate in an oil and gas environment, and a catalytic reactor may operate in either an oil and gas production environment or a pharmaceuticals environment. In embodiments, an operator operating, supervising, inspecting, or a combination thereof, one or more pieces of equipment 13006 may use the computer vision system 15000 to analyze the operation of the one or more pieces of equipment 13006, as described throughout this disclosure. In embodiments, the operator may review data, reports, charts, or other suitable output from the computer vision system 15000 to determine whether maintenance, repair, or other appropriate interaction is required for one or more devices 13006. For example, output from computer vision system 15000 may indicate that vibrations associated with one of devices 13006 may lead to failure if a particular component of device 13006 is not replaced or repaired within a particular timeframe. In an embodiment, computer vision system 15000 may be configured to analyze the image dataset, identify one or more problems (e.g., a failure or potential failure of one or more components), determine corrective actions (e.g., modify the operating speed of a device associated with the failed or failed component), and initiate the corrective actions (e.g., automatically analyze the data, identify the problems, determine the corrective actions, and implement at least a portion of the corrective actions), as will now be described.
[0001]
A computer vision system, such as the computer vision system 15000, may be adapted to automate tasks and/or functions of the human vision system. For example, the computer vision system 15000 may be configured to capture image data related to the device 13006 and analyze the image data using various vision techniques that simulate and improve aspects of human vision and analysis. For example, unlike human vision, the computer vision system 15000 may enhance images by zooming in on objects or analyzing individual frames or deltas between frames. In another example, the computer vision system 15000 may capture images outside the range typically perceptible by humans, such as ultraviolet or infrared signals. The computer vision system 15000 may then use vision techniques to identify various characteristics of the device 13006, such as the presence and amount of unwanted vibration. The computer vision system 15000 may be trained by a human operator, supervisor, or the like, or based on a dataset, model, or the like. Training may include presenting the computer vision system 15000 with one or more training data sets (including many types described throughout this disclosure) representing values such as sensor data, event data, parameter data, etc., and one or more indicators of results such as process results, computation results, event results, activity results, etc. Training may include optimization training, such as training the computer vision system 15000 to: Optimize one or more systems based on one or more optimization methods, such as Bayesian methods, parametric Bayesian classification methods, k-nEAREST-nEigHBor classification methods, iterative methods, interpolation methods, Pareto optimization methods, algorithmic methods, etc. Feedback may be provided in a variation and selection process, such as a genetic algorithm that evolves one or more solutions based on feedback over a series of rounds. Feedback may be determined and provided by a human operator or another component of the monitoring system.
[0002]
In embodiments, the computer vision system 15000 may be trained using a training data set including visual and/or non-visual data to identify operational characteristics of the device 13006 using data captured by one or more data capture devices 15002. In embodiments, the training data set may include image data corresponding to various operational states of the components of the device 13006. For example, the training data set may include image data corresponding to the components of the device 13006 operating within expected or acceptable conditions or tolerances, image data corresponding to the components of the device 13006 operating outside of expected or acceptable conditions or tolerances, and image data corresponding to the components of the device 13006 operating within but tending not to operate within expected or acceptable conditions or tolerances.
[0003]
In embodiments, the training data set may be generated based on image data of components of device 13006 or similar devices and data captured by various sensors (e.g., vibration sensors as described throughout this disclosure). For example, the training data set may include correlations between image data and sensed vibrations of components of device 13006 (e.g., image data indicating that a component is operating within expected or acceptable conditions or tolerances may be correlated with sensed vibration data indicating that vibrations are expected or acceptable).
[0004]
In embodiments, the computer vision system 15000 may capture data (e.g., image data) from the device 13006 using various visual input devices. For example, the data capture device 15002 may capture data, such as visual data or image data, during operation of the device 13006. For example, the data capture device 15002 may capture multiple images over a period of time (e.g., while the device 13006 is operating). The data capture device 15002 may capture images of the device 13006 at any suitable interval during the period. For example, the data capture device 15002 may capture images once per second, once per fraction of a second, or at any suitable interval during the period. In embodiments, the data capture device 15002 may capture raw image data. The raw image data may include signal images, subimages, data points representing an image, or other suitable raw image data. In embodiments, the data capture device 15002 may encode the raw image data using any suitable image encoding technique.

The data capture device 15002 may include a camera, a sensor, other image capture device, other data capture device, or a combination thereof. In an embodiment, the data capture device 15002 may include one or more full-spectrum cameras configured to capture image data including visible light image data and/or non-visible light image data including infrared image data, ultraviolet image data, other non-visible image data, or a combination thereof. In an embodiment, the data capture device 15002 may include one or more radiation imaging devices, such as an X-ray imaging device or other suitable radiation imaging device. The one or more radiation imaging devices may be configured to capture image data of the device 13006 during operation of the device 13006 using X-ray imaging or other suitable radiation imaging. In an embodiment, the data capture device 15002 may include one or more acoustic wave capture devices configured to capture image data of the device 13006 during operation of the device 13006 using sound waves, such as ultrasound or other suitable sound waves. In an embodiment, the data capture device 15002 may include an optical imaging, detection, and ranging (LIDAR) device configured to capture image data of the device 13006 during operation of the device 13006 by illuminating a target with pulsed light and measuring the distance to the target by measuring the reflected pulses with one or more sensors. In an embodiment, the data capture device 15002 may include a point cloud data capture device configured to capture image data of the device 13006 during operation of the device 13006 using a laser or other suitable light to generate a set of data points representing a three-dimensional model of the device 13006.

In an embodiment, the data capture device 15002 may include an infrared inspection device configured to capture image data of the device 13006 during operation of the device 13006 using infrared imaging. In an embodiment, the data capture device 15002 may include a digital image capture device, such as a digital camera, configured to capture image data of the device 13006 during operation of the device 13006 using visible light. For example, an operator operating, supervising, monitoring, and/or inspecting one or more devices 13006 may utilize a mobile device, such as a mobile phone, smartphone, tablet computer, or other suitable mobile device. The mobile device may include an image capture device, such as a digital camera. The operator may capture image data associated with the image capture device of the mobile device. In an embodiment, the data capture device 15002 may be a standalone device that captures image data and communicates the captured image data to a client, a server, or a combination thereof, as described.

In an embodiment, one or more data capture devices 15002 may be positioned at or near each device 13006 at a predefined distance and location relative to the respective device 13006. The predetermined distance and location at which the one or more data capture devices 15002 are positioned or located may be selected such that the one or more data capture devices 15002 have a desired field of data capture of a point of interest of the respective device 13006. The point of interest may include any suitable point or area of the respective device 13006. For example, the point of interest may include a belt, bearing, blade, vane, fan, or any other suitable component, point, or area of interest on or associated with the respective device 13006. The field of data capture may include a field of view for an image data capture device 15002, a field of sonic data capture for an sonic data capture device 15002, or any other suitable field of data capture. Data captured from the combine field of data capture from each data capture device located at or near each device 13006 may be used by image dataset generator 15006, as will be described, to generate one or more image datasets representing images of the point of interest of each device 13006. In an embodiment, data capture device 15002 may include any combination of the devices described herein, or other suitable data capture devices not described.

In an embodiment, the data capture device 15002 may capture image data for the device 13006 as described and communicate the captured image data to the client 15004 and/or the server 15010 using the network 15008. The client 15004 may include any suitable client, including those described throughout this disclosure. In an embodiment, the client 15004 may be a mobile device or other suitable client. The client may include a processor configured to execute instructions stored on a memory (e.g., instructions that, when executed by the processor, cause the processor to perform various portions of the computer vision system 15000 or various methods described herein). The client 15004 may be owned, operated, and/or utilized by an operator working on or near the device 13006, as described throughout this disclosure. The network 15008 may be any suitable network, including, but not limited to, any network described throughout this disclosure, such as the Internet, a cloud network, a local area network, a wide area network, a wireless network, a wired network, a cellular network, etc., or any combination thereof. The server 15010 may be any suitable server, including any of the servers described throughout this disclosure. The server 15010 may include a processor configured to execute instructions stored on a memory (e.g., instructions that, when executed by the processor, cause the processor to perform various portions of the computer vision system 15000 or various methods described herein). The server 15010 may be a standalone server or a collection of servers. The server 15010 may also be a dedicated server, a distributed computing server, a cloud server, or any combination thereof.

In an embodiment, the computer vision system 15000 may include an image dataset generator 15006. The image dataset generator 15006 may be an application or other suitable software or program executable on the client 15004 and/or the server 15010. In an embodiment, the client 15004 may be configured to execute the image dataset generator 15006. For example, an operator as described may carry the client 15004 when the operator interacts with the first device 13006. One or more of the data capture devices 15002 may be configured to capture image data as described associated with the first device 13006. For example, the first data capture device 15002 may be positioned near the first device 13006 such that the first data capture device 15002 has a field of data capture as described relative to a point of interest on the first device 13006. The first data capture device 15002 may capture raw image data associated with the first device 13006. The first data capture device 15002 may communicate the raw image data to the client 15004 via the network 15008. The image dataset generator 15006 may use the raw image data to generate one or more image datasets, as described below. In some embodiments, the server 15010 may be configured to execute the image dataset generator 15006, as generally shown in FIG. 152. The first data capture device 15002 may communicate the raw image data to the server 15010 via the network 15008. The image dataset generator 15006 executed by the server 15010 may use the raw image data to generate one or more image datasets, as described below.

In an embodiment, the image dataset generator 15006 may be configured to generate one or more image datasets using raw image data received from one or more data capture devices 15002. The image datasets may include images containing data (e.g., in a suitable format) that can be analyzed or processed by the visual analytics module 15012, as described below. The image dataset generator 15006 may be configured to decode the raw image data as follows: For example, as described, the one or more data capture devices 15002 may encode the raw image data before communicating the encoded raw image data to the client 15004 and/or the server 15010. The image dataset generator 15006 may be configured to decode the raw image data using any suitable image decoding technique. In some embodiments, the image dataset generator 15006 may be configured to generate the image dataset by correlating related raw image data, stitching the raw image data (e.g., by using multiple images from one or more data capture devices 15002 to create a single image of a point of interest on one of the devices 13006), or using any suitable image dataset generation technique and/or any suitable image processing technique.

In embodiments, the image dataset generator 15006 may generate the image dataset from raw data consisting of data other than visible light image data. For example, as described, the data capture device 15002 may capture data such as acoustic data, non-visible light data, and various other data. The image dataset generator 15006 may receive the non-image raw data and convert the non-image raw data into image data. For example, the image dataset generator 15006 may generate one or more images of a point of interest of the device 13006 using acoustic waves captured by one or more data capture devices 15002. The image dataset generator 15006 may generate the image dataset using any suitable technique. The image dataset generator 15006 may communicate the one or more image datasets to the visual analytics module 15012.

In an embodiment, the vision analysis module 15012 may be an application or other suitable software executable on the server 15010. While the vision analysis module 15012 is illustrated and described as being executed by the server 15010, it should be understood that the client 15004 may also be configured to execute the vision analysis module 15012.

As shown generally in FIG. 174, the vision analysis module 15012 may include an image data database 15014, a training data database 15016, a visual analyzer 15018, and a behavior characteristic detector 15020. In embodiments, the image data database 15014 may include any suitable database and may be located locally on the client 15004 and/or the server 15010, remotely from either the client 15004 and the server 15010, or at another suitable location. The image data database 15014 may store image datasets generated by the image dataset generator 15006, as described. For example, the image dataset generator 15006 may generate one or more image datasets, as described, and communicate the one or more image datasets to the image data database 15014. In embodiments, the image data database 15014 may be any suitable image repository configured to store image datasets.

The training data database 15016 may include any suitable database and may be located locally on the client 15004 and/or the server 15010, remotely from either the client 15004 or the server 15010, or located at another suitable location. The training data database 15016 may store training datasets generated by the deep learning system, as described below. In embodiments, the training data database 15016 may be any suitable training data repository configured to store training datasets. The training datasets may include any suitable training datasets. For example, the training datasets may be generated by the deep learning system, as described below, using various suitable image datasets, such as image datasets representing portions of the device 13006, portions of other devices, image datasets representing movement, vibration, or various other characteristics of the device 13006 or other devices, or any other suitable image dataset or other datasets.

In embodiments, the training dataset may be used to train the computer vision system 15000 to detect various operational characteristics of the device 13006. For example, as described, a deep learning system may train the visual analyzer 15018 to identify various data points in the image dataset, such as anomalies, features, characteristics, or other suitable data points. In embodiments, the visual analyzer 15018 may be trained by any suitable training system, such as a machine learning system, an artificial intelligence training system, a deep learning system, or may be programmed by a human programmer, or may be configured, trained, programmed, etc. using any suitable technique, method, and/or system. For example, the visual analyzer 15018 may be configured to identify a portion of the interest points of each device f3006 represented in the image dataset. For example, the visual analyzer 15018 may identify a portion of the belt of each device 13006 represented in the image dataset. The visual analyzer 15018 may be configured to analyze the portion of interest and determine whether characteristics (e.g., location, size, shape, and/or other suitable characteristics) of the portion of interest correspond to expected or predetermined characteristics of the portion of interest. For example, the visual analyzer 15018 may identify a portion of interest in one of a plurality of images associated with the image dataset. The visual analyzer 15018 may record values corresponding to various characteristics of the portion of interest associated with each of the plurality of images in the image dataset. For example, the visual analyzer 15018 may record: a position of a portion of the belt of each device 13006 in each image of a plurality of consecutive images in the image dataset, and a delta in the position of the belt in consecutive images.

The predicted or predetermined characteristic may be a predicted or predetermined characteristic based on a training dataset, and may correspond to a characteristic of the portion of the point of interest that indicates that the respective device 13006 is operating within an acceptable or expected tolerance range. For example, the predicted or predetermined characteristic of the portion of the point of interest may include a position of a portion of the belt while the respective device 13006 is operating. The position of the belt may correspond to an expected operating position of the belt while the respective device 13006 is operating (e.g., where a portion of the belt is expected to be while the respective device 13006 is operating according to acceptable operating tolerances). While various examples are described, it should be understood that the vision analyzer 15018 may analyze the image dataset using any suitable characteristic of the portion of the point of interest.

In embodiments, the visual analyzer 15018 may compare recorded characteristics of the portion of interest with predicted or predetermined characteristics of the portion of interest. The visual analyzer 15018 may be configured (e.g., trained, configured, programmed, etc., as described above) to generate an analysis of the portion of interest based on the comparison of the recorded characteristics of the portion of interest with the predicted or predetermined characteristics of the portion of interest. For example, the visual analyzer 15018 may determine the variance between the recorded position of the portion of interest and the predicted or predetermined position of the portion of interest (e.g., the variance between the actual or observed position of the belt of each device 13006 and the predicted or predetermined position of the belt of each device 13006). As described, the image dataset may include multiple images of the portion of interest taken over a period of time. The visual analyzer 15018 may determine, for a first interval during the time period (e.g., using a first image captured during the first interval), a first variance between a first recorded characteristic of the portion of interest and a first predicted or predetermined characteristic of the portion of interest. The visual analyzer 15018 may then determine a second variance between a second recorded characteristic of the portion of interest and a second predicted or predetermined characteristic. For a second interval during the time period (e.g., using a second image captured during the second interval), the visual analyzer 15018 may determine a predicted or predetermined characteristic of the portion of interest. The visual analyzer 15018 may continue to determine variances of the recorded characteristics and predicted or predetermined characteristics over the time period using images corresponding to intervals during the time period. In this manner, the visual analyzer 15018 may generate data over time representing the variance of the characteristic of the portion of interest relative to the predicted or predetermined characteristic of the portion of interest. For example, the vision analyzer 15018 may generate data representing the difference between the actual or observed position of the belt compared to the predicted or predetermined position of the belt over a period of time. The vision analyzer 15018 may quantize the variance. For example, the vision analyzer 15018 may be configured to determine a value representing the variance between the recorded characteristic and the predicted or predetermined characteristic (e.g., a value representing the distance between the recorded position of the belt and the predicted or predetermined position of the belt). In an embodiment, the vision analyzer 15018 may be configured to generate a variance dataset including values representing the variance between the recorded characteristic of the portion of interest and the recorded characteristic of the predicted or predetermined portion. The vision analyzer 15018 may communicate the variance dataset to the behavior characteristic detector 15020.

In embodiments, the behavior characteristic detector 15020 may be located or disposed on the vision analytics module 15012 or may be located or disposed remotely from the vision analytics module 15012. In embodiments, the behavior characteristic detector 15020 may be configured to determine or identify various behavior characteristics of each device 13006, or any suitable device 13006, based on the distributed data set. The various behavior characteristics may include vibration, heat, distortion, deflection, other suitable behavior characteristics, or combinations thereof, of a portion of a point of interest during operation of each device 13006, vibration, heat, distortion, deflection, other suitable behavior characteristics, or combinations thereof, of other portions of each device 13006. As described, the behavior characteristic detector 15020 may be trained by any suitable training system, such as a machine learning system, an artificial intelligence training system, a deep learning system, etc., may be programmed by a human programmer, or may be configured, trained, programmed, etc. using any suitable techniques, methods, and/or systems. In an embodiment, the behavioral characteristic detector 15020 may be configured to identify behavioral characteristics of portions of the point of interest by identifying various data in the distributed data set that are indicative of a quantity or other suitable measure of one or more behavioral characteristics of each device 13006.

For example, the behavior characteristic detector 15020 may identify data in the distributed dataset that indicates the belt is vibrating at a first frequency (e.g., by identifying values associated with the distributed dataset that indicate the position of the belt over a period of time is moving at the first frequency). The behavior characteristic detector 15020 may compare the identified behavior characteristic to trained or programmed behavior characteristics to determine whether the behavior characteristic is within an acceptable operating range for the respective device 13006. For example, the behavior characteristic detector 15020 may compare a value associated with the behavior characteristic to a threshold (e.g., determining whether the behavior characteristic is within an acceptable range depending on whether the value of the behavior characteristic is above or below the threshold), compare a value associated with the behavior characteristic to an expected value (e.g., determining that the behavior characteristic is not operating within an acceptable range if the values are different), perform any other suitable decision analysis, or a combination thereof. For example, the behavior characteristic detector 15020 may compare the frequency at which the belt is vibrating to the trained or programmed frequency. The trained or programmed frequencies may include frequencies of belt vibration during normal or acceptable operation of the respective device 13006, frequencies of belt vibration indicating that the belt is vibrating beyond an acceptable tolerance, frequencies of vibration that are within normal or acceptable operation of the respective device 13006 and that indicate the belt may eventually vibrate at frequencies that exceed the acceptable range of operation of the respective device 13006, or other suitable frequencies. Although only vibrations have been described, the trained or programmed behavior characteristics may indicate any suitable behavior characteristic of the respective device 13006. The behavior characteristic detector 15020 may output (e.g., to a database, a report, a monitor, or other suitable output location or device) a behavior characteristic dataset including data indicative of a value or behavior characteristic and/or information indicative of a predictive (e.g., future) behavior characteristic (e.g., determined based on actual or observed behavior characteristics of the portion of the point of interest and trained or programmed behavior characteristics that indicate that the actual or observed behavior characteristics are indicative of a particular further behavior characteristic), actual or observed behavior characteristics, other suitable information or values, or a combination thereof.

In an embodiment, an operator may review and/or analyze the operational characteristic dataset to determine whether each device 13006 and/or portions of the points of interest of each device 13006 are operating within expected or acceptable tolerances. Additionally or alternatively, the operator may make a determination that one or more components of each device 13006 have failed, will fail, require maintenance, or other appropriate determination based on the operational characteristic dataset. For example, the operational characteristic dataset may indicate that a belt is vibrating at a first frequency. The belt vibrating at the first frequency may indicate that a pulley associated with the belt has failed or requires maintenance. The operator may maintain or replace the pulley based on the operational characteristic data. In an embodiment, the operational characteristic detector 15020 may be configured to output information or data indicating that a component of each device 13006 requires maintenance or replacement. For example, as described, the operational characteristic dataset may indicate that a belt is vibrating at a first frequency. The operating characteristic detector 15020 may be configured to determine, based on the operating characteristic dataset (e.g., indicating that the belt is vibrating at a first frequency) and the trained or programmed operating characteristics, that the belt vibrating at the first frequency indicates that the first pulley is faulty and should be replaced or maintained. The operating characteristic detector 15020 may output information or data to an operator, as described, who may then act based on the information or data (e.g., by replacing or maintaining the first pulley).

In an embodiment, the computer vision system 15000 may capture data (e.g., non-image data) from each device 13006 using various non-visual input devices. For example, the data capture device 15002 may capture data such as temperature, pressure, chemical structure, other suitable non-visual data, or a combination thereof, during operation of each device 13006. The chemical structure may include molecular geometry, which represents the spatial arrangement of atoms within a molecule, and the chemical bonds that hold the atoms together. The chemical structure may be represented by a molecular model or a mathematical formula. For example, the data capture device 15002 may capture: Obtain multiple measurements over a period of time (e.g., while each device 13006 is operating). The data capture device 15002 may capture measurements of each device 13006 at any suitable interval during the period. For example, the data capture device 15002 may capture measurements once per second, once per fraction of a second, or at any suitable interval during the period. In an embodiment, the data capture device 15002 may capture raw measurement data. The raw measurement data may include temperature measurements, pressure measurements (e.g., of a liquid or gas within a portion of the respective device 13006), chemical structure measurements (e.g., of a liquid, gas, or solid within a portion of the respective device 13006), or other suitable raw measurement data. In an embodiment, the data capture device 15002 may encode the raw measurement data using any suitable measurement encoding technique.

The data capture device 15002 may include a pressure sensor, a temperature sensor, a chemical sensor, a fluid sensor, other sensors, other data capture devices, or a combination thereof. In an embodiment, the data capture device 15002 may include one or more pressure sensors configured to capture pressure measurement data including within a portion of the respective device 13006. For example, the pressure sensor may measure the pressure within a vat, pipe, tank, or other suitable pressurized enclosure of the respective device 13006. In an embodiment, the data capture device 15002 may include one or more temperature sensors configured to measure the temperature of a portion of the respective device 13006. For example, the temperature sensor may measure the temperature of an oven, kiln, tub, pipe, tank, or other suitable portion of the respective device 13006. In an embodiment, the data capture device 15002 may include one or more chemical sensors configured to measure or determine the chemical structure of a liquid, gas, or solid associated with the respective device 13006. For example, the chemical sensors may measure the chemical structure of parts manufactured by the respective devices 13006, the chemical structure of a cooling fluid used to cool the respective devices 13006 during operation, the chemical structure of waste products generated by the respective devices 13006 during operation, or other suitable chemical structure of other suitable liquids, fluids, gases, or solids associated with the respective devices 13006.

In an embodiment, the data capture device 15002 may be associated with a mobile device. For example, an operator operating, supervising, monitoring, and/or inspecting one or more respective devices 13006 may utilize a mobile device such as a mobile phone, smartphone, tablet computer, or other suitable mobile device. The mobile device may include a data capture device such as an add-on sensor. The operator may capture measurement data using the add-on sensor of the mobile device. In an embodiment, the data capture device 15002 may be a standalone device that captures measurement data as described and communicates the captured measurement data to the client 15004, the server 15010, or a combination thereof as described.

In an embodiment, one or more data capture devices 15002 may be positioned at or near each device 13006 at a predefined distance and location relative to the respective device 13006. The predetermined distance and location at which the one or more data capture devices 15002 are positioned or located may be selected such that the one or more data capture devices 15002 have a desired field of data capture of a point of interest of the respective device 13006. As described, the point of interest may include any suitable point or area of the respective device 13006. For example, the point of interest may include a tub, a tank, a pipe, an enclosure, a manufactured part, a coolant, a waste product, other suitable points of interest, or a combination thereof. The field of data capture may include an area in which desired measurements may be captured using the data capture device 15002. Data captured from the combine field from each data capture device 15002 located at or near each device 13006 may be used by the image dataset generator 15006, as described, to generate one or more image datasets representing images of the point of interest of each device 13006. In an embodiment, the data capture device 15002 may include any combination of the devices described herein or other suitable data capture devices not described.

In an embodiment, the data capture device 15002 may capture measurement data for each device 13006 as described and communicate the captured measurement data to the client 15004 and/or the server 15010 using the network 15008. The client 15004 may include any suitable client, including those described throughout this disclosure. In an embodiment, the client 15004 may be a mobile device or other suitable client. The client 15004 may be owned, operated, and/or utilized by an operator working on or near the respective device 13006 as described throughout this disclosure. The network 15008 may be any suitable network described throughout this disclosure, including, but not limited to, the Internet, a cloud network, a local area network, a wide area network, a wireless network, a wired network, a cellular network, etc., or any combination thereof. The server 15010 may be any suitable server, including any server described throughout this disclosure. The server 15010 may be a standalone server. The server 15010 may be a dedicated server, a distributed computing server, a cloud server, or a combination thereof.

In an embodiment, as described, the image dataset generator 15006 may comprise an application or other suitable software or program executable on the client 15004 and/or the server 15010. In an embodiment, the client 15004 may be configured to execute the image dataset generator 15006. For example, an operator as described may carry the client 15004 when the operator interacts with the first device 13006. One or more of the data capture devices 15002 may be configured to capture measurement data as described associated with the first device 13006. For example, the first data capture device 15002 may be positioned near the first device 13006 such that the first data capture device 15002 has a data capture field as described relative to a point of interest on the first device 13006. The first data capture device 15002 may capture raw measurement data associated with the first device 13006. The first data capture device 15002 may communicate the raw measurement data to the client 15004 via the network 15008. The image dataset generator 15006 may generate one or more image datasets using the raw measurement data. In some embodiments, the server 15010 may be configured to execute the image dataset generator 15006, as generally shown in FIG. 152. The first data capture device 15002 may communicate the raw measurement data to the server 15010 via the network 15008. The image dataset generator 15006 executed by the server 15010 may generate one or more image datasets using the raw measurement data.

In embodiments, the image dataset generator 15006 may be configured to generate one or more image datasets using raw measurement data received from one or more data capture devices 15002. The image dataset may include images containing data (e.g., in a suitable format) that can be analyzed or processed by the visual analytics module 15012, as described. The image dataset generator 15006 may be configured to decode the raw measurement data. For example, as described, one or more data capture devices 15002 may encode the raw measurement data before communicating the encoded raw measurement data to the client 15004 and/or server 15010. The image dataset generator 15006 may be configured to decode the raw measurement data using any suitable measurement decoding technique. For example, the image dataset generator 15006 may be configured to interpret signals representing measurements as measurements. In some embodiments, the image dataset generator 15006 may be configured to correlate related raw measurement data, stitch raw measurement data (e.g., using The image dataset may be generated using any suitable image dataset generation technique and/or any suitable measurement data processing technique, such as using multiple measurements from one or more data capture devices 15002 to create a single value representing a point of interest on each device 13006. For example, the image dataset generator 15006 may be configured to use measurement data corresponding to pressure, temperature, chemical structure, or other suitable measurement data to generate image data representing a point of interest on each device 13006.

In an embodiment, the image dataset generator 15006 may be configured to generate one or more image datasets using measurement data as described in combination with raw image data (e.g., captured by the data capture device 15002, as described above). For example, the image dataset generator 15006 may be configured to generate images of points of interest for each device 13006 using the captured image data in combination with associated temperature measurements to generate an accurate image of the points of interest (e.g., taking into account expansion, deflection, growth, contraction, or other changes in shape or size of a component due to its temperature). The image dataset generator 15006 may communicate one or more image datasets to the vision analytics module 15012. In an embodiment, the vision analytics module 15012 may be an application or other suitable software executable on the server 15010. While the vision analytics module 15012 is illustrated and described as being executed by the server 15010, it should be understood that the client 15004 may also be configured to execute the vision analytics module 15012. In embodiments, the visual analysis module 15012 may analyze the image dataset as described. For example, the visual analyzer 15018 may analyze the image dataset. The behavior characteristic detector 15020 may identify behavior characteristics as described.

In embodiments, as described, the training data database 15016 may include any suitable database and may be located locally on the client 15004 and/or the server 15010, remotely from either the client 15004 and the server 15010, or located at another suitable location. The training data database 15016 may store training datasets generated by the deep learning system, as described below. In embodiments, the training data database 15016 may be any suitable training data repository configured to store training datasets. The training datasets may include any suitable training datasets. For example, the training datasets may be generated by the deep learning system, as described below, using various suitable datasets, such as a dataset representing a portion of each device 13006, a dataset representing a portion of other devices, a dataset representing pressure, a dataset representing temperature, a dataset representing chemical structure, a dataset representing vibration, or various other characteristics of each device 13006 or other devices.

In embodiments, the training dataset may be used to train the computer vision system 15000 to detect various operational characteristics of each device 13006. For example, as described, a deep learning system may train the visual analyzer 15018 to identify various data points in the image dataset, such as anomalies, features, characteristics, or other suitable data points. In embodiments, the visual analyzer 15018 may be trained by any suitable training system, such as a machine learning system, an artificial intelligence training system, a deep learning system, may be programmed by a human programmer, or may be configured, trained, programmed, etc. using any suitable technique, method, and/or system. For example, the visual analyzer 15018 may be configured to identify a portion of the interest points of each device f3006 represented in the image dataset. For example, the visual analyzer 15018 may identify a portion of the belt of each device 13006 represented in the image dataset. The visual analyzer 15018 may be configured to analyze the portion of interest and determine whether characteristics of the portion of interest (e.g., location, size, shape, and/or other suitable characteristics) correspond to expected or predetermined characteristics of the portion of interest. For example, the visual analyzer 15018 may identify the portion of interest in one of a plurality of images associated with the image dataset. The visual analyzer 15018 may record various characteristics of the portion of interest associated with each of the plurality of images in the image dataset. For example, the visual analyzer 15018 may record a pressure value, temperature value, or other suitable measurement associated with a portion of the belt of each device 13006 in each of a plurality of consecutive images in the image dataset and track deltas of the belt measurements in consecutive images (e.g., using measurements captured by the data capture device 15002, as described). As described, the visual analyzer 15018 may generate a variance dataset based on the deltas between the recorded values and the expected or predetermined values.

In an embodiment, the behavioral characteristic detector 15020 may be located or disposed on the vision analytics module 15012 or may be located or disposed remotely from the vision analytics module 15012. In an embodiment, the behavioral characteristic detector 15020 may be configured to determine or identify various behavioral characteristics of each device 13006, or any suitable respective device 13006, based on the distributed data set. The various behavioral characteristics may include vibration, heat, strain, deflection, other suitable behavioral characteristics, or combinations thereof, of a portion of the point of interest of the respective device 13006 during operation, vibration, heat, strain, deflection, other suitable behavioral characteristics, or combinations thereof, of other portions of the respective device 13006.

As described, the behavioral characteristic detector 15020 may be trained by any suitable training system, such as a machine learning system, an artificial intelligence training system, a deep learning system, or may be programmed by a human programmer, or may be configured, trained, programmed, etc., using any suitable technique, method, and/or system. In embodiments, the behavioral characteristic detector 15020 may be trained by a deep learning system, as will now be described, using training datasets that may include a dataset representing a portion of each device 13006, a dataset representing a portion of other devices, a dataset representing pressure, a dataset representing temperature, a dataset representing chemical structure, a dataset representing vibration, or a dataset representing various other characteristics of each device 13006 or other devices, or any other suitable dataset. In embodiments, the behavioral characteristic detector 15020 may be configured to identify behavioral characteristics of portions of points of interest by identifying various data in the distributed datasets indicative of quantities or other suitable measurements of one or more behavioral characteristics of each device 13006. In an embodiment, the operating characteristics may include pressure within a component of each device 13006, a temperature of at least a portion of a component of each device 13006, a chemical structure of a material (e.g., a gas, liquid, or solid of or within a component of each device 13006, or a component or part produced by each device 13006), a density of a material (e.g., a gas, liquid, or solid of or within a component of each device 13006, or a component or part produced by each device 13006), other suitable operating characteristics, or a combination thereof.

For example, the operating characteristic detector 15020 may identify data in the distributed data set that indicates that a component of the respective device 13006 is malfunctioning due to an unexpected increase in temperature (e.g., by identifying values associated with the distributed data set that indicate that the component's temperature is increasing at a rate greater than expected over a period of time). The operating characteristic detector 15020 may compare the identified operating characteristic to trained or programmed operating characteristics to determine whether the operating characteristic is within the operating tolerances of the respective device 13006. For example, the operating characteristic detector 15020 may compare the component's rate of temperature change to the trained or programmed component's rate of temperature change. The behavior characteristic detector 15020 may output (e.g., to a database, a report, a monitor, or other suitable output location or device) a behavior characteristic dataset including data indicative of values or behavior characteristics and/or information indicative of predictive (e.g., future) behavior characteristics (e.g., determined based on actual or observed behavior characteristics of a portion of the point of interest and trained or programmed behavior characteristics that indicate that the actual or observed behavior characteristics exhibit certain additional behavior characteristics), the actual or observed behavior characteristics, other suitable information or values, or a combination thereof. As described, an operator can analyze the output data and take appropriate corrective action. Additionally, or instead, the computer vision system 15000 may automatically identify and initiate corrective action.

In an embodiment, the computer vision system 15000 may implement a classification model (e.g., using a deep neural network or other suitable neural or other network). For example, the vision analysis module 15012 may implement a classification module that receives an analysis of image data including the variance dataset described above. The vision analysis module 15012 may output a classification associated with the operating characteristics of each device 13006. For example, the classification model may receive, via the vision analysis module 15012, features defining the variance among recorded characteristics of the image dataset of the belt of each device 13006 in operation. The classification model may be trained using image data and/or non-image data corresponding to a failed belt, image data and/or non-image data corresponding to a belt that has not yet failed, and image data and/or non-image data corresponding to a belt operating in an expected and/or acceptable condition, and may output a classification indicating whether the belt has failed, is operating within expected and/or acceptable conditions but trending toward failure, or is in an expected and/or acceptable operating condition.

In embodiments, the operating characteristic detector 15020, the vision analysis module 15012, and/or the computer vision system 15000 may generate one or more warnings, signals, indicators, or other suitable outputs configured to alert an operator of one or more of the operating characteristics of the respective device 13006, one or more components of the respective device 13006 that require maintenance or replacement, any other suitable alert, or a combination thereof. For example, the computer vision system 15000 may be configured to generate a message, such as a text message, email message, pop-up message, or other suitable message, indicating that a component (e.g., the first pulley) of the respective device 13006 requires maintenance. The message may include text, characters, images, or other suitable information conveying the intended message. The computer vision system 15000 may be configured to communicate the message to the operator via the network 15008, near-field communication, or other suitable communication system or protocol. For example, the computer vision system 15000 may communicate the message to a mobile device, or other suitable device and/or location, as described.

In an embodiment, the computer vision system 15000 may be configured to display the current status of one or more respective devices 13006 on an output display. For example, the factory, plant, or other suitable location of each device 13006 may include an output display (e.g., a screen or monitor) positioned such that an operator in proximity to each device 13006 can view the output display. The computer vision system 15000 may be configured to display one or more statuses (e.g., a red, yellow, green status, an up or down status, or other suitable status or indicator, or a combination thereof) of each device 13006. For example, the computer vision system 15000 may display a green status next to each device 13006 that is operating within acceptable operating conditions (e.g., based on a visual analysis of the image dataset described above). In another example, the computer vision system 15000 may display a yellow status next to each device 13006 that is operating within acceptable operating conditions, and the visual analysis indicates that the respective device 13006 may begin operating outside of acceptable operating conditions if the operating characteristics (e.g., identified as described) continue along their current operating trends (e.g., based on the frequency of the belt vibration, the computer vision system 15000 may determine that continued vibration at that frequency and/or an increase in frequency may cause the respective device 13006 to operate outside of acceptable operating conditions). In another example, the computer vision system 15000 may display a red status next to each device 13006 that is currently operating outside of acceptable operating conditions. In an embodiment, the computer vision system 15000 may display the operating status of each device 13006 on another suitable display, such as a mobile device display, as described. For example, the mobile device may include an application that displays the operating status of each device 13006.

In embodiments, the output of vision analytics module 15012 may be used to update and/or improve the training dataset described above. For example, the output from vision analytics module 15012 may be used to update the training dataset to include additional behavioral characteristics, to improve the accuracy of values used to predict various behavioral characteristics, for other suitable updates or improvements to the training dataset, or any combination thereof. The training dataset may be used as continuous feedback to computer vision system 15000 to improve the prediction and decision-making capabilities of computer vision system 15000.

In embodiments, the output of the vision analysis module 15012 may be used to generate and/or update a knowledge base that can be used by an operator or the computer vision system 15000 to identify faults, schedule repairs or maintenance, adjust settings on the respective devices 13006, take other corrective actions, or take other appropriate actions. For example, the output of the vision analysis module 15012 may be correlated to repairs of the corresponding components (e.g., the output of the vision analysis module 15012 may indicate that belt vibrations are outside expected or acceptable tolerances, and the operator may replace a pulley in response to the output). The knowledge base may be updated to indicate that the output of the vision analysis module 15012 (e.g., including the values of the operating characteristics determined above) resulted in a replaced pulley. In this manner, the knowledge base may continue to grow and provide accurate and precise information to the operator or the computer vision system 15000 related to the operating characteristics and corresponding corrective actions, thereby improving the efficiency of the computer vision system 15000 and assisting the operator in identifying problems and corresponding corrective actions.

In embodiments, the computer vision system 15000 may be configured to visually inspect components, parts, systems, devices, or combinations thereof other than those described above. For example, the computer vision system 15000 may be configured to visually inspect parts manufactured at a part manufacturing facility, as described. For example, the data capture devices 15002 may be arranged or positioned such that the data capture field of each respective data capture device 15002 is directed toward at least a portion of the part being manufactured (e.g., on a part manufacturing line). The data capture devices 15002 may capture data related to the part as it moves along the part manufacturing line. The computer vision system 15000 may analyze the data captured by the data capture devices 15002 (e.g., as an image dataset generated by the image dataset generator 15006) to identify anomalies, variations, or other conditions that deviate from the acceptance criteria of the part. In embodiments, the part may include a vehicle part, a bicycle part, a bicycle chain, a gasket, a fastener (e.g., a screw, bolt, nut, nail, etc.), a printed circuit board, a capacitor, an inductor, a resistor, or other suitable part. For example, the computer vision system 15000 may analyze an image dataset associated with a bicycle chain in production. Based on the analysis described above, the computer vision system 15000 may identify an unacceptable bend in a portion of the bicycle chain. The computer vision system 15000 may generate a message indicating that the bicycle chain should be removed from distribution, repaired, destroyed, or other appropriate action taken, as described.

As shown generally in FIGS. 175-176, the deep learning system 15030 may be configured to use a training data set to train the computer vision system 15000 to identify operating characteristics of each device f3006 or other suitable device, identify corrective actions in response to the identified operating characteristics, and initiate the corrective actions based on the identified corrective actions. The deep learning system 15030 may train the computer vision system 15000 using learning based on data representations. In embodiments, the deep learning system 15030 may train the computer vision system 15000 using supervised training (e.g., using classification), semi-supervised training, or unsupervised training (e.g., using pattern analysis). In embodiments, the deep learning system 15030 may include a deep neural network, a deep belief network, a recurrent neural network, other suitable networks or learning systems, or a combination thereof.

In an embodiment, the deep learning system 15030 may include propositional expressions or latent variables organized into multiple layers. Each of the multiple layers may be configured to represent an abstract portion of an image. For example, a first layer may represent an abstract portion of pixels of an input image, e.g., an image representing a point of interest of the representative device 13006, and encode edges. A second layer may represent the placement of edges. A third layer may encode a first portion of a component (e.g., a portion of a belt, as described) within the point of interest of the representative device 13006. A fourth layer may represent another encoded portion of the component, such that the multiple layers, when stacked, represent the point of interest of the representative device 13006. The deep learning system 15030 may be configured to translate the layers into a training dataset used to train the computer vision system 15000. For example, the deep learning system 15030 may translate multiple layers of one or more images representing the belt of the representative device 13006 vibrating at a first frequency. The deep learning system 15030 may use input data from various sources to determine whether the first frequency represents a frequency at which the belt is vibrating within an expected or acceptable tolerance, as described. For example, the deep learning system 15030 may receive data indicative of repair data, maintenance data, uptime data, downtime data, profitability data, efficiency data, operational optimization data, or combinations thereof, associated with each device 13006, process, production line, equipment, or other suitable system.

In embodiments, the deep learning system 15030 may identify a data value corresponding to the first frequency of the belt. For example, the deep learning system 15030 may identify an uptime value, a downtime value, a profitability value, other suitable values, or a combination thereof, corresponding to the period during which each device 13006 operated with the belt vibrating at the first frequency. For example, the deep learning system 15030 may determine that the first frequency is within an expected or acceptable tolerance range if the data indicates that each device 13006 had uptime above a threshold, downtime below a threshold, profitability above a threshold, or a combination thereof. Conversely, the deep learning system 15030 may determine that the first frequency is outside an expected or acceptable tolerance range if, for example, downtime associated with each device 13006 exceeded a threshold. It should be understood that the deep learning system 15030 may identify any suitable behavioral characteristics other than those disclosed herein, and the deep learning system 15030 may determine a positive or negative outcome of the behavioral characteristics based on any suitable data analysis other than that described herein.

In embodiments, the deep learning system 15030 may generate a training dataset using the identified operating characteristics and associated analysis. In embodiments, the deep learning system 15030 may train the computer vision system 15000 using the training dataset. In embodiments, the deep learning system 15030 may receive feedback information from the computer vision system 15000, an operator, a programmer, other suitable sources, or a combination thereof. The deep learning system 15030 may update the training dataset based on the feedback. For example, the computer vision system 15000 trained using the training dataset may identify a component as faulty. The operator may visually inspect the component and determine that the component is not faulty. The operator and/or the computer vision system 15000 may communicate to the deep learning system 15030 that the component is not faulty based on the identified operating characteristics (e.g., identified by the computer vision system 15000). The deep learning system 15030 may update the training dataset using feedback from the operator and/or the computer vision system 15000.

In an embodiment, an apparatus for detecting operational characteristics of a manufacturing equipment includes a memory and a processor. The memory includes instructions executable by the processor to generate one or more image data sets using raw data captured by one or more data capture devices, identify one or more values corresponding to a portion of the manufacturing equipment within a point of interest represented by the one or more image data sets, record the one or more values, compare the recorded one or more values to corresponding predicted values, generate a variance data set based on a comparison of the recorded one or more values with corresponding predicted values, identify an operational characteristic of the manufacturing equipment based on the variance data, and generate a display indicative of the operational characteristic.

In an embodiment, the memory further includes instructions executable by the processor to identify a corrective action in response to identifying the operating characteristic. In an embodiment, the memory further includes instructions executable by the processor to initiate a corrective action in response to identifying the operating characteristic. In an embodiment, the operating characteristic includes vibration of a component of the manufacturing equipment. In an embodiment, the operating characteristic includes a shape of a component of the manufacturing equipment. In an embodiment, the operating characteristic includes a size of a component of the manufacturing equipment. In an embodiment, the operating characteristic includes a deflection of a component of the manufacturing equipment. In an embodiment, the operating characteristic includes electromagnetic radiation of a component of the manufacturing equipment. In an embodiment, the operating characteristic includes a temperature of the component of the manufacturing equipment. In an embodiment, the operating characteristic includes a temperature of a gas within a component of the manufacturing equipment. In an embodiment, the operating characteristic includes a temperature of a liquid within a component of the manufacturing equipment. In an embodiment, the operating characteristic includes a temperature of a solid within a component of the manufacturing equipment. In an embodiment, the operating characteristic includes a pressure within a component of the manufacturing equipment. In an embodiment, the operating characteristic includes a pressure of a gas within a component of the manufacturing equipment. In an embodiment, the operating characteristic includes a pressure of a liquid within a component of the manufacturing equipment. In an embodiment, the operating characteristic includes a density of a gas within a component of the manufacturing equipment.

In an embodiment, the operating characteristic includes the density of a liquid within a component of the manufacturing equipment. In an embodiment, the operating characteristic includes the density of a solid within a component of the manufacturing equipment. In an embodiment, the operating characteristic includes the density of a component manufactured by the manufacturing equipment. In an embodiment, the part includes a part for a vehicle. In an embodiment, the component includes a part for a bicycle. In an embodiment, the component includes a bicycle chain. In an embodiment, the component includes a gasket. In an embodiment, the component includes a fastener. In an embodiment, the component includes a part for a screw. In an embodiment, the component includes a part for a bolt. In an embodiment, the component includes a part for a printed circuit board. In an embodiment, the component includes a part for a capacitor. In an embodiment, the component includes a part for a resistor. In an embodiment, the component includes a part for an inductor. In an embodiment, the operating characteristic includes the chemical structure of a gas within a component of the manufacturing equipment.

In an embodiment, the operating characteristic includes the chemical structure of a liquid within a component of the manufacturing equipment. In an embodiment, the operating characteristic includes the chemical structure of a solid within a component of the manufacturing equipment. In an embodiment, the operating characteristic includes the chemical structure of a component manufactured by the manufacturing equipment. In an embodiment, the part includes a part for a vehicle. In an embodiment, the part includes a part for a bicycle. In an embodiment, the component includes a bicycle chain. In an embodiment, the part includes a gasket. In an embodiment, the part includes a fastener. In an embodiment, the component includes a part for a screw. In an embodiment, the part includes a part for a bolt. In an embodiment, the component includes a part for a printed circuit board. In an embodiment, the component includes a part for a capacitor.

In an embodiment, the component includes a part for a resistor. In an embodiment, the component includes a part for an inductor. In an embodiment, the data capture device includes an image capture device. In an embodiment, the data capture device includes a camera. In an embodiment, the data capture device includes a data measurement device. In an embodiment, the data capture device includes a sensor. In an embodiment, the data capture device includes a full spectrum camera. In an embodiment, the data capture device includes a radiographic imaging device. In an embodiment, the data capture device includes an X-ray imaging device. In an embodiment, the data capture device includes a non-visible light data capture device. In an embodiment, the data capture device includes a visible light data capture device. In an embodiment, the data capture device includes an acoustic data capture device. In an embodiment, the data capture device includes an image capture device. In an embodiment, the data capture device includes an optical imaging, detection, and ranging device. In an embodiment, the data capture device includes a point cloud data capture device. In an embodiment, the data capture device includes an infrared inspection device. In an embodiment, the data capture device includes an image capture device.

In embodiments, the data capture device includes a pressure sensor. In embodiments, the data capture device includes a temperature sensor. In embodiments, the data capture device includes a chemical sensor. In embodiments, the data capture device includes a standalone device. In embodiments, the data capture device includes one associated with a mobile device. In embodiments, the mobile device includes a smartphone. In embodiments, the mobile device includes a tablet. In embodiments, the raw data includes raw image data. In embodiments, the raw data includes raw measurement data. In embodiments, the portion of the manufacturing equipment within the point of interest includes a component of the manufacturing equipment. In embodiments, the portion of the manufacturing equipment within the point of interest includes a belt of the manufacturing equipment. In embodiments, the portion of the manufacturing equipment within the point of interest includes a component manufactured by the manufacturing equipment. In embodiments, the portion of the manufacturing equipment within the point of interest includes a bicycle chain manufactured by the manufacturing equipment.

In an embodiment, a method for detecting operational characteristics of a manufacturing equipment includes generating one or more image data sets using raw data captured by one or more data capture devices, identifying one or more values corresponding to a portion of the manufacturing equipment within a point of interest represented by the one or more image data sets, and recording the one or more values. The method further includes comparing the one or more recorded values to corresponding predicted values, generating a variance data set based on a comparison of the one or more recorded values with the corresponding predicted values, identifying operational characteristics of the manufacturing equipment based on the variance data, and generating a display indicative of the operational characteristics.

In an embodiment, the method also includes identifying a corrective action in response to identifying the operating characteristic. In an embodiment, the method also includes initiating the corrective action in response to identifying the operating characteristic. In an embodiment, the operating characteristic includes vibration of a component of the manufacturing equipment. In an embodiment, the operating characteristic includes a shape of a component of the manufacturing equipment. In an embodiment, the operating characteristic includes a size of a component of the manufacturing equipment. In an embodiment, the operating characteristic includes a deflection of a component of the manufacturing equipment. In an embodiment, the operating characteristic includes electromagnetic radiation of a component of the manufacturing equipment. In an embodiment, the operating characteristic includes a temperature of a component of the manufacturing equipment. In an embodiment, the operating characteristic includes a temperature of a gas within a component of the manufacturing equipment. In an embodiment, the operating characteristic includes a temperature of a liquid within a component of the manufacturing equipment. In an embodiment, the operating characteristic includes a temperature of a solid within a component of the manufacturing equipment. In an embodiment, the operating characteristic includes a pressure within a component of the manufacturing equipment. In an embodiment, the operating characteristic includes a pressure of a gas within a component of the manufacturing equipment. In an embodiment, the operating characteristic includes a pressure of a liquid within a component of the manufacturing equipment. In an embodiment, the operating characteristic includes a density of a gas within a component of the manufacturing equipment.

In an embodiment, the operating characteristic includes the density of a liquid within a component of the manufacturing equipment. In an embodiment, the operating characteristic includes the density of a solid within a component of the manufacturing equipment. In an embodiment, the operating characteristic includes the density of a component manufactured by the manufacturing equipment. In an embodiment, the part includes a part for a vehicle. In an embodiment, the component includes a part for a bicycle. In an embodiment, the component includes a bicycle chain. In an embodiment, the component includes a gasket. In an embodiment, the component includes a fastener. In an embodiment, the component includes a part for a screw. In an embodiment, the component includes a part for a bolt. In an embodiment, the component includes a part for a printed circuit board. In an embodiment, the component includes a part for a capacitor. In an embodiment, the component includes a part for a resistor. In an embodiment, the component includes a part for an inductor. In an embodiment, the operating characteristic includes the chemical structure of a gas within a component of the manufacturing equipment.

In an embodiment, the operating characteristic includes the chemical structure of a liquid within a component of the manufacturing equipment. In an embodiment, the operating characteristic includes the chemical structure of a solid within a component of the manufacturing equipment. In an embodiment, the operating characteristic includes the chemical structure of a component manufactured by the manufacturing equipment. In an embodiment, the part includes a part for a vehicle. In an embodiment, the part includes a part for a bicycle. In an embodiment, the component includes a bicycle chain. In an embodiment, the part includes a gasket. In an embodiment, the component includes a fastener. In an embodiment, the component includes a part for a screw. In an embodiment, the component includes a part for a bolt. In an embodiment, the component includes a part for a printed circuit board. In an embodiment, the component includes a part for a capacitor.

In an embodiment, the component includes a part for a resistor. In an embodiment, the component includes a part for an inductor. In an embodiment, the data capture device includes an image capture device. In an embodiment, the data capture device includes a camera. In an embodiment, the data capture device includes a data measurement device. In an embodiment, the data capture device includes a sensor. In an embodiment, the data capture device includes a full spectrum camera. In an embodiment, the data capture device includes a radiographic imaging device. In an embodiment, the data capture device includes an X-ray imaging device. In an embodiment, the data capture device includes a non-visible light data capture device. In an embodiment, the data capture device includes a visible light data capture device. In an embodiment, the data capture device includes an acoustic data capture device. In an embodiment, the data capture device includes an image capture device. In an embodiment, the data capture device includes an optical imaging, detection, and ranging device. In an embodiment, the data capture device includes a point cloud data capture device. In an embodiment, the data capture device includes an infrared inspection device. In an embodiment, the data capture device includes an image capture device.

In embodiments, the data capture device includes a pressure sensor. In embodiments, the data capture device includes a temperature sensor. In embodiments, the data capture device includes a chemical sensor. In embodiments, the data capture device includes a standalone device. In embodiments, the data capture device includes one associated with a mobile device. In embodiments, the mobile device includes a smartphone. In embodiments, the mobile device includes a tablet. In embodiments, the raw data includes raw image data. In embodiments, the raw data includes raw measurement data. In embodiments, the portion of the manufacturing equipment within the point of interest includes a component of the manufacturing equipment. In embodiments, the portion of the manufacturing equipment within the point of interest includes a belt of the manufacturing equipment. In embodiments, the portion of the manufacturing equipment within the point of interest includes a component manufactured by the manufacturing equipment. In embodiments, the portion of the manufacturing equipment within the point of interest includes a bicycle chain manufactured by the manufacturing equipment.

In an embodiment, a system for detecting operational characteristics of a manufacturing equipment includes at least one data capture device configured to capture raw data of a point of interest of the manufacturing equipment, a memory, and a processor. The memory includes instructions executable by the processor to: generate one or more image data sets using the captured raw data; identify one or more values corresponding to a portion of the manufacturing equipment within the point of interest represented by the one or more image data sets; record one or more values; compare the recorded one or more values with corresponding predicted values; generate a variance data set based on the comparison of the recorded one or more values with corresponding predicted values; identify operational characteristics of the manufacturing equipment based on the variance data, and generate a display indicative of the operational characteristics.

In an embodiment, the memory further includes instructions executable by the processor to identify a corrective action in response to identifying the operating characteristic. In an embodiment, the memory further includes instructions executable by the processor to initiate a corrective action in response to identifying the operating characteristic. In an embodiment, the operating characteristic includes vibration of a component of the manufacturing equipment. In an embodiment, the operating characteristic includes a shape of a component of the manufacturing equipment. In an embodiment, the operating characteristic includes a size of a component of the manufacturing equipment. In an embodiment, the operating characteristic includes a deflection of a component of the manufacturing equipment. In an embodiment, the operating characteristic includes electromagnetic radiation of a component of the manufacturing equipment. In an embodiment, the operating characteristic includes a temperature of a component of the manufacturing equipment. In an embodiment, the operating characteristic includes a temperature of a gas within a component of the manufacturing equipment. In an embodiment, the operating characteristic includes a temperature of a liquid within a component of the manufacturing equipment. In an embodiment, the operating characteristic includes a temperature of a solid within a component of the manufacturing equipment. In an embodiment, the operating characteristic includes a pressure within a component of the manufacturing equipment. In an embodiment, the operating characteristic includes a pressure of a gas within a component of the manufacturing equipment. In an embodiment, the operating characteristic includes a pressure of a liquid within a component of the manufacturing equipment. In an embodiment, the operating characteristic includes a density of a gas within a component of the manufacturing equipment.

In an embodiment, the operating characteristic includes the density of a liquid within a component of the manufacturing equipment. In an embodiment, the operating characteristic includes the density of a solid within a component of the manufacturing equipment. In an embodiment, the operating characteristic includes the density of a component manufactured by the manufacturing equipment. In an embodiment, the part includes a part for a vehicle. In an embodiment, the component includes a part for a bicycle. In an embodiment, the component includes a bicycle chain. In an embodiment, the component includes a gasket. In an embodiment, the component includes a fastener. In an embodiment, the component includes a part for a screw. In an embodiment, the component includes a part for a bolt. In an embodiment, the component includes a part for a printed circuit board. In an embodiment, the component includes a part for a capacitor. In an embodiment, the component includes a part for a resistor. In an embodiment, the component includes a part for an inductor. In an embodiment, the operating characteristic includes the chemical structure of a gas within a component of the manufacturing equipment.

In an embodiment, the operating characteristic includes the chemical structure of a liquid within a component of the manufacturing equipment. In an embodiment, the operating characteristic includes the chemical structure of a solid within a component of the manufacturing equipment. In an embodiment, the operating characteristic includes the chemical structure of a component manufactured by the manufacturing equipment. In an embodiment, the part includes a part for a vehicle. In an embodiment, the part includes a part for a bicycle. In an embodiment, the component includes a bicycle chain. In an embodiment, the part includes a gasket. In an embodiment, the component includes a fastener. In an embodiment, the component includes a part for a screw. In an embodiment, the component includes a part for a bolt. In an embodiment, the component includes a part for a printed circuit board. In an embodiment, the component includes a part for a capacitor.

In an embodiment, the component includes a part for a resistor. In an embodiment, the component includes a part for an inductor. In an embodiment, the data capture device includes an image capture device. In an embodiment, the data capture device includes a camera. In an embodiment, the data capture device includes a data measurement device. In an embodiment, the data capture device includes a sensor. In an embodiment, the data capture device includes a full spectrum camera. In an embodiment, the data capture device includes a radiographic imaging device. In an embodiment, the data capture device includes an X-ray imaging device. In an embodiment, the data capture device includes a non-visible light data capture device. In an embodiment, the data capture device includes a visible light data capture device. In an embodiment, the data capture device includes an acoustic data capture device. In an embodiment, the data capture device includes an image capture device. In an embodiment, the data capture device includes an optical imaging, detection, and ranging device. In an embodiment, the data capture device includes a point cloud data capture device. In an embodiment, the data capture device includes an infrared inspection device. In an embodiment, the data capture device includes an image capture device.

In embodiments, the data capture device includes a pressure sensor. In embodiments, the data capture device includes a temperature sensor. In embodiments, the data capture device includes a chemical sensor. In embodiments, the data capture device includes a standalone device. In embodiments, the data capture device includes one associated with a mobile device. In embodiments, the mobile device includes a smartphone. In embodiments, the mobile device includes a tablet. In embodiments, the raw data includes raw image data. In embodiments, the raw data includes raw measurement data. In embodiments, the portion of the manufacturing equipment within the point of interest includes a component of the manufacturing equipment. In embodiments, the portion of the manufacturing equipment within the point of interest includes a belt of the manufacturing equipment. In embodiments, the portion of the manufacturing equipment within the point of interest includes a component manufactured by the manufacturing equipment. In embodiments, the portion of the manufacturing equipment within the point of interest includes a bicycle chain manufactured by the manufacturing equipment.

In an embodiment, a computer vision system for detecting operating characteristics of a manufacturing equipment includes at least one data capture device configured to capture raw data of a point of interest of the manufacturing equipment, a memory, and a processor. The memory includes instructions executable by the processor to: generate one or more image data sets using the captured raw data; visually identify one or more values corresponding to a portion of the manufacturing equipment within the point of interest represented by the one or more image data sets; record the one or more values; visually compare the recorded one or more values to corresponding predicted values; generate a variance data set based on the comparison of the recorded one or more values to the corresponding predicted values; identify an operating characteristic of the manufacturing equipment based on the variance data; compare the operating characteristic to a threshold; determine whether the operating characteristic is within an acceptable range based on whether the operating characteristic is greater than the threshold; and generate an indication of the operating characteristic.

In an embodiment, the computer vision system is trained by a deep learning system. In an embodiment, the deep learning system is configured to train the computer vision system using at least one training dataset. In an embodiment, the at least one training dataset includes image data. In an embodiment, the at least one training dataset includes non-image data.

In an embodiment, a computer vision system for detecting operational characteristics of a device includes at least one data capture device configured to capture raw data of a point of interest of the device, a memory, and a processor. The memory includes instructions executable by the processor to: generate one or more image data sets using the captured raw data; visually identify one or more values corresponding to a portion of the device within the point of interest represented by the one or more image data sets; record the one or more values; visually compare the recorded one or more values with corresponding predicted values; and generate a variance data set based on the comparison of the recorded one or more values with the corresponding predicted values. Identify an operational characteristic of the device based on the variance data, compare the operational characteristic to a threshold, determine whether the operational characteristic is within an acceptable range based on whether the operational characteristic is greater than the threshold, and generate an indication of the operational characteristic.

In an embodiment, the apparatus includes an agitator. In an embodiment, the apparatus includes a vehicle control surface vibration device. In an embodiment, the apparatus includes a catalytic reactor. In an embodiment, the apparatus includes a compressor. In an embodiment, the apparatus includes a conveyor. In an embodiment, the apparatus includes a lifter. In an embodiment, the apparatus includes a pipeline. In an embodiment, the apparatus includes an electric powertrain. In an embodiment, the apparatus includes a robotic assembly device. In an embodiment, the apparatus includes an apparatus in a gas production environment. In an embodiment, the apparatus includes an apparatus in a pharmaceutical environment.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with the use of an analog crosspoint switch to collect a variable group of analog sensor inputs for remote monitoring is disclosed.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with upfront signal conditioning on a multiplexer to improve signal-to-noise ratio in remote monitoring.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with multiplexed continuous alarm monitoring capabilities with remote monitoring.

In one embodiment, a system is disclosed that uses a distributed CPLD chip with multiple MUXes and a dedicated bus for logical control of the data collection units, and performs remote monitoring to collect data using a computer vision system in an industrial environment.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with high amperage input capabilities using solid-state relays, providing a design topology with remote monitoring.

In an embodiment, a system for data collection in an industrial environment using a computer vision system has analog sensor channels with remote monitoring and the ability to power down at least one of the component boards.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with unique electrostatic protection for triggers and vibration inputs with remote monitoring is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an accurate voltage reference for the A/D zero reference, allowing for remote monitoring.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a phase-locked loop bandpass tracking filter for remote monitoring of low speed RPM and phase information.

In an embodiment, a system for data collection using a computer vision system is disclosed, which uses on-board timers to digitally derive phase for input and trigger channels for remote monitoring in an industrial environment.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a peak detector for autoscaling that is routed to a separate analog-to-digital converter for peak detection by remote monitoring.

In an embodiment, a system is disclosed for data collection in an industrial environment using a computer vision system to route raw or buffered trigger channels to other analog channels for remote monitoring.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed that uses higher input oversampling for a delta-sigma A/D for a lower sampling rate output to minimize AA filter requirements in remote monitoring.

In one embodiment, a system is disclosed that uses a CPLD as a clock distributor for a delta-sigma analog-to-digital converter in a data collection system in an industrial environment using a computer vision system, thereby achieving a lower sampling rate for remote monitoring without the need for digital resampling.

In an embodiment, a system is disclosed for collecting data in an industrial environment using a computer vision system with long blocks of data at a high sampling rate, as opposed to multiple data sets captured at different sampling rates for remote monitoring.

In one embodiment, a data collection system for industrial environments is disclosed that uses a computer vision system to store calibration data along with maintenance history on a remotely monitored board card set.

In an embodiment, a system for data collection in an industrial environment using a computer vision system with rapid route creation using hierarchical templates with remote monitoring is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with intelligent management of data collection bands through remote monitoring is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed that employs a neural net expert system for intelligent management of data collection bands through remote monitoring.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with the use of a database hierarchy for sensor data analysis with remote monitoring.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed that has an expert system GUI graphical approach to defining intelligent data collection bands and diagnostics for an expert system with remote monitoring.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with a graphical approach for remotely monitored back-calculation definition is disclosed.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment, proposing a method for remotely monitoring bearing analysis.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with remote monitoring and transient signal analysis to detect and analyze torsional vibrations.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with improved integration using both analog and digital methods for remote monitoring.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed that has adaptive scheduling techniques for continuous monitoring of analog data in a local environment with remote monitoring.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with remotely monitored data acquisition parking facilities.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a self-contained data collection box with remote monitoring.

In one embodiment, a system is disclosed that uses a computer vision system to collect data and perform remote monitoring in an industrial environment with SD card storage.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with enhanced on-board statistical capabilities for continuous monitoring via remote monitoring.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment using ambient noise, local noise, and vibration noise for remote monitoring prediction.

In an embodiment, a system for data collection in an industrial environment is disclosed that uses a computer vision system to create smart routes that change paths based on input data or alarms, simultaneously providing dynamic data for analysis or correlation via remote monitoring.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a smart ODS with remote monitoring and forwarding capabilities.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a hierarchical multiplexer with remote monitoring.

In one embodiment, a system is disclosed that uses a computer vision system to collect data for remote monitoring in industrial environments with overloaded identification sensors.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an inclinometer with RF identification and remote monitoring.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with continuous, remotely monitored ultrasonic monitoring.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with cloud-based machine pattern recognition based on the fusion of analog industrial sensors for remote monitoring.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with cloud-based machine pattern analysis of status information from multiple analog industrial sensors to provide predicted status information for remotely monitored industrial systems.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a cloud-based policy automation engine for IoT with creation, deployment, and management of IoT devices with remote monitoring is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with on-device sensor fusion and data storage for remote monitoring of industrial IoT devices.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a self-organizing data marketplace for industrial IoT data with remote monitoring.

In an embodiment, a system for collecting data in an industrial environment using a computer vision system self-organizes the data pool based on utilization and/or yield metrics while providing remote monitoring.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with training AI models based on industry-specific feedback with remote monitoring.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a self-organized group of industrial data collectors performing remote monitoring.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT distributed ledger for remote monitoring.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a self-organizing collector with remote monitoring.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a network-sensitive collector for remote monitoring.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with remotely organized collectors with remote monitoring.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with self-organizing storage for a multi-sensor data collector with remote monitoring is disclosed.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with self-organizing network coding for a multi-sensor data network with remote monitoring.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment is disclosed that has a wearable tactile user interface for an industrial sensor data collector with vibration, heat, electrical, and/or acoustic outputs.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment is disclosed, having a heat map displaying collected data for AR/VR with remote monitoring.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with automatically coordinated AR/VR visualization of data collected by a remotely monitored data collector.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT platform that performs remote monitoring.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment having an IoT data adapter for receiving data input and establishing a connection with one or more available IoT cloud platforms for publishing the data for remote monitoring is disclosed.

In one embodiment, a system for collecting data using a computer vision system in an industrial environment is disclosed, which includes a condition detector for remotely monitoring and detecting conditions associated with connection attempts made by an IoT data adapter to one or more IoT cloud platforms.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT data adapter equipped with an adaptive engine with remote monitoring.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with the use of machine learning to prepare data packets or streams for remote monitoring.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a data marketplace that provides a pool of cloud networking platforms available for remote monitoring.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment that has a messaging utility that provides messages to a cloud platform user interface indicating the availability of new data sources and instructions on how to integrate and use the data sources.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to maintain first and second transmission limits based on the received arrival rate and success rate of delivery feedback messages, and that limits the transmission of messages based on the transmission limits with remote monitoring.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to remotely monitor and restrict the transmission of further messages that have not yet been acknowledged as successfully delivered according to a window size.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to maintain an estimate of the rate of loss events and use it to adjust the rate of redundancy messages with remote monitoring.

In an embodiment, a system is disclosed for data communication between nodes having an estimated rate of loss events, in which the error correction code used to determine the selected redundancy message using a computer vision system is based on the estimated rate of loss events with remote monitoring.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of applying forward error correction based on received messages describing channel characteristics with remote monitoring.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to maintain/set timers based on the occurrence of delivery command events, allowing remote monitoring to use the timers to delay the transmission of feedback messages.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of maintaining/setting timers based on the occurrence of a distribution command event, allowing remote monitoring to delay timer-based changes to congestion window size.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system, which has the ability to maintain/set a timer based on the occurrence of a delivery command event, delay changes to the congestion window size based on the timer, and cancel changes to the congestion window size when a feedback message indicating successful delivery is received via remote monitoring.

In an embodiment, a system for data communication using a computer vision system between nodes with the ability to remotely monitor and configure new connections using maintained data characterizing current/previous connections is disclosed.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to remotely monitor and configure new connections using maintenance data that characterizes the error rates of current/previous connections.

In an embodiment, a system is disclosed for data communication between nodes with the ability to configure new connections using maintained data characterizing timing variations of current/previous connections using a computer vision system for remote monitoring.

In an embodiment, a system is disclosed for data communication between nodes that uses a computer vision system to remotely monitor and has the ability to configure new connections using maintained data characterizing the bandwidth of current/previous connections.

In an embodiment, a system is disclosed for data communication between nodes with the ability to configure new connections using maintained data characterizing the round-trip times of current/previous connections with remote monitoring using a computer vision system.

In an embodiment, a system is disclosed for data communication between nodes with the ability to configure new connections using maintained data characterizing communication control parameters of current/previous connections using a computer vision system for remote monitoring.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to configure new connections using maintained data that characterizes forward error correction parameters of current/previous connections.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system, the system having a data store for maintaining data characterizing one or more current or previous data communication connections, and a connection initiation module for initiating new data communication connections based on the maintained data while remotely monitoring the nodes.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of transmitting a first subset of data messages over a low-latency data path and a second subset of messages over a high-latency data path with remote monitoring.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of transmitting a first subset of time-critical data messages over a low-latency data path and a second subset of messages over a high-latency data path for remote monitoring.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of transmitting a first initial subset of data messages over a low-latency data path, and a second subset of messages later available for remote monitoring over a high-latency data path.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of transmitting a first subset of acknowledgement messages over a low-latency data path and a second subset of data messages over a high-latency data path with remote monitoring.

In an embodiment, a system for data communication using a computer vision system is provided between nodes capable of transmitting a first subset.
Remote monitoring of complementary/redundant data messages on a low-latency data path and a second subset of data messages on a high-latency data path is disclosed.

In an embodiment, a system is disclosed for communicating data between nodes using a computer vision system with a degree of redundancy associated with each message based on the message's position in a transmission order with remote monitoring.

In an embodiment, a system is disclosed for data communication between nodes using a computer vision system with redundancy associated with each message that increases with the message's location and is non-decreasing due to remote monitoring.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes in response to receiving feedback messages via remote monitoring, with a degree of redundancy associated with each message based on the message's position in the transmission order.

In an embodiment, a system is disclosed for data communication between nodes using a computer vision system to add or remove redundancy messages from a queue in response to receiving a feedback message based on the message's position in a transmission order, the redundancy messages being added or removed from the queue based on the feedback message with remote monitoring.

In one embodiment, a system for data communication between nodes using a computer vision system is disclosed that has the ability to adjust the number of messages sent over each of multiple different data paths having different communication protocols if the data path is determined to be altering the flow of messages through remote monitoring.

In one embodiment, a data communication system between nodes is disclosed that has the ability to adjust the number of messages sent on each of multiple different data paths with different communication protocols when a computer vision system is used to determine that a data path is changing the flow of messages at an initial split based on a previous communication connection with remote monitoring.

In an embodiment, a system for data communication between nodes is disclosed that has the ability to modify/add/delete redundancy information associated with encoded data as it travels from node to node over a channel based on channel characteristics with remote monitoring using a computer vision system.

In an embodiment, a system for data communication between nodes is disclosed that has the ability to transmit FEC packets at an estimated rate of loss events (isolated packet losses or bursts of consecutive packets) with remote monitoring using a computer vision system.

In an embodiment, a system for data communication between nodes using a computer vision system with hybrid coding, TCP, and pacing of packet transmissions with remote monitoring is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes having a forward error correction code structure that interleaves groups of message packets with parity packets, with coding across overlapping groups of message packets with remote monitoring.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system with a variant of TCP that combines delay-based backoff with a stable window increase function with remote monitoring.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with the use of analog crosspoint switches to collect a variable group of analog sensor inputs for predictive maintenance is disclosed.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with upfront signal conditioning on a multiplexer to improve signal-to-noise ratio in predictive maintenance.

In one embodiment, a system is provided that uses a computer vision system to collect data in an industrial environment with continuous monitoring alarm functionality for multiplexers with predictive maintenance.

In one embodiment, a system is disclosed that uses a distributed CPLD chip with multiple MUXes and a dedicated bus for logical control of the data collection units, and uses a computer vision system to collect data in an industrial environment where predictive maintenance is performed.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with high amperage input capabilities using solid-state relays, providing a design topology with predictive maintenance.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment is disclosed that has the ability to power down at least one of an analog sensor channel and a component board with predictive maintenance.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with unique electrostatic protection for triggers and vibration inputs with predictive maintenance.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with an accurate voltage reference for A/D zero reference with predictive maintenance.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a phase-locked loop bandpass tracking filter to obtain low-speed RPM and phase information for predictive maintenance.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment, using on-board timers to digitally derive phase for input and trigger channels for predictive maintenance.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment having a peak detector for autoscaling that is routed to another analog-to-digital converter for peak detection with predictive maintenance.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with routing of raw or buffered trigger channels to other analog channels involving predictive maintenance.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with the use of higher input oversampling for a delta-sigma A/D for a lower sampling rate output to minimize AA filter requirements in predictive maintenance.

In an embodiment, a data collection system using a computer vision system in an industrial environment is disclosed that uses a CPLD as a clock distributor for a delta-sigma analog-to-digital converter to achieve low sampling rates without the need for digital resampling in predictive maintenance.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with long blocks of data at a high sampling rate, as opposed to multiple sets of data acquired at different sampling rates in predictive maintenance.

In one embodiment, a system for collecting data in an industrial environment is disclosed that uses a computer vision system to store calibration data with maintenance history on a board card set with predictive maintenance.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with rapid path creation using hierarchical templates with predictive maintenance.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with intelligent management of data collection bands with predictive maintenance.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a neural net expert system that uses intelligent management of data collection bands with predictive maintenance.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with the use of a database hierarchy in sensor data analysis involving predictive maintenance.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed that has an expert system GUI graphical approach to defining intelligent data collection bands and diagnostics for an expert system with predictive maintenance.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with a graphical approach for back-calculation definition with predictive maintenance is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment that proposes a bearing analysis method involving predictive maintenance.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment for torsional vibration detection/analysis using transient signal analysis with predictive maintenance.

In an embodiment, a system for data collection using computer vision systems in industrial environments with predictive maintenance and improved integration using both analog and digital methods is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with adaptive scheduling techniques for continuous monitoring of analog data in a local environment with predictive maintenance.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with data collection parking lot functionality with predictive maintenance.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a self-sufficient data collection box with predictive maintenance.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with SD card storage for predictive maintenance.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with enhanced on-board statistical capabilities for continuous monitoring with predictive maintenance.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment using ambient noise, local noise, and vibration noise for predictive maintenance forecasting.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with smart routes that change routes based on input data or alarms, simultaneously providing dynamic data for analysis or correlation for predictive maintenance.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a smart ODS and forwarding capabilities that provides predictive maintenance.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a hierarchical multiplexer that performs predictive maintenance.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with overloaded identification sensors for predictive maintenance.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an inclinometer with RF identification and predictive maintenance.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with continuous ultrasonic monitoring for predictive maintenance.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with cloud-based machine pattern recognition based on the fusion of remote analog industrial sensors with predictive maintenance.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with cloud-based machine pattern analysis of condition information from multiple analog industrial sensors to provide predictive condition information for industrial systems with predictive maintenance.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a cloud-based policy automation engine for IoT with the creation, deployment, and management of IoT devices with predictive maintenance is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with on-device sensor fusion and data storage for industrial IoT devices with predictive maintenance.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a self-organizing data marketplace for industrial IoT data with predictive maintenance.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with self-organization of data pools based on utilization and/or yield metrics with predictive maintenance.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with industry-specific feedback-based training AI models involving predictive maintenance.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a self-organized swarm of industrial data collectors that perform predictive maintenance.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT distributed ledger for predictive maintenance.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with self-organizing collectors that perform predictive maintenance.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a network of sensitive collectors that perform predictive maintenance.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with remotely coordinated collectors performing predictive maintenance.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with self-organizing storage for multi-sensor data collectors that perform predictive maintenance.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with self-organizing network coding for multi-sensor data networks with predictive maintenance.

In an embodiment, a system for data collection in an industrial environment using a computer vision system is disclosed, having a wearable tactile user interface for an industrial sensor data collector, the system having vibration, heat, electrical and/or acoustic outputs with predictive maintenance.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a heat map displaying the collected data for AR/VR with predictive maintenance.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with automatically adjusted AR/VR visualization of data collected by data collection devices with predictive maintenance.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT platform that performs predictive maintenance.

In an embodiment, a computer vision system is disclosed for collecting data in an industrial environment having an IoT data adapter for receiving data input, and establishing a connection with one or more available IoT cloud platforms for publishing the data in a predictive maintenance system.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment having a condition detector for detecting conditions associated with connection attempts by an IoT data adapter to one or more IoT cloud platforms with predictive maintenance.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT data adapter equipped with an adaptive engine with predictive maintenance.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with the use of machine learning to prepare data packets or streams for predictive maintenance.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment having a data marketplace that provides a pool of cloud networking platforms available for predictive maintenance.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a messaging utility that provides messages to a cloud platform user interface indicating the availability of new data sources, and integrates and directs the use of data sources through predictive maintenance.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to maintain first and second transmission limits based on the received arrival rate and success rate of delivery feedback messages, and that limits the transmission of messages based on the transmission limits during predictive maintenance.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to limit the transmission of further messages that have not yet been acknowledged as successfully delivered according to a window size with predictive maintenance.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that has the ability to maintain an estimate of the rate of loss events and use it to adjust the rate of redundancy messages in predictive maintenance.

In an embodiment, a system is disclosed for data communication between nodes having an estimated rate of loss events, in which the error correction code used to determine the selected redundant message using a computer vision system is based on the estimated rate of loss events involving predictive maintenance.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system that has the capability to apply forward error correction based on received messages describing channel characteristics with predictive maintenance.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to maintain/set timers based on the occurrence of a distribution command event, and that can delay the transmission of feedback messages using timers with predictive maintenance.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of maintaining/setting timers based on the occurrence of a distribution command event, and that predictively maintains and delays timer-based changes to congestion window size.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system, which has the ability to maintain/set a timer based on the occurrence of a delivery command event, delay changes to the congestion window size based on the timer, and cancel changes to the congestion window size when a feedback message indicating successful delivery is received through predictive maintenance.

In an embodiment, a system is disclosed for data communication between nodes that uses a computer vision system to configure new connections using maintained data characterizing current/previous connections with predictive maintenance.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to configure new connections using maintained data characterizing the error rates of current/previous connections with predictive maintenance.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to configure new connections using maintained data that characterizes timing variations of current/previous connections with predictive maintenance.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to configure new connections using maintained data characterizing the bandwidth of current/previous connections with predictive maintenance.

In one embodiment, a data communication system using a computer vision system between nodes is disclosed that has the ability to configure new connections using maintained data characterizing round-trip times of current and past connections with predictive maintenance.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to configure new connections using maintenance data that characterizes communication control parameters of current/previous connections with predictive maintenance.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to configure new connections using maintained data characterizing forward error correction parameters of current/previous connections with predictive maintenance.

In one embodiment, a system for communicating data between nodes using a computer vision system is disclosed, the system having a data store for maintaining data characterizing one or more current or previous data communication connections, and a connection initiation module for initiating new data communication connections based on the maintained data with predictive maintenance.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between a node capable of transmitting a first subset of data messages over a low-latency data path and a node capable of transmitting a second subset of messages over a high-latency data path with predictive maintenance.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to transmit a first subset of time-critical data messages over a low-latency data path, and a system that transmits a second subset of messages over a high-latency data path for predictive maintenance.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to transmit a first initial subset of data messages over a low-latency data path, and a second subset of messages that is later available over a high-latency data path for predictive maintenance.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to transmit a first subset of acknowledgement messages over a low-latency data path and a second subset of data messages over a high-latency data path with predictive maintenance.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to transmit a first subset of supplemental/redundant data messages over a low-latency data path, and a system that transmits a second subset of data messages over a high-latency data path with predictive maintenance.

