JP7102801B2 - Control system, control device and display device - Google Patents

Description

The present disclosure relates to a control system, a control device and an information processing device for controlling a controlled object, and more particularly to a control system, a control device and a display device for collecting data related to the controlled object.

FA (Factory Automation) technology using a control device such as a PLC Programmable Logic Controller) is widely used in various production sites. With the recent development of information and communication technology (ICT), control devices in the FA field are becoming more sophisticated and highly functional.

As one of the high performance and high functionality described above, for example, a function of collecting data associated with a controlled object of a field by communication and monitoring the state of the controlled object is provided. For example, in the data monitor device disclosed in Patent Document 1, the communication control unit included in the data monitor device inputs and analyzes the equipment status signal of the automatic machine of the production equipment to detect an abnormality.

Japanese Unexamined Patent Publication No. 2003-21650

For the above abnormality detection, there is a need to accurately monitor the control target from the data associated with the control target. Since the data monitor device of Patent Document 1 monitors while inputting the equipment status signal by communication, there is a case where the equipment status signal input by the data monitor device is missing due to a delay in communication or data loss in communication. There is. When such a case occurs, the accuracy of the monitor is reduced.

One object of the present disclosure is to provide a mechanism that enables accurate monitoring of a controlled object from data associated with the controlled object in consideration of the above-mentioned needs.

The control system that controls the control target according to the example of the present disclosure includes a time-series storage means for storing data associated with the control target in a file in time series, and a file for storing time-series data from the time-series storage means. It is provided with a reading means for reading a file at a predetermined reading cycle, and a visualization means for generating display data for visualizing and displaying time-series data in a file read by the reading means.

According to the above disclosure, time-series data from the present to the past is acquired as a file for the data associated with the controlled object. As a result, data can be collected without loss of data due to communication, as compared with a method of collecting data while communicating in data units. Therefore, the display data to be visualized and displayed can accurately display the data associated with the controlled object without data loss.

In the above disclosure, the control system further comprises a periodic execution means for periodically executing the control calculation related to the control of the controlled object, and the read cycle is based on the cycle for executing the control calculation and the size of the file. ..

According to the above disclosure, the read cycle can be determined based on the cycle in which the control operation is executed and the size of the file.

In the above disclosure, the time-series storage means samples the data associated with the controlled object at different cycles according to preset information, and stores the sampled data of each cycle in a file in time series. including.

According to the above disclosure, it is possible to obtain time series data obtained by sampling the data associated with the controlled object at different cycles.

In the above disclosure, the time-series storage means samples the same type of data associated with the controlled object at different cycles according to preset information, and stores the sampled data of each cycle in a file in chronological order. Includes periodic storage means.

According to the above disclosure, it is possible to obtain time series data obtained by sampling the same type of data associated with the controlled object at different cycles.

In the above disclosure, the data associated with the controlled object includes data indicating that an event occurring in the controlled object has been detected, and the visualization means corresponds to the time when the event is detected from the time series data. A first visualization means for generating display data for extracting and visualizing partial data to be displayed is included.

According to the above disclosure, partial data corresponding to the time when the event is detected can be extracted from the time series data and displayed as a visualization.

In the above disclosure, the type of data associated with the controlled object includes the observed value of the controlled object.

According to the above disclosure, the observed value of the controlled object can be acquired as time series data.

In the above disclosure, the type of data associated with the controlled object includes features calculated from the observed values of the controlled object.

According to the above disclosure, the feature amount calculated from the observed value of the controlled object can be acquired as the time series data.

In the above disclosure, the type of data associated with the controlled object includes an evaluation value of the feature amount based on a comparison between the feature amount calculated from the observed value of the controlled object and the preset learning result.

According to the above disclosure, as time-series data, it is possible to obtain an evaluation value of the feature amount based on a comparison between the feature amount calculated from the observed value of the controlled object and the preset learning result.

In the above disclosure, when the evaluation value satisfies a predetermined abnormality detection condition, the visualization means extracts and visualizes the partial data corresponding to the time satisfying the abnormality detection condition from the time series data. A second visualization means for generating display data to be displayed is included.

According to the above disclosure, partial data corresponding to the time when the abnormality detection condition is satisfied can be extracted from the time series data and displayed as a visualization.

In the above disclosure, the operation receiving means for receiving the user's operation on the control system is further provided, and the preset information is based on the operation content received by the operation receiving means.

According to the above disclosure, preset information can be determined based on the operation content of the user.

The control device that controls the control target according to the example of the present disclosure is a time-series storage means for storing data associated with the control target in a file in time series, and a file for storing time-series data from the time-series storage means. It is provided with a reading means for reading a file at a predetermined reading cycle, and a visualization means for generating display data for visualizing and displaying time-series data in a file read by the reading means.

According to the above disclosure, time-series data from the present to the past is acquired as a file for the data associated with the controlled object. As a result, data can be collected without loss of data due to communication, as compared with a method of collecting data while communicating in data units. Therefore, the display data to be visualized and displayed can accurately display the data associated with the controlled object without data loss.

The display device according to an example of the present disclosure is a display device capable of exchanging data with a control device that controls a control target, and the control device stores data associated with the control target in a file in a time series. The display device includes a storage unit, and the display device includes a reading means for reading a file for storing time-series data from the time-series storage unit of the control device at a predetermined read cycle, and a file read by the periodic reading means. It is provided with a visualization means for generating display data for visualizing and displaying the time-series data of.

According to the above disclosure, time-series data from the present to the past is acquired as a file for the data associated with the controlled object. As a result, data can be collected without loss of data due to communication, as compared with a method of collecting data while communicating in data units. Therefore, the display data to be visualized and displayed can accurately display the data associated with the controlled object without data loss.

According to an example of the present disclosure, it is possible to realize an environment that enables the collection of data associated with the controlled object without omission.

It is a schematic diagram which shows the whole structure example of the control system 1 which concerns on this embodiment. It is a block diagram which shows the hardware configuration example of the control device 100 which constitutes the control system 1 which concerns on this embodiment. It is a block diagram which shows the hardware configuration example of the display device 200 which constitutes the control system 1 which concerns on this embodiment. It is a schematic diagram which shows an example of the application situation of the control system 1 which concerns on this embodiment. It is a schematic diagram for demonstrating the data mining process which concerns on this Embodiment and the related process. It is a figure which shows typically an example of the display screen by the setting tool which concerns on this Embodiment. It is a figure which shows typically another example of the display screen by the setting tool which concerns on this Embodiment. It is a figure which shows typically an example of the contents of the setting file 135 which concerns on this embodiment. It is a figure which shows typically an example of the CSV file 132 which concerns on this embodiment. It is a figure which shows typically an example of the display of the CSV file 132 which concerns on this embodiment. It is a figure which shows the other example of the display of the CSV file 132 which concerns on this embodiment schematically. It is a figure which shows typically an example of the data collection scenario which concerns on this Embodiment. It is a figure which shows the other example of the data collection scenario which concerns on this embodiment schematically. It is a schematic diagram which shows the modification of the control system 1 which concerns on this embodiment.

Embodiments of the present invention will be described in detail with reference to the drawings. The same or corresponding parts in the drawings are designated by the same reference numerals and the description thereof will not be repeated.

<A. Application example>
First, an example of a situation in which the present invention is applied will be described with reference to FIG. FIG. 4 is a schematic view showing an example of an application scene of the control system 1 according to the present embodiment. The control system 1 according to the present embodiment controls an arbitrary control target (for example, a manufacturing apparatus or equipment).

