JP2021092868A - Work process discrimination device and system for the same - Google Patents

Abstract

To provide a method by which a work process is discriminated without loading a burden on an operator.SOLUTION: A work process discrimination device 1 in this invention comprises a data acquisition part 110 and a machine learning device 100. The data acquisition part acquires data which include at least either one of an operation history information of a control device 3 or a machine periphery information that is detected by a sensor 6 about a periphery state of said industrial machine 4. The machine learning device analyzes data acquired by the data acquisition part 110 and conducts a machine learning transaction relating to both at least either one of the operation history information or the machine periphery information and a separation of a work process.SELECTED DRAWING: Figure 2

Description

The present invention relates to a work process discriminating device and a work process discriminating system.

At manufacturing sites such as factories, devices that monitor the operating status of industrial machines such as robots and machine tools installed on the production line and manage the operating status of the industrial machines have been introduced (for example, Patent Document 1 and the like). .. When monitoring the operation of an industrial machine, there is a desire to know in detail what the worker is doing in the "stopped" state where the processing operation of the industrial machine is not being performed. There is a desire to know what kind of work is taking when an industrial machine is "stopped" but a person is working in front of the industrial machine.

FIG. 10 is an example of displaying the operating state of the industrial machine managed by the operation management system. In FIG. 10, from 10:35:52 to 12:58:07 on November 28, the industrial machine of equipment 0001 is turned on but stopped. Normally, during the operation of an industrial machine, it is possible to determine what kind of work is being performed based on the data acquired from the industrial machine. However, while the industrial machine is stopped, sufficient data for determining the work content cannot be obtained. Therefore, there is a desire to determine the work content in some way. Hereinafter, each stage of human work is referred to as a work process.

There are the following methods as means for discriminating the work process. Buttons (for example, buttons such as "work transporting", "tool changing", and "dimensioning") are provided on the operation panel of an industrial machine to indicate the contents of the work process, and the operator can apply each work process. I press the button. Then, the operation monitoring system can determine the work process by the operator by detecting the ON / OFF signal of the button, and can manage the time taken for each work process.

Japanese Unexamined Patent Publication No. 2014-174996

If the configuration is such that an operator is allowed to operate the work process in order to determine the work process, there is a problem that it takes time and effort because some operation must be performed for each work process. Further, when the work process is to be managed in detail, the burden on the worker increases because the worker has to perform an operation of notifying the work process every time the work process changes.
Therefore, there is a demand for a technique that makes it possible to discriminate a work process without imposing a burden on the operator.

In the work process discriminating device and the work process discriminating system of the present invention, the operation history information acquired from the control device for controlling the industrial machine and the information around the machine by each sensor installed around the industrial machine are acquired and acquired. By performing machine learning using the above-mentioned information, the correlation between the operation history information and the machine peripheral information and the work process is learned. Then, using the learning result, it is possible to determine what kind of work process the worker is in even when the industrial machine is stopped.

The work process discriminating device and the work process discriminating system of the present invention include at least an embodiment in which unsupervised learning is used as a learning method and an embodiment in which supervised learning is used.
In embodiments that use unsupervised learning, the work is done by a person. Machine learning is performed using the machine peripheral information during work as input data, and the common processing performed by the machine learning device is extracted every time, and the characteristics of the machine peripheral information during the processing are extracted to determine the division of the work process. To do.
On the other hand, in the embodiment using supervised learning, in the learning phase, when the work process is divided during the work, the worker teaches the content and timing of the work process with a button or the like. By learning this as teacher data, the correlation between the operation history information and the machine peripheral information and the work process is learned.

Then, one aspect of the present invention is a work process discriminating device for discriminating a work process in a work using a control device for controlling an industrial machine, and sensors the operation history information of the control device and the peripheral state of the industrial machine. A data acquisition unit that acquires data including at least one of the machine peripheral information detected in the above, and an analysis of the data acquired by the data acquisition unit to obtain at least one of the operation history information and the machine peripheral information, and the work process. It is a work process discriminating device including a machine learning device that executes a machine learning process related to a break.

