Abnormal determination method and production management system

Abstract

This abnormality determining method, for a production control system for controlling a production line including a first production device, a second production device and a third production device, includes: acquiring at least first operation status data for the first production device and third operation status data for the third production device, among the first operation status data, second operation status data for the second production device, and the third operation status data (S11); if it is determined that the second operation status data have not been acquired (No in S13), predicting a dummy operating time corresponding to a planned production quantity for the second production device, and generating dummy operation status data including the planned production quantity and the dummy operating time (S14); performing abnormality determination processing for an overall production process on the basis of the first operation status data, the third operation status data, and the dummy operation status data (S16); and outputting determination result information indicating the result of the abnormality determination processing so as to be displayed on a display device included in the production control system (S19).

Description

Technical Field

[0001] The present disclosure relates to an abnormality determination method and a production management system.

Background Art

[0002] In a production site such as a factory, in order to quickly respond when an abnormality occurs, it is required to appropriately manage the operating status of equipment. When using machine learning (AI) to manage the status of various devices such as equipment, if input data exceeding the allowable range is input, or if input data is not input at all, it becomes impossible to accurately determine an abnormality.

[0003] On the other hand, for example, Patent Document 1 discloses a state determination device that performs guard processing to bring input data closer to the allowable range when data outside the allowable range is input. Further, Patent Document 2 discloses a communication method of an equipment operation monitoring device that transfers data by two types of communication methods so that data loss does not occur.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, in the state determination device disclosed in Patent Document 1, guard processing cannot be performed if input data is not input. Further, in the communication method disclosed in Patent Document 2, although the possibility of data loss may be reduced, if data loss occurs, an abnormality cannot be determined.

[0006] Therefore, the present disclosure provides an abnormality determination method and a production management system capable of determining an abnormality with high accuracy.

Means for Solving the Problems

[0007] An abnormality determination method according to an aspect of the present disclosure is an abnormality determination method in a production management system that manages a production line including a first production device corresponding to a first process, a second production device corresponding to a second process following the first process, and a third production device corresponding to a third process following the second process, the method including: (i) acquiring, via a network, at least (i) the first operation status data including the first production quantity and the first operation time corresponding to each production in the first production device and (iii) the third operation status data including the third production quantity and the third operation time corresponding to each production in the third production device; when it is determined, based on the first operation time and the third operation time, that the second operation status data has not been acquired, predicting a dummy operation time corresponding to the planned production quantity in the second production device based on the first operation status data and the third operation status data, generating dummy operation status data corresponding to the second operation status data including the planned production quantity and the dummy operation time, performing an abnormality determination process for the entire production process including the first process to the third process based on the first operation status data, the third operation status data, and the dummy operation status data, and outputting determination result information representing the result of the abnormality determination process to be displayed on a display device included in the production management system.

[0008] An abnormality determination method according to another aspect of the present disclosure is an abnormality determination method in a production management system that manages a production line including a first production device corresponding to a first process, a second production device corresponding to a second process following the first process, and a third production device corresponding to a third process following the second process. The method includes: (i) acquiring, via a network, first operation status data including a first production quantity and a first operation time corresponding to each production in the first production device, and (ii) third operation status data including a third production quantity and a third operation time corresponding to each production in the third production device. Based on the first operation status data and the third operation status data, predicting a dummy operation time corresponding to a planned production quantity in the second production device, generating dummy operation status data including the planned production quantity and the dummy operation time, performing an abnormality determination process for the entire production process including the first process to the third process based on the first operation status data, the third operation status data, and the dummy operation status data, and outputting determination result information representing the result of the abnormality determination process to be displayed on a display device included in the production management system.

[0009] An abnormality determination method according to another aspect of the present disclosure is an abnormality determination method in a production management system that manages a production line including a first production device corresponding to a first process and a second production device corresponding to a second process that is the final process following the first process. The method includes: (i) acquiring at least the first operation status data including the first production quantity and the first operation time corresponding to each production in the first production device, and (ii) acquiring at least the first operation status data among the second operation status data including the second production quantity and the second operation time corresponding to each production in the second production device via a network. When it is determined based on the first operation time that the second operation status data has not been acquired, predicting a dummy operation time corresponding to the planned production quantity in the second production device based on the first operation status data, generating dummy operation status data corresponding to the second operation status data including the planned production quantity and the dummy operation time, performing an abnormality determination process for the entire production process including the first process and the second process based on the first operation status data and the dummy operation status data, and outputting determination result information representing the result of the abnormality determination process to be displayed on a display device included in the production management system.

[0010] An abnormality determination method according to another aspect of the present disclosure is an abnormality determination method in a production management system that manages a production line including a first production device corresponding to a first process that is a leading process and a second production device corresponding to a second process following the first process, the method comprising: (i) first operation status data including a first production quantity in the first production device and a first operation time corresponding to each production, and (ii) second operation status data including a second production quantity in the second production device and a second operation time corresponding to each production. At least the second operation status data among them is acquired via a network. When it is determined that the first operation status data has not been acquired based on the second operation time, a dummy operation time corresponding to a planned production quantity in the first production device is predicted based on the second operation status data, and dummy operation status data corresponding to the first operation status data including the planned production quantity and the dummy operation time is generated. Based on the dummy operation status data and the second operation status data, an abnormality determination process for the entire production process including the first process and the second process is performed, and determination result information representing the result of the abnormality determination process is output to be displayed on a display device included in the production management system.

[0011] A production management system according to an aspect of the present disclosure is a production management system that manages a production line including a first production device corresponding to a first process, a second production device corresponding to a second process following the first process, and a third production device corresponding to a third process following the second process, the production management system acquiring at least (i) the first operation status data including the first production quantity and the first operation time corresponding to each production in the first production device and (iii) the third operation status data including the third production quantity and the third operation time corresponding to each production in the third production device via a network, and when it is determined that the second operation status data has not been acquired based on the first operation time and the third operation time, predicting a dummy operation time corresponding to the planned production quantity in the second production device based on the first operation status data and the third operation status data, generating dummy operation status data corresponding to the second operation status data including the planned production quantity and the dummy operation time, performing an abnormality determination process for the entire production process including the first process to the third process based on the first operation status data, the third operation status data, and the dummy operation status data, and outputting determination result information representing the result of the abnormality determination process to be displayed on a display device included in the production management system.

[0012] A production management system according to another aspect of the present disclosure is a production management system that manages a production line including a first production device corresponding to a first process, a second production device corresponding to a second process following the first process, and a third production device corresponding to a third process following the second process, the production management system obtaining, via a network, (i) first operation status data including a first production quantity and a first operation time corresponding to each production in the first production device, and (ii) third operation status data including a third production quantity and a third operation time corresponding to each production in the third production device, predicting a dummy operation time corresponding to a planned production quantity in the second production device based on the first operation status data and the third operation status data, generating dummy operation status data including the planned production quantity and the dummy operation time, performing an abnormality determination process for the entire production process including the first process to the third process based on the first operation status data, the third operation status data, and the dummy operation status data, and outputting determination result information representing the result of the abnormality determination process to be displayed on a display device included in the production management system.

[0013] Further, an aspect of the present disclosure can be realized as a program that causes a computer to execute the above-described abnormality determination method. Alternatively, an aspect of the present disclosure can also be realized as a computer-readable non-transitory recording medium storing the program.

Advantages of the Invention

[0014] According to the present disclosure, an abnormality can be determined with high accuracy.

Brief Description of the Drawings

[0015]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Embodiments for Carrying Out the Invention

[0016] (Summary of the Present Disclosure) An abnormality determination method according to an aspect of the present disclosure is an abnormality determination method in a production management system that manages a production line including a first production device corresponding to a first process, a second production device corresponding to a second process following the first process, and a third production device corresponding to a third process following the second process, including: (i) first operation status data including a first production quantity in the first production device and a first operation time corresponding to each production; (ii) second operation status data including a second production quantity in the second production device and a second operation time corresponding to each production; and (iii) third operation status data including a third production quantity in the third production device and a third operation time corresponding to each production. At least (i) the first operation status data and (iii) the third operation status data among them are acquired via a network. When it is determined that the second operation status data has not been acquired based on the first operation time and the third operation time, a dummy operation time corresponding to a planned production quantity in the second production device is predicted based on the first operation status data and the third operation status data, dummy operation status data corresponding to the second operation status data including the planned production quantity and the dummy operation time is generated, and based on the first operation status data, the third operation status data, and the dummy operation status data, an abnormality determination process for the entire production process including the first process to the third process is performed, and determination result information representing the result of the abnormality determination process is output to be displayed on a display device included in the production management system.