In FIG. 4, the control system 1 includes a control device 100 such as a PLC and a display device 200 that exchanges data with the control device 100. The display device 200 may include a portable general-purpose personal computer such as a stationary type or a tablet terminal. The display device 200 includes an input device such as a mouse and a keyboard that accepts user operations, and an output device such as a display that presents information to the user on a screen.

As shown in FIG. 4, the control system 1 defines in advance a time-series storage means for storing data associated with a controlled object in a file in time series and a file for storing time-series data from the time-series storage means. It is provided with a reading means for reading in a read reading cycle, and a visualization means for generating display data for visualizing and displaying time-series data in a file read by the reading means.

In this disclosure, the data associated with the controlled object may include data obtained by observing the behavior (motion) of the controlled object or data obtained by observing the state of the controlled object. “Observation” may include measurement by, for example, a sensor. The "time series" also includes data obtained by continuously observing changes in the behavior or state of the controlled object over time. It should be noted that the concept of continuously observing discontinuously at regular intervals may be included.

Further, in this disclosure, the "file" is, for example, CSV (comma-separated values), but the file type is not limited to CSV. Further, the "display data" includes display control data for driving a display or the like so that the time-series data in the file is displayed as a monitor screen. For example, the display data is included in the display control data for driving the display so that the time series data is displayed in a tabular format or a graph (including a trend graph). The mode of display is not limited to a table or a graph.

The time-series DB (Data Base) 131 of the control device 100 and the time-series DB program 163 that writes data to the time-series DB 131 are one implementation of the "time-series storage means". The time series DB 131 includes a storage medium such as an SD card.

Further, the data collection tool 227 of the display device 200 is an embodiment of the “reading means”. Further, the visualization tool 230 and the visualization application (abbreviation of application) 231 of the display device 200 are examples of the "visualization means". In this disclosure, a "tool" corresponds to an application. The application may include a program or a combination of programs and data that can be executed by the control device 100, the display device 200, and the like.

The control device 100 executes a user program such as the control program 160 and a system program under the OS (Operating System) 190. The system program includes a variable manager 154 that collects data observed from a field device such as a controlled object in synchronization with a control cycle, and a scheduler 152.

The scheduler 152 periodically executes a system program such as a control program and a variable manager 154 under the OS 190 based on a control cycle. The control program 160 includes a sequence / motion program 162 for control operations related to the control of the controlled object. Therefore, the scheduler 152 and the sequence / motion program 162 are an embodiment of the "periodic execution means" that periodically executes the control calculation related to the control of the controlled object.

In this way, in the control device 100, the control target is controlled according to the control calculation executed by the sequence / motion program 162 periodically based on the control cycle, and the data observed from the control result is synchronized with the control cycle. Collected by variable manager 154. The time-series DB program 163 stores the collected data in the CSV file 132 of the time-series DB 131 in time series. As a result, the control device 100 can store the current observation data to the observation data going back to the past in the CSV file 132 in the time series of the time series DB 131.

The data collection tool 227 of the display device 200 reads the CSV file 132 from the time series DB 131, and the visualization tool 230 and the visualization application 231 visualize and display the time series data in the read CSV file 132. Generate display data to be displayed on.

Therefore, the display device 200 communicates with the control device 100 by acquiring the data associated with the control target from the present to the past as a file, as compared with the method of collecting the data while communicating with the control device 100 in data units. Data can be collected without loss of data. This makes it possible to generate display data that enables accurate monitoring of the controlled object from the data associated with the controlled object.

The read cycle of the data collection tool 227 is predetermined so that one CSV file 132 can be repeatedly used in the control device 100 by, for example, a FIFO (First in, First out) and a ring buffer mechanism. That is, this read cycle is set so that the CSV file 132 (data) is read by the data collection tool 227 before the data of the CSV file 132 is overwritten. For example, when the amount of write data per control cycle is predetermined, the read cycle is predetermined based on the cycle for executing the control calculation and the size (more specifically, the capacity) of the CSV file 132. obtain.

In FIG. 4, the control system 1 includes a display device 200 separately from the control device 100, but the control device 100 may integrally include the display device 200.

Hereinafter, as a more specific application example of the present invention, a more detailed configuration and processing of the control system 1 according to the present embodiment will be described.

<B. Overall configuration example of control system>
An example of the overall configuration of the control system 1 according to the present embodiment will be described.

FIG. 1 is a schematic diagram showing an overall configuration example of the control system 1 according to the present embodiment. With reference to FIG. 1, the control system 1 according to the present embodiment includes a control device 100 that controls a controlled object and a display device 200 that can be connected to the control device 100 as main components. The display device 200 exchanges data with the control device 100 via communication or a storage medium.

The control device 100 may be embodied as a kind of computer such as a PLC (programmable controller). The control device 100 is connected to the field device group 10 via the first field network 2 and is connected to one or more devices 400 via the second field network 4. Further, the control device 100 is connected to the data logging device 600 via the local network 6. The control device 100 exchanges data with and from the connected device via each network. The data logging device 600 and the device 400 are optional configurations and are not essential configurations of the control system 1.

The control device 100 has control logic (hereinafter, also referred to as “PLC engine”) for executing various operations for controlling equipment and machines. In addition to the PLC engine, the control device 100 has a module that collects data measured by the field device group 10 and transferred to the control device 100 (hereinafter, also referred to as “input data”). Further, the control device 100 also has a module for monitoring the collected input data. By mounting these modules on the control device 100, the control device 100 can monitor the phenomenon occurring in the controlled object.

Specifically, the internal database (hereinafter, also referred to as “internal DB”) 130 mounted on the control device 100 provides the collection module, and the abnormality detection engine 140 mounted on the control device 100 provides the monitoring module. .. Details of the internal DB 130 and the abnormality detection engine 140 will be described later.

As the first field network 2 and the second field network 4, it is preferable to adopt a network that performs constant periodic communication in which the arrival time of data is guaranteed. Known networks that perform such periodic communication include EtherCAT (registered trademark), EtherNet / IP (registered trademark), DeviceNet (registered trademark), and CompoNet (registered trademark).

The field device group 10 includes a device that collects input data from a controlled object or a manufacturing device related to control, a production line, or the like (hereinafter, also collectively referred to as a “field”). As a device for collecting such input data, an input relay, various sensors, and the like are assumed. The field device group 10 further includes a device that gives some action to the field based on a command (hereinafter, also referred to as “output data”) generated by the control device 100. As a device that exerts some action on such a field, an output relay, a contactor, a servo driver and a servo motor, and any other actuator are assumed. These field device groups 10 exchange data including input data and output data with and from the control device 100 via the first field network 2.

In the configuration example shown in FIG. 1, the field device group 10 includes a remote I / O (Input / Output) device 12, a relay group 14, an image sensor 18, a camera 20, a servo driver 22, and a servo motor 24. include.

The remote I / O device 12 includes a communication unit that communicates via the first field network 2 and an input / output unit (hereinafter, also referred to as an “I / O unit”) for acquiring input data and outputting output data. .) Including. Input data and output data are exchanged between the control device 100 and the field via such an I / O unit. FIG. 1 shows an example in which digital signals are exchanged as input data and output data via the relay group 14.

The I / O unit may be directly connected to the field network. FIG. 1 shows an example in which the I / O unit 16 is directly connected to the first field network 2.

The image sensor 18 performs image measurement processing such as pattern matching on the image data captured by the camera 20, and transmits the processing result to the control device 100.

The servo driver 22 drives the servomotor 24 according to output data (for example, a position command) from the control device 100.

As described above, data is exchanged between the control device 100 and the field device group 10 via the first field network 2, and these exchanged data are on the order of several hundreds of μsec to several. It will be updated in a very short cycle of 10 msec order. The data update process of such exchanged data may be referred to as "I / O refresh process".

