JP7582362B2 - Information processing device, determination method, and determination program - Google Patents

Description

The present invention relates to an information processing device, a determination method, and a determination program.

The manufacturing process may include controlling the temperature of raw materials by heating or cooling them through a fluid called a heat transfer medium, such as a heat transfer medium or a refrigerant.

JP 2017-80520 A

However, in the above manufacturing process, when raw materials are not being fed into processing equipment such as heating and cooling devices, fluids such as heat transfer media and refrigerants continue to be supplied even when production activities are stopped, making it difficult to prevent energy waste.

The purpose of this invention is to help reduce energy waste.

An information processing device according to one aspect of the present invention has a first acquisition unit that acquires the temperature of a pipe from a temperature sensor installed outside the pipe that supplies a fluid, either a heat transfer medium or a refrigerant, to a processing device that heats or cools raw materials, and a first determination unit that determines the presence or absence of a flow of the fluid in the pipe based on the temperature of the pipe acquired by the first acquisition unit.

In one aspect of the present invention, a computer executes a process to obtain the temperature of a pipe that supplies a heat transfer medium or a refrigerant to a processing device that heats or cools raw materials from a temperature sensor installed on the outside of the pipe, and to determine whether or not the fluid is flowing in the pipe based on the temperature of the pipe.

The judgment program according to one aspect of the present invention causes a computer to execute a process of acquiring the temperature of a pipe that supplies a heat transfer medium or a refrigerant to a processing device that heats or cools raw materials from a temperature sensor installed on the outside of the pipe, and judging whether or not the fluid is flowing in the pipe based on the temperature of the pipe.

According to one embodiment, it can help reduce energy waste.

FIG. 1 is a schematic diagram showing an example of a production facility. 2 is a block diagram showing an example of a functional configuration of an information processing device; FIG. 1 is a schematic diagram illustrating an example of a machine learning model. FIG. 13 is a schematic diagram showing an example of determination of energy usage. 11 is a flowchart showing a procedure of a first determination process. 13 is a flowchart showing a procedure of a second determination process. 13 is a flowchart showing a procedure of a third determination process. FIG. 2 illustrates an example of a hardware configuration.

Below, the information processing device, the determination method, and the determination program according to the present application will be described with reference to the attached drawings. Each embodiment merely shows examples and aspects, and the numerical values, range of functions, and usage scenarios are not limited by such examples. Each embodiment can be adaptively combined to the extent that the processing contents are not contradictory.

<Example of production equipment>
FIG. 1 is a schematic diagram showing an example of a production facility. FIG. 1 shows a production facility 1 that realizes a manufacturing process in which raw materials conveyed by a belt conveyor 3 are heated by a heating device 4. FIG. 1 shows a usage scene in which "steam" is exemplified as a heat medium and a "heating device" is exemplified as a processing device, but is not limited thereto. The heating device 4 is merely an example of a processing device that heats or cools raw materials, and naturally, a usage scene in which cooling is performed with a refrigerant such as cooling water by a cooling device, which is another example of a processing device, is also included in the scope of this embodiment.

As shown in FIG. 1, the production equipment 1 has a belt conveyor 3, a motor M, a heating device 4, and piping 5. For example, the belt conveyor 3 is a device that conveys raw materials placed on the belt in the traveling direction (conveying direction) of the belt that rotates by the drive of the motor M. The heating device 4 is a device that heats the raw materials conveyed by the belt conveyor 3 using steam supplied from the piping 5 as a medium. Note that the belt conveyor 3 is an example of a conveying mechanism, and the motor M is merely an example of a drive unit that drives the conveying mechanism, and similar functions may be realized by other mechanisms or devices.

<One aspect of the issue>
As explained in the Background section above, in the above manufacturing process, there is an aspect of wasting energy because the supply of fluids such as heat transfer media and refrigerants continues even when production activities are stopped, for example, when raw materials are not being fed into processing equipment such as heating equipment and cooling equipment.

<One aspect of the problem-solving approach>
One approach to solving the above problem is to directly observe the physical quantity, namely the flow rate of steam flowing through the pipe 5. This realizes monitoring of the state in which steam is flowing through the pipe 5, i.e., the energy usage status. Note that the problem-solving approach described here is distinguished from conventional techniques that fall under the category of well-known techniques, including publicly known patent and non-patent documents.