[0017] As described above, in a production line including a first production device, a second production device, and a third production device, if any of the production devices malfunctions, the overall operation deteriorates and the production volume decreases. If an abnormality determination process is performed for each individual process and the cause is determined for each process, the determination time becomes long and a large amount of memory is required.

[0018] On the other hand, in the case of a production line in which the first production device, the second production device, and the third production device are connected, it is possible to identify the process in which an abnormality has occurred by performing an abnormality determination process for the entire production process including the first process, the second process, and the third process. Also, since the processing volume is reduced, it can be determined in a shorter period of time.

[0019] However, if there is first operation status data corresponding to the first process, second operation data corresponding to the second process, and third operation status data corresponding to the third process, if any of the data is missing, the abnormality determination process for the entire production process cannot be performed. Such data loss may occur, for example, due to the status of the network that communicates the first operation status data, the second operation status data, and the third operation status data.

[0020] Therefore, in the abnormality determination method according to one aspect of the present disclosure, as described above, when it is determined that there is data loss, corresponding dummy operation status data is generated. Thereby, even when data loss occurs, the abnormality determination process for the entire production process can be continued.

[0021] The dummy operation status data is generated based on the operation status data of the processes before and after the process in which data loss has occurred. For example, the number of products produced per operation time in the process where data loss has occurred is estimated based on the operation status data of the surrounding processes.

[0022] Thereby, even when operation status data loss corresponding to any process occurs due to the network status or the like, the abnormality determination process for the entire production process can be continued, and the abnormality can be determined in a short time without sacrificing accuracy.

[0023] Further, for example, when outputting the determination result information, it may be output that the abnormality determination process was performed using the dummy operation status data in the second process.

[0024] Thereby, by notifying that the abnormality determination process was performed using the dummy operation status data, it can be found that there was a problem in data transfer, which can lead to improvement.

[0025] Further, for example, the abnormality determination process may be a process of determining the presence or absence of an abnormality in the entire production process based on the total number of products produced during the total operation time in the entire production process.

[0026] As a result, abnormalities in the entire production process can be accurately determined.

[0027] Also, for example, the abnormality determination process may be a process of determining the presence or absence of an abnormality in each process in the entire production process based on the number of products produced during the operation time of the process.

[0028] As a result, abnormalities in each process can be accurately determined, and the factors causing the abnormalities can be accurately identified.

[0029] Also, for example, the result of the abnormality determination process may include that there is no abnormality in the production process.

[0030] As a result, the presence or absence of an abnormality can be clarified.

[0031] Also, for example, in the production line, the first production device, the second production device, and the third production device may be connected by a belt conveyor.

[0032] Also, a production management system according to an aspect of the present disclosure is a production management system that manages a production line including a first production device corresponding to a first process, a second production device corresponding to a second process following the first process, and a third production device corresponding to a third process following the second process, and acquires at least (i) the first operation status data including the first production quantity and the first operation time corresponding to each production in the first production device and (iii) the third operation status data including the third production quantity and the third operation time corresponding to each production in the third production device via a network. When it is determined that the second operation status data has not been acquired based on the first operation time and the third operation time, a dummy operation time corresponding to the planned production quantity in the second production device is predicted based on the first operation status data and the third operation status data, dummy operation status data corresponding to the second operation status data including the planned production quantity and the dummy operation time is generated, and based on the first operation status data, the third operation status data, and the dummy operation status data, an abnormality determination process for the entire production process including the first process to the third process is performed, and determination result information indicating the result of the abnormality determination process is output to be displayed on a display device included in the production management system.

[0033] Accordingly, the same effect as the above-described abnormality determination method can be obtained. That is, even when there is a lack of operation status data corresponding to any process, the abnormality determination process for the entire production process can be continued, and the abnormality can be determined in a short time without sacrificing accuracy.

[0034] Moreover, an abnormality determination method according to another aspect of the present disclosure is an abnormality determination method in a production management system that manages a production line including a first production device corresponding to a first process, a second production device corresponding to a second process following the first process, and a third production device corresponding to a third process following the second process, the method comprising: (i) acquiring, via a network, first operation status data including a first production quantity and a first operation time corresponding to each production in the first production device, and (ii) third operation status data including a third production quantity and a third operation time corresponding to each production in the third production device; predicting a dummy operation time corresponding to a planned production quantity in the second production device based on the first operation status data and the third operation status data; generating dummy operation status data including the planned production quantity and the dummy operation time; performing an abnormality determination process for the entire production process including the first process to the third process based on the first operation status data, the third operation status data, and the dummy operation status data; and outputting determination result information representing the result of the abnormality determination process to be displayed on a display device included in the production management system.

[0035] Thereby, dummy data can be generated instead of data that is not acquired not only in the case of data loss but also in the case where there is no plan to acquire data. Therefore, an abnormality determination process for the entire production process can be performed, and an abnormality can be determined in a short time without sacrificing accuracy.

[0036] Further, for example, when outputting the determination result information, it may be output that the abnormality determination process has been performed using the dummy operation status data in the second process.

[0037] Thereby, by notifying that the abnormality determination process has been performed using the dummy operation status data, it can be found that there is a problem in data transfer, which can lead to improvement.

[0038] Also, a production management system according to another aspect of the present disclosure is a production management system that manages a production line including a first production device corresponding to a first process, a second production device corresponding to a second process following the first process, and a third production device corresponding to a third process following the second process, wherein (i) first operation status data including a first production quantity and a first operation time corresponding to each production in the first production device, and (ii) third operation status data including a third production quantity and a third operation time corresponding to each production in the third production device are acquired via a network, a dummy operation time corresponding to a planned production quantity in the second production device is predicted based on the first operation status data and the third operation status data, dummy operation status data including the planned production quantity and the dummy operation time is generated, an abnormality determination process for the entire production process including the first process to the third process is performed based on the first operation status data, the third operation status data, and the dummy operation status data, and determination result information representing the result of the abnormality determination process is output to be displayed on a display device included in the production management system.

[0039] Thereby, the same effects as those of the above-described abnormality determination method can be obtained. That is, not only in the case of data loss but also in the case where there is no plan to acquire data, an abnormality determination process for the entire production process can be performed, and an abnormality can be determined in a short time without sacrificing accuracy.

[0040] Also, an abnormality determination method according to another aspect of the present disclosure is an abnormality determination method in a production management system that manages a production line including a first production device corresponding to a first process and a second production device corresponding to a second process that is the final process following the first process. The method includes: (i) acquiring at least the first operation status data including the first production quantity and the first operation time corresponding to each production in the first production device, and (ii) acquiring the second operation status data including the second production quantity and the second operation time corresponding to each production in the second production device via a network. When it is determined that the second operation status data has not been acquired based on the first operation time, predicting a dummy operation time corresponding to the planned production quantity in the second production device based on the first operation status data, generating dummy operation status data corresponding to the second operation status data including the planned production quantity and the dummy operation time, performing an abnormality determination process for the entire production process including the first process and the second process based on the first operation status data and the dummy operation status data, and outputting determination result information representing the result of the abnormality determination process to be displayed on a display device included in the production management system.

[0041] Thereby, even when there is a lack of operation status data corresponding to the final process during the entire production process, the abnormality determination process for the entire production process can be continued, and the abnormality can be determined in a short time without sacrificing accuracy.

[0042] Also, for example, when outputting the determination result information, it may be output that the abnormality determination process has been performed using the dummy operation status data in the second process.

[0043] Thereby, by notifying that the abnormality determination process has been performed using the dummy operation status data, it can be found that there is a problem in data transfer, which can lead to improvement.

[0044] Moreover, an abnormality determination method according to another aspect of the present disclosure is an abnormality determination method in a production management system that manages a production line including a first production device corresponding to a first step which is a leading step and a second production device corresponding to a second step following the first step. The method includes: (i) acquiring at least the second operation status data among the first operation status data including the first production quantity and the first operation time corresponding to each production in the first production device, and (ii) the second operation status data including the second production quantity and the second operation time corresponding to each production in the second production device, via a network. When it is determined based on the second operation time that the first operation status data has not been acquired, predicting a dummy operation time corresponding to the planned production quantity in the first production device based on the second operation status data, generating dummy operation status data corresponding to the first operation status data including the planned production quantity and the dummy operation time, performing an abnormality determination process for the entire production process including the first step and the second step based on the dummy operation status data and the second operation status data, and outputting determination result information representing the result of the abnormality determination process to be displayed on a display device included in the production management system.