Further, the device 400 connected to the control device 100 via the second field network 4 receives an operation from the user, transmits a command or the like according to the user operation to the control device 100, and also sends a command or the like according to the user operation to the control device 100. Graphically display the calculation results in.

The data logging device 600 is connected to the control device 100 via the local network 6, and exchanges necessary data with and from the control device 100. The data logging device 600 has, for example, a database, and collects event logs and the like generated by the control device 100 in chronological order. A general-purpose protocol such as Ethernet (registered trademark) may be implemented in the local network 6. That is, typically, the data transmission cycle or update cycle in the local network 6 may be later than the data transmission cycle or update cycle in the field network (first field network 2 and second field network 4). However, the local network 6 may be able to transmit more data at one time as compared with the field network.

The display device 200 is a device that supports the preparation necessary for the control device 100 to control the controlled object. The display device 200 is for setting, for example, an environment for monitoring data of the control device 100 and various devices (which may include a control target) connected to the control device 100, and various parameters (configurations) including parameters related to the monitor. Provide setting environment etc.

Further, the display device 200 can also provide an environment for transmitting the generated user program to the control device 100, an environment for modifying or changing the user program executed on the control device 100 online, and the like.

Further, the display device 200 according to the present embodiment also provides an environment for determining an abnormality detection parameter 136 or the like using time-series data described later in the internal DB 130 mounted on the control device 100.

<B-1. Hardware configuration example of each device>
Next, a hardware configuration example of the main devices constituting the control system 1 according to the present embodiment will be described.

(B1: Hardware configuration example of control device 100)
FIG. 2 is a block diagram showing a hardware configuration example of the control device 100 constituting the control system 1 according to the present embodiment. With reference to FIG. 2, the control device 100 includes a processor 102 such as a CPU (Central Processing Unit) and an MPU (Micro-Processing Unit), a chip set 104, a main storage device 106, a secondary storage device 108, and the like. Local network controller 110, USB (Universal Serial Bus) controller 112, memory card interface 114, internal bus controller 122, field bus controllers 118, 120, I / O units 124-1, 124-2, ... including.

The processor 102 reads various programs stored in the secondary storage device 108, expands them in the main storage device 106, and executes them to realize control according to the control target and various processes as described later. .. By controlling the processor 102 and each component, the chipset 104 realizes the processing of the control device 100 as a whole.

In the secondary storage device 108, in addition to the system program for realizing the PLC engine, a user program executed by using the PLC engine is stored. Further, the secondary storage device 108 also stores a program for realizing the internal DB 130 and the abnormality detection engine 140.

The local network controller 110 controls the exchange of data with other devices via the local network 6. The USB controller 112 controls the exchange of data with the display device 200 via the USB connection.

The memory card interface 114 is configured so that the memory card 116 can be attached and detached, data can be written to the memory card 116, and various data (user programs, trace data, etc.) can be read from the memory card 116. ing.

The internal bus controller 122 is an interface for exchanging data with the I / O units 124-1, 124-2, ... Mounted on the control device 100.

The fieldbus controller 118 controls the exchange of data with other devices via the first field network 2. Similarly, the fieldbus controller 120 controls the exchange of data with other devices via the second field network 4.

FIG. 2 shows a configuration example in which the necessary functions are provided by the processor 102 executing the program, and some or all of these provided functions are provided by a dedicated hardware circuit (for example, ASIC). (Application Specific Integrated Circuit) or FPGA (Field-Programmable Gate Array), etc.) may be used for implementation. Alternatively, the main part of the control device 100 may be realized by using hardware that follows a general-purpose architecture (for example, an industrial personal computer based on a general-purpose personal computer). In this case, a virtualization technique may be used to execute a plurality of OSs (Operating Systems) having different uses in parallel, and to execute necessary applications on each OS.

(B2: Hardware configuration example of display device 200)
Next, the display device 200 according to the present embodiment is realized, for example, by executing a program using hardware (for example, a general-purpose personal computer) that follows a general-purpose architecture.

FIG. 3 is a block diagram showing a hardware configuration example of the display device 200 constituting the control system 1 according to the present embodiment. With reference to FIG. 3, the display device 200 inputs a processor 202 such as a CPU or MPU, a drive 204, a main storage device 206, a secondary storage device 208, a USB controller 212, and a local network controller 214. A unit 216 and a display unit 218 are included. These components are connected via bus 220.

The processor 202 realizes various processes as described later by reading various programs stored in the secondary storage device 208, expanding them in the main storage device 206, and executing the programs.

The secondary storage device 208 has a relatively large storage capacity. The secondary storage device 208 includes, for example, an HDD (Hard Disk Drive) or an SSD (Flash Solid State Drive). The secondary storage device 208 typically stores various programs and data, including a user program executed by the display device 200. Specifically, the secondary storage device 208 stores a data collection tool 227, a visualization tool 230, a setting tool 228 including a data mining tool 226 described later, and a screen creation tool 229 described later, and related data. To. The relevant data includes the variable table 2281, which will be described later. The secondary storage device 208 may store the OS and other necessary programs.

The drive 204 is configured so that the memory card 116 or the storage medium 205 can be attached and detached. The drive 204 can write data to the memory card 116 or the storage medium 205 and read various data (user program, trace data, time series data, etc.) from the memory card 116 or the storage medium 205. .. The storage medium 205 includes, for example, a storage medium 205 (for example, an optical storage medium such as a DVD (Digital Versatile Disc)) that non-transiently stores a computer-readable program. From the memory card 116 or the storage medium 205, the program or data stored therein is read and installed in an internal storage area such as the secondary storage device 208.

The various programs executed by the display device 200 may be installed via a computer-readable memory card 116 or a storage medium 205, or may be installed by downloading from a server device or the like on the network. .. Further, the function provided by the display device 200 according to the present embodiment may be realized by using a part of the module provided by the OS.

The USB controller 212 controls the exchange of data with the control device 100 via the USB connection. The local network controller 214 controls the exchange of data with other devices via an arbitrary network. The data exchanged with the control device 100 by the USB controller 212 includes, for example, the CSV file 132 of the time series DB 131, the abnormality detection parameter 136 described later, and the learning data 134. The tool for the display device 200 to exchange data with the control device 100 is not limited to the USB controller 212, and may be Ethernet (registered trademark).

The input unit 216 is composed of a keyboard, a mouse, and the like, and receives user operations. The display unit 218 is composed of a display, various indicators, and the like, and outputs information such as a processing result from the processor 202. A printer may be connected to the display device 200. The display device 200 may include a touch pad 217 integrally including an input unit 216 and a display unit 218.

FIG. 3 shows a configuration example in which the necessary functions are provided by the processor 202 executing the program, and some or all of these provided functions are provided by a dedicated hardware circuit (for example, ASIC). Alternatively, it may be implemented using an FPGA or the like).

(B3: Hardware configuration example of data logging device 600)
Next, the data logging device 600 constituting the control system 1 according to the present embodiment can be realized by using a general-purpose file server or a database server as an example. Since the hardware configuration of such an apparatus is known, a detailed description thereof will not be given here.

(B4: Hardware configuration example of device 400)
Next, the device 400 constituting the control system 1 according to the present embodiment is called an HMI (Human Machine Interface) device, and a configuration implemented as a dedicated machine may be adopted or is used for general purposes. It may be realized by using hardware that follows a typical architecture (for example, an industrial personal computer based on a general-purpose personal computer).

<C. Environment provided by control system 1>
The environment provided by each device of the control system 1 according to the present embodiment will be described with reference to FIG. 4 again. In this embodiment, the display device 200 executes each program under, for example, a general-purpose OS (for example, Windows (registered trademark)).