When such a problem-solving approach is adopted, disadvantages arise, such as increased labor hours for installing a sensor that measures flow, such as a steam flow meter, and increased costs for the steam flow meter. For example, a type of steam flow meter that is installed on the inside of the pipe 5 requires increased labor hours for installation work. In addition, a type of flow meter that is installed on the surface of the pipe, such as an ultrasonic flow meter, increases costs because the steam flow meter itself is not inexpensive.

These increases in labor and costs are proportional to the number of pipes 5 to be monitored, so it is currently difficult from a cost-effectiveness perspective to install steam flow meters solely for the purpose of monitoring energy usage.

The technical significance of this embodiment is that it adopts a problem-solving approach that realizes monitoring of energy usage using a mechanism that does not rely on a steam flow meter that can observe flow rate as a physical quantity.

As an approach to solving such problems, this embodiment adopts an approach in which, rather than the flow rate of the steam flowing through the pipe 5 itself, a physical quantity that is related to the flow rate is acquired from a sensor that can be installed outside the pipe 5.

As just one example, the information processing device 10 acquires the surface temperature of the pipe 5 from a temperature sensor 5A installed on the outside of the pipe 5. Here, the temperature sensor 5A may be installed in contact with the outer surface of the pipe 5, but it does not necessarily have to be installed in contact, and may be installed in a non-contact state with the outer surface of the pipe 5. For example, the surface temperature of the pipe 5 and the flow rate of the pipe 5 are related in that the surface temperature is higher when steam is flowing through the pipe 5 than when no steam is flowing through the pipe 5.

As another example, the information processing device 10 acquires the vibration level of the pipe 5 from a vibration sensor 5B installed outside the pipe 5. For example, the vibration level of the pipe 5 and the flow rate of the pipe 5 are correlated such that the vibration level is higher when steam is flowing through the pipe 5 than when no steam is flowing through the pipe 5.

Based on the surface temperature of the pipe 5 and the vibration level of the pipe 5, the information processing device 10 determines whether steam is flowing through the pipe 5. Such a two-class classification task can be realized sufficiently and with high accuracy even if the flow rate of steam through the pipe 5 is not necessarily given as an input, but a physical quantity related to the flow rate is used as an input. Note that, although an example of using both the surface temperature of the pipe 5 and the vibration level of the pipe 5 has been given here, at least one of them can be used.

This allows the information processing device 10 to output an alert if it detects that steam is flowing through the pipe 5 even though raw materials are not being transported by the belt conveyor 3.

An example of such an output destination is an information processing terminal 20 (hereinafter referred to as the "work-related person terminal") used by work-related persons 2, including workers who work at the production facility 1 and site supervisors who supervise the site of the production facility 1.

For example, the work-related person terminal 20 may be realized by a mobile terminal device such as a smartphone or tablet terminal, a wearable terminal, or a desktop or laptop personal computer. In this case, the information processing device 10 can display an icon or message corresponding to a warning about wasted energy or a warning urging an operation to stop the supply of steam to the pipe 5. Note that the alert is not limited to a display output, and may be realized by an audio output or a print output.

In addition to the work-related person terminal 20, the information processing device 10 can also output alerts to output units, such as a display unit, audio output unit, or print output unit, of the equipment included in the production facility 1 shown in FIG. 1 or equipment not shown in FIG. 1.

Note that, although an example has been given here in which an alert is output to prompt the user to stop the supply of steam to the pipe 5, the control to stop the supply of steam to the pipe 5 may be executed automatically.

As described above, the information processing device 10 according to this embodiment can help reduce wasteful use of energy when production activities are stopped. Furthermore, since energy usage is monitored using a system that does not rely on a steam flow meter that can observe flow rate as a physical quantity, the labor and costs associated with installing sensors can also be reduced. The labor and cost reduction effects increase as the number of pipes 5 to be monitored increases.

<Configuration of information processing device 10>
Next, a functional configuration example of the information processing device 10 according to the present embodiment will be described. Fig. 2 is a block diagram showing a functional configuration example of the information processing device 10. As shown in Fig. 2, the information processing device 10 is connected to a power meter 3A, a temperature sensor 5A, a vibration sensor 5B, and a work-related person terminal 20 so as to be able to communicate with each other.

Communication conforming to industrial wireless standards may be carried out between the information processing device 10 and the group of sensors, such as the power meter 3A, temperature sensor 5A, and vibration sensor 5B. The work-related person terminal 20 and the information processing device 10 may be connected via any type of communication network, such as the Internet or a LAN (Local Area Network).