Another aspect of the present invention is a work process discriminating system that discriminates a work process in a work using a control device that controls an industrial machine, and uses a sensor to detect the operation history information of the control device and the peripheral state of the industrial machine. The data acquisition unit that acquires data including at least one of the detected machine peripheral information and the data acquired by the data acquisition unit are analyzed to separate at least one of the operation history information and the machine peripheral information from the work process. It is a work process discrimination system including a machine learning device that executes the machine learning process according to the above.

According to one aspect of the present invention, it becomes possible to determine the work content of the worker in the state where the machine is "stopped" without bothering the worker.

It is a schematic hardware block diagram of the work process discriminating apparatus by one Embodiment. It is a schematic functional block diagram of the work process discriminating apparatus according to 1st Embodiment. It is a figure explaining the operation of the work extraction part. It is a figure explaining the operation of the feature extraction unit. It is a schematic functional block diagram of the work process discriminating apparatus according to 2nd Embodiment. It is a figure explaining the determination result of a work process. It is a schematic functional block diagram of the modification of the work process discriminating apparatus according to 2nd Embodiment. It is a schematic functional block diagram of the work process discriminating apparatus according to 3rd Embodiment. It is a schematic functional block diagram of the work process discrimination system by another embodiment. This is an example of displaying the operating status of an industrial machine managed by an operation management system based on the conventional technology.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.
FIG. 1 is a schematic hardware configuration diagram showing a main part of a work process discriminating device according to an embodiment of the present invention. The work process discriminating device 1 of the present invention can be implemented as, for example, a control device for controlling an industrial machine. Further, the work process determination device 1 of the present invention includes a personal computer attached to a control device for controlling an industrial machine, a personal computer connected to the control device via a wired / wireless network, a cell computer, a fog computer, and a cloud server. Can be implemented on top of. In this embodiment, an example in which the work process determination device 1 is mounted on a personal computer connected to a control device for controlling an industrial machine via a network is shown.

The CPU 11 included in the work process determination device 1 according to the present embodiment is a processor that controls the work process determination device 1 as a whole. The CPU 11 reads the system program stored in the ROM 12 via the bus 22 and controls the entire work process determination device 1 according to the system program. Temporary calculation data, display data, various data input from the outside, and the like are temporarily stored in the RAM 13.

The non-volatile memory 14 is composed of, for example, a memory backed up by a battery (not shown), an SSD (Solid State Drive), or the like, and the storage state is maintained even when the power of the work process determination device 1 is turned off. In the non-volatile memory 14, data read from the external device 72 via the interface 15, data input via the input device 71, data acquired from the control device 3, the sensor 6 or the like via the interface 20, etc. Is memorized. The data stored in the non-volatile memory 14 may be expanded in the RAM 13 at the time of execution / use. Further, various system programs such as a known analysis program are written in the ROM 12 in advance.

The interface 15 is an interface for connecting the CPU 11 of the work process determination device 1 and an external device 72 such as a USB device. From the external device 72 side, for example, data acquired by another industrial machine or the like can be read. Further, the data or the like processed in the work process determination device 1 can be stored in the external storage means via the external device 72.

The interface 20 is an interface for connecting the CPU 11 of the work process determination device 1 and the wired or wireless network 5. A control device 3, a fog computer, a cloud server, and the like are connected to the network 5, and data is exchanged with each other with the work process determination device 1. Sensors 6 such as a camera, a sound sensor, a vibration sensor, and a proximity sensor are installed around the industrial machine 4 controlled by the control device 3, so that information around the industrial machine 4 can be observed. The interface 20 acquires operation information for the control device 3 and information around the industrial machine 4 via the network 5 and passes the information to the CPU 11.

On the display device 70, each data read on the memory, data obtained as a result of executing a program or the like, or the like is output and displayed via the interface 17. Further, the input device 71 composed of a keyboard, a pointing device, and the like receives commands, data, and the like based on operations on the work process determination device 1 via the interface 18 and passes them to the CPU 11.