[0045] Accordingly, even when there is a lack of operation status data corresponding to the leading step during the entire production process, it is possible to continue the abnormality determination process for the entire production process and determine the abnormality in a short time without sacrificing accuracy.

[0046] Further, for example, when outputting the determination result information, it may be output that the abnormality determination process was performed using the dummy operation status data in the first step.

[0047] Accordingly, by notifying that the abnormality determination process was performed using the dummy operation status data, it can be found that there was a problem in data transfer, which can lead to improvement.

[0048] Hereinafter, embodiments will be specifically described with reference to the drawings.

[0049] Note that the embodiments described below all show comprehensive or specific examples. The numerical values, shapes, materials, components, arrangement positions and connection forms of the components, steps, order of steps, etc. shown in the following embodiments are merely examples and are not intended to limit the present disclosure. In addition, among the components in the following embodiments, the components not described in the independent claims are described as optional components.

[0050] Also, each figure is a schematic diagram and is not necessarily drawn precisely. Therefore, for example, the scales etc. in each figure do not necessarily match. Also, in each figure, substantially the same configuration is denoted by the same reference numeral, and overlapping descriptions are omitted or simplified.

[0051] (Embodiment) [1. Overview of the production management system] First, the overview of the production management system according to this embodiment will be described with reference to FIG. 1.

[0052] FIG. 1 is a diagram showing the configuration of a production management system 1 according to this embodiment. The production management system 1 shown in FIG. 1 is a system that manages a production line including a plurality of production devices. In this embodiment, the production management system 1 manages the equipment group 10. First, the equipment group 10 to be managed by the production management system 1 will be described below.

[0053] Note that in FIG. 1, in order to individually distinguish a plurality of production lines and a plurality of pieces of equipment, for example, different reference numerals are given to each, such as a plurality of production lines 11a and 11b, and a plurality of pieces of equipment 12a_1, 12a_2, and 12b_1. When it is not necessary to distinguish the production line and the equipment in the following description, they are described as the production line 11 and the equipment 12.

[0054] The equipment group 10 includes x production lines 11. x is a natural number of 1 or more.

[0055] Each of the x production lines 11 includes n pieces of equipment 12. n is a natural number greater than or equal to 2. Note that the number of pieces of equipment 12 included in one production line 11 may be different from the number of pieces of equipment 12 included in other production lines 11. Each of the x production lines 11 produces a plurality of products. One product is produced by sequentially performing a plurality of processes. The plurality of processes are, for example, component mounting, processing, assembly, etc., but are not particularly limited. The product is produced by the n pieces of equipment 12 included in the production line 11 sequentially executing the processes assigned to each piece of equipment.

[0056] The equipment 12 is an example of a production device. For example, the equipment 12 is a component mounter, an assembly device, a processing machine, a conveying device, etc. In the example shown in FIG. 1, the n pieces of equipment 12 are connected by a belt conveyor. The work-in-process of the product is sequentially conveyed to the n pieces of equipment 12 by the belt conveyor.

[0057] For example, looking at the production line 11a, the equipment 12a_1 is a production device corresponding to the front-end process. The equipment 12a_n is a production device corresponding to the terminal process. The equipment 12a_2 to 12a_n - 1 are production devices corresponding to the intermediate processes. The equipment 12a_1 to 12a_n produce a product by executing the processes in this order.

[0058] One or more sensors (not shown) are provided in the equipment 12. The sensor measures a value representing the operating status of the equipment 12. For example, the sensor is an image sensor, an infrared sensor, a flow sensor, an ammeter, a pressure gauge, etc., but is not particularly limited. The sensor outputs the measurement result as the operating status data of the corresponding equipment 12.

[0059] The equipment group 10 and the production management system 1 are communicably connected via a network. The communication is wired communication or wireless communication, and the specific communication method is not particularly limited.

[0060] The production management system 1 according to this embodiment acquires the operation status data output by the sensors of each facility 12 in the facility group 10, and determines an abnormality in the production line 11 based on the acquired operation status data. Further, the production management system 1 identifies the cause of the abnormality in the production line 11. Specifically, the production management system 1 identifies the facility 12 that caused the abnormality and the type of the abnormality among the n facilities 12 included in the production line 11 determined to be abnormal. The determination of the abnormality and the identification of the cause of the abnormality are performed using a learning model generated by machine learning. The learning model is a model that outputs a determination result of an abnormality and, in the case of an abnormality, the cause thereof when the operation status data of each facility 12 is input for each production line 11.

[0061] Operation status data is required for the determination of an abnormality. However, due to the network situation, the operation status data may be missing. Alternatively, there may be a case where there is no plan to acquire the operation status data from the beginning, such as when no sensor is installed.

[0062] When the production management system 1 fails to acquire the operation status data due to a deficiency or other factors, the production management system 1 generates dummy data for the operation status data. By inputting the input data including the dummy data into the learning model, the production management system 1 can obtain a determination result of an abnormality and, in the case of an abnormality, the cause thereof. Thus, according to the production management system 1 according to this embodiment, even when the operation status data is not acquired, the abnormality determination process for the entire process of the production line 11 can be continued, and the abnormality can be determined in a short time without sacrificing the accuracy.

[0063] [2. Configuration of Production Management System] Next, the specific configuration of the production management system 1 will be described with reference to FIG. 2.

[0064] FIG. 2 is a block diagram showing the functional configuration of the production management system 1 according to this embodiment. As shown in FIG. 2, the production management system 1 includes an abnormality determination device 2 and an acquisition unit 13. The abnormality determination device 2 includes an input unit 20, a control unit 30, an output unit 40, and a storage unit 50.

[0065] The acquisition unit 13 acquires the operation status data of each facility 12 via a network. The acquisition unit 13 attempts to acquire the operation status data of all the facilities 12 included in the production line 11, but it is not necessary to acquire some of the operation status data.

[0066] The operation status data includes the number of products produced in each facility 12 and the operation time corresponding to each production. The number of products produced in the facility 12 is the number of products produced by the facility 12 during the operation time of the facility 12. In other words, the number of products produced is the output number of the products output by the facility 12.

[0067] Here, the product is an intermediate product, that is, a work-in-progress, except when the facility 12 is the facility at the end of the production line 11. The product produced by the end facility 12 is the final product of the production line 11. Hereinafter, without distinguishing between intermediate products and final products, the description will be made as "products". Also, the material input to the leading facility 12 may be referred to as a product for convenience. The number of products produced in the facility 12 may include not only the output number but also the input number of the products input to the facility 12.

[0068] The operation time corresponding to each production includes the start time and the end time of the process for one product by the facility 12. Alternatively, the operation time corresponding to each production may include the start time and the end time of the process in lot units.

[0069] The operation status data may include other information related to the facility 12 and the product. For example, the operation status data may include the identification information of the production line 11, the identification information of the facility 12 or the process, the identification information of the lot, and the product type information.

[0070] In addition, the operation status data may include information related to the stop of the facility 12. "Stop" includes short-term standby (temporary stop) of the facility called "chocolate stop", stop due to failure, and planned stop for maintenance work, etc. Information related to the stop includes the stop occurrence time, stop end time, and stop cause, etc. The stop occurrence time and stop end time can also be regarded as an example of the operation time.

[0071] The information related to the stop may include at least one of the waiting time for the previous process and the waiting time for the next process. Note that the waiting time for the previous process is the waiting time of the facility that performs the current process between the immediately preceding process and the current process. The waiting time for the next process is the waiting time of the facility that performs the current process between the current process and the immediately following process. Each waiting time can also be calculated, for example, as the difference between the stop end time and the stop occurrence time. Therefore, the operation status data including the waiting time can be regarded as synonymous with the operation status data including the stop occurrence time and the stop end time.

[0072] The acquisition unit 13 is a communication interface that communicates with the sensors provided in each facility 12 via a network. Alternatively, the acquisition unit 13 may be the sensor itself provided in each facility 12.

[0073] The input unit 20 receives operation inputs from users such as administrators. The input unit 20 is various input devices such as a keyboard and a mouse, for example. The operation inputs are, for example, an instruction to start abnormality determination, an instruction to start machine learning, an instruction to display the determination result, etc. The operation inputs may include the designation of the production line 11 to be the target of the abnormality determination process and the designation of the target period of the abnormality determination process.