Note that bidirectional communication does not necessarily have to be performed between the information processing device 10 and the sensor group, and serial communication may be performed from the sensor group to the information processing device 10. Furthermore, communication performed between the information processing device 10 and the sensor group is not limited to a specific communication standard such as an industrial communication standard, and is not limited to being wired or wireless.

Figure 2 shows a schematic diagram of blocks related to the energy usage monitoring function of the information processing device 10. As shown in Figure 2, the information processing device 10 has a communication control unit 11, a memory unit 13, and a control unit 15. Note that Figure 2 shows only a selection of functional units related to the above monitoring function, and the information processing device 10 may be provided with functional units other than those shown.

The communication control unit 11 is a functional unit that controls communication between the group of sensors, such as the power meter 3A, temperature sensor 5A, and vibration sensor 5B, and other devices, such as the work-related person terminal 20. As just one example, the communication control unit 11 can be realized by a network interface card. As one aspect, the communication control unit 11 can receive the power consumed by the motor M from the power meter 3A, the surface temperature of the pipe 5 from the temperature sensor 5A, or the vibration level of the pipe 5 from the vibration sensor 5B. As another aspect, the communication control unit 11 can output an alert of energy waste to the work-related person terminal 20 when production activities are stopped.

The storage unit 13 is a functional unit that stores various types of data. As just one example, the storage unit 13 is realized by internal, external, or auxiliary storage of the information processing device 10. For example, the storage unit 13 stores a machine learning model 13M. Note that an explanation of the machine learning model 13M will be given together with a situation in which the machine learning model 13M is referenced, generated, or registered.

The control unit 15 is a functional unit that performs overall control of the information processing device 10. For example, the control unit 15 can be realized by a hardware processor. As shown in FIG. 2, the control unit 15 has a first acquisition unit 15A, a second acquisition unit 15B, a third acquisition unit 15C, a first judgment unit 15D, a second judgment unit 15E, and a third judgment unit 15F. Note that the control unit 15 may also be realized by hardwired logic, etc.

The first acquisition unit 15A is a processing unit that acquires the surface temperature of the pipe 5 from the temperature sensor 5A. The second acquisition unit 15B is a processing unit that acquires the vibration level of the pipe 5 from the vibration sensor 5B. The third acquisition unit 15C is a processing unit that acquires the power consumed by the motor M from the power meter 3A. Note that here, the power consumption of the motor M is given as an example of an index value of power used to determine the energy input status, but the power consumption of the motor M is only one example, and the third acquisition unit 15C can acquire other index values of power related to the motor M or a driving unit similar to the motor M. For example, the third acquisition unit 15C may acquire index values of other items such as the current, voltage, and reactance consumed by the motor M. The third acquisition unit 15C may also acquire an index value of the power supplied to the motor M, rather than the index value of the power consumed by the motor M.

The first acquisition unit 15A, the second acquisition unit 15B, and the third acquisition unit 15C can acquire the sensor values output by each of the temperature sensor 5A, the vibration sensor 5B, and the power meter 3A in real time, and can acquire time series data of the sensor values for a specific length of time.

The first determination unit 15D is a processing unit that determines whether steam is flowing through the pipe 5, i.e., the energy usage status, based on the surface temperature of the pipe 5 acquired by the first acquisition unit 15A and the vibration level of the pipe 5 acquired by the second acquisition unit 15B.

As just one example, such a determination of energy usage status can be achieved by a machine learning model 13M that executes a classification task that takes the surface temperature of the pipe 5 and the vibration level of the pipe 5 as input and outputs the confidence level for each class of "present" or "absent" steam flow.

Below, we will give an example in which the above machine learning model is realized by a neural network, but it may also be realized by other machine learning models such as a support vector machine or a gradient boosting decision tree.

Figure 3 is a schematic diagram showing an example of machine learning model 13M. As shown in Figure 3, to determine the energy usage status, a trained machine learning model 13M in which machine learning model 13m is trained according to a machine learning algorithm such as deep learning is used.

To train the machine learning model 13m, a dataset 13TR can be used, which includes training data in which the surface temperature of the pipe 5 and the vibration level of the pipe 5 are associated with the correct label of "yes" or "no" steam flow.

For example, Figure 3 shows three training data excerpts as examples of dataset 13TR, in which time series data of temperature and time series data of vibration level are associated with one of two correct answer labels, "with" steam flow and "without" steam flow.