In an embodiment, a system is disclosed for communicating data between nodes using a computer vision system with a degree of redundancy associated with each message that is based on the message's position in a transmission order with predictive maintenance.

In an embodiment, a system is disclosed for communicating data between nodes using a computer vision system, with a degree of redundancy associated with each message increasing as the message's location decreases with predictive maintenance.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes in response to receiving feedback messages involving predictive maintenance, with a degree of redundancy associated with each message based on the message's position in a transmission order.

In an embodiment, a system is disclosed for data communication between nodes using a computer vision system to add or remove redundant messages from a queue in response to receiving a feedback message based on the message's position in a transmission order, the redundant messages being added or removed from the queue based on the feedback message involving predictive maintenance.

In one embodiment, a data communication system using a computer vision system is provided, which has the ability to adjust the number of messages sent over each of multiple different data paths with different communication protocols between nodes when it is determined that a data path is altering the flow of messages for predictive maintenance.

In an embodiment, a system for data communication between nodes using a computer vision system is disclosed that has the ability to adjust the number of messages sent over each of multiple different data paths having different communication protocols when it is determined that the data paths are altering the message flow, and performs initial division based on previous communication connections with predictive maintenance.

In an embodiment, a system for data communication between nodes is disclosed that has the ability to use a computer vision system to modify/add/remove redundancy information associated with encoded data as it travels from node to node over a channel based on channel characteristics with predictive maintenance.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to transmit FEC packets at an estimated rate for loss events (isolated packet losses or bursts of consecutive packets) with predictive maintenance.

In an embodiment, a system for data communication between nodes using a computer vision system with hybrid coding, TCP, and pacing of packet transmissions with predictive maintenance is disclosed.

In an embodiment, a system for data communication between nodes using a computer vision system is disclosed that has a forward error correction code structure that interleaves groups of message packets with parity packets, and has coding across overlapping groups of message packets with predictive maintenance.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system with a variant of TCP that combines delay-based backoff with a stable window growth function with predictive maintenance.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment is disclosed that uses an analog crosspoint switch to collect a variable group of analog sensor inputs for pattern recognition.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with upfront signal conditioning using a multiplexer to improve signal-to-noise ratio for pattern recognition.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with multiplexed continuous monitoring alarm functionality using pattern recognition.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment, using a distributed CPLD chip with multiple MUXs and a dedicated bus for logical control of the pattern recognition data collection unit.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in industrial environments with high amperage input capabilities using a design topology based on solid-state relays and pattern recognition.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment is disclosed that has the ability to power down at least one component board with analog sensor channels and pattern recognition.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with unique electrostatic protection for triggering and vibration input with pattern recognition.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an accurate voltage reference for A/D zero reference through pattern recognition.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a phase-locked loop bandpass tracking filter for pattern recognition to obtain low-speed RPM and phase information.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment, using an on-board timer with pattern recognition to digitally derive phase for input and trigger channels.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment having a peak detector for autoscaling that is routed to another analog-to-digital converter for peak detection by pattern recognition.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with routing of a raw or buffered trigger channel to other analog channels with pattern recognition.

In an embodiment, a system for data collection using computer vision systems in industrial environments is disclosed that has the use of higher input oversampling for delta-sigma A/Ds for low sampling rate outputs to minimize the requirement for AA filters in pattern recognition.

In one embodiment, a data collection system using a computer vision system in an industrial environment is disclosed, which uses a CPLD as a clock distributor for a delta-sigma analog-to-digital converter to achieve low sampling rates without the need for digital resampling through pattern recognition.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with long blocks of data at a high sampling rate, as opposed to multiple data sets taken at different sampling rates using pattern recognition.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment where calibration data with maintenance history is stored on board cards configured with pattern recognition.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with rapid route creation capabilities using hierarchical templates based on pattern recognition.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with intelligent management of data collection bands through pattern recognition is disclosed.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a neural net expert system that uses pattern recognition to intelligently manage data collection bands.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with the use of a database hierarchy in sensor data analysis involving pattern recognition is disclosed.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an expert system GUI graphical approach to defining intelligent data collection bands and expert system diagnostics using pattern recognition.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with a graphical approach for back-calculation definition through pattern recognition is disclosed.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment, proposing a bearing analysis method using pattern recognition.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment for the detection/analysis of torsional vibrations using transient signal analysis with pattern recognition.

In an embodiment, a system is disclosed for collecting data using computer vision systems in industrial environments with improved integration using both analog and digital methods with pattern recognition.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed that has an adaptive scheduling technique for continuous monitoring of analog data in the local environment using pattern recognition.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with a parking lot function that uses pattern recognition data acquisition is disclosed.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a self-sufficient data collection box equipped with pattern recognition.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with SD card storage and pattern recognition.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with enhanced on-board statistical capabilities for continuous monitoring through pattern recognition.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment that uses ambient noise, local noise, and vibration noise for pattern recognition prediction.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with smart routes that change routes based on input data or alarms, simultaneously providing dynamic data for analysis or correlation through pattern recognition.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with smart ODS and forwarding capabilities through pattern recognition.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a hierarchical multiplexer equipped with pattern recognition.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a plethora of identification sensors through pattern recognition.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment having RF identification and inclinometers with pattern recognition.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with continuous ultrasonic monitoring using pattern recognition.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with cloud-based machine pattern recognition based on fusion with remote analog industrial sensor pattern recognition.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with cloud-based, machine pattern analysis of status information from multiple analog industrial sensors to provide predictive status information for the industrial system through pattern recognition.

In an embodiment, a system for data collection using computer vision systems in industrial environments with a cloud-based policy automation engine for IoT with pattern recognition for the creation, deployment, and management of IoT devices is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with on-device sensor fusion and data storage for industrial IoT devices with pattern recognition is disclosed.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a self-organizing data market for industrial IoT data through pattern recognition.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with self-organization of the data pool based on utilization and/or yield metrics using pattern recognition.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with training AI models based on industry-specific feedback involving pattern recognition.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a self-organized group of industrial data collectors equipped with pattern recognition.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT distributed ledger equipped with pattern recognition.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment having a self-organizing collector with pattern recognition is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a network sensitive collector equipped with pattern recognition.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with remotely organized collectors equipped with pattern recognition is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with self-organizing storage for a multi-sensor data collector with pattern recognition is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with self-organizing network coding for multi-sensor data networks with pattern recognition is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment is disclosed that has a wearable tactile user interface for an industrial sensor data collector with vibration, heat, electrical, and/or sound outputs with pattern recognition.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment is disclosed, having a heat map that displays collected data for AR/VR using pattern recognition.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with automatically adjusted AR/VR visualization of data collected by the data collector using pattern recognition.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT platform equipped with pattern recognition.

In an embodiment, a system for data collection using a computer vision system in an industrial environment having an IoT data adapter for receiving data input is disclosed, which establishes a connection with one or more available IoT cloud platforms for publishing data for pattern recognition.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment, having a condition detector for using pattern recognition to detect conditions associated with connection attempts made by an IoT data adapter to one or more IoT cloud platforms.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment that includes an IoT data adapter with an adaptive engine that has pattern recognition.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with the use of machine learning to prepare data packets or streams for pattern recognition.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment having a data marketplace that provides a pool of cloud networking platforms available for pattern recognition.

In an embodiment, a system for data collection using computer vision systems in an industrial environment is disclosed, having a messaging utility that provides messages to a cloud platform user interface indicating the availability of new data sources and instructions for integrating and using data sources through pattern recognition.

In one embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to maintain first and second transmission limits based on the received arrival rate and success rate of delivery feedback messages, and that limits the transmission of messages based on pattern recognition transmission limits.

In an embodiment, a system for data communication using a computer vision system between nodes is disclosed that has the ability to restrict the transmission of further messages that have not yet been recognized as successfully delivered according to a window size using pattern recognition.

In one embodiment, a system is disclosed for data communication using a computer vision system between nodes that has the ability to maintain an estimate of the rate of loss events and use it to adjust the rate of redundancy messages through pattern recognition.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes having an estimated rate of loss events, where the error correction code used to determine the selected redundancy message is based on the estimated rate of loss events using pattern recognition.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of applying forward error correction based on received messages that describe channel characteristics using pattern recognition.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to maintain/set timers based on the occurrence of delivery order events, and that can delay the transmission of feedback messages using timers with pattern recognition.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of maintaining/setting timers based on the occurrence of a distribution command event, and that can delay changes to congestion window sizes based on a pattern-recognition timer.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system, which maintains/sets a timer based on the occurrence of a delivery order event, delays changes to the congestion window size based on the timer, and cancels the change to the congestion window size when a feedback message indicating successful delivery is received through pattern recognition.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes with the ability to create new connections using maintained data that characterizes current and previous connections through pattern recognition.

In an embodiment, a system for data communication between nodes is disclosed that has the ability to configure new connections using maintained data that characterizes the error rates of current/previous connections through pattern recognition using a computer vision system.

In an embodiment, a system for data communication between nodes is disclosed that has the ability to configure new connections using maintained data that characterizes timing variations of current/previous connections through pattern recognition using a computer vision system.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to configure new connections using maintained data characterizing the bandwidth of current/previous connections and has pattern recognition.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to configure new connections using maintained data that characterizes the round-trip times of current/previous connections using pattern recognition.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to configure new connections using maintained data that characterizes communication control parameters of current/previous connections using pattern recognition.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to configure new connections using maintained data that characterizes forward error correction parameters of current/previous connections using pattern recognition.

In one embodiment, a system for communicating data between nodes using a computer vision system is disclosed, the system having a data store for maintaining data characterizing one or more current or previous data communication connections, and a connection initiation module for initiating new data communication connections based on the maintained data using pattern recognition.

In one embodiment, a system is disclosed for data communication using a computer vision system between nodes capable of transmitting a first subset of data messages over a low-latency data path and a second subset of messages over a high-latency data path using pattern recognition.

In one embodiment, a system is disclosed for data communication using a computer vision system between nodes capable of using pattern recognition to transmit a first subset of time-critical data messages over a low-latency data path and a second subset of messages over a high-latency data path.

In one embodiment, a system is disclosed for data communication using a computer vision system between nodes capable of using pattern recognition to transmit a first initial subset of data messages over a low-latency data path and subsequently a second subset of available messages over a high-latency data path.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the capability to use pattern recognition to transmit a first subset of acknowledgement messages over a low-latency data path and a second subset of data messages over a high-latency data path.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of using pattern recognition to transmit a first subset of supplemental/redundant data messages over a low-latency data path and a second subset of data messages over a high-latency data path.

In an embodiment, a system is disclosed for communicating data between nodes using a computer vision system with a degree of redundancy associated with each message that is based on the message's position in a transmission order using pattern recognition.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes with a degree of redundancy associated with each message that increases as the message's location decreases with pattern recognition.

In an embodiment, a system is disclosed for data communication between nodes using a computer vision system, with a degree of redundancy associated with each message, in response to receiving feedback messages through pattern recognition based on the message's position in the transmission order.

In an embodiment, a system is disclosed for data communication between nodes using a computer vision system to add or remove redundant messages from a queue in response to receiving a feedback message based on the message's position in a transmission order, with the redundant messages having a degree of redundancy associated with each message, and the feedback message using pattern recognition.

In one embodiment, a data communication system between nodes is disclosed that has the ability to adjust the number of messages sent on each of multiple different data paths with different communication protocols when a computer vision system determines that the data path is altering the flow of messages through pattern recognition.

In an embodiment, a system for data communication between nodes is disclosed that has the ability to adjust the number of messages sent over each of multiple different data paths having different communication protocols when a computer vision system is used to determine that the data path is altering the initial division of the message flow based on previous communication connections involving pattern recognition.

In an embodiment, a computer vision system is used to communicate data between nodes with the ability to modify/add/delete redundant information. As encoded data travels from node to node over a channel, information related to the data can be derived based on channel characteristics through pattern recognition.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of transmitting FEC packets at an estimated rate of loss events (isolated packet losses or bursts of consecutive packets) using pattern recognition.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes, combining packet transmission encoding using pattern recognition, TCP, and pacing.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes having a forward error correcting code configuration that interleaves groups of message packets with parity packets and uses pattern recognition to encode across overlapping groups of message packets.

In one embodiment, a system is disclosed for data communication using a computer vision system between nodes that has a variation of TCP that combines delay-based backoff with a stable window increasing function using pattern recognition.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment is disclosed that uses analog crosspoint switches to collect a variable group of analog sensor inputs for manufacturing.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with upfront signal conditioning on a multiplexer for improved signal-to-noise ratio for manufacturing.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with multiplexed continuous monitoring alarm functionality for manufacturing.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment using a distributed CPLD chip with multiple MUXs for manufacturing and a dedicated bus for logical control of the data collection units.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with high amperage input capabilities using solid-state relays and a design topology for manufacturing are disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment having power-down capabilities for at least one of analog sensor channels and manufacturing component boards is disclosed.

In one embodiment, a system for data collection using a computer vision system in an industrial environment with unique electrostatic protection for manufacturing triggers and vibration inputs is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with an accurate voltage reference for A/D zero reference for manufacturing is disclosed.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with low RPM for manufacturing and a phase-locked loop bandpass tracking filter to obtain phase information.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment using on-board manufacturing timers to digitally derive phase for input and trigger channels.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed, with a peak detector for autoscaling routed to another analog-to-digital converter for peak detection for manufacturing.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with routing of a raw or buffered trigger channel to other analog channels for manufacturing.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed that uses higher input oversampling for a delta-sigma A/D for a lower sampling rate output to minimize AA filter requirements for manufacturing.

In an embodiment, a system for data collection using computer vision systems in an industrial environment is disclosed that uses a CPLD as a clock distributor for a delta-sigma analog-to-digital converter to achieve lower sampling rates without requiring digital resampling for manufacturing.

In an embodiment, a system is disclosed for data collection using a computer vision system in an industrial environment with long blocks of data at a high sampling rate, as opposed to multiple sets of data acquired at different sampling rates for manufacturing.

In an embodiment, a system for data collection in an industrial environment is disclosed that uses a computer vision system to store calibration data with maintenance history on a board card set for manufacturing.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with rapid route creation capabilities using hierarchical templates for manufacturing.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with intelligent management of data collection bands for manufacturing is disclosed.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a neural net expert system that uses intelligent management of data collection bands for manufacturing.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with the use of a database hierarchy in analyzing sensor data for manufacturing is disclosed.

In an embodiment, a system is disclosed that uses a computer vision system to perform data collection in an industrial environment with an expert system GUI graphical approach to defining intelligent data collection bands and diagnostics for manufacturing expert systems.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with a graphical approach for back-calculation definition for manufacturing is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a proposed bearing analysis method for manufacturing is disclosed.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with torsional vibration detection/analysis using transient signal analysis for manufacturing.

In an embodiment, a system for data collection using computer vision systems in an industrial environment with improved integration using both analog and digital methods for manufacturing is disclosed.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with adaptive scheduling techniques for continuously monitoring analog data in a local manufacturing environment.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with data acquisition parking functions for manufacturing.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a self-contained data collection box for manufacturing.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with SD card storage for manufacturing.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with enhanced on-board statistical capabilities for continuous monitoring of manufacturing is disclosed.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment using ambient noise, local noise, and vibration noise for manufacturing predictions.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with smart routes that change routes based on input data or alarms, enabling simultaneous dynamic data for analysis or correlation for manufacturing.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with smart ODS and forwarding capabilities for manufacturing is disclosed.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a hierarchical manufacturing multiplexer.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment having a plethora of identification sensors for manufacturing.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with RF identification and inclinometers for manufacturing.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with continuous ultrasonic monitoring for manufacturing is disclosed.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with cloud-based machine pattern recognition based on the fusion of remote analog industrial sensors for manufacturing.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with cloud-based, machine pattern analysis of status information from multiple analog industrial sensors to provide predictive status information for industrial systems for manufacturing.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a cloud-based policy automation engine for IoT, involving the creation, deployment, and management of IoT devices for manufacturing.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with on-device sensor fusion and data storage for industrial IoT devices for manufacturing is disclosed.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a self-organizing data marketplace for industrial IoT data for the manufacturing industry.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with self-organization of the data pool based on utilization and/or yield metrics for manufacturing.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with training AI models based on industry-specific feedback for manufacturing.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a self-organized group of industrial data collectors for manufacturing is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT distributed ledger for manufacturing.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with a self-organizing collector for manufacturing is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with network-sensitive collectors for manufacturing is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with remotely organized collectors for manufacturing is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with self-organizing storage for a multi-sensor data collector for manufacturing is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with self-organizing network coding for a multi-sensor data network for manufacturing is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment is disclosed having a wearable tactile user interface for an industrial sensor data collector with vibration, heat, electrical and/or acoustic outputs for manufacturing.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a heat map that displays the collected data for AR/VR in manufacturing.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with automatically adjusted AR/VR visualization of data collected by data collectors for manufacturing is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment having an IoT platform for manufacturing is disclosed.

In an embodiment, a system is disclosed for data collection using a computer vision system in an industrial environment having an IoT data adapter for receiving data input and establishing a connection with one or more available IoT cloud platforms to publish the data for manufacturing.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment is disclosed, having a condition detector for detecting conditions associated with connection attempts made by an IoT data adapter to one or more IoT cloud platforms for manufacturing.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT data adapter equipped with a manufacturing adaptation engine.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with the use of machine learning to prepare data packets or streams for manufacturing.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment having a data marketplace that provides a pool of available cloud networking platforms for the manufacturing industry.

In an embodiment, a system for data collection in an industrial environment using a computer vision system is disclosed, having a messaging utility that provides messages to a cloud platform user interface indicating the availability of new data sources and instructions for integrating and using data sources for manufacturing.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system and has the ability to maintain first and second transmission limits based on the received arrival rate and success rate of delivery feedback messages, and that limits the transmission of messages based on transmission limits for manufacturing.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system that has the ability to restrict the transmission of further messages that have not yet been acknowledged as successfully delivered according to a manufacturing window size.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that has the ability to maintain an estimate of the rate of loss events and use it to adjust the rate of redundancy messages for manufacturing.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes having an estimated rate of loss events, where the error correction code used to determine the selected redundancy message is based on the estimated rate of loss events for manufacturing.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of applying forward error correction based on received messages describing channel characteristics for manufacturing.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to maintain/set timers based on the occurrence of delivery order events and delay the transmission of feedback messages using a timer for manufacturing.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to maintain/set timers based on the occurrence of delivery command events, and that can delay congestion window size modifications based on the timer for manufacturing.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system, the system having the capability to maintain/set a timer based on the occurrence of a delivery command event, delay a change in congestion window size based on the timer, and cancel the change in congestion window size upon receiving a feedback message indicating successful delivery for manufacturing.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes with the ability to configure new connections using maintained data characterizing current and previous connections for manufacturing.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes with the ability to configure new connections using maintained data characterizing the error rates of current/previous connections for manufacturing.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes with the ability to configure new connections using maintained data that characterizes timing variations of current/previous connections for manufacturing purposes.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to configure new connections using maintained data characterizing the bandwidth of current/previous connections for manufacturing.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes with the ability to configure new connections using maintained data characterizing the round-trip times of current and previous connections for manufacturing.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes with the ability to configure new connections using maintained data characterizing communication control parameters of current/previous connections for manufacturing purposes.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to configure new connections using maintained data characterizing forward error correction parameters of current/previous connections for manufacturing purposes.

In an embodiment, a system is disclosed for communicating data between nodes using a computer vision system, the system having a data store for maintaining data characterizing one or more current or previous data communication connections, and a connection initiation module for initiating new data communication connections based on the data maintained for manufacturing.

In one embodiment, a system is disclosed for data communication using a computer vision system between nodes capable of transmitting a first subset of data messages over a low-latency data path and a second subset of messages over a high-latency data path for manufacturing purposes.

In one embodiment, a system is disclosed for data communication using a computer vision system between nodes capable of transmitting a first subset of time-critical data messages over a low-latency data path and a second subset of messages over a high-latency data path for manufacturing purposes.

In an embodiment, a system for communicating data using a computer vision system between nodes capable of transmitting a first initial subset of data messages over a low-latency data path, and a second subset of messages that are later made available over a high-latency data path for manufacturing, is disclosed.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of transmitting a first subset of acknowledgement messages over a low-latency data path for manufacturing and a second subset of data messages over a high-latency data path.

In an embodiment, a system is disclosed for data communication between nodes using a computer vision system for manufacturing, the system having the capability to transmit a first subset of supplemental/redundant data messages over a lower latency data path and a second subset of data messages over a higher latency data path.

In an embodiment, a system is disclosed for communicating data between nodes using a computer vision system, with a degree of redundancy associated with each message based on the message's position in a transmission sequence for manufacturing.

In an embodiment, a system is disclosed for communicating data between nodes using a computer vision system, with a degree of redundancy associated with each message increasing as the message's location decreases due to manufacturing.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes in response to receiving feedback messages for manufacturing, with a degree of redundancy associated with each message, based on the message's position in a transmission order.

In an embodiment, a system is disclosed for data communication between nodes using a computer vision system to add or remove redundant messages from a queue based on the message's position in a transmission order in response to receiving a feedback message, the redundant messages being added or removed from a queue based on the feedback message for production.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that has the ability to adjust the number of messages sent over each of multiple different data paths with different communication protocols when it is determined that the data paths are altering the flow of messages for manufacturing.

In an embodiment, a system for data communication between nodes is disclosed that has the ability to adjust the number of messages sent over each of multiple different data paths having different communication protocols when it is determined using a computer vision system that the data paths are altering the initial division of the message flow based on previous communication connections for manufacturing.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that has the ability to modify/add/remove redundancy information associated with the encoded data as it travels from node to node over a channel based on the channel characteristics for manufacturing.

In an embodiment, a system for data communication using a computer vision system between nodes capable of transmitting FEC packets at an estimated rate of loss events (isolated packet losses or bursts of consecutive packets) for production is disclosed.

In an embodiment, a system for data communication between nodes using a computer vision system with hybrid coding, TCP, and pacing for packet transmission for manufacturing is disclosed.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system with a forward error correcting code structure that interleaves groups of message packets with parity packets and encodes across overlapping groups of message packets for manufacturing.

In one embodiment, a system is disclosed for manufacturing purposes that uses a computer vision system to communicate data between nodes using a variation of TCP that combines a delay-based backoff with a stable window growth function.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment is disclosed that uses an analog crosspoint switch to collect a variable group of analog sensor inputs for fossil fuel energy production.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with upfront signal conditioning on a multiplexer for improved signal-to-noise ratio for fossil fuel energy production.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with multiplexer continuous monitoring alarm functionality for fossil fuel energy production.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment using distributed CPLD chips with dedicated buses for logical control of multiple MUXs and data collection units for fossil fuel energy production.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with high amperage input capabilities using solid-state relays and design topologies for fossil fuel energy production.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment having power-down capability for at least one analog sensor channel and component board for fossil fuel energy production is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with unique electrostatic protection for triggers and vibration inputs for fossil fuel energy production.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with an accurate voltage reference for A/D zero reference for fossil fuel energy production is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a phase-locked loop bandpass tracking filter to obtain low RPM and phase information for fossil fuel energy production.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment using on-board timers for fossil fuel energy production to digitally derive phase for input and trigger channels.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed that has a peak detector for autoscaling routed to a separate analog-to-digital converter for peak detection for fossil fuel energy production.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with routing of raw or buffered trigger channels to other analog channels for fossil fuel energy production.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed that uses higher input oversampling for a delta-sigma A/D for a lower sampling rate output to minimize AA filter requirements for fossil fuel energy production.

In an embodiment, a system for data collection using computer vision systems in an industrial environment is disclosed that uses a CPLD as a clock distributor for a delta-sigma analog-to-digital converter to achieve low sampling rates without the need for digital resampling for fossil fuel energy production.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with long blocks of data at high sampling rates, as opposed to multiple data sets taken at different sampling rates for fossil fuel energy production.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment where calibration data with maintenance history is stored on board card sets for fossil fuel energy production.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with rapid route creation capabilities using hierarchical templates for fossil fuel energy production.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with intelligent management of data collection bands for fossil fuel energy production is disclosed.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a neural net expert system that uses intelligent management of data collection bands for fossil fuel energy production.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with the use of a database hierarchy in analyzing sensor data for fossil fuel energy production.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed that has an expert system GUI graphical approach for defining intelligent data collection bands and diagnostics for an expert system for fossil fuel energy production.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a graphical approach for back-calculation definition for fossil fuel energy production is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a proposed bearing analysis method for fossil fuel energy production is disclosed.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with torsional vibration detection/analysis using transient signal analysis for fossil fuel energy production.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with improved integration using both analog and digital methods for fossil fuel energy production.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with adaptive scheduling techniques for continuous monitoring of analog data in a local environment for fossil fuel energy production is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a data collection parking facility for fossil fuel energy production.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a self-sufficient data collection box for fossil fuel energy production.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with SD card storage for fossil fuel energy production.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with enhanced on-board statistical capabilities for continuous monitoring of fossil fuel energy production.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with the use of ambient noise, local noise, and vibration noise for predictions for fossil fuel energy production.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with smart routes that change routes based on input data or alarms, enabling simultaneous dynamic data for analysis or correlation for fossil fuel energy production.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with smart ODS and forwarding capabilities for fossil fuel energy production.

In one embodiment, a system for collecting data using a computer vision system in an industrial environment having a hierarchical multiplexer for fossil fuel energy production is disclosed.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment having a plethora of identification sensors for fossil fuel energy production.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with RF identification and tilt meters for fossil fuel energy production.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with continuous ultrasonic monitoring for fossil fuel energy production.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with cloud-based machine pattern recognition based on the fusion of remote analog industrial sensors for fossil fuel energy production.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with cloud-based machine pattern analysis of condition information from multiple analog industrial sensors to provide predictive condition information for an industrial system for fossil fuel energy production.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a cloud-based policy automation engine for IoT, involving the creation, deployment, and management of IoT devices for fossil fuel energy production, is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with on-device sensor fusion and data storage for industrial IoT devices for fossil fuel energy production is disclosed.

In an embodiment, a system for data collection using a computer vision system is disclosed in an industrial environment with a self-organizing data marketplace for industrial IoT data for fossil fuel energy production.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with self-organization of data pools based on utilization and/or yield metrics for fossil fuel energy production.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with training AI models based on industry-specific feedback for fossil fuel energy production.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a self-organized group of industrial data collectors for fossil fuel energy production is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT distributed ledger for fossil fuel energy production.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with self-organizing collectors for fossil fuel energy production is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with network-sensitive collectors for fossil fuel energy production is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with remotely organized collectors for fossil fuel energy production is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with self-organizing storage for multi-sensor data collectors for fossil fuel energy production is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with self-organizing network coding for a multi-sensor data network for fossil fuel energy production is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed having a wearable tactile user interface for industrial sensor data collectors with vibration, heat, electrical, and/or acoustic outputs for fossil fuel energy production.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed, having a heat map displaying collected data for AR/VR for fossil fuel energy production.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with automatically adjusted AR/VR visualization of data collected by data collectors for fossil fuel energy production is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT platform for fossil fuel energy production.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment having an IoT data adapter for receiving data input and establishing a connection with one or more available IoT cloud platforms to publish data for fossil fuel energy production.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment having a condition detector for detecting conditions associated with connection attempts by an IoT data adapter to one or more IoT cloud platforms for fossil fuel energy production.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT data adapter equipped with an adaptive engine for fossil fuel energy production.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with the use of machine learning to prepare data packets or streams for fossil fuel energy production is disclosed.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment having a data marketplace that provides a pool of available cloud networking platforms for fossil fuel energy production.

In an embodiment, a system for data collection in an industrial environment using a computer vision system is disclosed, having a messaging utility that provides messages to a cloud platform user interface indicating the availability of new data sources and data source integration and usage instructions for fossil fuel energy production.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system and has the ability to maintain first and second transmission limits based on the received arrival rate and success rate of delivery feedback messages, and that limits the transmission of messages based on transmission limits for fossil fuel energy production.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system that has the ability to restrict the transmission of further messages that have not yet been acknowledged as successfully delivered according to a window size for fossil fuel energy production.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to maintain an estimate of the rate of loss events and use it to adjust the rate of redundancy messages for fossil fuel energy production.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes having an estimated rate of loss events, where the error correction code used to determine the selected redundancy message is based on the estimated rate of loss events for fossil fuel energy production.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of applying forward error correction based on received messages describing channel characteristics for fossil fuel energy production.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of delaying the transmission of feedback messages using timers for fossil fuel energy production and maintaining/setting the timers based on the occurrence of a broadcast command event.

In one embodiment, a system for fossil fuel energy production is disclosed that uses a computer vision system to communicate data between nodes that maintain/set timers based on the occurrence of delivery command events and have the ability to delay congestion window size modifications based on the timers.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system, which has the ability to maintain/set a timer based on the occurrence of a delivery command event, the ability to delay a change in congestion window size based on the timer, and the ability to cancel a change in congestion window size upon receiving a feedback message indicating successful delivery for fossil fuel energy production.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to configure new connections using maintained data characterizing current and previous connections for fossil fuel energy production.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of configuring new connections using maintained data characterizing the error rates of current and previous connections for fossil fuel energy production.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of configuring new connections using maintained data characterizing timing variations of current/previous connections for fossil fuel energy production.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of configuring new connections using maintained data characterizing the bandwidth of current and previous connections for fossil fuel energy production.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of configuring new connections using maintained data characterizing the round-trip times of current and previous connections for fossil fuel energy production.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of configuring new connections using maintained data characterizing communication control parameters of current/previous connections for fossil fuel energy production.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of configuring new connections using maintained data characterizing forward error correction parameters of current/previous connections for fossil fuel energy production.

In one embodiment, a system for communicating data between nodes for fossil fuel energy production using a computer vision system is disclosed, the system having a data store for maintaining data characterizing one or more current or previous data communication connections, and a connection initiation module for initiating new data communication connections based on the maintained data.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of transmitting a first subset of data messages over a low-latency data path and a second subset of messages over a high-latency data path for fossil fuel energy production.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of transmitting a first subset of time-critical data messages over a low-latency data path and a second subset of messages over a high-latency data path for fossil fuel energy production.

In one embodiment, a system is disclosed for fossil fuel energy production that uses a computer vision system to communicate data between a node capable of transmitting a first initial subset of data messages over a low-latency data path and a node capable of subsequently transmitting a second subset of available messages over a high-latency data path.

In one embodiment, a system is provided for communicating data using a computer vision system between nodes capable of transmitting a first subset of acknowledgments. A second subset of data messages is disclosed for fossil fuel energy production on a low-latency data path and a high-latency data path.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of transmitting a first subset of supplemental/redundant data messages over a low-latency data path and a second subset of data messages over a high-latency data path for fossil fuel energy production.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes with a degree of redundancy associated with each message based on the message's position in a transmission order for fossil fuel energy production.

In one embodiment, a system for fossil fuel energy production is disclosed that uses a computer vision system to communicate data between nodes with a degree of redundancy associated with each message that increases as the message's location decreases.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes in response to receiving feedback messages for fossil fuel energy production, with a degree of redundancy associated with each message based on the message's position in a transmission order.

In an embodiment, a system is disclosed for communicating data between nodes using a computer vision system with a degree of redundancy associated with each message based on the message's position in a transmission order, and in response to receiving a feedback message, the system adds or removes redundant messages from a queue based on the feedback message for fossil fuel energy production.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that has the ability to adjust the number of messages sent over each of multiple different data paths with different communication protocols when it is determined that the data paths are diverting messages due to fossil fuel energy production.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that has the ability to adjust the number of messages sent on each of multiple different data paths with different communication protocols when it is determined that the data paths are changing the flow of messages at an initial split based on previous communication connections for fossil fuel energy production.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that has the ability to modify/add/delete redundancy information associated with the encoded data as it travels from node to node over a channel based on channel characteristics for fossil fuel energy production.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of transmitting FEC packets at an estimated rate of loss events (isolated packet losses or bursts of consecutive packets) for fossil fuel energy production.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes with combined coding, TCP, and pacing of packet transmissions for fossil fuel energy production.

In an embodiment, a system is disclosed for data communication between nodes using a computer vision system with a forward error correction code structure that interleaves groups of message packets with parity packets and has coding across overlapping groups of message packets for fossil fuel energy production.

In one embodiment, a system is disclosed for fossil fuel energy production that uses a computer vision system to communicate data between nodes with a variation of TCP that combines a delay-based backoff and a stable window growth function.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment is disclosed that uses an analog crosspoint switch to collect a variable group of aerospace analog sensor inputs.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with upfront signal conditioning on a multiplexer for improved signal-to-noise ratio for aerospace applications.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with aerospace multiplexer continuous monitoring alarm functionality.

In one embodiment, a data collection system for computer vision systems in industrial environments is disclosed, using a distributed CPLD chip with multiple aerospace MUXes and a dedicated bus for logical control of the data collection units.

In embodiments, a system for collecting data using a computer vision system in industrial environments with high amperage input capabilities using solid-state relays, and a design topology for aerospace applications are disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment having the ability to power down at least one of an analog sensor channel and an aerospace component board is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with unique electrostatic protection for triggering and aerospace vibration input.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a precise voltage reference for an aerospace A/D zero reference.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a phase-locked loop bandpass tracking filter to obtain low-speed aerospace RPM and phase information.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment using an aerospace onboard timer to digitally derive phase for input and trigger channels.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment is disclosed that has a peak detector for autoscaling routed to a separate analog-to-digital converter for aerospace peak detection.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with routing of a buffered trigger channel to other analog channels for raw or aerospace applications.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment, using high input oversampling for a delta-sigma A/D for a low sampling rate output to minimize aerospace AA filter requirements.

In an embodiment, a data collection system using a computer vision system in an industrial environment is disclosed that uses a CPLD as a clock distributor for a delta-sigma analog-to-digital converter to achieve a lower sampling rate without the need for digital resampling for aerospace applications.

In an embodiment, a system is disclosed for data collection using a computer vision system in an industrial environment with long blocks of data at high sampling rates, as opposed to multiple data sets acquired at different sampling rates for aerospace applications.

In one embodiment, a data collection system for industrial environments is disclosed that uses a computer vision system to store calibration data with maintenance history on aerospace board card sets.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with rapid path creation capabilities using hierarchical aerospace templates.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with intelligent management of aerospace data collection bands.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a neural net expert system that uses intelligent management of aerospace data collection bands.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with the use of a database hierarchy in aerospace sensor data analysis.

In one embodiment, a system is disclosed that uses a computer vision system to perform data collection in an industrial environment with an expert system GUI graphical approach for defining intelligent data collection bands and diagnostics for aerospace expert systems.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with a graphical approach for aerospace back-calculation definition is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment proposing a method for analyzing aerospace bearings.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment, including torsional vibration detection/analysis using aerospace transient signal analysis.

In an embodiment, a system for data collection using computer vision systems in industrial environments with improved integration using both analog and digital methods for aerospace is disclosed.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with adaptive scheduling techniques for continuously monitoring analog data in aerospace local environments.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with aerospace data collection parking capabilities.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a self-contained aerospace data collection box.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with aerospace SD card storage.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with extended on-board statistical capabilities for continuous monitoring in aerospace applications.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with the use of ambient noise, local noise, and vibration noise for aerospace prediction.

In an embodiment, a system for data collection using a computer vision system is disclosed. This can be used to simultaneously obtain dynamic data for analysis and correlation for aerospace and industrial environments using smart routes and alarms that change routes based on input data.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with smart ODS and forwarding capabilities for aerospace applications.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an aerospace hierarchical multiplexer.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a plethora of aerospace identification sensors.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with RF identification and aerospace inclinometers.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with continuous ultrasonic monitoring for aerospace applications.

In an embodiment, a system is disclosed that uses computer vision systems to collect data in industrial environments with cloud-based machine pattern recognition based on the fusion of remote analog industrial sensors for aerospace applications.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with cloud-based machine pattern analysis of condition information from multiple analog industrial sensors to provide predictive condition information for an aerospace industrial system.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a cloud-based policy automation engine for IoT, involving the creation, deployment, and management of IoT devices for aerospace applications.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with on-device sensor fusion and data storage for aerospace and industrial IoT devices is disclosed.

In one embodiment, a system is disclosed that uses computer vision systems to collect data in an industrial environment with a self-organizing data marketplace for aerospace industrial IoT data.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with self-organization of data pools based on aerospace utilization and/or yield metrics.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with training AI models based on aerospace industry-specific feedback.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a self-organized group of industrial aerospace data collectors.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT distributed ledger for aerospace applications.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with a self-organizing collector for aerospace applications is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with a network-sensitive collector for aerospace is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with remotely coordinated collectors for aerospace applications is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with self-organizing storage for an aerospace multi-sensor data collector is disclosed.

In an embodiment, a system for data collection using computer vision systems in industrial environments with self-organizing network coding for aerospace multi-sensor data networks is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment is disclosed that has a wearable tactile user interface for an industrial sensor data collector with aerospace vibration, thermal, electrical, and/or acoustic outputs.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a heat map displaying collected data for aerospace AR/VR is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with automatically coordinated AR/VR visualization of data collected by an aerospace data collection device is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an aerospace IoT platform.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment having an IoT data adapter for receiving data input and establishing a connection with one or more available IoT cloud platforms for publishing the data for aerospace use.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment having a condition detector for detecting conditions associated with connection attempts by an IoT data adapter to one or more aerospace IoT cloud platforms.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT data adapter equipped with an aerospace adaptive engine.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with the use of machine learning to prepare data packets or streams for aerospace applications.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a data marketplace that provides a pool of available cloud networking platforms for aerospace.

In an embodiment, a system for data collection using computer vision systems in an industrial environment is disclosed, including a messaging utility that provides messages to a cloud platform user interface indicating the availability of new data sources, and instructions for integrating and using aerospace data sources.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system and has the ability to maintain first and second transmission limits based on the received arrival rate and success rate of delivery feedback messages, and that limits the transmission of messages based on aerospace transmission limits.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system that has the ability to restrict the transmission of further messages that have not yet been confirmed as successfully delivered according to a space window size.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to maintain an estimate of the rate of loss events and use it to adjust the rate of aerospace redundancy messages.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes having an estimated rate of loss events, where the error correction code used to determine the selected redundancy message is based on the estimated rate of aerospace loss events.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of applying forward error correction based on received messages describing aerospace channel characteristics.

In embodiments, a system for data communication between nodes using a computer vision system with the ability to maintain/set timers based on the occurrence of delivery command events, and a system using aerospace timers to delay the transmission of feedback messages, are disclosed.

In an embodiment, a system for data communication between nodes that uses a computer vision system to maintain/set timers based on the occurrence of delivery command events, and that delays congestion window size modifications based on an aerospace timer, is disclosed.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to maintain/set a timer based on the occurrence of a delivery command event, delay a change in congestion window size based on the timer, and cancel the change in congestion window size upon receiving a feedback message indicating successful delivery for aerospace.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes with the ability to configure new connections using maintained data characterizing current and previous aerospace connections.

In an embodiment, a system for data communication between nodes using a computer vision system is disclosed that has the ability to configure new connections using sustained data that characterizes the error rates of current/previous aerospace connections.

In an embodiment, a system for data communication between nodes using a computer vision system with the ability to configure new connections using maintenance data that characterizes timing variations of current/previous aerospace connections is disclosed.

In an embodiment, a system for data communication between nodes using a computer vision system and the ability to configure new connections using maintained data characterizing the bandwidth of current/previous connections for aerospace applications is disclosed.

In an embodiment, a system for data communication between nodes using a computer vision system is disclosed that has the ability to configure new connections using maintained data characterizing the round-trip times of current/previous aerospace connections.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of configuring new connections using maintained data characterizing communication control parameters of current and previous aerospace connections.

In an embodiment, a system for data communication between nodes using a computer vision system and capable of configuring new connections using maintained data characterizing forward error correction parameters of current/previous aerospace connections is disclosed.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system, the system having a data store for maintaining data characterizing one or more current or previous data communication connections, and a connection initiation module for initiating new data communication connections based on the maintained aerospace data.

In one embodiment, a system for aerospace applications is disclosed that uses a computer vision system to communicate data between nodes capable of transmitting a first subset of data messages over a low-latency data path and a second subset of messages over a high-latency data path.

In one embodiment, a system is disclosed for data communication using a computer vision system between nodes capable of transmitting a first subset of time-critical data messages over a low-latency data path and a second subset of messages over a high-latency aerospace data path.

In one embodiment, a system for communicating data using a computer vision system between nodes capable of transmitting a first initial subset of data messages over a low-latency data path, and a second subset of messages later available over a high-latency aerospace data path, is disclosed.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of transmitting a first subset of acknowledgement messages over a low-latency data path and a second subset of data messages over a high-latency aerospace data path.

In an embodiment, a system for data communication between nodes for aerospace applications using a computer vision system is disclosed that has the capability to transmit a first subset of supplemental/redundant data messages over a low-latency data path and a second subset of data messages over a high-latency data path.

In an embodiment, a system for communicating data between nodes using a computer vision system is disclosed, with a degree of redundancy associated with each message based on the message's position in a transmission sequence for aerospace applications.

In an embodiment, a system is disclosed for communicating data between nodes using a computer vision system, with a degree of redundancy associated with each message increasing as the message's location decreases due to aerospace.

In an embodiment, a system is disclosed for data communication between nodes using a computer vision system in response to receiving aerospace feedback messages based on the message's position in a transmission order, with a degree of redundancy associated with each message.

In one embodiment, a system for data communication between nodes using a computer vision system with a degree of redundancy associated with each message based on the message's position in a transmission order is disclosed, and the system adds or removes redundant messages from a queue based on the aerospace feedback message in response to receiving the feedback message.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that has the ability to adjust the number of messages sent over each of multiple different data paths with different communication protocols when it is determined that the data paths are altering the flow of messages for aerospace applications.

In an embodiment, a system for data communication between nodes is disclosed that has the ability to adjust the number of messages sent over each of multiple different data paths having different communication protocols when a computer vision system is used to determine that the data paths are altering the initial division of the message flow based on previous communication connections for aerospace applications.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that has the ability to modify/add/remove redundancy information associated with the encoded data as it travels from node to node over a channel based on aerospace channel characteristics.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of transmitting FEC packets at an estimated rate for aerospace loss events (isolated packet losses or bursts of consecutive packets).

In an embodiment, a system for data communication using a computer vision system between nodes with combined coding, TCP, and pacing of packet transmissions for aerospace applications is disclosed.

In one embodiment, a system for data communication between nodes using a computer vision system is disclosed that has a forward error correcting code structure that interleaves groups of message packets with parity packets and performs coding across overlapping groups of aerospace message packets.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system with a variation of TCP that combines a delay-based backoff and a space-stable window growth function.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment is disclosed that uses an analog crosspoint switch to collect a variable group of analog sensor inputs for mining.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with upfront signal conditioning on a multiplexer for improved signal-to-noise ratio for mining is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with multiplexed continuous monitoring alarm functionality for mining.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment, using a distributed CPLD chip with multiple MUXs and a dedicated bus for logical control of the data collection units.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with high amperage input capability using solid-state relays and a design topology for mining are disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment having the ability to power down at least one of an analog sensor channel and a mining component board is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with unique electrostatic protection for triggering and vibration input for mining.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with an accurate voltage reference for A/D zero reference for mining.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a phase-locked loop bandpass tracking filter to obtain low-speed RPM and phase information for mining.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed that uses an onboard timer for mining to digitally derive phase for input and trigger channels.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment having a peak detector for autoscaling that is routed to another analog-to-digital converter for peak detection for mining.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment that routes raw or buffered trigger channels to other analog channels for mining.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed that uses higher input oversampling for a delta-sigma A/D for a low sampling rate output to minimize AA filter requirements for mining.

In one embodiment, a data collection system using a computer vision system in an industrial environment is disclosed that uses a CPLD as a clock distributor for a delta-sigma analog-to-digital converter to achieve a lower sampling rate without requiring digital resampling for mining.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with long blocks of data at a high sampling rate, as opposed to multiple data sets captured at different sampling rates for mining.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment where calibration data with maintenance history is stored on mining board card sets.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with rapid route creation capabilities using hierarchical templates for mining.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with intelligent management of data collection bands for mining is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment is disclosed that uses a neural net expert system to intelligently manage data collection bands for mining.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with the use of a database hierarchy in analyzing sensor data for mining is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with an expert system GUI graphical approach for defining, analyzing, and mining the data is provided.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with a graphical approach for back-calculation definition for mining is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a proposed bearing analysis method for mining is disclosed.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with torsional vibration detection/analysis using transient signal analysis for mining.

In an embodiment, a system for data collection using computer vision systems in an industrial environment with improved integration using both analog and digital methods for mining is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with adaptive scheduling techniques for continuous monitoring of analog data in the local environment for mining.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with a data acquisition parking facility for mining is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a self-contained data collection box for mining.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with SD card storage for mining.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with enhanced on-board statistical capabilities for continuous monitoring for mining is disclosed.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment using ambient noise, local noise, and vibration noise for mining predictions.

In an embodiment, an alarm is disclosed in an industrial environment with smart routes, where a system that collects data using a computer vision system can change routes based on input data and simultaneously obtain dynamic data for mining, analysis, and correlation in such situations.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a smart ODS and forwarding capabilities for mining.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a hierarchical multiplexer for mining.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with overloaded identification sensors for mining is disclosed.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with RF identification and inclinometers for mining.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with continuous ultrasonic monitoring for mining is disclosed.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with cloud-based machine pattern recognition based on the fusion of remote analog industrial sensors for mining.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with cloud-based machine pattern analysis of condition information from multiple analog industrial sensors to provide predictive condition information for industrial systems for mining.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a cloud-based policy automation engine for IoT, along with the creation, deployment, and management of IoT devices for mining, is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with on-device sensor fusion and data storage for industrial IoT devices for mining is disclosed.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a self-organizing data marketplace for industrial IoT data mining.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with self-organization of a data pool based on utilization and/or yield metrics for mining.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with training AI models based on industry-specific feedback for mining.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a self-organized group of industrial data collectors for mining.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT distributed ledger for mining.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with a self-organizing collector for mining is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with a network-sensitive collector for mining is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with remotely organized collectors for mining is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with self-organizing storage for multi-sensor data collectors for mining is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with self-organizing network coding for mining multi-sensor data networks is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment is disclosed having a wearable tactile user interface for an industrial sensor data collector with vibration, heat, electrical and/or sound outputs for the mining industry.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment is disclosed, having a heat map displaying the collected data for AR/VR in the mining industry.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with automatically tailored AR/VR visualization of data collected by a data collector for mining.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with an IoT platform for mining is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment having an IoT data adapter for receiving data input, and establishing a connection with one or more available IoT cloud platforms to expose the data for mining is disclosed.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment having a condition detector for detecting conditions associated with connection attempts made by an IoT data adapter to one or more IoT cloud platforms for mining.

In one embodiment, a system for collecting data using a computer vision system in an industrial environment is disclosed that includes an IoT data adapter with an adaptive engine for mining.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with the use of machine learning to prepare data packets or streams for mining.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment having a data marketplace that provides a pool of cloud networking platforms available for mining.

In one embodiment, a system for collecting data using a computer vision system in an industrial environment is disclosed, having a messaging utility that provides messages to a cloud platform user interface indicating the availability of new data sources and instructions for integrating and using data sources for mining.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system and has the ability to maintain first and second transmission limits based on the received arrival rate and the success of delivery feedback messages, and that limits the transmission of messages based on the transmission limits for mining.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system that has the ability to restrict the transmission of further messages that have not yet been recognized as successfully delivered, depending on the mining window size.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to maintain an estimate of the rate of loss events and use it to adjust the rate of redundancy messages for mining.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes having an estimated rate of loss events, where the error correction code used to determine the selected redundancy message is based on the estimated rate of loss events for mining.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of describing channel characteristics for mining and applying forward error correction based on received messages.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of maintaining/setting timers based on the occurrence of a distribution command event, and that uses the timers to delay the transmission of feedback messages for mining purposes.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of maintaining/setting timers based on the occurrence of a distribution command event, and that delays timer-based congestion window size modifications for mining.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system, which has the ability to maintain/set a timer based on the occurrence of a distribution command event, delay changes to the congestion window size based on the timer, and cancel changes to the congestion window size when a feedback message indicating successful distribution for mining is received.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to create new connections using maintained data characterizing current and previous connections for mining purposes.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to create new connections using maintained data that characterizes the error rates of current and previous connections for mining purposes.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to create new connections using maintained data that characterizes timing variations of current/previous connections for mining purposes.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to create new connections using maintained data characterizing the bandwidth of current and previous connections for mining.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to create new connections using maintained data characterizing the round-trip times of current and previous connections for mining purposes.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to configure new connections using maintained data characterizing communication control parameters of current/previous connections for mining purposes.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to configure new connections using maintained data that characterizes forward error correction parameters of current/previous connections for mining.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system, the system having a data store for maintaining data characterizing one or more current or previous data communication connections, and a connection initiation module for initiating new data communication connections based on the maintained data for mining purposes.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of transmitting a first subset of data messages over a low-latency data path and a second subset of messages over a high-latency data path for mining.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system and has the capability to transmit a first subset of time-critical data messages over a low-latency data path and a second subset of messages over a high-latency data path for mining.

In one embodiment, a system for communicating data using a computer vision system between nodes capable of transmitting a first initial subset of data messages over a low-latency data path, and a second subset of messages later available over a high-latency data path for mining, is disclosed.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of transmitting a first subset of acknowledgement messages over a low-latency data path and a second subset of data messages over a high-latency data path for mining.

In an embodiment, a system for data communication using a computer vision system is disclosed, wherein the system includes nodes capable of transmitting a first subset of complementary/redundant data messages on a low-latency data path and a second subset of data messages on a high-latency data path for mining.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes with a degree of redundancy associated with each message that is based on the message's position in a transmission order for mining.

In an embodiment, a system is disclosed for communicating data between nodes using a computer vision system, with a degree of redundancy associated with each message increasing as the message's location decreases due to mining.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes with a degree of redundancy associated with each message in response to receiving feedback messages for mining based on the message's position in a transmission order.

In an embodiment, a system is disclosed for communicating data between nodes using a computer vision system, with a degree of redundancy associated with each message based on the message's position in a transmission order, and in response to receiving a feedback message, the system adds or removes redundancy messages from a queue based on the feedback message for mining.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that has the ability to adjust the number of messages sent over each of multiple different data paths with different communication protocols when it is determined that the data path is altering the flow of messages for mining.

In an embodiment, a system for data communication between nodes is disclosed that has the ability to adjust the number of messages sent over each of multiple different data paths with different communication protocols when a computer vision system is used to determine that the data path is altering the initial division of the message flow based on previous communication connections for mining.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that has the ability to modify/add/remove redundancy information associated with the encoded data as it travels from node to node over a channel based on channel characteristics for mining.

In an embodiment, a system for data communication using a computer vision system is disclosed between nodes capable of sending FEC packets at an estimated rate of loss events (isolated packet losses or bursts of consecutive packets) for mining.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system and combines coding, TCP, and pacing of packet transmissions for mining.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes having a forward error correcting code structure that interleaves groups of message packets with parity packets and performs coding across overlapping groups of message packets for mining.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system with a variation of TCP that combines a stable window increasing function and delay-based backoff for mining.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with the use of an analog crosspoint switch to collect a variable group of analog sensor inputs for construction is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with upfront signal conditioning on a multiplexer for improved signal-to-noise ratio for construction is disclosed.

In one embodiment, a system for collecting data using a computer vision system in an industrial environment with multiplexer continuous monitoring alarm functionality for construction is disclosed.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment, using a distributed CPLD chip with multiple MUXes and a dedicated bus for logical control of the data collection units.

In an embodiment, a system and design topology for building a system that uses a computer vision system to collect data in an industrial environment with high amperage input capabilities using solid-state relays is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment having the ability to power down at least one of an analog sensor channel and a structural component board is disclosed.

In one embodiment, a system for data collection using a computer vision system in an industrial environment with unique electrostatic protection for triggers and vibration input for construction is disclosed.

In an embodiment, a system for collecting data in an industrial environment using a computer vision system is disclosed.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a phase-locked loop bandpass tracking filter to obtain low-speed RPM and phase information for construction applications.

In an embodiment, a system for collecting data in an industrial environment using a computer vision system is disclosed, which uses an onboard timer to digitally derive phase for input and trigger channels.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed that has a peak detector for autoscaling that is routed to another analog-to-digital converter for peak detection for construction.

In an embodiment, a system for collecting data in an industrial environment using a computer vision system is disclosed, which has a trigger channel routed raw or buffered to other analog channels for construction.

In an embodiment, a system for data collection using computer vision systems in industrial environments is disclosed that has the use of higher input oversampling for delta-sigma A/Ds for lower sampling rate outputs to minimize AA filter requirements for construction.

In an embodiment, a data acquisition system using a computer vision system in an industrial environment is disclosed that uses a CPLD as a clock distributor for a delta-sigma analog-to-digital converter to achieve lower sampling rates without requiring digital resampling for implementation.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with long blocks of data at a high sampling rate, as opposed to multiple data sets captured at different sampling rates for construction.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment where calibration data with maintenance history is stored on construction board cards.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with rapid route creation capabilities using hierarchical templates for construction.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with intelligent management of data collection bands for construction is disclosed.

In one embodiment, a system for collecting data using a computer vision system in an industrial environment with a neural net expert system that uses intelligent management of data collection bands for construction is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with the use of a database hierarchy in analyzing sensor data for construction is disclosed.

In an embodiment, a system is disclosed for data collection in an industrial environment using a computer vision system with a graphical approach of an expert system GUI for defining intelligent data collection bands and diagnostics for the expert system for construction.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with a graphical approach for back-calculation definition for construction is disclosed.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment, proposing a bearing analysis method for construction.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with torsional vibration detection/analysis using transient signal analysis for construction.

In an embodiment, a system for data collection using computer vision systems in industrial environments with improved integration using both analog and digital methods for construction is disclosed.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with adaptive scheduling technology for continuously monitoring analog data in the local environment for construction.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with construction data acquisition parking lot capabilities.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a self-contained data collection box for construction.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with construction SD card storage.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with enhanced on-board statistical capabilities for continuous monitoring of construction.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with the use of ambient noise, local noise, and vibration noise for construction predictions.

In an embodiment, a system for data collection using a computer vision system is disclosed, where a smart route can change the route based on input data or alarms, simultaneously obtaining dynamic data for analysis or correlation for construction.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with smart ODS and forwarding capabilities for construction.

In one embodiment, a system for collecting data using a computer vision system in an industrial environment with a hierarchical multiplexer for construction is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a plethora of identification sensors for construction.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with RF identification and construction inclinometers.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with continuous ultrasonic monitoring for construction.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with cloud-based machine pattern recognition based on the fusion of remote analog industrial sensors for construction.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with cloud-based machine pattern analysis of condition information from multiple analog industrial sensors to provide predictive condition information for industrial systems for construction.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a cloud-based policy automation engine for IoT, involving the creation, deployment, and management of IoT devices for construction, is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with on-device sensor fusion and data storage for construction industrial IoT devices is disclosed.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a self-organizing data marketplace for industrial IoT data for construction.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with self-organization of a data pool based on utilization and/or yield metrics for construction.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with training AI models based on industry-specific feedback for construction.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a self-organized group of industrial data collectors for construction.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with an IoT distributed ledger for construction is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with self-organizing collectors for construction is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with network-sensitive collectors for construction is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with remotely organized collectors for construction is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with self-organizing storage for a multi-sensor data collector for construction is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with self-organizing network coding for a multi-sensor data network for construction is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment is disclosed having a wearable tactile user interface for an industrial sensor data collector with vibration, heat, electrical, and/or sound outputs for construction.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a heat map displaying collected data for AR/VR for construction is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with automatically adjusted AR/VR visualization of data collected by data collectors for construction is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a construction IoT platform.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT data adapter to receive data input and establishes a connection with one or more available IoT cloud platforms to publish the data for construction.

In one embodiment, a system is disclosed for collecting data in an industrial environment using a computer vision system, having a condition detector for detecting conditions related to connection attempts made by an IoT data adapter to one or more IoT cloud platforms for construction.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT data adapter equipped with an adaptive engine for construction.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with the use of machine learning to prepare data packets or streams for construction is disclosed.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment having a data marketplace that provides a pool of available cloud networking platforms for construction.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment, with a messaging utility that provides messages to a cloud platform user interface indicating the availability of new data sources and instructions for integrating and using the data sources for construction.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to maintain first and second transmission limits based on received arrival rates and the success of delivery feedback messages, and that limits the transmission of messages based on the transmission limits for construction.

In one embodiment, a system for data communication using a computer vision system between nodes is disclosed that has the ability to restrict the transmission of further messages that have not yet been acknowledged as successfully delivered, depending on a constructed window size.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes that has the ability to maintain an estimate of the rate of loss events and use it to adjust the rate of redundancy messages for construction.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes having an estimated rate of loss events, where the error correction code used to determine the selected redundancy message is based on the estimated rate of loss events for the construction.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of applying forward error correction based on received messages describing channel characteristics for construction.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of maintaining/setting timers based on the occurrence of a distribution command event, where the system uses a timer to delay the transmission of feedback messages.

In one embodiment, a system is disclosed for data communication using a computer vision system between nodes capable of maintaining/setting timers based on the occurrence of a distribution command event, and for delaying the modification of congestion window size based on the timer for construction.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system, which has the ability to maintain/set a timer based on the occurrence of a distribution command event, delay changes to the congestion window size based on the timer, and cancel changes to the congestion window size when a feedback message indicating successful distribution for construction is received.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes with the ability to configure new connections using maintained data characterizing current/previous connections for construction.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to configure new connections using maintained data that characterizes the error rates of current/previous connections for construction.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to configure new connections using maintained data that characterizes the timing variations of current/previous connections for construction.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to configure new connections using maintained data characterizing the bandwidth of current/previous connections for that purpose.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to configure new connections using maintained data that characterizes the round-trip times of current and previous connections for establishment.

In an embodiment, a system is disclosed for communicating data using a computer vision system between nodes that have the ability to configure new connections using maintained data characterizing the communication control parameters of current/previous connections for establishment.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes that have the ability to configure new connections using maintained data characterizing the forward error correction parameters of current/previous connections for the connection.

In an embodiment, a system for communicating data between nodes using a computer vision system is disclosed, the system having a data store for maintaining data characterizing one or more current or previous data communication connections, and a connection initiation module for initiating new data communication connections based on the maintained data for construction.

In one embodiment, a system is disclosed for data communication using a computer vision system between nodes capable of transmitting a first subset of data messages over a low-latency data path and a second subset of messages over a high-latency data path for construction purposes.

In one embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to transmit a first subset of time-critical data messages over a low-latency data path and a second subset of messages over a high-latency data path for construction.

In one embodiment, a system for communicating data using a computer vision system between nodes capable of transmitting a first initial subset of data messages over a low-latency data path, and a second subset of messages later available over a high-latency data path for construction, is disclosed.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to transmit a first subset of acknowledgement messages over a low-latency data path and a second subset of data messages over a high-latency data path for construction.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to transmit a first subset of supplemental/redundant data messages over a low-latency data path for construction and a second subset of data messages over a high-latency data path.

In an embodiment, a system is disclosed for communicating data between nodes using a computer vision system, with a degree of redundancy associated with each message based on the message's position in a transmission order for construction.

In an embodiment, a system is disclosed for communicating data between nodes using a computer vision system in which the degree of redundancy associated with each message increases with the message's position and is structurally non-decreasing.

In an embodiment, a system is provided for using a computer vision system to communicate data between nodes with redundancy associated with each of the following messages:
is disclosed in response to receiving a feedback message for construction based on the position of the message in the transmission order.

In an embodiment, a system is disclosed for communicating data between nodes using a computer vision system, with a degree of redundancy associated with each message based on the message's position in a transmission order, and in response to receiving a feedback message, the system adds or removes redundancy messages from a queue based on the feedback message for construction.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that has the ability to adjust the number of messages sent over each of multiple different data paths with different communication protocols when it is determined that the data paths are altering the flow of messages for construction.

In an embodiment, a system for data communication between nodes is disclosed that has the ability to adjust the number of messages sent over each of multiple different data paths having different communication protocols when a computer vision system is used to determine that the data path is changing the initial division of the message flow based on previous communication connections for construction.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that has the ability to modify/add/remove redundancy information associated with encoded data as it travels from node to node over a channel based on established channel characteristics.

In one embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to transmit FEC packets at an estimated rate of loss events (isolated packet losses or bursts of consecutive packets) for construction.

In an embodiment, a system is disclosed for communicating data between nodes using a computer vision system with combined coding, TCP, and pacing of packet transmissions for construction.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system with a forward error correction code structure that interleaves groups of message packets with parity packets and performs coding across overlapping groups of message packets for the structure.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system with a variant of TCP that combines delay-based backoff with a stable window growth function for construction.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment is disclosed that uses an analog crosspoint switch to collect a variable group of analog sensor inputs for a vessel.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with upfront signal conditioning on a multiplexer to improve the vessel's signal-to-noise ratio.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with multiplexer continuous monitoring alarm functionality for ships.

In one embodiment, a system is disclosed that uses a distributed CPLD chip with multiple MUXes and a dedicated bus for logical control of shipboard data collection units to collect data using a computer vision system in an industrial environment.

In embodiments, a system using a computer vision system to collect data in an industrial environment with high amperage input capabilities using solid-state relays, and a design topology for a marine vessel, are disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment having power-down capability for at least one analog sensor channel and a marine component board is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with unique electrostatic protection for triggers and vibration input for marine applications.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with an accurate voltage reference for an A/D zero reference for a vessel.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a phase-locked loop bandpass tracking filter to obtain low-speed RPM and phase information for a vessel.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment using an onboard timer for a vessel to digitally derive phase for input and trigger channels.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed that has a peak detector for autoscaling routed to a separate analog-to-digital converter for peak detection for vessels.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with routing of a trigger channel that is buffered to other analog channels for live or shipboard use.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed that uses higher input oversampling for a delta-sigma A/D for a lower sampling rate output to minimize the vessel's AA filter requirements.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed that uses a CPLD as a clock divider for a delta-sigma analog-to-digital converter to achieve lower sampling rates without requiring digital resampling for the vessel.

In an embodiment, a system is disclosed for collecting data in an industrial environment using a computer vision system with long blocks of data at a high sampling rate, as opposed to multiple data sets captured at different sampling rates for a ship.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment where calibration data with maintenance history is stored on board card sets for ships.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with rapid route planning capabilities using hierarchical templates for ships.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with intelligent management of data collection bands for ships.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a neural net expert system that uses intelligent management of data collection bands for ships.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with the use of a database hierarchy in sensor data analysis for a ship is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed that has a graphical approach of an expert system GUI for defining intelligent data collection bands and diagnostics for an expert system for a vessel.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a graphical approach for back-calculation definition for ships is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment, proposing a method for analyzing ship bearings.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment, including torsional vibration detection/analysis using transient signal analysis for marine applications.

In an embodiment, a system for data collection using computer vision systems in industrial environments with improved integration using both analog and digital methods for ships is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with adaptive scheduling techniques for continuous monitoring of analog data in a ship's local environment is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with data acquisition parking capabilities for ships is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a self-contained data collection box for a ship.

In one embodiment, a system for collecting data using a computer vision system in an industrial environment with SD card storage for a vessel is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with enhanced on-board statistical capabilities for continuous monitoring of vessels is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with the use of ambient noise, local noise, and vibration noise for ship prediction is disclosed.

In an embodiment, a system for data collection in an industrial environment using a computer vision system is disclosed that has a smart route, alters route based on input data, and enables simultaneous dynamic data for analysis or correlation for alarms on vessels.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with smart ODS and forwarding capabilities for ships is disclosed.

In one embodiment, a system for collecting data using a computer vision system in an industrial environment with a hierarchical multiplexer for a ship is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a plethora of vessel identification sensors.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with RF identification and marine inclinometers.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with continuous ultrasonic monitoring for ships.

In an embodiment, a system for data collection in industrial environments with cloud-based, ship-based, and machine pattern recognition based on fusion of remote analog industrial sensors using a computer vision system is disclosed.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with cloud-based, machine pattern analysis of status information from multiple analog industrial sensors to provide predictive status information for a marine industrial system.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a cloud-based policy automation engine for IoT, involving the creation, deployment, and management of IoT devices for ships, is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with on-device sensor fusion and data storage for industrial IoT devices on ships is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a self-organizing data marketplace for industrial IoT data on ships is disclosed.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with self-organization of a data pool based on vessel utilization and/or yield metrics.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with training AI models based on industry-specific feedback from vessels.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a self-organized group of industrial data collectors for ships.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT distributed ledger for ships.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with a self-organizing collector for a ship is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with a network-sensitive collector for a ship is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with remotely organized ship-based collectors is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with self-organizing storage for a multi-sensor data collector for a ship is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with self-organizing network coding for a multi-sensor data network for ships is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment is disclosed, having a wearable tactile user interface for an industrial sensor data collector with vibration, heat, electrical, and/or acoustic outputs for a marine vessel.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment is disclosed, including a heat map displaying the collected data for AR/VR on a ship.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with automatically coordinated AR/VR visualization of data collected by a shipboard data collection device is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT platform for ships.

In one embodiment, a system is disclosed for data collection using a computer vision system in an industrial environment having an IoT data adapter for receiving data input, and establishing a connection with one or more available IoT cloud platforms for publishing data for a vessel.

In one embodiment, a system is disclosed for collecting data in an industrial environment using a computer vision system, having a condition detector for detecting conditions associated with connection attempts made by an IoT data adapter to one or more ship IoT cloud platforms.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT data adapter equipped with an adaptive engine for a ship.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with the use of machine learning to prepare data packets or streams for a vessel.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment having a data marketplace that provides a pool of available cloud networking platforms for ships.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed having a messaging utility that provides messages to a cloud platform user interface indicating the availability of new data sources and instructions for integrating and using data sources for a vessel.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to maintain first and second transmission limits based on the received arrival rate and success rate of delivery feedback messages, and that limits the transmission of messages based on the vessel's transmission limits.

In an embodiment, a system is disclosed for communicating data between nodes using a computer vision system that has the ability to restrict the transmission of further messages that have not yet been acknowledged as successfully delivered according to a window size for a vessel.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to maintain an estimate of the rate of loss events and use it to adjust the rate of redundant messages for a vessel.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes having an estimated rate of loss events, where the error correction code used to determine the selected redundancy message is based on the estimated rate of loss events for the vessel.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of applying forward error correction based on received messages describing channel characteristics for a vessel.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of maintaining/setting timers based on the occurrence of a delivery order event, where the system uses a vessel timer to delay the transmission of feedback messages.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of maintaining/setting timers based on the occurrence of a delivery order event, and that delays modification of congestion window size based on a timer for a vessel.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system, with the nodes maintaining/setting a timer based on the occurrence of a distribution command event, delaying a change in congestion window size based on the timer, and canceling the change in congestion window size upon receiving a feedback message indicating successful distribution to a vessel.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes with the ability to configure new connections using maintained data characterizing a vessel's current and previous connections.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes with the ability to configure new connections using maintained data that characterizes the error rates of a vessel's current and previous connections.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to configure new connections using maintained data that characterizes timing variations of a vessel's current/previous connections.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to configure new connections using maintained data characterizing the bandwidth of a vessel's current and previous connections.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to configure new connections using maintained data characterizing the round-trip times of current/previous connections for a vessel.

In an embodiment, a system for data communication between nodes using a computer vision system with the ability to configure new connections using maintained data characterizing communication control parameters of current/previous connections for a vessel is disclosed.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to configure new connections using maintained data that characterizes forward error correction parameters of a vessel's current/previous connections.

In an embodiment, a system for communicating data between nodes using a computer vision system is disclosed, the system having a data store for maintaining data characterizing one or more current or previous data communication connections, and a connection initiation module for initiating new data communication connections based on the maintained data for a vessel.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of transmitting a first subset of data messages over a low-latency data path for a vessel and a second subset of messages over a high-latency data path.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to transmit a first subset of time-critical data messages over a low-latency data path and a second subset of messages over a high-latency data path for a vessel.

In one embodiment, a system for communicating data using a computer vision system between nodes capable of transmitting a first initial subset of data messages over a low-latency data path, and then a second subset of messages available over a high-latency data path for a vessel, is disclosed.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of transmitting a first subset of acknowledgment messages over a low-latency data path for a vessel and a second subset of data messages over a high-latency data path.

In an embodiment, a system for data communication between nodes is disclosed that has the capability to transmit a first subset of supplemental/redundant data messages over a low-latency data path and a second subset of data messages over a high-latency data path for a vessel using a computer vision system.

In an embodiment, a system is disclosed for communicating data between nodes using a computer vision system, with a degree of redundancy associated with each message based on the message's position in a vessel's transmission sequence.

In an embodiment, a system is disclosed for communicating data between nodes using a computer vision system, with a degree of redundancy associated with each message increasing as the message's position relative to the vessel decreases.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes in response to receiving feedback messages for a vessel, with a degree of redundancy associated with each message based on the message's position in the transmission order.

In an embodiment, a system for data communication between nodes using a computer vision system to add or remove redundant messages from a queue based on the message's position in a transmission order in response to receiving a feedback message, the system adding or removing redundant messages from a queue based on the feedback message for a vessel is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that has the ability to adjust the number of messages sent over each of multiple different data paths with different communication protocols if it is determined that the data path is altering the flow of messages for a vessel.

In an embodiment, a data communication system between nodes is disclosed that has the ability to adjust the number of messages sent over each of multiple different data paths with different communication protocols when a computer vision system is used to determine that the data path is changing the initial division flow of messages based on the vessel's previous communication connections.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that has the ability to modify/add/remove redundancy information associated with the encoded data as it travels from node to node over the channel based on the channel characteristics for the vessel.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to transmit FEC packets at an estimated rate of loss events (isolated packet losses or bursts of consecutive packets) for a vessel.

In an embodiment, a system for node-to-node data communication using a computer vision system with hybrid coding, TCP, and pacing of packet transmissions for ships is disclosed.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system with a forward error correction code structure that interleaves groups of message packets with parity packets and performs coding across overlapping groups of message packets for a vessel.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system with a TCP variant that combines a delay-based backoff and a stable window growth function for ships.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment is disclosed that uses an analog crosspoint switch to collect a variable group of analog sensor inputs for a submarine.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with upfront signal conditioning on a multiplexer for improved signal-to-noise ratio for submarines is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with multiplexer continuous monitoring alarm functionality for submarines.

In one embodiment, a system is disclosed for collecting data using computer vision systems in an industrial environment, using distributed CPLD chips with dedicated buses for logical control of multiple MUXes and submarine data collection units.

In embodiments, a design topology for a system using a computer vision system to collect data in an industrial environment with high amperage input capability using solid-state relays, and for a submarine, is disclosed.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment having power-down capability for at least one analog sensor channel and a submarine component board.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with unique electrostatic protection for submarine triggers and vibration inputs is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an accurate voltage reference for the submarine's A/D zero reference.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a phase-locked loop bandpass tracking filter to obtain low-speed RPM and phase information for a submarine.

In one embodiment, a data collection system for an industrial environment is disclosed that uses a computer vision system to digitally derive phase for input and trigger channels using a submarine's onboard timer.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed, with a peak detector for autoscaling routed to another analog-to-digital converter for peak detection for submarines.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with routing of a raw or buffered trigger channel to other analog channels for submarines.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed that uses higher input oversampling for a delta-sigma A/D for a lower sampling rate output to minimize the submarine's AA filter requirements.

In one embodiment, a data collection system using computer vision systems in an industrial environment is disclosed that uses a CPLD as a clock distributor for a delta-sigma analog-to-digital converter, achieving low sampling rates without the need for digital resampling for submarines.

In an embodiment, a system is disclosed for collecting data in an industrial environment using a computer vision system with long blocks of data at a high sampling rate, as opposed to multiple data sets captured at different sampling rates for a submarine.

In one embodiment, a data collection system for an industrial environment is disclosed that uses a computer vision system to store calibration data along with maintenance history on a board card set for a submarine.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with rapid route planning capabilities using hierarchical templates for submarines.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with intelligent management of submarine data collection bands.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a neural net expert system that uses intelligent management of submarine data collection bands.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment that uses a database hierarchy to analyze sensor data on a submarine.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed that has an expert system GUI graphical approach for defining intelligent data collection bands and diagnostics for a submarine expert system.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with a graphical approach for the reverse definition of submarines is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment, proposing a method for analyzing submarine bearings.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment, including torsional vibration detection/analysis using transient signal analysis for submarines.

In an embodiment, a system for data collection using computer vision systems in industrial environments with improved integration using both analog and digital methods for submarines is disclosed.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with adaptive scheduling techniques for continuously monitoring analog data in the submarine's local environment.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a data collection parking facility for submarines.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a self-contained data collection box for a submarine.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with SD card storage for submarines.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with enhanced on-board statistical capabilities for continuous monitoring of submarines is disclosed.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment using ambient noise, local noise, and vibration noise for submarine prediction.

In an embodiment, a system for data collection using a computer vision system is disclosed, where the smart route changes route based on input data or alarms, allowing for simultaneous dynamic data for analysis or correlation for the submarine.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a smart ODS and transfer capabilities for submarines.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a hierarchical multiplexer for a submarine.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with overloaded submarine identification sensors.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with RF identification and submarine tilt meters.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with continuous ultrasonic monitoring for submarines is disclosed.

In an embodiment, a system is disclosed that uses computer vision systems to collect data in industrial environments with cloud-based machine pattern recognition based on the fusion of remote analog industrial sensors for submarines.

In an embodiment, a system is provided for collecting data using a computer vision system in an industrial environment with cloud-based state machine pattern analysis.
Information from a plurality of analog industrial sensors is disclosed to provide predictive status information for a submarine industrial system.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a cloud-based policy automation engine for IoT, involving the creation, deployment, and management of IoT devices for submarines.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with on-device sensor fusion and data storage for industrial IoT devices for submarines is disclosed.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a self-organizing data marketplace for submarine industrial IoT data.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with self-organization of the data pool based on submarine utilization and/or yield metrics.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with industry-specific feedback-based training AI models for submarines is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a self-organized swarm of industrial data collectors for submarines is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT distributed ledger for submarines.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a self-organizing collector for a submarine.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with a network-sensitive collector for a submarine is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with a remotely coordinated collector for a submarine is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with self-organizing storage for a multi-sensor data collector for a submarine is disclosed.

In an embodiment, a system for data collection using computer vision systems in an industrial environment with self-organizing network coding for a submarine multi-sensor data network is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment is disclosed, having a wearable tactile user interface for an industrial sensor data collector with vibration, heat, electrical, and/or acoustic outputs for a submarine.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment is disclosed, including a heat map displaying the collected data for AR/VR for submarines.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with automatically adjusted AR/VR visualization of data collected by a submarine data collection device.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT platform for submarines.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment having an IoT data adapter for receiving data input and establishing a connection with one or more available IoT cloud platforms for publishing the data for a submarine.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment, having a condition detector for detecting conditions associated with connection attempts made by an IoT data adapter to one or more submarine IoT cloud platforms.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT data adapter equipped with an adaptive engine for submarines.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with the use of machine learning to prepare data packets or streams for submarines.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment having a data marketplace that provides a pool of available cloud networking platforms for submarines.

In an embodiment, a system for data collection in an industrial environment using a computer vision system is disclosed, having a messaging utility that provides messages indicating the availability of new data sources and instructions for data source integration and submarine usage to a cloud platform user interface.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to maintain first and second transmission limits based on the received arrival rate and success of delivery feedback messages, and that limits the transmission of messages based on the transmission limit for a submarine.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system that has the ability to restrict the transmission of further messages that have not yet been acknowledged as successfully delivered according to a submarine window size.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to maintain an estimate of the rate of loss events and use it to adjust the rate of submarine redundancy messages.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes having an estimated rate of submarine loss events, where the error correction code used to determine the selected redundancy message is based on the estimated rate of submarine loss events.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of applying forward error correction based on received messages describing channel characteristics for a submarine.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to maintain/set timers based on the occurrence of a broadcast command event, and a system that uses a timer for a submarine to delay the transmission of feedback messages.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of maintaining/setting timers based on the occurrence of a broadcast command event, and for delaying timer-based congestion window size modifications for submarines.

In an embodiment, a system is disclosed for communicating data between nodes using a computer vision system that has the ability to maintain/set a timer based on the occurrence of a delivery command event, and that is capable of delaying changes to the congestion window size based on the timer and canceling the change to the congestion window size upon receiving a feedback message indicating successful delivery for the submarine.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes with the ability to configure new connections using maintained data characterizing a submarine's current and previous connections.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to configure new connections using maintenance data that characterizes the error rates of a submarine's current/previous connections.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to configure new connections using maintained data that characterizes timing variations of a submarine's current/previous connections.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to configure new connections using maintained data that characterizes the bandwidth of a submarine's current and previous connections.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to configure new connections using maintained data that characterizes the round-trip times of a submarine's current and previous connections.

In an embodiment, a system for data communication between nodes using a computer vision system is disclosed that has the ability to configure new connections using maintained data characterizing communication control parameters of current and previous connections on a submarine.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to configure new connections using maintained data that characterizes the forward error correction parameters of a submarine's current/previous connections.

In one embodiment, a system for communicating data between nodes using a computer vision system is disclosed, the system having a data store for maintaining data characterizing one or more current or previous data communication connections, and a connection initiation module for initiating new data communication connections based on the maintained data for a submarine.

In one embodiment, a system is disclosed for communicating data between nodes that have the capability to transmit a first subset of data messages over a low-latency data path and a second subset of messages over a high-latency data path for a submarine, using a computer vision system.

In one embodiment, a system for communicating data using a computer vision system between nodes capable of transmitting a first subset of time-critical data messages over a low-latency data path and a system capable of transmitting a second subset of messages over a high-latency data path for a submarine is disclosed.