[0074] The control unit 30 is a processing unit that performs the main processing of the abnormality determination method. The control unit 30 includes, for example, a processor such as a CPU (Central Processing Unit), a non-volatile memory in which a program is stored, a volatile memory that is a temporary storage area for executing the program, and an input / output port. The control unit 30 may be a single computer device, or may be a plurality of computer devices connected via a network. The processing executed by the control unit 30 may be performed, for example, by cloud computing.

[0075] As shown in FIG. 2, the control unit 30 includes a request unit 31, a loss determination unit 32, a calculation unit 33, an abnormality detection unit 34, an evaluation unit 35, and an output processing unit 36.

[0076] The request unit 31 requests the storage unit 50 to transmit the operation status data. For example, the request unit 31 requests the transmission of the operation status data used for the abnormality determination process based on the production line 11 and the target period that are the targets of the abnormality determination process received by the input unit 20. In addition, the request unit 31 requests the loss determination unit 32 to execute the determination process of the non-acquisition of the operation status data transmitted from the storage unit 50.

[0077] The loss determination unit 32 determines the non-acquisition of the operation status data transmitted from the storage unit 50. Specifically, the loss determination unit 32 determines the presence or absence of loss of the operation status data of a predetermined process based on at least one of the operation time included in the operation status data of the previous process and the operation time included in the operation status data of the subsequent process. The loss determination unit 32 outputs the determination result of the loss and the operation status data transmitted from the storage unit 50 to the calculation unit 33.

[0078] When it is determined that the operation status data of a predetermined process has not been acquired, that is, when it is determined by the defect determination unit 32 that the operation status data of the process is missing, the calculation unit 33 generates dummy operation status data for the process. Hereinafter, a process for which the operation status data has not been acquired is referred to as a "defective process". In addition, the process immediately before the defective process is referred to as the "preceding process", and the process immediately after the defective process is referred to as the "subsequent process". The preceding process, the defective process, and the subsequent process are each an example of the first process, the second process, and the third process, respectively, and are continuously performed in this order without intervening other processes.

[0079] Specifically, the calculation unit 33 predicts a dummy operation time corresponding to the planned production quantity in the equipment of the defective process based on at least one of the operation status data of the preceding process and the operation status data of the subsequent process, and generates dummy operation status data including the planned production quantity and the dummy operation time. The dummy operation time is a predicted value corresponding to the operation time of the defective process. For example, the calculation unit 33 predicts a dummy operation time corresponding to the operation time of the defective process based on at least one of the operation time of the preceding process and the operation time of the subsequent process.

[0080] Note that the dummy operation status data may include a dummy waiting time instead of, or in addition to, the planned production quantity. The dummy waiting time is a predicted value of the waiting time in the defective process. In this case, the calculation unit 33 predicts the dummy waiting time in the defective process based on at least one of the waiting time between the preceding process and the defective process in the equipment performing the preceding process and the waiting time between the defective process and the subsequent process in the equipment performing the subsequent process.

[0081] The calculation unit 33 generates dummy operation status data using the model data 52 and the coefficient data 53 stored in the storage unit 50. A specific example of generating the dummy operation status data will be described later.

[0082] Further, the calculation unit 33 may generate a learning model by executing machine learning. The generated learning model is stored in the storage unit 50 as model data 52. Further, the calculation unit 33 may calculate coefficients for generating dummy operation status data by executing machine learning. The calculated coefficients are stored in the storage unit 50 as coefficient data 53.

[0083] The abnormality detection unit 34 performs an abnormality determination process for the entire production process based on the operation status data and the dummy operation status data of each process. When a plurality of production lines 11 are provided, the abnormality determination process is performed for each production line 11. That is, the abnormality detection unit 34 performs an abnormality determination process for the entire production process including all processes from the leading process to the trailing process for the target production line 11. Specifically, the abnormality determination process includes a process of determining the presence or absence of an abnormality in the entire production process based on the total number of products produced during the total operation time in the entire production process. Further, the abnormality determination process may include a process of determining the presence or absence of an abnormality in each process based on the number of products produced during the operation time of the process in the entire production process.

[0084] Note that the abnormality determination process may include a process of determining the presence or absence of an abnormality in the entire production process based on the total waiting time during the total operation time in the entire production process, in addition to or instead of the process using the number of products produced. Further, the abnormality determination process may include a process of determining the presence or absence of an abnormality in each process based on the waiting time during the operation time of the process in the entire production process.

[0085] The evaluation unit 35 performs a process of identifying the cause of the abnormality by evaluating the result of the abnormality determination process. Specifically, the evaluation unit 35 identifies the production line 11 determined to be abnormal. The evaluation unit 35 further identifies the abnormal equipment and its cause among all the equipment included in the production line 11 determined to be abnormal.

[0086] The evaluation unit 35 may further evaluate the dummy operation status data. Specifically, the evaluation unit 35 evaluates the credibility of the dummy operation status data. The higher the credibility of the dummy operation status data representing the actual operation status, the higher the accuracy of the result of the abnormality determination process.

[0087] The output processing unit 36 outputs determination result information representing the result of the abnormality determination process to the output unit 40. The result of the abnormality determination process may include not only the presence of an abnormality but also the absence of an abnormality. The output processing unit 36 may further output the evaluation result by the evaluation unit 35 to the output unit 40. For example, when outputting the determination result information, the output processing unit 36 may output that the abnormality determination process was performed using the dummy operation status data.

[0088] The output unit 40 outputs determination result information representing the result of the abnormality determination process. Specifically, the output unit 40 includes a display unit such as a liquid crystal display or an organic EL display. The display unit displays the determination result information. A display example by the output unit 40 will be described later. The output unit 40 may include an audio output unit in addition to or instead of the display unit.

[0089] The storage unit 50 stores information and data necessary for the processes performed by the production management system 1. The storage unit 50 is a non-volatile storage device such as an HDD (Hard Disk Drive) or an SSD (Solid State Drive). The storage unit 50 may be a plurality of storage devices connected via a network.

[0090] As shown in FIG. 2, the storage unit 50 stores production log data 51, model data 52, and coefficient data 53.

[0091] The production log data 51 is a set of operation status data. FIG. 3 is a diagram showing an example of the production log data 51. As shown in FIG. 3, the production log data 51 includes information on a plurality of items (also called attributes) described in the uppermost row. Specifically, the plurality of items include the production line, process, lot start time, lot end time, operation time, lot number, input quantity, output quantity, product type information, stop occurrence time, stop end time, and stop cause. The plurality of attributes may include the corresponding equipment name instead of the process. Note that the number and types of items included in the production log data 51 are not particularly limited.

[0092] The data (also called records) of each row shown in FIG. 3 corresponds to one stop. For example, the records from the first row to the third row are data representing the operation status of "Process A" on production line 11 of "Line1". The start time of production for the lot with lot number "L001" is "12:00", and the end time for the lot is "15:30". The operation time is "210" minutes. Note that this operation time may be calculated as the difference between the lot end time and the lot start time. The input quantity for the equipment performing "Process A" is "100" units, and the output quantity from the equipment, that is, the production quantity, is "100" units. Since the input quantity and the output quantity are equal, it can be seen that all production was carried out without causing production defects. The product type of the produced product is "Type 01".

[0093] The record on the first line indicates that during the operating hours of Process A on Production Line 11 of "Line1", it stopped at "12:10" due to the stop factor "Stop a" and the stoppage ended at "12:12" and production resumed. Similarly, the record on the second line indicates that it stopped at "12:16" due to the stop factor "Stop b" and the stoppage ended at "12:20" and production resumed. The record on the third line indicates that it stopped at "12:37" due to the stop factor "Waiting" and the stoppage ended at "12:40" and production resumed. Thus, during the operating hours of Process A on Production Line 11 of "Line1", three stoppages have occurred. Note that "Waiting" means a stop to wait for the processing of the process immediately following the target process. "Pre-waiting" means a stop to wait for the processing of the process immediately preceding the target process.

[0094] The operation status data corresponds to the records of the same process on the same production line 11. For example, the records from the first line to the third line are grouped together to form one piece of operation status data. Alternatively, the operation status data may be regarded as one record.