Here, the temperature time series data and the vibration level time series data may be data strings in which temperature or vibration level data values for a certain time length, for example 5 seconds, are arranged in a chronological order. The time of the starting data point, the time of the ending data point, the number of data points, and the time of each data point may be the same between these two data strings, but there may be a deviation within an acceptable range. In other words, the sampling periods of the temperature sensor 5A and the vibration sensor 5B do not necessarily have to be the same, and there may also be a deviation in the size of the window that extracts the time series data from the signal output by each sensor, or in the time position at which the window is applied to the signal.

Hereinafter, the time series data of the surface temperature of the pipe 5 may be referred to as "temperature data," and the time series data of the vibration level of the pipe 5 may be referred to as "vibration data."

For example, in the training phase, the temperature data and vibration data are set as explanatory variables of the machine learning model 13m, the correct answer label is set as the objective variable of the machine learning model 13m, and the machine learning model 13m is trained according to an arbitrary machine learning algorithm, for example, deep learning. The trained machine learning model 13M obtained in this way is registered in the storage unit 13. For example, hyperparameters related to the layer structure such as neurons and synapses of the input layer, hidden layer, and output layer that form the machine learning model 13M, parameters related to the objective function such as the weights and biases of each layer, etc. are stored in the storage unit 13.

In the inference phase, the temperature data acquired by the first acquisition unit 15A and the vibration data acquired by the second acquisition unit 15B are input to the machine learning model 13M. The machine learning model 13M to which the temperature data and the vibration data are input in this manner outputs the confidence level for each class of "presence" or "absence" of steam flow. For example, in the example shown in FIG. 3, "90%" is output as the confidence level for "presence" of steam flow. Furthermore, "10%" is output as the confidence level for "absence" of steam flow. Note that, although an example is given here in which time series data of temperature and vibration level is input to the machine learning model 13M, time series data of temperature and vibration level are not necessarily input. For example, feature values obtained by feature extraction of time series data of temperature and vibration level, such as the mean, variance, and median, may be input to the machine learning model 13M.

Based on the confidence level of "existence" of steam flow obtained in this manner, the first judgment unit 15D judges the energy usage status in the production equipment 1. For example, the first judgment unit 15D judges whether the confidence level of "existence" of steam flow is equal to or greater than the threshold value Th1. At this time, if the confidence level of "existence" of steam flow is equal to or greater than the threshold value Th1, the first judgment unit 15D outputs "existence" of steam flow to the third judgment unit 15F as the judgment result of the energy usage status. On the other hand, if the confidence level of "existence" of steam flow is not equal to or greater than the threshold value Th1, the first judgment unit 15D outputs "no" of steam flow to the third judgment unit 15F as the judgment result of the energy usage status.

FIG. 4 is a schematic diagram showing an example of determining the energy usage status. FIG. 4 shows a graph G1 in which the waveform of the signal output by the temperature sensor 5A is plotted as a solid line and the waveform of the signal output by the vibration sensor 5B is plotted as a dashed line. The vertical axis of the graph G1 indicates the sensor value of the surface temperature of the pipe 5 or the vibration level of the pipe 5, and the horizontal axis of the graph G1 also indicates time. On such a graph G1, windows W1 to W4 in which temperature data or vibration data is cut out from the signal of each sensor at four points in time from time t1 to time t4 are schematicized. Furthermore, FIG. 4 shows a graph G2 in which time series data of the confidence level of "existence" of steam flow output by the machine learning model 13M is plotted. The vertical axis of the graph G2 indicates the confidence level, and the horizontal axis of the graph G2 also indicates time. On such a graph G2, the lower limit of the confidence level for identifying "existence" of steam flow is shown as a threshold value Th1. Note that Figure 4 shows an example in which the window width, i.e., time length, of windows W1 to W4 is 5 seconds.

For example, at time t1, window W1 is set so that time t1 coincides with the end (right end) of window W1. In this case, the waveforms of the portions of the signals from temperature sensor 5A and vibration sensor 5B that correspond to the window width of window W1, i.e., the data strings of the sensor values from 5 seconds before time t1 to time t1, are extracted as temperature data and vibration data. The machine learning model 13M to which the extracted temperature data and vibration data are input outputs the confidence that steam flow is "present." The confidence that steam flow is "present" obtained here is equal to or greater than threshold Th1, so it is determined that the energy usage status is "present" with steam flow.