In one embodiment, a system for communicating data using a computer vision system between nodes capable of transmitting a first initial subset of data messages over a low-latency data path, and then a second subset of messages available over a high-latency data path for a submarine, is disclosed.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to transmit a first subset of acknowledgement messages over a low-latency data path and a second subset of data messages over a high-latency data path for a submarine.

In an embodiment, a system for data communication between nodes capable of transmitting a first subset of supplemental/redundant data messages over a low-latency data path using a computer vision system and a system capable of transmitting a second subset of data messages over a high-latency data path for a submarine is disclosed.

In an embodiment, a system is disclosed for communicating data between nodes using a computer vision system, with a degree of redundancy associated with each message based on the message's position in a submarine's transmission sequence.

In an embodiment, a system is disclosed for communicating data between nodes using a computer vision system, with a degree of redundancy associated with each message increasing as the message's location relative to the submarine decreases.

In an embodiment, a system is disclosed for data communication between nodes using a computer vision system in response to receiving feedback messages for a submarine based on the message's position in a transmission order, with a degree of redundancy associated with each message.

In an embodiment, a data communication system using a computer vision system is disclosed in which feedback messages in response to receiving and adding or removing redundant messages from a queue based on the submarine feedback messages between nodes having a degree of redundancy associated with each message that is based on the message's position in a transmission order.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that has the ability to adjust the number of messages sent over each of multiple different data paths with different communication protocols if it is determined that the data path is altering the flow of messages for a submarine.

In an embodiment, a system for data communication between nodes is disclosed that has the ability to adjust the number of messages sent over each of multiple different data paths having different communication protocols when a computer vision system is used to determine that the data path is altering the initial division of the message flow based on previous communication connections for the submarine.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to modify/add/delete redundancy information associated with encoded data as it travels from node to node over a channel based on channel characteristics for a submarine.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to transmit FEC packets at an estimated rate for submarine loss events (isolated packet losses or bursts of consecutive packets).

In an embodiment, a system for data communication between nodes with combined coding, TCP, and pacing of packet transmissions for submarines is disclosed using a computer vision system.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system with a forward error correcting code configuration that interleaves groups of message packets with parity packets and performs coding across overlapping groups of undersea message packets.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system with a variation of TCP that combines a stable window growth function for submarines with a delay-based backoff.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with the use of an analog crosspoint switch to collect a variable group of analog sensor inputs for wind energy production is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with upfront signal conditioning on a multiplexer for improved signal-to-noise ratio for wind energy production is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with multiplexer continuous monitoring alarm functionality for wind energy production.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment using distributed CPLD chips with multiple MUXes for wind power generation and a dedicated bus for logical control of the data collection units.

In one embodiment, a system is disclosed that uses a computer vision system to collect data on design topologies for wind energy production in industrial environments with high amperage input capabilities using solid-state relays.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment having the ability to power down at least one of an analog sensor channel and a component board for wind energy production is disclosed.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with unique electrostatic protection for triggers and vibration inputs for wind energy production.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with an accurate voltage reference for an A/D zero reference for wind energy production.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a phase-locked loop bandpass tracking filter to obtain slow RPM and phase information for wind energy production.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment using onboard timers for wind energy production to digitally derive phase for input and trigger channels.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed that has a peak detector for autoscaling routed to a separate analog-to-digital converter for peak detection for wind energy production.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with routing of a trigger channel that is raw or buffered to other analog channels for wind energy production.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed that uses higher input oversampling for a delta-sigma A/D for a lower sampling rate output to minimize AA filter requirements for wind energy production.

In one embodiment, a data collection system using a computer vision system in an industrial environment is disclosed that uses a CPLD as a clock distributor for a delta-sigma analog-to-digital converter to achieve a lower sampling rate without requiring digital resampling for wind power generation.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with long blocks of data at high sampling rates, as opposed to multiple data sets captured at different sampling rates for wind energy production.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment where wind power generation board card sets store calibration data with maintenance history.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with rapid route creation using hierarchical templates for wind energy production.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with intelligent management of data collection bands for wind energy production is disclosed.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a neural net expert system that uses intelligent management of data collection bands for wind energy production.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with the use of a database hierarchy in analyzing sensor data for wind energy production is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with an expert system GUI graphical approach for defining.
An intelligent data collection band and diagnostics for an expert system for wind energy production is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with a graphical approach for back-calculation definition for wind energy production is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a proposed bearing analysis method for wind energy production is disclosed.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment, including torsional vibration detection/analysis using transient signal analysis for wind energy production.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with improved integration using both analog and digital methods for wind energy production.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with adaptive scheduling techniques for continuous monitoring of analog data in a local environment for wind energy production.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment having a data acquisition parking facility for wind energy production is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with a self-sufficient data collection box for wind energy production is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with SD card storage for wind energy production.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with enhanced on-board statistical capabilities for continuous monitoring of wind energy production.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment using ambient noise, local noise, and vibration noise to predict wind energy production.

In an embodiment, a system that uses a computer vision system to collect data in an industrial environment with smart routes, alarms, and the ability to change routes based on incoming data and simultaneous dynamic data for analysis or correlation for wind energy production is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with smart ODS and transmission capabilities for wind energy production.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a hierarchical multiplexer for wind energy production.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment having a plethora of identification sensors for wind energy production.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with RF identification and inclinometers for wind energy production.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with continuous ultrasonic monitoring for wind energy production is disclosed.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with cloud-based machine pattern recognition based on the fusion of remote analog industrial sensors for wind energy production.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with cloud-based machine pattern analysis of condition information from multiple analog industrial sensors to provide predictive condition information for an industrial system for wind energy production.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a cloud-based policy automation engine for IoT, involving the creation, deployment, and management of IoT devices for wind energy production, is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with on-device sensor fusion and data storage for industrial IoT devices for wind energy production is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a self-organizing data marketplace for industrial IoT data for wind energy production is disclosed.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with self-organization of a data pool based on utilization and/or yield metrics of wind energy production.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with training AI models based on industry-specific feedback for wind energy production.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a self-organized group of industrial data collectors for wind energy production.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT distributed ledger for wind energy production.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with self-organizing collectors for wind energy production is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with network-sensitive collectors for wind energy production is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with remotely organized collectors for wind energy production is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with self-organizing storage for a multi-sensor data collector for wind energy production is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with self-organizing network coding for a multi-sensor data network for wind energy production is disclosed.

In one embodiment, a system is disclosed for data collection using a computer vision system in an industrial environment with a wearable tactile user interface for an industrial sensor data collector with vibration, heat, electrical, and/or acoustic outputs for wind energy production.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a heat map displaying collected data for AR/VR for wind energy production is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with automatically adjusted AR/VR visualization of data collected by a data collector for wind energy production is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT platform for wind energy production.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment having an IoT data adapter for receiving data input and establishing a connection with one or more available IoT cloud platforms for publishing data for wind energy production.

In one embodiment, a system for collecting data using a computer vision system in an industrial environment is disclosed, having a condition detector for detecting conditions associated with connection attempts by an IoT data adapter to one or more IoT cloud platforms for wind energy production.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT data adapter equipped with an adaptive engine for wind energy production.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with the use of machine learning to prepare data packets or streams for wind energy production.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a data marketplace that provides a pool of available cloud networking platforms for wind energy production.

In an embodiment, a system for data collection in an industrial environment using a computer vision system is disclosed having a messaging utility that provides messages to a cloud platform user interface indicating the availability of new data sources and instructions for integrating and using data sources for wind energy production.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to maintain first and second transmission limits based on the received arrival rate and success rate of delivery feedback messages, and that limits the transmission of messages based on transmission limits for wind energy production.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system that has the ability to restrict the transmission of further messages that have not yet been acknowledged as successfully delivered, depending on a window size for wind power generation.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of maintaining an estimate of the rate of loss events and using it to adjust the rate of redundancy messages for wind energy production.

In an embodiment, a system is disclosed for communicating data using a computer vision system between nodes having an estimated rate of loss events, where the error correction code used to determine the selected redundancy message is based on the estimated rate of loss events for wind energy production.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of applying forward error correction based on received messages describing channel characteristics for wind power generation.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of maintaining/setting timers based on the occurrence of a broadcast command event, and that uses a timer to delay the transmission of feedback messages for wind energy production.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of maintaining/setting timers based on the occurrence of a distribution command event, and that is capable of delaying the modification of congestion window size based on a timer for wind power generation.

In an embodiment, a system is disclosed for communicating data between nodes using a computer vision system, the system having the ability to maintain/set a timer based on the occurrence of a delivery command event, delay a change in congestion window size based on the timer, and cancel the change in congestion window size upon receiving a feedback message indicating successful delivery for wind energy generation.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to configure new connections using maintained data characterizing current and previous connections for wind energy production.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of configuring new connections using maintained data characterizing the error rates of current/previous connections for wind energy production.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of configuring new connections using maintained data characterizing timing variations of current/previous connections for wind energy production.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of configuring new connections using maintained data characterizing the bandwidth of current/previous connections for wind energy production.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of configuring new connections using maintained data characterizing the round-trip times of current and previous connections for wind energy production.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of configuring new connections using maintained data characterizing communication control parameters of current/previous connections for wind energy production.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of configuring new connections using maintained data characterizing forward error correction parameters of current/previous connections for wind energy production.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system, the system having a data store for maintaining data characterizing one or more current or previous data communication connections, and a connection initiation module for initiating new data communication connections based on the maintained data for wind energy production.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of transmitting a first subset of data messages over a low-latency data path and a second subset of messages over a high-latency data path for wind energy production.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of transmitting a first subset of time-critical data messages over a low-latency data path and a second subset of messages over a high-latency data path for wind energy production.

In one embodiment, a system for communicating data using a computer vision system between nodes capable of transmitting a first initial subset of data messages over a low-latency data path, followed by a second subset of messages available over a high-latency data path, for wind energy production is disclosed.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of transmitting a first subset of acknowledgement messages over a low-latency data path and a second subset of data messages over a high-latency data path for wind energy production.

In an embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of transmitting a first subset of supplemental/redundant data messages over a low-latency data path and a second subset of data messages over a high-latency data path for wind energy production.

In an embodiment, a system is disclosed for data communication between nodes using a computer vision system, with a degree of redundancy associated with each message based on the message's position in a transmission sequence for wind energy production.

In one embodiment, a system for wind energy production is disclosed that uses a computer vision system to communicate data between nodes with a degree of redundancy associated with each message that increases as the message's location decreases.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes in response to receiving feedback messages for wind energy production, with a degree of redundancy associated with each message based on the message's position in a transmission order.

In an embodiment, a system is disclosed for data communication between nodes using a computer vision system with a degree of redundancy associated with each message based on the message's position in a transmission order, and in response to receiving a feedback message, the system adds or removes redundant messages from a queue based on the feedback message for wind energy production.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that has the ability to adjust the number of messages sent over each of multiple different data paths with different communication protocols when it is determined that the data paths are altering the flow of messages for wind energy production.

In an embodiment, a system for data communication between nodes is disclosed that has the ability to adjust the number of messages sent on each of multiple different data paths having different communication protocols when a computer vision system is used to determine that the data paths are changing the message flow at an initial split based on previous communication connections for wind energy production.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that has the ability to modify/add/delete redundancy information associated with the encoded data as it travels from node to node over a channel based on channel characteristics for wind energy generation.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of transmitting FEC packets at an estimated rate of loss events (isolated packet losses or bursts of consecutive packets) for wind energy production.

In an embodiment, a system for data communication using a computer vision system between nodes with combined coding, TCP, and pacing of packet transmissions for wind energy production is disclosed.

In an embodiment, a system for data communication between nodes using a computer vision system is disclosed that interleaves groups of message packets with parity packets and has a forward error correction code structure with coding across overlapping groups of message packets for wind energy production.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system with a variation of TCP that combines a stable window growth function and delay-based backoff for wind energy production.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with the use of an analog crosspoint switch to collect a variable group of analog sensor inputs for hydroelectric energy production is disclosed.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with upfront signal conditioning on a multiplexer for improved signal-to-noise ratio for hydroelectric energy production.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with multiplexed continuous monitoring alarm functionality for hydroelectric energy production.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment using distributed CPLD chips with multiple MUXes for hydroelectric power generation and a dedicated bus for logical control of the data collection units.

In embodiments, a system using a computer vision system for data collection in an industrial environment with high amperage input capabilities using solid-state relays and a design topology for hydroelectric energy production are disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment having power-down capability for at least one analog sensor channel and a component board for hydroelectric power generation is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with unique electrostatic protection for triggers and vibration inputs for hydroelectric energy production is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with an accurate voltage reference for A/D zero reference for hydroelectric energy production is disclosed.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a phase-locked loop bandpass tracking filter to obtain slow RPM and phase information for hydroelectric energy production.

In an embodiment, a system for data collection in an industrial environment with digital derivation of phase for input and trigger channels using a computer vision system and an onboard timer for hydroelectric energy production is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed that has a peak detector for autoscaling routed to a separate analog-to-digital converter for peak detection for hydroelectric energy production.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with routing of a trigger channel that is raw or buffered to other analog channels for hydroelectric energy production.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed that uses higher input oversampling for a delta-sigma A/D for a lower sampling rate output to minimize AA filter requirements for hydroelectric energy production.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed that uses a CPLD as a clock distributor for a delta-sigma analog-to-digital converter to achieve lower sampling rates without the need for digital resampling for hydroelectric energy production.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with long blocks of data at high sampling rates, as opposed to multiple data sets taken at different sampling rates for hydroelectric energy production.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment where calibration data with maintenance history is stored on board card sets for hydroelectric power generation.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with rapid route creation using hierarchical templates for hydroelectric energy production.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with intelligent management of data collection bands for hydroelectric energy production is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a neural net expert system that uses intelligent management of data collection bands for hydroelectric energy production is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with the use of a database hierarchy in sensor data analysis for hydroelectric energy production is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed that has an expert system GUI graphical approach for defining intelligent data collection bands and diagnostics for an expert system for hydroelectric energy production.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a graphical approach for back-calculation definition for hydroelectric energy production is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a proposed bearing analysis method for hydroelectric energy production is disclosed.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with torsional vibration detection/analysis using transient signal analysis for hydroelectric energy production.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with improved integration using both analog and digital methods for hydroelectric energy production.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with adaptive scheduling techniques for continuous monitoring of analog data in a local environment for hydroelectric energy production is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment having a data acquisition parking facility for hydroelectric energy production is disclosed.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a self-sufficient data collection box for hydroelectric energy production.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with SD card storage for hydroelectric energy production.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with enhanced on-board statistical capabilities for continuous monitoring of hydroelectric energy production.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with the use of ambient noise, local noise, and vibration noise for predictions for hydroelectric energy production.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with smart routes that change routes based on input data or alarms, enabling simultaneous dynamic data for analysis or correlation for hydroelectric energy production.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with smart ODS and transmission capabilities for hydroelectric energy production.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a hierarchical multiplexer for hydroelectric energy production.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment having a plethora of identification sensors for hydroelectric energy production.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with RF identification and inclinometers for hydroelectric energy production.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with continuous ultrasonic monitoring for hydroelectric energy production.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with cloud-based machine pattern recognition based on the fusion of remote analog industrial sensors for hydroelectric energy production.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with cloud-based machine pattern analysis of condition information from multiple analog industrial sensors to provide predictive condition information for an industrial system for hydroelectric energy production.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a cloud-based policy automation engine for IoT, involving the creation, deployment, and management of IoT devices for hydroelectric energy production, is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with on-device sensor fusion and data storage for industrial IoT devices for hydroelectric energy production is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with a self-organizing data marketplace for industrial IoT data for hydroelectric energy production is disclosed.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with self-organization of data pools based on utilization and/or yield metrics for hydroelectric energy production.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with training AI models based on industry-specific feedback for hydroelectric energy production.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a self-organized group of industrial data collectors for hydroelectric energy production.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT distributed ledger for hydroelectric energy production.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with self-organizing collectors for hydroelectric energy production is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with network-sensitive collectors for hydroelectric energy production is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with remotely organized collectors for hydroelectric energy production.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with self-organizing storage for a multi-sensor data collector for hydroelectric energy production is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with self-organizing network coding for a multi-sensor data network for hydroelectric energy production is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment is disclosed having a wearable tactile user interface for an industrial sensor data collector with vibration, heat, electrical, and/or acoustic outputs for hydroelectric energy production.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a heat map displaying collected data for AR/VR for hydroelectric energy production is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with automatically tailored AR/VR visualization of data collected by data collectors for hydro-energy production is disclosed.

In one embodiment, a system for collecting data using a computer vision system in an industrial environment with an IoT platform for hydroelectric energy production is disclosed.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment having an IoT data adapter for receiving data input and establishing a connection with one or more available IoT cloud platforms for publishing the data for hydroelectric energy production.

In one embodiment, a system is disclosed for data collection using a computer vision system in an industrial environment having a condition detector for detecting conditions associated with connection attempts by an IoT data adapter to one or more IoT cloud platforms for hydroelectric energy production.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with an IoT data adapter equipped with an adaptive engine for hydroelectric energy production.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with the use of machine learning to prepare data packets or streams for hydroelectric energy production is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a data marketplace that provides a pool of available cloud networking platforms for hydroelectric energy production is disclosed.

In an embodiment, a system for data collection in an industrial environment using a computer vision system is disclosed, having a messaging utility that provides messages to a cloud platform user interface indicating the availability of new data sources, and integrating and directing the use of data sources for hydroelectric energy production.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to maintain first and second transmission limits based on received arrival rates and the success of delivery feedback messages, and that limits the transmission of messages based on transmission limits for hydroelectric energy production.

In an embodiment, a system is disclosed for communicating data between nodes using a computer vision system that has the ability to restrict the transmission of further messages that have not yet been acknowledged as successfully delivered according to a window size for hydroelectric energy generation.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of maintaining an estimate of the rate of loss events and using it to adjust the rate of redundancy messages for hydroelectric energy production.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes having an estimated rate of loss events, where the error correction code used to determine the selected redundancy message is based on the estimated rate of loss events for hydroelectric energy production.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of applying forward error correction based on received messages describing channel characteristics for hydroelectric energy production.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to maintain/set timers based on the occurrence of broadcast command events, and that uses timers to delay the transmission of feedback messages for hydroelectric energy production.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of maintaining/setting timers based on the occurrence of a distribution command event, and that delays modification of congestion window size based on a timer for hydroelectric energy production.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system, with the nodes maintaining/setting a timer based on the occurrence of a delivery command event, delaying a change in congestion window size based on the timer, and canceling the change in congestion window size upon receiving a feedback message indicating successful delivery for hydroelectric power generation.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of configuring new connections using maintained data characterizing current and previous connections for hydroelectric energy production.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to configure new connections using maintained data characterizing the error rates of current/previous connections for hydroelectric energy production.

In an embodiment, a system is disclosed for data communication between nodes that uses a computer vision system to configure new connections using maintained data characterizing timing variations of current/previous connections for hydroelectric energy production.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of configuring new connections using maintained data characterizing the bandwidth of current/previous connections for hydroelectric energy production.

In an embodiment, a system is disclosed for data communication between nodes using a computer vision system with the ability to configure new connections using maintained data characterizing the round-trip times of current/previous connections for hydroelectric energy production.

In an embodiment, a system for data communication between nodes using a computer vision system with the ability to configure new connections using maintained data characterizing communication control parameters of current/previous connections for hydroelectric energy production is disclosed.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to configure new connections using maintained data characterizing forward error correction parameters of current/previous connections for hydroelectric energy production.

In one embodiment, a system for communicating data between nodes using a computer vision system is disclosed, the system having a data store for maintaining data characterizing one or more current or previous data communication connections, and a connection initiation module for initiating new data communication connections based on the maintained data for hydroelectric energy production.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of transmitting a first subset of data messages over a low-latency data path and a second subset of messages over a high-latency data path for hydroelectric energy production.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of transmitting a first subset of time-critical data messages over a low-latency data path and a second subset of messages over a high-latency data path for hydroelectric energy production.

In an embodiment, a system is disclosed for data communication between a node capable of transmitting a first initial subset of data messages over a low-latency data path and a node capable of transmitting a later available second subset of messages over a high-latency data path for hydroelectric energy production, using a computer vision system.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of transmitting a first subset of acknowledgement messages over a low-latency data path and a second subset of data messages over a high-latency data path for hydroelectric energy production.

In an embodiment, a system is disclosed for data communication between nodes capable of transmitting a first subset of supplemental/redundant data messages over a low-latency data path and a second subset of data messages over a high-latency data path for hydroelectric energy production using a computer vision system.

In an embodiment, a system is disclosed for data communication between nodes using a computer vision system, with a degree of redundancy associated with each message based on the message's position in a transmission sequence for hydroelectric energy production.

In an embodiment, a system for data communication using a computer vision system is provided between nodes having a degree of redundancy associated with each of the following messages:
For hydroelectric power generation, it is disclosed that the location of the message increases rather than decreases.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes in response to receiving feedback messages for hydroelectric energy production, with redundancy associated with each message being based on the message's position in a transmission order.

In an embodiment, a system is disclosed for data communication between nodes using a computer vision system to add or remove redundant messages from a queue based on the message's position in a transmission order in response to receiving a feedback message, the redundant messages being added or removed from a queue based on the feedback message for hydroelectric energy production.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that has the ability to adjust the number of messages sent over each of multiple different data paths with different communication protocols when it is determined that the data path is altering the flow of messages for hydroelectric power generation.

In an embodiment, a system for data communication between nodes is disclosed that has the ability to adjust the number of messages sent over each of multiple different data paths having different communication protocols when a computer vision system is used to determine that the data path is altering the initial division of messages based on previous communication connections for hydroelectric energy production.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that has the ability to modify/add/delete redundancy information associated with encoded data as it travels from node to node over a channel based on channel characteristics for hydroelectric energy generation.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of transmitting FEC packets at an estimated rate of loss events (isolated packet losses or bursts of consecutive packets) for hydroelectric energy production.

In an embodiment, a system for data communication using a computer vision system between nodes with combined coding, TCP, and pacing of packet transmissions for hydroelectric energy production is disclosed.

In an embodiment, a system is disclosed for data communication between nodes using a computer vision system with a forward error correction code structure that interleaves groups of message packets with parity packets and has coding across overlapping groups of message packets for hydroelectric energy generation.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system with a TCP variant that combines a delay-based backoff and a stable window growth function for hydroelectric energy production.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with the use of an analog crosspoint switch to collect a variable group of analog sensor inputs for nuclear energy production is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with upfront signal conditioning on a multiplexer for improved signal-to-noise ratio for nuclear energy production is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with multiplexed continuous monitoring alarm functionality for nuclear energy production.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment using distributed CPLD chips with multiple MUXes for nuclear power generation and a dedicated bus for logical control of the data collection units.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with high amperage input capabilities using solid-state relays and design topologies for nuclear energy production.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment having power-down capability for at least one of an analog sensor channel and a nuclear power component board is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with unique electrostatic protection for triggers and vibration inputs for nuclear energy production.

In one embodiment, a system for data collection using a computer vision system in an industrial environment with an accurate voltage reference for A/D zero reference for nuclear energy production is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a phase-locked loop bandpass tracking filter to obtain slow RPM and phase information for nuclear energy production.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment using onboard timers for nuclear power plants to digitally derive phase for input and trigger channels.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed that has a peak detector for autoscaling routed to a separate analog-to-digital converter for peak detection for nuclear energy production.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with routing of raw or buffered trigger channels to other analog channels for nuclear energy production.

In an embodiment, a system for data collection in an industrial environment using a computer vision system is disclosed, which has the use of higher input oversampling for a delta-sigma A/D for a lower sampling rate output to minimize AA filter requirements for nuclear energy production.

In one embodiment, a data acquisition system using a computer vision system in an industrial environment is disclosed that uses a CPLD as a clock distributor for a delta-sigma analog-to-digital converter to achieve lower sampling rates without the need for digital resampling for nuclear power generation.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with long blocks of data at high sampling rates, as opposed to multiple data sets taken at different sampling rates for nuclear energy production.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment where calibration data with maintenance history is stored on board card sets for nuclear power generation.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with rapid route generation capabilities using hierarchical templates for nuclear energy production.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with intelligent management of data collection bands for nuclear energy production is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a neural net expert system that uses intelligent management of data collection bands for nuclear energy production is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with the use of a database hierarchy in sensor data analysis for nuclear energy production is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with an expert system GUI graphical approach to define intelligent data collection bands and diagnostics for an expert system for nuclear energy production is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with a graphical approach for back-calculation definition for nuclear energy production is disclosed.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment that proposes a bearing analysis method for nuclear energy production.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with torsional vibration detection/analysis using transient signal analysis for nuclear energy production.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with improved integration using both analog and digital methods for nuclear energy production.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with adaptive scheduling techniques for continuous monitoring of analog data in a local environment for nuclear energy production is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment having a data collection parking facility for nuclear energy production is disclosed.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a self-sufficient data collection box for nuclear energy production.

In one embodiment, a system for collecting data using a computer vision system in an industrial environment with SD card storage for nuclear energy production is disclosed.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with enhanced on-board statistical capabilities for continuous monitoring of nuclear energy production.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with the use of ambient noise, local noise, and vibration noise for predictions for nuclear energy production.

In an embodiment, a system for data collection in an industrial environment is disclosed that uses a computer vision system to have smart routes that change route based on input data or alarms, enabling simultaneous dynamic data for analysis or correlation for nuclear energy production.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with smart ODS and forwarding capabilities for nuclear energy production is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a hierarchical multiplexer for nuclear energy production.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a plethora of identification sensors for nuclear energy production.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with RF identification and tilt meters for nuclear energy production.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with continuous ultrasonic monitoring for nuclear energy production.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with cloud-based machine pattern recognition based on fusion of remote analog industrial sensors for nuclear energy production.

In an embodiment, a system is disclosed for data collection using a computer vision system in an industrial environment with cloud-based machine pattern analysis of condition information from multiple analog industrial sensors to provide predictive condition information for an industrial system for nuclear energy production.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a cloud-based policy automation engine for IoT, involving the creation, deployment, and management of IoT devices for nuclear energy production, is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with on-device sensor fusion and data storage for industrial IoT devices for nuclear energy production is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a self-organizing data marketplace for industrial IoT data for nuclear energy production is disclosed.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with self-organization of data pools based on utilization and/or yield metrics for nuclear energy production.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with training AI models based on industry-specific feedback for nuclear energy production is disclosed.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a self-organized group of industrial data collectors for nuclear energy production.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT distributed ledger for nuclear energy production.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with self-organizing collectors for nuclear energy production is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with network-sensitive collectors for nuclear energy production is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with remotely organized collectors for nuclear energy production is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with self-organizing storage for a multi-sensor data collector for nuclear energy production is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with self-organizing network coding for a multi-sensor data network for nuclear energy production is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment is disclosed having a wearable tactile user interface for an industrial sensor data collector with vibration, heat, electrical, and/or acoustic outputs for nuclear energy production.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a heat map displaying collected data for AR/VR for nuclear energy production is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with automatically tailored AR/VR visualization of data collected by data collectors for nuclear energy production is disclosed.

In one embodiment, a system for collecting data using a computer vision system in an industrial environment with an IoT platform for nuclear energy production is disclosed.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment having an IoT data adapter for receiving data input and establishing a connection with one or more available IoT cloud platforms for publishing the data for nuclear energy production.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment having a condition detector for detecting conditions associated with connection attempts by an IoT data adapter to one or more IoT cloud platforms for nuclear energy production.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment having an IoT data adapter with an adaptive engine for nuclear energy production is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with the use of machine learning to prepare data packets or streams for nuclear energy production is disclosed.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment having a data marketplace that provides a pool of available cloud networking platforms for nuclear energy production.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a messaging utility that provides messages to a cloud platform user interface indicating the availability of new data sources, and integrates and directs the use of data sources for nuclear energy production.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to maintain first and second transmission limits based on received arrival rates and the success of delivery feedback messages, and that limits the transmission of messages based on transmission limits for nuclear energy production.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to restrict the transmission of further messages that have not yet been acknowledged as successfully delivered according to a window size for nuclear energy production.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of maintaining an estimate of the rate of loss events and using it to adjust the rate of redundancy messages for nuclear energy production.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes having an estimated rate of loss events, where the error correction code used to determine the selected redundancy message is based on the estimated rate of loss events for nuclear energy production.

In an embodiment, a system is provided for data communication using a computer vision system between nodes having the ability to apply forward error correction based on:
A received message describing channel characteristics for nuclear power generation is disclosed.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to maintain/set timers based on the occurrence of delivery command events, where the timers are used to delay the transmission of feedback messages for nuclear energy production.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of maintaining/setting timers based on the occurrence of a broadcast command event, and that delays timer-based congestion window size modifications for nuclear power generation.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system, with the nodes maintaining/setting a timer based on the occurrence of a distribution command event, delaying a change in congestion window size based on the timer, and canceling the change in congestion window size upon receiving a feedback message indicating successful distribution for nuclear power generation.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to configure new connections using maintained data characterizing current and previous connections for nuclear energy production.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of configuring new connections using maintained data characterizing the error rates of current/previous connections for nuclear energy production.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to configure new connections using maintained data characterizing timing variations of current/previous connections for nuclear energy production.

In an embodiment, a system for data communication between nodes using a computer vision system with the ability to configure new connections using maintained data characterizing the bandwidth of current/previous connections for nuclear energy production is disclosed.

In an embodiment, a system is disclosed for data communication between nodes that uses a computer vision system and has the ability to configure new connections using maintained data characterizing the round-trip times of current/previous connections for nuclear energy production.

In an embodiment, a system is disclosed for data communication between nodes using a computer vision system with the ability to configure new connections using maintained data characterizing communication control parameters of current/previous connections for nuclear energy production.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to configure new connections using maintained data characterizing forward error correction parameters of current/previous connections for nuclear energy production.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system, the system having a data store for maintaining data characterizing one or more current or previous data communication connections, and a connection initiation module for initiating new data communication connections based on the maintained data for nuclear energy production.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of transmitting a first subset of data messages over a low-latency data path and a second subset of messages over a high-latency data path for nuclear energy production.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of transmitting a first subset of time-critical data messages over a low-latency data path and a second subset of messages over a high-latency data path for nuclear energy production.

In an embodiment, a system is disclosed for data communication between a node capable of transmitting a first initial subset of data messages over a low-latency data path and a node capable of transmitting a second subset of later available messages over a high-latency data path for nuclear energy production, using a computer vision system.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of transmitting a first subset of acknowledgment messages over a low-latency data path and a second subset of data messages over a high-latency data path for nuclear energy production.

In an embodiment, a system for data communication using a computer vision system, wherein the system has the capability to transmit a first subset of complementary/redundant data messages on a low latency data path and a second subset of data messages on a high latency data path, is disclosed for nuclear energy production.

In an embodiment, a system is disclosed for communicating data between nodes using a computer vision system, with a degree of redundancy associated with each message based on the message's position in a transmission sequence for nuclear energy production.

In one embodiment, a system for nuclear energy production is disclosed that uses a computer vision system to communicate data between nodes with a degree of redundancy associated with each message that increases as the message's location decreases.

In an embodiment, a system is disclosed for data communication between nodes using a computer vision system in response to receiving feedback messages for nuclear energy production based on the message's position in a transmission order, with a degree of redundancy associated with each message.

In an embodiment, a system is disclosed for data communication between nodes using a computer vision system to add or remove redundancy messages from a queue based on the message's position in a transmission order in response to receiving a feedback message, the redundancy messages being associated with each message, and for nuclear energy production.

In one embodiment, a system for data communication between nodes using a computer vision system is disclosed that has the ability to adjust the number of messages sent over each of multiple different data paths having different communication protocols if it is determined that the data path is altering the flow of messages for nuclear energy production.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to adjust the number of messages sent over each of multiple different data paths with different communication protocols when it is determined that the data paths are altering the initial division of messages based on previous communication connections for nuclear energy production.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that has the ability to modify/add/delete redundancy information associated with encoded data as it travels from node to node over a channel based on channel characteristics for nuclear power generation.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of transmitting FEC packets at an estimated rate of loss events (isolated packet losses or bursts of consecutive packets) for nuclear energy production.

In an embodiment, a system is disclosed for communicating data between nodes using a computer vision system with combined coding, TCP, and pacing of packet transmissions for nuclear energy production.

In an embodiment, a system is disclosed for data communication between nodes using a computer vision system with a forward error correction code structure that interleaves groups of message packets with parity packets and has coding across overlapping groups of message packets for nuclear energy production.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system with a variation of TCP that combines a stable window increasing function for nuclear power generation with delay-based backoff.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with the use of analog crosspoint switches to collect a variable group of analog sensor inputs for oil drilling is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with upfront signal conditioning on a multiplexer for improved signal-to-noise ratio for oil drilling is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with multiplexer continuous monitoring alarm functionality for oil drilling.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment using distributed CPLD chips with dedicated buses for logical control of multiple MUXes and data collection units for oil drilling.

In embodiments, a system using a computer vision system to collect data in an industrial environment with high amperage input capabilities using solid-state relays, and a design topology for oil drilling are disclosed.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment having the ability to power down at least one analog sensor channel and component board for oil drilling.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with unique electrostatic protection for triggers and vibration inputs for oil drilling.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with an accurate voltage reference for an A/D zero reference for oil drilling is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a phase-locked loop bandpass tracking filter to obtain low RPM and phase information for oil drilling.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment using an onboard timer for an oil drilling drill to digitally derive phase for input and trigger channels.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed that has a peak detector for autoscaling routed to a separate analog-to-digital converter for peak detection for oil drilling.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with routing of a trigger channel that is raw or buffered to other analog channels for oil drilling.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed that uses higher input oversampling for a delta-sigma A/D for a lower sampling rate output to minimize AA filter requirements for oil drilling.

In an embodiment, a system for data collection using computer vision systems in an industrial environment is disclosed that uses a CPLD as a clock distributor for a delta-sigma analog-to-digital converter to achieve low sampling rates without the need for digital resampling for oil drilling.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with long blocks of data at high sampling rates, as opposed to multiple data sets captured at different sampling rates for oil drilling.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment where calibration data with maintenance history is stored on board card sets for oil drilling.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with rapid route creation using hierarchical templates for oil drilling.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with intelligent management of data collection bands for oil drilling is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a neural net expert system that uses intelligent management of data collection bands for oil drilling is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with the use of a database hierarchy in analyzing sensor data for oil drilling is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed that has an expert system GUI graphical approach for defining intelligent data collection bands and diagnostics for an expert system for oil drilling.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a graphical approach for back-calculation definition for oil drilling is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a proposed bearing analysis method for oil drilling is disclosed.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment, including torsional vibration detection/analysis using transient signal analysis for oil drilling.

In an embodiment, a system for data collection using computer vision systems in an industrial environment with improved integration using both analog and digital methods for oil drilling is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with adaptive scheduling techniques for continuous monitoring of analog data in a local environment for oil drilling is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment having a data acquisition parking facility for oil drilling is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with a self-sufficient data collection box for oil drilling is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with SD card storage for oil drilling.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with enhanced on-board statistical capabilities for continuous monitoring of oil drilling.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with the use of ambient noise, local noise, and vibration noise for prediction of oil drilling is disclosed.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with smart routes that change routes based on input data or alarms, enabling simultaneous dynamic data for analysis or correlation for oil drilling.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with smart ODS and forwarding capabilities for oil drilling.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a hierarchical multiplexer for oil drilling.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a plethora of discriminatory sensors for oil drilling.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with RF identification and tilt meters for oil drilling.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with continuous ultrasonic monitoring for oil drilling.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with cloud-based machine pattern recognition based on the fusion of remote analog industrial sensors for oil drilling.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with cloud-based, machine pattern analysis of condition information from multiple analog industrial sensors to provide predictive condition information for an industrial system for oil drilling.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a cloud-based policy automation engine for IoT, involving the creation, deployment, and management of IoT devices for oil drilling, is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with on-device sensor fusion and data storage for industrial IoT devices for oil drilling is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with a self-organizing data marketplace for industrial IoT data for oil drilling is disclosed.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with self-organization of data pools based on utilization and/or yield metrics of oil drilling.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with training AI models based on industry-specific feedback for oil drilling.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a self-organized group of industrial data collectors for oil drilling.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT distributed ledger for oil drilling.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with self-organizing collectors for oil drilling is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with network-sensitive collectors for oil drilling is disclosed.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with remotely organized collectors for oil drilling.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with self-organizing storage for a multi-sensor data collector for oil drilling is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with self-organizing network coding for a multi-sensor data network for oil drilling is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment is disclosed having a wearable tactile user interface for an industrial sensor data collector with vibration, heat, electrical and/or sound outputs for oil drilling.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed, having a heat map displaying collected data for AR/VR for oil drilling.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with automatically tailored AR/VR visualization of data collected by data collectors for oil drilling is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT platform for oil drilling.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment having an IoT data adapter for receiving data input and establishing a connection with one or more available IoT cloud platforms for publishing the data for oil drilling.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment having a condition detector for detecting conditions associated with connection attempts by an IoT data adapter to one or more IoT cloud platforms for oil drilling.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT data adapter equipped with an adaptive engine for oil drilling.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with the use of machine learning to prepare data packets or streams for oil drilling is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a data marketplace that provides a pool of available cloud networking platforms for oil drilling is disclosed.

In an embodiment, a system for data collection in an industrial environment using a computer vision system is disclosed having a messaging utility that provides messages to a cloud platform user interface indicating the availability of new data sources and instructions for integrating and using data sources for oil drilling.

In an embodiment, a system for data communication between nodes is disclosed that uses a computer vision system to maintain first and second transmission limits based on received arrival rates and the success of delivery feedback messages, and that limits the transmission of messages based on transmission limits for oil drilling.

In an embodiment, a system is disclosed for communicating data between nodes using a computer vision system that has the ability to restrict the transmission of further messages that have not yet been acknowledged as successfully delivered according to a window size for oil drilling.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of maintaining an estimate of the rate of loss events and using it to adjust the rate of redundancy messages for oil drilling.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes having an estimated rate of loss events, where the error correction code used to determine the selected redundancy message is based on the estimated rate of loss events for oil drilling.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of applying forward error correction based on received messages describing channel characteristics for oil drilling.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to use a timer for oil drilling, maintain/set the timer based on the occurrence of a delivery order event, and delay the transmission of feedback messages.

In one embodiment, a system for oil drilling is disclosed that uses a computer vision system to communicate data between nodes that maintain/set timers based on the occurrence of delivery order events and have the ability to delay modification of congestion window sizes based on the timers.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system, the system having the ability to maintain/set a timer based on the occurrence of a delivery command event, delay a change in congestion window size based on the timer, and cancel the change in congestion window size upon receiving a feedback message indicating successful delivery for the oil drilling.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to configure new connections using maintained data characterizing current and previous connections for oil drilling.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to configure new connections using maintained data characterizing the error rates of current and previous connections for oil drilling.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to configure new connections using maintained data that characterizes timing variations of current and previous connections for oil drilling.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to configure new connections using maintained data characterizing the bandwidth of current and previous connections for oil drilling.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to configure new connections using maintained data characterizing the round-trip times of current and previous connections for oil drilling.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of configuring new connections using maintained data characterizing communication control parameters of current and previous connections for oil drilling.

In an embodiment, a system for data communication using a computer vision system is provided between nodes that has the ability to use maintained connections to form new connections.
Data characterizing forward error correction parameters of current/previous connections for oil drilling is disclosed.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system, the system having a data store for maintaining data characterizing one or more current or previous data communication connections, and a connection initiation module for initiating new data communication connections based on the maintained data for an oil drilling operation.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of transmitting a first subset of data messages over a low-latency data path and a second subset of messages over a high-latency data path for oil drilling.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of transmitting a first subset of time-critical data messages over a low-latency data path and a second subset of messages over a high-latency data path for oil drilling.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of transmitting a first initial subset of data messages over a low-latency data path and subsequently a second subset of available messages over a high-latency data path for oil drilling.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of transmitting a first subset of acknowledgement messages over a low-latency data path and a second subset of data messages over a high-latency data path for oil drilling.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of transmitting a first subset of supplemental/redundant data messages over a low-latency data path and a second subset of data messages over a high-latency data path for oil drilling.

In an embodiment, a system is disclosed for communicating data between nodes using a computer vision system, with a degree of redundancy associated with each message based on the message's position in a transmission sequence for an oil drilling operation.

In an embodiment, a system is disclosed for communicating data between nodes using a computer vision system, with a degree of redundancy associated with each message increasing as the location of the message decreases due to oil drilling.

In an embodiment, a system is disclosed for communicating data between nodes using a computer vision system in response to receiving feedback messages for oil drilling, with a degree of redundancy associated with each message based on the message's position in a transmission order.

In an embodiment, a system is disclosed for communicating data between nodes using a computer vision system with a degree of redundancy associated with each message based on the message's position in a transmission order, and in response to receiving a feedback message, the system adds or removes redundant messages from a queue based on the feedback message for an oil drilling.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that has the ability to adjust the number of messages sent over each of multiple different data paths with different communication protocols when it is determined that the data paths are altering the flow of messages for oil drilling.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that has the ability to adjust the number of messages sent over each of multiple different data paths with different communication protocols when it is determined that the data paths are altering the flow of the initial division of messages based on previous communication connections for oil drilling.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that has the ability to modify/add/delete redundancy information associated with the encoded data as it travels from node to node over a channel based on channel characteristics for oil drilling.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of transmitting FEC packets at an estimated rate of loss events (isolated packet losses or bursts of consecutive packets) for oil drilling.

In an embodiment, a system is disclosed for communicating data between nodes using a computer vision system with combined coding, TCP, and pacing of packet transmissions for oil drilling.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system with a forward error correcting code structure that interleaves groups of message packets with parity packets and performs coding across overlapping groups of message packets for oil drilling.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system with a variant of TCP that combines a stable window growth function and delay-based backoff for oil drilling.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment is disclosed that uses an analog crosspoint switch to collect a variable group of analog sensor inputs in an oil pipeline.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with upfront signal conditioning on a multiplexer to improve the signal-to-noise ratio of an oil pipeline.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with multiplexer continuous monitoring alarm functionality for oil pipelines.

In one embodiment, a data collection system using a computer vision system in an industrial environment is disclosed, using distributed CPLD chips with multiple MUXes and a dedicated bus for logical control of the data collection section of an oil pipeline.

In an embodiment, a system is disclosed that uses a computer vision system to collect data and design topology for oil pipelines in an industrial environment with high amperage input capabilities using solid-state relays.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment having the ability to power down at least one of an analog sensor channel and an oil pipeline component board is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with unique electrostatic protection for oil pipeline triggers and vibration inputs.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an accurate voltage reference for an A/D zero reference in an oil pipeline.

In one embodiment, a system is disclosed for data collection using a computer vision system in an industrial environment with a phase-locked loop bandpass tracking filter to obtain low-speed RPM and phase information for an oil pipeline.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment using an onboard timer for an oil pipeline to digitally derive phase for input and trigger channels.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment having a peak detector for autoscaling routed to a separate analog-to-digital converter for peak detection in an oil pipeline.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with routing of a raw or buffered trigger channel to other analog channels for an oil pipeline.

In an embodiment, a system for data collection using a computer vision system in an industrial environment is disclosed that uses higher input oversampling for a delta-sigma A/D for a lower sampling rate output to minimize AA filter requirements in oil pipelines.

In one embodiment, a data acquisition system using a computer vision system in an industrial environment is disclosed that uses a CPLD as a clock divider for a delta-sigma analog-to-digital converter to achieve a lower sampling rate without requiring digital resampling for an oil pipeline.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with long blocks of data at a high sampling rate, as opposed to multiple data sets taken at different sampling rates for an oil pipeline.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment where calibration data with maintenance history is stored on board card sets for oil pipelines.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with rapid route creation using hierarchical templates for oil pipelines is disclosed.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with intelligent management of data collection bands on an oil pipeline.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a neural net expert system that uses intelligent management of data collection bands on an oil pipeline.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with the use of a database hierarchy in analyzing sensor data for an oil pipeline.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with an expert system GUI graphical approach for defining intelligent data collection bands and diagnostics for an oil pipeline is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with a graphical approach for back-calculating the definition of oil pipelines is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a proposed bearing analysis method for oil pipelines is disclosed.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment, including the detection/analysis of torsional vibrations using transient signal analysis in oil pipelines.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with improved integration using both analog and digital methods for oil pipelines.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with adaptive scheduling techniques for continuous monitoring of analog data in the local environment of an oil pipeline is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a data acquisition parking facility for an oil pipeline.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a self-contained data collection box for an oil pipeline.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with SD card storage for an oil pipeline.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with enhanced on-board statistical capabilities for continuous monitoring of oil pipelines.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with the use of ambient noise, local noise, and vibration noise for the prediction of oil pipelines.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with smart routes that change routes based on input data or alarms, enabling simultaneous dynamic data for analysis or correlation of oil pipelines.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with smart ODS and forwarding capabilities for oil pipelines.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with a hierarchical multiplexer for an oil pipeline.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment overflowing with identification sensors for oil pipelines.

In an embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with RF identification and inclinometers for oil pipelines.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment with continuous ultrasonic monitoring for an oil pipeline is disclosed.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with cloud-based machine pattern recognition based on the fusion of remote analog industrial sensors for an oil pipeline.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with cloud-based, machine pattern analysis of condition information from multiple analog industrial sensors to provide predictive condition information for an industrial system for an oil pipeline.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a cloud-based policy automation engine for IoT, involving the creation, deployment, and management of IoT devices for oil pipelines, is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with on-device sensor fusion and data storage for industrial IoT devices for oil pipelines is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a self-organizing data marketplace for industrial IoT data from oil pipelines.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with self-organization of data pools based on utilization and/or yield metrics of an oil pipeline.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a training AI model based on industry-specific feedback from oil pipelines.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a self-organized group of industrial data collectors for an oil pipeline is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT distributed ledger for oil pipelines.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment with self-organizing collectors in an oil pipeline.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with a network of sensitive collectors on an oil pipeline.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with remotely coordinated collectors for oil pipelines is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with self-organizing storage for multi-sensor data collectors on oil pipelines is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with self-organizing network coding for a multi-sensor data network of an oil pipeline is disclosed.

In an embodiment, a system for collecting data using a computer vision system in an industrial environment is disclosed having a wearable tactile user interface for an industrial sensor data collector with vibration, heat, electrical, and/or acoustic outputs from an oil pipeline.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with a heat map displaying collected data for AR/VR of an oil pipeline is disclosed.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with automatically coordinated AR/VR visualization of data collected by data collectors for an oil pipeline is disclosed.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT platform for oil pipelines.

In an embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment having an IoT data adapter for receiving data input and establishing a connection with one or more available IoT cloud platforms for publishing oil pipeline data.

In one embodiment, a system is disclosed for collecting data using a computer vision system in an industrial environment having a condition detector for detecting conditions associated with connection attempts by an IoT data adapter to one or more IoT cloud platforms for an oil pipeline.

In one embodiment, a system is disclosed that uses a computer vision system to collect data in an industrial environment with an IoT data adapter equipped with an adaptive engine for an oil pipeline.

In an embodiment, a system for data collection using a computer vision system in an industrial environment with the use of machine learning to prepare data packets or streams for an oil pipeline is disclosed.

In an embodiment, a system for data collection using computer vision systems in an industrial environment with a data marketplace that provides a pool of available cloud networking platforms for oil pipelines is disclosed.

In an embodiment, a system for data collection in an industrial environment using a computer vision system is disclosed, including a messaging utility that provides messages to a cloud platform user interface indicating the availability of new data sources, and data source integration and usage instructions for an oil pipeline.

In an embodiment, a system for data communication between nodes capable of maintaining first and second transmission limits based on received arrival rates and delivery success feedback messages using a computer vision system is disclosed, where the system limits the transmission of messages based on transmission limits for an oil pipeline.

In an embodiment, a system for data communication using a computer vision system between nodes is disclosed that has the ability to restrict the transmission of further messages that have not yet been acknowledged as successfully delivered according to a window size for an oil pipeline.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of maintaining an estimate of the rate of loss events and using it to adjust the rate of redundancy messages in an oil pipeline.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes having an estimated rate of loss events, where the error correction code used to determine the selected redundancy message is based on the estimated rate of loss events in an oil pipeline.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of applying forward error correction based on received messages describing channel characteristics for an oil pipeline.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes using a timer for an oil pipeline, with the ability to maintain/set the timer based on the occurrence of a delivery order event and delay the transmission of feedback messages.

In one embodiment, a system is disclosed for an oil pipeline that uses a computer vision system to communicate data between nodes that maintain/set timers based on the occurrence of delivery order events and have the ability to delay modification of congestion window sizes based on the timers.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system, with the nodes maintaining/setting a timer based on the occurrence of a delivery command event, delaying changes to the congestion window size based on the timer, and canceling the changes to the congestion window size upon receiving a feedback message indicating successful delivery of an oil pipeline.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to configure new connections using maintained data characterizing current and previous connections in an oil pipeline.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of configuring new connections using maintained data that characterizes the error rates of current and previous connections in an oil pipeline.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of configuring new connections using maintained data that characterizes timing variations of current and previous connections in an oil pipeline.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of configuring new connections using maintained data characterizing the bandwidth of current and previous connections in an oil pipeline.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that have the ability to configure new connections using maintained data characterizing the round-trip times of current and previous connections in an oil pipeline.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of configuring new connections using maintained data characterizing communication control parameters of current and previous connections in an oil pipeline.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of configuring new connections using maintained data characterizing forward error correction parameters of current and previous connections in an oil pipeline.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system, the system having a data store for maintaining data characterizing one or more current or previous data communication connections, and a connection initiation module for initiating new data communication connections based on the maintained data for an oil pipeline.

In one embodiment, a system is disclosed for communicating data between nodes for an oil pipeline using a computer vision system, the nodes having the capability to transmit a first subset of data messages over a low-latency data path and a second subset of messages over a high-latency data path.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of transmitting a first subset of time-critical data messages over a low-latency data path and a second subset of messages over a high-latency data path for an oil pipeline.

In one embodiment, a system for communicating data using a computer vision system between nodes capable of transmitting a first initial subset of data messages over a low-latency data path, and a second subset of messages later available over a high-latency data path in an oil pipeline, is disclosed.

In one embodiment, a system is disclosed for communicating data using a computer vision system between nodes capable of transmitting a first subset of acknowledgment messages over a low-latency data path for an oil pipeline and a second subset of data messages over a high-latency data path.

In one embodiment, a system is disclosed for communicating data between nodes for an oil pipeline using a computer vision system, the nodes having the capability to transmit a first subset of supplemental/redundant data messages over a low-latency data path and a second subset of data messages over a high-latency data path.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes with a degree of redundancy associated with each message that is based on the message's position in the transmission order of an oil pipeline.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes with a degree of redundancy associated with each message that increases as the message's location relative to an oil pipeline decreases.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes in response to receiving feedback messages for an oil pipeline, with a degree of redundancy associated with each message based on the message's position in a transmission order.

In an embodiment, a system is disclosed for data communication between nodes using a computer vision system to add or remove redundancy messages from a queue based on feedback messages for an oil pipeline in response to receiving the feedback messages, with a degree of redundancy associated with each message being based on the message's position in a transmission order.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that has the ability to adjust the number of messages sent over each of multiple different data paths with different communication protocols when it is determined that the data paths are altering the flow of messages in an oil pipeline.

In an embodiment, a system for data communication between nodes is disclosed that has the ability to adjust the number of messages sent over each of multiple different data paths having different communication protocols when a computer vision system is used to determine that the data paths are changing the initial division of the message flow based on previous communication connections for an oil pipeline.

In an embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes that has the ability to modify/add/delete redundancy information associated with the encoded data as it travels from node to node over a channel based on channel characteristics for an oil pipeline.

In one embodiment, a system is disclosed that uses a computer vision system to communicate data between nodes capable of transmitting FEC packets at an estimated rate of loss events (isolated packet losses or bursts of consecutive packets) in an oil pipeline.

In an embodiment, a system for data communication using a computer vision system between nodes with combined coding, TCP, and pacing of packet transmissions for an oil pipeline is disclosed.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system with a forward error correcting code structure that interleaves groups of message packets with parity packets and performs coding across overlapping groups of message packets for an oil pipeline.

In one embodiment, a system is disclosed for communicating data between nodes using a computer vision system with a variation of TCP that combines a stable window increasing function and delay-based backoff for oil pipelines.

In an embodiment, the flow of information among participants and elements of a predictive maintenance knowledge platform may be configured as depicted in FIG. 177. Platform 28600, as illustratively configured in FIG. 177, may include multiple subsystems, including one or more of data storage, machine intelligence, and industrial machinery-related transactions. Such subsystems may be web server-based systems, distributed systems, handheld devices, co-located industrial machinery systems, etc. In one example, industrial machinery maintenance data analysis subsystem 28602 may include data storage 28604, machine learning and/or artificial intelligence facilities 28606, transaction facilities 28608, etc. Industrial machinery maintenance data analysis subsystem 28602 may provide services 28610, including service standards, failure prevention, service pricing, parts pricing, tests and standards for detecting potential machine failures, updates of industrial machinery-related data such as repair analysis, failure prediction metadata functions and updates, etc. The industrial machinery maintenance data analysis subsystem 28602 may provide information, such as that related to the provided services 28610, in the form of streams, transactions, database reads/writes, etc., for access to cloud-based data storage. The industrial machinery maintenance data analysis subsystem 28602 may receive information about individual industrial machines from the machines via a data collection network 28612. In embodiments, the data collection network 28612 may be described herein and in the documents referenced and incorporated herein. The industrial machinery maintenance data analysis subsystem 28602 may receive information from particular industrial machines, such as machine parameters, which may be obtained from one or more smart RFID elements 28614 of the industrial machines. In embodiments, the smart RFID elements may be configured as part of the industrial machines and may have functionality as described elsewhere herein.

In embodiments, the industrial machinery predictive maintenance subsystem 28616 may apply machine fault detection, identification, classification, and related algorithms to data provided by the industrial machinery maintenance data analysis subsystem 28602, and further data provided by the industrial machinery health monitoring facility 28618, etc., to generate data structures, streams, and other electronic data that can be communicated to facilitate predictive maintenance of the industrial machinery. In embodiments, the industrial machinery predictive maintenance subsystem 28616 may receive and analyze streams of industrial machinery health monitoring data, etc., from the industrial machinery health monitoring facility 28618. One or more results of such stream analysis may include determining conditions indicative of a healthy machine, an unhealthy machine, the likelihood that at least a portion of the machine may require service to avoid a failure, a specific machine requiring service, etc. Conditions that may indicate a healthy machine may be the result of tests, etc., performed on or by the industrial machine and communicated to the machine health monitoring facility 28618. In one example, the machine health monitoring facility 28618 may receive operation-related information, such as sensor data (e.g., torque, revolutions per minute, runtime, start/stop data, direction data, etc.) from motors of the industrial machines, in a live or delayed stream from one or more industrial machines. This operation-related data is processed by the health monitoring facility 28618 to, for example, determine the number of revolutions over a set period of time, such as a day, a week, or a month, exceeding a maintenance threshold. A portion of the stream data and/or results of processing by the health monitoring facility 28618 may be provided as a stream or the like to the industrial machinery predictive maintenance subsystem 28616 for uses as described, including identifying potential defects or the like that should be addressed with predictive maintenance or the like. The industrial machinery predictive maintenance subsystem 28616 may generate a predictive maintenance set of one or more data 28620 that may identify one or more industrial machines and that may indicate portions of the machines that are determined to benefit from service, maintenance, repair, replacement, etc. The set of data 28620 may include specific parts, service procedures, materials, and service windows required to perform predictive maintenance activities on one or more specific industrial machines. In an embodiment, machine failure analysis, which may be performed by the industrial machinery predictive maintenance subsystem 28616, may facilitate the generation of work orders from the CMMS subsystem 28622.

In an embodiment, the CMMS subsystem 28622 may receive details of the industrial machine, details of the service (e.g., repair, maintenance, upgrade, etc.) for the industrial machine, procedures to be followed, parts required, etc. from sources such as the industrial machine predictive maintenance subsystem 28616, the CMMS interface 28624, a data structure configured and maintained to include, for example, a parts list for the industrial machine, and any other information to facilitate the performance of the service for the industrial machine. The CMMS subsystem 28622 may initiate actions with parts suppliers, service providers, third-party partners, vendors, the owner/operator of the industrial machine receiving the service, etc. In one example, the CMMS subsystem 28622 may generate a service order from one or more service providers known to the CMMS subsystem 28622 as qualified to provide the required service.

In embodiments, the CMMS subsystem 28622 may interface with one or more predictive maintenance knowledge bases and/or knowledge graphs, which may be stored in a data store accessible by the CMMS subsystem. In embodiments, such CMMS knowledge bases, etc. may further include a knowledge graph that may contain information useful to the service decision and order generation services provided by the CMMS subsystem 28622. The CMMS knowledge graph may include or provide computer access to information regarding the industrial machine, service activities for the industrial machine, costs (e.g., history, trends, and forecasts) for industrial machine parts, materials, tools, and services, algorithms and functionality for providing the CMMS services 28626, etc. The CMMS subsystem 28622 may facilitate coordination with service providers, parts providers, material and tool providers, etc., based on the industrial machine owner's decisions regarding the service of the industrial machine so that the service can be performed in a timeframe selected by the owner.

The CMMS subsystem 28622 may access the information in the smart RFID element(s) 28614 via the CMMS interface 28624 to facilitate access to individual industrial machines, etc. The CMMS subsystem 28622 may use the information received via the CMMS interface 28624 to facilitate coordination of resources to effectively and efficiently perform maintenance on a particular machine. In one example, a particular industrial machine may have an operating cycle that results in higher than typical utilization of one of its moving parts (e.g., an industrial motor). This information may be processed by the predictive maintenance subsystem 28616 and result in an indication of service that may need to be performed on the machine. The predictive maintenance subsystem 28616 may provide information to the CMMS subsystem 28622, which the CMMS subsystem 28622 will process to generate orders for parts, service, etc. This knowledge may be used by the CMMS subsystem 28622 to interact with service, parts, and material suppliers to provide firm quotes for performing utilization-based maintenance services at different times (e.g., weeks or months earlier) than other comparable industrial machines with lower utilization.

In an embodiment, the CMMS subsystem 28622 may execute algorithms to collect information about different types of machines (e.g., stationary machines, mobile machines, vehicle-mounted machines, machines deployed at job sites, etc.) along with other information to facilitate the provision of service 28626, including service provider information, parts and parts provider information, part location and inventory information, machine production providers, third-party parts handlers, logistics providers, transportation providers, service activities including service criteria, service requirements, service results, etc., and coordinating orders for service, parts, etc.

In an embodiment, in response to industrial machine fault identification information provided by the preventive maintenance subsystem 28616, the predictive maintenance knowledge system 30002 may identify candidate service providers. Service providers are known to the CMMS subsystem 28622 as having been successfully validated. Experienced personnel for the procedures required for the requested service may be contacted to provide service quotes and/or price estimates for services, parts, etc. Similarly, parts and/or materials potentially related to the requested service procedures may be identified. Factors such as part cost, transportation cost, availability, location of the parts relative to the machine, and prior relationships between one or more part providers and parties associated with the service request, such as the industrial machine owner, may be evaluated to determine which part providers to contact in preparation for ordering the parts. Taking these factors into consideration, part queries may be made to one or more part providers in anticipation of a service accompanied by one or more service recommendations being performed in response to a qualified service indication from the preventive maintenance subsystem 28616. In an embodiment, the CMMS subsystem 28622 may have sufficient information to automatically select a specific service recommendation and, with or without explicit approval, may generate a service order 28626, including an order for parts/materials/tools, if required for the requested service.

In embodiments, information that CMMS subsystem 28622 can rely on may be obtained from an Enterprise Resource Planning (ERP) interface associated with the industrial machine, as well as from third-party sources, such as independent parts suppliers, service providers, etc., that may provide parts and/or services for the industrial machine. In embodiments, CMMS subsystem 28622 may interface with the industrial machine owner's ERP system, such as via ERP interface 28628, to enable ordering to service providers, parts providers, etc. CMMS subsystem 28622 may use service material provider information to determine pricing and availability of service materials. This information may be combined with service material inventory information to facilitate generating appropriate orders for service materials as part of industrial machine service provision 28626.

In an embodiment, the CMMS subsystem 28622 may receive the recommended repair along with the time frame within which the repair must be completed to avoid a failure and instructions from the manufacturer's manual on how to perform the repair. This repair information may then be processed by the CMMS subsystem 28622 (e.g., a cloud-based system), where a work order is created and tracked. The work order may be digitally pushed to an ERP system, which may check the factory production schedule to find when a particular machine needing maintenance will be available for repair based on the time frame provided by the analysis and information in the manufacturer's manual, for example, referenced in a service procedure that describes how long the repair will take. Once the ERP system finds available dates, it can interface with the CMMS subsystem 28622 to solicit bids from vendors for parts and service work or place orders with parts and service contractors, such as preferred contractors. In embodiments, the CMMS subsystem 28622 or ERP system may construct a bid request simply using the manufacturer's procedure manual to provide bidders with the necessary part information (e.g., part number, vintage, revision, specifications, aftermarket alternatives, last price paid, whether a used part is OK, etc.) and the repair actions required for the service action (e.g., procedure steps, diagnostics, required equipment/tools, required materials, required personnel, etc.). Bids are based on the repair actions described in the procedure manual, which may be the scope of work being bid on. In embodiments, if there are other issues discovered and addressed outside of this scope, a secondary process may be undertaken to approve additional compensation to the vendor.

In embodiments, the service delivery and tracking subsystem 28630 may be used by service providers, such as service technicians, industrial machine owners/operators, and third parties (e.g., auditors, regulators, union members, safety associations, parts manufacturers, etc.), to collect and report information related to ordered service requests, which may be determined from the service order data 28626. The service delivery and tracking subsystem 28630 may include functionality to match machine procedures to service requests and ensure that images related to the ordered service (e.g., parts to be serviced, machine installation, video of the machine operating before and/or after service, parts removed from the industrial machine, service personnel, etc.) are captured with sufficient quality to meet image quality standards for automatic detection of one or more parts of the industrial machine.

In an embodiment, the service delivery and tracking subsystem 28630 may compile data, repairs, images, etc. and report them as service data 28632 to the industrial machinery maintenance data analysis subsystem 28602 for improving service procedures, ordering parts, etc.

In an embodiment, compensation for the work and analysis performed by the various subsystems may come from a variety of sources. The operator/owner/affiliate of the CMMS subsystem 28622 may be compensated on a transactional basis, such as by receiving a commission for each part or service ordered. Such a commission may include a fixed portion (e.g., an amount per part ordered) or a variable portion (e.g., a percentage of the order total). This commission may be explicitly included in the fee charged to the party responsible for paying for the parts or services to perform the maintenance action. This commission may be incorporated into the cost of each part or service and recovered as a deduction from the payment passed on from the responsible party to the parts or service provider.

In an embodiment, the industrial machinery predictive maintenance system may include an industrial machinery data analysis facility that generates a stream of industrial machinery health monitoring data by applying machine learning to data representative of the condition of a portion of the industrial machinery received via a data collection network. The system may further include an industrial machinery predictive maintenance facility that generates industrial machinery service recommendations in response to the health monitoring data by applying machine fault detection and classification algorithms. The system may further include a computerized maintenance management system (CMMS) that generates at least one of service and parts orders and requests in response to receiving the industrial machinery service recommendations. And, the system may include a service and delivery coordination facility that receives and processes information regarding services performed on the industrial machinery in response to at least one of the service and parts orders and requests, thereby verifying the services performed and creating a ledger of service activities and results for each industrial machine.

In embodiments, methods and systems for finding a set of workers with relevant know-how and expertise regarding the maintenance, service, and repair of specific machines may employ machine learning algorithms with worker selection algorithms to ensure timely and high-quality workers are selected and deployed for industrial machine service, such as predictive maintenance, as described herein. Referring to FIG. 178, a machine learning-based method 32400 for finding a set of workers as described above is depicted. In embodiments, a facility 32402 for finding workers may be configured as a system that may include a set of algorithms and data structures that may be executed on a processor. The facility 32402 for finding workers may process data regarding workers, machines, procedures, etc. with algorithms that facilitate matching qualified workers with service activities, such as predictive maintenance activities. In one example of finding workers, the service activity may include following a service or maintenance procedure 32406, such as repairing and/or maintaining a portion of the industrial machine. The procedure 32406 may further indicate one or more industrial machines by model number, family, etc. The worker discovery facility 32402 may further access information that facilitates characterization of one or more workers, including procedures for which the worker has experience, training, certifications, etc., such as by retrieving information about the worker from a worker database 32422. One or more workers with experience in procedures, etc., may be selected for further refinement, including matching the worker's location to the machine's location, the worker's availability and/or schedule to the machine's service schedule, the worker's rates/fees to the machine owner's service budget, etc. One or more workers on the refined list of workers may be contacted about a service to be performed on the machine. For example, based on such worker's response to the contact, a first worker may be selected by the worker discovery facility 32402 and assigned to perform the service via procedure 32406.

In an embodiment, the worker discovery facility 32402 may access a list of procedures 3246 for which services may be requested. The worker discovery facility 32402 may build a dataset of workers qualified to perform the procedure, such as by searching worker information 32416 for workers who meet procedure criteria, such as the number of times the worker has performed the procedure, the number of times the worker has performed similar procedures, etc. Workers with more experience may be marked as preferred workers in such a database for a particular procedure so that when a procedure is requested to be performed, those preferred workers may be easily identified. In an embodiment, workers may directly maintain the worker database 32422 by updating information about the procedures they perform, etc.

In an embodiment, the worker discovery facility 32402 may receive information, such as procedure 32406, machine 32408, machine location 32410, machine owner and/or affiliation 32412, and required service schedule 32414, for one or more service activities, such as predictive maintenance activities, to be performed, and form a profile of preferred workers for a given combination of procedure, machine, location, owner, schedule, etc. The worker discovery facility 32402 may build profiles for various combinations of such information so that workers who best meet the profile can be easily found. In an embodiment, such preferred worker profiles may be made public so that third parties, such as service organizations, can provide quotes, etc. for providing services based on the profile. These quotes may be captured and used by methods and systems for predictive maintenance of industrial machinery, etc., to create a marketplace of service providers for common or frequently required services, such as preventive maintenance services.

In embodiments, information captured in the worker database 32422, etc., may be processed by machine learning algorithms 32424 to facilitate improved matching of workers with requirements to provide qualified workers for processes, etc. In embodiments, information received in response to preferred worker profiles and their publication may be processed by machine learning algorithms 32424 to improve the algorithms used to construct preferred worker profiles.

In embodiments, additional information that may influence the selection of workers by the labor discovery facility 32402 may include the worker's affiliation with service organizations, industrial machinery manufacturers, trade associations, etc. Referrals and/or feedback regarding particular workers may be factored into determining the desired worker status of an individual worker, a group of workers, etc. The worker's rates and/or fees (e.g., based on quotes, actual rates, payment terms, etc.) may also be considered in finding workers; for example, if two or more workers have similar overall qualifications, a worker with lower cost or easier payment terms may be ranked higher for a given procedure than a worker with higher cost, etc.

In embodiments, the techniques for finding workers may be performed in real time or near real time, depending on the demand for industrial machinery. In this manner, as new workers become available, the techniques for finding workers may incorporate updates, such as worker profiles accessible via the internet, such as on a website.

In an embodiment, the system may include an industrial machinery predictive maintenance facility that generates industrial machinery service recommendations by applying machine fault detection and classification algorithms to industrial machinery health monitoring data. Such a system may also include a worker discovery facility that identifies at least one candidate worker for performing the service indicated by the industrial machinery service recommendation by correlating information in the recommendation regarding at least one service to be performed with at least one of the experience and know-how of industrial service workers in an industrial service worker database. In an embodiment, the system may include a machine learning algorithm running on the processor that improves the correlation based on service-related information regarding multiple services performed on similar industrial machines and worker-related information regarding multiple services performed by at least one candidate worker.

In an embodiment, an industrial machinery maintenance parts/service ordering facility 32502 for industrial machinery service and maintenance 32500, including predictive maintenance, etc., may be embodied at least as depicted in FIG. 179 filed herein. The industrial machinery maintenance parts/service ordering facility 32502 may facilitate the search, ordering, and order fulfillment of relevant parts and components so that industrial machinery maintenance, service, and repair work occurs seamlessly with minimal interruption. In an embodiment, the industrial machinery maintenance parts/service ordering facility 32502 may receive industrial machine details 32508, industrial machine service (e.g., repair, maintenance, upgrade, etc.) details 32510, procedures to be followed 32506, required parts 32514, service providers 32520, parts providers 32522, etc. The industrial machinery maintenance parts/service ordering facility 32502 may initiate actions with parts suppliers, service providers, third-party partners, vendors, the owner/operator of the industrial machinery being serviced, etc. In one example, the industrial machinery maintenance parts/service ordering facility 32502 may generate service orders 32518 from one or more service providers 32520 known to the industrial machinery maintenance parts/service ordering facility 32502 as qualified to provide the required service. The industrial machinery maintenance parts/service ordering facility 32502 may also generate part orders 32516 from one or more part providers 32522 known to be qualified to provide the required parts on time, on budget, etc. The part orders 32516 and service orders 32518 may also be communicated to the owner 32512 or other entity responsible for ensuring access to the industrial machine. The selected parts and service providers may further coordinate with the owner 32512 to ensure the service is properly delivered. The industrial machinery maintenance parts/service ordering facility 32502 may access the preferences and/or requirements of the machine owner 32512 regarding schedule, budget, service and parts provider preferences and/or affiliations, etc., and facilitate coordination therewith with service providers, parts providers, material and tool providers, etc.

Factors such as part cost, transportation cost, availability, location of the part relative to the machine, and prior relationships between one or more part providers and parties associated with the service request, such as the industrial machine owner, may be evaluated to determine which part provider 32522 to contact.
and preparing to order the part 32516. Taking these factors into consideration, a parts query may be made to one or more part providers 32522 in the hopes that the service will be performed by a qualified service provider. In an embodiment, the industrial machinery maintenance parts/service ordering facility 32502 may have sufficient information to automatically select a particular service provider 32520 and may generate a service order 32518, with or without explicit approval.

In embodiments, the industrial machinery maintenance parts/service ordering facility 32502 may rely on information regarding vendors, etc. from an Enterprise Resource Planning (ERP) system owned and operated by the industrial machinery owner. In embodiments, the industrial machinery maintenance parts/service ordering facility 32502 may interface with the industrial machinery owner's ERP system to enable ordering from service providers, parts providers, etc.

In an embodiment, the system may include an industrial machinery maintenance parts and service ordering facility that prepares and controls parts and service orders in response to service recommendations received from an industrial machinery predictive maintenance facility that generates service recommendations for the industrial machinery by applying machine fault detection and classification algorithms to industrial machinery health monitoring data. In an embodiment, the system may further analyze procedures associated with the service recommendations to generate at least one of the parts and service orders.

In embodiments, an industrial machinery predictive maintenance system may include deploying smart RFID devices on portions of industrial machinery. The smart RFID devices may be configured to contain information about the machinery, such as configuration information, assembly information, physical element details (e.g., part numbers, revisions, production details, test details, etc.), procedural information (e.g., assembly, disassembly, test, configuration, service, part replacement, etc.), and other operational information. Smart RFID devices may be located with each key element of the machinery, such as each element that may contain information relevant to the efficient service and maintenance of the machinery. In embodiments, smart RFID devices may be located to capture specific part production information for the production of parts and subsystems of industrial machinery, etc. Smart RFID elements may not only provide storage for a variety of information, including extensive service manuals, but may also include search, indexing, linking, and other features that make it easy for users to quickly find procedures, such as lubrication procedures, bearing replacement procedures, and bearing failure frequencies, that are important for troubleshooting machinery, etc. In embodiments, at least one method for accessing information is compatible with existing technology used by specialized service personnel and may be taught to new service personnel while these experts remain on the job. In embodiments, providing easy access, including indexing, linking, etc., may be incorporated into the creation of documents, procedures, data sheets, manuals, etc., so that a common access approach can be used for any embodiment of information (e.g., in smart RFID, in RFID cloud representations, in third-party service manuals, in industrial machinery manufacturer systems, etc.).

Referring to FIG. 180, industrial machinery 32600 may be comprised of multiple elements, parts, subassemblies, etc. One such subassembly may include a motor 32602 of the industrial machinery. For a particular motor, an RFID device including details as described herein for smart RFID devices may be located with the machinery. The RFID device of the motor 32602 may communicate, such as via wireless communication, with another nearby device, such as a smartphone, tablet, etc. 32614, such that a user of the table, etc. 32614, can access information stored on the RFID device of the motor 32602 to perform service, maintenance, testing, etc. In an embodiment, service procedures for the motor 32602 may be retrieved from the RFID of the motor 32602 and displayed via an application running on the table 32614 for a service technician to follow. Another such subassembly may include a drive shaft 32604 of the industrial machinery. For a particular drive shaft 32604, an RFID device including details as described herein for smart RFID devices may be located with the machinery. The RFID device of the drive shaft 32604 may communicate, such as by wireless communication, with other nearby devices, such as a smartphone, tablet, etc. 32614, so that a user of the table, etc. 32614 can access information stored on the RFID device of the drive shaft 32604 to perform service, maintenance, testing, etc. In an embodiment, a service procedure for the drive shaft 32604 may be obtained from the RFID on the drive shaft 32604 and displayed via an application running on the table 32614 for a service technician to follow. Yet another such subassembly may include a gearbox 32606 of an industrial machine. For a particular gearbox 32606, an RFID device containing details such as those described herein for smart RFID devices may be located with the machine. The RFID device of the gearbox 32606 device may communicate, such as by wireless communication, with other nearby devices, such as a smartphone, tablet, etc. 32614, so that a user of the table, etc. 32614 can access information stored on the RFID device of the gearbox 32606 to perform service, maintenance, testing, etc. In an embodiment, a service procedure for the gearbox 32606 may be retrieved from the RFID on the gearbox 32606 and displayed via an application running on the table 32614 for a service technician to follow. Yet another such subassembly may include an articulated arm 32608 of industrial machinery. For a particular articulated arm 32608, an RFID device containing details such as those described herein for smart RFID devices may be located with the machine. The RFID device on the articulated arm 32608 may communicate, such as via wireless communication, with another device located nearby, such as a smartphone, tablet, etc. 32614, such that a user of the table, etc. 32614 can access information stored on the RFID device on the articulated arm 32608 to perform service, maintenance, testing, etc. In an embodiment, a service procedure for the articulated arm 32608 may be retrieved from the RFID on the articulated arm 32608 and displayed via an application running on the table 32614 for a service technician to follow.

With further reference to FIG. 180, yet another such subassembly may include a bucket 32610 of industrial machinery. An RFID device may be disposed with the machine, including details as described herein for a smart RFID device, for the particular bucket 32610. The RFID device of the bucket 32610 may communicate, such as via wireless communication, with another device disposed nearby, such as a smartphone, tablet, etc. 32614, such that a user of the table, etc. 32614, can access information stored in the RFID device of the bucket 32610 for service, maintenance, testing, etc. In an embodiment, another such subassembly may include a drivetrain 32612 of industrial machinery. An RFID device may be disposed with the machine, including details as described herein for a smart RFID device, for the particular drivetrain 32612. The RFID device of the drivetrain 32612 may communicate, such as by wireless communication, with other devices located nearby, such as a smartphone, tablet, etc. 32614, so that a user of the table, etc. 32614 can access information stored on the RFID device of the drivetrain 32612 to perform service, maintenance, testing, etc. In embodiments, service procedures for the drivetrain 32612 may be retrieved from the RFID on the drivetrain 32612 and displayed via an application running on the table 32614 for a service technician to follow. In embodiments, any of the RFID devices, such as the motor 32602 RFID, driveshaft 32604 RFID, gearbox 32606 RFID, articulated arm 32608 RFID, bucket 32610 RFID, drivetrain 32612 RFID, etc., may communicate via a wireless communication network with an access point, such as industrial machine access point 32616, which may be located on or near the industrial machine 32600. The RFID device may communicate through the industrial machine access point 32616 to gain access to a network 32618, such as a network for connecting other industrial machines within a facility or an external network such as the Internet. Information stored on the RFID device of the industrial machine may be transmitted via the network 32618 for use in the predictive maintenance methods and systems described herein.

In an embodiment, the system may include a smart RFID element configured to capture and store in non-volatile computer-accessible memory operational, physical, and diagnostic information for the piece of industrial machinery by communicatively coupling with at least one sensor configured to monitor the condition of the piece of industrial machinery. The smart RFID element may be further configured to receive, organize, and store in non-volatile memory information that enables execution of at least one service procedure for the industrial machinery.

In embodiments, information relating to a piece of industrial machinery or the like may be stored in an RFID element disposed on or within that piece of industrial machinery. The stored information may be configured to facilitate quick and efficient random access to any portion of the information, such as using a smartphone or other computing device configured with at least a web browser. The information may also be organized as one or more data structures, such as a hierarchical data structure, which may facilitate searching for the information, such as by browsing the hierarchy. Referring to FIG. 181, an exemplary high-level structure 32700 of a portion of such an RFID is presented and includes rows and columns. The exemplary high-level structure 32700 may include categories of information 32702 that may identify a general area of information, such as production. Each such category may be listed in a description field 32704 that may have further identifying information. A notes field 32706 may consist of free-form notes that may be updated as needed. In embodiments, categories 32702 may include various categories of information related to the industrial machinery, such as production, parts, quality, installation, validation, procedures, operations, assembly, etc. In the example of category 32702, verification 32708 may include a list of validation tests required and performed, along with the results. Validation tests may be performed, such as to verify installation at a customer site. Verification 32708 may also include a link to one or more RFID-accessible procedures required for validation through the procedures 32710 category.

In embodiments, industrial machine-related information stored in and/or accessible via smart RFID elements may include, but is not limited to, operational data collected by sensors deployed on the industrial machine and via the sensor data collection methods and systems described in the incorporated documents. Other information stored in or accessible from smart RFID elements may include, but is not limited to, exceptions detected in operational and/or test data, such as over-temperature, unexpected shutdowns, and system reboots. Smart RFID elements may communicate with external computing devices, such as smartphones, tablets, communication infrastructure nodes, computers, and mesh network devices, via various communication protocols, such as Wi-Fi, NFC, and Bluetooth. In embodiments, smart RFID elements may wirelessly communicate with portable computing devices when the computing devices are in wireless proximity, such as when the portable computing device is brought within NFC range of the smart RFID element. As IoT devices, smart RFID elements may communicate over a network, such as the Internet. The smart RFID elements may transmit data to a server, such as a web server, that can aggregate information from the elements and cloud-accessible sources for one or more service activities related to the industrial machinery. In embodiments, the smart RFID elements may communicate with external computing device(s) at convenient times, such as the end/start of an activity, a shift, a day, when preventive maintenance is about to be performed, etc.