The interface 21 is an interface for connecting the work process determination device 1 and the machine learning device 100. The machine learning device 100 stores a processor 101 that controls the entire machine learning device 100, a ROM 102 that stores a system program and the like, a RAM 103 that temporarily stores each process related to machine learning, a learning model, and the like. The non-volatile memory 104 used for the above is provided. The machine learning device 100 can observe each information (operation history information of the control device 3, peripheral information of the industrial machine 4, etc.) that can be acquired by the work process determination device 1 via the interface 21. Further, the work process determination device 1 acquires the information output from the machine learning device 100 via the interface 17, stores it in the non-volatile memory 14, or displays it on the display device 50.

FIG. 2 shows a schematic block diagram of the functions provided by the work process discriminating device 1 according to the first embodiment of the present invention. Each function of the work process discriminating device 1 according to the present embodiment is obtained by the CPU 11 included in the work process discriminating device 1 shown in FIG. 1 executing a system program and controlling the operation of each part of the work process discriminating device 1. It will be realized.

The work process determination device 1 of the present embodiment includes a data acquisition unit 110, a learning unit 106, and a display unit 120. Further, the RAM 13 to the non-volatile memory 14 of the work process determination device 1 are provided with an acquisition data storage unit 200 as an area for storing data acquired from the input device 71, the external device 72, the control device 3, and the like. ing. Further, the RAM 103 to the non-volatile memory 104 of the machine learning device included in the work process discriminating device 1 are provided with a learning model storage unit 220 as an area for storing the learning model created by the learning unit 106 in advance.

The data acquisition unit 110 executes a system program read from the ROM 12 by the CPU 11 included in the work process determination device 1 shown in FIG. 1, and mainly performs arithmetic processing using the RAM 13 and the non-volatile memory 14 by the CPU 11, and the interface 15. It is realized by performing the input control process using 18 or 20. The data acquisition unit 110 acquires data such as operation history information of the control device 3 by the operator and machine peripheral information of the industrial machine 4 detected by the sensor 6. When the data acquired by the data acquisition unit 110 is operation history information, the time when each operation included in the operation history is performed is associated and stored in the acquisition data storage unit 200. When the data acquired by the data acquisition unit 110 is the machine peripheral information detected by the sensor 6, the time when the machine peripheral information is detected is associated and stored in the acquired data storage unit 200. The operation history information may store a single button operation or a pointing device operation as one unit operation, but has meaning in the work such as "change of tool offset" and "program operation". It is desirable that a predetermined operation group is collectively stored as one unit operation. In addition, the machine peripheral information includes the standing position of the worker (which equipment is near the industrial machine 4, the operation panel of the control device 3, the work table, etc.), the tool holder, the machine door, etc., and the periphery of the industrial machine 4. It is desirable to store the operating state of the device, the sound around the industrial machine 4, and the like as a unit of information that each state has changed. The data acquisition unit 110 may acquire data directly from the control device 3 via the network 5. The data acquisition unit 110 may acquire data that has already been acquired and stored by an external device 72, a fog computer (not shown), a cloud server, or the like.

The learning unit 106 executes a system program read from the ROM 102 by the processor 101 of the machine learning device 100 included in the work process discriminating device 1 shown in FIG. 1, and is mainly calculated by the processor 101 using the RAM 103 and the non-volatile memory 104. It is realized by processing. The learning unit 106 according to the present embodiment performs unsupervised learning based on data acquired by the data acquisition unit 110 and stored in the acquired data storage unit 200, such as operation history information and machine peripheral information. The learning unit 106 generates a learning model that learns the correlation between the operation history information and the machine peripheral information and the division of the work process by performing unsupervised learning, and stores it in the learning model storage unit 220. The learning unit 106 according to the present embodiment includes a work extraction unit 107, a feature extraction unit 108, and an evaluation formula creation unit 109.