Furthermore, at times t2, t3, and t4, the certainty that there is steam flow is obtained, as in the case of time t1. For example, at time t2, the certainty that there is steam flow is equal to or greater than threshold Th1, so it is determined that the energy usage is that there is steam flow. At time t3, the certainty that there is steam flow is less than threshold Th1, so it is determined that the energy usage is that there is no steam flow. At time t4, the certainty that there is steam flow is also less than threshold Th1, so it is determined that the energy usage is that there is no steam flow.

Here, the operation at four points in time, t1 to t4, has been explained in cross section, but speaking over the entire period, it is as follows. That is, as shown at the bottom of graph G2, in the section where the hatched band is shown with a solid line, it is determined that there is steam flow, while in the section where the hatched band is shown with a dashed line, it is determined that there is no steam flow.

Note that, although an example has been given here in which two pieces of data, temperature data or vibration data, are input to the machine learning model 13M, the data input to the machine learning model 13M does not necessarily have to be both of the two pieces of data. In other words, the machine learning model 13M may input only one of the two pieces of data, temperature data or vibration data, and output a class of either "there is" steam flow or "there is no" steam flow.

In addition, although an example of determining the energy usage status using the machine learning model 13M has been given here, the machine learning model does not necessarily have to be used to determine the energy usage status. For example, the first determination unit 15D can also determine the energy usage status based on the slope and intercept of an approximate straight line obtained by applying regression analysis, such as linear regression, to the temperature data or vibration data. Specifically, when the sign of the slope is "positive", the possibility that steam is flowing in the pipe 5 increases. Also, when the slope is within a predetermined range from zero, the possibility that the steam flow is stable or that the state of no steam flow continues increases. At this time, when the intercept is a positive value and is equal to or greater than a certain value, the possibility that the steam flow is stable increases, while when the intercept is within a predetermined range from zero, the possibility that the state of no steam flow continues increases. From the above, when the sign of the slope is "positive" and the slope is not within a predetermined range from zero, it can be determined that there is a steam flow. Furthermore, if the slope is within a predetermined range from zero, the intercept is a positive value, and the intercept is equal to or greater than a threshold value, it can be determined that steam flow is present.

The second determination unit 15E is a processing unit that determines whether raw materials are being transported by the belt conveyor 3, i.e., the raw materials input status, based on the power consumption of the motor M acquired by the third acquisition unit 15C.

As just one example, the second judgment unit 15E judges whether the power consumption of the motor M is equal to or greater than the threshold value Th2. At this time, if the power consumption of the motor M is equal to or greater than the threshold value Th2, the second judgment unit 15E outputs raw materials "being added" to the third judgment unit 15F as the judgment result of the raw materials input status. On the other hand, if the power consumption of the motor M is not equal to or greater than the threshold value Th2, the second judgment unit 15E outputs raw materials "not being added" to the third judgment unit 15F as the judgment result of the raw materials input status.

The third judgment unit 15F is a processing unit that judges whether or not energy waste is occurring when production activities are stopped, based on the judgment result of the energy usage status by the first judgment unit 15D and the judgment result of the raw material input status by the second judgment unit 15E.

As merely one example, the third determination unit 15F determines whether the energy usage status is "with" steam flow and the raw material input status is "raw materials not being input." At this time, if the energy usage status is "with" steam flow and the raw material input status is "raw materials not being input," it can be identified that energy waste is occurring when production activities are stopped. In this case, the third determination unit 15F outputs an alert warning about energy waste or a warning urging an operation to stop the supply of steam to the piping 5 to any output destination including the work-related person terminal 20.

<Processing flow>
Next, a process flow of the information processing device 10 according to the present embodiment will be described. Here, (1) a first determination process, (2) a second determination process, and (3) a third determination process executed by the information processing device 10 will be described.

5 is a flowchart showing the procedure of the first determination process. This process is merely an example and can be executed when a sensor value is acquired from the temperature sensor 5A or the vibration sensor 5B, or at a fixed cycle.

As shown in FIG. 5, the first acquisition unit 15A acquires the surface temperature of the pipe 5 from the temperature sensor 5A, and the second acquisition unit 15B acquires the vibration level of the pipe 5 from the vibration sensor 5B (steps S101 and S102).

Then, the first determination unit 15D inputs the temperature data for a predetermined period of time in the past, including the surface temperature acquired in step S101, and the vibration data for a predetermined period of time in the past, including the vibration level acquired in step S101, to the machine learning model 13M (step S103).Then, the first determination unit 15D determines whether the confidence level of the steam flow "existence" output by the machine learning model 13M is equal to or greater than the threshold value Th1 (step S104).