[0095] The model data 52 includes one or more learning models generated by machine learning. The learning model is a production model used for anomaly determination processing. The production model is represented by, for example, the type of probability distribution of the number of products produced during the total operating hours of the entire production process and the values of the parameters. The types of probability distributions are normal distribution, lognormal distribution, 0-excess exponential distribution, gamma distribution, etc. The parameter types of the probability distribution are determined by the type of probability distribution. For example, in the case of a normal distribution, they are the mean μ and the standard deviation σ. The parameter values are generated based on past production results, that is, past operation status data.

[0096] The above learning models may include production models for each facility, which are represented by the type of probability distribution of the number of products produced during the operating time of each facility and the values of the parameters. Also, the one or more learning models may include production models for each cause, which are represented by the type of probability distribution of the downtime for each cause of stoppage during the operating time of each facility and the values of the parameters. At least one of the production model for each facility and the production model for each cause can be used to identify the facility where an abnormality has occurred and the cause of the abnormality.

[0097] Also, the one or more learning models may include a production model represented by the type of probability distribution of the total waiting time during the total operating time of the entire production process and the values of the parameters. This production model can be used for abnormality determination processing instead of the production model based on the number of products produced. Also, the one or more learning models may include production models for each facility, which are represented by the type of probability distribution of the waiting time during the operating time of each facility and the values of the parameters.

[0098] The parameters of the learning model can be obtained based on Bayesian estimation. For example, they can be obtained by sampling methods such as Markov Chain Monte Carlo simulation (MCMC), or by variational inference such as the VB-EM (Variational Bayesian - Expectation Maximization) algorithm.

[0099] The input data at the time of generating the learning model is the operating status data of each process. Specifically, the number of products produced, the operating time, the downtime (waiting time) for each cause, the facility name, and the product type of each process are used as input data. The types of input data used for generating the learning model are the types of data that the dummy operating status data should include. In other words, the dummy operating status data may not include data of types that are not used for generating the learning model.

[0100] The coefficient data 53 includes coefficients for generating dummy operation data. Specifically, the coefficient data 53 includes coefficients for calculating the dummy waiting time. The coefficient is a correction coefficient based on the tact difference between at least one of the process immediately before and the process immediately after the defective process and the defective process. That is, by using the coefficient, the dummy waiting time can be accurately calculated in consideration of the tact difference between processes.

[0101] The coefficient is calculated by machine learning, but is not limited thereto. The coefficient may be calculated recursively. Further, the coefficient data 53 may include coefficients for calculating the dummy operation time and the planned production quantity.

[0102] [3. Operation of Production Management System (Abnormality Judgment Method)] Next, the operation of the production management system 1, that is, the abnormality judgment method will be described with reference to the drawings.

[0103] FIG. 4 is a sequence diagram showing the operation of the production management system 1 according to the present embodiment. FIG. 5 is a flowchart showing the operation of the production management system 1 according to the present embodiment.

[0104] As shown in FIGS. 4 and 5, first, the acquisition unit 13 acquires operation status data from the equipment group 10 and stores it in the storage unit 50 (S11). The operation status data is acquired from all the equipment 12 included in the equipment group 10 and accumulated in the storage unit 50.

[0105] Next, the storage unit 50 transmits the operation status data for a predetermined period to the control unit 30 (S12). The predetermined period is the target period for the abnormality determination process and is determined based on the operation input received by the input unit 20. For example, the predetermined period is a period during which one lot of production is performed, one hour, one day, or the like. When the operation input received by the input unit 20 is an instruction for a specific production line 11, the storage unit 50 transmits the operation status data of all the equipment 12 included in the production line 11.

[0106] Next, the defect determination unit 32 of the control unit 30 determines whether the operation status data for the transmitted predetermined period is complete (S13). If there is unacquired operation status data (No in S13), the calculation unit 33 of the control unit 30 generates dummy operation status data (S14).

[0107] FIG. 6 is a flowchart showing the generation process (S14) of dummy operation status data.

[0108] As shown in FIG. 6, the calculation unit 33 identifies a defective process for which operation status data has not been obtained (S141).

[0109] Next, the calculation unit 33 acquires the operation status data of the processes before and after the defective process (S142). At this time, if the defective process is an intermediate process in all the production processes, the calculation unit 33 acquires the operation status data of the immediately preceding process and the operation status data of the immediately following process.

[0110] If the defective process is a leading process in all the production processes, since there is no immediately preceding process, the calculation unit 33 acquires the operation status data of the immediately following process. Instead of the operation status data of the immediately preceding process, the calculation unit 33 may acquire each initial value such as the number of products to be produced and the production start time in the production plan of the target production line 11.

[0111] Also, if the defective process is a terminal process in all the production processes, since there is no immediately following process, the calculation unit 33 acquires the operation status data of the immediately preceding process. Instead of the operation status data of the immediately following process, the calculation unit 33 may acquire each final value such as the number of products produced and the production end time based on the production results of the target production line 11.

[0112] Next, the calculation unit 33 acquires a coefficient for generating dummy operation status data from the storage unit 50 (S143).

[0113] Next, the calculation unit 33 generates dummy operation status data based on the acquired operation status data and coefficients (S144). For example, the calculation unit 33 predicts the planned production quantity and the dummy operation time, and generates dummy operation status data including the predicted planned production quantity and the dummy operation time. The planned production quantity is, for example, the production quantity of the previous process (i.e., the output quantity). Alternatively, the planned production quantity may be the input quantity of the next process. The dummy operation time is the average value of the operation time of the previous process and the operation time of the next process. Further, the calculation unit 33 may predict the dummy waiting time. The coefficients acquired in step S143 can be used for predicting the dummy waiting time.

[0114] Through the above steps, the production management system 1 generates dummy operation status data corresponding to the defective process.

[0115] Returning to FIG. 5, when the operation status data is complete (Yes in S13), or after generating the dummy operation status data, the abnormality detection unit 34 acquires the model data 52 (S15). Specifically, the abnormality detection unit 34 acquires the production model of the production line 11 that is the target of the abnormality determination process. Further, the abnormality detection unit 34 acquires the production models by equipment and the production models by factor for all the facilities 12 included in the production line 11 that is the target of the abnormality determination process.

[0116] Next, the abnormality detection unit 34 performs an abnormality determination process (S16). Specifically, the abnormality detection unit 34 calculates the degree of abnormality based on the total number of production units during the total operation time obtained from the operation status data including the dummy operation status data. Note that the abnormality detection unit 34 may calculate the degree of abnormality based on the total number of waiting units during the total operation time obtained from the operation status data including the dummy operation status data.

[0117] FIG. 7 is a diagram showing the relationship between the learned probability distribution of the production model of a production line and the degree of abnormality. The horizontal axis is, for example, the production tact. The production tact is represented by the total operation time divided by the total number of production units, or (the total operation time - the total waiting time) divided by the total number of production units.

[0118] The measured value indicated by the dashed line in FIG. 7 is the value of the production tact obtained based on the operation status data of all processes. When the operation status data has not been acquired, the dummy operation status data generated in step S14 is used. The hatched area in FIG. 7 is the area of the region on the right side of the measured value in the probability distribution, which corresponds to the upper probability, that is, the abnormality degree. When the upper probability is smaller than the threshold value, the production line 11 is determined to be abnormal.

[0119] Returning to FIG. 5, when it is determined to be abnormal ( "abnormal" in S16), the evaluation unit 35 performs cause identification processing (S17).

[0120] FIG. 8 is a flowchart showing the cause identification processing of the abnormality. As shown in FIG. 8, the evaluation unit 35 identifies the production line 11 determined to be abnormal (S171). Next, the evaluation unit 35 identifies the abnormal process and its cause among the identified production lines 11 (S172). Specifically, the evaluation unit 35 calculates the upper probability based on the actual value for each of a plurality of production models by equipment and cause in the same manner as the abnormality determination process. When the upper probability is smaller than the threshold value, the equipment and cause corresponding to the production model can be identified as the abnormal process and its cause.

[0121] Returning to FIG. 5, when it is not determined to be abnormal ( "normal" in S16), or after the cause identification processing is completed, the control unit 30 records the result of the abnormality determination process and / or the result of the cause identification process in the storage unit 50 (S18). Next, the output processing unit 36 of the control unit 30 outputs determination result information representing each result to the output unit 40 (S19). In the output unit 40, for example, a result display image representing the determination result information is generated and displayed.