For example, bearing frequency, gear tooth count and type, manufacturing/assembly version information, manufacturing/test parameters, self-test information, calibration information, test time, inventory hold time, etc.

Smart RFID elements may be used during installation and/or deployment of industrial machinery or portions thereof to capture machine orientation, test activities, startup activities, verification activities/executions, production start times, installation/deployment/configuration personnel, images of the industrial machinery, and the like, at least some of which may be determined by one or more installation and/or deployment procedures stored on or accessible through the smart RFID elements.

In an embodiment, the system may include a smart RFID element configured to capture and store in non-volatile computer-accessible memory operational, physical, and diagnostic information for a portion of the industrial machine by communicatively coupling with at least one sensor configured to monitor the condition of the portion of the industrial machine. The smart RFID element may be further configured to receive, organize, and store in non-volatile memory information enabling the performance of at least one service procedure for the industrial machine. The smart RFID element may further be configured to facilitate hierarchical access to information related to the industrial machine, including multiple portions directly accessible from a route entry for the industrial machine. In an embodiment, each of the multiple directly accessible portions is configured to store an entry for one portion selected from a list consisting of production information, parts information, quality information, installation information, verification information, procedure information, operational information, and assembly information.

In an embodiment, an alternative configuration of a smart RFID for storing and accessing industrial machinery information for servicing, etc., may include a data structure such as that depicted in FIG. 182. Data structure 32800 may be organized as shown, such as into columns and rows. The first column may be a topic column 32802, such as, but not limited to, a production topic including assembly date(s), location, model number, serial number, time, work order number, customer, an image of the industrial machinery as built, etc. Each topic in topic column 32802 may have one or more corresponding values in value column 32804. In one example, serial number topic 32808 in topic column 32802 may have one or more corresponding serial numbers for the particular industrial machinery listed in value column 32804. Comments or other metadata for each topic in topic column 32802 may be captured in a corresponding entry in notes column 32810.

In an embodiment, the system may include a smart RFID element configured to capture and store operational, physical, and diagnostic information for the piece of industrial machinery in non-volatile computer-accessible memory by communicatively coupling with at least one sensor configured to monitor the condition of the piece of industrial machinery. The smart RFID element may be further configured to receive, organize, and store in non-volatile memory information that enables execution of at least one service procedure for the industrial machinery. In an embodiment, the production piece may include entries for assembly date, assembly location, machine model number, machine serial number, machine assembly time, machine assembly work order number, customer, and an image of the piece of industrial machinery.

In an embodiment, an alternative smart RFID configuration for storing and accessing industrial machine information for servicing or the like may include a procedure data structure such as that depicted in FIG. 183. The machine-level procedure data structure 32900 may be organized as columns and rows, as shown. The first column may be a procedure column 32902 that lists machine-level procedures such as calibration, shutdown, regulatory compliance, assembly, safety check, image capture, etc. Each procedure in the machine-level procedure column 32902 may have one or more corresponding values in the attribute column 32904, such as a procedure identification number, version, etc. In one example, the safety check procedure 32908 entry in the procedure column 32902 may have one or more corresponding procedure number(s) and corresponding version number(s) in column 32904. Comments and other metadata for each procedure in the procedure column 32902 may be captured in a corresponding entry in the notes column 32910.

In an embodiment, the system may include a smart RFID element configured to capture and store operational, physical, and diagnostic information of the portion of industrial machinery in non-volatile computer-accessible memory by communicatively coupling with at least one sensor configured to monitor the condition of the portion of industrial machinery. The smart RFID element may be further configured to receive, organize, and store in non-volatile memory information enabling execution of at least one service procedure for the industrial machinery. In an embodiment, the procedure portion may include an entry for a procedure selected from the list consisting of calibration, shutdown, regulation, assembly, safety check, image capture, preventative maintenance, part repair, part replacement, and disassembly.

In an embodiment, referring to FIG. 184, methods and systems for collecting information 33000 about industrial machinery 33020, such as information about the machine's operation, condition, etc., may be useful for industrial machinery predictive maintenance methods and systems such as those described herein and elsewhere. In an embodiment, collecting information from sensors on the industrial machinery may include routing the collected information via one or more access points 33008 to a networked server 33018, which can process and store the information. In an embodiment, collecting information from sensors on the industrial machinery may include communicating between the sensors and a smart RFID device 33002 located on or with the machine. Data from sensors such as a temperature sensor 33010, vibration sensor 33012, rotation sensor 33014, and operating cycle sensor (e.g., cycle counter, etc.) 33016 may be provided to the smart RFID device 33002, where the information may be processed and stored for further access by an external device, such as the server 33018, a handling device (not shown) brought within communication proximity of the industrial machinery 33020, etc. Industrial machine-specific data may be collected from sensors and routed to one or more web servers 33018 that employ a processor 33006 to generate a digital twin 33004 of the smart RFID 33002 on computer-accessible memory other than the smart RFID 33002. In an embodiment, the digital twin 33004 may be generated by copying the contents of the smart RFID 33002. Similarly, machine-specific sensed data may be copied from the memory of the RFID twin 33004 to the smart RFID device 33002. Thus, the RFID twin 33004 may be a copy of the smart RFID 33002, may be created independently of the smart RFID 33002 while maintaining a compatible structure, format, and substantially identical content, or may be a source of machine-specific data (e.g., provided by sensors on access points) that may be copied to the smart RFID 33002 to maintain a copy of the information on the machine. In an embodiment, the server 33018 may maintain digital twins of multiple smart RFID devices for multiple industrial machines, including multiple smart RFID devices for a single industrial machine, etc.

In an embodiment, the system may include a smart RFID element configured to capture and store in non-volatile computer-accessible memory operational, physical, and diagnostic information for the piece of industrial machinery by communicatively coupling with at least one sensor configured to monitor the condition of the piece of industrial machinery. The smart RFID element may be further configured to receive, organize, and store in non-volatile memory information that enables execution of at least one service procedure for the industrial machinery. In an embodiment, the system also includes a data storage element accessible via the processor, which may include copies of the information stored in multiple smart RFID elements. In an embodiment, each copy of the information comprises a twin of the information stored in the corresponding smart RFID element.

In embodiments, predictive maintenance methods and systems for industrial machinery as described herein may include the use of one or more machine-resident smart RFID data structures that can capture information related to the planning, engineering, production, assembly, testing, etc., of portions of industrial machinery. An embodiment 33100 that can facilitate capturing information from these processes may be depicted in FIG. 185. The industrial machinery 33122 may include multiple elements, such as operational elements, structural elements, processing elements, and at least one smart RFID element 33102. During production of the industrial machinery 33122, the industrial machine-resident processor 33108 may perform tests of the industrial machinery, such as in cooperation with a self-test element 33124. Data collected during self-tests, such as verifying proper operation, may be stored in the smart RFID element 33102, such as by the processor writing the data to the memory of the smart RFID element 33102. In embodiments, the production test system 33118 may also perform tests of portions of the industrial machinery 33122, the results of which may be stored in the smart RFID element 33102. During production, industrial machines 33122 may communicate with a production network 33120, such as an intranet, to collect and/or provide information for various production systems, such as a quality system 33110, a manufacturing resource planning (MRP) system 33114, a production engineering system 33116, etc. Information such as parts lists, production information, etc. (example data structures of which are depicted in FIG. 182) may be stored with the smart RFID device 33102, such as by industrial machines 33122 communicating over the production network 33120, such as via a production access point 33112. Information from the various production systems, quality 33110, MRP 33114, engineering system 33116, test 33118, etc., may be transferred to the smart RFID device 33102 via the network 33120. In embodiments, the networked server 33126 may communicate with at least some of these production systems over the network 33120 to capture and process relevant production information by the processor 33106, for example, to be stored in a data structure in memory accessible to the smart RFID elements 33102 and/or the server 33126. The data structure 33104 may include at least some of the information stored in the smart RFID elements 33102. In embodiments, the data structure 33104 may be a digital twin of at least the relevant production content of the smart RFID elements 33102 for the particular industrial machine being produced. In embodiments, data from the production systems may flow over the network 33120 to the server 33126, where it may optionally be formatted, encoded, etc., and distributed via a wireless connection to the industrial machine 33122 for storage with the smart RFID 33102, etc. The production systems may include a quality control system 33110, which includes capturing images of parts, subassemblies, and pieces of industrial machinery. The captured images may be processed with machine vision or other image analysis techniques to verify assembly, etc. These images, and the image analysis data derived from these images, etc., may be stored so that they can be accessed via the smart RFID element 33102. In one example, procedures, such as test procedures used in production, may be useful for testing industrial machines 33122 as part of a deployment process. These procedures may be communicated from one of the production systems, such as the engineering system 33116, via the production network 33120, and ultimately stored in the smart RFID 33102, the digital twin 33104, or both. This may fulfill a goal of the methods and systems described herein of facilitating access to industrial machine-specific procedures via the smart RFID element on each industrial machine.

In embodiments, for example, production information stored in the smart RFID element 33102 may be useful for procedures to be followed during installation, calibration, repair, preventative maintenance, and the like. As one example, a particular test result may indicate operating margins (e.g., maximum and/or minimum values) that were verified during production. These results may be useful during validation testing of industrial machinery configurations to help ensure that the configuration continues to meet expectations. By making such information and other production and industrial machinery information available during installation and other deployment procedures, the machine-resident smart RFID element 33102 may reduce interdependencies between production and related systems after the industrial machinery leaves the production environment. In one example, a procedure for testing a piece of industrial machinery may be stored in the smart RFID element. The test results corresponding to that procedure may also be saved. Thus, even if the specific procedure is changed for a subsequently produced industrial machine, it is still possible to perform tests related to the specific procedure used to produce the particular industrial machine, thereby saving time and confusion that can occur when new test procedures are used but the test results of the old procedure are expected to be met.

In an embodiment, a method for configuring production data on a smart RFID tag of an industrial machine may include configuring a smart RFID tag on a corresponding piece of industrial machine to capture and store operational, physical, and diagnostic information of the corresponding piece of industrial machine in a non-volatile, computer-accessible memory. The method may include communicatively coupling the smart RFID tag to a processor of the industrial machine and at least one sensor configured to monitor a condition of the portion of industrial machine. The method may further include running a self-test on the portion of industrial machine with the processor and storing results of the self-test on the smart RFID tag. The method may further include coupling the industrial machine to a test system network and an industrial machine production server via a production access point. The method may further include performing a production test on the portion of industrial machine using the test system, the results of which are duplicated and stored on the smart RFID tag and in a data storage device accessible by the processor of the production server. In an embodiment, the duplicate test results stored in the data storage facility may be a twin of the corresponding piece of smart RFID tag.

In an embodiment, a marketplace for industrial machinery parts, services, tools, materials, etc. may be maintained through a CMMS control system in combination with information regarding services, parts, tools, materials, costs, and logistics provided by third parties. Such a marketplace may be cloud-based, allowing participants, such as industrial machinery owners, to access this information. In an embodiment, a representative embodiment is depicted in FIG. 186. A CMMS system 33202 for managing at least parts and service orders for needed services may serve as a control gateway to the marketplace 33212 for industrial machinery owners 33224 and the like. The CMMS system 33202 may also include managing bidding and ordering for parts, services, tools, materials, and other aspects of industrial machinery service and maintenance. Exemplary CMMS subsystems, systems, equipment, etc. are described elsewhere herein. In the embodiment of FIG. 186, the CMMS system 33202 may further maintain and update order history details 33210. These details may include information describing parts, services, etc. that may be ordered. The details may include historical prices, logistics requirements and costs, order lead times, and other factors useful in managing information in the marketplace 33212. In one example, a parts supplier 33208 may offer a part for sale in the marketplace. The parts' historical prices based on the order details 33210 may be used to recommend a price at which the parts supplier 33208 should offer the part. In another example, the parts supplier 33208 may offer the availability of the part with a two-day lead time. However, the history details 33210 may indicate that this supplier 33208 has underestimated the time required to provide the part, facilitating the incorporation of an appropriate lead time into the order so that the part can be ordered only when needed, but with sufficient lead time when a service requiring the part is scheduled to be performed. Such information management may be considered implicit management because it is based on actual performance, not merely on the provider's statements.

In embodiments, a service provider 33206 may configure a set of services 33216 offerings that meet its technical expertise. The service provider 33206 may configure this set of services directly and update it over time to reflect the services available from each individual service provider 33206. Similarly, a parts supplier 33208 may configure and maintain a list of industrial machine parts 33214 that it offers. Information such as availability (e.g., local inventory, lead time, etc.) may be maintained directly by the parts supplier 33208. The CMMS system 33202 may access information associated with the parts supplier 33214 in the marketplace 33212 when configuring orders for parts, services, etc. Similarly, a tool supplier may configure information related to industrial machine service tools 33220, and a material supplier may configure and maintain information related to industrial machine service materials 33222 (e.g., lubricants, other consumables, etc.).

In an embodiment, component manufacturers 33204 may also provide and maintain market information about the components they offer, including replacement parts, add-ons, upgrades, complete systems, subsystems, and accessories.

In an embodiment, a logistics provider 33218, such as a shipper, may offer and maintain a range of logistics services in a marketplace that provides maintenance parts, services, etc. for industrial machinery. The logistics provider 33218 may offer delivery services in different geographic regions and may use information, such as the location of the industrial machinery, to establish rates and services available in the relevant region.

In an embodiment, the industrial machinery predictive maintenance system may form a marketplace including a plurality of part supplier computing systems configured to maintain industrial machinery service marketplace information regarding industrial machinery parts offered for sale. The marketplace may also include a plurality of service provider computing systems configured to maintain industrial machinery service marketplace information regarding offered industrial machinery services. The marketplace may further include at least one computerized maintenance management system (CMMS) configured to facilitate access to at least one of services, parts, materials, and tools offered in the marketplace in response to industrial machinery maintenance recommendations provided by the industrial machinery predictive maintenance system. The marketplace may also include a plurality of logistics provider computing systems configured to maintain industrial machinery service marketplace information for at least one of shipping and logistics services offered in the marketplace. In further embodiments, each of the plurality of part suppliers, service providers, and logistics providers maintains corresponding information for direct offerings in the marketplace via at least one application programming interface of the marketplace. The marketplace may further include a CMMS that tailors parts, services, and logistics offerings to industrial machinery owners based on norms established from analysis of past orders for parts, services, and logistics.

In an embodiment, a distributed ledger for tracking field service activities, including predictive maintenance activities performed on industrial machines, is depicted in FIG. 187. Methods and systems disclosed herein for an industrial machine maintenance distributed ledger may include a distributed ledger 33302 that supports tracking of predictive maintenance activities performed in an automated industrial machine predictive maintenance ecosystem 33300. Embodiments may include a self-organizing data collector 33308 configured to distribute collected information to the distributed ledger 33302. Embodiments may include a network-sensitive data collector configured to distribute collected information to the distributed ledger based on network conditions. Embodiments may include a remotely organized data collector configured to distribute collected information to the distributed ledger based on intelligent remote management of the distribution. Embodiments may include a data collector with self-organizing local storage configured to distribute collected information to the distributed ledger. Embodiments may include a system 33300 for industrial machine maintenance-related data collection in an industrial environment using a distributed ledger for data storage and self-organizing network coding for data transport. In embodiments, the data storage may be in a data structure that supports a haptic interface for data presentation, a heat map interface for data presentation, and/or an interface that operates with self-organized tuning of the interface layer.

In an embodiment, storage of service and maintenance information, which may include records of services, parts, service providers, specific industrial machines, analytics generated from the service and maintenance information, etc., may include one or more distributed ledger 33302 instances across various elements of the system 33300. In one example, the distributed ledger 33302 may facilitate access to all information available in the distributed ledger 33302 without relying on any one network server, node, etc., due at least in part to some of the information being distributed and optionally replicated across different portions of a network, such as the Internet. The distributed ledger 33302 may be distributed among elements of an industrial machinery maintenance platform, including, but not limited to, the industrial machinery data analysis system 28602, the industrial machinery predictive maintenance subsystem 28616, the CMMS system 28622, the service delivery and tracking system 28630, the industrial machines 33304, the industrial facility computing system 33306, cloud-based storage 33316, etc.

In embodiments, information stored in the distributed ledger 33302 may be generated by and/or adjusted based on artificial intelligence 33310, such as machine learning algorithms, that process information sourced from the distributed ledger.

In embodiments, methods and systems that can support distributed ledger embodiments may include role-based access control 33314 to and from distributed ledger data. Exemplary roles 33312 that may be managed by a distributed ledger control facility include an owner role, which may be an entity or individual leasing the industrial machinery, an individual, or a buyer entity or individual that uses it directly; an operator role, which may be an entity or individual responsible for the day-to-day operation of the industrial machinery, such as a company that uses the industrial machinery to provide services or a lessor of the machinery; a lessor role, which may be an entity or individual that has a time-limited or other limited lease on the industrial machinery; a manufacturer role, which is an entity or individual that manufactures parts of the machinery and has limited access to information related to the manufactured parts, etc.; and a parts supplier role, which is an entity or individual that provides parts for functions such as manufacturing, service, upgrades, maintenance, and refurbishment, and provides the industrial machinery with O.I. Entities or individuals who may provide EM and/or aftermarket parts; Service provider role: An individual or entity that provides services such as preventive maintenance, repairs, emergency repairs, and upgrade contracts; For example, regional associations that facilitate automated service activities in certain countries or regions, or organizations or individuals that act as general contractors to provide oversight and assurance of work performed by third parties, which may require licensing or registration in certain countries; Regulatory role: Government and other authority agencies or individuals may have limited access to certain data necessary to ensure compliance with regulations, for activities such as preventive maintenance, use of authorized parts and service providers, and audits.

In embodiments, the predictive maintenance platform may use a secure architecture for tracking and resolving transactions, such as a distributed ledger. In embodiments, transactions within data packages are tracked in a chained, distributed data structure, such as Blockchain®, enabling forensic analysis and verification, with individual devices storing portions of the ledger representing the transactions within the data packages. The distributed ledger may be distributed across IoT devices, web servers, industrial machinery maintenance transaction archiving facilities, etc., allowing maintenance and related information to be verified without relying on a single, central repository of information. The platform may be configured to store data on the distributed ledger and retrieve data from the distributed ledger (and from constituent devices) to resolve service transactions, such as parts and service orders. In this manner, a distributed ledger for handling data for maintenance-related transactions is provided. In embodiments, a self-organizing storage system may be used to optimize the storage of distributed ledger data and to organize the storage of packages of data, such as IoT data, industrial machinery maintenance data, parts and service data, and knowledgeable worker data.

In an embodiment, a system may include a plurality of computing systems configured to perform one or more predictive maintenance actions. In an embodiment, the system includes a portion of the plurality of computing systems connected via a peer-to-peer communications network. A record of industrial machine maintenance actions, including a portion of the predictive maintenance actions, may be maintained as a distributed ledger by a portion of the plurality of computing systems. In an embodiment, the computing systems are:
A portion of the computing system performs at least one industrial machine maintenance role selected from the list consisting of industrial machine data analysis, industrial machine predictive maintenance recommendations, industrial machine maintenance order management, service action delivery and tracking, and industrial machine service scheduling, and posts results of performing the at least one industrial machine maintenance to the record.

In an embodiment, the system may include a plurality of computing systems configured to perform one or more predictive maintenance actions. In an embodiment, some of the plurality of computing systems are connected via a peer-to-peer communications network. In an embodiment, the system further includes a role-based control facility for accessing records of maintenance actions for the industrial machine, the records may include some of the predictive maintenance actions. In an embodiment, some of the plurality of computing systems operate the records as a distributed ledger.

In embodiments, methods and systems for operating a predictive maintenance analysis and control system can benefit from visual information as well as performance and operational data from industrial sensors and the like located on industrial machines. Visual information, such as images captured of individual parts, assemblies, process steps, machine conditions, and the like, can be analyzed using machine vision and other techniques, including human viewing and evaluation, to determine conditions that may affect, for example, the prediction of service needs. Generating and maintaining an updated and accurate image library of visual information for industrial machines can allow service personnel to benefit from capturing images of portions of each industrial machine in various states, including, but not limited to, in operation, testing, and non-operational states (e.g., during service, maintenance, repair, upgrades, and machine condition modifications). In embodiments, a system for facilitating image capture is depicted in FIG. 188. A procedure 33416 for servicing or repairing the industrial machine may be identified for scheduled service of the machine. The procedure 33416 may include a series of steps to be taken to perform the scheduled service activity. One or more of the steps may include capturing images of a portion of the industrial machine, such as an external view depicting the machine in a deployed environment, a view of the part to be replaced, or a view depicting the condition of gears, bearings, support structures, housings, etc. While the procedure includes capturing images, learning from the service technician performing the procedure is incorporated to perform the procedure in a proactive manner. The predictive maintenance system 33424 uses machine learning and other techniques to facilitate augmenting and/or adjusting image capture procedures, such as in a procedure. The predictive maintenance system 33424 may provide information, such as conditions, that suggest capturing images that may not be directly necessary in the procedure. Such a case may arise when the predictive maintenance system 33424 determines that a particular bearing exhibits visible wear before the bearing fails. The length of time a bearing can operate under various conditions may not be a sufficient indicator to perform service, but images that visually indicate such wear are sufficient. Thus, if a service technician is performing a service procedure that does not include capturing images of specific bearings, the service technician may be instructed to capture images of those specific bearings. This may be indicated to the service technician as a service alert, such as a general notice, but information about the visual status and timing of service activities may also be used to facilitate augmenting/updating procedures, such as procedure 33416, which includes capturing one or more images of a particular bearing.

In an embodiment, information from the predictive maintenance system 33424 may be processed by the image capture trigger facility 33422 to provide an indication to the procedure update facility 33402 that a procedure update is required, such as to add the capture of an image of a particular bearing. This indication may be combined with image capture timing information provided to the procedure update facility 33402 by the image capture timing facility 33420, which uses industrial machine usage and service schedule information 33426, to create a window of time during which a particular bearing is expected to be imaged. Such a window of time may include scheduled service and/or maintenance activities while the machine is offline. Such a window of time may include planned operating times while the machine is operating. A potential purpose of generating such a window may be to capture images of a particular bearing during a scheduled service visit to avoid specifically shutting down the machine to capture images, even though images are needed before a service activity in which the bearing would normally be imaged is performed, such as a scheduled preventive maintenance activity to inspect the bearing.

In an embodiment, if an existing procedure 33416 is to be applied during an image capture window output from the image capture timing facility 33420, the output of the image capture trigger facility 33422 may be checked. If the image capture triggering facility 33422 indicates that an image is required, the procedure may be updated by the procedure update facility 33402, such as by adding a step to the procedure or by changing the imaging target of an existing image capture step (e.g., from a part to a bearing).

In an embodiment, a revised procedure 33402 may be followed by a service technician. If additional/extended steps are performed to capture images of a particular bearing, an image capture template 33404 may be presented to the technician to assist in capturing an appropriate image. Similarly, as described elsewhere herein, an augmented reality application may be executed as part of such image capture steps to further assist the service technician in capturing an appropriate image. In an embodiment, a machine vision system 33408 and other image analysis techniques may be used to suggest improvements and/or verify that the captured images meet requirements to facilitate detection of the visual condition of a particular bearing.

In embodiments, the image capture reward facility 33414 may interface with the updated procedures 33418 and/or the service technician to facilitate motivating the service technician to capture acceptable images. Such reward facility 33414 may include rewards ranging from direct monetary rewards to positive feedback for the service technician, which may ultimately increase the technician's value and, consequently, compensation.

Captured images, such as those received by the machine vision system 33408, may be stored in the smart RFID element 33410 of the industrial machine, transferred to the smart RFID via an image capture device (e.g., a camera-enabled smartphone), and forwarded to one or more nodes in a distributed ledger of preventive maintenance data.

In an embodiment, a method for image capture of a portion of an industrial machine includes updating a procedure for performing a service to implement a predicted maintenance action on the industrial machine, the updating responsive to a trigger condition being met for capturing an image of the portion of the industrial machine. The image capture method may further include providing an image capture template on an electronic display overlaid on a live image of the portion of the industrial machine to facilitate image capture; applying augmented reality to indicate a degree of match between the live image and the template; inspecting the captured image using a machine vision system to determine at least one portion of the machine present in the captured image; and operating an image capture reward facility to generate a reward for the captured image in response to results of the machine vision inspection. In an embodiment, the updating is performed in response to a trigger condition based on an analysis of failure data for the industrial machine, the analysis suggesting capturing an image not specified in the procedure prior to the updating step. In an embodiment, the updating may be responsive to a procedure for performing a service being performed on the industrial machine that meets a predictive maintenance criterion associated with the portion of the industrial machine from which the image is captured. In an embodiment, the trigger conditions may include the type of industrial machine associated with the industrial machine on which the service procedure is being performed and the length of time since an image of the portion of the industrial machine was captured.

In embodiments, a system for facilitating predictive maintenance of industrial machinery may apply machine learning to images of industrial machinery captured during operations such as assembly, testing, service, repair, upgrade, routine maintenance, and preventative maintenance. Machine learning may be applied to the images and/or data derived from the images using algorithms such as image analysis algorithms, part detection algorithms, and machine vision to facilitate improved automated machine detection of parts of the industrial machinery such as individual parts, subassemblies, etc. In embodiments, automated machine detection of parts, subassemblies, etc. may provide information to methods and systems herein, including, but not limited to, predictive maintenance processes, service provider evaluation methods, procedure evaluation methods, inventory management systems, and maintenance scheduling (e.g., whether a maintenance operation should be scheduled earlier than previously estimated).

In an embodiment, a method and system for automatically detecting parts of an industrial machine may include steps of image capture, processing, analysis, learning, and automation, as illustrated in FIG. 189. In an embodiment, a method for automatically detecting parts of an industrial machine may begin with capturing an image step 33502. Alternatively, image data of a previously captured image may be accessed from an image data store, such as a database. Image capture step 33502 may be performed by a service technician or the like in connection with performing a service task, such as a maintenance procedure, repair procedure, or upgrade procedure. Image capture step 33502 may also be notified as follows: A procedure document indicating the parts to be imaged and their templates may be included. The procedure, target parts, templates, etc. may be obtained from imaging guidance data storage unit 33504. In an embodiment, the procedure may include specific instructions for using a part imaging process to capture images of one or more parts indicated in the procedure. As an example, a procedure for servicing a bearing of an industrial machine may include a procedure for photographing the shaft that the bearing handles. The procedure may present a representative image of the image to be captured on an electronic display of an image capture device, such as a tablet or smartphone. Such an image may be, for example, the most recently captured image of a particular industrial machine, retrieved from the image data structure of smart RFID elements located on the industrial machine (e.g., smart RFID elements configured on machine portions, including bearings, shafts, etc.). Such an image may be annotated with information such as the relative position of the camera on which the image was captured, date and time information, and the procedure number performed. In embodiments, such an image may be processed into a template (e.g., a colored-in/outline image) that facilitates manual alignment of the image capture device. In embodiments, such a template may be an active template that processes the image viewed through the image capture device and provides an indicator, such as a color change in the template, to further facilitate alignment of the image capture device. The active template may begin with a black (or other color) outline and change to green (or other color) when the vertices, edges, etc., associated with the template are sufficiently aligned to facilitate automatic machine detection of the part.

In an embodiment, the image captured in image capture step 33502 may be processed through image verification step 33506, which performs image analysis functions, such as comparing to a reference image retrieved or derived from information such as image capture guidance data store 33504. In an embodiment, the captured image may be processed to improve contrast, etc., and compared during valid image capture step 33506 to a most recently captured image from a smart RFID element located with the industrial machine, such as through an image subtraction process, to determine whether the captured image is valid. Images that do not verify may be discarded, and the user may be instructed to return to image capture step 33502 to capture another image.

In an embodiment, an image that may be verified in step 33506 may be passed to an image analysis or similar step 33508, which may process image analysis rules 33510 to detect one or more candidate parts from the verified image. The candidate parts may be stored in a candidate parts data structure 33514 for further use. In an embodiment, images of candidate parts in the candidate parts data structure 33514 may be retained for further training of machine learning algorithms that facilitate improved machine automation part detection from images. In an embodiment, images of candidate parts may be used in an instance of the machine automation part detection flow 33500 of FIG. 189 and then discarded, deleted, etc. In an embodiment, the image analysis rules 33510 may include data provided from the machine learning step 33520, such as in the form of feedback, which may improve image analysis of images with limitations, such as poor contrast, unexpected content (e.g., excessive solvent, moving parts, reflective parts, etc.).

In an embodiment, one or more candidate parts in the candidate parts data structure 33514 may be processed by a part recognition algorithm step 33516, which may, among other things, perform machine automated part recognition. The automated part recognition algorithm may include generating candidate part attributes, such as dimensions, which may be compared to part description information, which may be retrieved from smart RFID data storage 33512. In one example, the candidate parts may be processed to detect edges, etc., which may be processed by an automated measurement algorithm. The resulting measurements may be used to determine a specific part from a library of parts for a particular industrial machine, which may be available to the part recognition algorithm 33516 in RFID data storage 33512. The specific part information may be retrieved from a parts list, a production data system, such as an MRP system, and stored in RFID data storage 33512 during production operations, such as the exemplary production flow depicted in FIG. 185.

In an embodiment, one or more results of the part recognition algorithm 33516 may be forwarded to a machine learning facility, which may execute one or more machine learning algorithms 33520 to improve various aspects of machine-automated part detection, including, but not limited to, the image capture process 33502, the image verification process 33506, the image analysis process 33508, the part recognition process 33516, etc. In one example, the part recognition process 33516 may provide the machine learning process 33520 with information extracted during the part recognition process, such as images of one or more candidate parts, corresponding reference parts, associated attributes, etc. The machine learning process may apply machine learning techniques to facilitate determining aspects of the candidate parts that represent the best candidates for the corresponding reference parts, and may provide feedback to at least the part recognition process 33516 to improve part detection, etc.

In an embodiment, information describing the recognized part may be stored in an updated smart RFID element 33518, a comparable updated server-based data structure 33522, etc. The stored information may include one or more candidate part images, a reference part identifier, recognition data, the procedure number followed to capture the image, etc.

In an embodiment, a method for machine learning-based part recognition may include applying a target part image template to an image verification procedure that determines whether a captured image meets image capture verification criteria. The method may further include performing image analysis by processing the captured image with image analysis rules that facilitate detecting candidate industrial machine parts present in the image. In an embodiment, the method may include recognizing one or more parts of the set of candidate parts as industrial machine parts based on similarity of the candidate parts to images of the particular industrial machine parts. The method may further include adapting at least one of the target part template, image analysis rules, and part recognition based on feedback generated from machine learning of the recognized parts, thereby improving at least one of image capture, image analysis, and part recognition.

In embodiments, information collected and generated for the maintenance lifecycle of an industrial machine, including predictive maintenance, manufacturer-required maintenance, breakdown repair, parts and service provision and ordering, maintenance activity follow-up, procedure and service provider evaluation, failure rate and predictive analysis, worker training, experience, and ratings, etc., may be captured throughout the service lifecycle, processed with artificial intelligence and other machine learning type algorithms, and stored in databases such as data models, linked databases, enumerated databases, etc. FIG. 169 illustrates a set of such data embodied as a knowledge graph 33602. In embodiments, information about the industrial machine, such as parts, images, configuration, internal structure, usage schedule, etc., along with information from other sources, including, without limitation, service information, breakdown information, worker-related information, etc., may be processed by artificial intelligence type functionality 33606 (e.g., machine learning algorithms, etc.). Information processing algorithms, such as information association algorithms, executed by the exemplary artificial intelligence facility 33606 may update portions of the predictive maintenance and industrial machinery services knowledge graph 33602 by establishing, modifying, deleting, strengthening, etc., knowledge graph node links 33616 between data nodes 33618, and may add, update, partition, etc., data nodes 33618 to initiate and refine a graph-based understanding of the relationships between facts, know-how, analytical results, etc. that affect aspects of the predictive maintenance process as described herein.

In an embodiment, information about machines may be processed and stored in machine data node 33608, information about failures may be processed and stored in failure data node 33610, information about industrial machine servicing may be processed and stored in service data node 33612, and information about personnel for performing industrial machine servicing may be processed and stored in personnel data node 33614. Relationships between data nodes, such as the relationship between machine data node 33608 and service data node 33612, may be depicted as links 33616 between the nodes. The purpose of initiating and updating such knowledge graphs may be to further improve, among other things, the collection, discovery, capture, dissemination, management, and processing of information about industrial machines, including factual information (such as about internal structure, parts, and components), operational information, and procedural information, including know-how and other information related to maintenance, service, and repair.

In an embodiment, as maintenance/service/repair/upgrade/installation and other industrial machinery-related activities are performed, data about the activities may be processed and used to enhance, augment, improve, refine, clarify, and modify data nodes 33618, relationships between nodes, and the like. In an embodiment, preparation of maintenance/service/repair and other industrial machinery activities may benefit from knowledge found in knowledge graph 33602, thereby improving efficiency and reducing computational complexity for generating appropriate service options, recommendations, orders, and the like, for example, by utilizing existing relationships between fault nodes 33610 and worker nodes 33614 to efficiently identify the appropriate worker to resolve a fault when it occurs on a particular machine.

In embodiments, improved methods and systems are provided herein for collecting, discovering, capturing, disseminating, managing, and processing information about industrial machinery, including factual information (such as internal structure, parts, and components), operational information, and procedural information, including know-how and other information related to maintenance, service, and repair. These improved methods and systems may comprise a predictive maintenance knowledge system platform 33700, as depicted in FIG. 191. The predictive maintenance knowledge system 33702 may facilitate collecting, discovering, capturing, disseminating, managing, and processing information about industrial machinery, such as to facilitate its service and maintenance using the methods and systems described herein. This may include, but is not limited to, locating a set of workers with relevant know-how and expertise regarding the maintenance, service, and repair of a particular machine, and locating, ordering, and fulfilling orders for related parts and components so that maintenance, service, and repair work occurs seamlessly with minimal interruptions. The predictive maintenance knowledge system 33702 may interface with one or more predictive maintenance knowledge bases and/or knowledge graphs 33704. The knowledge base 33704 may further include or reference one or more knowledge graphs, which may contain information useful to methods and systems that may be enabled by the predictive maintenance knowledge system 33702. The predictive maintenance knowledge graph may include or provide computer access to information regarding industrial machines, service activities for industrial machines, costs (e.g., history, trends, and forecasts) of industrial machine parts, materials, tools, and services, algorithms and functionality for operating the predictive maintenance knowledge system 33702, the platform 33700, etc. In embodiments, the predictive maintenance knowledge system 33702 may process information from the predictive maintenance knowledge base 33704 regarding expedited service fees charged for specific instances of industrial machine service and develop price-time relationships that can aid industrial machine owners in making decisions regarding service approvals and their costs. The industrial machine owner is informed of the costs of expedited versus standard-timed service, which can help them decide whether it is better to pay an expedited fee and have the maintenance function performed immediately while the machine is offline for other reasons, rather than maintaining the maintenance function's schedule. The predictive maintenance knowledge system 33702 provides maintenance functions that require the machine to be taken offline, such as in the near future. The predictive maintenance knowledge system 33702 may facilitate coordination with service providers, parts providers, material and tool providers, etc. based on the owner's decisions so that service can be performed within a timeframe selected by the owner.

In embodiments, information for a particular industrial machine may be stored on one or more smart RFID elements 33706 co-located with the particular machine and/or in a compatible (e.g., backup, duplicate/twin, or other format data structure) cloud-based data structure 33708. The predictive maintenance knowledge system 33702 may access (e.g., read data from and/or write data to) the RFID element(s) 33706, the cloud-based data structure 33708, etc. Data read from the smart RFID 33706/cloud-based structure 33708 may be specific to a particular deployed industrial machine and may facilitate methods and systems, such as predictive maintenance described herein, that coordinate resources to effectively and efficiently perform maintenance on the particular machine. As an example, a particular industrial machine may have an operating cycle that results in a higher than typical utilization of one of its moving parts (e.g., an industrial motor). This knowledge can be used by the predictive maintenance knowledge system 33702 to interact with service, parts, and material suppliers to provide robust quotes for performing utilization-based maintenance services at different times (e.g., weeks or months earlier) than other comparable industrial machines with lower utilization.

In embodiments, the predictive maintenance knowledge system 33702 may execute algorithms to collect information regarding a plurality of industrial machines, including a plurality of industrial machines of different types (e.g., stationary machines, mobile machines, vehicle-mounted machines, job site-deployed machines, etc.), along with information such as service provider information, parts and parts provider information, part location and inventory information, machine production providers, third-party parts handlers, logistics providers, transportation providers, service criteria, service requirements, service results, etc., to facilitate the predictive maintenance methods and systems described herein. One or more functions of the predictive maintenance knowledge system 33702 can utilize service request information 33726, such as service requests for a particular industrial machine and/or a collection of industrial machines from the industrial machine.
Such service requests are intended to facilitate owners, operators, providers, and users in fulfilling service requests. In embodiments, such service requests may be input to an algorithm that predicts when service will be recommended not only for the requester, but also for comparable industrial machinery. As an example, an industrial machinery owner may request that a subset of industrial machines at a job site receive a first service action. The predictive maintenance knowledge system 33702 may use this request information, along with other information about the machines, such as the age and availability of the machines, to determine when other industrial machines of the same type as the machine for which service was requested should be scheduled to receive an equivalent service action.

In embodiments, in response to a particular service request 33726, the predictive maintenance knowledge system 33702 may access information in the smart RFID 33706 or its cloud-based backup 33708 to determine the particular procedures involved and what experience potential service providers need to perform the service. The predictive maintenance knowledge system 33702 may access the knowledge base 33704 to identify potential service providers. Service providers known to the predictive maintenance knowledge system 33702 (e.g., based on information in the knowledge base 33704, etc.) as having successfully demonstrated experience with the procedures required for the requested service may be contacted to provide a service quote 33736 and/or a price quote 33734 for the service, parts, etc. Similarly, parts and/or materials that may be related to the requested service procedure may be identified. The predictive maintenance knowledge system 33702 may also access the knowledge base 33704 to source parts and/or materials information. Factors such as part cost, transportation cost, availability, part-to-machine location, and pre-existing relationships between one or more part providers and parties associated with the service request, such as the industrial machinery owner, may be evaluated to determine which part providers to contact in preparation for ordering the part. Taking these factors into consideration, one or more part providers may be queried for the part in anticipation of a qualified service provider performing the service as scheduled. The predictive maintenance knowledge system 33702 may respond to the service request 33726 with one or more service recommendations 33732 that may be associated with one or more price-based service recommendation options 33710 that the requester may select. In an embodiment, the predictive maintenance knowledge system 33702 may populate the response with sufficient information from the knowledge base 33704, such as a service quote request 33736, to automatically select a particular price-based service recommendation 33710 from the options and generate a service order 33718, parts/materials/tool order 33716, if necessary for the requested service 33726, with or without the requester's explicit approval.

In embodiments, service requests and/or predicted maintenance activities, etc., may be processed by the predictive maintenance knowledge system 33702 to output service funding recommendations and/or requests 33712. Such recommendations may include funding the services from operating revenues, obtaining a loan for the services, or seeking third-party funding (e.g., industry sources, government grants, private funding sources, etc.). Such requests may include providing information about the requested services to one or more third parties that the third parties can use to submit funding proposals and/or responses. In one example, an industrial machine that provides clean water for a community to the public may require costly services. The predictive maintenance knowledge system 33702 may determine that a particular industrial machine is eligible for federal reimbursement for at least a portion of the services. Federal funding requests may be configured and initiated via the service funding 33712, etc.

In an embodiment, sources of information that the predictive maintenance knowledge system 33702 may rely on may include information from service providers 33724, information from parts providers 33722, information from service material providers 33720, machine schedules 33730, incoming service estimates and/or quotations 33728, etc. The predictive maintenance knowledge system 33702 may use the service material provider information 33720 to determine the price and availability of service materials. This information may be combined with the requester's service material inventory (e.g., centralized, depot-based, or on-site at the industrial machine), material inventory of one or more qualified service providers, etc. In one example, if a service provider has sufficient inventory of the required material accessible locally to the industrial machine for which service is requested but needs to replenish that inventory after performing the service, the system may provide a recommendation to the service material provider for the service material provider to deliver the service material to the industrial machine's site in time for the scheduled service. In one example, if the service provider and industrial machine owner do not have the required service materials in stock, the predictive maintenance knowledge system 33702 may generate an order with one of the service material providers 33720 based on total price, availability, existing relationships with the industrial machine owner and/or service provider, etc. In an embodiment, at least a portion of one or more inventories of the service material providers 33720 may be managed directly by the predictive maintenance knowledge system 33702 such that the predictive maintenance knowledge system 33702 can allocate materials from its inventory for the service action. The service material provider 33720 may receive notification from the predictive maintenance knowledge system 33702 that it has been selected to provide materials for the service action. Payment for the materials may be made through transaction facilities associated with the predictive maintenance knowledge system 33702 such that the operator of the predictive maintenance knowledge system 33702 and the service material provider 33720 are compensated for their role in the service action. Comparable examples may be envisioned for the parts provider 33722, the service provider 33724, a service funding source (not shown), etc.

In an embodiment, the predictive maintenance knowledge system platform 33700 may include a computerized maintenance management system (CMMS) 33714 that facilitates creating work orders, such as maintenance actions, to resolve equipment problems. The CMMS 33714 may facilitate communication of parts and service requests to an Enterprise Resource Planning (ERP) system (not shown), which may facilitate processing of parts and service orders. In an embodiment, the ERP system may be associated with one or more of the owner/operator/provider/lessee/lessor of the industrial machinery for which service actions are coordinated by the predictive maintenance knowledge system 33702. In an embodiment, the CMMS 33714 may interface with the industrial machinery owner's ERP system to enable ordering to service providers, parts providers, etc.

In an embodiment, the predictive maintenance system may include a predictive maintenance knowledge system that facilitates collecting, discovering, capturing, disseminating, managing, and processing information about the industrial machines and facilitating taking predictive maintenance actions for the industrial machines. The knowledge system may include multiple interfaces for receiving information from service providers, parts providers, material providers, and machine usage schedulers; multiple interfaces for transmitting information to service ordering facilities, parts ordering facilities, service management facilities, and service financing facilities; and multiple interfaces to smart RFID elements on the multiple industrial machines. The predictive maintenance system may further include a predictive maintenance knowledge graph that facilitates access by the predictive maintenance knowledge system to information related to predictive maintenance services for the industrial machines through links between data domains, including service providers, parts providers, service requests, service quotes, machine schedules, and maintenance activity forecasts. In an embodiment, the predictive maintenance knowledge system may generate at least one of service recommendations, price-based service options, price estimates, and service estimates.

In embodiments, preventive maintenance or other scheduled maintenance for industrial machinery and the like may be scheduled at set intervals based on manufacturer expectations regarding failure rates and the like. By collecting and analyzing information about the industrial machinery and the like, such as operational data, failure data, and conditions discovered during preventive maintenance activities, a new schedule of maintenance activities may be constructed that can further reduce the occurrence of unscheduled shutdowns due to component failures and the like. FIG. 192 illustrates a preventive maintenance schedule 33808 for a set of bearings in a group of industrial machines 33802 that use bearings. As shown, bearing preventive maintenance events A, B, C, and D are scheduled to occur at timed intervals for each machine. Data collected and analyzed by a predictive maintenance system using the methods and systems for predictive maintenance of industrial machinery described herein may indicate that a different schedule of bearing maintenance is needed to prevent failures. In the example of FIG. 192, failure 33804 of machines 4 and 3 occurred after preventive maintenance activity B. In response to this, a new bearing maintenance schedule may be established for the machines, taking into account other factors, such as the operating cycle rate of the industrial machines. Because machines 1 and 2 have not yet failed, predictive maintenance events may be scheduled for machine 1 (33810) and machine 2 (33812). In an embodiment, machine 2 may have a substantially lower availability rate than machine 1, and therefore, while both machines use the bearings that failed on machines 3 and 4, predictive maintenance events may be scheduled for each machine individually. Machine 1's predictive maintenance event 33810 may be scheduled to occur earlier than scheduled in the predictive maintenance schedule 33808 (Event C). Machine 2's additional maintenance event 33812 may also be scheduled to occur immediately after a future scheduled preventive maintenance event (another Event C), based, for example, on the timing of the failures of machines 3 and 4 after preventive maintenance event B. By shortening the interval between preventive maintenance event C and predictive maintenance event 2 (33812), the risk of a bearing-related failure may be reduced.

In an embodiment, the predictive maintenance system for industrial machinery can apply machine learning and other factors to predict and expedite service, such as determining the schedule for service, identifying at least one qualified party to perform the service, recommending sources of one or more materials required for the service, procuring and delivering the materials required for the service, and assessing service for one or more parts of the industrial machinery. The machine learning capabilities of such systems may be used for infrared thermography of one or more components of industrial machinery, ultrasonic testing of one or more components of industrial machinery, motor testing of one or more components of industrial machinery, magnetic field testing of motors of one or more components of industrial machinery, electro-magnetic flux (EMF) testing of one or more components of industrial machinery (e.g., current and/or voltage testing of one or more components of industrial machinery, such as by machine-resident test equipment and/or externally applied test equipment), torsion testing of one or more components of industrial machinery, such as by electromotive force, non-destructive testing of one or more components of industrial machinery (e.g., non-destructive inspection of one or more components of industrial machinery, such as required by the nuclear and power industries), x-ray inspection of one or more components of industrial machinery (e.g., turbine blades), video analysis for vibration detection of one or more components of industrial machinery, and the like. Examples of such testing include electric field testing of one or more components of industrial machinery, magnetic field testing of one or more components of industrial machinery, acoustic detection of one or more components of industrial machinery, power and/or current and/or voltage testing of one or more components of industrial machinery (e.g., applying algorithms equivalent to those used in vibration analysis to determine whether changes in current are abnormal), spectral analysis of power consumed by a machine (e.g., rotating machinery, etc.), correlation of mechanical and power defects in one or more components of industrial machinery, sound meters to verify sounds generated by or at least in proximity to one or more components of industrial machinery, etc. In embodiments, machine learning may be applied individually to any of these sources of test data to detect patterns, etc., useful, for example, for detecting when a significant change in the detected pattern has occurred or is about to occur.

In embodiments, a combination of diagnostic tests, such as those described herein, can be used with machine learning to verify or negate one or more potential causes of an anomaly that may indicate a need for service, etc. In embodiments, combining infrared thermography with motor testing, such as applying a test load to the motor while capturing infrared images, can be useful in determining combinations of conditions that may indicate a potential failure, or at least a condition related to a failure, a need for service, etc. In embodiments, combining sound meter capture with non-destructive testing, for example, can generate sound patterns that can be compared to baseline sounds for specific non-destructive testing conditions, thereby enabling multi-modal evaluation of results (non-destructive testing results and sound test results). In embodiments, variations in sounds generated by or proximate to an industrial machine can indicate a potential fault condition, verify a candidate fault condition, and/or reduce the likelihood of a potential failure. In embodiments, combining multiple modes of non-destructive testing, such as acoustic and x-ray, can help determine whether a condition that may be detected in one inspection mode (e.g., acoustic) correlates with a potential anomaly detectable in another inspection mode (e.g., x-ray). In embodiments, machine learning can develop an array of test conditions, test results, and conformance to expected results for each of the diagnostic/test scenarios described herein. Such an array can facilitate determining when an anomaly represents a valid potential fault condition.

In embodiments, each test condition, such as those described above, may be applied and results obtained. While a given test condition is being applied, other test conditions may be applied, thereby facilitating the collection of combinations of each test condition with other test conditions. The results of each combination may be captured and represented in an array, such as the array described above. Testing combinations of test conditions may be performed when a service call, such as preventive maintenance or repair, is necessary. In embodiments, an industrial machinery predictive maintenance system may facilitate coordinating maintenance, such as replacing worn bearings on an industrial machine. The test condition combination array may be referenced to determine which test conditions may be applied in combination with a test after a bearing replacement, such as detecting that one or more cells in the array have little or no combined data along the test axis after the bearing replacement. Work instructions and/or procedures for testing after a bearing replacement may be conditionally adapted for specific cases to include the following:
This approach, along with the step of applying additional test conditions indicated by specific cells of the array, can increase test data while spreading the testing burden over time, or at least over the servicing of industrial machinery.

Machine learning can also be applied to combinatorial testing, for example, to discover which combinations of test conditions are most correlated with actual failures. By learning which combinations are correlated with failures, combinations that are less likely to result in potential failures may be deprioritized, allowing valuable testing resources, such as service personnel, to be directed toward combinatorial testing that is more likely to yield actionable information.

In embodiments, test results from a first mode of a particular industrial machine, such as a motor test, may be processed using a machine learning algorithm or similar algorithm that can correlate the particular machine test results with one or more candidate failure modes. Test results from a second mode of a particular machine, such as a torsion test, may be processed using a machine learning algorithm or similar algorithm that can correlate the particular torsion test results with one or more candidate failure modes. One or more candidate failure modes from the machine test may be compared to those from the torsion test. Candidate failure modes that match between the two types of tests may be candidates for processing the combined test results using machine learning. When the results of the machine test and the torsion test are combined and processed using machine learning, the candidate failure modes may be correlated. If one of the candidate failure modes from the combined test matches one of the candidate failure modes from the combined test, the likelihood that the combined test indicates a possible failure may be strengthened. If such confirmation is detected through the machine learning process of the combined test results, service/repair actions may be initiated to prevent a failure of the particular industrial machine. Test procedures involving combined testing may also be adapted for other industrial machines to avoid possible failure modes from the combined test results.

Referring to FIG. 193, an industrial machinery predictive maintenance system 33902 may run machine learning algorithms 33904, etc., on data from various diagnostic inspection systems, such as an infrared thermography system 33906, an ultrasonic inspection system 33908, a motor inspection system 33910, a current and voltage inspection system 33912, a torsion inspection system 33914, a non-destructive inspection system 33916, a power, current, and voltage inspection system 33918, and a sound and vibration inspection system 33917, as well as a test system 33920. The industrial machinery predictive maintenance system 33902 may access a library of test results 33922, which may include test results from these test systems for prior calls for tests on the particular industrial machine and/or similar industrial machines. These results, along with failure mode information for the particular industrial machine and/or similar industrial machines, may be processed by the machine learning algorithm to determine test conditions, where specific combinations of test conditions may correlate to specific failure modes. The machine learning algorithm 33904 uses artificial intelligence techniques to determine patterns, similarities, etc. between data from the library, thereby facilitating the detection of combinations of test conditions that may correlate to one or more failure modes.

In an embodiment, a method for improving correlation between diagnostic test results and machine faults may include improving correlation between results of multiple diagnostic tests performed on an industrial machine and failure information related to similar industrial machine faults by detecting at least one of a pattern of diagnostic test results that correlate to machine faults and a similarity between machine faults and diagnostic test results. In an embodiment, a single type of machine fault is correlated to failure results of a subset of diagnostic tests.

In embodiments, improved methods and systems for maintenance of industrial machinery include methods and systems that facilitate the collection, discovery, capture, dissemination, management, and processing of information about the industrial machinery, including factual information (e.g., regarding internal structure, parts, and components), operational information, and procedural information, including know-how and other information related to maintenance, service, and repair. The methods may include a method for rating a set of services and service providers related to, for example, predictive maintenance of industrial machinery. In embodiments, service providers for performing maintenance and related activities may be rated. While performing the service specified in a service procedure, a service provider (e.g., a technician, etc.) may be rated on the degree to which the procedure was followed. The degree to which the procedure was followed may be implicitly determined by an independent determination of whether the procedure was completed in the specified order. In embodiments, a procedure that requires taking a photograph of a bearing after removing a bearing cover panel may be verified by the service technician submitting a photograph of the uncovered bearing before proceeding. In embodiments, the service technician accesses the service procedure through an interface on a computing device, such as a tablet, mobile phone, or industrial portable computer, through which the user-technician accesses the service procedure. Service technicians may be evaluated based on a variety of criteria, including ease of scheduling, level of expertise and training with a particular machine or service activity, results of post-service diagnostic tests (e.g., self-tests), estimated versus actual costs of service, speed at performing service as scheduled, subjective cleanliness, adherence to procedures (as described above), and reliance on other resources, such as third parties.

In an embodiment, a vendor rating system 34000 is depicted in FIG. 194. The vendor rating system 34000 may include a vendor rating facility 34002 that captures information about a vendor 34006 (e.g., location(s), user feedback, etc.), service data for one or more procedures 34008 that the vendor 34006 claims to know, and vendor rating weighting data 34010 that may affect how the information is used to rate the vendor (e.g., older data may be weighted less than newer data, service on machines with very little service information may be weighted less, etc.). The vendor rating system facility 34002 may further consider the overall experience level of the vendor by applying an experience scale 34012 that influences the confidence in a particular vendor rating based on the vendor's experience and level of rating. Service technician input 34014 may consider structured (e.g., multiple choice answers) and/or free-form input that a service technician may provide about a service activity, such as to explain why a procedure was not followed or why service took longer than expected. The vendor evaluation facility 34002 may further receive information from diagnostic tests 34022, such as tests performed and test results related to service activities, which may be used to evaluate the success of the service activities performed. Diagnostic test information 34022 may include information from diagnostic tests such as infrared thermography, ultrasonic testing, motor testing, current/voltage testing, torsion testing, non-destructive testing, power density testing, acoustic testing, etc. In an embodiment, the vendor evaluation facility 34002 may evaluate vendors on a set of vendor evaluation criteria 34016, including, but not limited to, the results of post-service diagnostics determined from diagnostic test result data 30222, etc. The vendor evaluation criteria may further include schedule, degree of experience with procedures, machines, etc., cost, promptness, cleanliness, adherence to procedures, etc.
The vendor evaluation results may be stored and accessed in a vendor evaluation results data store 34022, which may be processed by machine learning algorithms 34024, for example, to improve the correlation between the vendor evaluation criteria (e.g., degree of experience) and the vendor's evaluation.

In an embodiment, a method of vendor evaluation may include determining a rating of an industrial machinery service provider by collecting feedback regarding industrial machinery services provided by a service provider and comparing the feedback to a plurality of evaluation criteria, including results of diagnostic tests performed after completion of at least one industrial machinery service, scheduling of the service provider, cost of the services provided, promptness of the service provider, cleanliness of the service provider, adherence to procedures for the at least one industrial machinery service, and measures of the service provider's experience with at least one of the procedures and the industrial machine. In an embodiment, the method may include applying machine learning to the vendor rating results and incorporating the machine learning output when rating the vendor, thereby improving correlation between the vendor rating results and the rating criteria.

In embodiments, improved methods and systems for maintaining industrial machinery that facilitate the collection, discovery, capture, dissemination, management, and processing of information about the industrial machinery, including factual information (e.g., regarding internal structure, parts, and components), operational information, and procedural information, including know-how and other information related to maintenance, service, and repair, may include a method for rating a series of activities and information related to, for example, predictive maintenance of the industrial machinery. In embodiments, procedural information for performing maintenance and related activities may be rated. While performing the service specified in the service procedure, a service provider (e.g., a technician) may indicate a rating for the operation of each procedure, e.g., each substantive service procedure, through a user interface through which the technician accesses the service procedure. The service technician may rate each procedure along various criteria, including, but not limited to, ease of access to the information, educational value of the information, accuracy of the explanation, accuracy of the images, accuracy of the sequence, difficulty of performing the service, etc. Service providers and others who rely on procedural information to perform, for example, maintenance of one or more machines can use such procedural information to develop know-how for servicing the system. Such know-how may be reflected in the procedure evaluation system through free-form comments related to procedures and suggested edits to published procedures.

In embodiments, a procedure for performing a maintenance task may be clear to a service technician familiar with a particular machine, but not clear enough for a less experienced service representative. Therefore, information about the service technicians who completed the procedure evaluation task may be applied to better weight the evaluation. Furthermore, service procedures may be rated on an experience scale, which may facilitate identifying when less experienced personnel can be used to perform the service task versus when an experienced provider is preferred. Such information may be useful to an industrial machinery predictive maintenance system to facilitate, for example, the selection of a suitable service entity to perform the required service task. In embodiments, an industrial machinery predictive maintenance system may collect information that can describe various aspects of a service/maintenance procedure, such as an experience scale rating, when facilitating access to vetted service personnel. In particular, if a service procedure is rated as being highly complex, a service entity with few experienced personnel available to perform the service may be avoided or at least ranked lower than a service entity with more experience, more available experienced service technicians, etc. The rated procedure information may further enhance the system that generates service procedure information, such as by identifying characteristics of a service procedure that favor it over a service procedure that is deemed lacking.

In an embodiment such as that shown in FIG. 195, a method and system for rating industrial machinery service and/or repair procedures may include a procedure rating facility 34102 that aggregates various sources of procedure rating content to generate one or more ratings for the procedures, such as ease of use, accuracy, flexibility, etc. Such rating facility 34102 may have access to the procedures 34106 to process the procedure's text, images, flowcharts, etc., thereby facilitating the rating of various factors contributing to the procedure. The procedure rating facility 34102 may also have access to procedure service data 34108, such as the length of the procedure's use case. Such service data may be useful in determining the confidence in the rating of the procedure. Ratings of infrequently used procedures may be less reliable than ratings of frequently used procedures, at least in part due to the lack of comparative data for infrequently used procedures. The evaluation of a procedure may also include accessing weightings 34110 of factors contributing to the evaluation; such weightings may be explicitly stated or implicitly determined and may vary based on factors such as the age of the procedure, the availability of materials needed to follow the procedure, etc. In embodiments, the evaluation of some procedures may be influenced by the experience of contributors to the evaluation process, such as service technicians, supervisors, procedure quality testers, etc. Accordingly, an experience scale 34112 may be applied to the evaluation algorithm, such as to influence, for example, which aspects of the procedure a contributor with a given experience may be permitted to evaluate. In embodiments, service technician and other contributor input 34114 to the evaluation process may be gathered explicitly, such as by contributors marking rating scales for various aspects of the procedure (e.g., procedure text, procedure translation, etc.). Contributor opinions may also be gathered implicitly, such as by tracking the time it takes to perform a procedure step. In embodiments, if a service technician follows different or additional steps than those presented in the procedure, the procedure evaluation facility can take this input and the reasons for these other steps as factors influencing the procedure evaluation. This feedback can help identify procedures with inaccurate machine analysis and/or manufacturer guidance, which may help improve service quality. Incorrect machine fault diagnoses may be analyzed by artificial intelligence, such as the machine learning facility 34124, to improve analysis. Technician feedback, procedure evaluation analysis, and results can be made available or pushed to procedure developers (e.g., industrial machinery manufacturers) to facilitate procedure improvements for better and faster repairs. Incentivized feedback programs, such as evaluation procedures 34102, and their appropriate use can instill institutional knowledge into all aspects of the preventive maintenance system without the need for traditional one-on-one training.

In embodiments, a procedure evaluation facility, such as evaluation facility 34102, may further have access to evaluation criteria 34116, which may include, without limitation, the accessibility of the procedure, the translatability of the procedure, the educational value of the procedure, the accuracy of the text, the accuracy of the images/graphics, the accuracy of the associated content (e.g., parts list), etc.; the appropriateness of the set of procedures; the overall ease of obtaining error-free results the first time the procedure is used; and the degree of dependency on other procedures, whether directly documented or not. An evaluation facility, such as procedure evaluation facility 34102, may generate procedure evaluation results 34122, which may be stored electronically, such as in a non-volatile computer-accessible memory. In embodiments, procedure ratings for a particular industrial machine may be stored on one or more smart RFID components co-located with the machine. The procedure evaluation results 34122 may be improved, such as through the use of machine learning 34124 operating in concert with the procedure evaluation facility 34102.

In an embodiment, a method for rating industrial maintenance procedures may include collecting feedback on the procedures from service providers who use the procedures to perform industrial machine services, and determining a rating for the industrial machine service procedures by comparing the feedback to a plurality of rating criteria consisting of procedure accessibility, translatability, educational value, accuracy of content, accuracy of sequence, ease of following the procedure, and reliance on actions outside the procedure. The method may further include applying machine learning to the procedure evaluation results and incorporating the machine learning output when rating the procedures, thereby improving correlation between the procedure evaluation results and the rating criteria.

In embodiments, blockchain technology and applications, such as distributed voting, cryptographic hashing, verifiability, security, open access, speed of access and updates, and ease of adding participants (e.g., contributors, verifiers, etc.), may be applied to the predictive maintenance methods and systems for industrial machinery described herein. Data collection from industrial machinery, such as operational, test, and fault data, may be processed using a blockchain approach, which facilitates ensuring the verifiability of information related to system status, faults, etc. Transactions such as part orders and service orders may be processed using a blockchain, thereby increasing the security and verifiability of transactions containing information such as costs that can be utilized by the predictive maintenance systems described herein to manage maintenance and service activities for industrial machinery. Other uses of blockchain may include securing a distributed public ledger, such as distributed ledger 33302 depicted in and described in connection with FIG. 187 herein.

In embodiments, transactions conducted on a peer-to-peer network of industrial machines, such as IoT devices, may be operated as a Blockchain®-enabled distributed ledger, thereby reducing reliance on central management or repositories of preventive maintenance data for industrial machines, etc. In one example of Blockchain® functionality in a predictive maintenance system for industrial machines:
Changes to the smart IC tags installed on individual machines and to copies existing on the network are processed using the Blockchain® distributed ledger system, making it possible to make IC tag information open, including accessing related information on copies existing on the network.

In an embodiment, FIG. 196 illustrates a blockchain® for transactions related to a particular industrial machine 34200, which may begin 34202 when the industrial machine is shipped or finalized for shipment. As additional transactions for the particular industrial machine are performed, such as during installation 34204, collection of operational information from sensors located on the industrial machine 34206, machine service events 34208, parts and service orders 34210, diagnostic activities 34212, etc., each may be added to the blockchain® for the particular industrial machine, thereby providing a secure, verifiable, and traceable dataset for the industrial machine that can be utilized by the predictive maintenance methods and systems described herein.

In an embodiment, a method for accumulating information about an industrial machine may include initiating a blockchain of industrial machine information for a particular industrial machine by generating a starting block, and generating subsequent blocks of the blockchain for the particular industrial machine by combining data from at least one of shipment preparation, installation, operational sensor data, service events, parts orders, service orders, and diagnostic activities with a hash of the most recently generated block in the blockchain.

In embodiments, predictive maintenance schedules, actions, etc. may be based on an analysis of operational data of the industrial machine, such as data from sensors located with the industrial machine. Determining maintenance trigger thresholds for operational data, including sensed data, may include identifying the type of effect the data represents and then determining data values representing acceptable, suspect, unacceptable, and other types of operation. In embodiments, vibration sensors located to detect and monitor vibration activity on industrial machine components, structural elements, etc., can facilitate determining how vibrations in machine components contribute to predictive maintenance actions. Determining the significance of vibration data from sensors relative to, for example, the timing of predictive maintenance actions may require more than traditional vibration analysis. In embodiments, vibration measurements may be converted into units of severity for use in predicting maintenance needs, etc.

In an embodiment, vibration is useful for determining adverse effects on industrial machinery, but vibration analysis is generally complex and varies greatly based on the frequency of the vibration, the source of the vibration, the material being vibrated, the machine's operating cycles per minute, etc. Vibration metrics such as vibration velocity may be useful for determining whether vibration is a problem at moderate vibration frequencies, but alone do not provide useful insights at low or high frequencies. Therefore, performing frequency-independent vibration analysis, such as a normalized vibration analysis metric, may provide useful predictive maintenance information.

In embodiments, vibration analysis results may be normalized to units of severity as described herein to facilitate vibration frequency independence. Overall vibration spectra, RMS levels, and the like may be expressed in units of displacement, velocity, acceleration, and the like. As an example, bearing cap vibration measurements may be expressed as vibration velocity, at least in part because they relate directly to the mechanical severity of the vibration. As noted above, while vibration velocity may be sufficient for mid-frequency components, low- and high-frequency components present significant exceptions to the relevance of vibration velocity for predictive maintenance algorithms. It will be understood in light of this specification that vibration velocity may be characterized, for example, through an amplitude-versus-frequency chart that substantially linearly reduces low- and high-frequency speed severity requirements (e.g., vibration amplitude) compared to mid-range frequency speed severity requirements.

In embodiments, the methods and systems described herein extend and enhance the frequency chart methodology to facilitate normalization of vibration spectra so that they can be expressed in consistent vibration severity units across a wide vibration frequency spectrum, from frequencies near zero to well above 18,000 cycles per minute (cpm). Components of the vibration spectrum occurring at frequencies below the low-end linearity frequency (e.g., low-end knee frequency value) are processed with an algorithm that normalizes them to displacement values (e.g., preset values of millimeters of displacement) because displacement (e.g., amplitude) has been shown to be a more significant indicator of severity than velocity at low frequencies. Components of the vibration spectrum occurring above the high-end linearity frequency (e.g., high-end knee frequency value) are processed with an algorithm that normalizes them to gravitational force unit values (e.g., preset values of g's or g-forces). As a result, each range of the frequency spectrum (below knee threshold, mid-range, and over knee threshold) can be uniformly mapped to a severity unit. In many instances, the frequency spectrum may be divided into three ranges (below knee threshold, mid-range, and above knee threshold at the high end), and fewer or more ranges of the frequency spectrum may be determined and applied without exceeding the scope of the vibration data normalization technique for generating vibration severity units for predictive maintenance.

In embodiments, the methods and systems include normalizing vibration amplitude units to frequency-independent units. These units may be referred to as severity units or action units. In many instances, vibration spectra, overall levels, or root-mean-square levels are expressed in units of displacement, velocity, or acceleration. For example, in bearing cap measurements, vibration velocity is most commonly used because it can be directly related to mechanical severity. While mid-frequency components are sufficient, there are significant exceptions in the low- and high-frequency ranges. It will be understood in light of this disclosure that many amplitude-frequency severity charts are constructed to linearly decrease velocity severity requirements for both the low- and high-frequency components depicted on the chart.

In embodiments, methods and systems include developing and constructing a severity graph for normalizing vibration spectra in units of severity. By way of example, as depicted in FIG. 176, low-frequency components below a predetermined knee level of approximately 1,200 cycles per minute are scaled by a predetermined factor (as a function of slope) so that their amplitudes in units of severity can be normalized with respect to severity. Similarly, for high-frequency components above a knee level of approximately 18,000 cycles per minute, the spectral peaks are also scaled by a different predetermined factor to achieve a flatness in severity. In embodiments, the spectrum displayed in units of severity may be displayed with horizontal lines to separate the severity levels. In many aspects of the embodiments, other spectral components associated with one or more bearing defect frequencies and/or one or more bearing resonant frequencies may have their corresponding amplitudes adjusted for severity. By way of example, other spectral components associated with one or more bearing defect frequencies may have their corresponding amplitudes increased to adjust for severity, and other spectral components associated with one or more bearing resonant frequencies may have their corresponding amplitudes decreased to adjust for severity. Additionally, other digital processing techniques that output spectra, such as envelopes, may be employed to complement or overlap spectral peaks within the severity spectrum. Additionally, in embodiments, the final severity spectrum may be accessed and displayed via local, remote, and/or cloud network facilities for presentation and analysis purposes. In embodiments, the final severity spectrum may be fed into an expert system for analysis and assessment of severity. In many aspects of the embodiments, an overall level may be calculated or derived from this "normalized" spectrum, producing an overall level or root-mean-square level in units of severity rather than the typical collection of discrete units utilized in current vibration monitoring systems.

In an embodiment, FIG. 197 illustrates a severity unit conversion function for normalizing vibration sensor data for casing vibration of industrial machinery. The severity unit conversion function 30602 includes vibration displacement rate (inches/second) along vertical axis 30604 and vibration frequency (cpm) (cycles per minute) along horizontal axis 30606. The low-end frequency demarcation 30608 is set to 1200 cpm and defines the upper end of the low-end vibration frequency region 30610 and the lower end of the mid-frequency region 30612. The high-end frequency demarcation 30614 is set to 18000 cpm and defines the lower end of the high-end vibration frequency region 30616 and the high end of the mid-frequency region 30612.

The severity of the embodiment in Figure 176 is calculated as follows:

S=MxA (30601)

In equation 30601, S is the calculated severity value, A is the intermediate severity limit, and M is the severity normalization value calculated as follows for each of the three vibrational spectral ranges:

For the low-end range of 30610, M = frequency / low-end boundary value

For the mid-range 30612, M=l;

For the high-end range: 30616: M = high-end demarcation value/frequency.

In the example embodiment of Figure 197, M = frequency/1200 for the low-end range and M = 18000/frequency for the high-end range. This results in acceptable severity values of approximately 2.5 mil for the low-end range and approximately 2.5 g for the high-end range.

In embodiments, the severity normalization function illustrated in FIG. 197 can facilitate the development of severity units for each frequency range that can be used by the predictive maintenance methods and systems described herein.

In an embodiment, five severity units may be identified and applied to each frequency range. The severity units may be labeled as acceptable, monitor, review, action soon, immediate, etc. In an embodiment, vibration data resulting in acceptable severity units has little impact on predictive maintenance analysis and action recommendations. Vibration sensor data studies resulting in acceptable severity units may be collected and further analyzed for variations between industrial machines, such as similar industrial machines, similar parts of industrial machines, and different generations of industrial machines or parts thereof.

In embodiments, additional severity categories may be added, as depicted in FIG. 198. Continuing to refer to FIG. 198, an exemplary severity chart may define severity levels with actions associated with those levels. In this example, the severity chart may be associated with spectral peaks acquired by an accelerometer mounted on a bearing cap. The range in which one or more detected signals are considered acceptable, and therefore the least severe of three ranges of detected signals, is less than approximately 2.5 thousandths of an inch peak-to-peak (approximately 63.5 micrometers peak-to-peak) when measuring displacements in the regime of less than approximately 1,200 cycles/minute or less than approximately 20 Hz. In the range of approximately 1,200 cycles/minute to approximately 18,000 cycles/minute, or approximately 20 Hz to approximately 300 Hz, the severity chart evaluates signals in terms of velocity, and the acceptable, and therefore least severe, level may be less than approximately 0.15 inches/second peak-to-peak (approximately 3.81 millimeters/second peak-to-peak). In regimes above about 18,500 bpm or above about 300 Hz, the severity chart evaluates the signal in terms of acceleration, and an acceptable, and therefore minimum severity level, may be below about a 2.5 g peak level.

The range of one level above the most severe across the three ranges of detected signals where one or more detected signals are deemed worth looking at is between 2.5 thousandths of an inch peak-to-peak (approximately 63.5 micrometers peak-to-peak) and 5 thousandths of an inch peak-to-peak (approximately 127 micrometers peak-to-peak) when measuring displacement for regimes below about 1,200 cycles/minute or below about 20 Hz. For regimes between about 1,200 cycles/minute and about 18,000 cycles/minute or between about 20 Hz and about 300 Hz, the severity chart allows for rating signals in terms of speed and worth looking at, thus indicating that the next level above the least severe is between about 0.15 inches/second peak-to-peak (approximately 33.8 millimeters/second peak-to-peak) and about 0.3 inches/second peak-to-peak (approximately 67.6 millimeters/second peak-to-peak). For regimes above about 18,500 cycles per minute, or above about 300 Hz, the signal can be assessed on a severity chart.
Therefore, the next level up from the lowest level is between a level of about 2.5g peak and a level of about 5g peak.

One or more detection signals are determined to be sufficient to suggest or require reinvestigation of the machine or path from which the one or more signals were obtained, and therefore, across three ranges of detection signals, one level of severity higher than the monitoring level and two levels of severity higher than the least severe: 2. When measuring displacement in a regime of less than approximately 1,200 cycles per minute or less than approximately 20 Hz, between 5/1000 of an inch peak-to-peak (approximately 63.5 micrometers peak-to-peak) and 5/1000 of an inch peak-to-peak (approximately 127 micrometers peak-to-peak). In the regime of about 1,200 cycles per minute to about 18,000 cycles per minute or about 20 Hz to about 300 Hz, the severity chart may evaluate signals in terms of velocity and define a range sufficient to suggest or request a reinspection of a machine or route where one or more signals are obtained between about 0.3 inches per second (about 7.62 millimeters per second peak) and about 0.6 inches per second (about 15.24 millimeters per second peak). For regimes of about 18,500 cycles per minute or greater, or about 300 Hz or greater, the severity chart may evaluate signals in terms of acceleration and define a range sufficient to suggest or request a reinspection of a machine or route where one or more signals are obtained between about a 5g peak level and about a 10g peak level.

In this example, the range where one or more detected signals are deemed sufficient to flag for immediate action is one level below the severity level that flags for action. In other examples, there may be flag actions including a flag for immediate action and a flag for shutdown when the severity of one or more detected signals warrants such a flag. When measuring displacement at a rate below about 1,200 cycles per minute or below about 20 Hz, the range sufficient to flag for immediate action may be between about 1/1000 of an inch peak-to-peak (about 254 micrometers peak-to-peak) and about 1/1600 of an inch peak-to-peak (about 421.64 micrometers peak-to-peak). For regimes of about 1,200 cycles/minute to about 18,000 cycles/minute, or about 20 Hz to about 300 Hz, the severity chart may evaluate signals in terms of speed and define a range between about 0.6 inches/second (about 15.24 millimeters/second) peak and about 0.5 inches/second (about 0.5 millimeters/second) peak that is sufficient to suggest or require a reinvestigation of the machine or route on which one or more signals are obtained.
For regimes above about 18,500 cycles per minute, or above about 300 Hz, a severity chart may be sufficient to evaluate the signal in terms of acceleration and suggest or request a reinvestigation of a machine or route where one or more signals are obtained between about 10 g peak and about 16.6 g peak.

This example shows a range where one or more detected signals are deemed sufficient to raise a flag for immediate action and are therefore at the highest severity level. In other examples, flag actions may include a flag for immediate action and a flag for shutdown if the severity of one or more detected signals warrants such a flag. When measuring displacement in a regime below approximately 1,200 cycles/minute or below approximately 20 Hz, a distance close enough to raise a flag for immediate action may be approximately 16.6 thousandths of an inch peak-to-peak (approximately 421.64 micrometers peak-to-peak) or greater. In regimes between approximately 1,200 cycles/minute and approximately 18,000 cycles/minute, or between approximately 20 Hz and approximately 300 Hz, the severity chart may evaluate signals in terms of velocity, defining a range where a peak of approximately 1 inch/second (approximately 25.4 millimeters/second) or greater may be sufficient to raise a flag for immediate action. In the regime above approximately 18,500 cycles per minute, or approximately 300Hz, the severity chart evaluates the signal in terms of acceleration, and once it exceeds a peak level of approximately 16.6g, it can flag it sufficiently for immediate action.

It will be appreciated in light of this disclosure that the severity chart in Figure 197 depicts a velocity of 0.15 inches per second at 1,250 cycles per second in the Tolerance category. The conversion between displacement, velocity, and acceleration depicted in Figure 197 shows that, for normalization to determine units of severity, 2 thousandths of an inch of peak-to-peak displacement is equivalent to a velocity of 0.15 inches per second at 1,250 cycles per second. Figure 197 also shows that a peak velocity of 0.2 inches per second at 61,450 cycles per minute corresponds to a 2.5g level of acceleration. The Watch category is in the 6dB range. The Reinvestigate category is 6dB, and the Act Immediately category is approximately 4.5dB.

It will be appreciated in light of this disclosure that many example severity charts may be based on very specific equipment types. In many examples, some of these classifications may be simplified, as many categories of machinery operating at sufficiently low or relatively slow speeds may not require separate severity categories. In these examples, speed-based severity units may be sufficient to provide a diagnosis. In many examples, communication between different subsystems, such as a raw data server providing vibration waveforms, spectra, and overall levels, and an expert system engine that must convert this raw data into meaningful severity units, may be greatly simplified through the use of normalization to generate the severity units.

In embodiments, units of severity may be applied to non-oscillatory data, where signal processing techniques may be applied to any raw data set that has technical significance but must be normalized for successful comparison or analysis. In embodiments, actuarial data regarding the viability of a particular pharmaceutical treatment, which may be gender specific, may be normalized to the general population. It will be appreciated in light of this disclosure that one or more established techniques or guidelines for normalizing gender-specific data into a gender-free universe will be useful for subsystem communication to AI, statistical, tutorial, or other related systems.

In embodiments, the vibration data resulting from the Watch Severity Unit may influence aspects of the predictive maintenance recommendation, such as the frequency with which vibration data collection and analysis occurs. The Watch Severity Unit's determination may result in at least more frequent collection and analysis of vibration data, and/or may result in the identification of other conditions of the component experiencing the vibrations, such as by performing calibrations, diagnostic tests, visual inspections, etc.

In an embodiment, vibration data resulting from a review severity unit may trigger vibration data collection and analysis to be performed as soon as possible. The review severity unit decision may result in sending a signal (e.g., a series of commands) to the relevant portion of the affected industrial machinery to configure data collection and routing functions and elements to repeat the vibration data collection and analysis again. The industrial machinery data collection control system may also be configured to initiate data collection from other sensors on the affected industrial machinery element. Similarly, comparable vibration sensor data from other similar industrial machinery may be collected and made available for comparative analysis, such as a reviewed vibration survey, to increase priority.

In embodiments, vibration data resulting in an immediate action severity unit may trigger scheduling of a service action on the affected part well in advance of the next scheduled maintenance of the portion of industrial machinery having the affected part, and may also result in escalating action (e.g., preventative, investigation, analysis, etc.) on the associated element. As an example, if vibration data on a motor indicates that action is imminent, vibration data collection, preventative maintenance action, calibration action, etc. may be initiated on the motor's drive shaft, the gearbox driven by the drive shaft, etc.

In embodiments, vibration data resulting in an immediate severity unit may be treated as a constructive approval to perform all necessary part replacements as soon as possible, thereby triggering the ordering of replacement parts, materials, etc., to perform one or more service actions on the industrial machine. Such a result may also trigger certain automated actions, such as taking the industrial machine out of service until service is performed, reducing the industrial machine's duty cycle, or reducing the industrial machine's operating cycle rate.