At this time, if the confidence level that steam flow is "present" is equal to or greater than the threshold value Th1 (Yes in step S104), the first determination unit 15D outputs "present" steam flow as the determination result of the energy usage status to the third determination unit 15F (step S105), and ends the process.

On the other hand, if the confidence level that steam flow is "present" is not equal to or greater than threshold value Th1 (step S104: No), the first judgment unit 15D outputs steam flow "absent" as the judgment result of the energy usage status to the third judgment unit 15F (step S106), and ends the process.

The order of execution of the processes in steps S101 and S102 in the flowchart shown in FIG. 5 is not limited to the order of the step numbers shown, and may be random or may be simultaneous.

6 is a flowchart showing the procedure of the second determination process. This process is merely an example and can be executed when the power consumption of the motor M is obtained from the power meter 3A or at a fixed cycle.

As shown in FIG. 6, the third acquisition unit 15C acquires the power consumption of the motor M from the power meter 3A (step S301). Next, the second determination unit 15E determines whether the power consumption of the motor M acquired in step S301 is equal to or greater than the threshold value Th2 (step S302).

At this time, if the power consumption of the motor M is equal to or greater than the threshold value Th2 (Yes in step S302), the second judgment unit 15E outputs "raw material being added" as the judgment result of the raw material input status to the third judgment unit 15F (step S303), and ends the process.

On the other hand, if the power consumption of the motor M is not equal to or greater than the threshold value Th2 (No in step S302), the second judgment unit 15E outputs "raw material not being added" as the judgment result of the raw material input status to the third judgment unit 15F (step S304), and ends the process.

(3) Third Determination Process Fig. 7 is a flowchart showing the procedure of the third determination process. This process is merely an example, and can be executed when the energy usage status is determined by the first determination unit 15D, when the raw material input status is determined by the second determination unit 15E, or at a fixed cycle.

As shown in FIG. 7, the third judgment unit 15F judges whether or not the result of the judgment of the energy usage status by the first judgment unit 15D is that there is steam flow (step S501). If there is no steam flow (step S501 No), the process ends.

At this time, if there is a steam flow (step S501: Yes), the third judgment unit 15F further judges whether the result of the judgment of the raw material input status by the second judgment unit 15E is raw materials not being input (step S502). If the raw materials are being input (step S502: No), the process ends.

If the raw materials are "not being input" (Yes in step S502), it can be determined that energy waste is occurring when production activities are stopped. In this case, the third determination unit 15F outputs an alert to any output destination, such as the work-related person terminal 20, warning of energy waste or warning to prompt an operation to stop the supply of steam to the pipe 5 (step S503), and ends the process.

The order of execution of the processes in steps S501 and S502 in the flowchart shown in FIG. 7 is not limited to the order of the step numbers shown, and may be random or may be simultaneous.

<One aspect of the effect>
As described above, the information processing device 10 according to the present embodiment judges whether steam is flowing through the pipe 5 based on the surface temperature of the pipe 5 and the vibration level of the pipe 5. As a result, for example, when a state in which steam is flowing through the pipe 5 is detected even though raw materials are not being transported by the belt conveyor 3, an alert can be output. Therefore, the information processing device 10 according to the present embodiment can support the reduction of wasteful use of energy when production activities are stopped. Furthermore, since the monitoring of energy usage is realized by a mechanism that does not depend on a steam flow meter that can observe the flow rate as a physical quantity, it is also possible to reduce the labor and costs involved in installing sensors. The effect of reducing these labor and costs increases as the number of pipes 5 to be monitored increases.

<Numeric values, etc.>
The matters described in the above embodiment, such as the number of sensors, the specific examples of the training method and the inference method of the machine learning model 13M, etc., are merely examples and can be changed. In addition, the order of processes in the flowcharts described in the embodiment can be changed within a range that does not cause inconsistencies.

<System>
The information including the processing procedures, control procedures, specific names, various data and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified. For example, any one or more of the functional units of the first judgment unit 15D, the second judgment unit 15E and the third judgment unit 15F may be configured as separate devices.

In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure. In other words, all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc. Each configuration may also be a physical configuration.

Furthermore, each processing function performed by each device may be realized, in whole or in part, by a CPU (Central Processing Unit) and a program analyzed and executed by the CPU, or may be realized as hardware using wired logic.