The work extraction unit 107 analyzes the data stored in the acquired data storage unit 200, and extracts the work indicated by the data such as the operation history information and the machine peripheral information. The work extraction unit 107 creates vector data having data values such as operation history information and machine peripheral information at the same time as elements. The work extraction unit 107 may create one vector data from each set of data values when any of the data values changes with respect to the data values such as the operation history information and the machine peripheral information. Further, the work extraction unit 107 may create one vector data from a set of data values at the timing when a predetermined operation is detected. FIG. 3 shows an example of vector data created by the work extraction unit 107. In the example of FIG. 3, for example, the vector data v2 is created from a set of operation history, worker position, work position, tool holder operation, and sound data values around the machine at the timing when the work is detected. It is a thing. Further, the vector data v3 is created from a set of data values of the operation history, the position of the worker, the position of the work, the movement of the tool holder, and the sound around the machine at the timing when the movement of the tool holder is detected. is there. Each vector data is data indicating work by an operator at a predetermined timing.

The feature extraction unit 108 applies a known cluster analysis technique to the vector data created by the work extraction unit 107 to create a cluster of vector data. Then, the characteristics of each work are extracted from the created cluster. FIG. 4 is a diagram showing an example of a cluster created by the feature extraction unit 108. Although FIG. 4 shows an example of a cluster created in a vector space having the operation history, the position of the worker, and the sound around the machine as each element, the actual data such as the operation history information and the machine peripheral information are obtained. It becomes a vector space of the dimension of the number of kinds. By creating such a cluster, it can be analyzed that the vector data belonging to the cluster shows the work performed constantly, and the vector data not belonging to the cluster shows the work unsteady. Further, when there are a predetermined number or more temporal transitions between the vector data belonging to the cluster, the transitions between them can be analyzed as a work process. Then, the feature extraction unit 108 can extract the element values of the vector data that have changed between the cluster before the work process and the cluster after the work process as the features that divide the work process. ..

The evaluation formula creation unit 109 creates an evaluation formula for the work that divides the work process based on the feature that divides the work process extracted by the feature extraction unit 108. The evaluation formula creation unit 109 can be defined as an expression that highly evaluates the change in the data value or the predetermined operation at the end of the work process analyzed by the feature extraction unit 108. For example, the evaluation formula creation unit 109 creates the following equation 1 as an evaluation formula. In the equation 1, α1 to αn are weighting coefficients, and the statement (IF to THEN to ELSE) described after the weighting coefficient becomes 1 when a predetermined value appears in a predetermined element of the vector data. It means a function.

In the example of the equation 1, the evaluation formula creation unit 109 sets the weight coefficient related to the element value of the vector data extracted by the work extraction unit 107 as a feature that divides the work process as a high weight, and sets the other weight coefficients as a low weight. Create the evaluation formula. The evaluation formula creation unit 109 stores the created evaluation formula in the learning model storage unit 220.

The display unit 120 executes a system program read from the ROM 12 by the CPU 11 included in the work process determination device 1 shown in FIG. 1, and mainly uses the arithmetic processing by the CPU 11 using the RAM 13 and the non-volatile memory 14 and the interface 17. It is realized by performing the input control processing that has been performed. The display unit 120 displays the cluster created by the feature extraction unit 108 and the evaluation formula created by the evaluation formula creation unit 109 on the display device 70. The evaluation formula or the like displayed by the display unit 120 may be modified or the like based on the operation of the input device 71, for example.

The work process determination device 1 according to the present embodiment having the above configuration analyzes data such as operation history information and machine peripheral information collected from the control device 3 that controls the industrial machine 4, and determines the division of the work process. Create an evaluation formula for this as a learning model. When creating an evaluation formula as a learning model, it is desirable to use a large amount of data obtained from daily work in a factory or the like. By using this evaluation formula, even when the industrial machine is not being processed, it is possible to automatically determine the division of the worker's work process without bothering the worker's hands. Become.