[0122] As described above, in the production management system 1 according to the present embodiment, even when operation status data cannot be obtained, dummy operation status data is generated and used for abnormality determination processing. Since the abnormality determination processing uses a learning model generated by machine learning, conventionally, it could not be executed due to insufficient data. On the other hand, according to the present embodiment, it is possible to execute the abnormality determination processing that could not be executed due to insufficient data and obtain a determination result.

[0123] [4. Generation Process of Learning Model] Next, the generation process of the learning model by machine learning will be described with reference to FIG. 9. FIG. 9 is a flowchart showing the generation process of the learning model by machine learning.

[0124] As shown in FIG. 9, first, the storage unit 50 transmits operation status data for a predetermined period to the control unit 30 (S21). The predetermined period here is, for example, a period longer than the predetermined period in step S12 of FIG. 5, and is a long period such as one day, one week, one month, several months, half a year, or one year.

[0125] The deficiency determination unit 32 of the control unit 30 determines whether there is a deficiency in the operation status data transmitted from the storage unit 50 (S22). If it is determined that there is a deficiency (Yes in S22), the calculation unit 33 of the control unit 30 removes the operation status data related to the deficiency (S23). For example, assume that the operation status data when production related to a predetermined lot is performed on the facility 12b_3 of the production line 11b in FIG. 1 is missing. In this case, the operation status data related to the production, specifically, the operation status data of the other facilities 12 of the production line 11b is removed. Note that "removing" means not using it for the generation of the learning model. For the generation of the learning model, only those with complete operation status data for all processes are used.

[0126] When it is determined that there is no defect (No in S22), or after the data removal is completed, the calculation unit 33 generates a learning model and coefficients for generating dummy operation status data by machine learning (S24). Next, the calculation unit 33 records the generated learning model and coefficients in the storage unit 50 (S25).

[0127] Note that the learning process shown in FIG. 9 may be performed by a processing unit other than the control unit 30. That is, the production management system 1 may use a learning model and coefficients generated by other computer devices.

[0128] [5. Specific Example] Subsequently, a plurality of specific generation examples of dummy operation status data will be described.

[0129] [5-1. First Example] First, an example in the case where the defective process is an intermediate process will be described with reference to FIG. 10. FIG. 10 is a diagram showing an example of dummy operation status data generated when the operation status data of an intermediate process is missing.

[0130] In this example, it is assumed that one production line 11 is composed of four pieces of equipment: equipment A, equipment B, equipment C, and equipment D. Equipment A, equipment B, equipment C, and equipment D are connected by a belt conveyor in this order. Equipment A executes the front-end process A. Equipment B executes the intermediate process B. Equipment C executes the intermediate process C. Equipment D executes the terminal process D. Let the operation status data of each of equipment A, equipment B, equipment C, and equipment D be data A, data B, data C, and data D, respectively.

[0131] As shown in FIG. 10, data A to D each include an operation time, an operation duration, a total stop time during the operation duration, and a production quantity. Also, data A to D each include detailed time information related to the stop.

[0132] The operating time includes, for example, the production start time and the production end time of a lot. The operating hours are the difference between the production end time and the production start time of the lot. The total downtime is the sum of the downtime for each stop (i.e., waiting time) that occurred during the operating hours. For example, Data A includes the stop start time and the stop end time for each of the three factors of "Stop a", "Stop b", and "post-waiting". Note that in FIG. 10, only three factors are shown, but more stops have occurred, and the total of these stops is "45 minutes". The number of products produced is the number of products produced by Facility A, i.e., the output number.

[0133] In the example shown in FIG. 10, Data B could not be obtained due to a defect. In this case, the calculation unit 33 of the control unit 30 generates dummy data B for the defective process based on Data A of the previous process and Data C of the subsequent process.

[0134] FIG. 11 is a diagram showing input data and output data related to the generation process of dummy operation status data. The input data is Data A of the previous process and Data C of the subsequent process. The output data is dummy data B for the defective process.

[0135] Let the operating hours, downtime, and number of products produced of Data A of the previous process be Ta, Da, and Pa, respectively. Let the operating hours, downtime, and number of products produced of Data C of the subsequent process be Tc, Dc, and Pc, respectively. Applying the example of FIG. 10, Ta = 210 minutes, Da = 45 minutes, Pa = 100 pieces, Tc = 211 minutes, Dc = 45 minutes, and Pc = 95 pieces. Note that for the downtime Da and Dc, it may be the downtime for each stop.

[0136] The calculation unit 33 calculates predicted values for each of the operating hours, downtime, and number of products produced using the functions f(Ta, Tc), fs(Da, Dc), and fp(Pa). Each function is stored, for example, in a storage unit (not shown) provided in the control unit 30 or in the storage unit 50.

[0137] The function f(Ta, Tc) is a function for calculating the operating time Tb of dummy data B. Specifically, f(Ta, Tc) is represented by the following formula (1).

[0138] (1) Tb = f(Ta, Tc) = Ave(Ta, Tc)

[0139] Ave( ) is a function that returns the average value of the values within the parentheses. That is, the operating time Tb of dummy data B is the average value of Ta and Tc. Applying the example in Figure 10, the operating time Tb = 210.5 minutes. In Figure 10, the display of the decimal part is omitted.

[0140] The function fs(Da, Dc) is a function for calculating the stop time Db of dummy data B. Specifically, fs(Da, Dc) is represented by the following formula (2).

[0141] (2) Db = fs(Da, Dc) = min(Da, Dc) × α

[0142] min( ) is a function that returns the minimum value of the values within the parentheses. Also, α is a coefficient included in the coefficient data 53. α is a value determined based on the tact difference between process A and process B and the tact difference between process B and process C. For example, it is in the range of 0.9 or more and 1.1 or less, but is not limited to this.

[0143] Here, by using the stop time for each stop as Da and Dc, the detailed dummy stop time for each stop can be calculated. Specifically, the waiting time for the subsequent process is used as Da, and the waiting time for the previous process is used as Db. The waiting time Da for the subsequent process of the immediately preceding process A and the waiting time Dc for the previous process of the immediately following process C are each likely to be the waiting times resulting from the stop of the missing process B. Therefore, by using the waiting time Da for the subsequent process of the immediately preceding process A and the waiting time Dc for the previous process of the immediately following process C, the waiting time Db of the dummy data B can be accurately calculated. For example, referring to the example shown in Figure 10, the first waiting time (Dummy1) of the dummy data B is calculated based on the waiting time for the previous process of data C from 12:10 to 12:12.

[0144] The function fp(Pa) is a function for calculating the predicted production quantity of dummy data B, that is, the planned production quantity Pb. Specifically, fp(Pa) is represented by the following formula (3).

[0145] (3) Pb = fp(Pa) = Pa

[0146] That is, the planned production quantity Pb of dummy data B is regarded as equal to the production quantity Pa of the previous process A. This is because all the products produced in the previous process A can be regarded as being processed in the defective process B.

[0147] As described above, when data B is missing, dummy data B is generated. Dummy data B contains data of the same type as the data contained in data B. Therefore, dummy data B can be used for abnormality determination processing instead of data B.

[0148] Note that the type of data contained in dummy data B does not have to be exactly the same as the type of data contained in data B. Dummy data B only needs to contain the types of data used when generating the learning model. For example, when the production quantity is not used when generating the learning model, dummy data B does not have to contain the production quantity. Similarly, when the waiting time (stop time) is not used when generating the learning model, dummy data B does not have to contain the waiting time.

[0149] Also, the above formulas (1) to (3) are only examples and are not limited to the above examples. For example, the planned production quantity Pb may be the production quantity Pc of the subsequent process C. Or the planned production quantity Pb may be the average value of Pa and Pc.

[0150] [5-2. Second Example] Next, an example where the defective process is the leading process will be described with reference to FIG. 12. FIG. 12 is a diagram showing an example of dummy operation status data generated when operation status data of the leading process is missing. In the following description, the explanation will focus on the differences from the first example, and the explanation of the common points will be omitted or simplified.

[0151] In the example shown in FIG. 12, data A of the leading process cannot be obtained due to being missing. In this case, since there is no data immediately before the defective process, the calculation unit 33 of the control unit 30 generates dummy data A of the defective process based on data B of the subsequent process.

[0152] Specifically, the functions for calculating the predicted values of each of the operation time, stop time, and production quantity can be expressed as f(Tb), fs(Db), and fp(Pb) with the operation time Tb, stop time Db, and production quantity Pb of the data B of the subsequent process as variables. In this case, the operation time Ta, stop time Da, and production quantity Pa of the dummy data A of the defective process can be expressed by the following formulas (4) to (6).