One embodiment of severity units applicable to vibrations over a wide vibration frequency range is representatively depicted in Figure 198. In the representative embodiment of Figure 198, five severity units correspond to three vibration spectrum regions depicted in Figure 197, specifically vibration frequencies below 1200 cpm, vibration frequencies between 1200 cpm and 18000 cpm, and vibration frequencies above 18000 cpm.

In embodiments, severity units are defined within each spectral region. For the spectral region below a low-end threshold (e.g., 1200 cpm), a vibration displacement of 2.5 mils peak-to-peak or less meets the criteria for an acceptable severity unit, between 2.5 and 50 indicates a monitor severity unit, between 5.0 and 10.0 indicates a review severity unit, a displacement between 10.0 and 16.6 mils indicates an immediate action severity unit, and a displacement greater than 16.6 mils triggers an immediate action severity unit. For the vibration frequency spectrum between 1200 cpm and 18,000 cpm, normal severity is characterized by a displacement of 0.15 inches per second peak (ipsp) or less, monitor between 0.15 and 0.3 ipsp, review between 0.3 and 0.6 ipsp, immediate action severity between 0.6 and 1.0 ipsp, and a vibration displacement rate greater than 1.0 ipsp triggers immediate action severity. For vibration frequency spectra above 18,000 cpm, acceptable severity indicates a vibration analysis peak of less than 2.5 gs, with severity units of 2.5 gs to 5.0 gs for monitoring, 5.0 gs to 10.0 gs for review, and 10.0 gs to 16.6 gs for immediate action, with immediate action indicated for vibrations producing forces greater than 16.6 gs.

Applications of the severity unit methods and systems described herein include use with a variety of machines operating at different speeds. However, the algorithm-based approach described herein can easily accommodate slower machines by effectively removing unnecessary computational complexity and other aspects associated with machine speed effects. In environments where different machines operate differently, such as raw data analysis and severity detection, increased communication bandwidth is required to support providing sufficient information to ensure robust severity determinations. Use of the severity unit methods and systems described herein significantly simplifies the data communication needs in such embodiments, thereby reducing communication bandwidth demands in such environments.

While this discussion of severity units has been directed to vibration data analysis and the like, the methods and systems for determining and detecting severity units can be applied to data sources other than vibration that can benefit from normalization for normal comparisons. In embodiments, actuarial data regarding the viability of specific pharmaceutical treatments for one or both genders can be normalized using the methods and systems described herein and applied to the general population. While addressing existing guidelines regarding severity, the methods and systems described herein may be used to extend them and generate algorithms that generate gender-neutral (gender-normalized) severity measurements.

In an embodiment, a method for predicting service events from vibration data may include a series of operational steps, including capturing vibration data from at least one vibration sensor positioned to capture vibrations of a portion of industrial machinery. The captured vibration data may be processed to determine at least one of a frequency, an amplitude, and a gravity of the captured vibration. A segment of a multi-segment vibration frequency spectrum bounded by the captured vibration may then be determined, for example, based on the determined frequency. Accordingly, calculation of vibration severity units for the captured vibration may be performed based on the determined segment and at least one of a peak amplitude and a gravity obtained from the vibration data. Furthermore, the method may include generating, in a predictive maintenance circuit, a signal for performing a maintenance action on the portion of industrial machinery based on the severity units.

In an embodiment, the segments are determined based on comparing the determined frequencies with upper and lower limit values of a middle segment of the multi-segment vibration frequency spectrum. A first segment of the multi-segment vibration frequency spectrum may include frequency values that are less than or equal to the lower limit value of the middle segment of the multi-segment vibration frequency spectrum. The lower limit of the middle segment of the multi-segment vibration frequency spectrum may be 1,200 kHz and the upper limit may be 18,000 kHz. In an embodiment, a second segment of the multi-segment vibration frequency spectrum may include determined frequency values that are greater than or equal to the upper limit value of the middle segment of the multi-segment vibration frequency spectrum.

In an embodiment, calculating the vibration severity units may include generating a severity value by multiplying one of a plurality of severity normalization parameters by a mid-severity limit value and mapping the vibration severity value to one of a plurality of severity unit ranges for the determined segment. A first severity normalization value of the plurality of severity normalization values is calculated by dividing the determined frequency by a low-end frequency value of a mid-segment of the multi-segment vibration frequency spectrum. A particular one of the plurality of severity normalization parameters includes the first severity normalization value when the determined frequency value is less than the low-end frequency value.

In an embodiment, the second severity normalization value of the plurality of normalization values is calculated by dividing the high-end frequency value of the mid-segment of the multi-segment vibration frequency spectrum by the determined frequency. A particular one of the plurality of severity normalization parameters includes the second severity normalization value when the determined frequency value is greater than the high-end frequency value.

For segments of the multi-segment vibration frequency spectrum, a first segment of the multi-segment vibration frequency spectrum is divided into multiple units of severity based on the determined vibration amplitude. A second segment of the multi-segment vibration frequency spectrum is divided into multiple units of severity based on the determined gravity.

In an embodiment, the vibration severity units are determined based on a peak displacement of a determined vibration amplitude for a determined vibration frequency within a first segment of the multi-segment vibration frequency spectrum. In one example, the vibration severity units are determined based on a determined vibration-induced gravity force for a determined vibration frequency within a second segment of the multi-segment vibration frequency spectrum.

In an embodiment, the part of the industrial machinery may be a moving part, a structural member supporting the moving part, a motor, a drive shaft, etc.

In an embodiment, a system for predicting service events from vibration data may include an industrial machine including at least one vibration sensor positioned to capture vibrations of a portion of the industrial machine. The system may further include a vibration analysis circuit in communication with the at least one vibration sensor and generating at least one of a frequency, a peak amplitude, and a gravity of the captured vibration. The system may further include a multi-segment vibration frequency spectrum structure that facilitates mapping the captured vibration to one vibration frequency segment of a plurality of vibration frequency segments. The system may also include a severity unit algorithm that receives the determined frequency of the vibration and the corresponding mapped segment and generates a severity value that maps to one of a plurality of severity units defined for the corresponding mapped segment. In an embodiment, the system may also include a signal generation circuit that receives one of the plurality of severity units and, based thereon, signals a predictive maintenance server to perform a corresponding maintenance action on the portion of the industrial machine.

In an embodiment, the system may calculate the vibration severity level via vibration severity calculation software. The vibration severity calculation software may be configured to substantially digitally perform one or more functions of the vibration analysis circuit, the multi-segment vibration frequency spectrum structure, and the severity unit algorithm, and may be configured to be executed by any general-purpose processor or other suitable machine. The vibration severity calculation software may be configured to receive an input of a signal from a vibration sensor. The signal may be a digital or analog signal and may include a vibration waveform, i.e., the captured vibration.

In embodiments, the vibration severity calculation software may digitally perform one or more of high-pass filtering, low-pass filtering, integration, and differentiation of a signal received from a vibration sensor to calculate vibration severity. The vibration severity calculation software may also generate at least one of a frequency, a peak amplitude, and a gravity of the vibration acquired from the vibration sensor. The vibration severity calculation software may map the captured vibration to one vibration frequency segment of a plurality of vibration frequency segments. The vibration severity calculation software may generate the severity value.
Based on the determined frequency of the vibration, the severity value is mapped to one of a plurality of severity units defined for the corresponding mapped segment.

In embodiments, the severity units may be output by the vibration severity calculation software to a user or analyst and/or one or more expert systems so that action can be taken based thereon. In some embodiments, the vibration severity calculation software receives one of the plurality of severity units and signals a predictive maintenance server to perform a corresponding maintenance action on the portion of the industrial machine from which the captured vibration was captured, where the corresponding maintenance action may be based on one of the plurality of severity units. The vibration severity calculation software may be implemented to calculate the vibration severity level instead of, or in addition to, one or more of the vibration analysis circuitry, the multi-segment vibration frequency spectrum structure, and the severity unit algorithm.

In embodiments, vibration-related data collected from sensors located on industrial machinery may include displacement, velocity, acceleration, and the like. Furthermore, velocity, acceleration, and other data may be calculated from raw collected data, such as displacement, collected over known time periods. Velocity may be based on counting detectable vibration events over a specific time period. Velocity may be independent of the magnitude or length of a displacement event. In embodiments, acceleration may be calculated as the rate of change of velocity measurements. In embodiments, acceleration may be generated from one or more acceleration sensors that detect the relative time of the start and end of a displacement in a specific direction, and based thereon, the acceleration of a part during vibration may be determined. Vibration data may be useful in determining whether a part is experiencing excessive vibration. Analyzing such vibration data to make a determination requires consideration of vibration aspects, such as frequency. As discussed herein, conventional vibration analysis approaches to determining the degree to which detected vibration is unacceptable require different evaluations of vibrations in different parts of the vibration spectrum. Novel approaches for normalizing the assessment of vibration effects across a broad range of the vibration spectrum, such as thresholds for vibrations likely to cause problems such as failure of a vibrating component, would be beneficial for predictive maintenance systems such as expert systems that seek to provide actionable information to machine owners and others.

In embodiments, severity units can facilitate normalization of vibration analysis for purposes of determining whether a detected vibration is unacceptable by eliminating, or at least obfuscating, the need to calculate multiple vibration measurements across a range of the vibration spectrum. By normalizing different vibration measurement units across the spectrum range, severity units, also referred to herein as action units, can facilitate application to a wide range of vibration analysis applications, including, but not limited to, industrial machinery vibration analysis, moving parts vibration analysis, vibration of complex mechanical systems, etc.

In embodiments, the system may normalize one or more severity units using an included (or accessible) severity normalization methodology. In some embodiments, the severity normalization methodology may perform an envelope analysis method. In embodiments, the severity normalization methodology may scan the stream of vibration severity units across multiple bands (e.g., 1 kHz to 40 kHz) with little overlap using a bandpass filter (e.g., a bandpass filter with a width of 500 Hz). The severity normalization method may include processing each of the scanned bands, for example, via harmonic filtering, and analyzing the road speed and its electrical signal to determine an envelope. This allows the overall AC and DC values of the envelope to be calculated, and an optimal region for the bandpass filter position can be determined based on the AC and DC values. In these examples, the AC values may be used by the severity normalization methodology to detect modulation of bearing defect frequencies. In a further example, the DC value may be used to determine issues such as lack of lubrication. In these examples, the determined bandpass filter position may be referred to as the envelope spectrum. In embodiments, the severity normalization methodology may overlay envelope spectra from different severity units at different frequencies. In these examples, the severity normalization methodology may be configured to be executed by any general-purpose processor or other suitable machine.

In embodiments, the severity normalization methodology may include applying a waveform analysis process, such as overall, true peak, peak-to-peak, crest factor, K factor, or the product of crest factor and amplitude. In embodiments, the severity normalization methodology may further include applying a statistical stability measurement technique to the vibration waveform within the envelope spectrum. In these examples, the waveform may be labeled according to the results of the waveform analysis process. In embodiments, the severity normalization methodology may perform phase stability spectrum analysis by marking the time trend of the phase fluctuations of the vibration waveform in the stream of severity units. In embodiments, the severity normalization methodology may also perform phase stability spectrum analysis by directly marking the trend of the phase fluctuations of the vibration waveform over time. In doing so, the severity normalization methodology may include qualification of the stability of the phase fluctuations. In embodiments, the severity normalization methodology may perform amplitude stability spectrum analysis (as opposed to phase stability spectrum analysis) by directly marking the trend of the amplitude fluctuations of the stream of severity units and/or the vibration waveform over time. In embodiments, amplitude stability spectrum analysis may include qualitative enhancement of the stability of phase fluctuations. In embodiments, severity normalization methodologies may include generating histograms of phase, amplitude, and other characteristics of the vibration waveform for analysis by a user, analyst, and/or expert system.

In an embodiment, Figure 199 shows a vibration severity graph with frequency plotted along the horizontal axis. The graph has two vertical axes: one representing traditional vibration measurements that are frequency-dependent, and the other representing severity units that are frequency-independent. Line 30802, the traditional vibration index, has three segments, indicating safe vibration limits in three frequency ranges. Line 30804, the severity units, shows a single horizontal line indicating safe vibration-severity limits across all frequency ranges. Traditional vibration analysis scales the vibration derivative with frequency. Vibration derivatives below line 30802 may represent acceptable levels of vibration. Similarly, vibration derivatives above 30802 represent unacceptable levels of vibration. However, the functions required to determine whether a vibration sample falls above or below line 30802 are different for different vibration frequencies. Knee values 30806 and 30808 may typically be aligned to vibration frequencies of 1,200 CPM and 18,000 CPM, as described herein, although the type of material, the type of vibrating object, and other factors may further affect the function performed. In contrast, the methods and systems described herein for generating and using severity units and/or action units may be adapted to generate normalized limit values for vibration severity, represented by line 30804. Severity/action unit-based calculated vibration measurements below line 30804 may indicate safe vibration limits, while severity/action unit-based measurements above line 30804 may indicate unacceptable levels of vibration. Expert systems, such as the [unclear text - likely a misreading] system, are used to predict maintenance for industrial machinery. For example, the severity/action units of industrial machinery can be applied using a simple comparison function that compares the severity/action units to a severity/action unit threshold. Unit values below the threshold have little or no impact on predicting the need for maintenance. If the unit value is at or above the threshold, the impact on the prediction of the need for maintenance is substantial and may directly trigger the prediction of a maintenance event. The results of comparing the unit value with the threshold can also be used to adjust the weighting of other factors processed to predict a maintenance event. Predicting the need for maintenance of industrial machinery through the weighting of the severity/action units of other factors can combine sub-threshold or marginal results of vibration and other factors into the prediction of industrial machinery maintenance.

In embodiments, other signal processing techniques may be used to calculate severity units. These other signal processing techniques may generate a normalized action unit representation of the sensed vibration data. In embodiments, other frequency thresholds may be used with different techniques and may depend on various factors of the vibrated machine component, such as, but not limited to, the severity peak vibration level, the gas pulse frequency peak level, the machine component type, and bearing failure frequency. In embodiments, the normalized severity/action units may be weighted based on the component type for applications such as hammer mills, crushers, high horsepower prime movers, and soft foundations (e.g., spring isolation). While examples such as FIG. 178 herein use a low threshold of 1200 Hz and a high threshold of 18,000 Hz, other values, such as a low threshold of 500 Hz and a high threshold of 5,000 Hz, may also be used. The relationship between the low and high thresholds for a particular application may be determined based on the material, operating frequency, severity sensitivity, and the like.

For example, a roller bearing defect that causes vibration events that are dependent on the machine cycle (e.g., an impact when the roller bearing strikes the defect). Once the vibration events detected by enveloping are captured, they can be processed to obtain peak values that can be mapped to a frequency spectrum of severity units. In this way, vibration events detected in an envelope filtered by RMS or a similar time-average calculation can be mapped to a frequency chart of severity/action units.

In embodiments, the severity of various components in an industrial machine or portion thereof (e.g., a gearbox, etc.) can be aggregated into an overall severity for the machine/portion. One approach is to generate an aggregated severity value by summing all severity unit calculations for one or more components of the machine/portion. Another approach is to calculate an overall average severity for the machine/portion, such as by determining the average of the generated severity values. Other approaches to calculating the overall severity for a machine/portion can include weighting some of the severity values of the individual components, etc.

In embodiments, calculation of severity units for industrial machinery components, such as moving parts of the industrial machinery (e.g., gears, shafts, motors, heads, etc.), may be mapped onto a severity graph, such as depicted in FIG. 198 and described herein, such as by identifying in the map a correspondence between spectral peak levels and severity level scales. The mapped severity levels may be determined based on the identification. A graphical element may be assigned to each severity level so that the severity of the industrial machinery components can be presented pictorially, for example, as an overlay on an image, drawing, or other representation showing the individual components of the industrial machinery. FIG. 200 illustrates a block diagram representing a component 30902 of industrial machinery 30900 having a severity unit level indicated by a graphical overlay element 30904. In embodiments, the overlay image 30904' may be presented in a graphical user interface that can facilitate data discovery by a user interacting with the overlay, for example, by touching or otherwise selecting one of the graphical overlay elements 30904. Such a scenario is illustrated in FIG. 200. The component severity and related information in the pop-up window 30908 is visualized in response to a user selecting a graphical overlay element 30904. In an embodiment, the graphical overlay element 30904 may represent a composite severity for a group of components, such as a gearbox, a motor assembly, etc. When the composite graphical overlay element is selected, a second image, such as details of a gearbox, etc., may be visualized in the graphical user interface, allowing the user to dive into further details for the component, etc., within the assembly.

In embodiments, the severity units may be presented in the context of a Master Action Unit Nomogram (MAUN). In embodiments, vibration data may be collected in at least three dimensions, and thus a three-dimensional MAUN may be generated that presents the vibration data or severity units in action in a three-dimensional presentation.

In embodiments, raw vibration data may be provided to a predictive maintenance system, such as a system that applies techniques such as machine learning to determine acceptable vibration thresholds across a spectrum. However, learning from this raw information may require environmental information and vibration analysis engineering, resulting in highly complex maintenance prediction operations. Severity Units, such as those described herein, including MAUNs, may be provided to the predictive maintenance system to simplify learning by more efficiently matching raw vibration data to normalized vibration severity measures (e.g., Severity Units, etc.). The use of Severity Units, etc., may further reduce the complexity of filtering and evaluation for the predictive maintenance system, as at least some of these operations may be incorporated into the generation of severity unit measurements from the raw vibration data.

In embodiments, learnings from such systems may be applied as feedback to a severity unit calculation function, such as one executed locally by a data collection agent, a local network processor, or the like. This feedback may be applied, for example, to a threshold refinement algorithm that adjusts the determination of severity levels (e.g., thresholds) from raw vibration data, thereby allowing vibration thresholds to be tailored to local conditions, etc. Such feedback may also be useful in the process of determining which of multiple data processing techniques/algorithms (e.g., generating severity and/or action units, etc.) is likely to produce a more accurate MAUN measurement. Doing so may reduce processing complexity and data storage demands, which may be desirable to reduce the overall cost and sophistication of data collection devices, etc. that may generate severity unit data.

In embodiments, predictive maintenance methods and systems may be applied to industrial machines, such as rotating equipment machines. Exemplary rotating equipment machines that may use the predictive maintenance methods and systems described herein include, but are not limited to, drills, boring heads, polishers, motors, turbines, gearboxes, transmissions, rotary vibratory adapters, drive shafts, computer numerically controlled (CNC) routers, lathes, mills, grinders, centrifuges, combustion engines, compressors, reciprocating engines, pumps, fans, blowers, generators, and the like. Exemplary rotating equipment manufacturers, as well as interested parties such as testing services, parts manufacturers, and subcontractors, may have access to technical data about such equipment on a machine-by-machine basis. Additionally, information about machines, subassemblies, individual components, accessories, rotating integration parts, and the like may include design parameters, test specifications, operating specifications, product revisions, and the like. This information and related information may apply to one or more deployed machines, such as a specific serial number, an industrial machine product line, a given production version, or a production run. Available machine information may cover aspects of equipment related to one or more rotating components, such as the number of gear teeth on one or more gears (e.g., gearboxes such as helical gearboxes, worm reduction gearboxes, planetary gearboxes, and power transfer gear sets), the number of rotor bars on a motor (e.g., squirrel cage rotors and wound rotor bars, such as in synchronous motors), and the RPM rate of a rotating component. Additionally, information may be available and utilized for planning and executing predictive maintenance events for industrial machinery, such as roller bearing-based systems, including, but not limited to, data on: number of roller balls, number of balls, number of balls/rollers, ball-roller contact angle(s), race dimensions (e.g., inner and outer race dimensions), number of vanes, number of flutes, and mode shapes (e.g., relative displacement).

Providing access to rotating equipment information as illustratively described herein for predictive maintenance processing, such as predictive maintenance analysis circuits, may be automated by a range of means, including, but not limited to: (ii) updating a non-volatile storage element integral with the machine with relevant rotating component information after deployment or as part of deployment, such as during deployment validation activities; (iii) storing data representative of rotating equipment specifications, measurements, production tests, etc., in a network-accessible data storage facility (e.g., (iii) a cloud-based data storage facility indexed by at least one identifier of a part, subsystem, machine, etc., such as a serial number or set thereof that associates a part (e.g., a roller bearing assembly) with a machine/deployment; and (iv) a data storage facility accessible from a network with at least a subset of the information stored in the non-volatile data storage facility deployed with the machine in (i) or a combination of (ii) and (iii) (e.g., machine serial number, rotating equipment component serial number, etc., that can be used to identify pertinent information for the deployed machine). To address commercial confidentiality issues, some and/or all of the information accessible to the network may be protected by security measures such as passwords. Similarly, information stored on non-volatile storage devices such as RFID tags located on industrial machines may include non-confidential information accessible to third parties (e.g., serial number, model number) and confidential information that requires explicit authentication for access (e.g., performance data, date of last failure, prediction of next failure, failure rate of the machine or its superset).

To access such rotating equipment information, a mobile data collection device, such as a mobile phone equipped with data collection circuitry that interacts with nearby industrial machinery to access at least the non-sensitive portion of the RFID tag, can be used. Once the data collection circuitry is activated to communicate with the industrial machinery, predictive maintenance-related information (e.g., information as described herein) about the nearby industrial machinery can be collected either directly from the RFID or by applying indexing (e.g., URLs) information collected from the RFID, and the appropriate information can be accessed from a networked server hosting the indexing information. As an example, publicly accessible URLs and confidential machine serial numbers can be obtained from the RFID by a remote data collector. The data collector can then provide the obtained information to a predictive maintenance system, which can then apply the obtained information to a web query to the URL, etc.

However, predictive maintenance functions requiring information not available at the time of collection (e.g., information that must be obtained over the Internet) may be performed at a later time, such as when the data collection circuitry has access to the Internet. In embodiments, predictive maintenance event analysis may be performed on an appropriately equipped data collection device (e.g., a mobile device with sufficient processing power, data storage, etc.), or on a server, such as a network server, or a combination thereof. Predictive maintenance event analysis may also be performed by a computing device accessible over a network other than the Internet, such as a local area network accessible by a mobile data collection device while in proximity to the industrial machine. Such a site-specific local area network may facilitate access to the rotating part-related information of the industrial machine over the Internet, etc., with appropriate authentication information presented by the mobile data collector.

In embodiments, rotor bar defects or weakening may be a precursor to secondary degradation that could lead to more costly repairs, such as rotor core replacement. Thus, detecting broken or weakened rotor bars can minimize maintenance and repair costs. Knowing the number of rotor bars can be a factor in determining when to perform maintenance and/or service on one or more rotor bars. As an example, by applying the rotor bar failure rate to a formula that predicts when a rotor bar will fail, knowing the number of rotor bars on a given machine, among other factors such as cycle rate and age, can facilitate predicting when service and/or testing of a rotor bar-based system might be beneficial. A predictive maintenance circuit that predicts maintenance events, such as for industrial machinery, can predict maintenance for a machine with a high number of rotor bars earlier than for a comparable machine with a low number of rotor bars.

In embodiments, predicting maintenance events for a machine, such as a rotating equipment-based machine, may be adapted from predicted maintenance events for similar machines while considering the number of gear teeth on the machine and similar machines. For example, an aspect of predicting a maintenance event that may be affected by the number of gear teeth may be the timing of the event. In one example, a machine with more gear teeth than a similar machine may suggest predicting the need to maintain the machine with more gear teeth earlier than a similar machine. In embodiments, predicting maintenance events for moving parts of a machine, such as rotating equipment-based parts, may be adapted from predictions of maintenance events for similar parts of the same machine or similar machines while considering the number of gear teeth on the machine and similar parts or machines. In embodiments, predicting maintenance events for rotating parts of a machine, such as rotating parts of a rotating equipment-based machine, may be adapted from predicted maintenance events for similar rotating parts on the same or similar machines while considering the number of gear teeth on the machine and similar parts or machines. In embodiments, predicting maintenance events for a maintenance event ...
The predicted maintenance events are adapted from predictions for similar parts of the same or similar machines, taking into account the number of teeth on gears of the machines and similar parts or machines. In an embodiment, predictions of maintenance events for components of machines that include multi-tooth gears, such as rotating equipment-based components, may be adapted from predictions of maintenance events for similar components of the same or similar machines, taking into account the number of teeth on gears of the machines and similar parts or machines.

In an embodiment, predicting a maintenance event for rotating equipment may be a function of predictive maintenance circuitry responding to, for example, the number of gear teeth on a rotatable component of the machine, whereby the predictive maintenance circuitry generates a maintenance event alert (e.g., a signal that facilitates triggering at least an automated portion of the maintenance event, such as ordering a replacement part). In an embodiment, the predictive maintenance circuitry may process operational data for the machine or a rotating portion thereof and/or process failure data for particular rotating components of the machine or similar machines, thereby incorporating contextual information about the particular machine into the prediction along with static information about the machine, such as the number of gear teeth.

In an embodiment, the number of gear teeth of a service component, such as an RFID component, embedded in an industrial machine, such as rotating equipment, may be input to a machine learning circuit, which may process the input along with service information for similar service components across multiple industrial machines. The machine learning circuit may generate a predictive maintenance adjustment factor that can be applied to the predictive maintenance circuit processing, thereby generating machine-specific predictive maintenance events.

In an embodiment, predicting a maintenance event for rotating equipment may be a function of the predictive maintenance circuitry responding to, for example, a motor rotor bar count of a rotatable component of the machine, whereby the predictive maintenance circuitry generates a maintenance event alert. In an embodiment, a motor rotor bar count of a service component, such as from an RFID component integrated with or embedded in an industrial machine, such as rotating equipment, may be input to a machine learning circuitry that processes the input along with service information for similar service components across multiple industrial machines. The machine learning circuitry can generate a predictive maintenance adjustment factor that can be applied to the predictive maintenance circuitry processing, thereby generating a machine-specific predictive maintenance event.

In an embodiment, predicting a maintenance event for rotating equipment may be a function of the predictive maintenance circuitry responding to data representative of revolutions per minute, e.g., of an internal rotatable component of a machine for which the predictive maintenance circuitry generates a maintenance event alert. In an embodiment, RPM data for a service component, such as from an RFID component integrated with or embedded in an industrial machine, such as rotating equipment, may be input to a machine learning circuitry that processes the input along with service information for similar service components across multiple industrial machines. The machine learning circuitry can generate a predictive maintenance adjustment factor that can be applied to the predictive maintenance circuitry processing, thereby generating a machine-specific predictive maintenance event.

In embodiments, predicting a maintenance event for a rotating equipment may be a function of the predictive maintenance circuit responding to data representative of roller bearing aspects of a rotatable component of a machine, such as number of balls per roller, ball-to-roller contact angle, inner race dimensions, outer race dimensions, number of vanes, number of flutes, mode shape information, etc., for which the predictive maintenance circuit generates a maintenance event alert. In embodiments, roller bearing aspect data for a service component, such as from an RFID component integrated with or embedded in an industrial machine such as a rotating equipment, may be input to the machine learning circuit, which may process the input along with service information for similar service components across multiple industrial machines. The machine learning circuit may generate predictive maintenance adjustment factors applicable to the predictive maintenance circuit processing, thereby generating machine-specific predictive maintenance events. In embodiments, the predictive maintenance event may be selected from a list of maintenance events including, but not limited to, part replacement, machine subsystem replacement, calibration, deep data collection, machine service, machine shutdown, preventive maintenance, etc.

In an embodiment, at least one aspect of the roller bearing service component may be stored in a portion of a digital data structure of roller bearing component production information obtained via an RFID component located with the roller bearing component on the industrial machine. In an embodiment, the portion of the digital data may be specific to the industrial machine on which the roller bearing component is located. In an embodiment, the portion of the digital data structure may be retrieved by accessing a network location retrieved from the RFID component and may be further indexed by a machine-specific identifier retrieved from the RFID component. In an embodiment, the network location may be accessed via a WiFi interface of the data collection device while the data collection device is in short-range wireless communication with the RFID component. Further, in an embodiment, the network location may be accessed via a WiFi interface of the data collection device when the data collection device is no longer in short-range wireless communication with the RFID component. In an embodiment, the portion of the digital data structure may be retrieved by providing a machine-specific key obtained from the RFID component to an application programming interface function of a predictive maintenance system that facilitates access to roller bearing component production information stored external to the industrial machine. In an embodiment, the portion of the digital data structure may include production information retrieved from the RFID component. In an embodiment, the circuit predicts a maintenance event for the roller bearing component in response to retrieving a portion of the digital data structure from the RFID component, independent of network connectivity of a processor executing the circuit. In a further embodiment, the data collection device may include predictive maintenance circuitry that predicts a maintenance event for the roller bearing component in response to retrieving a portion of the digital data structure from the RFID component, independent of network connectivity of the data collection device.

Referring to FIG. 201, a diagram of a data structure 31000 for storing rotating part-related information for use in predicting maintenance events for a portion of industrial machinery associated with a rotating part is depicted. The rotating parts 31002 may include specific gears of the industrial machinery, gears in a gearbox, shafts, roller bearings, etc. The parameters 31004 of each rotating part may include, but are not limited to, number of teeth, number of gears, type of gear in a gearbox, number of rotations, number of balls, race size, number of vanes, etc. Values 31006 for each rotating part and parameter combination may be stored in the data structure 31000. This data structure may be representative of a portion of the rotating part data stored on RFID components deployed on the industrial machinery. The number of entries in the data structure, the type of data within the data structure, and the format of the values (e.g., decimal, hexadecimal, etc.) may vary as needed to support the storage of rotating part-related configuration, production, and test information.

Referring to FIG. 202, a flowchart is depicted illustrating a method for predicting maintenance events for rotating components, such as gears, motors, and roller bearings, based on a stream of sensed rotating component health data and component-specific configuration information, such as gear tooth count, roller bearing/chase dimensions, and motor rotor bar count. Method 3100 may include step 31102 of generating a stream of rotating component health data, such as gears, motors, and roller bearings. Method 3100 may continue with step 31104 of accessing rotating component configuration information, such as from an RFID tag deployed with the industrial machine hosting the rotating component and/or from a network-accessible data storage facility. Method 3100 may continue with step 31106 of predicting at least one of a gear-, motor-, and/or roller bearing-related maintenance event/action/possibility. Method 3100 may continue with step 31108 of generating predicted maintenance action instructions to maintain, repair, and/or replace the rotating component for which a maintenance action/event is predicted. Method 3100 may continue with step 31110 of validating the maintenance action(s) taken based on the rotating component based on service data of the maintenance event, which data may be received by a processor, such as a networked server, from the industrial machine, etc.

The present disclosure also relates to an Industrial Internet of Things (IIoT) system configured to address the above-identified needs and other needs. More particularly, the present disclosure is directed to an IIoT platform optimized to improve data collection, storage, processing, sharing, and utilization in industrial environments. The IIoT platform can be arranged into multiple distinct data processing layers in a layered topology. This layered topology facilitates independent optimization of each data processing layer. For example, the layers can include a data collection/monitoring layer, a data storage layer, an adaptive intelligence layer, and an application platform layer. Each layer interfaces with other layers via a microservices architecture, allowing outputs, events, results, and the like to be exchanged and shared between layers. In this way, as described above, each data processing layer can be independently optimized for a specific function (storage, monitoring, intelligence development, applications), while the platform as a whole allows for sharing and optimization between layers.

In one aspect, the IIoT platform can constitute a multi-application IIoT application platform that shares a common infrastructure that facilitates the development and utilization of intelligence. The common infrastructure provides data sharing between applications and tiers, including the sharing of events, outputs, and results, to facilitate coordinated optimization of the IIoT platform (e.g., via machine learning). The common data processing infrastructure enables efficient monitoring of industrial entities and applications, as well as efficient sharing of such collected data, and can provide an environment for rapid development and deployment of intelligence solutions. The common infrastructure can also provide a consistent user experience across multiple applications related to different industrial processes.

In another aspect, the IIoT platform may include an adaptive intelligence layer that provides adaptive intelligence solutions to various components within the IIoT platform. The adaptive intelligence layer may include a set of data processing, artificial intelligence, and computing systems that develop, improve, or adapt processes of the IIoT platform. The adaptive intelligence layer utilizes data collected, generated, stored, or otherwise obtained by the IIoT platform. The data may relate to various entities in an industrial environment, including, but not limited to, machines, devices, processes, workflows, and combinations thereof. The adaptive intelligence layer may include an adaptive edge compute management system that adaptively manages edge compute, storage, and processing in the IIoT system. Additionally or alternatively, the adaptive intelligence layer may include a robotic process automation system that develops and deploys automation capabilities for at least one of multiple industrial entities within the IIoT system. Furthermore, the adaptive intelligence layer may include a set of protocol adapters that facilitate adaptive protocol conversion of data within the IIoT system. The adaptive intelligence layer may additionally or alternatively include an edge intelligence system that adapts edge computing resources. For example, the edge intelligence system may adapt edge computing resources so that the computing resources are utilized in an optimized manner based on various constraints (speed, cost, etc.).

In a further aspect, the adaptive intelligence layer can include an adaptive networking system that adapts network communications in the IIoT system. In another aspect, the adaptive intelligence layer can include a set of state and event managers that adapt processes within the IIoT system based on state and event data. Opportunity mining systems (including, and sometimes referred to herein as, a set of opportunity miners) can also be included in the adaptive intelligence layer. The set of opportunity miners can identify opportunities for automation or increased intelligence in the IIoT system. Finally, the adaptive intelligence layer can include a set of artificial intelligence systems that develop, improve, or adapt processes in the IIoT system.

As described above, the robotic process automation system develops and deploys automation capabilities for at least one of multiple industrial entities within an IIoT system. The robotic process automation system may develop such capabilities for each process, workflow, etc. managed, controlled, or mediated by each of the applications within the multi-application IIoT application platform. Moreover, the robotic process automation system may develop such capabilities for a combination of applications. Additionally or alternatively, the robotic process automation system may develop and deploy automation capabilities for various industrial processes, including, but not limited to, energy production processes, manufacturing processes, transportation processes, storage processes, refining processes, distillation processes, fluid processing processes, energy storage processes, chemical processes, petrochemical processes, semiconductor processes, gas production processes, maintenance processes, service processes, repair processes, and supply chain processes.

Robotic process automation systems can develop and deploy automation capabilities based on oversight/monitoring of software interactions (e.g., by workers using various software interfaces), hardware interactions (e.g., by watching workers actually interact with or use machines, equipment, tools, etc.), or a combination thereof. Additionally, robotic process automation systems can utilize data collected, generated, or otherwise obtained from or about IIoT platforms to support their activities.

As briefly mentioned above, a set of protocol adapters facilitates adaptive protocol conversion of data within an IIoT system. For example, the set of protocol adapters can facilitate adaptive in-flight data protocol conversion, communication network protocol conversion, and link (e.g., gateways, routers, switches). In some aspects, this includes recognizing appropriate protocols used by each of the data processing layers and various components and systems in each industrial environment so that data can be moved, stored, and processed regardless of the native storage format, processing format, or communication system protocol. In some aspects, the set of protocol adapters can be self-organizing. The self-organizing protocol adapter can facilitate adaptive in-flight data protocol conversion of data by selecting at least one interface from a set of possible interfaces between communicating nodes. Alternatively or additionally, the self-organizing protocol adapter can facilitate adaptive in-flight data protocol conversion of data by selecting an appropriate protocol for the data, and in some aspects can also convert the data to conform to the selected appropriate protocol.

As described above, the adaptive intelligent systems layer can include an opportunity mining system that uses data to identify opportunities for increased automation within the platform. The opportunity mining system can be configured to collect information about a set of industrial environments and industrial entities to help identify and prioritize opportunities for increased automation and/or intelligence within the platform and in the IIoT system. For example, the opportunity mining system can use sensors (e.g., cameras or wearables) or other systems to observe clusters of workers by time, type, or location to identify labor-intensive areas or processes. Additionally, the opportunity mining system can characterize the degree of domain-specific or entity-specific knowledge or expertise required to perform an action, use a program, operate a machine, etc., by observing the identity, qualifications, and experience of workers involved in a given process. In some implementations, the opportunity mining system can also include a system that allows developers to solicit or specify useful information (e.g., a video showing an expert doing something) and offers compensation/reward for providing the specified information.

In certain aspects, the adaptive intelligent systems layer can include an edge intelligence system that adapts edge computing resources. The edge intelligence system can adaptively manage "edge" computation, storage, and processing, such as by varying where data is stored and processed (e.g., in the application of At) between on-device storage, local systems, networks, and the cloud. The edge intelligence system can enable and facilitate the dynamic definition of what constitutes "edge" for a given application, device, system, etc. Additionally, the edge intelligence system enables multi-application-aware adaptation of edge computation, such as by considering quality of service, latency requirements, congestion, cost, and other factors.

In another aspect, the industrial entity-oriented data storage system layer can include at least one geofenced virtual asset tag associated with a specific industrial entity among multiple industrial entities in the IIoT system. The at least one geofenced virtual asset tag can be configured as a data structure containing entity data related to the specific industrial entity and linked to the proximity of the specific industrial entity. Essentially, the geofenced virtual asset tag restricts access as if the tag were physically located on the asset. IIoT devices within the geofence can recognize the presence of a reader device (e.g., by recognizing an interrogation signal) and use it to communicate with the geofenced virtual asset tag, e.g., with the help of a protocol adapter. Furthermore, in some aspects, IIoT devices can function as decentralized blockchain nodes, e.g., for verifying enchained data (e.g., via various consensus protocols) including transaction history for maintenance, repair, and service. IIoT devices within the geofence can collectively verify the location and identity of fixed assets, e.g., in a neighbor-verifies-other-neighbor configuration.

Referring to FIG. 203, a platform 34900 for facilitating the development of intelligence in an Industrial Internet of Things (IIoT) system is illustrated, including a set of systems, applications, processes, modules, services, layers, devices, components, machines, products, subsystems, interfaces, connections, and other elements that work in concert to enable intelligent management of a set of industrial entities 34930 that may be part of, integrated with, linked to, or operated by the platform 34900. The industrial entities 34930 may include any of a wide variety of assets, systems, devices, machines, facilities, individuals, or other entities referred to throughout this disclosure or in the documents incorporated by reference herein, such as, but not limited to, industrial machines 34952 and their components (such as factory components, power generation machines, turbines, motors, reactors, fluid handling systems, capacitors, fans, software components, hardware components, electrical components, physical components, etc.), industrial processes 34950 (such as power production processes, software processes (including applications, programs, services, etc.)), factory production processes, manufacturing processes (such as semiconductor manufacturing processes, chemical manufacturing processes, petroleum production processes, biological manufacturing processes, service, maintenance, and repair processes, diagnostic processes, security processes, safety processes, etc.), wearable and portable devices. 34948 (e.g., mobile phones, tablets, industrial-specific portable devices, data collectors (including mobile data collectors), sensor-based devices, watches, glasses, hearables, head-worn devices, wearable devices, armbands, bracelets, neck-worn devices, AR/VR devices, headphones), workers 34944 (factory workers), workers 34944 (factory workers, maintenance and service personnel, supervisors, engineers, floor managers, warehouse workers, inspectors, fuel personnel, material handlers, process supervisors, security personnel, safety personnel), robotic systems 34942 (e.g., physical robots, collaborative robots ("cobots"), software bots), and operating facilities 34940 (e.g., power production facilities, refineries, assembly facilities, manufacturing facilities, warehouse facilities, plants, factories, mining facilities, power extraction facilities, Construction sites, exploration sites, drilling sites, harvesting sites, etc. These facilities include, but are not limited to, Storage and Warehousing Facilities IP138 (facilities for storing inventory, parts, packaging materials, goods, products, machinery, equipment, etc.), Transportation Facilities 34934 (facilities such as ports, depots, hangars, transportation equipment, vehicles, docks, loading bays, and assembly lines for moving goods, parts, machinery, raw materials, etc.), and Manufacturing Facilities 34932 (facilities for manufacturing, assembling, refining, finishing, packaging, or otherwise producing a variety of goods).

In embodiments, the platform 34900 may include multiple data processing layers 34908, each configured to provide a set of capabilities that facilitate the development and deployment of intelligence (e.g., to facilitate automation, machine learning, artificial intelligence applications, intelligent transactions, state management, event management, and process management) for a wide variety of industrial applications and end uses. In some implementations, the data processing layers 34908 include an industrial monitoring system layer 34906, an industrial entity-oriented data storage system layer 34910 (sometimes referred to herein as simply the data storage layer 34910 for convenience), an adaptive intelligent system layer 34904, and an industrial management application platform layer 34902. Each of the data processing layers 34908 may include various services, programs, applications, workflows, systems, components, and modules, as further described herein and in documents incorporated by reference. In particular implementations, each of the data processing tiers 34908 (and optionally the platform 3490 as a whole) is configured so that one or more of its elements are accessible as services by other tiers 34908 or other systems, for example as a Platform-as-a-Service deployed on a set of cloud infrastructure components in a microservices architecture. For example, the data processing layer 34908 may have a set of interfaces 34980 (e.g., application programming interfaces (APIs), brokers, services, connectors, wired or wireless communication links, ports, human-accessible interfaces, software interfaces, etc.) that allow data to be exchanged between the data processing layer 34908 and other layers, systems, or subsystems of the platform 3490, and may also include interfaces 34980 with other systems (e.g., industrial entities 34930 or external systems, cloud-based or on-premise enterprise systems (e.g., accounting systems, resource management systems, customer relationship management (CRM) systems, supply chain management systems, etc.)). Each of the data processing layers 34908 may include a set of services (e.g., microservices) for data processing, including facilities for data extraction, transformation, and loading, facilities for data cleansing and deduplication, facilities for data normalization, facilities for data synchronization, facilities for data security, facilities for computation (e.g., for performing predefined computational operations on data streams and providing output streams), facilities for compression and decompression, and facilities for analytics (e.g., for providing automated production of data visualizations).

In various aspects, each data handling layer 34908 has a set of interfaces 34980 (e.g., application programming interfaces or "APIs") for automating data exchange with each of the other data handling layers 34908. In aspects, the data handling layers 34908 are configured in a topology that facilitates the collection and distribution of shared data across multiple applications and uses within the platform 3490 by the industrial monitoring system layer 34906. The industrial monitoring system layer 34906 can include various data collection and management systems 34918 (referred to in some aspects for convenience as data collection systems 34918) for collecting and organizing data collected from or about the industrial entities 34930, as well as data collected from or about the various data processing layers 34908 or their services and/or components.

For example, a stream of physiological data from a wearable device worn by a worker 34944 on a factory floor can be distributed via the industrial monitoring system layer 34906 to multiple different applications in the industrial management application platform layer 34902, such as an application that facilitates monitoring the worker's health and an application that facilitates operational efficiency. In an aspect, the industrial monitoring system layer 34906 facilitates the alignment (e.g., time synchronization, normalization) of data collected regarding one or more industrial entities 34930. For example, one or more collected video streams of a worker 34944 in an industrial environment, such as from a set of camera-enabled IoT devices, may be aligned to a common clock so that the relative timing of the set of videos can be understood by systems that may process the video, such as a machine learning system operating based on images within the video, changes between images in different frames of the video, etc. In such an example, the industrial monitoring system layer 34906 can further align the collection of video with other data, such as streams of data from wearable devices, streams of data generated by industrial systems (such as on-board diagnostic systems, telematics systems, and various other sensors), streams of data collected by mobile data collectors, and other data or data streams that are sensed, generated, or otherwise obtained. Configuring the industrial monitoring system layer 34906 as a common platform (or set of microservices) accessed across many applications can dramatically reduce the number of interconnections an enterprise needs to have in order to have a growing set of applications monitoring the growing number of IoT devices and other systems and devices under their control.

In an aspect, the data processing layer 34908, via the industry entity-oriented data storage system layer 34910 (sometimes referred to herein simply as the storage layer 34910 for convenience), is configured in a topology that facilitates shared or common data storage across multiple applications and uses of the platform 3490. For example, various data collected about the industry entities 34930, as well as data generated by other data processing layer 34908 services, applications, programs, etc., may be stored in the industry entity-oriented data storage system layer 34910 such that any of the various data processing layer 34908 services, applications, programs, etc., can access a common data source. This may facilitate a dramatic reduction in the amount of data storage required to process vast amounts of data by or about the industry entities 34930 in the platform 3490. For example, a supply chain management application (e.g., for ordering replacement parts) in the industrial management application platform layer 34902 may access the same data set of which parts have been replaced for a set of machines as a predictive maintenance application used to predict whether a machine is likely to need repair. In aspects, the industrial entity-oriented data storage system layer 34910 may provide an extremely rich environment for the collection of data that can be used to extract features or inputs for an intelligent system, such as an expert system, an artificial intelligence system, a robotic process automation system, a machine learning system, a deep learning system, a supervised learning system, or any other intelligent system disclosed throughout this disclosure and the documents incorporated by reference herein. As a result, each application in the industrial management application platform layer 34902 and each adaptive intelligent system in the adaptive intelligent systems layer 34904 can benefit from data collected or generated by or for each other application.

A wide range of data types may be stored in storage layer 34910 using a variety of storage media and data storage types and formats, including: asset and facility data 34920 (including asset identity data, operational data, transaction data, event data, status data, workflow data, maintenance data, and other data), worker data 34922 (including identity data, role data, task data, workflow data, health data, performance data, quality data, and other data). Event Data 34924 (including data related to process events, financial events, output events, input events, state change events, operational events, repair events, maintenance events, service events, damage events, injury events, replacement events, refueling events, charging events, and supply events), Claims Data 34954 (including data related to insurance claims, such as business interruption insurance, product liability insurance, insurance for goods, facilities, and equipment, flood insurance, and insurance for contract-related risks. Data related to product liability, general liability, workers' compensation, and personal injury claims, and claims data related to contracts, such as supply contract performance claims, product delivery requirements, warranty claims, indemnity claims, energy production requirements, delivery requirements, timing requirements, milestones, and key performance indicators), Production Data 34958 (such as data related to energy production from databases of utility companies and independent service organizations that maintain energy infrastructure, data related to manufacturing output, and data related to the output of mining and energy extraction facilities, and drilling and pipeline facilities), and Supply Chain Data 34960 (such as data related to items supplied, amounts, prices, deliveries, sources, routes, customs information, and other aspects of the supply chain).

In aspects, the data processing layer 34908 is configured in a topology that facilitates shared adaptive capabilities, which may be provided, managed, mediated, etc., by one or more of a set of services, components, programs, systems, or capabilities in the adaptive intelligence system layer 34904, conveniently referred to herein as the adaptive intelligence layer 34904. The adaptive intelligence system layer 34904 may include a set of data processing, artificial intelligence, and computational systems 34914, described in more detail elsewhere throughout this disclosure. In this manner, the use of various resources, such as computing resources (available processing cores, available servers, available edge computing resources, available on-device resources—for a single device or a peered network, available cloud infrastructure, etc.), data storage resources (including local storage on a device, storage resources within or on an industrial entity), etc., constitutes the adaptive intelligence system layer 34904. Environment (including on-device storage, on-asset tag storage, local area network storage), network storage resources, cloud-based storage resources, database resources, etc.), network resources (including cellular network spectrum, wireless network resources, fixed network resources, etc.), and energy resources (available battery power, available renewable energy, fuel, grid-based power, etc.) may be optimized in a coordinated or shared manner on behalf of operators, enterprises, systems, applications, etc., such as for the benefit of multiple applications, programs, workflows, or other services/processes. For example, the adaptive intelligence layer 34904 may manage and provision available network resources for both industrial analytics applications and industrial remote control applications, such that low-latency resources are used for remote control and longer-latency resources are used for analytics applications. As described in more detail throughout this disclosure and the documents incorporated herein by reference, a wide variety of adaptations may be provided on behalf of various services and functions across the various layers 34908, including based on application requirements, quality of service, budget, cost, pricing, risk factors, operational objectives, optimization parameters, return on investment, profitability, and uptime/downtime.

The industrial management application platform layer 34902 (for convenience herein, sometimes referred to as the application platform layer 34902) may include a set of industrial processes, workflows, activities, events, and applications 34912 (individually and collectively referred to as applications 34912, unless the context dictates otherwise) that enable an operator to manage multiple aspects of an industrial environment or industrial entity 34930 in a common application environment. The common application environment may enable the platform 34900 to utilize common data storage in the data storage layer 34910, common data collection or monitoring in the industrial monitoring system layer 34906, and/or common adaptive intelligence in the adaptive intelligence system layer 34904. Output from the applications 34912 in the application platform layer 34902 may be provided to other data handling layers 34908. These may include, but are not limited to, state and status information for various objects, entities, processes, flows, etc., object information (such as identity, attribute, and parameter information for various classes of objects of various data types), event and change information (such as for workflows, dynamic systems, processes, procedures, protocols, and algorithms), including, but not limited to, timing information, outcome information (such as indications of success and failure, indications of process or milestone completion, indications of correct or incorrect predictions, indications of correct or incorrect labeling or classification, and success metrics such as those related to yield, engagement, return on investment, profitability, efficiency, timeliness, quality of service, quality of product, customer satisfaction, and other measures of success). Output from each application 34912 may be stored in the data storage layer 34910, distributed for processing by the data collection layer 34906, and/or used by the adaptive intelligence layer 34904. The cross-application nature of application platform layer 34902 thus facilitates convenient configuration of all of the infrastructure elements necessary to add intelligence to any application, including feeding machine learning about cross-application outcomes, providing enrichment of a given application's automation through machine learning based on outcomes from other applications (or other elements of platform 3490), and allowing application developers to focus on application-native processes while benefiting from other capabilities of platform 3490.

Referring to FIG. 204, additional details, components, subsystems, and other elements of any implementation of the platform 34900 of FIG. 203 are illustrated. The industrial management application platform layer 34902, in any of various implementations, may include a set of applications, systems, solutions, interfaces, or services (individually and collectively referred to herein as applications 34912 for convenience) that enable an operator or owner of the industrial entity 34930, or other users, to manage, monitor, control, analyze, or otherwise interact with one or more elements of the industrial entity 34930. The set of applications 34912 may include one or more other applications 34912 that facilitate improved operations of an industrial entity, facility, or the like for an owner, operator, or other user, including a blockchain-based industrial asset lifecycle management application 35002, an industrial asset lifecycle management application 35004, a process control optimization application 35010, a building automation and control application 35012, an enterprise asset management application 35014, a cloud/PaaS/SaaS solution 35008, a factory operations visibility and intelligence (FOVI) application 35018, an autonomous manufacturing application 35020, a smart supply chain application 35022, an inventory quality control application 35024, and an industrial analytics application 35028.

In certain aspects, one or more applications 34912 of the industrial management application platform layer 34902 and/or artificial intelligence system 35048 may include an artificial intelligence-enabled assistant 35089 that provides documentation related to the industrial entity 34930 (e.g., machinery and/or processes that may require maintenance or repair), provides diagnostics related to the industrial entity 34930, and/or provides a set of recommendations for service, updates, maintenance, replacement, repair, or other actions. This artificial intelligence-enabled assistant 35089 may be part of a suite of solutions or applications 34912 that use the capabilities of the platform 34900 and various shared microservices and layers (including artificial intelligence and advanced analytics) to enable preventative and predictive tasks related to the industrial entity 34930, such as downtime and maintenance management.

In a further aspect, application 34912 may also include asset performance management solutions 35091 and/or enterprise asset management applications 35093 to, among other things, reduce the risk of failure or improve the performance of various assets or industrial entities 34930, such as vehicles, manufacturing robots, turbines, mining equipment, elevators, transformers, motors, generators, and other machinery or components thereof. Such solutions may use data collection systems 34918 and other data sources to collect data in near real time from physical assets to provide information regarding operational, process, and/or fault conditions, as well as predict potential problems and perform other similar tasks. In aspects, recommendations for service, maintenance, repair, upgrade, or replacement may be provided, including recommendations regarding replacement parts, procedural information, identification of timing and scheduling information, identification, assessment of personnel or entities capable of undertaking repairs, and other similar information, as described throughout this disclosure and the documents incorporated by reference.

In various implementations, application 34912 may include industry- or entity-specific versions, such as for the energy industry, manufacturing industry, power generation industry, and mining industry. It should be understood that other entities/industries are contemplated and within the scope of the present disclosure. Data collected, organized, compiled, produced, utilized, etc. by the industry- or entity-specific versions may include industry-specific risk models, models related to the performance and degradation of particular types of machinery, and external data, such as weather, operating, and/or market conditions.

In some implementations, hardware for machine learning at the edge can take the form of edge-based Tensor Processing Units (TPUs), single-board computers running System-on-Modules (SOMs) (such as the recently announced SOMs available from Coral®), and USB-connected or other accessory devices that bring machine learning inference to existing systems.

In certain aspects, the adaptive intelligent systems layer 34904 may include a set of systems, components, services, and other capabilities that collectively facilitate the coordinated development and deployment of intelligent systems, such as those that can power one or more of the applications 34912 in the industrial management application platform layer 34902. The adaptive intelligent systems layer 34904 may include, for example, an adaptive edge compute management system 35030, a robotic process automation system 35042, a set of protocol adapters 35602, a packet acceleration system 35034, an edge intelligence system 35038, an adaptive networking system 35040, a set of state and event managers 35044, a set of opportunity miners 35046, and a set of artificial intelligence systems 35048, although additional or fewer elements are possible.

In aspects, the industrial monitoring system layer 34906 and its data collection systems 34918 can include a wide range of systems for collecting data. This layer includes, but is not limited to, real-time monitoring systems 35068 (such as on-board monitoring systems like on-board diagnostic systems and telematics systems, monitoring infrastructure (cameras, motion sensors, ambient sensors, etc.), and removable and replaceable monitoring systems like portable and mobile data collectors), software interaction observation systems 35050 (such as for logging and tracking events involving user interactions with software user interfaces (mouse movements, mouse clicks, cursor movements, keyboard interactions, navigation actions, eye movements, menu selections, etc.), mobile data collectors 35052 (such as those described herein and in documents incorporated by reference), and visual quality detection systems 35054 (such as for monitoring materials, components, machines, housings, seals, bearings, and many other elements of industrial entities 34930). This includes the use of video and still imaging systems, LIDAR, IR, and other systems that enable visualization of processes, as well as inspection systems that monitor processes, worker activity, etc. Sensors and Cameras include On-Board Diagnostic (OBD) and Telematics Systems 35070, which can provide diagnostic codes and events via an event bus, communications port, or other communications system; Observation Systems 35058, which track physical interactions between physical process workers and other workers, between workers and physical entities such as machinery or equipment, and between physical entities and other physical entities (including video cameras, motion sensing systems (including optical sensors, LIDAR, IR, and other sensor sets); Robotic Motion Tracking Systems (e.g., tracking the movement of a system attached to a human or physical entity); and Machine Condition Monitoring Systems 35060, which include on-board and external monitors of machine condition, status, operating parameters, or other measures of machine status. 35062 (including on-board sensors, sensors in industrial environments, cameras that monitor the entire environment, dedicated cameras for specific machines, processes, workers, or other functions, wearable cameras, portable cameras, cameras located on mobile robots, cameras in portable devices such as smartphones and tablets, and any of the many sensor types disclosed throughout this disclosure or in the documents incorporated by reference herein), indoor air quality monitoring systems 35072 (including chemical nose and other chemical sensor sets, as well as visual sensors), continuous emissions monitoring systems 35074, indoor sound monitoring systems 35078, and any other of a wide variety of Internet of Things (IoT) data collection devices, as described throughout this disclosure and in the documents incorporated by reference herein.

In certain implementations, and as described above, the industrial entity-oriented data storage system layer 34910 may include various systems for storage of data. These may include, but are not limited to, physical storage systems, virtual storage systems, local storage systems 35092, distributed storage systems, databases, memory, network-based storage, and network-attached storage systems 35082 (such as using Non-Volatile Memory Express ("NVMe"), storage-attached networks, and other network storage systems). Additionally or alternatively, the storage layer 34910 may store data in one or more knowledge graphs 35080, such as directed acyclic graphs, data maps, data hierarchies, or self-organizing maps. Furthermore, the data storage layer 34910 may store data in an industrial digital thread 35084, such as for maintaining a record of industrial entities 34930 over time, including any of the entities described herein. As described further herein, the data storage layer 34910 may be enabled using virtual asset tags 35088, which may include data structures associated with assets and accessed and managed as if the tags were physically located on the assets, such as using access controls, whereby data storage and retrieval is optionally linked to local processes, but also optionally open to remote retrieval and storage options. In embodiments, the storage layer 34910 may include one or more blockchains 35090, such as those that store identity data, transaction data, historical interaction data, and other data, with access controls that may be role-based or based on credentials associated with an industry entity 34930, a service, or one or more applications 34912.

With further reference to FIG. 205, the adaptive intelligence systems layer 34904 may include a robotic process automation ("RPA") system 35042 that includes a set of components, processes, services, interfaces, and other elements for the development and deployment of automation capabilities for various industry entities 34930, environments, and applications 34912. Without limitation, the robotic process automation system 35042 may apply automation capabilities to each of the processes managed, controlled, or mediated by each of the set of applications 34912 in the application platform layer 34902.

In an aspect, the robotic process automation system 35042 leverages the presence of multiple applications 34912 within the industrial management application platform layer 34902, allowing pairs of applications to share data sources (e.g., data storage layer 34910) and other inputs (e.g., from the industrial monitoring system layer 34906) collected about industrial entities 34930, and share outputs (e.g., events, status information, and other data), which collectively can provide a much richer environment for process automation, including the use of artificial intelligence systems 35048 (including any of the various expert systems, artificial intelligence systems, neural networks, supervised learning systems, machine learning systems, deep learning systems, and other systems described throughout this disclosure and in the documents incorporated by reference).

For example, the inventory quality control application 35024 may use the robotic process automation system 35042 to automate an inspection process typically performed or supervised by a human. While this process may involve visual inspection using video or still images from a camera or other imaging device displaying images of the entity 34930, the robotic process automation 35042 system may be trained to automate the inspection by, for example, observing the interaction of a set of human inspectors or supervisors with an interface used to identify, diagnose, measure, parameterize, or otherwise characterize potential defects in the items. On the one hand, the human inspectors' or supervisors' interactions may include a labeled dataset in which labels or tags indicate the type of defect or other characteristics, allowing a machine learning system to identify those same characteristics using the training dataset. Identification of those same characteristics may, in turn, be used to automate a visual quality detection process in which defects are automatically classified and detected in a set of video or still images, which may then be used within the inventory quality control application 35024 to flag inventory items that should be rejected or require further inspection. In certain implementations, the robotic process automation system 35042 may include multi-application or cross-application sharing of inputs, data structures, data sources, events, states, outputs, or results. For example, the inventory quality application 35042 may receive information from the smart supply chain application 35022 to enrich the robotic process automation by the robotic process automation system 35042 of the inventory quality control application 35042, such as information regarding expected characteristics of products or other items from a particular vendor, which may help reduce false positives or false negatives in the visual inspection process. These and many other examples of multi-application or cross-application sharing of robotic process automation 35042 across applications 34912 are encompassed by this disclosure.

In various implementations, the robotic process automation system 35042 may operate in a shared or converged process between various sets of applications 34912 in the industrial management application platform layer 34902, such as, but not limited to, a converged process including a Factory Operations Visual Intelligence (FOVI) system 35018 and a Process Control Optimization (PCO) system 35010, and processes such as integrated automation of a blockchain-based industrial asset lifecycle management application 35002 and a smart supply chain application 35022. Other examples are contemplated by this disclosure.

In certain aspects, the converged process may include a shared data structure for multiple applications 34912, including those that track the same transactions on the blockchain but may consume different subsets of available attributes of data objects maintained on the blockchain, or those that use a common set of knowledge graph nodes and links. For example, a transaction indicating a change in ownership of an industry entity 34930 may be stored on the blockchain and used by multiple applications 34912, such as to enable role-based access control, role-based authorization for remote control, identity-based event reporting, and other functionality. In aspects, the converged process may include a shared process flow across applications 34912, including the subset.
of a larger flow that involves one or more of a set of applications 34912. For example, a visual inspection flow for entity 34930 may serve an inventory quality control application 35024, an industrial analytics application 35028, an enterprise asset management application 35014, etc.

In embodiments, the RPA system 35042 can provide robotic process automation for a wide range of industrial processes referenced throughout this disclosure and the documents incorporated herein by reference, including energy production, manufacturing, transportation, storage, refining, distillation, fluid processing, energy storage, chemical processes, petrochemical processes, semiconductor processes, gas production processes, maintenance processes, service processes, repair processes, supply chain processes, assembly line processes, inspection processes, trading processes, fault detection processes, and power utilization optimization processes.

An environment for developing robotic process automation may include a set of interfaces for a developer to configure the artificial intelligence system 35048 to take inputs from selected data sources in the data storage layer 34910, events or other data from the industrial monitoring system layer 34906, and provide them to the RPA system 35042 as inputs for classification or prediction, as outcomes, or for other purposes, such as for neural networks. The RPA system 35042 may be configured to obtain one or more process and application outputs and outcomes 34928 from various applications 34912 to facilitate automated learning and improvement of classification, prediction, or other activities involved in the process intended to be automated.

In aspects, the development environment, and the resulting robotic process automation performed by the RPA system 35042, may include monitoring a combination of both software program interaction observations (e.g., received from a software interaction observation system 35050), such as by observing workers interacting with various software interfaces of applications 34912, including industrial entities 34930, and physical process interaction observations (e.g., received from a physical process observation system 35058), such as by observing workers interacting with or using machines, equipment, tools, or other components. In various implementations, the observation of software interactions by the software interaction observation system 35050 may include observation of interactions between software components with other software components, such as how one application 34912 interacts with another application 34912 via an API. In certain embodiments, the observation of physical process interactions by the physical process observation system 35058 may include observation (e.g., by video cameras, motion detectors, or other sensors) as well as detection of various physical interactions between the industrial entities 34930 and/or their individual elements. For example, such physical interactions may include, without limitation, observing/detecting the location, movement, etc. of hardware (e.g., robotic hardware), how human workers interact with industrial entities 34930 (e.g., worker locations, including routes through a facility; where a given type of worker is located during a given series of events, processes, etc.; how workers manipulate pieces of equipment or other items using various tools or physical interfaces; the timing of worker responses with respect to various events (e.g., responses to alerts and warnings); procedures by which workers perform scheduled maintenance, update, repair, and service processes; procedures by which workers adjust items involved in production; etc.). The physical process observation system 35058 may track characteristics such as worker position, angle, force, velocity, acceleration, pressure, torque, etc. as the worker manipulates hardware (e.g., tools). Such observations may be obtained through any combination of video data, data detected within the machine (e.g., the positions of machine elements detected and reported by position detectors), or data collected by a wearable device (e.g., an exoskeleton including position detectors, force detectors, torque detectors, and/or other sensors configured to detect physical characteristics of interactions between a human worker and a hardware item for the purpose of developing a training dataset). By collecting both software interaction observations (e.g., with software interaction observation system 35050) and physical process interaction observations (e.g., with physical process observation system 35058), RPA system 35042 can more comprehensively automate processes involving industrial entities 34930, such as using software automation in combination with physical robots.

In various implementations, the RPA system 35042 is configured to train a series of physical robots having hardware elements that facilitate undertaking tasks traditionally performed by humans. These can include robots that can walk (including up and down stairs), climb (such as climbing a ladder), navigate a facility, attach to items, grasp items (such as using a robotic arm, hand, pliers, etc.), lift items, carry items, remove and replace items, and use tools, among other activities.

Referring to FIG. 206, opportunity mining system 35046 may be provided as part of adaptive intelligence layer 34904. Opportunity mining system 35046 is configured to seek and recommend opportunities to improve one or more elements of platform 3490, such as through the addition of artificial intelligence system 35048, automation (including robotic process automation, e.g., via robotic process automation system 35046), etc., to one or more of the systems, subsystems, components, applications, or other aspects of platform 3490, or other systems, applications, etc. with which platform 3490 interacts. In an aspect, opportunity miner 35046 may be configured or used by developers of AI or RPA solutions to find opportunities for better solutions and optimize existing solutions. In certain implementations, the opportunity mining system 35046 may include a set of systems within the platform 3490 that collect information about and for a set of industrial environments and entities 34930, which may help identify and prioritize opportunities for increased automation and/or intelligence. For example, the opportunity mining system 35046 may include a system that observes clusters of workers by time, type, and location, such as using cameras, wearables, or other sensors, to identify labor-intensive areas and processes in a set of industrial environments. These may be presented in a ranked or prioritized list or visualized (e.g., heat maps showing worker dwell times on a map of the environment or heat maps showing routes workers travel within the environment) to indicate locations of high labor activity. In various implementations, the industrial analytics application 35028 may be used to identify which environments or activities would most benefit from automation for labor-saving purposes.

In an additional or alternative implementation, the opportunity mining system 35046 may include a system for characterizing the degree of domain-specific or entity-specific knowledge or expertise required to perform an action, use a program, use a machine, or perform any task in a process, for example, by observing the identity, qualifications, experience, and/or other characteristics of the workers involved in a given process. This is particularly beneficial in situations involving highly experienced workers (e.g., maintenance or rebuild processes for large or complex machinery, or the fine-tuning of complex processes where accumulated experience is required to work effectively), especially when those workers may be in short supply (e.g., due to retirement or a declining supply of new workers with the same qualifications). Thus, the opportunity mining system 35046 may collect and provide to the industry analytics application 35028 (e.g., to prioritize the development of automation such as RPA) data indicating which processes of or relating to the industry entity 34930 most intensively rely on workers with a particular set of experience or qualifications (e.g., those with scarce or declining experience or qualifications). The opportunity mining system 35046 may, for example, correlate aggregated data (including trend information) regarding the age, qualifications, and/or experience of workers (including by process type) with data regarding the processes in which those workers are involved (by tracking worker location by type, by tracking time spent on processes by worker type, or otherwise). A set of high-value automation opportunities may be automatically recommended based on a ranking set, such as a ranking set that weights opportunities based at least in part on the relative reliance of the set of processes on workers that are in short supply or are expected to be in short supply.

In various embodiments, the opportunity mining system 35046 may use information related to the costs of workers involved in a set of processes by accessing labor data 34922, which may include, for example, human resources database information showing various workers' salaries (individually or by type), information on rates charged by service workers or other contractors, or other forms of cost data. The opportunity mining system 35046 may provide such cost information for correlation with process tracking information, such as enabling the industry analytics application 35028 to identify which processes occupy the most hours of the most expensive workers. This may include visualization of such processes, such as with a heat map showing which locations, routes, or processes are responsible for the most expensive worker hours in an industrial environment or with respect to an industry entity 34930. The opportunity mining system 35046 may provide ranked lists, weighted lists, or other forms of datasets that indicate to developers which areas are most likely to benefit from further automation or artificial intelligence deployment.

In certain embodiments, opportunity mining system 35046 may "mine" the industrial environment for RPA opportunities by searching human resources databases and/or other labor tracking databases for areas containing labor-intensive processes. For example, opportunity mining system 35046 may search the system for areas where worker qualifications indicate a relatively high potential for automation, track clusters of workers (e.g., via wearable devices or other sensors) to find labor-intensive machines or processes, and/or track clusters of workers by worker type (e.g., via wearable devices or other sensors) to find labor-intensive processes.

The opportunity mining system 35046 may include facilities for soliciting appropriate training datasets that can be used to facilitate process automation. Certain types of data or other inputs, if available, can provide exceptional value to automation, such as video datasets capturing highly experienced and/or highly specialized workers performing complex tasks. Accordingly, the opportunity mining system 35046 may search for such video datasets, as described herein. If such data is not successfully searched for, or to supplement available data, the platform 34900 may include a system that allows a user, such as a developer, to specify desired types of data, such as software interaction data (e.g., data of experts working with a program to perform a particular task), video data (e.g., video showing a series of experts performing a particular type of repair, an expert rebuilding a machine, an expert optimizing a particular type of complex process, or the like), and/or physical process observation data (e.g., video or other types of sensor data).

The platform 3490 may be used to solicit such data, such as by offering some form of compensation (monetary reward, tokens, cryptocurrency, licenses or rights, revenue sharing, or other compensation) to parties who provide the requested types of data. Rewards may be offered to parties who provide existing data and/or to parties who take steps to capture expert interactions, such as videotaping the process. The resulting library of interactions captured in response to the designation, solicitation, and rewards may be captured as a dataset in the data storage layer 34910 for consumption by various applications 34912, elements of the adaptive intelligence systems layer 34904, and other processes and systems. In aspects, the library may include videos specifically developed as instructional videos to facilitate the development of automation maps where the instructions in the video can be followed, such as by providing a sequence of steps that follow a procedure or protocol, or by breaking down the procedure or protocol into substeps that are candidates for automation, among other uses. For example, such instructional videos may be processed using natural language processing to automatically develop sequences of labeled instructions that a developer can use to, for example, facilitate maps, graphs, or other models of a process to aid in the development of process automation. In aspects, a set of designated training data sets may be configured to serve as inputs for learning. For example, the training data may be temporally synchronized with other data within platform 34900 (e.g., outputs and outcomes from application 34912, outputs and outcomes of industry entities 34930, etc.) to associate a given video of a process with those outputs and outcomes, thereby enabling learning feedback that is sensitive to outcomes that have occurred for the captured process.

206, a set of opportunity miners 35046 may be provided as part of the adaptive intelligence layer 34904, which may be configured to seek and recommend opportunities to improve one or more elements of the platform 34900, such as by adding artificial intelligence 35048, automation (including robotic process automation 35046), etc., to one or more of the systems, subsystems, components, applications, etc. of the platform 100. In embodiments, the opportunity miners 35046 may be configured or used by developers of AI or RPA solutions to find opportunities for better solutions and optimize existing solutions. In embodiments, the opportunity miners 35046 may include a set of systems that collect information within the platform 100, and collect information within, about, and for a set of industrial environments and entities 34930, where the collected information may aid in identifying and prioritizing opportunities for automation and/or intelligence improvements. For example, opportunity miner 35046 may include a system that observes clusters of workers by time, type, and location, such as using cameras, wearables, or other sensors, to identify labor-intensive areas and processes in a set of industrial environments. These may be presented as ranked or prioritized lists or visualizations (such as heat maps showing worker dwell times on a map of the environment or heat maps showing routes taken by workers within the environment) to indicate locations of high labor activity. In embodiments, analytics 35028 may be used to identify which environments or activities would most benefit from automation for labor-saving purposes.

In embodiments, opportunity miner 35046 may include a system for characterizing the degree of domain- or entity-specific knowledge or expertise required to perform an action, use a program, operate a machine, etc., such as by observing the identity, qualifications, and experience of workers involved in a given process. This is particularly beneficial in situations involving highly experienced workers (such as maintenance or rebuild processes for large or complex machinery, or the fine-tuning of complex processes that require accumulated experience to work effectively), especially when those workers may be in short supply (e.g., due to retirement or a diminishing supply of new workers with the same qualifications). Thus, a set of opportunity miners 35046 may collect and feed to analytics solution 35028 data indicating which processes of or regarding industrial entity 34930 most intensively rely on workers with the following qualifications, such as to prioritize the development of automation 35042:
There may also be specific sets of experience or qualifications, such as those with experience or qualifications that are in short supply or declining. The opportunity miner 35046 may, for example, correlate aggregated data (including trend information) about workers' age, qualifications, and experience (including by process type) with data about the processes in which those workers are involved (e.g., tracking worker location by type, tracking time spent on processes by worker type, etc.). A set of high-value automation opportunities may be automatically recommended based on a ranking set, such as weighting opportunities based at least in part on the set of processes' relative reliance on workers that are in short supply or are expected to become more scarce.

In embodiments, the set of opportunity miners 35046 may use information related to the costs of workers involved in a set of processes, such as by accessing human resources database information indicating various workers' salaries (either individually or by type), worker data 34922, including information on the rates charged by service workers or other contractors, etc. The opportunity miners 35046 may provide such cost information for correlation with process tracking information, such as to enable the analytics solution 35028 to identify processes that occupy the most hours of the most expensive workers. This may include visualization of such processes, such as with a heat map showing which locations, routes, or processes in an industrial environment or with respect to an industry entity 34930 involve the most expensive worker hours. The opportunity miners 35046 may also provide developers with ranked lists, weighted lists, or other datasets indicating which areas are most likely to benefit from further automation or artificial intelligence deployment.

In embodiments, mining an industrial environment for robotic process automation opportunities may include searching HR databases and/or other labor tracking databases for areas containing labor-intensive processes, searching the system for areas with worker credentials that indicate automation potential, tracking clusters of workers via wearables to find labor-intensive machines or processes, tracking clusters of workers by worker type via wearables to find labor-intensive processes, etc.

In embodiments, opportunity mining may include facilities for soliciting appropriate training datasets that may be used to facilitate process automation. For example, certain inputs, if available, would provide exceptional value to automation, such as video datasets capturing highly experienced and/or highly specialized workers performing complex tasks. Opportunity miner 35046 may search for such videos.
However, if unsuccessful (or to supplement available data), the platform may include a system that allows users, such as developers, to specify desired types of data, such as software interaction data (e.g., data on experts working with a program to perform a specific task), video data (e.g., video showing a set of experts performing a specific type of repair, experts rebuilding a machine, experts optimizing a specific type of complex process, etc.), observational data of a physical process (e.g., video, sensor data, etc.). This specification may be used to solicit such data, such as by offering some form of compensation (e.g., monetary compensation, tokens, cryptocurrency, licenses or rights, revenue share, or other compensation) to parties that provide the requested type of data. Compensation may be provided to parties that provide existing data and/or to parties that take steps to capture the expert interactions, such as videotaping the process. The resulting library of interactions captured in response to the specification, solicitation, and compensation may be captured as a dataset in the data storage layer 34910, such as for consumption by various applications 34912, adaptive intelligence systems 34904, and other processes and systems. In embodiments, the library may include videos specifically developed as instructional videos, such as to facilitate the development of automation maps that can follow the instructions in the video, such as providing a sequence of steps according to a procedure or protocol, or breaking down a procedure or protocol into substeps that are candidates for automation. In embodiments, such videos may be processed by natural language processing, for example, to automatically develop sequences of labeled instructions that developers can use to facilitate maps, graphs, or other models of processes that aid in the development of process automation. In embodiments, a designated set of training datasets may be configured to serve as inputs for learning. In such cases, the training data may be synchronized in time with other data in the platform 34900, such as outputs and outcomes from applications 34912, outputs and outcomes of industry entities 34930, etc., to associate a given video of a process with those outputs and outcomes, thereby enabling learning feedback that is sensitive to outcomes that occurred during a given process captured (e.g., on video or through observation of software interactions or physical process interactions).

As described elsewhere herein and in the documents incorporated by reference, artificial intelligence (e.g., any of the techniques or systems described throughout this disclosure) can be used in connection with various industrial entities 34930, functions, and applications to, among other things, facilitate: (a) the optimization, automation, and/or control of various functions, workflows, applications, features, resource utilization, etc.; (b) the recognition or diagnosis of various states, entities, patterns, events, contexts, behaviors, or other factors; and/or (c) the prediction of various states, events, contexts, or other factors. As artificial intelligence advances, various specialized and general artificial intelligence systems are becoming available and are expected to continue to proliferate. When developers seek solutions to domain-specific problems, such as those associated with industrial entities 34930 and various applications of platform 34902 described throughout this disclosure, they face challenges in selecting artificial intelligence models (e.g., which set of neural networks, machine learning systems, expert systems, etc.) and in discovering and selecting inputs that may enable the effective and efficient use of artificial intelligence for a given problem. As mentioned above, Opportunity Miner 35046 can assist in discovering opportunities for increased automation and intelligence. However, once an opportunity is discovered, selecting and configuring an AI solution remains a significant challenge, and this challenge is likely to continue to grow as AI solutions proliferate.

One set of solutions to these challenges is artificial intelligence store FMRP104, configured to enable the collection, organization, recommendation, and presentation of a related set of artificial intelligence systems based on one or more attributes of a domain and/or a problem related to the domain. In embodiments, artificial intelligence store FMRP104 may include a set of interfaces to artificial intelligence systems that enable downloading related artificial intelligence applications, linking to or establishing other connections with the artificial intelligence systems (e.g., linking to cloud-deployed artificial intelligence systems via APIs, ports, connectors, or other interfaces), etc. The artificial intelligence store FMRP104 may include descriptive content about each of the various artificial intelligence systems, such as metadata or other descriptive material indicating the system's suitability for solving a particular type of problem (e.g., prediction, NLP, image recognition, pattern recognition, motion detection, route optimization, or many other problems) and/or for operating with domain-specific inputs, data, or other entities. In embodiments, artificial intelligence store FMRP104 may be organized by categories such as domain, input type, processing type, output type, computational requirements and capabilities, cost, energy usage, and other factors. In embodiments, interfaces to application store FMRP104 may take input from developers and/or A set of recommendations may also be provided via an artificial intelligence attribute search engine (e.g., opportunity miner 35046) for a subset of artificial intelligence solutions that may represent favorable candidates based on the developer's domain-specific problem. In embodiments, the search results or recommendations may be based at least in part on collaborative filtering, such as by asking the developer to indicate or select favorable model elements, and clustering, such as by using an affinity matrix, k-means clustering, or other clustering techniques, to associate similar developers, similar domain-specific problems, and/or similar artificial intelligence solutions. The artificial intelligence store FMRP104 may include e-commerce functionality, such as ratings, reviews, links to related content, and mechanisms for provisioning, licensing, distribution, and payment (including allocation of payments to affiliates and/or contributors), including mechanisms that operate using smart contracts and/or blockchain functionality to automate purchasing, licensing, payment tracking, transaction settlement, or other functions.