<C-1. Environment provided by the display device 200>
With reference to FIG. 4, the display device 200 includes a communication middleware 238 for communicating with the control device 100, a data collection tool 227, a large-capacity memory 107, a visualization application 231 including an AI (Artificial Intelligence) application 232, and data. It includes a mining tool 226, a visualization tool 230, and a setting tool 228 for setting information of the control device 100.

The memory 107 corresponds to a part of the area of the secondary storage device 208 such as an HDD. The data collection tool 227 outputs the request command of the CSV file 132 according to the above read cycle. When the internal DB access program 164 of the control device 100 receives the request command from the data collection tool 227, the internal DB access program 164 reads the CSV file 132 from the time series DB 131 and transmits it on the display device 200. As a result, the data acquisition tool 227 can read the CSV file 132 from the time series DB 131 of the control device 100.

Further, the data collection tool 227 stores the CSV file 132 received from the control device 100 in the memory 107. The data collection tool 227 manages the CSV file 132 in the memory 107 on a folder-by-folder basis. In management, the data collection tool 227 assigns each folder a name (identifier) according to the order in which the folder is received from the control device 100 and manages the folder. As a result, in the memory 177, the data associated with the controlled object of the control device 100 is managed in a time series according to the order of observation.

The data mining tool 226 generates, for example, anomaly detection parameters 136 and learning data 134 suitable for detecting an abnormality occurring in a controlled object based on the execution result by executing machine learning from the contents of the CSV file 132. do. The generation of the anomaly detection parameter 136 and the training data 134 by the data mining tool 226 may include the concept of determination and adjustment (modification) of the anomaly detection parameter 136 and the training data 134.

The setting tool 228 includes a screen creation tool 229 and an operation reception tool 234. The operation reception tool 234 is an embodiment of an "operation reception means" that receives a user's operation on the control system 1. The operation reception tool 234 converts, for example, the operation contents (keyboard operation, mouse operation, etc.) of the input unit 216 into commands. The screen creation tool 229 creates, for example, screen data displayed on the display unit 218.

The setting tool 228 transfers the information to be set in the control device 100 via the communication middleware 238. Such information is set (stored) in the setting file 135 of the control device 100. The content of the setting file 135 set by the setting tool 228 includes the type of data to be sampled (collected) based on the user operation. Further, the setting file 135 may include a collection cycle for the type of data to be sampled. In addition, the configuration file 135 may include information indicating the type of event to be monitored. Further, the setting file 135 may include learning data 134 as a result of machine learning, abnormality detection parameter 136, and the like.

Further, in the present embodiment, the setting file 135 includes information for designating data to be monitored. The data to be monitored may include data representing the operating state of the control device 100 (system variable 1542 described later).

The visualization tool 230 generates information (for example, an image) that can visualize the contents based on the contents of the CSV file 132. The visualization tool 230 includes a first visualization tool 2301 and a second visualization tool 2302. The first visualization tool 2301 generates display data that visualizes and displays information related to an event that occurs in the controlled object. The second visualization tool 2302 is a time series of the CSV file 132 when the control device 100 determines that the data associated with the control target satisfies the abnormality detection condition based on the learning data 134 and the abnormality detection parameter 136. Partial data corresponding to the time satisfying the abnormality detection condition is extracted from the data of the above, and visualized and displayed.

The visualization tool 230 activates the visualization application 231 including the AI application 232 when creating display data. When the visualization application 231 is started, it creates display data from the contents of the CSV file 132. At this time, the visualization application 231 creates display data from the contents of the CSV file 132 while following the settings of the visualization tool 230 and referring to the library of the screen creation tool 229. The display data generated by the visualization tool 230 and the visualization application 231 is output to the display unit 218 via the setting tool 228.

Each of the above-mentioned parts of the display device 200 may be provided including a program or circuit (ASIC, FPGA, etc.).

<C-2. Environment provided by control device 100>
The control device 100 includes an internal DB 130, an abnormality detection engine 140, and a PLC engine 150. These are basically realized by the processor 102 (FIG. 2) of the control device 100 executing the program under the control of the OS 190.

The information stored in the internal DB 130 includes a time-series DB 131 for storing the CSV file 132, learning data 134, and a setting file 135. The details of the contents of the setting file 135 will be described later, but the learning data 134 may be included in the setting file 135.

The PLC engine 150 is typically provided by executing a user program such as a system program and a control program 160 on the OS 190. More specifically, the PLC engine 150 includes a counter 153, a scheduler 152, a variable manager 154 and a control program 160.

The scheduler 152 controls the execution timing and execution order of each program (or a task corresponding thereto) constituting the PLC engine 150. The counter 153 counts the value in synchronization with the output of a timer (not shown) of the display device 200. Since the timer of the display device 200 sets the time with a timer (not shown) of the control device 100, the counter 153 can output a count value synchronized with the timer of the control device 100.

The variable manager 154 manages the values available in the PLC engine 150 in the form of variables. More specifically, the data updated by the I / O refresh process periodically executed in the PLC engine 150 is managed as a variable. The variables managed by the variable manager 154 include a system variable 1542 indicating the state of the control device 100 and the like, and a user variable / device variable 1544. The user variable / device variable 1544 is a device variable indicating a value held by various devices connected to the control device 100 via a local bus or a field bus, and a control program (user program) 160 executed by the control device 100. Contains both user variables that indicate the values to keep.

In the present embodiment, the data associated with the controlled object can be collected mainly as a user variable / device variable 1544. Also, the event data to be monitored described above can be collected as system variable 1542.

The control program 160 corresponds to a user program that can be arbitrarily created by the user, and typically includes a sequence / motion program 162, an internal DB access program 164, a time series DB program 163, an abnormality detection engine interface 166, and a feature amount. Includes generation program 174. The instructions of the programs constituting the control program 160 may be described as an integrated program, or may be described separately in a plurality of programs.

The sequence / motion program 162 includes instructions for performing logical operations and / or numerical operations for controlling a controlled object. The internal DB access program 164 sets (stores) the setting received from the display device 200 in 135 in the setting file of the internal DB 130. Further, the internal DB access program 164 reads the CSV file 132 and transfers it to the display device 200 in response to the read request from the display device 200.

The time-series DB program 163 selects the data of the variable specified in advance (that is, the I / O data set in the setting file 135) from the variables included in the user variable / device variable 1544, and selects the data of the time-series DB 131. Write to CSV file 132. Further, the time-series DB program 163 selects the data of the variable specified in advance (that is, the data of the event set in the setting file 135) from the variables included in the system variable 1542, and the CSV file of the time-series DB 131. It may be written in 132. Further, the time-series DB program 163 may write the feature amount 148 and the score value 147 output from the abnormality detection engine 140 into the CSV file 132 of the time-series DB 131 according to the contents of the setting file 135.

The time-series DB 131 writes the data to be written in the CSV file 132 to the time-series DB 131 with a time stamp. The value of this time stamp is typically a counter value output from the counter 153.

Further, the time-series DB program 163 may include, for example, a periodic storage program 1631. The cycle storage program 1631 uses the data of the variable specified in advance (I / O data set in the setting file 135) among the variables included in the user variable / device variable 1544 in a different cycle specified in the setting file 135. The data of each cycle sampled by the above may be stored in the CSV file 132 with a time stamp.

The anomaly detection engine interface 166 includes instructions for operating the anomaly detection engine 140. Specifically, the abnormality detection engine interface 166 monitors the abnormality detection engine 140 by instructing the abnormality detection engine 140 to extract the feature amount using the abnormality detection parameter 136 and monitoring the feature amount using the abnormality detection parameter 136. Includes commands to instruct anomaly detection.