FIG. 5 shows a schematic block diagram of the functions provided by the work process discriminating device 1 according to the second embodiment of the present invention. Each function of the work process discriminating device 1 according to the present embodiment is obtained by the CPU 11 included in the work process discriminating device 1 shown in FIG. 1 executing a system program and controlling the operation of each part of the work process discriminating device 1. It will be realized.

The work process determination device 1 of the present embodiment includes a data acquisition unit 110, a work process determination unit 112, and a display unit 120. Further, the RAM 13 to the non-volatile memory 14 of the work process determination device 1 are provided with an acquisition data storage unit 200 as an area for storing data acquired from the control device 3 or the like in advance. Further, in the RAM 103 to the non-volatile memory 104 of the machine learning device included in the work process determination device 1, a learning model storage unit 220 is prepared in advance as an area for storing the learning model created by the learning unit 106 according to the first embodiment. ing.

The data acquisition unit 110 according to the present embodiment has the same functions as the data acquisition unit 110 according to the first embodiment.

The work process determination unit 112 analyzes data such as operation history information and machine peripheral information acquired by the data acquisition unit 110 using the learning model stored in the learning model storage unit 220, and determines the division of the work process. .. The work process determination unit 112 creates vector data having data values such as operation history information and machine peripheral information at the same time as elements for data such as operation history information and machine peripheral information acquired by the data acquisition unit. Next, the work process determination unit 112 substitutes the created vector data into the evaluation formula stored in the learning model storage unit 220 to calculate the evaluation value. Then, when the calculated evaluation value is equal to or higher than a predetermined threshold value, the time when the vector data is detected is determined as a delimiter of the work process.

Then, as illustrated in FIG. 6, the display unit 120 displays each work process by the operator on the display device 70 so that the division of the work process determined by the work process determination unit 112 can be grasped. When each work process is selected by operating the input device 71, the display unit 120 sets the information related to the delimiter when entering the work process (delimiter based on the change of any element value of the vector data). Whether it was judged or not) may be displayed on the screen.

The work process discriminating device 1 according to the present embodiment having the above configuration uses the learning model generated by the work process discriminating device 1 according to the first embodiment, even when the industrial machine is not processed and operated. It is possible to determine the division of the work process of the worker. The site manager who sees the display illustrated in FIG. 6 confirms the division of each work process, and what kind of work is performed in each work process according to the contents (for example, tool change). It is possible to determine whether it is, whether it is dimensioning, etc.), and it is also possible to easily set (meaning) information on the work process as needed.

As a modification of the work process determination device 1 according to the present embodiment, rules for defining the relationship between typical work process divisions and work process contents are defined in advance, and work process information is automatically set to some extent. It may be configured to do so. For example, as illustrated in FIG. 7, the RAM 13 to the non-volatile memory 14 included in the work process determination device 1 are provided with information related to delimiters when the work process is entered (based on changes in any element value of vector data). A work process rule storage unit 210 for storing a rule defining the relationship between the work process and the work process (whether it was determined to be a break, etc.) was provided, and a typical rule (for example, the tool holder was rotated at the work process break). In this case, one or more work processes for changing tools, etc.) are defined. Then, when the work process determination unit 112 determines the division of the work process, the work process rule storage unit 210 is referred to, and if any of the rules is met, the work process is defined according to the rule. You can do it. By providing such a configuration, even if it is difficult to discriminate all the work processes, it is possible to automatically give meaning to a typical work process.

FIG. 8 shows a schematic block diagram of the functions provided by the work process discriminating device 1 according to the third embodiment of the present invention. Each function of the work process discriminating device 1 according to the present embodiment is obtained by the CPU 11 included in the work process discriminating device 1 shown in FIG. 1 executing a system program and controlling the operation of each part of the work process discriminating device 1. It will be realized.