[0153] (4) Ta = f(Tb) = Tb (5) Da = fs(Db) = Db × β (6) Pa = fp(Pb) = Pb

[0154] β in formula (5) is a coefficient generated by machine learning or the like, similar to α in formula (2). Also, similar to the case of the first example, the stop time Da can be calculated for each stop. By using the above formulas (4) to (6), as shown in FIG. 12, the calculation unit 33 can generate dummy data A.

[0155] Note that the above formulas (4) to (6) are merely examples and are not limited to the above-described examples. For example, not only the data B of the subsequent process but also an initial value based on the production plan may be used. For example, the planned production quantity Pa may be the planned production quantity determined in the production plan.

[0156] [5-3. Third Example] Next, an example where the defective process is the last process will be described with reference to FIG. 13. FIG. 13 is a diagram showing an example of dummy operation status data generated when the operation status data of the last process is missing. In the following description, the explanation will focus on the differences from the first example, and the explanation of the common points will be omitted or simplified.

[0157] In the example shown in FIG. 13, the data D of the last process cannot be obtained due to being missing. In this case, since there is no data immediately after the defective process, the calculation unit 33 of the control unit 30 generates dummy data D of the defective process based on the data C of the previous process.

[0158] Specifically, the functions for calculating the predicted values of the operation time, stop time, and production quantity can be expressed as f(Tc), fs(Dc), and fp(Pc) with the operation time Tc, stop time Dc, and production quantity Pc of the data C of the previous process as variables. In this case, the operation time Td, stop time Dd, and production quantity Pd of the dummy data D of the defective process can be expressed by the following equations (7) to (9).

[0159] (7) Td = f(Tc) = Tc (8) Dd = fs(Dc) = Dc × γ (9) Pd = fp(Pc) = Pc

[0160] γ in equation (8) is a coefficient generated by machine learning or the like, similar to α in equation (2). Also, similar to the case of the first example, the stop time Dd can be calculated for each stop. By using the above equations (7) to (9), as shown in FIG. 13, the calculation unit 33 can generate the dummy data D.

[0161] Note that the above equations (7) to (9) are only examples and are not limited to the above examples. For example, not only the data C of the previous process but also the final value based on the final production result may be used. For example, the planned production quantity Pd may be the quantity actually produced on the production line 11.

[0162] [5-4. Fourth Example] In the first to third examples described above, in each case, the operation status data that should originally be obtained is missing. On the other hand, there may be cases where operation status data is not scheduled to be obtained from the beginning due to some cause such as equipment problems. Even in this case, dummy operation status data can be generated.

[0163] FIG. 14 is a diagram showing an example of dummy operation status data generated in place of operation status data that is not scheduled to be obtained. In the following description, the explanation will focus on the differences from the first example, and the explanation of the common points will be omitted or simplified.

[0164] In the example shown in FIG. 14, there is only a difference in whether the unobtained operation status data is data that should originally be obtained or data that is not scheduled to be obtained from the beginning. In terms of the fact that operation status data is not obtained, it is the same as the first example. Therefore, similar to the first example, dummy data B can be generated based on formulas (1) to (3).

[0165] In the case of the fourth example, the determination process (step S13 in FIG. 5) for the lack (non-acquisition) of operation status data can be omitted. Since the equipment for which operation status data is not scheduled to be obtained has been identified, dummy operation status data for the equipment can be set in advance to be generated.

[0166] In the fourth example, the case where the data of the intermediate process is not scheduled to be obtained has been described. However, when the data of the upstream process or the downstream process is not scheduled to be obtained, dummy operation status data can be generated by performing the same processing as in the second or third example.

[0167] [6. Display Example] Subsequently, an example of the display of the determination result by the production management system 1 will be described with reference to FIG. 15. FIG. 15 is a diagram showing an example of the display of the determination result by the production management system 1 according to the present embodiment.

[0168] In FIG. 15, a display screen 60 showing the results of the abnormality determination process for three production lines 1 to 3 is shown. Each production line includes four facilities A to D in this order.

[0169] The display screen 60 includes a schematic diagram 61 showing the configuration of the production line. Also, at the upper part of the schematic diagram 61, an icon 62 indicating whether operation status data could be acquired is displayed. Also, at the lower part of the schematic diagram 61, a text 63 indicating the cause of the abnormality is displayed. The text 63 is not displayed when there is no abnormal facility (process). For the abnormal facility, a dashed-line frame 64 is displayed. Thus, the abnormal facility can be emphasized and displayed in an easy-to-understand manner. Also, on the right side of the schematic diagram 61, a graph 65 showing the abnormality determination results of the production line in chronological order and an icon 66 indicating the presence or absence of the occurrence of an abnormality are displayed.

[0170] In the display example shown in FIG. 15, it can be seen that in production line 1, there was no lack of operation status data and no abnormality occurred. On the other hand, in production line 2, it can be seen that there was a lack of operation status data in facility B, but the production itself ended without abnormality. Since it can be seen from the icon 62 that there was a lack of operation status data, the user can be prompted to perform inspections on the network related to the acquisition of operation status data.

[0171] Also, in production line 3, not only was there a lack of operation status data in facility B, but an abnormality also occurred in the production, and it can be seen that the cause of the abnormality was the cause "Stop B" that occurred in facility B. By displaying the occurrence of the abnormality, the user can be prompted to perform maintenance work. Also, by displaying the cause of the abnormality, it becomes possible to present the specific target facility and work content of the maintenance work. Therefore, the work efficiency of the maintenance work can be increased, the downtime of the facility can be shortened, and the production efficiency can be improved.

[0172] Note that the display example shown in FIG. 15 is only an example and is not particularly limited. Instead of displaying the schematic diagram 61, only the icon 66 indicating whether it is abnormal or normal (not abnormal) for each production line may be displayed. Also, the icon 62 indicating the acquisition status of the operation status data, the text 63 indicating the cause of the abnormality, and the frame 64 representing the abnormal equipment may not be displayed. Instead of the frame 64, the abnormal equipment may be drawn with a thick line or may be displayed in a blinking manner.

[0173] (Other embodiments) As described above, the abnormality determination method and the production management system according to one or more aspects have been described based on the embodiments. However, the present disclosure is not limited to these embodiments. As long as the gist of the present disclosure is not deviated from, various modifications conceived by those skilled in the art applied to the present embodiment, and forms constructed by combining components in different embodiments are also included within the scope of the present disclosure.

[0174] For example, in the above embodiment, two cases were described: one in which the abnormality determination process is performed using the number of products produced in the equipment, and the other in which the abnormality determination process is performed using the waiting time in the equipment. However, both cases may be performed, or only one of them may be performed. When both are performed, if at least one of them is determined to be abnormal, it can be determined as abnormal.

[0175] When only one of them is performed, the amount of information included in the operation status data can be reduced, and the data volume can be reduced. For example, when using the number of products produced by the equipment, the operation status data may not include the waiting time. Also, when using the waiting time of the equipment, the operation status data may not include the number of products produced.

[0176] Also, the communication method between the devices described in the above embodiments is not particularly limited. When wireless communication is performed between devices, the wireless communication method (communication standard) is, for example, short-range wireless communication such as ZigBee (registered trademark), Bluetooth (registered trademark), or wireless LAN (Local Area Network). Alternatively, the wireless communication method (communication standard) may be communication via a wide-area communication network such as the Internet. Also, between devices, instead of wireless communication, wired communication may be performed. Specifically, the wired communication is, for example, power line carrier communication (PLC: Power Line Communication) or communication using a wired LAN.

[0177] Also, in the above embodiments, the processing executed by a specific processing unit may be executed by another processing unit. Also, the order of a plurality of processes may be changed, or a plurality of processes may be executed in parallel. Also, the distribution of the components included in the production management system to a plurality of devices is an example. For example, the components included in one device may be included in another device. Also, the production management system may be realized as a single device.

[0178] For example, the processing described in the above embodiments may be realized by centralized processing using a single device (system), or may be realized by distributed processing using a plurality of devices. Also, the processor that executes the above program may be singular or plural. That is, centralized processing may be performed, or distributed processing may be performed.

[0179] Also, in the above embodiments, all or part of the components such as the control unit may be configured by dedicated hardware, or may be realized by executing a software program suitable for each component. Each component may be realized by a program execution unit such as a CPU or a processor reading and executing a software program recorded on a recording medium such as an HDD or a semiconductor memory.