The feature amount generation program 174 includes an instruction to generate a feature amount using the specified variable of the user variable / device variable 1544 according to the feature amount generation method specified in advance. The display device 200 determines an appropriate feature amount generation method according to the control target. That is, the feature amount generation program 174 generates a feature amount suitable for detecting an abnormality occurring in the control target from the data related to the control target.

In the abnormality detection engine 140, the feature amount extraction unit 142 uses the feature amount generated by the execution of the feature amount generation program 174 to be of the type indicated by the designated feature amount 1362 in the frame indicated by the frame parameter 1363 of the abnormality detection parameter 136. Extract features. In the present embodiment, the frame is a time (period) for performing abnormality detection by the abnormality detection engine 140. Specifically, the anomaly detection engine interface 166 outputs the above command for operating the anomaly detection engine 140 during this frame time. As a result, abnormality detection by the abnormality detection engine 140 can be performed on the frame.

The abnormality detection unit 144 compares the feature amount extracted by the feature amount extraction unit 142 with the learning data 134, and outputs a score value 147 which is an evaluation value of the degree of deviation from the learning data 134 from the comparison result. Further, the abnormality detection unit 144 detects the presence or absence of an abnormality based on whether or not the score value 147 exceeds the threshold value 1361 of the abnormality detection parameter 136. Further, the abnormality detection unit 144 outputs the feature amount 148 and the score value 147 used for detecting the abnormality, and when detecting any abnormality, outputs the event log 146 indicating the detected content. The time-series DB program 163 may store the event log 146 in the CSV file 132.

<D. Data mining tool ＞
Next, the data mining tool provided by the control system 1 according to the present embodiment will be described. In the present embodiment, the data mining tool 226 included in the display device 200 is used to perform monitoring processing including abnormality detection based on the CSV file 132 that stores the data associated with the control target collected by the control device 100. Necessary settings such as abnormality detection parameter 136 and training data 134 are set.

FIG. 5 is a schematic diagram for explaining a data mining process and related processes according to the present embodiment. FIG. 5 shows a monitoring process step (5) performed by the abnormality detection engine 140 of the control device 100 in association with the steps (1) to (4) of the data mining tool 226.

In FIG. 5, for example, data mining is performed on the time-series data associated with the control target of the CSV file 132 from the control device 100, that is, the time-series data of the user variable / device variable 1544 specified in advance by the setting file 135. However, the data mining target is not limited to the data of the CSV file 132. For example, data specified by a user operation from the input unit 216 may be added to the data mining target.

First, (1) a data collection process is carried out. (1) In the data collection step, the display device 200 receives the CSV file 132 from the control device 100 and stores it in, for example, the secondary storage device 208.

Next, (2) a data mining step is carried out. (2) In the data mining step, the display device 200 reads the time-series data written in the secondary storage device 208 and determines the abnormality detection method. Specifically, the user operates the input unit 216 of the display device 200 using the data mining tool 226 to read the data from the CSV file 132 and analyze it to determine the feature amount generation method and the abnormality detection method. ..

Next, (3) a feature amount generation step is carried out. In the (3) feature amount generation step, the feature amount is generated from the data in the CSV file 132 by applying the feature amount generation method determined in (2) the data mining step.

(3) In the feature amount generation step, the display device 200 generates a feature amount from the data of the CSV file 132 by using, for example, a feature amount generation program similar to the feature amount generation program 174 of the control device 100.

Next, (4) feature amount learning step is carried out. (4) In the feature amount learning process, the data mining tool 226 executes machine learning on the feature amount generated in the (3) feature amount generation step, and from the result of this machine learning, the input unit 216 is used. Based on the user operation, the abnormality detection parameter 136 (threshold value 1361, designated feature amount 1362, frame parameter 1363) and learning data 134 are determined.

By the steps (1) to (4) described above, the display device 200 determines the definition of the feature amount used for abnormality detection, the abnormality detection parameter 136 for determining the abnormality, the learning data 134, and the like. can do. The learning data 134 and the abnormality detection parameter 136 determined by the data mining tool 226 are transferred to the control device 100 and set (stored) in the setting file 135.

In the control device 100, (5) the feature quantity monitoring step is carried out using the learning data 134 and the abnormality detection parameter 136 determined by the data mining tool 226 of the display device 200. (5) In the feature amount monitoring step, the feature amount is generated by the feature amount generation program 174 described above, the score value 147 is output by the abnormality detection engine 140, and the feature amount 148 used for the determination is output. In addition, an event log 146 indicating the content of abnormality detection is output.

<E. Setting tool>
The setting tool 228 of the display device 200 will be described. FIG. 6 is a diagram schematically showing an example of a display screen by the setting tool according to the present embodiment. FIG. 7 is a diagram schematically showing another example of the display screen by the setting tool according to the present embodiment. In the present embodiment, the setting tool 228 provides a UI (User Interface) for the user to select data to be collected using the CSV file 132 from the variable table 2281 of the secondary storage device 208. The UI is a screen displayed on the display unit 218, and includes a screen created by the screen creation tool 229.

The variable table 2281 contains a list of data indicated by the user and device variables 1544 and the system variable 1542. When the setting tool 228 is started, it reads the contents of the variable table 2281. The screen creation tool 229 creates screen display data representing a list of read contents. The setting tool 228 outputs the created display data to the display unit 218.

As a UI for the user variable / device variable 1544, for example, the screen of FIG. 6 is displayed on the display unit 218. With reference to the screen of FIG. 6, the screen includes tab 1281, tab 1282, icon 1284, tab 1290, tab 1291 and tab 1292, list 1283 and window 1289. Tab 1281 and tab 1282 provide the user with a notification that the screen is a screen for registering a variable of data to be collected from the user variable / device variable 1544. In addition, list 1283 shows a list of data (variable name, data type, collection cycle) indicated by user variable / device variable 1544 and system variable 1542. The user specifies the variable to be registered as the collection target from the list 1283 by, for example, operating the input unit 216. The user also sets the collection cycle for each variable.

The collection cycle can be set based on, for example, the control cycle (T) of the control device 100. Therefore, the user can set a cycle (2T, 3T, etc.) longer than the control cycle for the variables that do not need to be collected frequently.

The basic cycle is not limited to the control cycle, and may be, for example, a cycle based on a frame longer than the control cycle (T) or a cycle based on the takt time. In the present embodiment, the frame time interval corresponds to, for example, a time width depending on the takt time. For example, when the device to be controlled is a packaging device, the frame corresponds to a time width depending on the tact time such as the operation cycle of the cutter arm that cuts the packaging material.

The icon 1284 is operated when the CSV file 132 is transferred (imported) from the control device 100 to the display device 200. When the icon 1284 is operated, the data acquisition tool 227 transmits the read request to the control device 100.

Window 1289 shows the start and end times of data collection using the CSV file 132. This time corresponds to the read cycle as described above. The read cycle is based on the cycle in which the scheduler 152 executes the control calculation by the sequence / motion program 162 of the control program 160 and the size of the CSV file 132.

Tab 1292 is operated to command the controller 100 to start or end the collection of data for the variables specified in Listing 1283. Therefore, by operating the tab 1292, it is possible to instruct the control device 100 to start and end the collection of the data of the variables specified in the list 1283 at the time based on the window 1289.

Further, as a UI for the system variable 1542, for example, the screen of FIG. 7 is displayed on the display unit 218. With reference to the screen of FIG. 7, tabs 1281, list 1293, list 1294, window 1295, window 1289, tab 1290, tab 1291 and tab 1292 and are included. Tab 1281 presents the user with a notification that the screen is a screen for registering the event variables to be collected among the system variables 1542. In addition, list 1293 shows a list of event types (event names, IDs) operated and selected by the user.