In embodiments, another set of solutions that can be deployed alone or in conjunction with other elements of the platform, including the artificial intelligence store FMRP104, can include a set of functional imaging capabilities FMRP102, which can comprise a monitoring system 34906, such as for monitoring various industrial entities 34930, and possibly a physical process observation system 35058 and/or a software interaction observation system 35050. In embodiments, the functional imaging system FMRP102 can provide significant insight into the types of artificial intelligence likely to be most effective in solving particular types of problems. As discussed elsewhere in this disclosure and in documents incorporated by reference herein, as computing and networked systems grow in scale, complexity, and interconnectivity, they manifest problems such as information overload, noise, network congestion, energy waste, and many other issues. As the Internet of Things grows to hundreds of billions of devices and a virtually infinite number of potential interconnections, optimization becomes extremely difficult. The human brain faces similar challenges and has evolved rational solutions to a wide range of extremely difficult optimization problems over millennia. The human brain operates as a vast neural network composed of interconnected modular systems, each adapted to solve specific problems, such as controlling biological systems and maintaining life. These modules play a role in a variety of areas, including homeostasis, detecting diverse static and dynamic patterns, and recognizing threats and opportunities. Functional imaging systems, such as functional magnetic resonance imaging (fMRI), electroencephalography (EEG), and computed tomography (CT), have become sophisticated enough to recognize patterns of brain activity in real time and temporally correlate them with other information, such as behavior, stimulus information, environmental condition data, gestures, and eye movements. Through functional imaging (FMRP) 102, alone or in combination with other information collected by monitoring systems 34906, the platform can determine and classify which brain modules, operations, systems, and/or functions are being used in performing a series of tasks or activities, such as software interactions 35050, physical process observations 35058, or a combination thereof. This classification can assist in selecting and/or configuring a set of artificial intelligence solutions, such as from an artificial intelligence store FMRP104, that includes a set of capabilities and/or functions similar to the set of modules and functions of the human brain when undertaking an activity, such as for initial configuration of a robotic process automation (RPA) system 35042 that automates a task performed by a human expert. Accordingly, the platform may include a system that receives input from a functional imaging system FRMP102 and configures, optionally automatically, a set of artificial intelligence capabilities for the robotic process automation system based on attribute matching between one or more biological systems, such as a brain system, and one or more artificial intelligence systems. The selection and configuration can further include selecting inputs to the robotic process automation and/or artificial intelligence that are configured based at least in part on functional imaging of the brain as the worker performs the task, such as selecting visual inputs (e.g., images from a camera) that highly activate the brain's visual system, selecting acoustic inputs that highly activate the brain's auditory system, or selecting chemical inputs (e.g., chemical sensors) that highly activate the brain's olfactory system. In this way, biologically aware robotic process automation systems could be improved through initial setup and iterative refinement, either automatically or under developer control, with image-derived information collected as workers perform specialized tasks that could benefit from automation.

Referring to FIG. 207, additional details of an embodiment of platform 34900 are provided, particularly with respect to elements of an adaptive intelligent systems layer 34904 that facilitate improved edge intelligence, including an adaptive edge compute management system 35030 and an edge intelligence system 35038. These elements provide a set of systems that adaptively manage computation, storage, and processing at the "edge," such as by varying where data is stored and processed (e.g., AI-optimized) between on-device storage, local systems, within the network, and in the cloud. The adaptive edge compute management system 35030 and edge intelligence system 35038 enable users, such as developers, operators, or hosts of platform 100, to facilitate dynamic definition of what constitutes the "edge" for the purposes of a given application, for example, in environments where data connections are slow or unreliable, such as industrial facilities lacking good access to cellular networks (e.g., due to the remote location of the environment). For example, in environments such as remote locations (e.g., excavation, construction, piping, exploration), obstructions or interference (e.g., where thick concrete or large metal equipment inhibits networking performance), or congestion (e.g., where there are many devices seeking access to limited networking facilities), edge computing capabilities can be defined and deployed to operate on the environment's local area network, on a peer-to-peer network of devices, or on the computing capabilities of local industrial entities. In locations where strong data connections are available (e.g., where good backhaul facilities exist), edge computing capabilities can be deployed within the network, such as to cache frequently used data where it improves input/output performance, reduces latency, or otherwise improves platform 34900 performance. In this manner, adaptive definition and designation of edge computing operating locations is possible. This adaptive definition/designation can be under the control of a developer or operator and/or can be determined automatically (e.g., by an expert or automation system based on detected network conditions for the environment, the industrial entity 34930, or the network as a whole). In certain implementations, the edge intelligence system 35038 can enable adaptation of edge computation (where computation occurs within various available networking resources, how networking occurs (e.g., by protocol selection), where data storage occurs, etc.) to be multi-application aware, such as taking into account QoS, latency requirements, congestion, and cost, understood and prioritized based on an understanding of the value (including cost information such as ROI, yield, and cost of failure) of edge computation capabilities across multiple applications, including any combination and subset of the applications 34912 described herein or in the documents incorporated by reference herein.

In various aspects, the edge intelligence system 35038 may be partially enabled by edge computing capabilities, such as using a tensor processing unit (TPU), such as a single-board computing device running Google's® edge-based Tensor Processing Unit (TPU). In additional or alternative aspects, the edge intelligence system 35038 may employ system-on-module (SOM) capabilities, such as Coral's® SOM, and one or more accessories configured to provide machine learning inference capabilities to edge devices and systems, such as USB-connected accessories, Power-over-Ethernet (PoE)-powered accessories, and accessories connected via other local power and data protocols. Such capabilities for the edge intelligence system 35038 may be deployed to edge devices and systems of or relating to various industrial entities 34930 and may be used to provide pattern recognition, predictions, inferences, and the like for a variety of purposes, such as predictive maintenance, service and repair recommendations, anomaly detection, fault detection, process fault recognition, process optimization, machine vision, visual inspection, robotics, process automation, status reporting, natural language processing, diagnostic condition recognition, and speech recognition.

By way of example only, the Edge TPU may include an application-specific integrated circuit (ASIC), such as an NXP® i.MX 8M system-on-chip (SOC), featuring a quad-core Cortex-A53 and Cortex-M4F, or similar processing device. The system may use, for example, an integrated graphics GPU, such as the GC7000 Lite Graphics GPU, and include RAM (e.g., 1 GB of RAM) and Flash memory (e.g., 8 GB or more of Flash memory).

In some implementations, the system may include various ports that enable linking edge intelligence capabilities to various edge devices and systems via various protocols, such as a MicroSD slot, Gigabit or other Ethernet ports, PoE ports, and various audio ports. It also supports various wireless protocols, such as NFC, WiFi, Zigbee, and Bluetooth 4.1. Connectivity may include wired connectivity, such as USB connectivity, via Type-C OTG, Type-C power connection, Type-A 3.0 host, and/or Micro-B serial console. In some implementations, the SOM may be integrated into an edge device or system, such as a Linux system like Raspberry Pi, or a system using another conventional operating system. Additionally, elements of the system may run a software operating system, such as a Linux-based system like Mendel®. Additionally, in some implementations, models using AI modeling systems like TensorFlow® may be compiled for execution on the system.

208, additional details, components, subsystems, and other elements of an exemplary implementation of the industry entity-oriented data storage system layer 34910 of the platform 3490 are illustrated, particularly related to an implementation including a geofenced virtual asset tag 35088. The virtual asset tag 35088 can be implemented as a data structure containing data about an industry entity 34930 (such as a machine, an item of equipment, an item of inventory, a manufactured article, a component, a tool, a device, a worker, etc.), where the data is intended to be "tagged" to the asset. For example, the data can be uniquely associated with a particular asset (e.g., to a unique identifier for the individual asset) or linked to proximity to the asset (e.g., geofenced to an area or location at or near the asset). Thus, the virtual asset tag 35088 is functionally equivalent to a physical asset tag, such as an RFID tag, in that it provides access to the data structure to a local reader or similar device when the local reader or similar device is in proximity to the virtual asset stage 35088 (just as a reader accesses an RFID tag). In some aspects, access control can be managed and/or controlled as if the tag were physically located on the asset. For example, certain data may be encrypted with a key that only allows reading, writing, modification, etc., by operators who are verified to be in the vicinity of the tagged industrial entity 34930. This implementation allows for partitioning between local-only and remote data processing.

In some aspects, the virtual asset tag 35088 can be configured to recognize the presence of an RF reader (e.g., by recognizing an interrogation signal) and communicate with the reader (with the aid of a protocol adapter), e.g., via an RF communications link or other communications protocol, despite the absence of a traditional RFID tag. This can occur through communications from IoT devices, telematics systems, and other devices present on a local area network. In additional or alternative embodiments, a set of IoT devices in an industrial environment can function as distributed blockchain nodes, e.g., for storing virtual asset tag data, tracking transactions, and verifying (e.g., via various consensus protocols) enchantment data, including transaction histories for maintenance, repair, and service. IoT devices within a geofence can collectively verify the location and identity of fixed assets tagged with the virtual asset tag 35088, such that peers or neighbors can verify other peers or neighbors as being in a given location, thereby verifying the unique identity and location of the asset.
The verification can use a voting protocol, a consensus protocol, other protocols, or a combination thereof. In an aspect, the identity of the tagged industrial entity 34930 can be maintained on a blockchain. Additionally or alternatively, in some aspects, the virtual asset tag 35088 can include information related to the industrial digital thread 35084, such as historical information about the asset, its components, its history, etc.

Referring to FIG. 209, in various aspects, the RPA system 35042 may be configured to develop and deploy one or more automation capabilities, including or enabling capabilities for a robot operations analysis system 35502. The robot operations analysis system 35502 may, in certain aspects, analyze a series of robotic operational actions, including with respect to the location, mobility, and routing of mobile robots, and with respect to the behavior of robotic components, such as when robots and/or robotic components are used within a wide range of protocols or procedures (e.g., manufacturing processes, assembly processes, transportation processes, maintenance and repair processes, data collection processes, etc.).

In some aspects, the RPA system 35042 may include or enable capabilities for machine learning on unstructured data 35508, including, but not limited to, learning on a training set of human labels, tags, or other activities that enable characterization of the unstructured data, extraction of content from the unstructured data, and/or generation of diagnostic codes or similar summaries from the content of the unstructured data. For example, the RPA system 35042 may include subsystems or functionality for processing technical documentation (e.g., technical data sheets, functional specifications, repair instructions, user manuals, and other documentation related to the industrial entity 34930), processing human-entered notes (e.g., notes related to diagnosing problems, prescribing or recommending actions, characterizing operational activities, and notes related to maintenance and repair work), and processing information such as unstructured content contained on websites, social media feeds, etc. (e.g., information about products and systems in industrial environments obtained from vendor websites) and other documents contained on websites, social media, etc.).

In certain aspects, the RPA system 35042 may constitute a unified platform with a set of RPA capabilities and may also include monitoring systems (such as systems in the monitoring layer 34906 and data collection system 34918), raw data processing system(s) 35504 (including, but not limited to, systems that perform optical character recognition (OCR), natural language processing (NPL), computer vision processing, speech processing, and other processing).
Other capabilities may include: a workflow characterization and management system(s) 35516, analytics system(s) 35510, artificial intelligence system(s) 35048, and management system(s) 35514 (for policy, governance, and service provisioning, roles, access control, etc.). In certain implementations, the RPA system 35042 may include such capabilities as a set of microservices in a microservices architecture. The RPA system 35042 may have a set of interfaces to other platform layers 34908 and external systems for data exchange so that the RPA system 35042 can be accessed as an RPA platform-as-a-service by other platform layers 34908 and/or external systems that can benefit from one or more automation capabilities.

In embodiments, the RPA system 35042 may include a work quality characterization system 35512 that can, for example, identify high-quality work relative to other work or otherwise evaluate, measure, or characterize work quality. Examples of such characterizations of work quality services include recognizing human work as distinct from work performed by machines, recognizing which human work is likely to be of the highest quality (e.g., work involving the most experienced or expensive personnel), recognizing which machine-performed work is likely to be of the highest quality (e.g., work performed by machines that have been extensively trained based on feedback from many results compared to newly deployed machines), and recognizing which work has historically provided good results (e.g., based on analysis or correlation with past results). A set of thresholds that can be varied under the control of the RPA system 35042 developer or other user can be applied to indicate by type, quality level, or other measure that a dataset indicative of past work is to be used for training within a machine learning system that drives automation in the RPA system 35042.

As briefly mentioned above, a series of protocol adapters can facilitate adaptive protocol conversion of data within an IIoT system. With reference to FIGS. 210-212, exemplary methods and systems for data processing in industrial environments utilizing protocol adapters are illustrated in conjunction with various components, interfaces, machines, devices, programs, methods, processes, protocols, and other elements collectively referred to herein as platform 35600. In various implementations, platform 35600 can include intelligent, automated, machine learning, or other “smart” protocol adapters (referred to herein as self-organizing protocol adapters 35602, except where context indicates) that can connect to one or more clouds.
A networked and/or distributed computing platform (referred to herein as IoT cloud platform 35610 unless the context requires otherwise).

Platform 35600 may include, connect to, or integrate with one or more sensors 35622, which may be connected to self-organizing protocol adapter 35602 or to one or more IoT cloud platforms 35610. In this manner, one or more sensors 35622 may provide information about the industrial environment, information about one or more machines, components, or devices within the industrial environment, information about one or more network conditions (such as network bandwidth, spectrum availability, congestion, interference, cost, timing, and/or availability), or information about one or more cloud conditions or parameters. Among other things, sensors 35622 may be used by self-organizing protocol adapter 35602 to facilitate the organization or selection of an appropriate protocol over which one or more IoT devices (e.g., industrial IoT device 35620 in industrial environment 35624) can communicate. The platform 35600 may include one or more external data sources 35618 (such as databases, data warehouses, data streams, data packages, mobile data collectors, or other sources) located in the industrial environment 35624 or elsewhere, including the cloud 35612. Various IoT devices 35620 may be located in the industrial environment 35624. In some aspects, an IoT cloud platform 35610 is deployed in the cloud 35612, and various network devices, such as the industrial IoT devices 35620, have one or more interfaces 35614 that can connect to the IoT cloud platform 35610 via one or more protocols 35608.

In an aspect, the sensor 35612 may include one or more of Touch ID, chemical, electrical, acoustic, vibration, acceleration, velocity, position, light, motion, temperature, magnetic field, gravity, humidity, moisture, pressure, electric field, and sound sensors.

The self-organizing protocol adapter 35602 can select, create, determine, and/or organize a self-organizing protocol, which can be at least one of a centralized protocol, a decentralized protocol, and a hybrid protocol. In some aspects, the self-organizing protocol is self-organized by artificial intelligence, e.g., via at least one of an expert system, a machine learning system, a deep learning system, and a neural network, to select, create, determine, and/or organize the self-organizing protocol. For example, the IoT cloud platform 35610 can use one or more protocols 35608 selected from the group consisting of REST/HTTP, WebSockets, MQTT, CoAP, M2M IoT, Modbus, XMPP, and DDS, although any protocol suitable for use is within the scope of this disclosure.

In some implementations, the IoT cloud platform 35610 is at least one of a Websphere platform, an AWS platform, an Azure platform, a Google Cloud platform, an IBM Watson platform, an Oracle platform, an SAP platform, a GE Predix platform, a Cisco platform, and a Bosch platform. However, it should be understood that the IoT cloud platform 35610 can be of any type or form. Additionally, in various aspects, the industrial IoT device 35620 may be one or more of an Internet Protocol (IP)-enabled device, a non-IP-enabled device, an IoT client device, a low-power device, a Java device, or any other suitable IoT device.

In various aspects, the industrial environment 35624 is one or more of an energy production environment, a manufacturing environment, an energy extraction environment, and a construction environment.

In an additional or alternative implementation, a method and system for industrial data processing having a self-organizing protocol adapter 35602 and having a smart industrial heater 35604 is provided.

In additional or alternative implementations, the IoT cloud platform 35610 may include an IoT data adapter 35700. As depicted in FIG. 211, the IoT data adapter 35700 can receive IoT data 35710 as input. The input can be received from any one or more of the many external data sources 35618 (such as databases, data warehouses, data streams, data packages, and mobile data collectors) identified elsewhere in this disclosure, sensors 35622, and any other data source. In some implementations, the IoT data adapter 35700 can establish connections to publish data to one or more available IoT cloud platforms 35610, or any other device capable of receiving the data, such as a server computing device. In some aspects, the connection can be established to one or more available IoT cloud platforms 35610, or alternatively, by detecting a condition with the condition detector 35716, for example. The condition can be related to a connection attempt or attempts made by the IoT data adapter 35700 to one or more IoT cloud platforms 35610. These conditions related to the attempt or attempt may include receiving a response message 35718 from the IoT cloud platform 35610. The response message 35718 may indicate the success or failure of the connection and/or may include content suggesting alternative protocols under which the connection may be successfully established, or similar content such as data or usage metrics from the cloud platform.

In some aspects, data received by the IoT cloud platform 35610 from the IoT adapter 35700 can be automatically published by the IoT cloud platform 35610.
formats, wraps, translates, or otherwise prepares the data package 35720 or data stream 35722. The data package 35720 or data stream 35722 may be formatted in any of a wide variety of available data formats, including, but not limited to, those described elsewhere in this disclosure.

Optionally, the IoT data adapter 35700 may include an adaptation engine 35724 for implementing the adaptation techniques described herein. The IoT data adapter 35700 may use the adaptation techniques to establish a successful connection to one or more IoT cloud platforms 35610. The adaptation techniques may include using any of the machine learning techniques described elsewhere in this disclosure.

In various aspects, the IoT data adapter 35700 may or may alternatively make connections from a data marketplace. In such an implementation, the data package 35720 associated with the initial connection of a new data source may prompt the user interface of the IoT cloud platform 35610 with messages indicating the availability of the new data source, how to integrate the data source (e.g., by providing metadata about the data source and/or terms for using the data), and other similar information.

212, an exemplary connection attempt is depicted in accordance with certain aspects of the present disclosure. The sensor swarm 35810 attempts to establish an HTTP protocol connection 35814 to the IoT cloud platform 35610 via the condition detector 35716. The IoT cloud platform 35610 rejects the attempt to establish the HTTP protocol connection 35814 and sends a reply message 35718 to the IoT data adapter 35700 indicating the failed attempt. Upon receiving the message indicating the failed attempt to establish the HTTP protocol connection 35814, the adaptation engine 35724 can send a message indicating the failure to the sensor group 35810 via the condition detector 35716. Further, in some embodiments, the message from the adaptation engine 35724 can include information related to a suggestion that the sensor group 35810 retry connecting to the IoT cloud platform 35610 using a different protocol, such as the illustrated MQTT protocol connection 35812. It should be understood that the exemplary connection attempt illustrated in FIG. 212 is merely exemplary, and that other connection attempts may include additional, fewer, or different elements, messages, data, etc.

FIG. 213 illustrates an exemplary environment for a digital twin system 40000. In an embodiment, the digital twin system 40000 generates a set of digital twins of a set of industrial environments 40020 and/or industrial entities within the set of industrial environments. In an embodiment, the digital twin system 40000 maintains a set of states for each industrial environment 40020, such as using sensor data obtained from each sensor system 40030 that monitors the industrial environment 40020. In an embodiment, the digital twin system 40000 may include a digital twin management system 40002, a digital twin I/O system 40004, a digital twin simulation system 40006, a digital twin dynamic model system 40008, a cognitive intelligence system 40010, and/or an environmental control module 40012. In an embodiment, the digital twin system 40000 may provide a real-time sensor API that provides a set of functions to enable a set of interfaces for sensors of each sensor system 40030. In embodiments, digital twin system 40000 may include and/or employ other suitable APIs, brokers, connectors, bridges, gateways, hubs, ports, routers, switches, data integration systems, peer-to-peer systems, etc. to facilitate the transfer of data to and from digital twin system 40000. In these embodiments, these connectivity components may enable HOT sensors or intermediary devices (e.g., relays, edge devices, switches, etc.) within sensor system 40030 to communicate data to digital twin system 40030 and/or receive data (e.g., configuration data, control data, etc.) from digital twin system 40030 or another external system. In embodiments, digital twin system 40000 may further include a digital twin data store 40016 that stores digital twins 40018 of various industrial environments 40020 and objects 40022, devices 40024, sensors 40026, and/or people 40028 within the environments 40020.

A digital twin may refer to a digital representation of one or more industrial entities, such as an industrial environment 40020, physical objects 40022, devices 40024, sensors 40026, people 40028, or any combination thereof. Examples of industrial environments 40020 include, but are not limited to, factories, power plants, food production facilities (which may include inspection facilities), commercial kitchens, indoor cultivation facilities, natural resource extraction sites (mines, oil fields, etc.), etc. Depending on the type of environment, the types of objects, devices, and sensors present in the environment will vary. Non-limiting examples of physical objects 40022 include raw materials, manufactured goods, excavations, containers (e.g., boxes, dumpsters, cooling towers, tubs, pallets, barrels, pallets, bins, etc.), furniture (e.g., tables, counters, workstations, shelves, etc.), etc. Non-limiting examples of device 40024 include robots, computers, vehicles (e.g., cars, trucks, tankers, trains, forklifts, cranes, etc.), machines/equipment (e.g., tractors, tillers, drills, presses, assembly lines, conveyor belts, etc.), etc. Sensor 40026 may be any sensor device and/or sensor aggregator found in a sensor system 40030 in the environment. Non-limiting examples of sensors 40026 that may be implemented in the sensor system 40030 may include a temperature sensor 40032, a humidity sensor 40034, a vibration sensor 40036, a LIDAR sensor 40038, a motion sensor 40040, a chemical sensor 40042, an audio sensor 40044, a pressure sensor 40046, a weight sensor 40048, a radiation sensor 40050, a video sensor 40052, a wearable device 40054, a relay 40056, an edge device 40058, a crosspoint switch 40060, and/or any other suitable sensor. Examples of different types of physical objects 40022, devices 40024, sensors 40026, and environments 40020 are referenced throughout this disclosure.

In an embodiment, the crosspoint switch 40060 is implemented in a sensor system 40030 having multiple inputs and multiple outputs, including a first input connected to a first sensor and a second input connected to a second sensor. The multiple outputs include a first output and a second output configured to be switchable between a state in which the first output is configured to switch between transmitting a first sensor signal and a second sensor signal, and a state in which the first sensor signal is simultaneously transmitted from the first output and the second sensor signal is simultaneously transmitted from the second output. Each of the multiple inputs is configured to be individually assigned to one of the multiple outputs. Unassigned outputs are configured to be switched off, creating a high impedance state.

In an embodiment, the first sensor signal and the second sensor signal are continuous vibration data relating to an industrial environment. In an embodiment, the second sensor in the sensor system 40030 is configured to be connected to a first machine. In an embodiment, the second sensor in the sensor system 40030 is configured to be connected to a second machine in the industrial environment. In an embodiment, the computing environment of the platform is configured to compare the relative phases of the first and second sensor signals. In an embodiment, the first sensor is a single-axis sensor and the second sensor is a three-axis sensor. In an embodiment, at least one of the multiple inputs of the crosspoint switch 40060 includes Internet Protocol front-end signal conditioning to improve the signal-to-noise ratio. In an embodiment, the crosspoint switch 40060 includes a third input configured as a continuously monitored alarm having a predetermined trigger condition when the third input is not assigned to one of the multiple outputs.

In an embodiment, the multiple inputs of the crosspoint switch 40060 include a third input connected to the second sensor and a fourth input connected to the second sensor.
The first sensor signal is from a single-axis sensor at a fixed position relative to the first machine. In an embodiment, the second sensor is a three-axis sensor. In an embodiment, the sensor system 40030 is configured to simultaneously record gap-free digital waveform data from at least a first input, a second input, a third input, and a fourth input. In an embodiment, the platform is configured to determine a relative phase change based on the simultaneously recorded gap-free digital waveform data. In an embodiment, the second sensor is configured to be movable to multiple positions relative to the first machine while acquiring the simultaneously recorded gap-free digital waveform data. In an embodiment, the multiple outputs of the crosspoint switch include a third output and a fourth output. The second, third, and fourth outputs are assigned together to a series of three-axis sensors, each positioned at a different position relative to the machine. In an embodiment, the platform is configured to determine an operational deflection shape based on the relative phase change and the simultaneously recorded gap-free digital waveform data.

In an embodiment, the invariant position is a position relative to an axis of rotation of the first machine. In an embodiment, each of the three-axis sensors in the sequence of three-axis sensors is located at a different position on the first machine, but is associated with a different bearing on the machine. In an embodiment, each of the three-axis sensors in the sequence of three-axis sensors is located at a similar position relative to a similar bearing, but is associated with a different machine. In an embodiment, the sensor system 40030 is configured to acquire simultaneously recorded gap-free digital waveform data from the first machine while both the first machine and the second machine are operating. In an embodiment, the sensor system 40030 is configured to characterize contributions from the first machine and the second machine in the simultaneously recorded gap-free digital waveform data from the first machine. In an embodiment, the simultaneously recorded gap-free digital waveform data has a duration of more than one minute.

In an embodiment, a method for monitoring a machine having at least one shaft supported by a set of bearings includes monitoring a first data channel assigned to a one-axis sensor at a constant location relative to the machine. The method includes monitoring second, third, and fourth data channels assigned to respective axes of a three-axis sensor. The method includes simultaneously recording gap-free digital waveform data from all data channels while the machine is operating, and determining relative phase changes based on the digital waveform data.

In an embodiment, the triaxial sensor is positioned at multiple locations relative to the machine during digital waveform acquisition. In an embodiment, the second, third, and fourth channels are assigned together to a sequence of triaxial sensors, each positioned at a different location relative to the machine. In an embodiment, data is received simultaneously from all sensors. In an embodiment, the method includes determining an operational deflection shape based on the change in relative phase information and the waveform data. In an embodiment, the invariant location is a location relative to the shaft of the machine. In an embodiment, each triaxial sensor in the sequence of triaxial sensors is positioned at a different location and each associated with a different bearing of the machine. In an embodiment, the invariant location is a location relative to the shaft of the machine. Each triaxial sensor in the sequence of triaxial sensors is positioned at a different location and each associated with a different bearing supporting the shaft in the machine.

In an embodiment, the method includes monitoring a first data channel assigned to a one-axis sensor at a fixed location located on the second machine. The method includes monitoring second, third, and fourth data channels assigned to axes of a three-axis sensor located at a location relative to the second machine. The method also includes simultaneously recording gap-free digital waveform data from all data channels of the second machine while both of the second machines are operating. In an embodiment, the method includes characterizing the contribution from each machine in the simultaneously recorded gap-free digital waveform data from the second machines.

In some embodiments, on-device sensor fusion and data storage for industrial IoT devices is supported, where data from multiple sensors is multiplexed on the device and a fused data stream is stored. For example, pressure and temperature data may be multiplexed into a combined pressure-temperature data stream in a time series, e.g., byte-like structure (time, pressure, and temperature are bytes in the data structure, so that pressure and temperature remain linked in time without requiring separate processing of the streams by an external system), or by addition, division, multiplication, subtraction, etc., allowing the fused data to be stored on the device. Any of the sensor data described in this disclosure, including vibration data, can be fused in this manner and stored in a local data pool, storage, or data collector, machine component, or other IoT device.

In some embodiments, the set of digital twins may represent an entire organization, such as an energy production organization, an oil and gas organization, a renewable energy production organization, an aerospace manufacturer, a vehicle manufacturer, a heavy equipment manufacturer, a mining organization, a drilling organization, or an offshore platform organization. In these examples, the digital twin may include a digital twin of one or more industrial facilities of the organization.

In an embodiment, the digital twin management system 40002 generates a digital twin. A digital twin may be composed of other digital twins (e.g., via reference). In this manner, a discrete digital twin may be composed of a collection of other discrete digital twins. For example, a digital twin of a machine may include digital twins of sensors installed on the machine, digital twins of components that make up the machine, digital twins of other devices built into or integrated with the machine (e.g., systems that provide input to or obtain output from the machine), and/or digital twins of products or other items produced by the machine. Taking this example a step further, a digital twin of an industrial facility (e.g., a factory) may include a digital twin representing the layout of the industrial facility, including the placement of physical assets and systems in and around the facility, as well as digital assets of assets within the facility (e.g., digital twins of machines), digital twins of storage locations within the facility, digital twins of people collecting vibration measurements from machines within the facility, and so on. In this second example, the digital twin of the industrial facility may reference embedded digital twins, which may in turn reference other digital twins embedded within those digital twins.

In some embodiments, a digital twin may represent an abstract entity such as a workflow or process, including its inputs, outputs, sequence of steps, decision points, processing loops, etc. For example, a digital twin may be a digital representation of a manufacturing process, a logistics workflow, an agricultural process, a mineral extraction process, etc. In these embodiments, the digital twin may include references to industrial entities involved in the workflow or process. A digital twin of a manufacturing process may reflect various stages of the process. In some of these embodiments, the digital twin system 40000 receives real-time data from the industrial facility where the manufacturing process takes place (e.g., from the sensor system 40030 of the environment 40020) and reflects the current (or substantially current) state of the process in real time.

In embodiments, the digital representation may include a set of data structures (e.g., classes) that collectively define a set of properties and/or possible behaviors of the represented physical object 40022, device 40024, sensor 40026, or environment 40020. For example, the set of properties of a physical object 40022 may include the type of physical object, the dimensions of the object, the mass of the object, the density of the object, the material of the object, the physical properties of the material, the surface of the physical object, the state of the physical object, the location of the physical object, identifiers of other digital twins contained within the object, and/or other suitable properties. Examples of the behavior of a physical object include the state of the physical object (e.g., solid, liquid, gas), the melting point of the physical object, the density of the physical object when in a liquid state, the viscosity of the physical object when in a liquid state, the freezing point of the physical object, the density of the physical object when in a solid state, and the hardness of the physical object when in a solid state. Examples of characteristics include the malleability of a physical object, the buoyancy of a physical object, the conductivity of a physical object, the fire point of a physical object, how humidity affects a physical object, how water or other liquids affect a physical object, the terminal velocity of a physical object, etc. In another example, a set of device characteristics includes the type of device, the dimensions of the device, the mass of the device, the density of the device, the material of the device, the physical properties of the material, the surface of the device, the output of the device, the state of the device, the location of the device, the trajectory of the device, the vibration characteristics of the device, identifiers of other digital twins to which the device is connected and/or contains, etc. Examples of equipment behavior include the maximum acceleration of the device, the maximum speed of the device, the operating range of the device, the heating profile of the device, the cooling profile of the device, the process performed by the device, the operation performed by the device, etc. Examples of environmental characteristics include the dimensions of the environment, the boundaries of the environment, the temperature of the environment, the humidity of the environment, the airflow of the environment, physical objects in the environment, and the currents of the environment (in the case of a body of water). Examples of environmental behavior include scientific laws that govern the environment, processes that govern the environment, processes that do not govern the environment, processes that do not govern the environment, processes that do not govern the environment, processes that do not govern the environment, processes that do not govern the environment, processes that do not govern the environment, and so on.
It includes what happens in the environment and the rules and regulations that must be followed in the environment.

In embodiments, a property of the digital twin may be adjusted. For example, the temperature of the digital twin, the humidity of the digital twin, the shape of the digital twin, the material of the digital twin, the dimensions of the digital twin, or any other suitable parameter may be adjusted. When a property of the digital twin is adjusted, other properties may also be affected. For example, if the temperature of the environment 40020 increases, the pressure in the environment (e.g., the pressure of a gas according to the ideal gas law) may also increase. In another example, if a digital twin of a sub-freezing environment is raised to a temperature above freezing, the property of an embedded twin of solid water (i.e., ice) may change over time to a liquid state.

The digital twin may be represented in several different forms. In embodiments, the digital twin may be a visual digital twin rendered by a computing device to allow a human user to view digital representations of the environment 40020 and/or the physical objects 40022, devices 40024, and/or sensors 40026 within the environment. In embodiments, the digital twin may be rendered and output to a display device. In some of these embodiments, the digital twin may be rendered in a graphical user interface to allow a user to interact with the digital twin. For example, a user may be able to "drill down" into a particular element (e.g., a physical object or device) to view additional information about that element (e.g., the state of the physical object or device, properties of the physical object or device, etc.). In some embodiments, the digital twin may be rendered and output in a virtual reality display. For example, a user may view a 3D rendering of the environment (e.g., using a monitor or virtual reality headset). The user may then view/inspect the digital twins of the physical assets or devices within the environment.

In some embodiments, the data structure of a visual digital twin (i.e., a digital twin configured to be displayed in a 2D or 3D manner) may include surfaces (e.g., splines, meshes, polygon meshes, etc.). In some embodiments, the surfaces may include texture data, shading information, and/or reflection data. In this manner, the surfaces may be displayed more realistically. In some embodiments, such surfaces may be rendered by a visualization engine (not shown) when the digital twin is in the field of view and/or when present in a larger digital twin (e.g., a digital twin of an industrial environment). In these embodiments, the digital twin system 40000 may render:
The rendered digital twin is depicted as a set of adjacent surfaces.

In an embodiment, a user can provide input via a graphical user interface to control one or more properties of a digital twin. For example, a user may provide input to change a property of a digital twin. In response, the digital twin system 40000 can calculate the impact of the changed property and update the digital twin and other digital twins affected by the property change.

In embodiments, a user can view a process (e.g., manufacturing a product, extracting minerals from a mine or well, inspecting livestock, etc.) being performed on one or more digital twins. In these embodiments, a user can view the entire process or a specific step within the process.

In some embodiments, a digital twin (and any digital twins embedded therein) may be represented in a non-visual representation (or "data representation"). In these embodiments, the digital twin and any embedded digital twins exist in a binary representation, but relationships between the digital twins are maintained. For example, in embodiments, each digital twin and/or its components may be represented by a set of physical dimensions that define the shape of the digital twin (or its components). Additionally, a data structure embodying a digital twin may include the location of the digital twin. In some embodiments, the location of the digital twin may be provided by a set of coordinates. For example, a digital twin of an industrial environment may be defined with respect to a coordinate space (e.g., Cartesian coordinate space, polar coordinate space, etc.). In embodiments, an embedded digital twin may be represented as a set of one or more ordered triples (e.g., [x coordinate, y coordinate, z coordinate] or other vector-based representation). In some of these embodiments, each ordered triple may represent the location of a particular point (e.g., center point, top point, bottom point, etc.) on an industrial entity (e.g., object, device, or sensor) in relation to the environment in which the industrial entity resides. In some embodiments, a digital twin's data structure may include vectors that indicate the digital twin's motion relative to its environment. For example, a fluid (e.g., a liquid or gas) or solid may be represented by a vector that indicates the velocity (e.g., direction and magnitude of velocity) of the entity represented by the digital twin. In embodiments, vectors within a twin may represent microscopic subcomponents, such as particles within a fluid, and the digital twin may represent physical properties such as displacement, velocity, acceleration, momentum, etc.
These include kinetic energy, vibrational properties, thermal properties, and electromagnetic properties.

In some embodiments, a set of two or more digital twins may be represented by a graph database including nodes and edges connecting the nodes. In some embodiments, the edges may represent spatial relationships (e.g., "abuts," "rests upon," "contains," etc.). In these embodiments, each node in the graph database may represent a digital twin of an entity (e.g., an industrial entity) and may include a data structure that defines the digital twin. In these embodiments, each edge in the graph database may represent a relationship between the two entities represented by the connected nodes. In some embodiments, the edges may represent spatial relationships (e.g., "abuts," "rests upon," "interlocks with," "bears," "contains," etc.). In embodiments, various types of data may be stored on the nodes or edges. In embodiments, the nodes may store property data, status data, and/or metadata related to the facility, system, subsystem, and/or component. The type of property data and status data varies depending on the entity represented by the node. For example, a node representing a robot may include property data indicating what material the robot is made of, the dimensions of the robot (or its components), the mass of the robot, etc. In this example, state data for the robot may include the robot's current pose, its position, etc. In embodiments, an edge may store relationship data and metadata data related to the relationship between two nodes. Examples of relationship data may include the nature of the relationship, whether the relationship is persistent (e.g., a fixed component will have a persistent relationship with the structure it is attached to or rests on), etc. In embodiments, an edge may include metadata regarding the relationship between two entities. For example, if a product is produced on an assembly line, one relationship that might be recorded between the product's digital twin and the assembly line may be "Created by." In these embodiments, an example edge representing a "Created by" relationship might include a timestamp indicating when the product was created. In another example, a sensor may take measurements related to the state of a device, whereby one relationship between the sensor and the device may include "measured" and define the type of measurement taken by the sensor. In this example, the metadata stored on the edge may include a list of N measurements taken and a timestamp for each measurement. In this manner, temporal data relating to the nature of the relationship between two entities may be maintained, thereby providing a visualization engine for leveraging such temporal relationship data, such as by aligning different data sets to a series of points in time, to facilitate causal analysis for use in analytics engines, machine learning engines, and/or predictive systems.

In some embodiments, a graph database may be implemented in a hierarchical manner, such that the graph database relates a set of facilities, systems, and components. For example, a digital twin of a manufacturing environment may include a node representing the manufacturing environment. The graph database may further include nodes representing various systems within the manufacturing environment, such as an HVAC system, a lighting system, a manufacturing system, etc., all of which may connect to the node representing the manufacturing system. In this example, each system may further connect to various subsystems and/or components of the system. For example, within an HVAC system, the HVAC system may connect to a subsystem node representing the facility's cooling system, a second subsystem node representing the facility's heating system, a third subsystem node representing the facility's fan system, and one or more nodes representing the facility's thermostat (or thermostats). Furthering this example, subsystem nodes and/or component nodes may connect to lower-level nodes that contain subsystem nodes and/or component nodes. For example, a subsystem node representing a cooling subsystem may be connected to a component node representing an air conditioning unit. Similarly, a component node representing a thermostat device may be connected to one or more component nodes representing various sensors (e.g., temperature sensors, humidity sensors, etc.).

In embodiments where a graph database is implemented, the graph database may relate to a single environment or may represent a larger enterprise. In the latter scenario, an enterprise may have various manufacturing and distribution facilities. In these embodiments, an enterprise node representing the enterprise may be connected to environment nodes for each facility. In this manner, digital twin system 40000 may maintain digital twins for multiple industrial facilities of an enterprise.

In embodiments, digital twin system 40000 may use the graph database to generate a digital twin that may be rendered and displayed and/or represented in a data representation. In the former scenario, digital twin system 40000 may receive a request to render a digital twin, whereby the request includes one or more parameters indicating the view to be rendered. For example, the one or more parameters may indicate the industrial environment to be rendered and the type of rendering (e.g., a "real-world view" that depicts the environment as a human would see it, an "infrared view" that depicts objects as a function of their respective temperatures, an "airflow view" that depicts airflow through the digital twin, etc.). In response, digital twin system 40000 may traverse the graph database and determine the configuration of the environment to be rendered based on nodes in the graph database that are related (either directly or through descendent nodes) to the environment's environment nodes and the edges that define the relationships between the related nodes. Having determined the configuration, digital twin system 40000 may identify the surfaces to be rendered and render those surfaces. The digital twin system 40000 may then render the requested digital twin by connecting the surfaces according to the configuration. The rendered digital twin may then be output to a viewing device (e.g., a VR headset, a monitor, etc.). In some scenarios, the digital twin system 40000 may receive real-time sensor data from the sensor system 40030 of the environment 40020 and update the visual digital twin based on the sensor data. For example, the digital twin system 40000 may receive sensor data (e.g., vibration data from the vibration sensor 40036) related to a motor and its set of bearings. Based on the sensor data, the digital twin system 40000 may update the visual digital twin to show the approximate vibration characteristics of the set of bearings within the motor's digital twin.

In scenarios in which the digital twin system 40000 provides a data representation of a digital twin (e.g., for dynamic modeling, simulation, or machine learning), the digital twin system 40000 may traverse the graph database to determine the configuration of the depicted environment based on nodes in the graph database that are related (either directly or through descendent nodes) to environment nodes of the environment and edges that define relationships between the related nodes. In some scenarios, the digital twin system 40000 may receive real-time sensor data from a sensor system 40030 of the environment 40020 and apply one or more dynamic models to the digital twin based on the sensor data. In other scenarios, the digital twin data representation may be used to perform simulations, as discussed in more detail throughout this specification.

In some embodiments, the digital twin system 40000 may implement a digital ghost that runs on the digital twin of the industrial environment. In these embodiments, the digital ghost may monitor one or more sensors of the sensor system 40030 to detect anomalies in the industrial environment that may indicate a malicious virus or other security issue.

As described, the digital twin system 40000 may include a digital twin management system 40002, a digital twin I/O system 40004, a digital twin simulation system 40006, a digital twin dynamic model system 40008, a cognitive intelligence system 40010, and/or an environmental control module 40012.

In embodiments, the digital twin management system 40002 creates new digital twins, maintains/updates existing digital twins, and/or renders digital twins. The digital twin management system 40002 may receive user input, uploaded data, and/or sensor data to create and maintain existing digital twins. Upon creating a new digital twin, the digital twin management system 40002 may store the digital twin in the digital twin data store 40016. Creating, updating, and rendering digital twins are discussed in more detail throughout this disclosure.

In embodiments, the digital twin I/O system 40004 receives input from various sources and outputs data to various recipients. In embodiments, the digital twin I/O system receives sensor data from one or more sensor systems 40030. In these embodiments, each sensor system 40030 may include one or more IoT sensors that output their respective sensor data. Each sensor may be assigned an IP address or have another suitable identifier. Each sensor may output a sensor packet that includes the sensor's identifier and the sensor data. In some embodiments, the sensor packet may further include a timestamp indicating the time the sensor data was collected. In some embodiments, the digital twin I/O system 40004 may interface with the sensor system 40030 via real-time sensor connectivity 40014, such as a webhook, API, or the like. In these embodiments, one or more devices (e.g., sensors, aggregators, edge devices) in the sensor system 40030 may send sensor packets containing sensor data to the digital twin I/O system 40004 via a webhook, API, or the like. The digital twin I/O system may determine which sensor system 40030 sent the sensor packet and its contents, and provide the sensor data and other relevant data (e.g., timestamp, environment identifier/sensor system identifier, etc.) to the digital twin management system 40002.

In embodiments, the digital twin I/O system 40004 may receive imported data from one or more sources. For example, the digital twin system 40000 may provide a portal for users to create and manage their own digital twins. In these embodiments, the user may upload one or more files (e.g., image files, LIDAR scans, blueprints, etc.) associated with the new digital twin being created. In response, the digital twin I/O system 40004 may provide the imported data to the digital twin management system 40002. The digital twin I/O system 40004 may receive other suitable types of data without departing from the scope of this disclosure.

In some embodiments, the digital twin simulation system 40006 is configured to run simulations using the digital twin. For example, the digital twin simulation system 40006 may iteratively adjust one or more parameters of the digital twin and/or one or more embedded digital twins. In embodiments, the digital twin simulation system 40006 may run a simulation based on the set of parameters for each set of parameters and collect simulation result data resulting from the simulation. In other words, the digital twin simulation system 40006 may collect characteristics of the digital twin and the digital twins within or including the digital twin used during the simulation, as well as any results resulting from the simulation. For example, when running a simulation on a digital twin of an indoor farming facility, the digital twin simulation system 40006 may vary temperature, humidity, airflow, carbon dioxide, and/or other relevant parameters and run a simulation that outputs results resulting from different combinations of parameters. In another example, the digital twin simulation system 40006 may simulate the operation of a particular machine in an industrial facility that generates an output given a set of inputs. In some embodiments, the inputs may be varied to determine the machine's effect on its output. In another example, the digital twin simulation system 40006 may simulate vibrations of a machine and/or machine components. In this example, the digital twin of the machine may include a set of operating parameters, interfaces, and capabilities of the machine. In some embodiments, the operating parameters may be varied to evaluate the effectiveness of the machine. The digital twin simulation system 40006 is described in further detail throughout this disclosure.

In an embodiment, digital twin dynamic model system 40008 is configured to model one or more behaviors for a digital twin of an environment. In an embodiment, digital twin dynamic model system 40008 may receive a request to model a certain behavior for an environment or a process and model that behavior using a dynamic model, a digital twin of the environment or process, and sensor data collected from one or more sensors monitoring the environment or process. For example, an operator of a machine that has bearings may want to model the behavior of the bearings.
The digital twin dynamic model system 40008 may measure vibrations in the machine and/or bearings to determine whether the machine and/or bearings can withstand the increased power output. In this example, the digital twin dynamic model system 40008 may execute a dynamic model configured to determine whether the increased power output will result in adverse consequences (e.g., failure, downtime, etc.). The digital twin dynamic model system 40008 is described in further detail throughout this disclosure.

In embodiments, the cognitive processing system 40010 performs machine learning and artificial intelligence related tasks on behalf of the digital twin system. In embodiments, the cognitive processing system 40010 may train any suitable type of model, including, but not limited to, various types of neural networks, regression models, random forests, decision trees, hidden Markov models, Bayesian models, etc. In embodiments, the cognitive processing system 40010 trains the machine learning model using the output of a simulation performed by the digital twin simulation system 40006. In some of these embodiments, the results of the simulation may be used to supplement training data collected from real-world environments and/or processes. In embodiments, the cognitive processing system 40010 utilizes the machine learning model to make predictions, identifications, classifications, and provide decision support related to the real-world environments and/or processes represented by the respective digital twin.

For example, a machine-learned predictive model may be used to predict the cause of irregular vibration patterns (e.g., suboptimal vibration, critical, or alarm vibration fault conditions) in bearings of an engine at an industrial facility. In this example, the cognitive processing system 40010 may receive vibration sensor data from one or more vibration sensors located on or near the engine, may receive maintenance data from the industrial facility, and may generate a feature vector based on the vibration sensor data and maintenance data. The cognitive processing system 40010 may input the feature vector into a machine learning model trained specifically for the engine (e.g., using a combination of simulation data and real-world data on the causes of irregular vibration patterns) to predict the cause of the irregular vibration pattern. In this example, possible causes of the irregular vibration pattern may include loose bearings, insufficient bearing lubrication, misaligned bearings, worn bearings, bearing phases that may be aligned with the engine phase, loose housings, and loose bolts.

In another example, a machine-learned model may be used to provide decision support for bringing bearings in an engine at an industrial facility, which is operating in a suboptimal vibration fault level state, to a normal operating vibration fault level state. In this example, the cognitive processing system 40010 may receive vibration sensor data from one or more vibration sensors located on or near the engine, may receive maintenance data from the industrial facility, and may generate a feature vector based on the vibration sensor data and the maintenance data. The cognitive processing system 40010 may input the feature vector into a machine learning model trained specifically for the engine (e.g., using a combination of simulated and real-world data for solutions to irregular vibration patterns) to provide decision support for achieving a normal operating fault level state for the bearings. In this example, the decision support may be a recommendation to tighten the bearings, lubricate the bearings, recondition the bearings, order new bearings, order new parts, collect additional vibration measurements, change the engine operating speed, tighten the housing, tighten the bolts, etc.

In another example, machine-learned models may be used to provide decision support related to vibration measurement collection by workers. In this example, the cognitive processing system 40010 may receive historical vibration measurement data from an industrial facility and generate feature vectors based on the historical vibration measurement data. The cognitive processing system 40010 may input the feature vectors into an engine-specific trained machine learning model (e.g., using a combination of simulation data and real historical vibration measurement data) to provide decision support regarding the selection of vibration measurement locations.

In yet another example, a machine-learned model may be used to identify vibration signatures associated with problems with machinery and/or machine components. In this example, the cognitive processing system 40010 may receive historical vibration measurement data from an industrial facility and generate feature vectors based on the historical vibration measurement data. The cognitive processing system 40010 may input the feature vectors into a machine learning model trained specifically for the engine (e.g., using a combination of simulation data and real-world historical vibration measurement data) to identify vibration signatures associated with the machinery and/or machine components. The foregoing examples are non-limiting, and the cognitive processing system 400f0 may be used for other suitable AI/machine learning-related tasks performed in connection with an industrial facility.

In embodiments, the environmental control system 40012 controls one or more aspects of an industrial facility. In some of these embodiments, the environmental control system 40012 may control one or more devices within the industrial environment. For example, the environmental control system 40012 may control one or more machines within the environment, robots within the environment, HVAC systems within the environment, alarm systems within the environment, assembly lines within the environment, etc. In embodiments, the environmental control system 40012 may utilize the digital twin simulation system 40006, the digital twin dynamic model system 40008, and/or the cognitive process system 40010 to determine one or more control instructions. In embodiments, the environmental control system 40012 may implement a rule-based and/or machine learning approach to determine the control instructions. In response to determining the control instructions, the environmental control system 40012 may output the control instructions to the intended devices within the particular environment via the digital twin I/O system 40004.

FIG. 214 illustrates an exemplary digital twin management system 40002 according to some embodiments of the present disclosure. In an embodiment, the digital twin management system 40002 includes, but is not limited to, a digital twin creation module 40064, a digital twin update module 40066, and a digital twin visualization module 40068.

In embodiments, the digital twin creation module 40064 may create a new digital twin of a set of environments using input from a user, imported data (e.g., blueprints, specifications, etc.), image scans of the environment, 3D data from LIDAR devices and/or SLAM sensors, and other suitable data sources. For example, a user (e.g., a user belonging to an organization/customer account) may provide input to create a new digital twin of an environment via a client application 40070. In doing so, the user may upload 2D or 3D image scans of the environment and/or blueprints of the environment. The user may also upload 3D data captured with a camera, LIDAR device, IR scanner, an array of SLAM sensors, radar device, EMF scanner, etc. In response to the provided data, the digital twin creation module 40064 may create a 3D representation of the environment, which may include any objects captured in the image data/detected in the 3D data. In embodiments, the cognitive processing system 40072 may analyze input data (e.g., blueprints, image scans, 3D data) to classify rooms, hallways, equipment, etc. and assist in generating the 3D representation. In some embodiments, the digital twin creation module 40064 may map the digital twin into a 3D coordinate space (e.g., a Cartesian space with x, y, and z axes).

In some embodiments, the digital twin creation module 40064 may output a 3D representation of the environment to a graphical user interface (GUI). In some of these embodiments, a user may identify specific areas and/or objects and provide input related to the identified areas and/or objects. For example, a user may label a specific room, piece of equipment, machine, etc. Additionally or alternatively, a user may provide data related to the identified objects and/or areas. For example, when identifying equipment, a user may provide the serial number/model number of the equipment. In some embodiments, the digital twin creation module 40064 may obtain information from the manufacturer of the device, equipment, or machine. This information may include one or more characteristics and/or operation of the device, equipment, or machine. In some embodiments, a user may identify the location of sensors in the environment via the GUI. For each sensor, the user may provide the sensor type and associated data (e.g., manufacturer, model, IP address, etc.). The digital twin creation module 40064 may record the location (e.g., the x, y, z coordinates of the sensor) in the digital twin of the environment. In embodiments, digital twin system 40000 may employ one or more systems to automate the population of the digital twin. For example, digital twin system 40000 may employ a machine vision-based classifier to classify the make and model of a device, equipment, or sensor. Additionally or alternatively, digital twin system 40000 may repeatedly ping known sensors of different types to identify the presence of specific types of sensors in the environment. Each time a sensor responds to a ping, digital twin system 40000 may infer the make and model of the sensor.

In some embodiments, a manufacturer may provide or make available digital twins of its products (e.g., sensors, devices, machines, equipment, raw materials, etc.). In these embodiments, the digital twin creation module 40064 may import digital twins of one or more products identified in the environment and embed those digital twins into the digital twin of the environment. In embodiments, embedding a digital twin within another digital twin may include creating a relationship between the embedded digital twin and the other digital twin. In these embodiments, the manufacturer of the digital twin may define the behavior and/or characteristics of each product. For example, a digital twin of a machine may define how the machine operates, the machine's inputs/outputs, etc. In this way, the machine's digital twin can reflect the behavior of the machine given a set of inputs.

In embodiments, a user can define one or more processes that occur in the environment. In these embodiments, a user can define the steps of the process, the machines/devices that perform each step of the process, the inputs to the process, and the outputs of the process.

In embodiments, the digital twin creation module 40064 may create a graph database that defines the relationships between the set of digital twins. In these embodiments, the digital twin creation module 40064 may create nodes for the environment, the systems and subsystems of the environment, the devices in the environment, the sensors in the environment, the workers operating in the environment, the processes running in the environment, etc. In embodiments, the digital twin creation module 40064 may write the graph database representing the set of digital twins to the digital twin data store 40016.

In an embodiment, for each node, the digital twin creation module 40064 may include in the node representing an entity any data related to the entity. For example, when defining a node representing an environment, the digital twin creation module 40064 may include in the node dimensions, boundaries, layout, paths, and other relevant spatial data. Additionally, the digital twin creation module 40064 may define a coordinate space relative to the environment. If the digital twin may be rendered, the digital twin creation module 40064 may include in the node references to any shapes, meshes, splines, surfaces, etc. that may be used to render the environment. When representing a system, subsystem, device, or sensor, the digital twin creation module 40064 may create a node for each entity and include any associated data. For example, the digital twin creation module 40064 may create a node representing a machine in the environment. In this example, the digital twin creation module 40064 may include in the node representing the machine dimensions, behavior, characteristics, location, and/or any other suitable data related to the machine. The digital twin creation module 40064 may connect nodes of related entities with edges, thereby creating relationships between the entities. The relationships created between the entities may then define the type of relationship characterized by the edge. When representing a process, the digital twin creation module 40064 may create a node for the entire process or a node for each step in the process. In some of these embodiments, the digital twin creation module 40064 may associate a node of the process with a node representing a machine/device that performs the step of the process. In embodiments in which an edge connects a process step node to a machine/device that performs the process step, one of the edges or nodes may include information indicating the inputs to the step, the outputs of the step, the amount of time the step takes, the nature of the processing of the inputs to generate the outputs, the set of states or modes the process can undergo, etc.

In embodiments, the digital twin update module 40066 updates the set of digital twins based on the current state of one or more industrial entities. In some embodiments, the digital twin update module 40066 receives sensor data from the industrial environment sensor system 40030 and updates the state of the digital twin of the industrial environment and/or any affected systems, subsystems, devices, workers, processes, etc. As described, the digital twin I/O system 40004 may receive the sensor data in one or more sensor packets. The digital twin I/O system 40004 may provide the sensor data to the digital twin update module 40066 and may identify the environment from which the sensor packet was received and the sensor that provided the sensor packet. In response to the sensor data, the digital twin update module 40066 may update the state of one or more digital twins based on the sensor data. In some of these embodiments, the digital twin update module 40066 may update records (e.g., anodes in a graph database) corresponding to the sensors that provided the sensor data to reflect the current sensor data. In some scenarios, the digital twin updating module 40066 may identify specific areas in the environment monitored by sensors and update records (e.g., nodes in a graph database) to reflect current sensor data. For example, the digital twin updating module 40066 may receive sensor data reflecting different vibration characteristics of a machine and/or machine component. In this example, the digital twin updating module 40066 may update records representing the vibration sensors that provided the vibration sensor data and/or records representing the machine and/or machine component to reflect the vibration sensor data. In another example, in some scenarios, workers in industrial environments (e.g., manufacturing facilities, industrial storage facilities, mines, excavation operations, etc.) may be required to wear wearable devices (e.g., smart watches, smart helmets, smart shoes, etc.). In these embodiments, the wearable device may collect sensor data related to the worker (e.g., location, movement, heart rate, respiration rate, temperature, etc.) and/or the environment surrounding the worker and may communicate the collected sensor data to the digital twin system 40000 (e.g., via real-time sensor connectivity 40014, such as webhooks), either directly or through an aggregation device in the sensor system. In response to receiving sensor data from the worker's wearable device, the digital twin update module 40066 may update the worker's digital twin to reflect, for example, the worker's location, the worker's trajectory, the worker's health status, etc. In some of these embodiments, the digital twin update module 40066 may update the edges connecting the nodes representing the worker and/or the nodes representing the environment to the collected sensor data to reflect the worker's current state.

In some embodiments, the digital twin update module 40066 may provide sensor data from one or more sensors to the digital twin dynamic model system 40008, which may model the environment and/or the operation of one or more industrial entities to estimate additional state data.

In embodiments, the digital twin visualization module 40068 receives a request to view a visual digital twin or portion thereof. In embodiments, the request may indicate the digital twin to be viewed (e.g., an environment identifier). In response, the digital twin visualization module 40068 may determine the requested digital twin and other digital twins implied by the request. For example, when requesting to view the digital twin of an environment, the digital twin visualization module 40068 may also identify digital twins of any industrial entities within the environment. In embodiments, the digital twin visualization module 40068 may identify spatial relationships between the industrial entities and the environment, for example, based on relationships defined in a graph database. In these embodiments, the digital twin visualization module 40068 may determine the relative positions of embedded digital twins within the containing digital twin, the relative positions of adjacent digital twins, and/or the transitivity of the relationships (e.g., whether an object is fixed at a point or whether the object moves). The digital twin visualization module 40068 may render the requested digital twin and other related digital twins based on the identified relationships. In some embodiments, the digital twin visualization module 40068 may determine, for each digital twin, a digital twin surface. In some embodiments, the digital surface may be defined or referenced in a record corresponding to the digital twin, which may be provided by a user, determined from imported images, or defined by the manufacturer of the industrial entity. In scenarios where an object can assume different poses or shapes (e.g., an industrial robot), the digital twin visualization module 40068 may determine the pose or shape of the object for the digital twin. The digital twin visualization module 40068 may embed the digital twin in the requested digital twin and output the requested digital twin to the client application.

In some embodiments, the digital twin update module 40004 may provide sensor data from one or more sensors to the digital twin dynamic system 40008, which may model the behavior of the environment and/or one or more industrial entities to estimate additional state data. For example, if an industrial storage facility includes temperature sensors 40032 at four entrances and exits to a large space, each of the temperature sensors 40032 outputting a respective temperature reading corresponding to the ambient temperature surrounding the temperature sensor 40032, the digital twin dynamic system 40008 may determine the temperature of other, unmonitored areas of the industrial storage facility. In this example, the digital twin dynamic system 40008 may output the determined temperatures to the digital twin update module 40004, which may update the digital twin of the environment to reflect the extrapolated temperatures. In these exemplary embodiments, the determined temperatures may be used in any number of downstream applications. In some embodiments, the digital twin system 40004 may output the extrapolated temperatures (and temperatures measured by sensors) to a monitoring system that classifies overheated or improper temperatures in the environment. For example, the digital twin system 40004 may output the extrapolated temperature of a bearing, such that determining an overheated bearing indicates a fault in rotating machinery. In another example, the digital twin system 40004 may output the extrapolated temperature of a brake pad, such that determining that the brake pad is overheated indicates a brake failure. In another example, the digital twin system 40004 may output the extrapolated temperature of a food production facility, such that an improper temperature (e.g., below a minimum threshold or above an upper threshold) may lead to spoilage of perishable goods. In another example, the digital twin system 40004 may output the extrapolated temperature for a chemical process, such that an improper temperature (e.g., below a minimum threshold or above an upper threshold) may lead to a failure of the chemical-based process. In another example, the digital twin system 40004 may output an extrapolated temperature for the growing facility, such that inappropriate temperatures (e.g., below a minimum threshold or above an upper threshold) can lead to crop failure. In another example, the digital twin system 40004 may output the extrapolated temperature (and the temperature measured by the sensor) to a control system (e.g., an HVAC controller) that adjusts the temperature in the environment based on the extrapolated temperature and/or the temperature measured by the sensor.

In some of these embodiments, the request to view the digital twin may further indicate a view type. As discussed, in some embodiments, the digital twin may be depicted in a number of different view types. For example, an environment or device may be viewed in a “real-world” view, which depicts the environment or device as it normally would be; a “thermal” view, which depicts the environment or device in a manner that indicates the temperature of the environment or device; a “vibration” view, which depicts machines and/or machine components in an industrial environment in a manner that indicates the vibration characteristics of the machines and/or machine components; a “filtered” view, which displays only certain types of objects within the environment or device components (e.g., objects that require attention due to recognized fault conditions, alerts, updated reports, or other factors); an expanded view, which overlays data on the digital twin; and/or other suitable view types. In embodiments, the digital twin may be depicted in a number of different role-based view types. For example, devices in a manufacturing facility may be viewed in an “operator” view, which depicts the facility in a manner appropriate for facility operators; a “C-Suite” view, which depicts the facility in a manner appropriate for C-suite managers; and a “marketing” view, which depicts the facility in a manner appropriate for workers in sales and/or marketing roles. a "Board of Directors" view that depicts the facility in a manner suitable for board members, a "Regulatory" view that depicts the facility in a manner suitable for regulatory managers, and a "Human Resources" view that depicts the facility in a manner suitable for human resources personnel. In response to a request indicating a view type, the digital twin visualization module 40068 may retrieve data for each digital twin that corresponds to the view type. For example, if a user requests a vibration view of a factory floor, the digital twin visualization module 40068 may retrieve vibration data for the factory floor (which may include vibration measurements taken from different machines and/or machine components and/or vibration measurements extrapolated by the digital twin dynamic model system 40008 and/or simulated vibration data from the digital twin simulation system 40006), as well as available vibration data for any industrial entities that appear on the factory floor. In this example, the digital twin visualization module 40068 may determine a color corresponding to each machine component on the factory floor that represents the status of the vibration disturbance level (e.g., red for alarm, orange for critical, yellow for suboptimal, and green for normal operation). The digital twin visualization module 40068 then renders the digital twin of the mechanical components in the environment based on the determined color. Additionally or alternatively, the digital twin visualization module 40068 may render the digital twin of the mechanical components in the environment with indicators having the determined color. For example, if the vibration fault level condition of a motor's inbound bearing is suboptimal and the motor's outbound bearing is critical, the digital twin visualization module 40068 may render the digital twin of the inbound bearing with an indicator in a yellow shade (e.g., suboptimal) and the outbound bearing with an indicator in an orange shade (e.g., critical). Note that in some embodiments, the digital twin system TS06 may include an analytics system (not shown) that determines how the digital twin visualization system TS06 presents information to a human user. For example, the analytics system may track outcomes related to human interactions with real-world environments or objects in response to information presented in the visual digital twin. In some embodiments, the analytics system may apply cognitive models to determine the most effective way to display visualized information (e.g., what color to use to indicate an alarm condition, what motion or animation to use to draw attention to an alarm condition, etc.) or audio information (e.g., what sound to use to indicate an alarm condition) based on the results data. In some embodiments, the analytics system may apply cognitive models to determine the most appropriate way to display visualized information based on a user's role. In embodiments, the visualization may include displaying information related to the visualized digital twin, including graphical information, graphical information depicting vibration characteristics, graphical information depicting harmonic peaks, graphical information depicting peaks, vibration severity unit data, vibration fault level status data, recommendations from the cognitive intelligence system 40010, predictions from the cognitive intelligence system 40010, failure probability data, maintenance history data, time to failure data, downtime cost data, downtime probability data, repair cost data, machine replacement cost data, shutdown probability data, manufacturing KPIs, etc.

In another example, a user may request a filtered view of a process's digital twin, whereby the digital twin of the process shows only the components (e.g., machines or equipment) involved in the process. In this example, the digital twin visualization module 40068 may retrieve the process's digital twin as well as related digital twins (e.g., a digital twin of the environment and the digital twins of any machines or equipment that affect the process). The digital twin visualization module 40068 may then render each of the digital twins (e.g., the environment and related industrial entities) and then execute the process on the rendered digital twins. Note that because a process may be executed over a period of time and may involve moving items and/or parts, the digital twin visualization module 40068 may generate a series of consecutive frames showing the process. In this scenario, the movement of the machines and/or equipment involved in the process may be determined according to the behavior defined in the machines' and/or equipment's respective digital twins.

As described, the digital twin visualization module 40068 may output the requested digital twin to the client application 40070. In some embodiments, the client application 40070 is a virtual reality application, whereby the requested digital twin is displayed on a virtual reality headset. In some embodiments, the client application 40070 is an augmented reality application, whereby the requested digital twin is rendered on an AR-enabled device. In these embodiments, the requested digital twin may be filtered so that visual elements and/or text are overlaid on the display of the AR-enabled device.

Although a graph database has been described, it should be noted that the digital twin system 40000 may employ other suitable data structures for storing information related to a set of digital twins. In these embodiments, the data structures, and associated storage systems, may be implemented such that the data structures provide a degree of feedback loop and/or recursion in representing iterative flows.

FIG. 215 illustrates an example of a digital twin I/O system 40004 interfacing with an environment 40020, a digital twin system 40000, and/or components thereof to provide bidirectional transfer of data between coupled components, according to some embodiments of the present disclosure.

In embodiments, the transferred data includes signals (e.g., request signals, command signals, response signals, etc.) between connected components, which may include software components, hardware components, physical devices, virtualized devices, simulated devices, combinations thereof, etc. Signals may include material properties (e.g., physical quantities such as temperature, pressure, humidity, density, viscosity, etc.), measurements (e.g., real-time or stored values obtained by a device or system), device characteristics (e.g., device ID or device design specification characteristics, materials, measurement capabilities, dimensions, absolute position, relative position, combinations thereof, etc.), setpoints (e.g., target values for material properties, device properties, system properties, combinations thereof, etc.), and/or critical points (e.g., thresholds such as minimum and maximum values for material properties, device properties, system properties, etc.). Signals may be used to acquire data (e.g., directly measure or generate it) or otherwise obtain it (e.g., receive, calculate, lookup, filter, etc.). ) system or device, and may be communicated to or from the digital twin I/O system 40004 at predetermined times or in response to a request (e.g., polling) from the digital twin I/O system 40004. Communication may occur via direct or indirect connections (e.g., via intermediate modules in a circuit and/or intermediate devices between connected components). Values may correspond to real-world elements 40302r (e.g., inputs or outputs for tangible vibration sensors) or virtual elements 40302v (e.g., inputs or outputs for digital twin 40302d and/or simulated elements 40302s providing vibration data).

In an embodiment, the real-world elements 40302r may be elements within the industrial environment 40020. The real-world elements 40302r may include, for example, non-network elements 40022, devices 40024 (smart or non-smart), sensors 40026, and people 40028. The real-world elements 40302r may be process or non-process equipment within the industrial environment 40020. For example, process equipment may include motors, pumps, mills, fans, paint sprayers, welding machines, smelting machines, etc., and non-process equipment may include personal protective equipment, safety devices, emergency stations or devices (such as safety showers, eyewash stations, fire extinguishers, sprinkler systems, etc.), warehouse features (such as walls, floor layouts, etc.), obstacles (such as people or other items within the environment 40020), etc.

In embodiments, the virtual element 40302v may be a digital representation of, or correspond to, a contemporaneously existing real-world element 40302r. Additionally or alternatively, the virtual element 40302v may be a digital representation of, or correspond to, a real-world element 40302r available for later addition and implementation into the environment 40020. The virtual element may include, for example, a simulated element 40302s and/or a digital twin 40302d. In embodiments, the simulated element 40302s may be a digital representation of a real-world element 40302s that does not exist in the industrial environment 40020. The simulated element 40302s may mimic desired physical characteristics that can later be integrated into the environment 40020 as the real-world element 40302r (e.g., a "black box" that mimics the dimensions of the real-world element 40302r). The simulated elements 40302s may include digital twins of existing objects (e.g., a single simulated element 40302s may include one or more digital twins 40302d for existing sensors). Information related to the simulated elements 40302s may be obtained, for example, from a library (e.g., a physics library, a chemistry library, etc.) that defines the information and behavior of the simulated elements 40302s, by using mathematical models and algorithms to evaluate the behavior of the corresponding real-world elements 40302r.

In embodiments, the digital twin 40302d may be a digital representation of one or more real-world elements 40302r. The digital twin 40302d is configured to mimic, copy, and/or model the behavior and responses of the real-world elements 40302r in response to inputs, outputs, and/or conditions of the surrounding or ambient environment. Data related to the physical properties and responses of the real-world elements 40302r may be obtained, for example, via user input, sensor input, and/or physical modeling (e.g., thermodynamic models, electrodynamic models, mechanical dynamic models, etc.). Information for the digital twin 40302d may correspond to and be obtained from one or more real-world elements 40302r that correspond to the digital twin 40302d. For example, in some embodiments, digital twin 40302d may correspond to one real-world element 40302r that is a fixed digital vibration sensor 40036 on a mechanical component, and vibration data for digital twin 40302d may be obtained by polling or fetching vibration data measured by the fixed digital vibration sensor on the mechanical component. In a further example, digital twin 40302d may correspond to multiple real-world elements 40302r, each of which may be a fixed digital vibration sensor on the mechanical component, and vibration data for digital twin 40302d may be obtained by polling or fetching vibration data measured by each of the fixed digital vibration sensors on the multiple real-world elements 40302r. Additionally or alternatively, the vibration data of the first digital twin 40302d may be obtained by fetching vibration data of the second digital twin 40302d embedded within the first digital twin 40302d, or the vibration data of the first digital twin 40302d may include or be derived from the vibration data of the second digital twin 40302d. For example, the first digital twin may be a digital twin 40302d of the environment 40020 (alternatively referred to as an "environment digital twin"), and the second digital twin 40302d may be a digital twin 40302d corresponding to vibration sensors disposed within the environment 40020, such that the vibration data of the first digital twin 40302d is derived from or calculated based on data including the vibration data of the second digital twin 40302d.

In an embodiment, the digital twin system 40000 uses sensors 40026 to monitor characteristics of real-world elements 40302r within each environment 40020 that is, or may be, represented by the output of the model of the digital twin 40302d and/or one or more simulated elements 40302s. In an embodiment, the digital twin system 40000 can minimize network congestion while maintaining effective monitoring of the process by extending the polling interval of the sensor corresponding to the affected real-world element 40302r and/or minimizing data transfer and running the simulation (e.g., via the digital twin simulation system 106) during the extended interval using data obtained from other sources (e.g., sensors physically proximate to or affecting the affected real-world element 40302r). Additionally or alternatively, error checking may be performed by comparing collected sensor data with data obtained from the digital twin simulation system 106. For example, consistent deviations or variations between sensor data obtained from real-world element 40302r and simulated element 40302s may indicate a malfunction or another fault condition of the respective sensor.

In embodiments, the digital twin system 40000 may optimize characteristics of an environment through the use of one or more simulated elements 40302. For example, the digital twin system 40000 may evaluate the effects of simulated elements 40302s within the digital twin of the environment to quickly and efficiently determine the costs and/or benefits flowing from the inclusion, exclusion, or substitution of real-world elements 40302r within the environment 40020. The costs and benefits may include, for example, increased machinery costs (e.g., capital investment and maintenance), increased efficiency (e.g., process optimization to reduce waste or increase throughput), reduced or modified footprint within the environment 40020, extended or optimized service life, minimized component failure, minimized component downtime, etc.

In embodiments, the digital twin I/O system 40004 may include one or more software modules executed by one or more controllers of one or more devices (e.g., server devices, user devices, and/or distributed devices) to affect the described functionality. The digital twin I/O system 40004 may include, for example, an input module 400304, an output module 400306, and an adapter module 400308.

In embodiments, input module 400304 may obtain or import data from a data source in communication with digital twin I/O system 40004, such as sensor system 40030 or digital twin simulation system 40006. The data may be immediately used by digital twin system 40000 or stored within digital twin system 40000. Imported data may be captured from a data stream, a data batch, a combination thereof, in response to a trigger event, etc. Input module 400304 may receive data in a format suitable for transferring, reading, and/or writing information within digital twin system 40000.

In embodiments, the output module 400306 may output or export data to other system components (e.g., the digital twin data store 40016, the digital twin simulation system 40006, the cognitive intelligence system 40010, etc.), the device 40024, and/or the client application 40070. The data may be output as a data stream, a data batch, in response to a triggering event (e.g., a request), a combination thereof, etc. The output module 400306 may output the data in a format suitable for use or storage by the target element (e.g., one protocol for output to a client application and another protocol for the digital twin data store 40016, etc.).

In embodiments, the adapter module 400308 may process and/or convert data between the input module 400304 and the output module 400306. In embodiments, the adapter module 400308 may convert and/or route data automatically (e.g., based on data type) or in response to a received request (e.g., in response to information within the data).

In an embodiment, the digital twin system 40000 may represent a set of industrial workpiece elements as a digital twin, and the digital twin simulation system 40006 may simulate a set of physical interactions of a worker with the workpiece elements. The simulated physical interactions may include, for example, workpiece movement (e.g., a worker carrying a workpiece between locations), workpiece positioning (e.g., a worker mounting or aligning a workpiece for further processing), machine operation (e.g., a machine bending sheet metal in response to a worker's hand and/or foot being placed on a designated trigger), manual workpiece modification (e.g., a worker manually painting, welding, or removing material from a workpiece), etc.

In embodiments, digital twin simulation system 40006 may consider simulated human factors to determine process outcomes of simulated physical interactions. For example, variations in workpiece throughput may be modeled by digital twin system 40000, including, for example, worker response times to events, worker fatigue, discontinuities in worker behavior (e.g., natural variations in human movement speed, different positioning times, etc.), the impact of discontinuities on downstream processes, etc. In embodiments, historical data collected, acquired, and/or stored by digital twin system 40000 can be used to model individual worker interactions.
The simulation can begin with an estimated amount (e.g., worker age, industry average, workplace expectations, etc.), and the simulation may also individualize data for each worker (e.g., comparing the estimated amount with collected worker-specific results).

In an embodiment, information about a worker (e.g., fatigue rate, efficiency rate, etc.) can be determined by analyzing a particular worker's performance over time and modeling that performance.

In an embodiment, the digital twin system 40000 includes a plurality of proximity sensors in the sensor array 40030. The proximity sensors are configured or may be configured to detect elements of the environment 40020 that are within a predetermined area. For example, the proximity sensors may include electromagnetic sensors, optical sensors, and/or acoustic sensors.

Electromagnetic sensors are configured to or may sense objects or interactions via one or more electromagnetic fields (e.g., emitted or received electromagnetic radiation). In embodiments, electromagnetic sensors include inductive sensors (e.g., radio frequency identification sensors), capacitive sensors (e.g., contact and non-contact capacitive sensors), combinations thereof, etc.

Optical sensors may be configured to or may sense objects or interactions via electromagnetic radiation, for example, in the far-infrared, near-infrared, light, and/or ultraviolet spectrums. In embodiments, optical sensors may include image sensors (e.g., charge-coupled devices and CMOS active pixel sensors), photoelectric sensors (e.g., transmissive sensors, retroreflective sensors, and diffuse sensors), combinations thereof, and the like. Additionally, optical sensors may be implemented as part of a system or subsystem, such as a light detection and ranging ("LIDAR") sensor.

Acoustic sensors are configured or may sense objects or interactions via sound waves emitted and/or received by the acoustic sensors. In embodiments, acoustic sensors may include low-frequency sensors, sonic sensors, and/or ultrasonic sensors. Additionally, acoustic sensors may be grouped as part of a system or subsystem, such as a Sound Navigation and Ranging ("SONAR") sensor.

In an embodiment, digital twin system 40000 stores and collects data from a series of proximity sensors within environment 40020 or portions thereof. The collected data may be stored, for example, in digital twin data store 40016 for use by components of digital twin system 40000 and/or visualization by a user. Such use and/or visualization may occur simultaneously with data collection or subsequent to collection (e.g., during later analysis and/or process optimization).

In embodiments, data collection may occur in response to trigger conditions, such as the expiration of a predetermined static or dynamic interval, the acquisition of a value that falls short of or exceeds a static or dynamic value, the receipt of an automatically generated request or command from the digital twin system 40000 or its components, an interaction of an element with a respective sensor or sensors (e.g., in response to, for example, a worker or machine breaking a beam or coming within a predetermined distance of a proximity sensor), a user interaction with a digital twin (e.g., selection of an environment digital twin, a sensor array digital twin, a sensor digital twin), or a combination thereof.

In some embodiments, the digital twin system 40000 collects and/or stores RFID data in response to a worker's interaction with a real-world element 40302r. For example, in response to a worker's interaction with a real-world environment, the digital twin collects and/or stores RFID data from RFID sensors in or associated with the corresponding environment 40020. Additionally or alternatively, a worker's interaction with a sensor array digital twin collects and/or stores RFID data from RFID sensors in or associated with the corresponding sensor array. Similarly, a worker's interaction with a sensor digital twin collects and/or stores RFID data from the corresponding sensors. The RFID data may include appropriate data achievable by the RFID sensors, such as nearby RFID tags, RFID tag location, authorized RFID tags, unauthorized RFID tags, unrecognized RFID tags, RFID type (e.g., active or passive), error codes, combinations thereof, etc.

In embodiments, the digital twin system 40000 may further embed output from one or more devices within the corresponding digital twin. In embodiments, the digital twin system 40000 embeds output from devices associated with a set of individuals into an industrial digital twin. For example, the digital twin I/O system 40004 may receive information output from one or more wearable devices 40054 or mobile devices (not shown) associated with individuals in an industrial environment. The wearable devices may include image capture devices (e.g., body cameras or augmented reality headwear), navigation devices (e.g., GPS devices, inertial guidance systems), motion trackers, acoustic capture devices (e.g., microphones), radiation detectors, combinations thereof, etc.

In an embodiment, upon receiving the output information, the digital twin I/O system 40004 routes the information to the digital twin creation module 40064 to verify and/or update the environment digital twin and/or related digital twins within the environment (e.g., digital twins of the positions of workers, machines, or robots at a given time). Additionally, the digital twin system 40000 may use the embedded output to determine characteristics of the environment 40020.

In an embodiment, the digital twin system 40000 embeds output from a LIDAR point cloud system into the industrial digital twin. For example, the digital twin I/O system 40004 may receive information output from one or more LIDAR devices 40038 within the industrial environment. The LIDAR devices 40038 are configured to provide a plurality of points with associated position data (e.g., absolute or relative x-, y-, and z-coordinate values). Each of the plurality of points may include additional LIDAR attributes, such as intensity, number of returns, total number of returns, laser color data, return color data, scan angle, scan direction, etc. The LIDAR device 40038 may provide a point cloud including the plurality of points to the digital twin system 40000, for example, via the digital twin I/O system 40004. Additionally or alternatively, the digital twin system 40000 may receive a stream of points and assemble the stream into a point cloud, or may receive a point cloud and assemble the received point cloud with existing point cloud data, map data, or three-dimensional (3D) model data.

In embodiments, upon receiving the output information, the digital twin I/O system 40004 routes the point cloud information to the digital twin creation module 40064 to check and/or update the environment digital twin and/or related digital twins within the environment (e.g., digital twins of the worker, machine, or robot's position at a given time). In some embodiments, the digital twin system 40000 is further configured to determine closed-shaped objects within the received LIDAR data. For example, the digital twin system 40000 may group multiple points within the point cloud as an object and, if necessary, estimate obstructed surfaces of the object (e.g., surfaces of the object that touch or are adjacent to the floor, or surfaces of the object that touch or are adjacent to another object, such as another piece of equipment). The system can use such closed-shaped objects to narrow the search space of the digital twin, thereby improving the efficiency of matching algorithms (e.g., shape matching algorithms).