<Hardware>
Next, a hardware configuration example of the computer described in the embodiment will be described. Fig. 8 is a diagram for explaining the hardware configuration example. As shown in Fig. 8, the information processing device 10 has a communication device 10a, a HDD (Hard Disk Drive) 10b, a memory 10c, and a processor 10d. In addition, each unit shown in Fig. 8 is connected to each other by a bus or the like.

The communication device 10a is a network interface card or the like, and communicates with other servers. The HDD 10b stores programs and databases that operate the functions shown in FIG. 2.

The processor 10d reads out a program that executes the same processing as the processing unit shown in FIG. 2 from the HDD 100b, etc., and expands it in the memory 100c, thereby operating a process that executes the functions described in FIG. 2, etc. For example, this process executes the same functions as the processing unit possessed by the information processing device 10. Specifically, the processor 10d reads out a program having the same functions as the first acquisition unit 15A, the second acquisition unit 15B, the third acquisition unit 15C, the first judgment unit 15D, the second judgment unit 15E, the third judgment unit 15F, etc., from the HDD 10b, etc. Then, the processor 10d executes a process that executes the same processing as the first acquisition unit 15A, the second acquisition unit 15B, the third acquisition unit 15C, the first judgment unit 15D, the second judgment unit 15E, the third judgment unit 15F, etc.

In this way, the information processing device 10 operates as an information processing device that executes a cause analysis method by reading and executing a program. The information processing device 10 can also realize functions similar to those of the above-described embodiment by reading the program from a recording medium using a media reading device and executing the read program. Note that the program in these other embodiments is not limited to being executed by the information processing device 10. For example, the present invention can be similarly applied to cases where another computer or server executes a program, or where these cooperate to execute a program.

The above program can be distributed via a network such as the Internet. The above program can also be recorded on any recording medium and executed by a computer by reading it from the recording medium. For example, the recording medium can be a hard disk, a flexible disk (FD), a CD-ROM, an MO (Magneto-Optical disk), a DVD (Digital Versatile Disc), etc.

＜Other＞
Some examples of combinations of the disclosed technical features are set out below.

(1) a first acquisition unit that acquires a temperature of a pipe from a temperature sensor installed outside the pipe that supplies a fluid, either a heat transfer medium or a refrigerant, to a processing device that heats or cools raw materials;
a first determination unit that determines whether or not the fluid flows in the pipe based on the temperature of the pipe acquired by the first acquisition unit;
13. An information processing device comprising:

(2) Further comprising a second acquisition unit that acquires a vibration level of the pipe from a vibration sensor installed outside the pipe,
The information processing device described in (1) is characterized in that the first judgment unit judges whether or not the fluid is flowing in the piping based on the temperature of the piping acquired by the first acquisition unit and the vibration level of the piping acquired by the second acquisition unit.

(3) a third acquisition unit that acquires an index value of power consumed by a drive unit that drives a transport mechanism that transports the raw materials to the processing device, or of power supplied to the drive unit;
a second determination unit that determines whether the raw material is being input or not based on the power index value acquired by the third acquisition unit;
a third determination unit that determines whether or not the determination result by the first determination unit is that the fluid is flowing and the determination result by the second determination unit is that the raw material is not being introduced;
The information processing device according to (2) further comprises:

(4) The information processing device according to (3), characterized in that the third determination unit outputs an alert when the fluid is flowing and the raw material is not being added.

(5) The information processing device according to any one of (1) to (4), characterized in that the temperature sensor is installed in contact with the outer surface of the pipe.

(6) The information processing device according to any one of (1) to (5), wherein the first determination unit determines whether or not the fluid is flowing in the pipe based on an output when the time series data of the temperature of the pipe acquired by the first acquisition unit is input to a machine learning model that classifies the data into a class of whether or not the fluid is flowing.

(7) The information processing device described in (6) is characterized in that the first determination unit determines whether or not the fluid is flowing in the pipe based on whether or not the confidence level of the class indicating that the fluid is flowing output by the machine learning model is equal to or greater than a threshold value.

(8) The information processing device according to (6) or (7), characterized in that the machine learning model is trained by executing machine learning with the time series data of the temperature of the pipe as an explanatory variable of the machine learning model and the label of the presence or absence of the fluid flow as the objective variable of the machine learning model.

(9) acquiring the temperature of a pipe from a temperature sensor installed on the outside of the pipe that supplies a fluid, either a heat transfer medium or a refrigerant, to a processing device that heats or cools the raw material;
determining whether or not the fluid is flowing through the pipe based on the temperature of the pipe;
A determination method characterized in that the processing is executed by a computer.