On the screen of FIG. 7, when the setting tool 228 accepts the event registration operation in Listing 1293, it searches the variable table 2281 for the system variable 1542 and the user variable / device variable 1544 related to the type of the operated event. Shown in Listing 1294. In addition, the user can set the period for collecting the data of the user variable / device variable 1544 related to the type of the event in the window 1295 as a frame variable.

The setting tool 228 sets the contents set by the user operation in the UI of FIG. 6 or 7 in the setting file 135 of the control device 100. The control device 100 uses the setting file 135 set in the UI of FIG. 6 or 7 to sample the data associated with the control target in the time-series DB program 163 (or the cycle storage program 1631) at different cycles. Then, the sampled data of each cycle can be stored in the CSV file 132 in chronological order. This different period may include, for example, a frame period, a control period shorter than the frame, a control period, a period longer than the control period, and the like.

Further, by using the setting file 135 set by the UI of FIG. 6 or 7, the same type of data associated with the control target is transmitted to the time series DB program 163 (or the periodic storage program 1631), which is different from the above. It is also possible to sample in cycles and store the sampled data of each cycle in the CSV file 132 in chronological order.

<F. Configuration file>
FIG. 8 is a diagram schematically showing an example of the contents of the setting file 135 according to the present embodiment. With reference to FIG. 8, the configuration file 135 includes a plurality of variable names 1441 of the user variable / device variable 1544 and the system variable 1542 set by the UI of FIG. 6 or FIG. The configuration file 135 further includes, in association with each variable name 1461, a data collection cycle 1462, an event variable 1466 corresponding to the event type, anomaly detection parameters 136, training data 134, and a frame setting 1465 indicating the frame cycle. ..

Note that in FIG. 8, the frame setting 1465 may include a subframe setting. Further, when the learning data 134 is relatively large data, the setting file 135 may include a pointer to the learning data 134 stored in advance in the secondary storage device 108 instead of the learning data 134.

<G. CSV file>
FIG. 9 is a diagram schematically showing an example of the CSV file 132 according to the present embodiment. With reference to FIG. 9, the CSV file 132 contains a plurality of records 1324. The record 1324 has a counter value 1321 output by the counter 153 as a time stamp. Further, record 1324 includes data 1322 and data 1323 collected at the time of counter value 1321. The data 1322 includes the data of the user variable / device variable 1544 or the system variable 1542 specified by the variable name 1461 of the setting file 135. The data 1323 includes the data of the system variable 1542 specified by the event variable 1463 of the configuration file 135.

In the present embodiment, the value of the event variable includes "1" indicating that the event has occurred or "0" indicating that the event has not occurred. Data 1322 in FIG. 9 indicates that the data for each variable is collected in the corresponding period 1462 of configuration file 135.

Further, the data of the abnormality detection result by the abnormality detection engine 140 is linked to the record 1324 of the CSV file 132 of FIG. This link associates the result of anomaly detection with the same counter value 1321 (ie, made at the same time) with record 1324 of the collected data. The result of the abnormality detection includes the counter value 1321, the feature amount 148 used for the determination, the score value 147, and the event log 146.

According to the structure of the CSV file 132 of FIG. 9, when the event log 146 indicates "abnormality" by making the above link, the feature amount 148 and the score value 147 used for determining the abnormality detection are made. And the data 1322 and 1323 collected at the time of the abnormality detection can be associated and collected.

<H. CSV file display example>
FIG. 10 is a diagram schematically showing an example of display of the CSV file 132 according to the present embodiment. The visualization tool 230 uses the visualization application 231 to generate an image for visualizing the CSV file 132, and outputs the display data of the generated image to the display unit 218. For example, on the visualization screen, as shown in FIG. 10, the collected data is displayed in a tabular format in association with a counter value 1321 indicating the collection time. The icon 2810 also displays the period during which the data was collected. The display of the CSV file 132 is not limited to the tabular format, and may be a trend graph.

FIG. 11 is a diagram schematically showing another example of displaying the CSV file 132 according to the present embodiment. The first visualization tool 2301 searches the time-series data of the CSV file 132, extracts the partial data corresponding to the time when the event is detected from the time-series data, and visualizes and displays the display data. Generate. With this display data, for example, the screen of FIG. 11 can be displayed on the display unit 218.

The screen of FIG. 11 may also provide information for analysis when an event occurs. Specifically, on the screen of FIG. 11, a trend graph showing a change in the value of the event data 1323 and a change in the variable data 1322 related to the event data is displayed on the same time axis. Data 1322 of FIG. 11 includes data collected during changes in the values of event data 1312.

The user operates the icon 126 to analyze the event on the screen of FIG. The setting tool 228 specifies a part T2 of the trend graph showing the change of the data 1322 from the operation contents of the user using the icon 126. The setting tool 228 sets the time of the designated portion T2 of the trend graph as the time for generating the feature amount, that is, the frame parameter 1363 according to the operation content.

In this way, the user can obtain support information for analyzing the cause of the event occurrence from the trend graph showing the time-series change of the data 1322 provided to the user when the event occurs. Here, the support information is information that supports the setting of the frame parameter 1363, but the support information is not limited to the information that supports the setting of the frame parameter 1363.

Further, as another setting method of the frame parameter 1363, the user may set using the elapsed time T1 from the occurrence of the event. As a result, it is possible to set the frame parameter 1363 instructing that the abnormality detection engine 140 starts the abnormality detection when the elapsed time T1 from the event occurrence elapses. In this case, the setting tool 228 transfers the frame parameter 1363 indicating the changed period (part T2) on the screen of FIG. 11 to the control device 100 so as to be set in the setting file 135.

Further, when the user operates the icon 126 to specify a part of the trend graph showing the change of the data 1322 in the time series, the visualization tool 230 CSVs only the data 133 corresponding to the time of the specified part. You may search from the file 132 and have the display unit 218 display, for example, an enlarged display.

Further, the second visualization tool 2302 of the visualization tool 230 indicates that the event log 146 of the CSV file 132 indicates "abnormality", that is, the score value 147 is a predetermined abnormality detection condition (for example, score value 147>. When the threshold value 1361) is satisfied, the CSV file 132 is searched and partial data corresponding to the time satisfying the abnormality detection condition is extracted from the time series data of the data 1322. Then, the second visualization tool 2302 generates display data for visualizing and displaying the extracted partial data, and outputs the display data to the display unit 218. For example, this display data may be displayed as a time-series trend graph.

As a result, it is possible to present to the user the time-series change of the variable data 1322 collected when it is determined that there is an abnormality.

Further, the data extracted by the first visualization tool 2301 or the second visualization tool 2302 may be the feature amount 148 used for the determination. In this case, when an event occurs or an abnormality is detected, the time-series change of the feature amount 148 used by the abnormality detection engine 140 for determining the abnormality detection can be presented.

<I. Data collection scenario>
The data collected by using the CSV file 132 by the time-series DB program 163 in the present embodiment is used for machine learning (acquisition of learning data 134 and abnormality detection parameter 136) for the abnormality detection engine 140 of the control device 100. Can be used.

Such data collection includes data collection when the user is aware of an event (an event occurring in the control device 100) and data collection "for the time being" without grasping the event. Can include. These two data acquisition scenarios will be described.

FIG. 12 is a diagram schematically showing an example of a data collection scenario according to the present embodiment. FIG. 12 is an example of the above-mentioned “temporary” data collection. Steps S2 and S3 of FIG. 12 show processing by user operation.