In an embodiment, the digital twin system 40000 embeds output from a simultaneous location and mapping (“SLAM”) system into the environment digital twin, for example:
The digital twin I/O system 40004 may receive output information from a SLAM system, such as a SLAM sensor 40062, and embed the received information into an environment digital twin corresponding to the location determined by the SLAM system. In an embodiment, upon receiving the output information from the SLAM system, the digital twin I/O system 40004 routes the information to the digital twin creation module 40064 to check and/or update the environment digital twin and/or related digital twins within the environment (e.g., digital twins of workpieces, furniture, movable objects, or autonomous objects). Such updates provide digital twins of unconnected elements (e.g., furniture or people) automatically, without requiring user interaction with the digital twin system 40000.

In embodiments, the digital twin system 40000 can leverage known digital twins to reduce the computational requirements of the slam sensor 40062 by using a suboptimal map-building algorithm. For example, a suboptimal map-building algorithm can allow for greater uncertainty tolerance by using a simple bounded area representation to identify potential digital twins. Additionally or alternatively, the digital twin system 40000 can use a bounded area representation to limit the number of digital twins, analyze them for features that distinguish between potential groups of twins, then perform a more refined analysis of the distinguishing features to identify and/or eliminate categories, groups, or individual digital twins, and, if no matching digital twins are found, perform a refined scan of only the remaining scanned area.

In embodiments, digital twin system 40000 may further reduce the computation required to construct the location map by leveraging data captured from other sensors in the environment (e.g., captured images or video, radio imagery, etc.) to perform an initial map-building process (e.g., a simple bounded area map or other suitable photogrammetry method). Digital twins of known environmental objects may be associated with features of the simple bounded area map to refine the simple bounded area map, and the remaining simple bounded areas may be more accurately scanned to further refine the map. In some embodiments, digital twin system 40000 may detect objects within the received mapping information and, for each detected object, determine whether the detected object corresponds to an existing digital twin of the real-world element. In response to determining that the detected object does not correspond to an existing digital twin of the real-world element, digital twin system 40000 may generate a new digital twin corresponding to the detected object (e.g., a digital twin of the detected object) using, for example, digital twin creation module 40064, and add the digital twin of the detected object to the digital twin of the real-world element in the digital twin data store. Additionally or alternatively, in response to determining that the detected object corresponds to an existing real-world element digital twin, the digital twin system 40000 may update the real-world element digital twin to include the contemporaneous location information and new information detected by the mapping sensor, if any.

In an embodiment, the digital twin system 40000 represents the location and attributes of autonomously or remotely movable elements within an industrial digital twin. Such movable elements may include, for example, workers, people, vehicles, autonomous vehicles, robots, etc. The location of the movable elements may be updated in response to trigger conditions. Such trigger conditions may include, for example, expiration of a static or dynamic predetermined interval, receipt of an automatically generated request or command from the digital twin system 40000 or its components, interaction of the elements with their respective sensors or sensors (e.g., in response to a worker or machine breaking a beam or coming within a predetermined distance of a proximity sensor), interaction of a user with the digital twin (e.g., selection of an environment digital twin, a sensor array digital twin, or a sensor digital twin), or combinations thereof.

In embodiments, the time intervals may be based on the probability that each mobile element has moved within a certain period of time. For example, the time intervals for updating the location of a worker may be relatively short for a worker who is expected to move frequently (e.g., a worker performing tasks such as lifting and carrying objects in and through the environment 40020) and relatively long for a worker who is expected to move infrequently (e.g., a worker performing tasks such as monitoring a process stream). The time intervals may be dynamically adjusted based on applicable conditions, such as increasing the time interval when no mobile elements are detected, decreasing the time interval when the number of mobile elements in the environment increases (e.g., when the number of workers increases and worker interaction increases), increasing the time interval during periods of reduced environmental activity (e.g., during breaks such as lunch), and decreasing the time interval during periods of reduced environmental activity. Other possibilities include increasing the time interval during periods of low environmental activity (e.g., lunch breaks), decreasing the time interval during periods of abnormal environmental activity (e.g., tours, inspections, maintenance), decreasing the time interval when unexpected or uncharacteristic movement is detected (e.g., frequent movement of normally sedentary elements, or coordinated movement such as workers approaching an exit or working together to carry a large object), or any combination of these.
includes additional semi-random acquisitions. For example, intermediate interval positions may be acquired by digital twin system 40000 from time to time to reinforce or evaluate the effectiveness of particular time intervals.

In an embodiment, the digital twin system 40000 may analyze the data received from the digital twin I/O system 40004 to refine, remove, or add conditions. For example, the digital twin system 40000 may optimize data collection time for moving elements that are updated more frequently than necessary (e.g., multiple consecutive received positions are identical or within a predetermined tolerance).

In an embodiment, the digital twin system 40000 may receive, identify, and/or store a set of states 40040a-n associated with the environment 40020. The states 40040a-n may be, for example, a data structure including multiple attributes 40404a-n and a set of identification criteria 40406a-n for uniquely identifying each state 40040a-n. In an embodiment, the states 40040a-n may correspond to conditions for which it is desirable for the digital twin system 40000 to set or change conditions of the real-world elements 40302r and/or the environment 40020 (e.g., increase/decrease monitoring intervals, change operating conditions, etc.).

In embodiments, the set of states 40040a-n may further include, for example, minimum monitored attributes for each state 40040a-n, a set of identification criteria 40406a-n for each state 40040a-n, and/or actions that can be taken or are recommended to be taken in response to each state 40040a-n. Such information may be stored, for example, by the digital twin data store 40016 or another data store. The states 40040a-n, or portions thereof, may be provided to, determined by, or modified by the digital twin system 40000. Additionally, the set of states 40040a-n may include data from heterogeneous sources. For example, details for identifying and/or responding to the occurrence of a first condition may be provided to the digital twin system 40000 via user input, details for identifying and/or responding to the occurrence of a second condition may be provided to the digital twin system 40000 via an external system, details for identifying and/or responding to the occurrence of a third condition may be determined by the digital twin system 40000 (e.g., via simulation or analysis of process data), and details for identifying and/or responding to the occurrence of a fourth condition may be stored by the digital twin system 40000 and changed as desired (e.g., in response to analysis of data collected during simulation of the occurrence of the condition and the occurrence and response to the condition).

In an embodiment, the plurality of attributes 40404a-n includes at least attributes 40404a-n necessary to identify the respective states 40040a-n. The plurality of attributes 40404a-n may further include additional attributes that are, or may be, monitored in determining the respective states 40040a-n, but are not necessary to identify the respective states 40040a-n. For example, the plurality of attributes 40404a-n related to the first state may include relevant information such as rotational speed, fuel level, energy input, linear velocity, acceleration, temperature, strain, torque, volume, weight, etc.

The set of identifying criteria 40406a-n may include information to uniquely identify each state for each of the set of attributes 40404a-n. The identifying criteria 40406a-n may include, for example, rules, thresholds, limits, ranges, logical values, conditions, comparisons, combinations thereof, etc.

The change in operating conditions or monitoring may be any suitable change. For example, after identifying the occurrence of each state 40406a-n, the digital twin system 40000 may increase or decrease the monitoring interval of the device without changing the operation of the device (e.g., decreasing the monitoring interval in response to a measured parameter that differs from nominal operation). Additionally or alternatively, the digital twin system 40000 may change the operation of the device without changing the monitoring of the device (e.g., decreasing the speed or power input). In further embodiments, the digital twin system 40000 may change the operation of the device (e.g., decreasing the speed or power input) and change the monitoring interval of the device (e.g., decreasing the monitoring interval).

FIG. 216 illustrates an example set of identified states 40040a-n related to an industrial environment that the digital twin system 40000 may identify and/or store for access by an intelligent system (e.g., cognitive intelligence system 40010) or user of the digital twin system 40000, according to some embodiments of the present disclosure. The states 40040a-n may include operating conditions (e.g., suboptimal, normal, optimal, critical, or alarm operation of one or more components), excess or shortage conditions (e.g., supply or output quantities), combinations thereof, etc.

In embodiments, the digital twin system 40000 may monitor attributes 40404a-n of the real-world element 40302r and/or the digital twin 40302d to determine their respective states 40040a-n. The attributes 40404a-n may be, for example, operating conditions, set points, critical points, status indicators, other sensed information, combinations thereof, etc. For example, the attributes 40404a-n may include a power input 40404a, an operating speed 40404b, a critical speed 40404c, and an operating temperature 40404d.
Although the illustrated example shows uniform monitoring attributes, the monitoring attributes may vary depending on the target device (e.g., digital twin system 40000 does not monitor the rotational speed of an object that does not have a rotatable component).

Each of the states 40040a-n includes a set of identification criteria 40406a-n that meet certain criteria that are unique among the group of monitored states 40040a-n. The digital twin system 40000 may identify the overspeed state 40040a, for example, in response to the monitored attributes 40404a-n meeting a first set of identification criteria 40406a (e.g., operating speed 40404b is greater than critical speed 40404c while operating temperature 40404d is nominal).

In response to determining that one or more conditions 40040a-n exist or have occurred, digital twin system 40000 may update trigger conditions of one or more monitoring protocols, issue alerts or notifications, or trigger actions of subcomponents of digital twin system 40000. For example, subcomponents of digital twin system 40000 may take action to mitigate and/or assess the impact of the detected condition 40040a-n. When taking action to mitigate the impact of the detected condition 40040a-n on real-world element 40302r, digital twin system 40000 may determine that instructions exist (e.g., stored in digital twin data store 40016) or should be developed (e.g., developed via simulation and cognitive intelligence or via user or operator input). Additionally, the digital twin system 40000 may evaluate the impact of the detected condition 40040a-n, for example, concurrently with mitigation actions or in response to determining that the digital twin system 40000 does not have stored mitigation actions instructions for the detected condition 40040a-n.

In an embodiment, the digital twin system 40000 employs a digital twin simulation system 40006 to simulate one or more effects, such as immediate, upstream, downstream, and/or ongoing effects of a recognized condition. The digital twin simulation system 40006 may collect and/or be provided with values related to the evaluated conditions 40040a-n. In simulating the effects of one or more conditions 40040a-n, the digital twin simulation system 40006 may recursively evaluate performance characteristics of the affected digital twin 40302d until convergence is achieved. The digital twin simulation system 40006 may, for example, cooperate with the cognitive intelligence system 40010 to determine response actions to mitigate, mitigate, suppress, and/or prevent the occurrence of one or more conditions 40040a-n. For example, the digital twin simulation system 40006 may recursively simulate the effects of one or more states 40040a-n until a desired fitness is achieved (e.g., convergence) and provide the simulated values to the cognitive intelligence system 40010. The intelligence system for evaluating and deciding on potential actions 40010 receives the potential actions and evaluates the impact of each potential action on each desired fitness (e.g., a cost function such as minimizing production disruptions, preserving critical components, minimizing maintenance and/or downtime, optimizing system, worker, user, or individual safety, etc.).

In embodiments, the digital twin simulation system 40006 and the cognitive intelligence system 40010 may iteratively share and update simulated values and response actions for each desired outcome until a desired condition is met (e.g., convergence of each evaluated cost function for each evaluated action). The digital twin system 40000 may store the results in the digital twin data store 40016 for use in response to determining that one or more conditions 40040a-n have occurred. Additionally, simulation and evaluation by the digital twin simulation system 40006 and/or the cognitive intelligence system 40010 may occur in response to the occurrence or detection of an event.

In an embodiment, simulation and evaluation are triggered only if no associated actions exist within the digital twin system 40000. In a further embodiment, simulation and evaluation are performed concurrently with the use of stored actions to evaluate the effectiveness or efficacy of the actions in real time and/or to evaluate whether further actions should be taken or whether an unrecognized condition may have occurred. In an embodiment, the cognitive intelligence system 40010 may also provide notification of instances of undesirable actions, with or without data regarding the undesirable aspects or consequences of such actions, to optimize subsequent evaluation.

In embodiments, the digital twin system 40000 evaluates and/or represents the impact of machine downtime within a digital twin of a manufacturing facility. For example, the digital twin system 40000 may employ a digital twin simulation system 40006 to simulate the immediate, upstream, downstream, and/or ongoing impacts of a machine downtime condition 40040b. The digital twin simulation system 40006 may collect or be provided with performance-related values, such as optimal, suboptimal, and minimum performance requirements for elements (e.g., real-world elements 40302r and/or nested digital twins 40302d) within the affected digital twin 40302d, and/or characteristics of the affected digital twin 40302d, nested digital twins 40302d, redundant systems within the affected digital twin 40302d, combinations thereof, etc.

In an embodiment, the digital twin system 40000 is configured to use real-world element digital twins to perform the following steps: simulating one or more operational parameters of the real-world elements in response to providing predetermined characteristics to the industrial environment; calculating mitigation actions to be taken by one or more of the real-world elements in response to providing contemporaneous characteristics; and actuating the mitigation actions in response to detecting the contemporaneous characteristics. The calculations may be performed in response to detecting contemporaneous characteristics or operational parameters that deviate from their respective design parameters, or may be determined by simulation prior to detecting such characteristics.

Additionally or alternatively, the digital twin system 40000 may provide an alert to one or more users or system elements in response to detecting the condition.

In an embodiment, the digital twin system 40000 includes power source characteristics of the industrial environment in the digital twin. Power source characteristics can include, for example, potential power sources, available power from individual lines or the grid, battery-based devices that can share power with other elements of the environment, backup power systems, and environmental power sources (e.g., heat sources that can be harnessed and converted to electricity). Power source characteristics can further include power delivery information such as delivery rate, power quality, utility frequency, circuit frequency, phase shift (e.g., differences in capacitance and inductance in the power path), switching time lag, distribution time lag (e.g., when a device or circuit requires an amount of energy or reaches a steady state before operating), or combinations thereof.

In embodiments, mitigation actions may include, for example, shutting down power-consuming elements in the environment, reducing the power supplied to one or more devices in the environment, supplying power from an alternative power source external to the environment, allocating power from a power storage device in the environment, combinations thereof, etc. Batteries and/or capacitors in the environment may be separate elements (e.g., a battery bank or capacitor bank) or integrated into elements of the environment (e.g., a battery pack in an electric vehicle or an element with a battery backup). Furthermore, mitigation actions may be performed iteratively, with additional actions being taken in response to a continued power loss condition. For example, in response to detecting a power loss condition 40402b, the digital twin system 40000 may switch the environment to power supplied from a battery bank and shut down a first set of power-consuming elements. If the power loss condition 40402b continues via a specific trigger event, the digital twin system 40000 may take further action, such as further reducing the environment's power consumption by shutting down a second set of power-consuming elements and/or reducing the operation of a third set of power-consuming elements. The mitigation action may further include, for example, activating one of an inductive circuit or a capacitive circuit operably coupled between the power source and the real-world element to optimize power delivered to the real-world element in the industrial environment.

In an embodiment, the trigger event may include, for example, the stored energy in the battery bank falling below a predetermined level, the digital twin system 40000 receiving notification that the power loss condition 40402b is expected to continue for a certain period of time, the digital twin system 40000 determining that the power loss condition 40402b is expected to continue for a certain period of time, combinations thereof, etc.

Additionally or alternatively, digital twin system 40000 may provide an alert to one or more users or system elements in response to detecting a condition such as power loss condition 40402b. For example, digital twin system 40000 may provide an alert to a user of digital twin system 40000 because action taken by digital twin system 40000 may prevent a significant environmental impact from power loss condition 40402b. The alert may be notification of the occurrence of power loss condition 40402b, display of data corresponding to power loss condition 40402b (e.g., reliability statistics), instructions for reducing the impact of future events (e.g., switching a power source in response to power reliability dropping below a predetermined amount), instructions regarding the environmental impact of a particular power loss condition 40402b (e.g., modifying equipment that behaved unexpectedly during power loss condition 40402b or a maintenance schedule), or any combination thereof.

In embodiments, the digital twin system 40000 can plan for the longevity of power backup systems in an environment based on simulations performed by the simulation system. For example, the backup systems can be maintained at a reduced capacity by determining the probability that such backup systems will be employed within a time frame. The probability calculation can include, for example, weather forecast data, contemporaneous weather data, historical data collected by the digital twin system 40000, simulation data based on data collected by a sensor array (e.g., fluctuations indicating an unexpected power outage or impending mechanical event), or a combination thereof.

In an embodiment, the backup battery system is maintained at an optimal level below maximum capacity, thereby providing sufficient backup capacity and increasing battery life while minimizing the total storage capacity of the backup system. For example, a battery bank may be energized to approximately 80% of capacity and maintained at that level until the probability of a power outage (determined by digital twin system 40000) exceeds a predetermined threshold (e.g., a 50% probability) within a predetermined window (e.g., the time it takes to charge the backup system to capacity). In response to the probability exceeding the predetermined amount, digital twin system 40000 may begin charging the battery system to full capacity. Digital twin system 40000 may maintain charging at capacity until a power outage necessitates discharging or until the probability of a power outage falls below another predetermined threshold (e.g., 10% or less) within the predetermined window. In response to the probability of a power outage falling below a predetermined threshold while the backup system is above its optimal charge, digital twin system 40000 may selectively discharge the backup system back to an optimal level or a desired level to promote battery health and lifespan.

Additionally or alternatively, digital twin system 40000 may utilize probabilistic calculations to minimize the cost of stored power. For example, in an energy storage backup system such as a battery bank or capacitor bank, digital twin system 40000 may delay charging the backup until cheaper electricity is available (e.g., during off-peak hours, when wholesale prices fall to a certain amount, or when solar or other renewable energy becomes available). Furthermore, in a power generation backup system (e.g., a fuel-fired generator) that receives fuel from an on-site storage tank, digital twin system 40000 may delay purchasing additional fuel until fuel prices meet a desired quantity or the probability of a power outage before delivery exceeds a predetermined threshold (e.g., delivery takes one week from the time of order, and digital twin system 40000 determines the probability of a power outage due to a weather event proximate to that lead time).

In embodiments, digital twin system 40000 evaluates and/or represents the impact of network connectivity outages in a digital twin of a real-world network. For example, digital twin system 40000 may employ digital twin simulation system 40006 to simulate the immediate, upstream, downstream, and/or ongoing impacts of network constrained conditions. Network constrained conditions can include, for example:
These include connection loss or constraints (e.g., loss of bandwidth, network congestion or bandwidth depletion, increased latency), interference (e.g., intermittent connectivity, packet drops, increased transmission overhead), reduced signal strength, data collisions, address depletion, or a combination thereof.

In embodiments, the digital twin simulation system 40006 may collect or be provided with network-related values, such as optimal, suboptimal, and minimum bandwidth and/or quality of service requirements for real-world elements 40302r in or connected to the network, potential data transmission paths through the network, alternative connection capabilities for real-world elements 40302r in the network, the impact of connectivity loss on real-world elements 40302r, reduced bandwidth or increased latency within the network, redundant systems within the affected network, or combinations thereof. In embodiments, the digital twin simulation system 40006 may utilize a digital twin of a network or its components to simulate various network constraint conditions, such as the loss of one or more components in the environment, loss of connectivity between components, loss of communication between the environment and the WAN, bottlenecks, human interaction with network-connected components, simulated changes in bandwidth or connectivity from external events (e.g., rain, temperature, electromagnetic interference, increased transparency at night, etc.), increased signaling through the system (e.g., in response to one or more devices in the environment increasing polling or increasing transmission values), or combinations thereof. The digital twin simulation system 40006 may store such simulations for later use, for example, in the digital twin data store 40016.

In the context of communications networks, mitigation measures may include, for example, establishing failover connections, establishing ad hoc network connections that can route data around the affected device, reducing data from one or more devices, increasing the number of real-world elements 40302r among which data can be transferred (e.g., increasing access points), allocating bandwidth to one or more WAN-connectable devices, or any combination thereof. Data from one or more devices may be reduced by, for example, reducing polling intervals from low-priority or redundant devices, stopping data transfer from potentially redundant devices, pushing data processing toward the edge to reduce network throughput of raw data, etc. Bandwidth from WAN-connectable devices may be allocated to service the affected portion of the network. As used herein, a "WAN-connectable device" is a device capable of direct connection to devices outside the environment (e.g., connection to a cellular tower or an independent Internet connection). For example, the wearable device 40054 may include not only a Wi-Fi transceiver but also a cellular transceiver capable of transmitting data over a cellular network. Digital twin system 40000 may be configured to provide such devices with rule sets or executable instructions for establishing connections to the WAN in response to, or in anticipation of, the occurrence of a network-constrained condition. For example, in response to network congestion or bandwidth depletion, one or more of the WAN-connectable devices may operate to establish additional connections to digital twin system 40000 in parallel with the congested or depleted connections (e.g., to provide additional communication bandwidth to the connected devices).

Furthermore, a reduction in data available for communication may inhibit the use of certain operating parameters. For example, a process may require suboptimal processing in low data traffic conditions, e.g., to prevent a runaway reaction. The digital twin system 40000 may determine optimal parameters for multiple processes operating at suboptimal levels by minimizing the time it takes for a network connection to return to a steady state after an outage.

Additionally or alternatively, digital twin system 40000 may provide an alert to one or more users or system elements in response to detecting a condition, such as a network constrained condition. For example, digital twin system 40000 may provide an alert to a user of digital twin system 40000 because action taken by digital twin system 40000 may prevent a noticeable impact on the environment from the network constrained condition. The alert may be a notification of the occurrence of the network constrained condition, a display of data corresponding to the network constrained condition (e.g., reliability statistics or constraint points), instructions for mitigating the impact of future events (e.g., locations to increase connection points or available bandwidth), instructions regarding the impact of a particular network constrained condition on the environment (e.g., missing data from affected devices), or any combination thereof.

In an embodiment, the digital twin I/O system 40004 includes a routing module 400310. The routing module 400310 may import navigational data from the element 40302, provide and/or request navigational data from components of the digital twin system 40000 (e.g., the digital twin simulation system 40006, the digital twin behavior system 108, and/or the cognitive intelligence system 40010), and/or output navigational data to the element 40302 (e.g., to the wearable device 40054). Navigation data may be collected or estimated using, for example, historical data, guidance data provided to the element 40302, a combination thereof, etc.

For example, navigation data may be collected or estimated using historical data stored by the digital twin system 40000. The historical data may include or be processed to provide information such as acquisition time, associated elements 40302, polling intervals, tasks performed, loaded or unloaded status, whether prior guidance data was provided and/or followed, the state of the environment 40020, other elements 40302 within the environment 40020, or combinations thereof. The estimated data may be determined using one or more appropriate pathfinding algorithms. For example, the estimated data may be calculated using a suitable order picking algorithm, a suitable pathfinding algorithm, combinations thereof, or the like. The order picking algorithm may be, for example, a maximum gap algorithm, an S-shaped algorithm, an aisle-by-aisle algorithm, a composite algorithm, combinations thereof, or the like. The pathfinding algorithm may be, for example, a Dijkstra's algorithm, an A* algorithm, a hierarchical pathfinding algorithm, an incremental pathfinding algorithm, an arbitrary angle pathfinding algorithm, a flow field algorithm, combinations thereof, or the like.

Additionally or alternatively, navigation data may be collected or estimated using worker guidance data. Guidance data may include, for example, a calculated route provided to a worker's device (e.g., a mobile device or wearable device 40054). In another example, guidance data may include a calculated route provided to a worker's device and instruct the worker to collect vibration measurements from one or more locations on one or more machines along the route. The collected and/or estimated navigation data may be provided to a user of the digital twin system 40000 for visualization, used by other components of the digital twin system 40000 for analysis, optimization, and/or modification, provided to one or more elements 40302, combinations thereof, etc.

In an embodiment, the digital twin system 40000 captures navigation data for a set of workers for representation in the digital twin. Additionally or alternatively, the digital twin system 40000 captures navigation data for a set of mobile equipment assets in an industrial environment in the digital twin.

In an embodiment, digital twin system 40000 incorporates a system for modeling traffic of mobile elements in an industrial digital twin. For example, digital twin system 40000 may model traffic patterns of workers or people, mobile equipment assets, combinations thereof, etc. within environment 40020. Traffic patterns may be estimated based on modeling traffic patterns from historical data and contemporaneously captured data. Furthermore, traffic patterns may be updated continuously or intermittently depending on conditions within environment 40020 (e.g., multiple autonomous mobile equipment assets may provide information to digital twin system 40000 at a slower update interval than an environment 40020 that includes both workers and mobile equipment assets).

The digital twin system 40000 may alter traffic patterns (e.g., by providing updated navigation data to one or more mobile elements) to achieve one or more predetermined criteria. The predetermined criteria may include, for example, improving process efficiency, reducing interactions between loaded workers and mobile equipment assets, minimizing worker path length, routing mobile equipment around people's paths or potential paths, combinations thereof, etc.

In embodiments, the digital twin system 40000 may provide traffic data and/or navigational information to mobile elements of the industrial digital twin. Navigational information may be provided as instructions or rule sets, displayed route data, or selective activation of devices. For example, the digital twin system 40000 may provide a set of instructions to a robot to guide the robot to and/or along a desired route, to collect vibration data from one or more specified locations of one or more specified machines along the route using vibration sensors. The robot may communicate updates to the system, including information about obstacles, route changes, unexpected interactions with other assets in the environment 40020, etc.

In some embodiments, the ant-based system 40074 enables industrial entities, including robots, to lay trails with one or more messages for other industrial entities, including themselves, to follow on later journeys. In embodiments, the messages include information related to vibration measurement collection. In embodiments, the messages include information related to vibration sensor measurement locations. In some embodiments, the trails may be configured to fade over time. In some embodiments, the ant-based trails may be experienced via an augmented reality system. In some embodiments, the ant-based trails may be experienced via a virtual reality system. In some embodiments, the ant-based trails may be experienced via a mixed reality system. In some embodiments, the ant-based area tagging can trigger a pain response and/or accumulate into an alarm signal. In some embodiments, the ant-based trails may be configured to generate an information filtering response. In some embodiments, the ant-based trails may be configured to generate an information filtering response, where the information filtering response is heightened visual awareness. In some embodiments, the ant-based trails may be configured to generate an information filtering response, where the information filtering response is heightened acoustic awareness. In some embodiments, the messages include vectorized data.

In an embodiment, the digital twin system 40000 includes design specification information for representing real-world elements 40302r using a digital twin 40302d. The digital may correspond to existing real-world elements 40302r or potential real-world elements 40302r. The design specification information may be received from one or more sources. For example, the design specification information may include design parameters set by user input, design parameters determined by the digital twin system 40000 (e.g., via the digital twin simulation system 40006), design parameters optimized by the user or the digital twin simulation system 40006, or a combination thereof. The digital twin simulation system 40006 may represent the design specification information of the component to the user, for example, via a display device or a wearable device. The design specification information may be displayed schematically (e.g., as part of a process diagram or table of information) or as part of an augmented reality or virtual reality display. The design specification information may be displayed, for example, in response to a user interaction with the digital twin system 40000 (e.g., via a user selection of an element or a user selection to generally include design specification information in the display). Additionally or alternatively, the design specification information may be displayed automatically, for example, when an element comes within the field of view of an augmented reality or virtual reality device. In an embodiment, the displayed design specification information may further include an indicator of the source of the information (e.g., different display colors indicate user input and digital twin system 40000 decisions), an indicator of a mismatch (e.g., between design specification information and operational information), a combination thereof, etc.

In an embodiment, the digital twin system 40000 embeds a control instruction set for a wearable device within the industrial digital twin, and the control instructions are provided to the wearable device to induce an experience for the wearer of the wearable device upon interaction with elements of the industrial digital twin, such as an augmented reality (AR) experience or a virtual reality (VR) experience.
A wearable device, such as a headset, may be configured to output visual, audio, and/or haptic feedback to the wearer to induce the experience. For example, the wearable device may include a display device, and the experience may include displaying information related to each digital twin. The displayed information may include maintenance data related to the digital twin, vibration data related to the digital twin, vibration measurement location data related to the digital twin, financial data related to the digital twin (e.g., profit or loss associated with the operation of the digital twin), manufacturing KPIs related to the digital twin, and information related to occluded elements (e.g., subassemblies). Examples of the displayed information include profit or loss associated with the operation of the digital twin, manufacturing KPIs related to the digital twin, information related to hidden elements (e.g., subassemblies) that are at least partially obscured by foreground elements (e.g., housings), a virtual model of the hidden element overlaid on and displayed with the foreground elements, operational parameters of the hidden element, a comparison of the displayed operational parameters with corresponding design parameters, or a combination thereof. The comparison may include, for example, modifying the display of the operational parameters to change the color, size, display duration, etc. of the operational parameters.

In some embodiments, the displayed information may include indicators for removable elements that are or may be configured to provide access to an occluded element, with each indicator displayed adjacent to or on the respective removable element. Furthermore, the indicators may be displayed sequentially, such that a first indicator corresponding to a first removable element (e.g., the housing) is displayed, and in response to the operator removing the first removable element, a second indicator corresponding to a second removable element (e.g., an access panel within the housing) is displayed. In some embodiments, the guided experience allows the wearer to view one or more locations on the machine for optimal vibration measurement collection. In an example, the digital twin system 40000 may provide an augmented reality view that includes highlighted vibration measurement collection locations on the machine and/or instructions related to collecting vibration measurements. By way of further example, the digital twin system 40000 may provide an augmented reality view that includes instructions related to the timing of collecting vibration measurements. Information utilized in displaying the highlighted placement locations may be obtained using information stored by the digital twin system 40000. In some embodiments, the mobile element is tracked by the digital twin system 40000 (e.g., via observed elements within the environment 40020 and/or via path information communicated to the digital twin system 40000) and continuously displayed on the wearable device within the worker's occluded field of view, thereby optimizing the element's movement within the environment 40020, increasing worker safety, and minimizing element downtime due to damage.

In some embodiments, the digital twin system 40000 may provide an augmented reality view that displays to the wearer mismatches between design or expected parameters of real-world elements 40302r. The displayed information may correspond to real-world elements 40302r that are not within the wearer's field of view (e.g., elements in another room or elements obscured by machinery). This allows the operator to quickly and accurately troubleshoot the mismatch and identify one or more causes of the mismatch. The cause of the mismatch may then be determined, for example, by the digital twin system 40000, and corrective action may be prescribed. In an exemplary embodiment, the wearer may be able to see a failed subcomponent of a machine without removing an occlusion element (e.g., a housing or shield). Additionally or alternatively, the wearer may provide instructions for repairing the device, such as indication of the removal process (e.g., location of fasteners to be removed), assemblies or subassemblies to be transported to another location for repair (e.g., parts sensitive to dirt), assemblies or subassemblies that need lubrication, and location of objects for reassembly (e.g., the wearer remembers where they placed a removed object and directs the wearer or another wearer to the remembered location for expedited reassembly, minimizing further disassembly of reassembled elements or missing parts). This may allow for faster repair operations, minimized impact to the process, operators disassembling and reassembling the device (e.g., coordinating disassembly without direct communication between operators), improving the life and reliability of the device (e.g., ensuring all components are properly replaced before returning to service), and combinations thereof.

In some embodiments, the guided experience includes a virtual or augmented reality view that allows the wearer to view information related to existing or planned elements. The information may be unrelated to the element's physical performance (e.g., asset value, energy costs, input material costs, output material values, financial performance such as regulatory compliance, business operations, etc.). One or more wearers may perform a virtual or augmented walkthrough of the industrial environment 40020.

In an example, a wearable device displays compliance information that expedites inspection or work execution. For example, an electrical inspector can walk through and inspect equipment, finishes, and other inspection points for compliance with specific codes, even when those inspection points are not visible. This expedites construction and inspections and minimizes change orders because work does not have to be delayed or modified to obtain inspector approval. Additionally, rework can be minimized because compliance can be ensured even by individuals unfamiliar with codes (e.g., workers unfamiliar with electrical codes may be able to ensure electrical work is compliant before installing equipment).

In a further example, the wearable device displays financial information used to identify targets for change or optimization. For example, a manager or executive can inspect the environment 40020 for compliance with updated regulations, including information regarding compliance with older regulations, "grandfathered" and/or exempted elements. This can be used to reduce unnecessary downtime (e.g., scheduling upgrades during the least impactful time, such as during a planned maintenance cycle), prevent unnecessary upgrades (e.g., replacing grandfathered or exempted equipment), and reduce capital expenditures.

Returning to FIG. 213, in embodiments, the digital twin system 40000 may include, integrate, federate, manage, process, link, take inputs, provide outputs, control, collaborate, or otherwise interact with the digital twin dynamic model system 40008. The digital twin dynamic model system 40008 may update properties of a digital twin of a set of industrial entities and/or environments (or any of the other types of entities or environments described in this disclosure or the documents incorporated by reference herein), including properties of physical industrial assets, workers, processes, manufacturing facilities, warehouses, etc., in a manner that enables the digital twin to represent those industrial entities and environments, and their properties or attributes, in real time or near real time. In some embodiments, the digital twin dynamic model system 40008 may obtain sensor data received from the sensor system 40030 and, based on the sensor data, determine one or more characteristics of the industrial environment or industrial entities within the environment based on one or more dynamic models.

In embodiments, the digital twin dynamic model system 40008 may update/assign values for various properties in the digital twin and/or one or more embedded digital twins, including, but not limited to, vibration values, vibration fault level states, failure probability values, downtime probability values, downtime cost values, shutdown probability values, financial values, KPI values, temperature values, humidity values, heat flow values, fluid flow values, radiation values, substance concentration values, velocity values, acceleration values, position values, pressure values, stress values, strain values, luminous intensity values, noise values, volume values, shape properties, material properties, dimensions, etc.

In embodiments, a digital twin may be composed (e.g., via reference) of other embedded digital twins. For example, a digital twin of a manufacturing facility may include an embedded digital twin of the machine and one or more embedded digital twins of one or more respective motors encapsulated within the machine. A digital twin may be embedded, for example, in the memory of an industrial machine having an on-board IT system (e.g., the memory of an on-board diagnostic system, a control system (e.g., a SCADA system), etc.). Other non-limiting examples of where a digital twin may be embedded include on a worker's wearable device, memory on local network assets such as switches, routers, and access points, cloud computing resources provisioned for the environment or entity, and on an asset tag or other memory structure dedicated to the entity.

In one example, the digital twin dynamic model system 40008 can update vibration characteristics of the entire industrial environment digital twin based on captured vibration sensor data measured at one or more locations within the industrial environment and one or more dynamic models that model vibrations within the industrial environment digital twin. Prior to updating, the industrial digital twin may already contain information about the characteristics of industrial entities and/or the environment, such as materials, shape/volume (e.g., of conduits), location, connections/interfaces, etc., that can be used to feed into the dynamic model so that vibration characteristics can be represented for the entities and/or the environment within the digital twin. Alternatively, such information may be used to configure the dynamic model. Alternatively, a thermodynamic model may be configured using such information. Other sensor data, such as pressure data (e.g., using PV=nRT), may also serve to update thermodynamic behavior. The thermodynamic model may also be configured to represent the diffusion of heat through static objects (e.g., large metal machinery) as well as fluids (e.g., circulating fluids in a cooling system).

In another example, the digital twin dynamic system 40008 can update chemical (analyte) concentration values throughout the industrial environment digital twin based on captured chemical sensor data and one or more diffusion models that model the concentrations of chemicals within the industrial environment digital twin. The industrial environment digital twin can include a set of characteristics and/or attributes of the environment and/or entities that serve to provide input to the chemical diffusion model and/or chemical interaction/reaction model, such as chemical composition of materials, fluids, gases, etc.; shape/volume of components, conduits, spaces, etc.; temperature and pressure. Sensors can include not only chemical sensors but also sensors that may provide information to the diffusion model, such as pressure, temperature, flow rate, etc.

In an embodiment, the digital twin dynamic model system 40008 may update properties of the digital twin and/or one or more embedded digital twins on behalf of the client application 40070. In an embodiment, the client application 40070 may be an application related to an industrial component or environment (e.g., monitoring an industrial facility or components therein, simulating an industrial environment, etc.). In an embodiment, the client application 40070 may be used in connection with both fixed and mobile data collection systems. In an embodiment, the client application 40070 may be used in connection with an Industrial Internet of Things sensor system 40030.

In an embodiment, the digital twin dynamic model system 40008 utilizes a digital twin dynamic model 400100 to model the behavior of industrial entities and/or the environment. The dynamic model 400100 can enable the digital twin to represent physical reality, including the interactions of industrial entities, by using a limited number of measurements to enrich the digital representation of the industrial entities and/or the environment, such as based on scientific principles. In an embodiment, the dynamic model 400100 is a formalized or mathematical model. In an embodiment, the dynamic model 400100 conforms to scientific laws, laws of nature, and formulas (e.g., Newton's laws of motion, the second law of thermodynamics, Bernoulli's principle, the ideal gas law, Dalton's law of partial pressures, Hooke's law of elasticity, Fourier's law of heat conduction, Archimedes' principle of buoyancy, etc.). In an embodiment, the dynamic model is a machine-learned model. For example, temperature sensors in a warehouse may each take a temperature measurement at a specific geospatial coordinate, but these limited measurements do not provide values for other locations in the warehouse, such as locations not covered by the sensors. In this example, a dynamic model can be configured to model the temperature throughout the warehouse using measurements from a limited number of sensors, providing a richer representation of the warehouse's digital twin.

In embodiments, the digital twin system 40000 may have a digital twin dynamic model data store 400102 for storing dynamic models 400100 that may be represented in a digital twin. In embodiments, the digital twin dynamic model data store may be searchable and/or discoverable. In embodiments, the digital twin dynamic model data store may include metadata that allows a user to understand what characteristics a given dynamic model can handle, what inputs it requires, what outputs it provides, etc. In some embodiments, the digital twin dynamic model data store 400102 may be hierarchical (e.g., models may become deeper or simpler based on the range of data and/or inputs available, the granularity of the inputs, and/or situational factors (e.g., something becomes of high interest and a higher fidelity model may be accessed for a period of time)).

In an embodiment, a digital twin or digital representation of an industrial entity or facility may include a set of data structures that collectively define a set of properties and/or possible behaviors of the represented physical industrial asset, device, worker, process, facility, and/or environment. In an embodiment, the digital twin dynamic model system 40008 may utilize a dynamic model 400100 to inform the set of data structures that collectively define the digital twin with real-time data values. The digital twin dynamic model 400100 may receive one or more sensor measurements, industrial internet of things device data, and/or other suitable data as inputs and calculate one or more outputs based on the received data and the one or more dynamic models 400100. The digital twin dynamic model system 40008 then uses the one or more outputs to update the digital twin data structure.

In one example, the set of properties of the digital twin of an industrial asset that are updated by the digital twin dynamic model system 40008 using the dynamic model 400100 may include the vibration characteristics of the asset, the temperature of the asset, and the state of the asset (e.g., solid, liquid, gas). The dynamic model 400100 associated with an asset's digital twin may be configured to calculate, interpolate, extrapolate, and/or output values for such asset's digital twin properties based on input data and/or other suitable data collected from sensors and/or devices located in the industrial environment, and/or other suitable data.

In some embodiments, the set of properties of an industrial device's digital twin that may be updated by the digital twin dynamic model system 40008 using the dynamic model 400100 may include the device's status, the device's location, the device's temperature(s), the device's trajectory, identifiers of other digital twins that the device's digital twin is embedded in, embedded in, linked to, contained in, integrated with, receiving input from, providing output to, and/or interacting with, etc. The dynamic model 400100 associated with the device's digital twin may be configured to calculate or output values for these device digital twin properties based on the input data and subsequently update the device digital twin with the calculated values.

In some embodiments, a set of properties of an industrial worker's digital twin that may be updated by the digital twin dynamic model system 40008 using the dynamic model 400100 may include the worker's status, the worker's location, the worker's stress indicators, the tasks being performed by the worker, the worker's performance indicators, etc. The dynamic model associated with the industrial worker's digital twin may be configured to calculate or output values for such properties based on input data, and these properties may be used to populate the industrial worker's digital twin. In embodiments, the industrial worker's dynamic model (e.g., a psychometric model) may be configured to predict responses to stimuli, such as cues given to the worker to instruct the worker to perform a task, or warnings or alerts intended to guide safe behavior. In embodiments, the industrial worker's dynamic model may be a workflow model (e.g., a Gantt chart), a failure mode and effects analysis model (FMEA), a biophysical model (e.g., modeling the worker's fatigue, energy utilization, hunger, etc.), etc.

Examples of digital twin characteristics of an industrial environment that the digital twin dynamic model system 40008 can update using the dynamic model 400100 may include dimensions of the industrial environment, temperature of the industrial environment, humidity values of the industrial environment, fluid flow characteristics of the industrial environment, heat flow characteristics of the industrial environment, lighting characteristics, acoustic characteristics, vibration characteristics of the industrial environment, etc.
It provides information about the characteristics of the industrial environment, the physical objects in the environment, the processes occurring in the industrial environment, the flows in the industrial environment (in the case of a body of water), etc. The dynamic model associated with the digital twin of the industrial environment can be configured to calculate or output these characteristics based on input data and/or other suitable data collected from sensors and/or devices located in the industrial environment, and then input the calculated values into the digital twin of the industrial environment.

In embodiments, the dynamic model 400100 may adhere to physical constraints that define boundary conditions, constants, or variables for modeling the digital twin. For example, physical characteristics of a digital twin of an industrial entity or industrial environment may include a gravitational constant (e.g., 9.8 m/s²), a surface friction coefficient, a material thermal coefficient, a maximum asset temperature, a maximum flow capacity, etc. Additionally or alternatively, the dynamic model may adhere to laws of nature. For example, the dynamic model may adhere to laws of thermodynamics, laws of motion, laws of fluid mechanics, laws of buoyancy, laws of heat transfer, laws of radiation, laws of quantum mechanics, etc. In some embodiments, the dynamic model may adhere to the theory of biological aging or principles of mechanical aging. Thus, when the digital twin dynamic model system 40008 facilitates a real-time digital representation, the dynamic model may be adhered to such that the digital representation mimics real-world conditions. In some embodiments, output from the dynamic model may be presented to a human user or compared to real-world data to verify convergence of the dynamic model to the real world. Furthermore, because the dynamic model is based in part on assumptions, the characteristics of the digital twin can be improved and/or modified if real-world behavior differs from that of the digital twin. In embodiments, additional data collection and/or measurement can be recommended based on the recognition that the desired dynamic model is missing inputs, that the operating model is not performing as expected (perhaps due to missing or flawed sensor information), or that a different outcome is desired (due to situational factors that make it interesting), etc.

Dynamic models can be obtained from several different sources. In some embodiments, a user can upload a model created by the user or a third party. Additionally or alternatively, models may be created on the digital twin system using a graphical user interface. Dynamic models may include custom models configured for a particular environment and/or set of industrial entities, and/or agnostic models applicable to similar types of digital twins. Dynamic models may also be machine-learned models.

FIG. 217 illustrates an exemplary embodiment of a method in 41100 for updating a set of properties of a digital twin and/or one or more embedded digital twins on behalf of a client application 40070. In an embodiment, the digital twin dynamic model system 40008 utilizes one or more dynamic models 400100 to update a set of properties of a digital twin and/or one or more embedded digital twins on behalf of the client application 40070 based on the influence of collected sensor data from the sensor system 40030, data collected from Internet of Things connected devices 40024, and/or other suitable data in the set of dynamic models 400100 used to enable the industrial digital twin. In an embodiment, the digital twin dynamic model system 40008 may be instructed to execute a particular dynamic model using one or more digital twins representing physical industrial assets, devices, workers, processes, and/or industrial environments managed, maintained, and/or monitored by the client application 40070.

In embodiments, the digital twin dynamic model system 40008 may obtain data from other types of external data sources that are not necessarily industry-related, but that can provide data that can be used as input data for the dynamic model. For example, weather data, news events, social media data, etc. may be collected, crawled, subscribed to, etc. to supplement the sensor data, Industrial Internet of Things device data, and/or other data used by the dynamic model. In embodiments, the digital twin dynamic model system 40008 may obtain data from a machine vision system. The machine vision system may be included in the sensor system 40030 and video sensor 40052 and may use video and/or still images to provide measurements (e.g., position, status, etc.) that can be used as inputs by the dynamic model.

In an embodiment, the digital twin dynamic model system 40008 may feed this data to one or more of the dynamic models described above to obtain one or more outputs. These outputs may include calculated vibration failure level states, vibration severity unit values, vibration characteristics, failure probability values, downtime probability values, shutdown probability values, downtime cost values, shutdown cost values, time to failure values, temperature values, pressure values, humidity values, precipitation values, visibility values, air quality values, strain values, stress values, displacement values, velocity values, acceleration values, position values, performance values, financial values, manufacturing KPI values, electrodynamic values, thermodynamic values, fluid flow values, and the like. The client application 40070 may then initiate a digital twin visualization event using the results obtained by the digital twin dynamic model system 40008. In an embodiment, the visualization may be a heat map visualization.

In an embodiment, the digital twin dynamic model system 40008 may receive a request to update one or more properties of a digital twin of an industrial entity and/or environment so that the digital twin represents the industrial entity and/or environment in real time. At 41102, the digital twin dynamic model system 40008 receives a request to update one or more properties of a digital twin of an industrial entity and/or environment. For example, the digital twin dynamic model system 40008 may receive the request from a client application 40070 or from another process (e.g., a predictive maintenance process) executed by the digital twin system 40000. The request may indicate one or more properties and the digital twin or digital twins that the request involves. At 41104, the digital twin dynamic model system 40008 determines one or more digital twins needed to fulfill the request and retrieves the one or more needed digital twins, including any embedded digital twins, from the digital twin data store 40016. At 41108, the digital twin dynamic model system 40008 determines one or more dynamic models needed to fulfill the request and retrieves the one or more needed dynamic models from the digital twin dynamic model store. At 41110, the digital twin dynamic model system 40008 selects one or more sensors from the sensor system 40030, data collected from the Internet of Things connected devices 40024, and/or other data sources from the digital twin I/O system 40004 based on the available data sources and one or more required inputs of the dynamic model(s). In an embodiment, the data sources may be defined with the inputs needed by the one or more dynamic models or may be selected using a lookup table. At 41112, the digital twin dynamic model system 40008 retrieves the selected data from the digital twin I/O system 40004. At 41114, the digital twin dynamic model system 40008 executes the dynamic model(s) using the retrieved input data (e.g., vibration sensor data, industrial internet of things device data, etc.) as input and determines one or more output values based on the dynamic model(s) and the input data. At 41120, the digital twin dynamic model system 40008 updates values of one or more properties of one or more digital twins based on one or more outputs of the dynamic model(s).

In example embodiments, the client application 40070 may be configured to provide a digital representation and/or visualization of a digital twin of an industrial entity. In embodiments, the client application 40070 may include one or more software modules executed by one or more server devices. These software modules may be configured to quantify characteristics of the digital twin, model characteristics of the digital twin, and/or visualize behavior of the digital twin. In embodiments, these software modules may allow a user to select and display a visualization of a particular digital twin's behavior. In embodiments, these software modules may allow a user to select to view a playback of the digital twin behavior visualization. In some embodiments, the client application 40070 may provide the selected behavior visualization to the digital twin dynamic model system 40008.

In an embodiment, the digital twin dynamic model system 40008 may receive a request to update the properties of the digital twin from the client application 40070 to enable a digital representation of the industrial entity and/or environment, where the real-time digital representation is a visualization of the digital twin. In an embodiment, the digital twin may be rendered by a computing device to allow a human user to view a digital representation of a real-world industrial asset, equipment, worker, process, and/or environment. For example, the digital twin may be rendered and displayed as a result on a display device. In an embodiment, dynamic model output and/or related data may be overlaid on the rendering of the digital twin. In an embodiment, dynamic model output and/or related information may be displayed in a display interface along with the rendering of the digital twin. In an embodiment, the related information may include real-time video footage related to the real-world entity represented by the digital twin. In an embodiment, the related information may include a sum of each state of the machine's vibration disturbance level. In an embodiment, the related information may be graphical information. In an embodiment, the graphical information may depict the operation of individual machine components and/or their operation as a function of frequency. In embodiments, the graphical information may depict the movement and/or motion of individual machine components as a function of frequency, where a user can select a view of the graphical information in the x, y, and z dimensions. In embodiments, the graphical information may depict the movement and/or motion of individual machine components as a function of frequency, where the graphical information includes harmonic peaks and peaks. In embodiments, the relevant information may be cost data including cost of downtime per day data, cost of repair data, cost of new parts data, cost of new machines data, etc. In embodiments, the relevant information may be probability of downtime data, probability of failure data, etc. In embodiments, the relevant information may be time to failure data.

In embodiments, the relevant information may be recommendations and/or insights. For example, recommendations or insights received from a cognitive intelligence system associated with the machine may be displayed along with a rendering of the machine's digital twin in the display interface.

In embodiments, a user may "drill down" to view underlying subsystems or processes and/or embedded digital twins by clicking, touching, or otherwise interacting with a digital twin rendered in the display interface. For example, in response to a user clicking on a machine bearing rendered in the machine's digital twin, the display interface may enable the user to drill down to view information related to the bearing, view a 3D visualization of the bearing's vibration, and view the bearing's digital twin.

In embodiments, a user can "drill down" to view underlying information by clicking, touching, or otherwise interacting with information related to the digital twin rendered in the display interface.

Figure 218 shows an exemplary embodiment of a display interface that renders a digital twin of a dryer centrifuge and other information related to the dryer centrifuge.

In some embodiments, the digital twin may be rendered and output on a virtual reality display. For example, a user may view a 3D rendering of the environment (e.g., using a monitor or virtual reality headset). The user may also inspect and/or interact with the digital twin of the industrial entity. In embodiments, the user may view processes being performed with respect to one or more digital twins (e.g., measurement collection, movement, interaction, inventory, loading, packing, shipping, etc.). In embodiments, the user may provide inputs to control one or more properties of the digital twin via a graphical user interface.

In some embodiments, the digital twin dynamic model system 40008 may receive a request from a client application 40070 to update properties of the digital twin to enable a digital representation of an industrial entity and/or environment, where the digital representation is a heat map visualization of the digital twin. In embodiments, a platform is provided having a heat map that displays collected data from the sensor system 40030, the Internet of Things connected devices 40024, and data output from the dynamic model 400100 to provide input to a display interface. In embodiments, the heat map interface is provided as an output for the digital twin data, such as for processing and providing information for visualization of various sensor data, dynamic model output data, and other data (e.g., map data, analog sensor data, and other data) to another system, such as a mobile device, tablet, dashboard, computer, AR/VR device, etc. The representation of the digital twin may be provided in any form factor (e.g., a user device, a VR-enabled device, an AR-enabled device, etc.) suitable for providing visual input to a user, such as displaying a map including indicators indicating levels of analog sensor data, digital sensor data, output values from a dynamic model (e.g., data indicating the status of vibration disturbance levels, values of vibration severity units, values of probability of downtime, values of cost of downtime, probability of shutdown, time to failure, probability of failure, manufacturing KPIs, temperature, rotational speed, vibration characteristics, fluid flow, heating/cooling, pressure, concentration of a substance, and many other output values). In an embodiment, signals from various sensors or input sources (or selective combinations, permutations, mixtures, etc.) may provide input data to the heat map, as well as data determined by the digital twin dynamic model system 40008. Coordinates may include real-world position coordinates (e.g., geolocation or location on a map of the environment), as well as time-based coordinates, frequency-based coordinates, or other coordinates that allow for the representation of various combinations of analog sensor signals, digital signals, dynamic model outputs, input source information, and other coordinates, such that color represents various levels of input along the relevant dimension in a map-based visualization. For example, if a component of an industrial machine is experiencing a critical vibration failure level, a heat map interface may color the machine component orange to alert the user. In the heat map example, by clicking, touching, or otherwise interacting with the heat map, a user can drill down to view the underlying sensor, dynamic model output, or other input data used as input for the heat map display. In other examples where a digital twin is displayed in a VR or AR environment, if an industrial machine part is vibrating outside of normal operation (e.g., suboptimal, critical, or alarm vibration failure levels), a haptic interface may induce vibrations when the user touches a representation of the machine part, and if the machine part is operating in an unsafe manner, a directional sound signal may direct the user's attention to the digital twin's machine, such as by playing it through a specific speaker in a headset or other sound system.

In embodiments, the digital twin dynamic model system 40008 may obtain a set of ambient environmental data and/or other data and automatically update a set of properties of the digital twin of the industrial entity or facility based on the effect of the environmental data and/or other data on the set of dynamic models 400100 used to enable the digital twin. The ambient environmental data may include temperature data, pressure data, humidity data, wind data, rainfall data, tide data, storm surge data, cloud cover data, snowfall data, visibility data, water level data, etc. Additionally or alternatively, the digital twin dynamic model system 40008 may use a set of environmental data measurements collected by a set of Internet of Things connected devices 40024 deployed in the industrial environment as input for the set of dynamic models 400100 used to enable the digital twin. For example, the digital twin dynamic model system 40008 may feed the dynamic model 400100 data collected, processed, or exchanged by Internet of Things connected devices 40024, such as cameras, monitors, embedded sensors, mobile devices, diagnostic devices and systems, instrumentation systems, telematics systems, etc., for monitoring various parameters and characteristics of machines, equipment, components, parts, operations, functions, conditions, states, events, workflows, and other elements (collectively encompassed by the term "state") of an industrial environment. Other examples of Internet of Things connected devices include smart fire alarms, smart security systems, smart air quality monitors, smart/remote thermostats, smart lighting systems, etc.

FIG. 219 illustrates an exemplary embodiment of a method in 42000 for updating the vibration fault level status of a set of bearings in a machine's digital twin. In this example, a client application 40070 interfacing with the digital twin dynamic model system 40008 may be configured to provide visualization of the fault level status of the bearings in the machine's digital twin.

In this example, digital twin dynamic model system 40008 may receive a request from client application 40070 to update the vibration fault level state of a machine digital twin. In 42002, digital twin dynamic model system 40008 receives a request from client application 40070 to update one or more vibration fault level states of a machine digital twin. Then, in 42004, digital twin dynamic model system 40008 determines one or more digital twins needed to fulfill the request and retrieves the one or more needed digital twins from digital twin data store 40016. In this example, digital twin dynamic model system 40008 may search the machine's digital twin and any embedded digital twins, for example, any embedded motor digital twins and bearing digital twins, as well as any digital twins that embed the machine's digital twin, such as a manufacturing facility digital twin. In 42008, digital twin dynamic model system 40008 determines one of the following: Retrieve one or more dynamic models needed to fulfill the request from digital twin dynamic model data store 400102. At 42010, the digital twin dynamic model system 40008 selects dynamic model input data sources (e.g., one or more sensors from the sensor system 40030, data from the Internet of Things connected device 40024, and any other suitable data) via the digital twin I/O system 40004 based on available data sources (e.g., available sensors from the sensor set of the sensor system 40030) and one or more requested inputs of the dynamic model(s). In this example, the retrieved dynamic model(s) 400100 may take one or more vibration sensor measurements from the vibration sensor 40036 as input to the dynamic model. In an embodiment, the vibration sensor 40036 may be an optical vibration sensor, a single-axis vibration sensor, a three-axis vibration sensor, etc. At 42012, the digital twin dynamic model system 40008 obtains one or more measurements from each of the selected data sources from the digital twin I/O system 40004. Next, at 42014, the digital twin dynamic model system 40008 executes the dynamic model(s) using the retrieved vibration sensor measurements as inputs to calculate one or more outputs representing bearing vibration fault level conditions. Next, at 42018, the digital twin dynamic model system 40008 updates one or more bearing fault level conditions of the manufacturing facility digital twin, the machine digital twin, the motor digital twin, and/or the bearing digital twin based on the one or more outputs of the dynamic model(s). The client application 40070 may retrieve the bearing vibration fault level conditions, may associate and display the retrieved vibration fault level conditions with each bearing, and may display a color associated with the fault level severity (e.g., red for alarm, orange for critical, yellow for suboptimal, green for normal operation) in one or more renderings of the digital twin on the display interface.

Continuing the example, the client application 40070 may additionally or alternatively be configured to provide a heat map visualization of strain on industrial entities within a manufacturing facility, such as pipes. Piping materials can exhibit linear expansion and contraction with temperature, and thermal expansion of the piping can cause strain on the piping material.

The rate of thermal expansion and contraction is characterized by the coefficient of thermal expansion. The change in the dimensions of the pipe can be defined as:

e=a(T2-T1)(Equation 1)

by the way

e = strain (in/in)

a = Coefficient of thermal expansion (unit: in/°F)

T2 = End temperature (°F)

T1 = Start-up temperature (°F)

Given the temperature at installation (Tl), the coefficient of thermal expansion, and a sensor measurement (T2) providing the real-time temperature at a particular point on the pipe, pipe strain values may be calculated from a dynamic model that takes one or more temperature measurements from temperature sensor 40032 as input(s) to the dynamic model to calculate one or more estimated pipe strain values pursuant to Equation 1. Additionally or alternatively, the dynamic model may be configured to take other suitable data as inputs (e.g., humidity data from humidity sensor 40034, pressure data from pressure sensor 40046, data from Internet of Things connected device 40024, etc.) and calculate one or more pipe strain values. Digital twin dynamic system 40008 may then update the manufacturing facility digital twin, the pipe digital twin, and any other suitable industrial entity digital twin with the pipe strain values.

In another example, client application 40070 may be an augmented reality application. In some embodiments of this example, client application 40070 may obtain vibration fault level conditions of bearings within the field of view of the AR-enabled device (e.g., smart glasses) hosting the client application from a digital twin of the industrial environment (e.g., via an API, web hook, etc. of digital twin system 40000) and display the obtained vibration fault level conditions on the display of the AR-enabled device such that the displayed vibration fault level conditions correspond to a position within the field of view of the AR-enabled device. In this way, vibration fault level conditions may be displayed even if a vibration sensor is not positioned within the field of view of the AR-enabled device.

Figure 220 shows an exemplary embodiment of a method in 42100 for updating a set of vibration severity unit values for bearings in a machine's digital twin. Vibration severity units may be measured as displacement, velocity, and acceleration.

In this example, a client application 40070 interfacing with the digital twin dynamic model system 40008 may be configured to provide a visualization of three-dimensional vibration characteristics of bearings in the machine's digital twin. The RF spectral characteristics may include signal frequency, signal amplitude, power level, etc. In an embodiment, these characteristics may be measured by an RF sensor 40078. The RF sensor 40078 may be a spectrum analyzer, a power meter, a frequency counter, an RF vector network analyzer (VNA), etc.

In this example, digital twin dynamic model system 40008 may receive a request from client application 40070 to update a vibration severity unit value for a bearing of a machine's digital twin. In 42102, digital twin dynamic model system 40008 receives a request from client application 40070 to update one or more vibration severity unit value(s) for a manufacturing facility's digital twin. Then, in 42104, digital twin dynamic model system 40008 determines one or more digital twins needed to fulfill the request and retrieves the one or more needed digital twins from digital twin data store 40016. In this example, digital twin dynamic model system 40008 may search the machine's digital twin and any embedded digital twins (e.g., digital twins of bearings and other components). In 42108, digital twin dynamic model system 40008 determines one or more dynamic models needed to fulfill the request and retrieves the one or more needed dynamic models from dynamic model data store 400102. At 42110, digital twin dynamic model system 40008 selects dynamic model input data sources (e.g., one or more sensors from sensor system 40030, data from Internet of Things connected devices 40024, and any other suitable data) via digital twin I/O system 40004 based on available data sources (e.g., available sensors from the sensor set of sensor system 40030) and one or more required inputs of the dynamic model(s). In this example, the retrieved dynamic model may be configured to receive measurements from one or more vibration sensors as inputs and provide unit values of bearing severity in the machine. At 42112, digital twin dynamic model system 40008 obtains one or more measurements from each of the selected sensors. In this example, digital twin dynamic model system 40008 obtains measurements from vibration sensor 40036 via digital twin I/O system 40004. At 42114, the digital twin dynamic model system 40008 runs the dynamic model(s) using the retrieved vibration measurements as input to calculate one or more output values representing vibration severity unit values for the bearings in the machine. Then, at 42118, the digital twin dynamic model system 40008 updates the one or more vibration severity unit values for the bearings in the machine digital twin and all other embedded digital twins or digital twins embedding the machine digital twin based on the one or more values output by the dynamic model(s).

FIG. 221 illustrates an exemplary embodiment of a method 42200 for updating a set of machine component failure probability values in a digital twin of a machine. FIG. 217 illustrates an exemplary embodiment of a method for updating a set of electrodynamics-related values in a digital twin of an industrial environment, such as a manufacturing facility. In this example, a client application 40070 interfacing with the digital twin dynamics system 40008 may be configured to provide a visualization of the geospatial radiation characteristics of the manufacturing facility in the digital twin of the manufacturing facility. In an embodiment, the electrodynamics-related values may be related to electromagnetic field (EMF) radiation. Exemplary types of EMF radiation include radio frequency, magnetic field, and electric field. The geospatial radiation characteristics may include radiation intensity, radiation frequency, etc.

In this example, digital twin dynamic model system 40008 may receive a request from client application 40070 to update failure probability values for components of a machine digital twin. At 42202, digital twin dynamic model system 40008 receives a request from client application 40070 to update one or more failure probability values for the machine digital twin, any embedded component digital twins, and any digital twins that embed the machine digital twin, such as a manufacturing facility digital twin. Then, at 42204, digital twin dynamic model system 40008 determines one or more digital twins needed to fulfill the request and retrieves the one or more needed digital twins. In this example, digital twin dynamic model system 40008 may retrieve the manufacturing facility digital twin, the machine digital twin, and the machine component digital twins from digital twin data store 40016. At 42208, digital twin dynamic model system 40008 determines one or more dynamic models needed to fulfill the request and retrieves the one or more needed dynamic models from dynamic model data store 400102. At 42210, digital twin dynamic model system 40008 selects dynamic model input data sources (e.g., one or more sensors from sensor system 40030, data from Internet of Things connected devices 40024, and any other suitable data) based on available data sources (e.g., available sensors from the sensor set of sensor system 40030) and one or more required inputs of the dynamic model(s) via digital twin I/O system 40004. In this example, the retrieved dynamic model may take one or more vibration measurements from vibration sensor 40036 and historical failure data as inputs for the dynamic model and output failure probability values for machine components in the machine's digital twin. At 42212, digital twin dynamic model system 40008 retrieves data from each of the selected sensors and/or Internet of Things connected devices via digital twin I/O system 40004. At 42214, the digital twin dynamic model system digital twin dynamic model system 40008 runs the dynamic model(s) using the retrieved vibration data and historical failure data as inputs to calculate one or more outputs representing failure probability values for the bearings of the machine digital twin. Then, at 42218, the digital twin dynamic model system 40008 updates the one or more failure probability values for the bearings in the machine digital twin, all embedded digital twins, and all digital twins that embed the machine digital twin based on the output of the dynamic model(s).

FIG. 222 illustrates an exemplary embodiment of a method 42300 for updating a set of machine downtime probabilities in a digital twin of a manufacturing facility. The chemical properties may include chemicals present in the environment, concentrations of chemicals, etc. The chemical sensor 40054 may detect and measure the concentration of a target molecule (also called an analyte). In an embodiment, the chemical sensor 40054 may be a gas sensor (such as a semiconductor gas sensor, an electrochemical gas sensor, a catalytic combustion gas sensor, an optical gas sensor, and a polymer gas sensor), an ion sensor, and a humidity sensor.

In this example, a client application 40070 interfacing with the digital twin dynamic model system 40008 may be configured to provide a visualization of the probability of manufacturing facility downtime values in the manufacturing facility's digital twin.

In this example, digital twin dynamic model system 40008 may receive a request from client application 40070 to assign probabilities of downtime values to machines in a manufacturing facility digital twin. At 42302, digital twin dynamic model system 40008 receives a request from client application 40070 to update probabilities of one or more downtime values for machines in the manufacturing facility digital twin and any embedded digital twins, such as individual machine digital twins. Then, at 42304, digital twin dynamic model system 40008 determines one or more digital twins required to fulfill the request and retrieves the one or more required digital twins from digital twin data store 40016. In this example, digital twin dynamic model system 40008 may retrieve the manufacturing facility digital twin and any embedded digital twins from digital twin data store 40016. At 42308, digital twin dynamic model system 40008 determines one or more dynamic models required to fulfill the request and retrieves the one or more required dynamic models from dynamic model data store 400102. At 42310, digital twin dynamic model system 40008 selects dynamic model input data sources (e.g., one or more sensors from sensor system 40030, data from Internet of Things connected devices 40024, and any other suitable data) based on available data sources (e.g., available sensors from the sensor set of sensor system 40030) and one or more required inputs of the dynamic model(s) via digital twin I/O system 40004. In this example, the dynamic model(s) may be configured to take vibration measurements from vibration sensors and historical downtime data as inputs and output probabilities of downtime values for different machines throughout the manufacturing facility. At 42312, digital twin dynamic model system 40008 obtains one or more measurements from each of the selected sensors via digital twin I/O system 40004. At 42314, digital twin dynamic model system 40008 runs the dynamic model(s) using the retrieved vibration measurements and historical downtime data as inputs and calculates one or more outputs representing probabilities of downtime values for machines in the manufacturing facility. Next, in 42318, the digital twin dynamic model system 40008 updates the probability of one or more downtime values for the machines in the manufacturing facility's digital twin and all embedded digital twins based on one or more outputs of the dynamic model.

FIG. 223 shows an example embodiment of a method 42400 for updating one or more shutdown probability values in a digital twin of an enterprise having a set of manufacturing facilities.

In this example, digital twin dynamic model system 40008 may receive a request from client application 40070 to update shutdown probability values for a set of manufacturing facilities within an enterprise digital twin. At 42402, digital twin dynamic model system 40008 receives a request from client application 40070 to update one or more shutdown probability values for the enterprise digital twin and any embedded digital twins. Then, at 42404, digital twin dynamic model system 40008 determines one or more digital twins needed to fulfill the request and retrieves the one or more required digital twins from digital twin data store 40016. In this example, digital twin dynamic model system 40008 may search the enterprise digital twin and any embedded digital twins. At 42408, digital twin dynamic model system 40008 determines one or more dynamic models needed to fulfill the request and retrieves the one or more required dynamic models from dynamic model data store 400102. At 42410, digital twin dynamic model system 40008 selects dynamic model input data sources (e.g., one or more sensors from sensor system 40030, data from Internet of Things connected devices 40024, and any other suitable data) based on available data sources (e.g., available sensors from the sensor set of sensor system 40030) and one or more required inputs of the dynamic model(s) via digital twin I/O system 40004. In this example, the retrieved dynamic model may be configured to take as input one or more vibration measurements from vibration sensors 40036 and/or other suitable data and output a shutdown probability value for each manufacturing entity in the enterprise digital twin. At 42412, digital twin dynamic model system 40008 retrieves one or more vibration measurements from each of the selected vibration sensors 40036 from digital twin I/O system 40004. At 42414, the digital twin dynamic model system 40008 runs the dynamic model(s) using the retrieved vibration measurements and historical shutdown data as inputs to calculate one or more outputs representing shutdown probability values for the manufacturing equipment in the enterprise digital twin. Then, at 42418, the digital twin dynamic model system 40008 updates one or more shutdown probability values for the enterprise digital twin and all embedded digital twins based on the one or more outputs of the dynamic model(s).

FIG. 224 illustrates an exemplary embodiment of a method 42500 for updating a set of downtime cost values for machines in a digital twin of a manufacturing facility. In the embodiment, the manufacturing

In this example, digital twin dynamic model system 40008 may receive a request from client application 40070 to populate real-time downtime cost values associated with machines in a manufacturing facility digital twin. At 42502, digital twin dynamic model system 40008 receives a request from client application 40070 to update one or more downtime cost values for the manufacturing facility digital twin and any embedded digital twins (e.g., machines, machine parts, etc.). Then, at 42504, digital twin dynamic model system 40008 determines one or more digital twins needed to fulfill the request and retrieves the required one or more digital twins. In this example, digital twin dynamic model system 40008 may search digital twins of the manufacturing facility, machines, machine parts, and other embedded digital twins from digital twin data store 40016. At 42508, digital twin dynamic model system 40008 determines one or more dynamic models needed to fulfill the request and retrieves the required one or more dynamic models from dynamic model data store 400102. At 42510, the digital twin dynamic model system 40008 selects dynamic model input data sources (e.g., one or more sensors from the sensor system 40030, data from the Internet of Things connected devices 40024, and other suitable data) based on available data sources (e.g., available sensors from the sensor set of the sensor system 40030) and one or more required inputs of the dynamic model(s) via the digital twin I/O system 40004. In this example, the retrieved dynamic model(s) may be configured to take historical downtime data and operational data as inputs and output data representing the cost of downtime per day of machines in the manufacturing facility. At 42512, the digital twin dynamic model system 40008 retrieves the historical downtime data and operational data from the digital twin I/O system 40004. At 42514, the digital twin dynamic model system 40008 runs the dynamic model(s) using the retrieved data as inputs and calculates one or more outputs representing the cost of downtime per day of machines in the manufacturing facility. Next, at 42518, the digital twin dynamic model system 40008 updates one or more downtime cost values for the manufacturing facility digital twin and the machine digital twin based on one or more outputs of the dynamic model(s).

FIG. 225 illustrates an exemplary embodiment of a method 42600 for updating a set of manufacturing KPI values in a digital twin of a manufacturing facility. In an embodiment, the manufacturing KPIs include uptime, capacity utilization, standard operating efficiency, overall operating efficiency, overall equipment effectiveness, machine downtime, unplanned downtime, machine setup time, inventory turns, inventory accuracy, quality (e.g., quality (defective rate), first pass rate, rework, scrap, audit failures, on-time delivery, returns, training hours, employee turnover, reportable health and safety incidents, revenue per employee, profit per employee, schedule attainment, total cycle time, throughput, changeover time, yield, planned maintenance rate, availability rate, and return rate.

In this example, digital twin dynamic model system 40008 may receive a request from client application 40070 to populate the manufacturing facility digital twin with real-time manufacturing KPI values. At 42602, digital twin dynamic model system 40008 receives a request from client application 40070 to update one or more KPI values for the manufacturing facility digital twin and any embedded digital twins (e.g., machines, machine parts, etc.). Then, at 42604, digital twin dynamic model system 40008 determines one or more digital twins needed to fulfill the request and retrieves the required one or more digital twins. In this example, digital twin dynamic model system 40008 may search digital twins of the manufacturing facility, machines, machine parts, and any other embedded digital twins from digital twin data store 40016. At 42608, digital twin dynamic model system 40008 determines one or more dynamic models needed to fulfill the request and retrieves the required one or more dynamic models from dynamic model data store 400102. At 42610, the digital twin dynamic model system 40008 selects dynamic model input data sources (e.g., one or more sensors from the sensor system 40030, data from the Internet of Things connected devices 40024, and other suitable data) based on available data sources (e.g., available sensors from the sensor set of the sensor system 40030) and one or more required inputs of the dynamic model(s) via the digital twin I/O system 40004. In this example, the retrieved dynamic model(s) may be configured to take as input one or more vibration measurements and other operational data obtained from the vibration sensors 40036 and output one or more manufacturing KPIs for the facility. At 42612, the digital twin dynamic model system 40008 obtains one or more vibration measurements from each of the selected vibration sensors 40036 and obtains the operational data from the digital twin I/O system 40004. At 42614, the digital twin dynamic model system 40008 runs the dynamic model(s) using the retrieved vibration measurements and operational data as inputs to calculate one or more outputs representing the manufacturing KPIs of the manufacturing facility. Then, at 42618, the digital twin dynamic model system 40008 updates one or more KPI values for the manufacturing facility digital twin, the machine digital twin, the machine part digital twin, and any other embedded digital twins based on the one or more outputs of the dynamic model(s).

A further embodiment includes a method for updating a set of concentration values for a biologically hazardous agent in a digital twin of an industrial entity, such as a wastewater treatment plant. Biologically hazardous agents may be found in factories that use metalworking fluids and may also be found in waste treatment facilities. Biologically hazardous substances can be detected using biosensors. In this example, a client application interfacing with the digital twin dynamic system may be configured to provide a visualization of the concentration of the biologically hazardous agent in the digital twin of the wastewater treatment plant. In an embodiment, the biosensor may be an acoustic biosensor, an amperometric biosensor, an electrochemical biosensor, a photoelectric biosensor, a calorimetric biosensor, a potentiometric biosensor, an immunobiosensor, a piezoelectric biosensor, or the like.

In this example, the digital twin dynamic system may receive a request from a client application to update concentration values of a biologically harmful agent in a wastewater treatment plant digital twin. In a next block, the digital twin dynamic system receives a request from the client application to update concentration values of one or more biologically harmful agents in the wastewater treatment plant digital twin and any embedded digital twins, such that the concentration values represent real-time concentration levels of the biologically harmful agents in the plant. In a next block, the digital twin dynamic system determines one or more digital twins needed to fulfill the request and retrieves the required one or more digital twins from the digital twin data store. In this example, the digital twin dynamic system may search the wastewater treatment plant digital twin or may search other embedded digital twins. In a next block, the digital twin dynamic system determines one or more dynamic models needed to fulfill the request and retrieves the one or more required dynamic models from the dynamic model data store. In a next block, the digital twin dynamic system selects input data sources for the dynamic model (e.g., one or more sensors from the sensor system, data from Internet of Things connected devices, and other suitable data) based on available data sources (e.g., available sensors from the sensor set of the sensor system) and one or more required inputs of the dynamic model(s) via the digital twin I/O system. In this example, the retrieved dynamic model(s) may be configured to receive inputs of one or more concentration measurements from a biosensor, temperature measurements from a temperature sensor, and/or pressure measurements from a pressure sensor, and output concentration measurements of a biohazardous agent at different locations within the plant. In a next block, the digital twin dynamic system retrieves measurements from the biosensors, temperature sensors, and pressure sensors located within the plant via the digital twin I/O system. In a next block, the digital twin dynamic system executes the dynamic model using the retrieved measurements as inputs and calculates one or more outputs representing concentration values of the biohazardous agent at different locations within the wastewater treatment plant or throughout the plant. In the next block, the digital twin dynamic system updates one or more biologically harmful agent concentration values in the wastewater treatment plant digital twin, and all other embedded digital twins, based on the output of the dynamic model(s).

A further exemplary embodiment includes a method for updating a set of fluid dynamic properties in a digital twin of an industrial entity, such as a water piping system. In this example, a client application interfacing with the digital twin dynamic system may be configured to provide a visualization of fluid flow within the water piping system in the digital twin of the water piping system. The fluid flow rate may depend on pressure, dimensions, and material properties of the conduit (e.g., shape, roughness, restriction, etc.). A fluid flow sensor may be configured to measure the fluid flow rate. The fluid flow sensor may be a flow meter, such as a differential pressure flow meter or a pressure meter.
Flow meters include orifice plates, flow nozzles, Venturi tubes, and variable area rotameters, velocity flow meters, positive displacement flow meters, mass flow meters, and open channel flow meters (weirs, flumes, submerged orifices, current meters, acoustic flow meters, etc.).

In this example, the digital twin dynamic system may receive a request from a client application to update flow rate values in the digital twin of a water piping system. In a next block, the digital twin dynamic system receives a request from the client application to update one or more flow rate values in the digital twin of the piping system and any embedded digital twins so that the flow rate values represent real-time fluid flow rates in the piping system. In a next block, the digital twin dynamic system determines one or more digital twins needed to fulfill the request and retrieves the needed one or more digital twins from the digital twin data store. In this example, the digital twin dynamic system may search the digital twin of the water piping system, the digital twin of the facility including the water piping system, and other embedded digital twins. In a next block, the digital twin dynamic system determines one or more dynamic models needed to fulfill the request and retrieves the needed one or more dynamic models from the dynamic model data store. In a next block, the digital twin dynamic system selects input data sources for the dynamic models (e.g., one or more sensors from the sensor system, data from Internet of Things connected devices, and other appropriate data) based on available data sources (e.g., available sensors from a sensor set of a sensor system) and one or more requested inputs of the dynamic models via the digital twin I/O system. In this example, the retrieved dynamic model may be configured to retrieve one or more flow measurements obtained from the fluid flow sensors and model flow values throughout the piping system. In a next block, the digital twin dynamic system retrieves one or more measurements from each of the selected fluid flow sensors from the digital twin I/O system. In a next block, the digital twin dynamic system executes the dynamic model using the retrieved fluid flow measurements as inputs and calculates one or more outputs representing flow values throughout the piping system and/or at different locations throughout the piping system. In a next block, the digital twin dynamic system updates one or more flow values in the water supply piping digital twin, the manufacturing facility digital twin, and all embedded digital twins based on one or more outputs of the dynamic model(s).

Further exemplary embodiments include a method for updating a set of rays.
Digital twins can model relevant values in digital twins of industrial environments such as nuclear power plants. Radiation modeling in digital twins can be useful for nuclear energy production, nuclear research reactors, fuel cycles, nuclear marine propulsion, and more. Radiation sensors can measure site-specific levels of alpha, beta, gamma, or neutron radiation using various types of detectors. In this example, a client application interfacing with the digital twin dynamic system may be configured to provide visualization of gamma radiation dose rates at a nuclear production facility in the digital twin of the nuclear production facility.

The digital twin dynamic system may receive a request from a client application to update the gamma dose rate of the nuclear production facility digital twin. In a next block, the digital twin dynamic system receives a request from the client application to update one or more gamma dose rate values of the nuclear production facility digital twin and any embedded digital twins so that the gamma dose rate represents the real-time gamma dose rate in the physical nuclear production facility system. In a next block, the digital twin dynamic system determines one or more digital twins needed to fulfill the request and retrieves the required one or more digital twins from the digital twin data store. In this example, the digital twin dynamic system may search the nuclear power facility digital twin and other embedded digital twins. In a next block, the digital twin dynamic system determines one or more dynamic models needed to fulfill the request and retrieves the required one or more dynamic models from the dynamic model data store. In a next block, the digital twin dynamic system selects input data sources for the dynamic models (e.g., one or more sensors from the sensor system, data from Internet of Things connected devices, and other appropriate data) based on available data sources (e.g., available sensors from the sensor set of the sensor system) and one or more required inputs of the dynamic models via the digital twin I/O system. In this example, the retrieved dynamic model may be configured to take one or more gamma dose rate measurements obtained from the radiation sensors as inputs and output gamma dose rate values at other locations throughout the nuclear production facility. In a next block, the digital twin dynamic system retrieves one or more measurements from each of the selected radiation sensors from the digital twin I/O system. In a next block, the digital twin dynamic system executes the dynamic model using the retrieved gamma dose rate measurements as inputs and calculates one or more outputs representing gamma dose rate values at different locations within and/or throughout the facility. In a next block, the digital twin dynamic system updates one or more gamma dose rate values in the nuclear production facility digital twin and all embedded digital twins based on the one or more outputs of the dynamic model(s).