(10) acquiring the temperature of a pipe from a temperature sensor installed on the outside of the pipe that supplies a fluid, either a heat transfer medium or a refrigerant, to a processing device that heats or cools raw materials;
determining whether or not the fluid is flowing through the pipe based on the temperature of the pipe;
A determination program that causes a computer to execute a process.

REFERENCE SIGNS LIST 1 Production equipment 2 Work-related person 3 Belt conveyor 3A Power meter 4 Heating device 5 Pipe 5A Temperature sensor 5B Vibration sensor 10 Information processing device 11 Communication control unit 13 Memory unit 13M Machine learning model 15 Control unit 15A First acquisition unit 15B Second acquisition unit 15C Third acquisition unit 15D First judgment unit 15E Second judgment unit 15F Third judgment unit 20 Work-related person terminal

Claims (8)

a first acquisition unit that acquires a temperature of a pipe from a temperature sensor installed outside the pipe that supplies a fluid of either a heat transfer medium or a refrigerant to a processing device that heats or cools raw materials;
A second acquisition unit that acquires a vibration level of the pipe from a vibration sensor installed outside the pipe;
a third acquisition unit that acquires an index value of power consumed by a drive unit that drives a transport mechanism that transports the raw materials to the processing device, or of power supplied to the drive unit;
a first determination unit that determines whether or not the fluid is flowing through the pipe based on the temperature of the pipe acquired by the first acquisition unit and the vibration level of the pipe acquired by the second acquisition unit;
a second determination unit that determines whether the raw material is being input or not based on the power index value acquired by the third acquisition unit;
a third determination unit that determines whether or not the determination result by the first determination unit is that the fluid is flowing and the determination result by the second determination unit is that the raw material is not being introduced;
13. An information processing device comprising : The information processing apparatus according to claim 1 , wherein the third determination unit outputs an alert when the fluid is flowing and the raw material is not being fed. The information processing device according to claim 1, characterized in that the temperature sensor is installed in contact with the outer surface of the pipe. The information processing device according to any one of claims 1 to 3, characterized in that the first judgment unit judges whether or not the fluid is flowing in the piping based on an output when time series data of the temperature of the piping acquired by the first acquisition unit is input into a machine learning model that classifies the data into classes of whether or not the fluid is flowing. The information processing device according to claim 4 , wherein the first determination unit determines whether or not the fluid is flowing in the piping based on whether or not a certainty factor of the class indicating that the fluid is flowing output by the machine learning model is equal to or greater than a threshold value. The information processing device according to claim 4, characterized in that the machine learning model is trained by performing machine learning with the time series data of the temperature of the pipe as an explanatory variable of the machine learning model and a label of the presence or absence of fluid flow as a target variable of the machine learning model. The temperature of a pipe is obtained from a temperature sensor installed outside the pipe, which supplies a fluid of a heat medium or a coolant to a processing device that heats or cools the raw material;
acquiring a vibration level of the pipe from a vibration sensor installed on the outside of the pipe;
acquiring an index value of power consumed by a drive unit that drives a transport mechanism that transports the raw materials to the processing device, or an index value of power supplied to the drive unit;
determining whether or not the fluid is flowing through the pipe based on the temperature of the pipe and the vibration level of the pipe ;
determining whether the raw material is being input or not based on the index value of the power;
determining whether the result of the determination of the presence or absence of a flow of the fluid in the piping is that the fluid is flowing and whether the result of the determination of whether the raw materials are being fed or not is that the raw materials are not being fed;
A determination method characterized in that the processing is executed by a computer. The temperature of a pipe is obtained from a temperature sensor installed outside the pipe, which supplies a fluid of a heat medium or a coolant to a processing device that heats or cools the raw material;
acquiring a vibration level of the pipe from a vibration sensor installed on the outside of the pipe;
acquiring an index value of power consumed by a drive unit that drives a transport mechanism that transports the raw materials to the processing device, or an index value of power supplied to the drive unit;
determining whether or not the fluid is flowing through the pipe based on the temperature of the pipe and the vibration level of the pipe ;
determining whether the raw material is being input or not based on the index value of the power;
determining whether the result of the determination of the presence or absence of a flow of the fluid in the piping is that the fluid is flowing and whether the result of the determination of whether the raw materials are being fed or not is that the raw materials are not being fed;
A determination program that causes a computer to execute a process.

Images