[0180] Moreover, components such as a control unit may be composed of one or more electronic circuits. Each of the one or more electronic circuits may be a general-purpose circuit or a dedicated circuit.

[0181] The one or more electronic circuits may include, for example, a semiconductor device, an IC (Integrated Circuit), or an LSI (Large Scale Integration). The IC or LSI may be integrated on one chip or on multiple chips. Here, we refer to them as ICs or LSIs, but the name may change depending on the degree of integration, and they may be called system LSIs, VLSIs (Very Large Scale Integration), or ULSIs (Ultra Large Scale Integration). Also, an FPGA (Field Programmable Gate Array) programmed after the manufacture of the LSI can be used for the same purpose.

[0182] Furthermore, the general or specific aspects of the present disclosure may be implemented by a system, a device, a method, an integrated circuit, or a computer program. Alternatively, it may be implemented by a computer-readable non-transitory recording medium such as an optical disk, an HDD, or a semiconductor memory storing the computer program. Also, it may be implemented by any combination of a system, a device, a method, an integrated circuit, a computer program, and a recording medium.

[0183] Also, various changes, replacements, additions, omissions, etc. can be made to the above-described embodiments within the scope of the claims or their equivalents.

Industrial Applicability

[0184] The present disclosure can be used, for example, in a management system and an abnormality determination device at a production site such as a factory.

Explanation of Signs

[0185] 1 Production management system 2 Abnormality determination device 10 Equipment group 11 Production line 12 Equipment 13 Acquisition unit 20 Input unit 30 Control unit 31 Request unit 32 Defect determination unit 33 Calculation unit 34 Abnormality detection unit 35 Evaluation unit 36 Output processing unit 40 Output unit 50 Memory unit 51 Production log data 52 Model data 53 Coefficient data 60 Display screen 61 Schematic diagram 62, 66 Icon 63 Text 64 Frame 65 Graph

Claims

1. An abnormality determination method in a production management system for managing a production line including a first production device corresponding to a first process, a second production device corresponding to a second process following the first process, and a third production device corresponding to a third process following the second process, comprising: (i) acquiring at least (i) the first operation status data including the first production quantity and the first operation time corresponding to each production in the first production device and (iii) the third operation status data including the third production quantity and the third operation time corresponding to each production in the third production device via a network; when it is determined that the second operation status data has not been acquired based on the first operation time and the third operation time, predicting a dummy operation time corresponding to the planned production quantity in the second production device based on the first operation status data and the third operation status data, and generating dummy operation status data corresponding to the second operation status data including the planned production quantity and the dummy operation time; performing an abnormality determination process for the entire production process including the first process to the third process based on the first operation status data, the third operation status data, and the dummy operation status data; outputting the determination result information indicating the result of the abnormality determination process to be displayed on a display device included in the production management system; Abnormality determination method.

2. When outputting the determination result information, outputting that the abnormality determination process has been performed using the dummy operation status data in the second process; The abnormality determination method according to Claim 1.

3. The abnormality determination process is a process of determining the presence or absence of an abnormality in the entire production process based on the total production quantity in the total operation time in the entire production process. The abnormality determination method according to Claim 1 or 2.

4. The abnormality determination process is a process of determining the presence or absence of an abnormality in each process in the entire production process based on the production quantity in the operation time of the process. The abnormality determination method according to Claim 1 or 2.

5. The result of the abnormality determination process includes that there is no abnormality in the production process. The abnormality determination method according to Claim 1 or 2.

6. In the production line, the first production device, the second production device, and the third production device are connected by a belt conveyor. The abnormality determination method according to claim 1 or 2.

7. A production management system for managing a production line including a first production device corresponding to a first process, a second production device corresponding to a second process following the first process, and a third production device corresponding to a third process following the second process, (i) First operation status data including the first production quantity and the first operation time corresponding to each production in the first production device, (ii) Second operation status data including the second production quantity and the second operation time corresponding to each production in the second production device, and (iii) Third operation status data including the third production quantity and the third operation time corresponding to each production in the third production device, and at least (i) the first operation status data and (iii) the third operation status data among them are acquired via a network. When it is determined that the second operation status data has not been acquired based on the first operation time and the third operation time, a dummy operation time corresponding to the planned production quantity in the second production device is predicted based on the first operation status data and the third operation status data, and dummy operation status data corresponding to the second operation status data including the planned production quantity and the dummy operation time is generated. Based on the first operation status data, the third operation status data, and the dummy operation status data, an abnormality determination process for the entire production process including the first process to the third process is performed. Output so as to display determination result information representing the result of the abnormality determination process on a display device included in the production management system. Production management system.

8. An abnormality determination method in a production management system for managing a production line including a first production device corresponding to a first process, a second production device corresponding to a second process following the first process, and a third production device corresponding to a third process following the second process, (i) First operation status data including the first production quantity and the first operation time corresponding to each production in the first production device, and (ii) Third operation status data including the third production quantity and the third operation time corresponding to each production in the third production device are acquired via a network. Predict a dummy operation time corresponding to the planned production quantity in the second production device based on the first operation status data and the third operation status data, and generate dummy operation status data including the planned production quantity and the dummy operation time. Based on the first operation status data, the third operation status data, and the dummy operation status data, perform an abnormality determination process for the entire production process including the first process to the third process. Output so as to display determination result information representing the result of the abnormality determination process on a display device included in the production management system. Abnormality determination method.

9. When outputting the determination result information, output that the abnormality determination process was performed using the dummy operation status data in the second process. The abnormality determination method according to claim 8.

10. A production management system that manages a production line including a first production device corresponding to a first process, a second production device corresponding to a second process following the first process, and a third production device corresponding to a third process following the second process, (i) First operation status data including the first production quantity in the first production device and the first operation time corresponding to each production, and (ii) Third operation status data including the third production quantity in the third production device and the third operation time corresponding to each production are acquired via a network. Predict a dummy operation time corresponding to the planned production quantity in the second production device based on the first operation status data and the third operation status data, and generate dummy operation status data including the planned production quantity and the dummy operation time. Based on the first operation status data, the third operation status data, and the dummy operation status data, perform an abnormality determination process for the entire production process including the first process to the third process. Output so as to display determination result information representing the result of the abnormality determination process on a display device included in the production management system. Production management system.

11. An abnormality determination method in a production management system that manages a production line including a first production device corresponding to a first process and a second production device corresponding to a second process that is the final process following the first process. At least the first operation status data including the first production quantity in the first production device and the first operation time corresponding to each production, and (ii) the second operation status data including the second production quantity in the second production device and the second operation time corresponding to each production are acquired via a network. When it is determined that the second operation status data has not been acquired based on the first operation time, a dummy operation time corresponding to the planned production quantity in the second production device is predicted based on the first operation status data, and dummy operation status data corresponding to the second operation status data including the planned production quantity and the dummy operation time is generated. Based on the first operation status data and the dummy operation status data, an abnormality determination process for the entire production process including the first process and the second process is performed. Output the determination result information indicating the result of the abnormality determination process so as to be displayed on a display device included in the production management system. Abnormality determination method.

12. When outputting the determination result information, output that the abnormality determination process has been performed using the dummy operation status data in the second process. The abnormality determination method according to claim 11.

13. An abnormality determination method in a production management system that manages a production line including a first production device corresponding to a first process that is a leading process and a second production device corresponding to a second process following the first process, At least the second operation status data including the second production quantity in the second production device and the second operation time corresponding to each production, and (ii) the first operation status data including the first production quantity in the first production device and the first operation time corresponding to each production are acquired via a network. When it is determined that the first operation status data has not been acquired based on the second operation time, a dummy operation time corresponding to the planned production quantity in the first production device is predicted based on the second operation status data, and dummy operation status data corresponding to the first operation status data including the planned production quantity and the dummy operation time is generated. Based on the dummy operation status data and the second operation status data, an abnormality determination process for the entire production process including the first process and the second process is performed. Output the determination result information indicating the result of the abnormality determination process so as to be displayed on a display device included in the production management system. Abnormality determination method.

14. When outputting the determination result information, output that the abnormality determination process was performed using the dummy operation status data in the first step. The abnormality determination method according to claim 13.

15. A program for causing a computer to execute the abnormality determination method according to any one of claims 1, 2, 8, 9, and 11 to 14.

Images