The work process discriminating device 1 of the present embodiment includes a data acquisition unit 110, a learning unit 106, and a display unit 120, similarly to the work process discriminating device 1 according to the first embodiment. Further, the RAM 13 to the non-volatile memory 14 of the work process determination device 1 are provided with an acquisition data storage unit 200 as an area for storing data acquired from the input device 71, the external device 72, the control device 3, and the like. ing. Further, the RAM 103 to the non-volatile memory 104 of the machine learning device included in the work process discriminating device 1 are provided with a learning model storage unit 220 as an area for storing the learning model created by the learning unit 106 in advance.

The data acquisition unit 110 according to the present embodiment acquires data such as operation history information of the control device 3 by the operator and machine peripheral information of the industrial machine 4 detected by the sensor 6. Further, the data acquisition unit 110 according to the present embodiment outputs information related to the division of the work process from the input device 71 to the data such as the operation history information of the control device 3 and the machine peripheral information of the industrial machine 4 detected by the sensor 6. get. The information related to the work process delimiter acquired by the data acquisition unit 110 may include time information used as the work process delimiter. Further, the information related to the division of the work process acquired by the data acquisition unit 110 may include information indicating the work content in the work process. The information related to the division of the work process acquired by the data acquisition unit 110 is stored in the acquisition data storage unit 200 in association with data such as operation history information and machine peripheral information.

The learning unit 106 according to the present embodiment is supervised learning based on data such as operation history information, machine peripheral information, etc. acquired by the data acquisition unit 110 and stored in the acquired data storage unit 200, and information related to division of work processes. I do. The learning unit 106 generates a learning model that learns the correlation between the operation history information and the machine peripheral information and the division of the work process by performing supervised learning, and stores it in the learning model storage unit 220. The learning unit 106 according to the present embodiment includes a work extraction unit 107, a feature extraction unit 108, and an evaluation formula creation unit 109.

The work extraction unit 107 according to the present embodiment analyzes the data stored in the acquired data storage unit 200, and extracts the work indicated by the data such as the operation history information and the machine peripheral information. The work extraction unit 107 according to the present embodiment performs vector data for data such as operation history information and machine peripheral information associated with information related to the division of work processes by the same processing as the work extraction unit 107 according to the first embodiment. By creating, work is extracted.

The feature extraction unit 108 according to the present embodiment extracts the features of each work from the vector data created by the work extraction unit 107. Information related to the division of the work process is associated with the vector data from which the feature extraction unit 108 according to the present embodiment extracts the work feature. The feature extraction unit 108 according to the present embodiment extracts the element values of the vector data that have changed before and after the division of the work process as the feature that divides the work process for the work process of the same work content.

The evaluation formula creation unit 109 creates an evaluation formula for the work that divides the work process based on the feature that divides the work process extracted by the feature extraction unit 108. The evaluation formula creating unit 109 according to the present embodiment has the same function as the evaluation formula creating unit 109 according to the first embodiment.

The display unit 120 displays the cluster created by the feature extraction unit 108 and the evaluation formula created by the evaluation formula creation unit 109 on the display device 70. The evaluation formula or the like displayed by the display unit 120 may be modified or the like based on the operation of the input device 71, for example.

The work process determination device 1 according to the present embodiment having the above configuration inputs information related to the work process, for example, to the collected data such as operation history information and machine peripheral information. Then, using the input information related to the work process, data such as operation history information and machine peripheral information is analyzed, and an evaluation formula for determining the division of the work process is created as a learning model. In addition, since the information related to the work process input by the administrator is used, it is possible to create a learning model with a higher system than the learning model created by the work process discriminating device 1 according to the first embodiment, although it takes time and effort. There is expected. By using this evaluation formula, even when the industrial machine is not being processed, it is possible to automatically determine the division of the worker's work process without bothering the worker's hands. Become.