With reference to FIG. 12, the setting tool 228 accepts the variables to be collected or the collection cycle based on the operation contents of the user (step S1). The user operates the input unit 216 to input the designated feature amount 1362 and the frame parameter 1363 (step S2 and step S3). Further, the setting tool 228 registers the collection time (collection start time and end time) (step S4). The setting tool 228 transmits the contents received in steps S1 to S3 to the control device 100 (step S5). As a result, the contents set in steps S1 to S3 are set in the setting file 135 of the control device 100.

The data collection tool 227 sets the data collection time registered in step S4 (step S10). Further, the time-series DB program 163 sets parameters such as variables and cycles to be collected in the internal DB 130 based on the contents in the setting file 135 (step S15). Further, the control device 100 sets parameters such as the abnormality detection parameter 136 and the learning data 134 in the internal DB 130 based on the content of the user operation (step S18).

The data collection tool 227 outputs a data collection start / end command to the control device 100 based on the data collection time set in step S10 (step S11). In the operating control device 100, the time-series DB program 163 collects data at a set cycle for the variables set in the setting file 135 from the commanded data collection start time to the end time (step S16). , The score value 147 output by the abnormality detection engine 140 and the feature amount 148 used for the determination are collected (step S19). The time-series DB program 163 stores the collected data in the CSV file 132 in a time-series manner.

When the control device 100 receives the read request from the data collection tool 227 of the display device 200, the control device 100 exports the CSV file 132 (transmits it to the control device 100) (step S17). Further, the data collection tool 227 receives the CSV file 132 from the control device 100 and stores it in the memory 107 (step S12). After that, the visualization tool 230 performs a visualization process for generating display data for visualizing and displaying the time-series data in the CSV file 132 received from the control device 100 (step S41).

FIG. 13 is a diagram schematically showing another example of the data acquisition scenario according to the present embodiment. FIG. 13 shows a data collection scenario when the user is aware of an event (an event occurring in the control device 100). In addition, the scenario of FIG. 13 may show a case after the data collection of "for the time being" is carried out.

In FIG. 13, the processes of steps S21 to S24 are performed based on the operation contents of the user. Specifically, as described above, the setting tool 228 receives the user operation via the UI screen of FIG. 6 or 7, and sets the setting based on the received operation content in the setting file 135 of the control device 100. Set to. As a result, the variables to be collected, the collection cycle, the abnormality detection parameter 136, the learning data 134, and the like are set in the setting file 135 as shown in FIG. 8 (step S35).

Further, the data collection tool 227 outputs a command at the collection start time and the collection end time (step S30, step S31). The time-series DB program 163 collects data according to the setting contents of the setting file 135 according to a command at the start and end of data collection, and stores the data in the CSV file 132 in time series (step S36).

At the end of data collection, the data collection tool 227 sends a read request to the control device 100. The time-series DB program 163 exports (transmits) the CSV file 132 to the display device 200 in response to the read request (step S37). The data collection tool 227 receives the CSV file 132 from the control device 100 and stores it in the memory 107 (step S32). After that, the visualization tool 230 visualizes and displays the time-series data in the CSV file 132 received from the control device 100, and performs a visualization process to generate display data (step S41).

<J. Modification example>
FIG. 14 is a schematic view showing a modified example of the control system 1 according to the present embodiment. In the above embodiment, the control system 1 includes the control device 100 and the display device 200 independent of the control device 100, but the control device 100 may integrally include the display device 200. A control device 105 having this integrated configuration will be described with reference to FIG.

A software configuration for realizing the environment provided by the control device 105 will be described with reference to FIG. The instruction code included in these software is read out at an appropriate timing and executed by the processor 102.

The control device 105 includes a PLC engine 1043 that runs under a real-time OS 1045 (e.g., equivalent to OS 190) with a scheduler and a monitor engine 1044 that runs under OS 1046. The environment for executing the monitor engine 1044 under the OS 1046 is provided as a virtual computer included in the control device 105.

The PLC engine 1043 includes a system program 1049 with a variable manager 154 and a user program 1050. The user program 1050 includes a control program 160 and an anomaly detection engine 140. Each program (or task) of the PLC engine 1043 is executed by the scheduler of the real-time OS 1045 while being scheduled according to a predetermined priority based on the control cycle.

Further, the monitor engine 1044 in the virtual computer includes a data acquisition tool 227, a visualization tool 230, a data mining tool 226, and a setting tool 228 of the display device 200 shown in FIG. Each tool of the monitor engine 1044 runs under OS 1046. An OS such as Windows (registered trademark) can be applied to the OS 1046, but the type of the OS 1046 for a virtual computer is not limited to Windows.

In the control device 105 of FIG. 14, the PLC engine 1043 and the monitor engine 1044 are executed under the corresponding OS to provide an environment similar to that of the control system 1 of FIG. The PLC engine 1043 and the monitor engine 1044 running in the virtual machine share the hardware resource 1042 via the corresponding OS. In order to share the hardware resource 1042 in this way, the hypervisor 1047 is installed in the control device 105. Each OS of the PLC engine 1043 and the monitor engine 1044 executed in the virtual computer accesses the CSV file 132 stored in the hardware resource 1042 and the setting file 135 via the hypervisor 1047. The collection start command, the collection end command, and the read request are also exchanged between the PLC engine 1043 and the monitor engine 1044 via the hypervisor 1047. Further, the hypervisor 1047 receives a user operation on the control device 105 from the external input unit 216 by using the communication I / F (Interface) 1048 of the hardware resource 1042, and receives the display data from the monitor engine 1044 externally. Output to the display unit 218.

In this way, by providing the control device 105 with a virtual computer that executes each tool of the display device 200, it is possible to realize a configuration in which the control device 100 integrally includes the display device 200.

<K. Addendum>
The present embodiment as described above includes the following technical ideas.
[Structure 1]
A control system (1) that controls a controlled object.
A time-series storage means (163) that stores data associated with a controlled object in a file (132) in chronological order, and
A reading means (227) for reading the file for storing the time-series data from the time-series storage means at a predetermined read cycle, and
A control system comprising a visualization means (230) for generating display data for visualizing and displaying the time-series data in the file read by the reading means.
[Structure 2]
The control system
A periodic execution means (152) for periodically executing a control operation related to the control of the controlled object is further provided.
The control system according to configuration 1, wherein the read cycle is based on a cycle for executing the control operation and the size of the file.
[Structure 3]
The time series storage means
A cycle storage means (1631) is included in which data associated with the control target is sampled at different cycles according to preset information (135) and the sampled data of each cycle is stored in a file in the time series. The control system according to configuration 1 or 2.
[Structure 4]
The time series storage means
A cycle storage means (1631) is included, which samples the same type of data associated with the control target at different cycles according to preset information, and stores the sampled data of each cycle in a file in the time series. The control system according to configuration 1 or 2.
[Structure 5]
The data associated with the controlled object includes data indicating that an event occurring in the controlled object has been detected.
The visualization means includes a first visualization means (2301) that extracts partial data corresponding to the time when the event is detected from the time-series data and generates display data to be visualized and displayed. The control system according to any one of configurations 1 to 4.
[Structure 6]
The control system according to any one of configurations 1 to 5, wherein the type of data associated with the controlled object includes an observed value (1322) of the controlled object.
[Structure 7]
The control system according to configuration 6, wherein the type of data associated with the controlled object includes a feature amount (148) calculated from the observed value of the controlled object.
[Structure 8]
The type of data associated with the control target includes the evaluation value (147) of the feature amount based on the comparison between the feature amount calculated from the observed value of the control target and the preset learning result. Or the control system according to 7.
[Structure 9]
When the evaluation value satisfies the predetermined abnormality detection condition (136), the visualization means extracts and visualizes the partial data corresponding to the time satisfying the abnormality detection condition from the time series data. The control system according to configuration 8, which includes a second visualization means (2362) for generating display data to be displayed.
[Structure 10]
An operation receiving means (234) for receiving a user's operation on the control system is further provided.
The control system according to any one of configurations 1 to 9, wherein the preset information is based on the operation content received by the operation receiving means.
[Structure 11]
A control device (105) that controls a controlled object.
A time-series storage means (132) that stores the data associated with the controlled object in a file in chronological order, and
A reading means (163) for reading the file for storing the time-series data from the time-series storage means at a predetermined read cycle.
A control device comprising a visualization means (230) for generating display data for visualizing and displaying the time-series data in the file read by the reading means.
[Structure 12]
A control device (100) that controls a controlled object and a display device (200) that can exchange data.
The control device includes a time series storage unit (163) that stores data associated with a controlled object in a file (132) in time series.
The display device is
A reading means (227) for reading the file for storing the time-series data from the time-series storage unit of the control device at a predetermined read cycle.
A display device comprising a visualization means (230) for generating display data for visualizing and displaying the time-series data in the file read by the periodic reading means.