An exemplary embodiment includes a method for updating a set of quantum mechanical values in a digital twin of an industrial environment. In this example, a client application interfacing with the digital twin dynamic system may be configured to provide a visualization of the quantum mechanical values in the digital twin of the industrial environment. For example, industrial entities with near-atomic dimensions may exhibit quantum mechanical behavior and be modeled by dynamic models that adhere to quantum mechanical principles. The quantum mechanical properties may be measured by quantum sensors.

In this example, the digital twin dynamic system may receive a request from a client application to update one or more quantum mechanical values of an industrial environment digital twin in which an industrial entity digital twin representing an atomic-scale industrial entity is embedded. In a next block, the digital twin dynamic system receives a request from the client application to update one or more quantum mechanical values of the industrial environment digital twin and the embedded digital twin to represent real-time characteristics in the physical industrial environment. In a next block, the digital twin dynamic system determines one or more digital twins required to fulfill the request and retrieves the required one or more digital twins from the digital twin data store. In this example, the digital twin dynamic system may retrieve the industrial environment digital twin and the embedded atomic digital twin. In a next block, the digital twin dynamic system determines one or more dynamic models required to fulfill the request and retrieves the required one or more dynamic models from the dynamic model data store. In a next block, the digital twin dynamic system selects input data sources for the dynamic model (e.g., one or more sensors from the sensor system, data from Internet-of-Things connected devices, or other appropriate data) based on available data sources (e.g., available sensors from a sensor set of a sensor system) and one or more requested inputs of the dynamic model(s) via the digital twin I/O system. In this example, the retrieved dynamic model(s) may be configured to take one or more quantum mechanical measurements obtained from quantum sensors located in the industrial environment as inputs and apply one or more quantum mechanically compliant dynamic models to obtain one or more quantum mechanical values for different locations in the industrial environment and/or the entire environment. In a next block, the digital twin dynamic system obtains one or more measurements from each of the selected quantum sensors via the digital twin I/O system. In a next block, the digital twin dynamic system executes the dynamic models using the obtained quantum mechanical measurements as inputs to calculate one or more quantum mechanical values for different locations in the industrial environment and/or the entire industrial environment. In a next block, the digital twin dynamic system updates one or more values in the industrial environment digital twin, the atomic industrial entity digital twin, and all other embedded digital twins based on one or more outputs of the quantum mechanical dynamic models.

An exemplary embodiment includes a method for updating a set of positions of industrial entities, such as containers, in a digital twin of an industrial environment, such as a manufacturing facility. In this example, a client application interfacing with the digital twin dynamics system may be configured to provide a visualization of the positions of containers through the manufacturing facility in the digital twin of the manufacturing facility.

In this example, the digital twin dynamics system may receive a request from a client application to update the location values of a container in a manufacturing facility digital twin. In a next block, the digital twin dynamics system receives a request from the client application to update the location values of one or more containers in the manufacturing facility digital twin, the embedded container digital twin, and other embedded digital twins so that the location values represent the real-time location of the container in the physical manufacturing facility. In a next block, the digital twin dynamics system determines one or more digital twins needed to fulfill the request and retrieves the required one or more digital twins from the digital twin data store. In this example, the digital twin dynamics system may retrieve the manufacturing facility digital twin, the container digital twin, the robot digital twin, and other embedded digital twins. In a next block, the digital twin dynamics system determines one or more dynamic models needed to fulfill the request and retrieves the required one or more dynamic models. In a next block, the digital twin dynamics system selects input data sources for the dynamic model (e.g., one or more sensors from the sensor system, data from Internet of Things connected devices, and any other suitable data) based on available data sources (e.g., available sensors from a set of sensors in a sensor system) and one or more required inputs for the dynamic model using the digital twin I/O system. In this example, the retrieved dynamic model may be based on classical mechanics. The one or more dynamic models may be configured to take as input one or more velocity measurements obtained from Internet of Things connected devices used to move the container, such as robots used to move the container, and apply the dynamic model to obtain one or more output values related to the location of the container throughout the manufacturing facility. In a next block, the digital twin dynamic system obtains one or more velocity measurements from each of the selected robots via the digital twin I/O system. In a next block, the digital twin dynamic system executes the dynamic model using the obtained velocity measurements as input to calculate one or more output values representing the location of the container in the environment. In a next block, the digital twin dynamic system updates one or more location values for the container in the manufacturing facility digital twin, the container digital twin, the robot digital twin, and all embedded digital twins based on one or more outputs of the dynamic model.

An exemplary embodiment includes a method for updating a set of metal concentrations in an industrial environment, such as a waste stream. In this example, a client application interfacing with a digital twin dynamic system may be configured to provide a visualization of metal concentrations in the waste stream in the digital twin of the waste stream. For example, copper, chromium, nickel, and zinc are frequently found in high concentrations in industrial wastewater, and each may be removed by precipitation.

The digital twin dynamic system may receive a request from a client application to update the copper concentration of an industrial waste stream digital twin. In a next block, the digital twin dynamic system receives a request from the client application to update one or more copper concentration values of the waste stream digital twin and other embedded digital twins (such as the sediment filter digital twin) so that the copper concentration values represent real-time copper concentrations in the waste stream. In a next block, the digital twin dynamic system determines one or more digital twins needed to fulfill the request and retrieves the one or more needed digital twins from the digital twin data store. In this example, the digital twin dynamic system may search the waste stream digital twin and other embedded digital twins. In a next block, the digital twin dynamic system determines one or more dynamic models needed to fulfill the request and retrieves the one or more needed dynamic models from the dynamic model data store. In a next block, the digital twin dynamic system selects input data sources (e.g., one or more sensors from a sensor system, data from Internet of Things connected devices, and any other suitable data) for the dynamic model based on available data sources (e.g., one or more sensors from a sensor system, data from Internet of Things connected devices, and any other suitable data).
The digital twin dynamic system retrieves one or more copper concentration values from each of the selected chemical sensors via the digital twin I/O system. The digital twin dynamic system then executes the dynamic model using the retrieved measurements as inputs to calculate one or more outputs representing copper concentration values at different locations within the industrial waste stream and/or the entire industrial waste stream. The digital twin dynamic system then updates one or more copper concentration values in the industrial waste stream's digital twin and all embedded digital twins based on one or more outputs of the dynamic model.

An exemplary embodiment includes a method for updating a set of concentrations of organic compounds in a digital twin of an industrial entity, such as a container. In this example, a client application interfacing with the digital twin dynamic system may be configured to provide a visualization of the concentrations of organic compounds, such as in a digital twin of a vessel having liquid and gas components.

In this example, the digital twin dynamic system may receive a request from a client application to update the concentration of an organic compound in the digital twin of a container. In a next block, the digital twin dynamic system receives a request from the client application to update one or more organic compound concentration values in the digital twin of the container and other embedded digital twins such that the organic compound concentration values represent the real-time organic compound concentration in the container. In a next block, the digital twin dynamic system determines one or more digital twins needed to fulfill the request and retrieves the required digital twin or twins. In this example, the digital twin dynamic system may retrieve the digital twin of the container, the digital twins embedding the container, and the other embedded digital twins from a digital twin data store. In a next block, the digital twin dynamic system determines one or more dynamic models needed to fulfill the request and retrieves the required dynamic model or models from a dynamic model data store. The dynamic models in this example may conform to principles of organic chemistry. In a next block, the digital twin dynamic system selects input data sources for the dynamic model (e.g., one or more sensors from the sensor system, data from Internet-of-Things connected devices, and other suitable data) based on available data sources (e.g., available sensors from the sensor set of the sensor system) and one or more required inputs of the dynamic model(s) via the digital twin I/O system. The dynamic model may be configured to take one or more organic compound concentration measurements from a chemical sensor, a temperature measurement from a temperature sensor, and/or a pressure measurement from a pressure sensor as inputs and apply the dynamic model to obtain one or more output values related to organic compound concentrations at different locations within the vessel and/or throughout the vessel. In a next block, the digital twin dynamic system acquires one or more measurements from each of the selected chemical sensors, temperature sensors, and pressure sensors via the digital twin I/O system. In a next block, the digital twin dynamic system executes the dynamic model using the acquired measurements as inputs and calculates one or more outputs representing organic compound concentrations in the vessel. In a next block, the digital twin dynamic system updates one or more organic compound concentration values for the container digital twin, all digital twins incorporating the container, and all embedded digital twins based on one or more outputs of the dynamic model.

An exemplary embodiment includes a method for updating a set of biologically relevant values in a digital twin of an industrial entity, such as a beer brewing system. In this example, a client application interfacing with the digital twin dynamic system may be configured to provide a visualization of concentrations of biological compounds in the digital twin of the beer brewing system.

In this example, the digital twin dynamic system may receive a request from a client application to update concentrations of biological compounds in the digital twin of a beer brewing system. In a next block, the digital twin dynamic system receives a request from the client application to update concentration values of one or more biological compounds in the digital twin of the brewing system and other embedded digital twins so that the concentration values represent real-time concentrations in a physical process. In a next block, the digital twin dynamic system determines one or more digital twins needed to fulfill the request and retrieves the required one or more digital twins from a digital twin data store. In this example, the digital twin dynamic system may search the digital twin of the brewing system, the digital twins of the machine components, and/or any other embedded digital twins. In a next block, the digital twin dynamic system determines one or more dynamic models needed to fulfill the request and retrieves the required one or more dynamic models from a dynamic model data store. In a next block, the digital twin dynamic system selects input data sources for the dynamic models (e.g., one or more sensors from a sensor system, data from Internet of Things connected devices, and other appropriate data) based on available data sources (e.g., available sensors from a sensor set of a sensor system) and one or more required inputs of the dynamic models via the digital twin I/O system. In this embodiment, the retrieved dynamic model may be based on biological principles.

The dynamic model takes as input one or more biological compound concentration measurements obtained from biosensors within the brewing system and applies the dynamic model to obtain one or more output values of biological compound concentration at different locations throughout the system. In a next block, the digital twin dynamic system obtains one or more measurements from each of the selected biosensors via the digital twin I/O system. In a next block, the digital twin dynamic system executes the dynamic model using the obtained biological compound concentration measurements as input and calculates one or more outputs representing biological compound concentration values at different locations within and/or throughout the system. In a next block, the digital twin dynamic system updates one or more biological compound concentration values in the brewing system digital twin and all embedded digital twins based on one or more outputs of the dynamic model. In embodiments, the digital twin dynamic system can be utilized to enable visual representation of biological models in the digital twin of the industrial environment. In some embodiments, the biological model may be a biological population growth model. In some embodiments, the biological model may be a pathogen spread model. In some embodiments, the biological model is an aging model.

FIG. 218 illustrates an exemplary embodiment of a display interface at 41200 that renders, for example, a digital twin of a dryer centrifuge and displays other information related to the dryer centrifuge. Display interface 41200 includes a title area at 41202 that displays any number of faults or other information related to the device. The display interface at 41200 may include a main screen at 41210 that may depict machine connections monitored by the digital twin and rendered on the display interface.
41200. The main screen 41210 can depict a left bearing 41302 connected to a motor 41304 with a right bearing 41308. The right bearing 41308 can be connected to a pulley 41340. The pulley 41340 can be connected to a belt 41350, which can be connected to a drive pulley 41360. The pulley 41360 can be connected to a left bearing 41370, which can be connected to a dryer centrifuge 41372. The dryer centrifuge 41372 can have a right bearing 41374 connected to a pulley 41380. The pulley 41380 is connected to a belt 41390. The belt 41390 is connected to a pulley 41400. The pulley 41400 is connected to a left bearing 41410 of the motor 41412. The motor 41412 has a right bearing 41414. In these embodiments, the movement of the left bearing 41302 can be depicted at 41320. The movement of the right bearing 41308 can be depicted at 41330. The movement of the left bearing 41370 can be depicted at 41420. The movement of the right bearing 41374 can be depicted at 41422. It will be understood in light of the present disclosure that the display interface 41200 can be configured and reconfigured to display and depict the movement (or a characterization of such movement enlarged for easier visualization) of one or more bearings and other machine components selected from the equipment available in the digital twin. The display interface 41200 further includes a detailed listing of each bearing or other associated machine component at 41220 and the lifetime activity associated with those bearings (or a portion thereof). In embodiments, such information can include costs associated with repairs related to the operation displayed by the digital twin. In embodiments, these estimates can include time to failure, current probability of failure, cost of downtime, cost of repair, etc. In an embodiment, the display interface 41200 can depict the movement of bearings and other related machine components at 41210, can depict them in a simplified graph at 41240 that can be selected between various positions at 41230, can depict harmonic peaks at 41242, other related peaks 41244, etc.

FIG. 226 shows an exemplary embodiment of a display interface that renders, for example, a digital twin of a dryer centrifuge and displays other information related to the dryer centrifuge. Display interface 45000 includes a title area at 45002 that displays any number of faults or other information related to the equipment. Display interface 41200 can include a main screen at 45010 that can depict the machine connections monitored by the digital twin and rendered on display interface 41200. In this view, a user can adjust the connections to depict specific areas, such as a shop floor, manufacturing area, etc., where these machines may be located. In this view, a user can configure what is depicted on main screen 45010 of display interface 41200.
In this view, the user can configure (and reconfigure) not only what is depicted on the main screen 45010 of the display interface 41200, but also what connections the digital twin is listening to and recording conditions such as vibrations and movements. Additionally, the user can configure (and reconfigure) how the received information is displayed on the display interface. By these examples, the sensed information at 45020 can be configured (and reconfigured) to be displayed as a simplified motion by frequency at 41240 in FIG. 218, as shown at 46050 in FIG. 227.

FIG. 227 illustrates an exemplary embodiment of a display interface 46000 that renders a digital twin of, for example, a dryer centrifuge and displays other information related to the dryer centrifuge. The display interface 46000 includes a title area at 46002 that displays any number of faults or other information related to the device. The display interface 46000 may include a main screen at 46010 that may depict the machine connections monitored by the digital twin and rendered on the display interface 46000 similar to that of FIG. 346. The display interface 46000 further includes a detailed listing of each bearing and other associated machine component at 46010, and the lifetime activities associated with those bearings (or portions thereof). In an embodiment, such information may include costs associated with repairs related to the operation displayed by the digital twin. In an embodiment, these estimates may include time to failure, current probability of failure, cost of downtime, cost of repair, etc. In an embodiment, the display interface 41200 can depict the movement of bearings and other related machine components at 46050, a simplified graph at 46020 with the ability to select between various positions at 46030, harmonic peaks at 46032, other related peaks at 46034, filtered and combined views at 46042, etc. The user can configure (reconfigure) how the information received on the display interface is displayed.

FIG. 228 illustrates an exemplary embodiment of a display interface at 47000 that renders a digital twin whose view at 47002 provides a selection between a digital twin dryer centrifuge 47040, a digital twin lathe 47010, a digital twin spinner 47102, etc. The digital twin dryer centrifuge 47040 includes a centrifuge and twin motor configuration at 47044 similar to that depicted in FIG. 346. The digital twin dryer centrifuge 47040 can include a repair cost indicator 47060 based on detected defects depicted at 47062. The digital twin dryer centrifuge 47040 can also include a repair cost indicator 47060 based on detected defects depicted at 47062. A downtime indicator at 47050 and a current failure probability indicator at 47052. The digital twin lathe at 47010 can depict a motor 47012 connected to a lathe 47014. The digital twin lathe at 47010 may also include a repair cost indicator 47030 based on detected failures depicted at 47032, a downtime cost indicator at 47020, and a current failure probability indicator at 47022. Similar to the digital twin lathe at 47010, the digital twin spinner at 47102 may include a motor and spinner combination at 47100. If desired, the user may configure (reconfigure) each view to add or modify what is depicted.

Figure 229 shows an exemplary embodiment of a display interface at 48000 in which a view at 48002 can render a digital twin incorporating connected machines, each with a drive bearing. The exemplary bearings 1, 2, 3, 4, 5, 6, 7, 8, 9, and 10 depicted in Figure 229 can be displayed by the twin as two bearings 48012 and 48014 between the solid connection at 48010, which correlate to bearings 1 and 2. Additionally, two bearings 48022 and 48024 between the solid connection at 48020 can correlate to bearings 3 and 4, two bearings 48032 and 48034 between the solid connection at 48030 can correlate to bearings 5 and 6, and so on. The display interface 48000 includes visualization controls at 48050, which can control the field of view, angle of view, and excitation frequency. These examples show that the two bearings 48032 and 48034 between the solid connections at 48030 are moving outside of their nominal motion. In a sense, a user can clearly see which bearings or other components are squealing, vibrating, or otherwise moving outside of their nominal allowable operation, which can indicate a need for repair, a need for maintenance, etc. It will also be understood in light of this disclosure that the problem of the two bearings 48032 and 48034 between the solid connections at 48030 vibrating can be attributed to the movement of other bearings outside of their nominal motion, as seen with bearing 7.

FIG. 230 illustrates an exemplary embodiment of a display interface at 48500 in which a view at 48502 can render a digital twin incorporating connected machines, each with a driven bearing. The exemplary bearings 1, 2, 3, and 4 depicted in FIG. 230 may be displayed by the twin as two bearings between a solid connection at 48520 correlating to bearings 1 and 2 and a solid connection at 48530 correlating to bearings 3 and 4. These examples show that the two bearings and the solid connection at 48520 (and to a lesser extent at 48530) are moving outside of their nominal motion. Again, the user can clearly see which bearings or other components are squealing, vibrating, or otherwise moving outside of their nominal allowable operation, which may indicate a need for repair, maintenance, etc. Again, the vibration between the two bearings and the solid connection at 48520 can contribute to the movement of other bearings outside of their nominal motion, as can be seen for bearings 3 and 4. FIG. 231 shows an example embodiment of a display interface in 48800 where the view in 48802 can render a digital twin incorporating connected machines each having a drive bearing as in FIG. 230. These examples show the nominal movement between the two bearings and solid connections in 48820 and 48830 relative to that shown in FIG. 230.

Figure 232 shows an example embodiment of a display interface at 49000 in which a view at 49002 can render a digital twin incorporating connected machines, each with a drive bearing. Exemplary bearings 1, 2, 3, and 4 can be displayed by the twin as two bearings 49022 and 49024 between the solid connections at 49020 that correlate to bearings 1 and 2, and bearings 49042 and 49044 between the solid connections at 49040 that correlate to bearings 3 and 4. These examples show that the solid connections between the two bearings and 49020 (and to a lesser extent 49040) are moving outside of nominal operation. Again, the user can clearly see which bearings or other components are squealing, vibrating, or otherwise moving outside of nominal allowable operation, which can indicate a need for repair, maintenance, etc. Again, vibrations between the two bearings and the solid connection at 49020 can contribute to the movement of the other bearing outside of its nominal motion, as can be seen in bearings 3 and 4. Information about the motor and mill is in 49060. In this example, the motor can drive the shaft from one end with a belt drive, and such motion and single-sided drive can be depicted in the diagram. FIG. 233 shows an exemplary embodiment of a display interface at 50000 where a view at 50002 can render a digital twin incorporating connected machines, each with a drive bearing like that of FIG. 232. These examples show that the two bearings 50012 and 50014 between the solid connection at 50010 and the two bearings 50022 and 50024 between the solid connection at 50020 are nominally moving relative to what is shown in FIG. 232.

Referring to FIG. 234, the artificial intelligence system 55050 may define a machine learning model 55052 to perform analysis, simulation, decision-making, and predictions related to one or more data processing, data analysis, simulation creation, and simulation analysis of a manufacturing entity 55010. A machine learning model 55052 is an algorithm and/or statistical model that does not use explicit instructions but instead relies on patterns and inference to perform a specific task. The machine learning model 55052 builds one or more mathematical models based on training data to make predictions and/or decisions without being explicitly programmed to perform a specific task. The machine learning model 55052 may receive input of sensor data as training data, including event data 55140 and state data 55140 related to one or more manufacturing entities 55010. The sensor data input to the machine learning model 55052 may be used to train the machine learning model 55052 to perform analysis, simulation, decision-making, and predictions related to data processing, data analysis, simulation creation, and simulation analysis of one or more manufacturing entities 55010. The machine learning model 55052 may also use input data from or to a user of the information technology system. The machine learning model 55052 may include an artificial neural network, a decision tree, a support vector machine, a Bayesian network, a genetic algorithm, any other suitable form of machine learning model, or a combination thereof. The machine learning model 55052 may be configured to learn by supervised learning, unsupervised learning, reinforcement learning, self-learning, feature learning, sparse dictionary learning, anomaly detection, association rules, a combination thereof, or any other suitable algorithm for learning.

The artificial intelligence system 55050 may also define a digital twin system 55070 to create one or more digital replicas of the manufacturing entity 55010. The digital twin system 55070, the artificial intelligence system 55050, and the adaptive edge intelligence system 55060 may be included in an adaptive intelligence system 55080. The adaptive intelligence system 55080 may be connected to the manufacturing entity 55010 via a connection facility 55020, which may also enable connection to the monitoring system 55100 and the data collector system 55110. The one or more digital replicas of the manufacturing entity may use substantially real-time sensor data to provide a substantially real-time virtual representation of the manufacturing entity and provide a simulation of one or more possible future states of the one or more manufacturing entities. The digital replica exists simultaneously with the one or more manufacturing entities 55010 being replicated. The digital replica provides one or more simulations of both the physical elements and characteristics of the one or more manufacturing entities being replicated, as well as their dynamics, in embodiments, throughout the entire lifecycle of the one or more manufacturing entities being replicated. The digital replica may provide virtual simulation of one or more manufacturing equipment by enabling virtual extrapolation of sensor data to simulate conditions of one or more manufacturing equipment, for example, during the design phase before the one or more manufacturing equipment are constructed or manufactured, or during or after the construction or manufacturing of the one or more manufacturing equipment, such as under high stress, after a period of component wear becomes an issue, during maximum throughput operation, after one or more hypothetical or planned improvements have been made to one or more manufacturing entities, or other suitable hypothetical situations. In some embodiments, the machine learning model 55052 can automatically predict hypothetical situations for simulation using the digital replica, for example, by predicting potential improvements to one or more manufacturing entities, predicting the likelihood of failure of one or more components of one or more manufacturing entities, and/or proposing potential improvements to one or more manufacturing entities, such as timing settings, placement, components, or any other suitable changes to the manufacturing entities. The digital replica enables simulation of one or more manufacturing equipment during both the design and operation phases of the one or more manufacturing equipment, and also enables simulation of virtual operating conditions and configurations of the one or more manufacturing equipment. The digital replica enables invaluable analysis and simulation of one or more manufacturing entities by facilitating the observation and measurement of nearly every type of metric, including temperature, wear, light, vibration, etc., not only in, on, and around each component of the one or more manufacturing entities, but in some embodiments, even within the one or more manufacturing entities. In some embodiments, the machine learning model 55052 may process sensor data, including event data 55140 and state data 55130, from the data storage system 55120 to define simulation data for use by the digital twin system 55070. The machine learning model 55052 may, for example, receive the state data 55130 and event data 55140 associated with a particular manufacturing entity of the plurality of manufacturing entities and perform a series of operations on the state data 55130 and event data 55140 to format the state data 55140 and event data 55140 into a format suitable for use by the digital twin system 55070 in creating the digital replica of the manufacturing entity. For example, the one or more manufacturing entities may include a robot configured to augment products on an adjacent assembly line. The machine learning model 55052 may collect data from one or more sensors located on, near, in, and/or around the robot. The machine learning model 55052 may perform operations on the sensor data to process the sensor data into simulation data and output the simulation data to the digital twin system 55070. The digital twin system 55070 may use the simulation data to create one or more digital replicas of the robot, where the simulation includes metrics including, for example, temperature, wear, speed, rotation, and vibration of the robot and its components. The simulation may be a substantially real-time simulation, allowing a human user of the information technology to view a simulation of the robot, its associated metrics, and metrics associated with its constituent components in substantially real time. The simulation may be a predictive or hypothetical situation, allowing a human user of the information technology to view a predictive or hypothetical simulation of the robot, its associated metrics, and metrics associated with its components.

In some embodiments, the machine learning model 55052 and the digital twin system 55070 can process sensor data to create a digital replica of a set of manufacturing entities of multiple manufacturing entities to facilitate design, real-time simulation, predictive simulation, and/or virtual simulation of a related group of manufacturing entities. The digital replica of the set of manufacturing entities can use substantially real-time sensor data to provide a substantially real-time virtual representation of the set of manufacturing entities and provide a simulation of one or more possible future states of the set of manufacturing entities. The digital replica exists contemporaneously with the set of replicated manufacturing entities. The digital replica provides one or more simulations of both the physical elements and characteristics of the set of replicated manufacturing entities, as well as their dynamics, in embodiments throughout the lifecycle of the set of replicated manufacturing entities. The one or more simulations may include a visual simulation, such as a wireframe virtual representation of one or more manufacturing entities, viewable on a monitor, using an augmented reality (AR) device, or using a virtual reality (VR) device. The visual simulation may be operable by a human user of the information technology system, for example, to zoom in on or highlight components of the simulation, or to provide an exploded view of one or more manufacturing entities. The digital replica can provide a virtual simulation of a set of manufacturing entities by enabling virtual extrapolation of sensor data, for example, during the design phase before the one or more manufacturing entities are built or manufactured, or during or after the construction or manufacture of the one or more manufacturing entities, to simulate conditions of the set of manufacturing entities, such as under high stress, after a period of part wear becomes an issue, during maximum throughput operation, after one or more hypothetical or planned improvements have been made to the set of manufacturing entities, or other suitable hypothetical situations. In some embodiments, the machine learning model 55052 can automatically predict hypothetical situations for simulation using the digital replica, such as predicting potential improvements to the set of manufacturing entities, predicting the likelihood that one or more components of the set of manufacturing entities will fail, and/or suggesting potential improvements to the set of manufacturing entities, such as timing settings, placement, components, or any other suitable changes to the manufacturing entities. The digital replica enables simulation of a fleet of manufacturing equipment during both the design and operation phases of the fleet, as well as simulation of virtual operating conditions and configurations of the fleet of manufacturing equipment. The digital replica enables valuable analysis and simulation of one or more manufacturing entities by facilitating the observation and measurement of nearly any type of metric, including temperature, wear, light, vibration, etc., within, on, and around each component of the set of manufacturing entities, as well as, in some embodiments, within the set of manufacturing entities. In some embodiments, the machine learning model 55052 may process sensor data, including event data 55140 and state data 55140, to define simulation data for use by the digital twin system 55070. The machine learning model 55052 may, for example, receive state data 55130 and event data 55140 associated with a particular manufacturing entity of the plurality of manufacturing entities and perform a series of operations on the state data 55130 and event data 55140 to format the state data 55140 and event data 55140 into a format suitable for use by the digital twin system 55070 in creating the digital replica of the set of manufacturing entities. For example, a set of manufacturing entities may include a die machine configured to place products onto a conveyor belt, a conveyor belt onto which the die machine is configured to place the products, and a plurality of robots configured to add parts to the products as they move along an assembly line. The machine learning model 55052 may collect data from one or more sensors located on, near, in, and/or around each of the die machine, the conveyor belt, and the plurality of robots. The machine learning model 55052 may perform operations on the sensor data to process the sensor data into simulation data and output the simulation data to the digital twin system 55070. The digital twin system 55070 may use the simulation data to create one or more digital replicas of the die machine, the conveyor belt, and the plurality of robots, where the simulation includes metrics including, for example, temperature, wear, speed, rotation, and vibration of the die machine, the conveyor belt, and the plurality of robots and their components. The simulation may be a substantially real-time simulation, allowing a human user of the information technology to view a simulation of the die machine, conveyor belt, and multiple robots, their associated metrics, and metrics associated with their components, in substantially real time. The simulation may be a predictive or hypothetical situation, allowing a human user of the information technology to view a predictive or hypothetical simulation of the die machine, conveyor belt, and multiple robots, their associated metrics, and metrics associated with their components.

In some embodiments, the machine learning model 55052 may prioritize the collection of sensor data for use in the digital replica simulation of one or more manufacturing entities. The machine learning model 55052 may use sensor data and user input to learn, thereby learning which types of sensor data are most effective in creating a digital replica simulation of one or more manufacturing entities. For example, the machine learning model 55052 may discover that a particular manufacturing entity has dynamic characteristics, such as component wear and throughput, that are affected by temperature, humidity, and load. Through machine learning, the machine learning model 55052 may prioritize the collection of sensor data related to temperature, humidity, and load, and may prioritize processing the prioritized types of sensor data into simulation data for output to the digital twin system 55070. In some embodiments, the machine learning model 55052 may suggest to a user of the information technology system that more and/or different sensors of prioritized types be implemented in the information technology near and around the manufacturing entity being simulated, so that more and/or better data of the prioritized types can be used in the simulation of the manufacturing entity via its digital replica.

In some embodiments, the machine learning model 55052 may be configured to learn to determine, based on one or both of the modeling goal and the quality or type of sensor data, what type of sensor data should be processed into simulation data for transmission to the digital twin system 55070. The modeling goal may be an objective set by a user of the information technology system, or may be predicted or learned by the machine learning model 55052. Examples of modeling goals include creating a digital replica that can:
This may be indicative of the dynamics of assembly line throughput and may include the collection, simulation, and modeling of, for example, heat, power, component wear, and other metrics of conveyor belts, assembly machines, one or more products, and other components of the manufacturing ecosystem. To realize such a model, the machine learning model 55052 may be configured to learn to determine what type of sensor data needs to be processed into simulation data for transmission to the digital twin system 55070. In some embodiments, the machine learning model 55052 can analyze what kind of sensor data is being collected, the quality and quantity of the sensor data being collected, and what the collected sensor data represents, make decisions, predictions, analyses, and/or decisions related to which types of sensor data are relevant and/or not relevant to achieving the modeling goals, and make decisions, predictions, analyses, and/or decisions to prioritize, improve, and/or achieve the quality and quantity of sensor data that is processed into simulation data for use by the digital twin system 55070 to achieve the modeling goals.

In some embodiments, a user of the information technology system may input modeling goals into the machine learning model 55052. The machine learning model 55052 may analyze the training data and output suggestions to the user of the information technology system regarding the types of sensor data most relevant to achieving the modeling goals, e.g., one or more types of sensors located in, on, or near the manufacturing entity or entities. The machine learning model may output suggestions to the user of the information technology system regarding whether one or more types of sensors located in, on, or near the manufacturing entity or entities relevant to achieving the modeling goals are sufficient and/or insufficient to achieve the modeling goals, and how different configurations of sensor types, such as adding, removing, or rearranging sensors, may facilitate the machine learning model 55052 and the digital twin system 55070 in achieving the modeling goals. In some embodiments, the machine learning model 55052 may automatically increase or decrease the collection rate, processing, storage, sampling rate, bandwidth allocation, bit rate, and other attributes of sensor data collection to achieve or better achieve the modeling goals. In some embodiments, the machine learning model 55052 may make suggestions or predictions to a user of the information technology system related to increasing or decreasing collection rates, processing, storage, sampling rates, bandwidth allocation, bit rates, and other attributes of sensor data collection to achieve or better achieve the modeling goals. In some embodiments, the machine learning model 55052 may automatically create and/or propose modeling goals using sensor data, simulation data, previous, current, and/or future digital replica simulations of one or more of the multiple manufacturing entities. In some embodiments, the modeling goals automatically created by the machine learning model 55052 may be automatically implemented by the machine learning model 55052. In some embodiments, the modeling goals automatically created by the machine learning model 55052 may be proposed to a user of the information technology system and implemented only after acceptance and/or partial acceptance by the user, such as after modifications are made to the user-proposed modeling goals.

In some embodiments, a user may input one or more modeling goals, for example, by entering one or more modeling commands into the information technology system. The one or more modeling commands may include, for example, commands to the machine learning model 55052 and the digital twin system 55070 to create a digital replica simulation of a manufacturing entity or set of manufacturing entities, and may include a command indicating that the digital replica simulation is one or more of a real-time simulation and a virtual simulation. The modeling commands may also include, for example, what type of sensor data to use, a sampling rate for the sensor data, and other parameters of the sensor data used in the one or more digital replica simulations. In some embodiments, the machine learning model 55052 may be configured to predict modeling commands, such as by using previous modeling commands as learning data. The machine learning model 55052 may suggest predicted modeling commands to a user of the information technology system, for example, to facilitate simulation of one or more manufacturing entities useful for managing the manufacturing entities and/or to enable the user to easily identify potential problems or opportunities for improvement at the manufacturing entities.

In some embodiments, the machine learning model 55052 may be configured to evaluate a set of one or more virtual simulations of the manufacturing entity. The set of what-if simulations may be created by the machine learning model 55052 and the digital twin system 55070 as a result of one or more modeling commands, as a result of one or more modeling objectives, as a result of one or more modeling commands, by predictions by the machine learning model 55052, or a combination thereof. The machine learning model 55052 may evaluate the set of what-if simulations based on one or more metrics defined by a user, one or more metrics defined by the machine learning model 55052, or a combination thereof. In some embodiments, the machine learning model 55052 evaluates each of the virtual simulations in the set of virtual simulations independently of one another. In some embodiments, the machine learning model 55052 may evaluate one or more of the virtual simulations in relation to one another, for example, by ranking the virtual simulations or creating a hierarchy of virtual simulations based on one or more metrics.

In some embodiments, the machine learning model 55052 may include one or more model interpretability systems to facilitate human understanding of the output of the machine learning model 55052, as well as information and insights related to the cognition and processes of the machine learning model 55052. That is, the one or more model interpretability systems allow a human to understand not only "what" the machine learning model 55052 is outputting, but also "why" the machine learning model 55052 is outputting that output, and what the process was that led the machine learning model 55052 to formulate that output. The one or more model interpretability systems may also be used by a human user to improve and guide the training of the machine learning model 55052, to help debug the machine learning model 55052, and to help recognize bias in the machine learning model 55052. The one or more model interpretability systems may include one or more of linear regression, logistic regression, generalized linear model (GLM), generalized additive model (GAM), decision tree, decision rule, RuleFit, and Naive Bayes Classifier. The model may include K-nearest neighbors algorithms, partial dependence plots, individual conditional expectation (ICE), cumulative local effect (ALE) plots, feature interactions, permutation feature importance, global surrogate models, local surrogate (LIME) models, scoped rules, i.e., anchors, Shapley values, Shapley additive explanations (SHAP), feature visualization, network decomposition, or other suitable machine learning interpretability implementations. In some embodiments, the one or more model interpretability systems may include a model dataset visualization system. The model dataset visualization system is configured to automatically provide a human user of the information technology system with visual analysis related to the distribution of values of data nodes in the sensor data, simulation data, and machine learning model 55052.

In some embodiments, the machine learning model 55052 may include and/or implement an embedded model interpretability system, such as a Bayesian case model (BCM) or glass box. The Bayesian case model uses Bayesian case-based reasoning, prototype classification, and clustering to facilitate human understanding of the machine learning model's 55052 data, such as sensor data, simulation data, and data nodes. In some embodiments, the model interpretability system may include and/or implement a glass box interpretability method, such as a Gaussian process, to facilitate human understanding of the machine learning model's 55052 data, such as sensor data, simulation data, and data nodes.

In some embodiments, the machine learning model 55052 may include and/or implement testing with concept activation vectors (TCAVs). TCAVs enable the machine learning model 55052 to learn human-interpretable concepts, such as "run," "don't run," "powered," "unpowered," "robot," "human," "truck," or "ship," from examples through a process that includes defining the concept, determining concept activation vectors, and calculating directional derivatives. By learning human-interpretable concepts, objects, states, etc., TCAVs can enable the machine learning model 55052 to output useful information related to manufacturing entities and data collected therefrom in a format that is easily understandable to human users of information technology systems.

In some embodiments, the machine learning model 55052 may be and/or include an artificial neural network, e.g., a connectionist system configured to “learn” to perform a task by considering examples without being explicitly programmed with task-specific rules. The machine learning model 55052 may be based on a collection of connected units and/or nodes, which may behave like artificial neurons that in some respects emulate neurons in a biological brain. The units and/or nodes may each have one or more connections to other units and/or nodes. The units and/or nodes may be configured to transmit information, e.g., one or more signals, to other units and/or nodes, process signals received from other units and/or nodes, and forward the processed signals to other units and/or nodes. One or more units and/or nodes, as well as the connections therebetween, may be assigned one or more numerical “weights.” The assigned weights may be configured to facilitate the learning, i.e., training, of the machine learning model 55052. The assigned weights may increase and/or decrease one or more signals between one or more units and/or nodes, and in some embodiments may have one or more thresholds associated with one or more of the weights. The one or more thresholds may be configured such that signals are only transmitted between one or more units and/or nodes if the signals and/or aggregate signals exceed the thresholds. In some embodiments, the units and/or nodes may be assigned to multiple layers, each having one or both of an input and an output. A first layer may be configured to receive training data, transform at least a portion of the training data, and transmit the training data and a signal related to the transformation to a second layer.
The final layer may be configured to output an estimate, conclusion, product, or other result as a result of processing one or more inputs by the machine learning model 55052. Each of the layers may perform one or more types of transformations, and one or more signals may pass through one or more of the layers one or more times. In some embodiments, the machine learning model 55052 may be modeled and/or configured at least in part as a deep neural network, a deep belief network, a recurrent neural network, and/or a convolutional neural network, such as by employing deep learning and being configured to include one or more hidden layers.

In some embodiments, the machine learning model 55052 may be and/or include a decision tree, e.g., a tree-based predictive model configured to identify one or more observations and determine one or more conclusions based on inputs. The observations may be modeled as one or more "branches" of the decision tree, and the conclusions may be modeled as one or more "leaves" of the decision tree. In some embodiments, the decision tree may be a classification tree, which may include one or more leaves representing one or more class labels and one or more branches representing one or more connections of features configured to lead to the class labels. In some embodiments, the decision tree may be a regression tree. The regression tree may be configured such that one or more target variables take on continuous values.

In some embodiments, machine learning model 55052 may be and/or include a support vector machine, e.g., a set of related supervised learning methods configured for use in one or both of data classification and regression-based modeling. The support vector machine may be configured to predict whether a new example falls into one or more categories, where the one or more categories are configured during training of the support vector machine.

In some embodiments, the machine learning model 55052 may be configured to perform regression analysis to determine and/or estimate relationships between one or more inputs and one or more features of the one or more inputs. The regression analysis may include linear regression, and the machine learning model 55052 may calculate a single line of best fit to the input data according to one or more mathematical criteria.

In embodiments, inputs to a machine learning model 55052 (e.g., a regression model, a Bayesian network, a supervised model, or other type of model) may be tested, such as using a test dataset independent of the dataset used to create and/or train the machine learning model, to test the impact of various inputs on the accuracy of the model 55052. For example, inputs to a regression model may be removed, including single inputs, pairs of inputs, triplets, etc., to determine whether the absence of the inputs results in a significant degradation of the success of the model 55052. This may be useful in identifying inputs that are indeed correlated (e.g., linear combinations of the same underlying data), redundant, etc. Comparing the success of the models may allow selection among alternative input datasets that provide similar information. For example, it may be possible to identify an input (among multiple similar ones) that introduces the least amount of "noise" into the model, or an input that has the greatest impact on the model's effectiveness at the lowest cost. In this manner, testing of input variations and their impact on model effectiveness may be used to prune or enhance model performance for any of the machine learning systems described throughout this disclosure.

In some embodiments, the machine learning model 55052 may be and/or include a Bayesian network. The Bayesian network may be a probabilistic graphical model configured to represent a set of random variables and the conditional independence of the set of random variables. The Bayesian network may be configured to represent the random variables and the conditional independence via a directed acyclic graph. The Bayesian network may include one or both of a dynamic Bayesian network and an influence diagram.

In some embodiments, the machine learning model 55052 may be defined via supervised learning, i.e., one or more algorithms configured to build a mathematical model of a set of training data including one or more inputs and a desired output. The training data may consist of a set of training examples, each of which has one or more inputs and a desired output, i.e., a supervisory signal. Each of the training examples may be represented in the machine learning model AIDLT102 by an array and/or vector, i.e., a feature vector. The training data may be represented in the machine learning model 55052 by a matrix. The machine learning model 55052 may learn one or more functions through iterative optimization of an objective function, thereby learning to predict outputs associated with new inputs. Once optimized, the objective function can provide the machine learning model 55052 with the ability to accurately determine outputs for inputs other than those included in the training data. In some embodiments, the machine learning model 55052 may be defined via one or more supervised learning algorithms, such as active learning, statistical classification, regression analysis, and similarity learning. Active learning may involve the machine learning model 55052 interactively querying a user and/or using a source of information to label new data points with a desired output. Statistical classification may involve the machine learning model 55052 identifying to which of a set of subcategories, or subpopulations, a new observation belongs based on a training set of data containing observations with known categories. Regression analysis may involve the machine learning model 55052 estimating the relationship between a dependent variable, or outcome variable, and one or more independent variables, or predictors, covariates, and/or features. Similarity learning may involve the machine learning model 55052 learning from examples using a similarity function designed to measure how similar or related two objects are.

In some embodiments, the machine learning model 55052 may be defined via unsupervised learning, i.e., one or more algorithms configured to build a mathematical model of a dataset including only the input by finding structure in the data, such as groupings or clustering of data points. In some embodiments, the machine learning model 55052 may ream from unlabeled, unclassified, test data, i.e., training data. The unsupervised learning algorithm may involve the machine learning model 55052 identifying commonalities in the training data and reactively learning based on the presence or absence of the identified commonalities in new data portions. In some embodiments, the machine learning model 55052 may generate one or more probability density functions. In some embodiments, the machine learning model 55052 may ream by performing cluster analysis, such as assigning a set of observations to subsets, i.e., clusters, according to one or more pre-specified criteria, such as according to a similarity metric that factors in internal compactness, separation, estimated density, and/or graph connectivity.

In some embodiments, the machine learning model 55052 may be defined via one or more algorithms that use semi-supervised learning, i.e., training data in which some training examples may lack training labels. Semi-supervised learning may also be weakly supervised learning, in which the training labels may be noisy, limited, and/or inaccurate. Noisy, limited, and/or inaccurate training labels may be created more cheaply and/or with less effort, and thus the machine learning model 55052 may be trained on a larger set of training data with less cost and/or effort.

In some embodiments, the machine learning model 55052 may be defined via reinforcement learning, such as one or more algorithms using dynamic programming, such that the machine learning model 55052 can be trained by taking actions in an environment to maximize cumulative reward. In some embodiments, the training data is represented as a Markov decision process.

In some embodiments, the machine learning model 55052 may be defined via self-learning, where the machine learning model 55052 is configured to train using training data without external rewards and external instruction, such as by employing a crossbar adaptive array (CAA). The CAA computes behavioral and/or emotional decisions regarding resulting situations in a crossbar manner, thereby enabling the interplay between cognition and emotion to drive the instruction of the machine learning model 55052.

In some embodiments, the machine learning model 55052 may be defined via feature learning, i.e., one or more algorithms designed to find increasingly accurate and/or relevant representations of one or more inputs, e.g., training data, provided during training. Feature learning may include learning via principal component analysis and/or cluster analysis. The feature learning algorithm may involve an attempt by the machine learning model 55052 to transform the input training data such that the transformed input training data is useful while preserving the input training data. In some embodiments, the machine learning model 55052 may be configured to transform the input training data before performing one or more classifications and/or predictions on the input training data. Thus, the machine learning model 55052 may be configured to reconstruct the input training data from one or more unknown data-generating distributions without necessarily conforming to the improbable configurations of the input training data according to the distributions. In some embodiments, the feature learning algorithm may be performed by the machine learning model 55052 in a supervised, unsupervised, or semi-supervised manner.

In some embodiments, the machine learning model 55052 may be defined via anomaly detection, i.e., by identifying rare and/or outlier instances of one or more items, events, and/or observations. Rare and/or outlier instances may be identified by the instances differing significantly from the patterns and/or characteristics of the majority of the training data. Unsupervised anomaly detection may involve the machine learning model 55052 detecting anomalies in an unlabeled training dataset under the assumption that the majority of the training data is "normal." Supervised anomaly detection may involve training on a dataset in which at least a portion of the training data is labeled as "normal" and/or "anomalous."

In some embodiments, the machine learning model 55052 may be defined via robot learning. Robot learning may include the generation of one or more curricula by the machine learning model 55052, where the curricula are sequences of learning experiences that cumulatively acquire new skills through exploration guided by the machine learning model 55052 and social interaction with humans by the machine learning model 55052. The acquisition of new skills may be facilitated by one or more guidance mechanisms, such as active learning, maturation, motor synergy, and/or imitation.

In some embodiments, the machine learning model 55052 may be defined via association rule learning. Association rule learning may involve discovering relationships between variables in a database by the machine learning model 55052 to identify strong rules using some measure of "interestingness." Association rule learning may involve identifying, learning, and/or evolving rules for storing, manipulating, and/or applying knowledge. The machine learning model 55052 may be configured to learn by identifying and/or utilizing a set of association rules, which collectively represent the knowledge captured by the machine learning model 55052. Association rule learning may include one or more of a learning classifier system, inductive logic programming, and an artificial immune system. A learning classifier system is an algorithm that may combine a discovery component, such as one or more genetic algorithms, with a learning component, such as one or more algorithms for supervised learning, reinforcement learning, or unsupervised learning. Inductive logic programming may include rule learning by the machine learning model 55052, which uses logic programming to represent one or more of input examples, background knowledge, and hypotheses determined by the machine learning model 55052 during training. The machine learning model 55052 may be configured to derive a logic program of hypotheses involving all positive examples, given an encoding of known background knowledge and a set of examples represented as a logical database of facts.

In embodiments, the platform can deploy many systems and methods for the Industrial Internet of Things (IIoT), including solutions configurable as IIoT-in-a-Box and other system configurations for IIoT, IIoT interfacing devices and systems (e.g., AR, VR, xR, wearables, etc.), advanced chips, boards, and switches for IIoT applications, etc. In embodiments, the platform can deploy many different systems and methods for data collection, sensor fusion, data management, and artificial intelligence, including systems and methods for intelligent data collection for IIoT, systems and methods for equipment-specific data collection and management systems, and the following systems and methods:
Systems and methods for advanced operational awareness and control, including systems and methods for advanced industrial process control (e.g., hydrolysis to produce hydrogen for industrial heating, cooking, processing, etc.), artificial intelligence and data processing for IIoT pattern and condition detection and prediction, platforms and related methodologies for agile management and governance of IIoT operations (e.g., twins; dashboards; policy engines; etc.), systems and methods for domain-specific applications of IIoT intelligence platforms (e.g., oil &gas;mining;agriculture;municipalities; etc.), systems and methods for converged IIoT platforms, and systems and methods for automated industrial service ecosystems. In embodiments, the platform can deploy many networking and computing capabilities for IIoT entities, including systems and methods for edge and networking convergence, systems and methods for enhanced radio frequency (RF) networking for IIoT, systems and methods for quantum algorithms combined with artificial intelligence for IIoT intelligence, and systems and methods for smart networking protocols.

While only a few embodiments of the present disclosure have been shown and described, it will be apparent to those skilled in the art that many changes and modifications can be made thereto without departing from the spirit and scope of the present disclosure as set forth in the following claims. All foreign and domestic patent applications and patents, and all other publications mentioned herein, are incorporated herein in their entirety to the maximum extent permitted by law.

While many of the features disclosed herein may be described independently of one another, it should be understood that combinations of such features are possible in various embodiments. In embodiments, such combinations may refer to or include, for example, the use of mobile data collection devices, such as wearable devices, handheld devices, mobile robots, and/or mobile vehicles; the use of a ledger, e.g., having a blockchain structure, to store records related to predictive maintenance of industrial machinery; converting or mapping vibration data to units of severity; or a combination of two or more of predictive maintenance of industrial machinery. It should be understood that other combinations of features not explicitly described herein are possible in accordance with embodiments of the present disclosure.

While the foregoing written description will enable one of ordinary skill in the art to make and use what is currently believed to be the best mode thereof, one of ordinary skill in the art will understand and appreciate the existence of variations, combinations, and equivalents of the specific embodiments, methods, and examples herein. Therefore, the present disclosure should not be limited by the above-described embodiments, methods, and examples, but rather by all embodiments and methods within the scope and spirit of the present disclosure.

The methods and systems described herein may be deployed, in part or in whole, via a machine executing computer software, program code, and/or instructions on a processor. The present disclosure may be implemented as a method on a machine, as a system or apparatus that is part of or associated with a machine, or as a computer program product embodied in a computer-readable medium that executes on one or more machines. In embodiments, the processor may be part of a server, cloud server, client, network infrastructure, mobile computing platform, stationary computing platform, or other computing platform. A processor may be any type of computing or processing device capable of executing program instructions, code, binary instructions, etc., including central processing units (CPUs), general processing units (GPUs), logic boards, chips (e.g., graphics chips, video processing chips, data compression chips, etc.), chipsets, controllers, systems-on-chips (e.g., RF systems-on-chips, AI systems-on-chips, video processing systems-on-chips, etc.), integrated circuits, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), approximate computing processors, quantum computing processors, parallel computing processors, neural network processors, and other types of processors. A processor may be or include any variation such as a signal processor, digital processor, data processor, embedded processor, microprocessor, or coprocessor (e.g., mathematical coprocessor, graphics coprocessor, communication coprocessor, video coprocessor, AI coprocessor, etc.) that can directly or indirectly facilitate the execution of program code or program instructions stored thereon. Additionally, a processor may enable the execution of multiple programs, threads, and codes. Threads may be executed simultaneously to increase processor performance and facilitate simultaneous operation of applications.
As a method of implementation, the methods, program codes, program instructions, etc. described herein may be implemented with one or more threads. A thread may spawn other threads, which may have associated priorities, and the processor may execute these threads based on priorities or other ordering based on instructions provided in the program code. The processor, or any machine utilizing one, may include non-transitory memory that stores the methods, codes, instructions, and programs described herein and elsewhere. The processor may access non-transitory storage media through an interface that can store methods, codes, and instructions as described herein and elsewhere. Storage media associated with the processor for storing methods, programs, codes, program instructions, or other types of instructions executable by a computing or processing device may include, but are not limited to, one or more of a CD-ROM, a DVD, memory, a hard disk, a flash drive, RAM, ROM, cache, network-attached storage, server-based storage, etc.

A processor may contain one or more cores, which can increase the speed and performance of a multiprocessor. In embodiments, a process may be a dual-core processor, a quad-core processor, or other chip-level multiprocessor that combines two or more independent cores (sometimes called dies).

The methods and systems described herein may be deployed, in part or in whole, via machines executing computer software on servers, clients, firewalls, gateways, hubs, routers, switches, infrastructure-as-a-service, platform-as-a-service, or other such computer and/or network hardware or systems. The software may be associated with servers, including file servers, print servers, domain servers, Internet servers, intranet servers, cloud servers, infrastructure-as-a-service servers, platform-as-a-service servers, web servers, and other variations such as secondary servers, host servers, distributed servers, failover servers, backup servers, and server farms. A server may include one or more of the following: memory, processors, computer-readable media, storage media, ports (physical and virtual), communication devices, and interfaces accessible to other servers, clients, machines, and devices via wired or wireless media. The methods, programs, or code described herein may be executed by a server. Additionally, other equipment necessary to execute the methods described herein may be considered part of the infrastructure associated with the server.

The server may provide an interface to other devices, including, but not limited to, clients, other servers, printers, database servers, print servers, file servers, communication servers, distributed servers, social networks, etc. Furthermore, this coupling and/or connection may facilitate remote execution of programs over a network. Networking some or all of these devices may facilitate parallel processing of a program or method at one or more locations without departing from the scope of this disclosure. Furthermore, any of the devices connected to the server via an interface may include at least one storage medium capable of storing methods, programs, code, and/or instructions. A central repository may provide program instructions to be executed on different devices. In this embodiment, the remote repository may function as a storage medium for program code, instructions, and programs.

Software programs may be associated with clients, including file clients, print clients, domain clients, Internet clients, intranet clients, and other variations such as secondary clients, host clients, and distributed clients. Clients may include one or more of the following: memory, processors, computer-readable media, storage media, ports (physical and virtual), communication devices, and interfaces that allow access to other clients, servers, machines, and devices via wired or wireless media. Methods, programs, or code described herein may be executed by a client. Additionally, other devices necessary for the execution of methods such as those described herein may be considered part of the infrastructure associated with the client.

Clients may provide interfaces to other devices, including, but not limited to, servers, other clients, printers, database servers, print servers, file servers, communication servers, distributed servers, etc. Furthermore, this coupling and/or connection may facilitate remote execution of programs over a network. Networking some or all of these devices may facilitate parallel processing of a program or method at one or more locations without departing from the scope of this disclosure. Additionally, any of the devices attached to a client via an interface may include at least one storage medium capable of storing methods, programs, applications, code, and/or instructions. A central repository may provide program instructions to be executed on different devices. In this embodiment, remote repositories may function as storage media for program code, instructions, and programs.

In embodiments, one or more of the controllers, circuits, systems, data collectors, storage systems, network elements, components, etc. described throughout this disclosure may be embodied in an integrated circuit, such as an analog, digital, or mixed-signal circuit, e.g., a microprocessor, a programmable logic controller, an application-specific integrated circuit, a field-programmable gate array, or other circuitry, e.g., on one or more chips disposed on one or more circuit boards, that provides one or more of the functions described herein in hardware (potentially with increased speed, energy performance, input/output performance, or the like). For example, billions of logic gates, flip-flops, multiplexers, and other circuits may be placed in a small space, enabling high-speed processing, low power consumption, and reduced manufacturing costs compared to board-level integration. In embodiments, digital ICs, typically microprocessors, digital signal processors, microcontrollers, etc., may process digital signals using Boolean algebra to embody the complex logic involved in the circuits, controllers, and other systems described herein. In embodiments, data collectors, expert systems, storage systems, etc. may be embodied as digital integrated circuits ("ICs"), such as logic ICs, memory chips, interface ICs (e.g., level shifters, serializers), etc. Digital integrated circuits ("ICs") such as logic ICs, memory chips, interface ICs (e.g., level shifters, serializers, deserializers), power management ICs and/or programmable devices, analog integrated circuits such as linear ICs, RF ICs, or mixed-signal ICs such as data acquisition ICs (including A/D converters, D/A converters, digital potentiometers) and/or clock/timing ICs.

The methods and systems described herein may be deployed in part or in whole over a network infrastructure. The network infrastructure may include elements such as computing devices, servers, routers, hubs, firewalls, clients, personal computers, communication devices, routing devices, and other active and passive devices, modules, and/or components known in the art. The computing and/or non-computing device(s) associated with the network infrastructure may include, among other components, storage media such as flash memory, buffers, stacks, RAM, ROM, and the like. The processes, methods, program codes, and instructions described herein and elsewhere may be executed by one or more of the network infrastructure elements. The methods and systems described herein may be adapted for use in any type of private, community, or hybrid cloud computing network or cloud computing environment, including Software as a Service (SaaS), Platform as a Service (PaaS), and/or Infrastructure as a Service (IaaS) functionality.

The methods, program codes, and instructions described herein may be implemented on a cellular network having multiple cells. The cellular network may be either a frequency division multiple access (FDMA) network or a code division multiple access (CDMA) network. The cellular network may include mobile devices, cell sites, base stations, repeaters, antennas, towers, etc. The cell network may be a GSM, GPRS, 3G, 4G, 5G, LTE, EVDO, mesh, or other network type.

The methods, program codes, and instructions described herein and elsewhere may be implemented on or via a mobile device. Mobile devices may include navigation devices, mobile phones, mobile personal digital assistants, laptops, palmtops, netbooks, pagers, e-book readers, music players, and the like. These devices may include, among other components, storage media such as flash memory, buffers, RAM, ROM, and one or more computing devices. The computing devices associated with a mobile device may be capable of executing program code, methods, and instructions stored thereon. Alternatively, the mobile device may be configured to execute instructions in cooperation with other devices. The mobile device may communicate with a base station interfaced with a server and configured to execute program code. The mobile device may communicate over a peer-to-peer network, a mesh network, or other communications network. The program code may be stored in storage media associated with the server and executed by a computing device embedded within the server. The base station may include a computing device and a storage medium. The storage device may store program code and instructions executed by the computing device associated with the base station.

Computer software, program code, and/or instructions may be stored in and/or accessed by computer components, devices, and machine-readable media, such as recording media that retain digital data used for computing for a certain period of time, semiconductor storage known as random access memory (RAM), magnetic storage such as optical disks, hard disks, tapes, drums, and cards, processor registers, cache memory, volatile memory, non-volatile memory, optical storage such as CDs and DVDs, removable media such as flash memory (e.g., CINEMA), removable media such as USB sticks and keys, floppy disks, magnetic tape, paper tape, punch cards, standalone RAM disks, Zip drives, removable mass storage, offline, and other computer memory such as dynamic memory, static memory, read/write storage, mutable storage, read-only, random access, sequential access, location addressable, file addressable, content addressable, network attached storage, storage area network, barcode, magnetic ink, network attached storage, network storage, NVME accessible storage, PCIE attached storage, distributed storage, and the like.

The methods and systems described herein may transform physical and/or intangible items from one state to another. The methods and systems described herein may also transform data representing physical and/or intangible items from one state to another.

The elements described and depicted herein, including the flowcharts and block diagrams in the figures, imply logical boundaries between the elements. However, in accordance with software or hardware engineering practices, the depicted elements and their functionality may be implemented in a machine through computer-executable code using a processor capable of executing program instructions stored thereon, as a monolithic software structure, as a standalone software module, as a module employing external routines, code, services, etc., or any combination thereof; all such implementations are considered within the scope of this disclosure. Examples of such machines include, but are not limited to, personal digital assistants, laptops, personal computers, mobile phones and other handheld computing devices, medical equipment, wired or wireless communication devices, transducers, chips, calculators, satellites, tablet PCs, e-books, gadgets, electronic devices, appliances, artificial intelligence, computing devices, network equipment, servers, routers, and the like. Furthermore, the elements depicted in the flowcharts and block diagrams and other logical entities may be implemented in a machine capable of executing program instructions. Thus, while the foregoing drawings and description illustrate functional aspects of the disclosed system, the specific arrangement of software for implementing those functional aspects should not be inferred from these descriptions unless expressly stated or apparent from the context. Similarly, it will be understood that the various steps identified and described above may be varied, and the order of steps may be adapted to particular applications of the techniques disclosed herein. All such variations and modifications are intended to be within the scope of the present disclosure. As such, the depiction and/or description of the order of various steps should not be understood as requiring a particular order of execution of those steps unless required for a particular application, or unless expressly stated or apparent from the context.

The methods and/or processes described above, and their associated steps, may be implemented in hardware, software, or any combination of hardware and software suitable for a particular application. Hardware may include general-purpose computers and/or special-purpose computing devices, or specific computing devices, or specific aspects or components of specific computing devices. The processes may be implemented in one or more microprocessors, microcontrollers, embedded microcontrollers, programmable digital signal processors, or other programmable devices, along with internal and/or external memory. The processes may also be embodied in application-specific integrated circuits, programmable gate arrays, programmable array logic, or other devices or combinations of devices configured to process electronic signals. It will be understood that one or more of the processes may be implemented as computer-executable code executable on a machine-readable medium.

Computer-executable code may be written using a structured programming language such as C, an object-oriented programming language such as C++, or other high-level or low-level programming language (including assembly language, hardware description languages, and database programming languages and techniques), and may be stored, compiled, or interpreted for execution on one of the above devices as well as heterogeneous combinations of processors, processor architectures, or combinations of different hardware and software, or other machines capable of executing program instructions. Computer software may employ features such as virtualization, virtual machines, containers, dock facilities, and porters.

Thus, in one aspect, the above-described methods and combinations thereof may be embodied in computer-executable code that, when executed on one or more computing devices, performs the steps. In another aspect, the methods may be embodied in systems that perform the steps, may be distributed among devices in many ways, or all of the functionality may be integrated into dedicated stand-alone devices or other hardware. In another aspect, the means for performing the steps associated with the above-described processes may include any of the hardware and/or software described above. All such permutations and combinations are intended to fall within the scope of the present disclosure.

While the present disclosure has been disclosed in connection with the preferred embodiments shown and described in detail, various modifications and improvements thereon will be readily apparent to those skilled in the art. Accordingly, the spirit and scope of the present disclosure is not intended to be limited by the foregoing examples, but is to be understood in the broadest sense permitted by law.

The use of the terms "a" and "an," as well as "the" and similar referents in the context of describing this disclosure (particularly in the context of the claims below), shall be construed to cover both the singular and the plural unless otherwise indicated herein or clearly contradicted by context. The terms "comprising," "with," "including," and "containing" shall be construed as open-ended terms (i.e., meaning "including, but not limited to") unless otherwise noted. The recitation of ranges of values herein, unless otherwise indicated herein, is merely intended to serve as a shorthand method of individually referencing each separate value falling within the range, and each separate value is incorporated herein as if it were individually set forth herein. All methods described herein can be performed in any suitable order unless otherwise indicated herein or clearly contradicted by context. The use of any and all examples or exemplary language (e.g., "such as") provided herein is intended merely to better illuminate the disclosure and does not pose a limitation on the scope of the disclosure unless otherwise claimed. The term "set" may include sets having a single member. No language in the specification should be construed as indicating any non-claimed element as essential to the practice of the present disclosure.

While the foregoing written description will enable one of ordinary skill in the art to make and use what is currently believed to be the best mode thereof, one of ordinary skill in the art will understand and appreciate the existence of variations, combinations, and equivalents of the specific embodiments, methods, and examples herein. Therefore, the present disclosure should not be limited by the above-described embodiments, methods, and examples, but rather by all embodiments and methods within the scope and spirit of the present disclosure.

All documents referenced herein are incorporated by reference as if fully set forth herein.
Based on the above-described embodiment, for example, the following aspects can be considered.
(1)
1. A method for updating one or more properties of one or more digital twins, comprising:
receiving a request for one or more digital twins;
retrieving, from a digital twin data store, the one or more digital twins necessary to fulfill the request;
obtaining one or more dynamic models corresponding to one or more properties depicted in the one or more digital twins indicated by the request;
selecting a data source from a set of available data sources based on one or more inputs of the one or more dynamic models;
retrieving data from selected data sources;
using the acquired data as one or more inputs to the one or more dynamic models to determine one or more outputs; and
updating the one or more properties of the one or more digital twins based on the one or more outputs of the one or more dynamic models.
(2)
10. The method of claim 1, wherein the request is received from a client application corresponding to an industrial environment and/or one or more industrial entities within the industrial environment.
(3)
10. The method of claim 1, wherein the request is received from a client application supporting an industrial Internet of Things sensor system.
(4)
The method according to claim (1), characterized in that the digital twin is a digital twin of at least one of an industrial entity and an industrial environment.
(5)
10. The method of claim 1, wherein the one or more dynamic models take data selected from the set consisting of temperature, pressure, humidity, wind, rainfall, tide, storm surge, cloud cover, snowfall, visibility, radiation, audio, video, imagery, water level, quantum, flow rate, signal power, signal frequency, motion, speed, acceleration, lighting level, analyte concentration, biological compound concentration, metal concentration, and organic compound concentration data.
(6)
10. The method of claim 1, wherein the selected data sources include devices connected to the Internet of Things.
(7)
10. The method of claim 1, wherein the selected data source includes a machine vision system.
(8)
The method of claim (1), wherein obtaining the one or more dynamic models includes identifying the one or more dynamic models based on the one or more properties depicted in the digital twin indicated by the request and the respective types of the one or more digital twins.
(9)
10. The method of claim 9, wherein the one or more dynamic models are identified using a look-up table.
(10)
receiving import data from one or more data sources, the import data corresponding to an industrial environment;
generating an environment digital twin representing the industrial environment based on the imported data;
identifying one or more industrial entities within the industrial environment;
generating a set of discrete digital twins representing the one or more industrial entities within the environment;
Embedding the set of discrete digital twins within the environmental digital twin;
establishing a connection with a sensor system of said industrial environment;
receiving real-time sensor data from one or more sensors of the sensor system via the connection; and
updating at least one of the environmental digital twin and the set of discrete digital twins based on the real-time sensor data.
(11)
11. The method of claim 10, wherein the connection with the sensor system is established via one of a web hook and an application programming interface (API).
(12)
The method of claim 10, wherein the environmental digital twin and the set of discrete digital twins are visual digital twins configured to be rendered in a visual manner.
(13)
13. The method of claim 12, further comprising outputting the visual digital twin to a client application that displays the visual digital twin via a virtual reality headset.
(14)
13. The method of claim 12, further comprising outputting the visual digital twin to a client application that displays the visual digital twin via a display device of a user device.
(15)
13. The method of claim 12, further comprising outputting the visual digital twin to a client application that displays the visual digital twin via an augmented reality enabled device.
(16)
receiving user input regarding one or more steps to be performed in an industrial process associated with the industrial environment; and
The method of claim (10), further comprising generating a process digital twin that defines the steps of the industrial process with respect to one or more of the industrial environment and the set of industrial entities.
(17)
The method of claim (10), further comprising instantiating a graph database having a set of nodes connected by edges, wherein a first node of the set of nodes includes data defining the environment digital twin, and wherein one or more entity nodes each include respective data defining a respective discrete digital twin of the set of discrete digital twins.
(18)
18. The method of claim 17, wherein each of the edges represents a relationship between two respective digital twins.
(19)
The method of claim (18), wherein embedding a discrete digital twin includes connecting entity nodes corresponding to each discrete digital twin to the first node with edges representing respective relationships between each industrial entity represented by the respective discrete digital twin and the industrial environment.
(20)
The method of claim 18, wherein each of the edges represents a spatial relationship between the two respective digital twins and an operational relationship between the two respective digital twins.
(21)
19. The method of claim 18, wherein each of the edges stores metadata corresponding to the relationship between the two respective digital twins.
(22)
18. The method of claim 17, wherein each entity node of the one or more entity nodes includes one or more properties of a respective property of a respective industry entity represented by the entity node.
(23)
The method of claim 17, wherein each entity node of the one or more entity nodes includes one or more behaviors of a respective property of a respective industry entity represented by the entity node.
(24)
18. The method of claim 17, wherein the environment node includes one or more properties of the environment.
(25)
18. The method of claim 17, wherein the environment node comprises one or more behaviors of the environment.
(26)
The method of claim 10, further comprising: performing a simulation based on the environmental digital twin and the one or more discrete digital twins.
(27)
The method of claim 26, wherein the simulation simulates one of the operation of a machine that generates an output based on a set of inputs in the industrial environment and the movement of a worker in the industrial environment.
(28)
11. The method of claim 10, wherein the imported data includes a three-dimensional scan of the environment.
(29)
11. The method of claim 10, wherein the imported data includes a LIDAR scan of the industrial environment.
(30)
The method of claim 10, wherein generating the digital twin of the industrial environment includes one of generating a set of surfaces of the industrial environment and configuring a set of dimensions of the industrial environment.
(31)
The method of claim (10), wherein generating the set of discrete digital twins includes importing a predefined digital twin of an industrial entity from a manufacturer of the industrial entity, the predefined digital twin including the properties and behavior of the industrial entity.
(32)
The method of claim (10), wherein generating the set of discrete digital twins includes classifying industrial entities in the imported data of the industrial environment and generating discrete digital twins corresponding to the classified industrial entities.
(33)
1. A system for monitoring interactions in an industrial environment, comprising:
a digital twin data store containing data collected by a set of proximity sensors located within an industrial environment, the data including position data indicating the position of each of a plurality of elements within the industrial environment;
one or more processors;
the one or more processors
maintaining an industrial environment digital twin for the industrial environment via the digital twin data store;
receiving a signal from the plurality of elements indicative of activation of at least one proximity sensor in the set of proximity sensors by a real-world element;
collecting updated location data for the real-world element using the at least one proximity sensor in response to activation of the at least one proximity sensor; and
updating the industrial environment digital twin in the digital twin data store to include the updated location data.
(34)
33. The system of claim 32, wherein each of the set of proximity sensors is configured to detect a device associated with a user.
(35)
The system described in (34) above, characterized in that the device is a wearable device and an RFID device.
(36)
33. The system of claim 32, wherein each of the plurality of elements is a mobile element.
(37)
The system described in clause (33), wherein each of the plurality of elements is a respective worker.
(38)
The system described in clause (33), wherein the plurality of elements include mobile device elements and workers, and wherein mobile device location data is determined using data transmitted by each of the mobile device elements, and worker location data is determined using data acquired by the system.
(39)
38. The system of claim 38, wherein the worker location data is determined using information transmitted from a device associated with each worker.
(40)
34. The system of claim 33, wherein the activation of the at least one proximity sensor occurs in response to an interaction between a respective worker and the proximity sensor.
(41)
The system described in clause (33), wherein activation of the at least one proximity sensor occurs in response to an interaction between a worker and each of at least one proximity sensor digital twin corresponding to the at least one proximity sensor.
(42)
The system described in clause (33), wherein the one or more processors collect updated position data for the plurality of elements using the set of proximity sensors in response to activation of the at least one proximity sensor.
(43)
1. A system for modeling moving elements of an industrial digital twin, comprising:
a digital twin data store that stores industrial environment digital twins corresponding to industrial elements, the industrial environment digital twins including real-world element digital twins embedded therein, each real-world element digital twin corresponding to a respective real-world element located within the industrial environment, the real-world element digital twins including mobile element digital twins corresponding to respective mobile elements within the industrial environment;
one or more processors;
The one or more processors
For each mobile element, determining whether the mobile element is moving and obtaining route information from the mobile element;
1. The system, configured to model traffic in the industrial environment via a digital twin simulation system in response to obtaining route information for each mobile element.
(44)
The system according to clause (43), characterized in that the route information is obtained from a navigation module of the mobile element.
(45)
the one or more processors
detecting movement of the mobile element using a plurality of sensors in the industrial environment;
obtaining a destination of said mobile element;
calculating an optimized path for the mobile element using the plurality of sensors in the industrial environment; and
instructing the mobile element to follow the optimized path;
The system according to claim 43, further configured to obtain the route information by
(46)
The system described in clause (45), wherein the optimized route includes route information about other mobile elements within the real-world element, and the optimized route minimizes interactions between mobile elements and humans within the industrial environment.
(47)
45. The system of claim 45, wherein the mobile elements include autonomous and non-autonomous vehicles, and the optimized route reduces interaction between the autonomous and non-autonomous vehicles.
(48)
The system described in clause (43), characterized in that the traffic modeling includes the use of a particle traffic model, a trigger-response mobile element following traffic model, a macroscopic traffic model, a microscopic traffic model, a submicroscopic traffic model, a mesoscopic traffic model, or a combination thereof.
(49)
1. A method for updating one or more vibration fault level states of one or more digital twins, comprising:
receiving a request from a client application to update one or more vibration fault level states of one or more digital twins;
Obtaining one or more digital twins necessary to satisfy said request;
obtaining one or more dynamic models necessary to satisfy the requirements, the one or more dynamic models including a dynamic model that predicts when a vibration fault level will occur based on an input data set;
selecting a data source from a set of available data sources based on one or more inputs of the one or more dynamic models;
retrieving data from selected data sources;
using the acquired data as one or more inputs to the one or more dynamic models to determine one or more outputs; and
updating one or more vibration fault level states of the one or more digital twins based on the outputs of the one or more dynamic models.
(50)
49. The method of claim 49, wherein the request is received from a client application corresponding to an industrial environment and/or one or more industrial entities within the industrial environment.
(51)
49. The method of claim 49, wherein the request is received from a client application supporting an industrial Internet of Things sensor system.
(52)
The method according to claim (49), characterized in that the digital twin is a digital twin of at least one of an industrial entity and an industrial environment.
(53)
49. The method of claim 49, wherein the dynamic model takes data selected from the set consisting of vibration, temperature, pressure, humidity, wind, rainfall, tide, storm surge, cloud cover, snowfall, visibility, radiation, audio, video, imagery, water level, quantum, flow rate, signal power, signal frequency, motion, displacement, velocity, acceleration, light level, finance, cost, stock market, news, social media, revenue, workers, maintenance, productivity, asset performance, worker performance, worker response time, analyte concentration, biological compound concentration, metal concentration, and organic compound concentration data.
(54)
49. The method of claim 49, wherein the data source is selected from the set consisting of an Internet of Things connected device, a machine vision system, an analog vibration sensor, a digital vibration sensor, a fixed digital vibration sensor, a three-axis vibration sensor, a single-axis vibration sensor, an optical vibration sensor, and a crosspoint switch.
(55)
The method of claim (49), wherein obtaining the one or more dynamic models includes identifying the one or more dynamic models based on one or more properties indicated in the request and the respective types of the one or more digital twins.
(56)
49. The method of claim 49, wherein the one or more dynamic models are identified using a look-up table.
(57)
1. A system for monitoring navigation route data through an industrial environment having real-world elements disposed therein, comprising:
a digital twin data store including an industrial environment digital twin corresponding to the industrial environment and a worker digital twin corresponding to each worker of a set of workers within the industrial environment;
one or more processors;
the one or more processors
maintaining the industrial environment digital twin via the digital twin data store to include contemporaneous locations of the set of workers within the industrial environment;
monitoring the movement of each worker in the set of workers via a sensor array;
determining navigation path data for each worker in response to detecting movement of the each worker; and
updating the industrial environment digital twin to include an indicator of the navigational path data for the respective worker and to display movement of the worker digital twin along a path corresponding to the navigational path data.
(58)
The system described in clause (57), wherein the one or more processors are further configured to determine navigation route data for remaining workers in the set of workers in response to representing the movement of each worker.
(59)
The system according to claim (58), characterized in that the navigation route data is automatically transmitted to the system by one or more personal associated devices.
(60)
The system of claim 59, wherein the personal device is one of a mobile device with cellular data capability and a wearable device associated with the worker.
(61)
The system according to clause (57), characterized in that the navigation route data is determined via environment-related sensors.
(62)
The system described in clause (61), wherein the navigation route data is determined using historical route data stored in the digital twin data store.
(63)
The system of claim 62, wherein the historical route data is obtained from a device associated with each of the workers.
(64)
The system of claim 62, wherein the historical route data is obtained from devices associated with other workers.
(65)
The system of claim 64, wherein the historical route data is associated with the worker's current task.
(66)
The system described in clause (57), wherein the digital twin data store includes an industrial environment digital twin.
(67)
the one or more processors
determining the existence of a conflict between the navigation route data and the industrial environment digital twin;
modifying the navigation path data of the worker in response to determining accuracy of the industrial environment digital twin via the sensor array; and
The system described in clause (66) is further configured to update the industrial environment digital twin in response to determining inaccuracy of the industrial environment digital twin via the sensor array, thereby resolving the conflict.
(68)
The system described in clause (67) is characterized in that the industrial environment digital twin is updated using collected data sent from the workers.
(69)
The system of claim 68, wherein the collected data includes proximity sensor data, image data, or a combination thereof.
(70)
57. The system of claim 57, wherein the navigation path includes a path for collecting vibration measurements.

Claims (23)

1. A computer-implemented method comprising:
receiving import data from one or more data sources, wherein the import data is data collected in an industrial environment;
generating an environment digital twin representing the industrial environment based on the imported data;
identifying one or more industrial entities within said industrial environment;
obtaining data relating to the one or more industrial entities within the industrial environment;
generating a set of discrete digital twins representing the one or more industrial entities in the industrial environment based on the data related to the one or more industrial entities;
Embedding the set of discrete digital twins within the environmental digital twin;
establishing a connection with a sensor system of said industrial environment;
receiving real-time sensor data from one or more sensors of the sensor system via the connection; and
updating at least one of the environmental digital twin and the set of discrete digital twins based on the real-time sensor data. The method of claim 1, wherein the connection with the sensor system is established via one of a web hook and an application programming interface (API). The method of claim 1, wherein the environmental digital twin and the set of discrete digital twins are visual digital twins configured to be rendered in a visual manner. The method of claim 3, further comprising outputting the visual digital twin to a client application that displays the visual digital twin via a virtual reality headset. The method of claim 3, further comprising outputting the visual digital twin to a client application that displays the visual digital twin via a display device of a user device. The method of claim 3, further comprising outputting the visual digital twin to a client application that displays the visual digital twin via an augmented reality-enabled device. receiving user input regarding one or more steps to be performed in an industrial process associated with the industrial environment; and
10. The method of claim 1, further comprising generating a process digital twin that defines the steps of the industrial process with respect to one or more of the industrial environment and the set of industrial entities. The method of claim 1, further comprising instantiating a graph database having a set of nodes connected by edges, wherein a first node of the set of nodes includes data defining the environment digital twin, and wherein one or more entity nodes each include respective data defining a respective discrete digital twin of the set of discrete digital twins. The method of claim 8, wherein each of the edges represents a relationship between two respective digital twins. The method of claim 9, wherein embedding discrete digital twins includes connecting entity nodes corresponding to each discrete digital twin to the first node with edges representing respective relationships between each industrial entity represented by the respective discrete digital twin and the industrial environment. The method of claim 9, wherein each of the edges represents a spatial relationship between the two respective digital twins and an operational relationship between the two respective digital twins. The method of claim 9, wherein each of the edges stores metadata corresponding to the relationship between the two respective digital twins. The method of claim 8, wherein each entity node of the one or more entity nodes includes one or more properties of a respective industry entity represented by the entity node. The method of claim 8, wherein each entity node of the one or more entity nodes includes one or more behaviors of a respective property of a respective industry entity represented by the entity node. The method of claim 8, wherein the first node includes one or more properties of the industrial environment. The method of claim 8, wherein the first node includes one or more behaviors of the industrial environment. The method of claim 1, further comprising: performing a simulation based on the environmental digital twin and the one or more discrete digital twins. The method of claim 17, wherein the simulation simulates one of the operation of a machine in the industrial environment that generates an output based on a set of inputs, or the movement of a worker in the industrial environment. The method of claim 1, wherein the imported data includes a three-dimensional scan of the industrial environment. The method of claim 1, wherein the imported data includes a LIDAR scan of the industrial environment. The method of claim 1, wherein generating the environmental digital twin of the industrial environment includes one of generating a set of surfaces of the industrial environment and constructing a set of dimensions of the industrial environment. The method of claim 1, wherein generating the set of discrete digital twins includes importing a predefined digital twin of an industrial entity from a manufacturer of the industrial entity, the predefined digital twin including properties and behaviors of the industrial entity. 2. The method of claim 1, wherein generating the set of discrete digital twins comprises classifying industrial entities in the imported data of the industrial environment and generating discrete digital twins corresponding to the classified industrial entities.