Although one embodiment of the present invention has been described above, the present invention is not limited to the examples of the above-described embodiments, and can be implemented in various embodiments by making appropriate changes.
For example, in the above-described embodiment, an example in which the configuration required for discriminating the work process is mounted on one work process discriminating device 1 is shown, but the present invention shows the present invention via a network as illustrated in FIG. The work process discriminating system 500 may be configured in which the configurations required for discriminating the work process are distributed and arranged on a plurality of interconnected devices. In the example of FIG. 9, the learning unit 106 and the learning model storage unit 220 are arranged on the cloud server 8, and the work process determination unit 112 is arranged on the fog computer 7. Although not shown, the cloud server 8 and the fog computer 7 each include a data acquisition unit 110. The learning unit 106 can collect data such as operation history information and machine peripheral information from control devices 3 installed at many sites via a network, and generate a learning model based on the large amount of collected data. it can. Further, the work process determination unit 112 can acquire a learning model shared by the cloud server 8 via the network and determine the work process in each control device 3. The method of arranging the functions in a distributed manner is not limited to the example of FIG.

1 Work process discriminator 3 Control device 4 Industrial machinery 5 Network 6 Sensor 7 Fog computer 8 Cloud server 9 Cell 11 CPU
12 ROM
13 RAM
14 Non-volatile memory 15, 17, 18, 20 Interface 22 Bus 70 Display device 71 Input device 72 External device 100 Machine learning device 101 Processor 102 ROM
103 RAM
104 Non-volatile memory 106 Learning unit 107 Work extraction unit 108 Feature extraction unit 109 Evaluation formula creation unit 112 Work process discrimination unit 110 Data acquisition unit 200 Acquisition data storage unit 210 Work process rule storage unit 220 Learning model storage unit

Claims (8)

It is a work process discriminating device that discriminates the work process in the work using the control device that controls the industrial machine.
A data acquisition unit that acquires data including at least one of the operation history information of the control device and the machine peripheral information detected by the sensor in the peripheral state of the industrial machine.
A machine learning device that analyzes the data acquired by the data acquisition unit and executes machine learning processing related to at least one of the operation history information and the machine peripheral information and the division of the work process.
Work process discriminating device equipped with. The machine learning device
A learning unit that analyzes the data acquired by the data acquisition unit and generates a learning model that learns the correlation between at least one of the operation history information and the machine peripheral information and the division of the work process.
The work process discriminating device according to claim 1. The learning unit performs unsupervised learning using the data acquired by the data acquisition unit, and learns the correlation between at least one of the operation history information and the machine peripheral information and the division of the work process. To generate,
The work process discriminating device according to claim 2. The learning unit
A work extraction unit that extracts data related to the work from the data acquired by the data acquisition unit, and a work extraction unit.
A feature extraction unit that performs cluster analysis of data related to the work and extracts the characteristics of the division of the work process.
An evaluation formula creation unit that creates an evaluation formula based on the characteristics of the division of the work process,
The work process discriminating device according to claim 3. The data acquisition unit further acquires information related to the division of the work process, and obtains information.
The learning unit performs supervised learning using the data acquired by the data acquisition unit, and learns the correlation between at least one of the operation history information and the machine peripheral information and the division of the work process. To generate,
The work process discriminating device according to claim 2. The learning unit
A work extraction unit that extracts data related to the work from the data acquired by the data acquisition unit, and a work extraction unit.
A feature extraction unit that extracts the features of the division of the work process from the data related to the work, and
An evaluation formula creation unit that creates an evaluation formula based on the characteristics of the division of the work process,
The work process discriminating device according to claim 5. The machine learning device
A learning model storage unit that stores a learning model that has learned the correlation between at least one of the operation history information and the machine peripheral information and the division of the work process.
Based on the data acquired by the data acquisition unit, the work process determination unit that executes the determination process of the division of the work process using the learning model stored in the learning model storage unit, and the work process determination unit.
The work process discriminating device according to claim 1. It is a work process discrimination system that discriminates the work process in the work using the control device that controls the industrial machine.
A data acquisition unit that acquires data including at least one of the operation history information of the control device and the machine peripheral information detected by the sensor in the peripheral state of the industrial machine.
A machine learning device that analyzes the data acquired by the data acquisition unit and executes machine learning processing related to at least one of the operation history information and the machine peripheral information and the division of the work process.
Work process discrimination system equipped with.

Images