It should be considered that the embodiments disclosed this time are exemplary in all respects and not restrictive. The scope of the present invention is shown not by the above description but by the scope of claims, and is intended to include all modifications within the meaning and scope equivalent to the scope of claims.

1 Control system, 100, 105 control device, 102, 202 processor, 132 CSV file 133, 1312, 1322, 1323 data, 134 training data, 135 setting file, 136 abnormality detection parameter, 140 abnormality detection engine, 142 feature amount extraction unit 144 anomaly detector, 146 event log, 147 score value, 148 feature amount, 152 scheduler, 153 counter, 154 variable manager, 160 control program, 174 feature amount generator, 200 display device, 216 input unit, 217 touch pad, 218 Display, 226 Data Mining Tool, 227 Data Collection Tool, 228 Setting Tool, 229 Screen Creation Tool, 230 Visualization Tool, 231 Visualization App, 234 Operation Reception Tool, 238 Communication Middleware, 1042 Hardware Resource, 1044 Monitor Engine , 1047 hypervisor, 1049 system program, 1321 counter value, 1362 specified feature quantity, 1363 frame parameter, 1461 variable name, 1462 cycle, 1464 event variable, 1542 system variable, 1544 device variable, 1631 cycle storage program, 2281 variable table, 2301 1st visualization tool, 2302 2nd visualization tool, 131 time series DB.

Claims (13)

A control system that controls a controlled object
A periodic execution means for periodically executing the control operation of the controlled object in a control cycle,
An operation of displaying a list of data names of a plurality of data associated with the control target including the observed values observed from the control target on the screen, specifying the data to be collected in the list of data names, and the control. UI (user interface) means for accepting user operations, including operations for setting the data collection cycle synchronized with the cycle, and
A collection means that collects the data specified by the user operation in the collection cycle set by the user operation, and
A time-series storage means for storing the collected data in a file in chronological order,
A reading means for reading the file for storing the time-series data from the time-series storage means at a predetermined read cycle, and
A visualization means for generating display data for visualizing and displaying the time-series data in the file read by the reading means is provided .
The data associated with the control target includes event data indicating that an event occurring in the control target has been detected.
The visualization means generates display data for visualizing and displaying a graph showing changes in the values of the event data over time and a graph showing changes in the values of the time-series data on the same time axis. 1 Including visualization means
The display data generated by the first visualization means is display data that is visualized and displayed by extracting a portion corresponding to the time when the event is detected from a graph showing changes in the values of the time-series data. Including control system. The control system according to claim 1, wherein the read cycle is based on the control cycle and the size of the file. The control system according to claim 1 or 2, wherein the operation of setting the collection cycle includes an operation of setting different collection cycles for the same data specified by the designated operation. The control system according to claim 1 or 2, wherein the operation of setting the collection cycle includes an operation of setting the same collection cycle for different data specified by the designated operation. The file constitutes a ring buffer and
The control system according to any one of claims 1 to 4 , wherein the file stores a predetermined amount of data per control cycle by the time series storage means. The control system according to claim 5 , wherein the type of data associated with the controlled object includes a feature amount calculated from an observed value of the controlled object. The type of data associated with the control target includes claim 5 or 6 including an evaluation value of the feature amount based on a comparison between a feature amount calculated from the observed value of the control target and a preset learning result. The control system described in. When the evaluation value satisfies a predetermined abnormality detection condition, the visualization means extracts partial data corresponding to the time satisfying the abnormality detection condition from the time-series data, visualizes it, and displays it. The control system according to claim 7 , wherein the control system includes a second visualization means for generating display data. The UI means is any one of claims 1 to 8 , wherein the UI means displays a tab on the screen that accepts a user operation for instructing the control system to start and end the collection of data specified by the specified operation. The control system according to item 1. A control device that controls a controlled object
A periodic execution means for periodically executing the control operation of the controlled object in a control cycle,
The control target is controlled according to the control calculation, and a list of data names of a plurality of data associated with the control target including the observed values observed from the control target is displayed on the screen and collected in the list of the data names. A UI (user interface) means for accepting user operations including an operation of specifying data to be performed and an operation of setting a data collection cycle synchronized with the control cycle.
A collection means that collects the data specified by the user operation in the collection cycle set by the user operation, and
A time-series storage means for storing the collected data in a file in chronological order,
A reading means for reading the file for storing the time-series data from the time-series storage means at a predetermined read cycle, and
A visualization means for generating display data for visualizing and displaying the time-series data in the file read by the reading means is provided .
The data associated with the control target includes event data indicating that an event occurring in the control target has been detected.
The visualization means generates display data for visualizing and displaying a graph showing changes in the values of the event data over time and a graph showing changes in the values of the time-series data on the same time axis. 1 Including visualization means
The display data generated by the first visualization means is display data that is visualized and displayed by extracting a portion corresponding to the time when the event is detected from a graph showing changes in the values of the time-series data. Including control device. A display device that can exchange data with a control device that controls a controlled object.
The control device is
A periodic execution means for periodically executing the control operation of the controlled object in a control cycle,
The control target is controlled according to the control calculation, and a list of data names of a plurality of data associated with the control target including the observed values observed from the control target is displayed on the screen and collected in the list of the data names. A UI (user interface) means for accepting user operations including an operation of specifying data to be performed and an operation of setting a data collection cycle synchronized with the control cycle.
A collection means that collects the data specified by the user operation in the collection cycle set by the user operation, and
A time-series storage means for storing the collected data associated with the control target in a file in chronological order is provided.
The display device is
A reading means for reading the file for storing the time-series data from the time-series storage means of the control device at a predetermined read cycle.
A visualization means for generating display data for visualizing and displaying the time-series data in the file read by the reading means is provided.
The data associated with the control target includes event data indicating that an event occurring in the control target has been detected.
The visualization means generates display data for visualizing and displaying a graph showing changes in the values of the event data over time and a graph showing changes in the values of the time-series data on the same time axis. 1 Including visualization means
The display data generated by the first visualization means is display data that is visualized and displayed by extracting a portion corresponding to the time when the event is detected from a graph showing changes in the values of the time-series data. Including display device. The file constitutes a ring buffer and
The file according to claim 10 , wherein a predetermined amount of data per control cycle is stored in the file by the time series storage means, and the read cycle is based on the control cycle and the size of the file. Control device. The file constitutes a ring buffer and
The file according to claim 11 , wherein a predetermined amount of data is stored in one control cycle by the time series storage means, and the read cycle is based on the control cycle and the size of the file. Display device.

Images