JP2022149300A - Anomaly detection device, anomaly detection method, and anomaly detection program - Google Patents

Abstract

To provide an anomaly detection device capable of detecting an anomaly in a manufacturing plant.SOLUTION: An anomaly detection device 100 acquires a planned production, which indicates the pre-planned production volume of a product and which a production volume of a product produced during a predetermined period using equipment installed in a factory and an actual production volume representing the production volume of the product that has been produced during the predetermined period. The anomaly detection device 100 compensates the planned production by the product yield rate and detects an anomaly in the plant based on the compensated planned production and the actual production volume.SELECTED DRAWING: Figure 3

Description

The present invention relates to an abnormality detection device and the like.

In a manufacturing factory, products are produced based on a production plan, but various abnormalities may occur on a daily basis, and there are cases where products cannot be produced according to the production plan. In order to suppress the influence of such an occurrence of an abnormality, various types of information are shared among a plurality of manufacturing plants, and measures such as adjustment of production volume are taken.

JP 2004-178465 A JP 2005-050176 A JP 2005-092689 A Japanese Patent Application Laid-Open No. 2002-373012

As mentioned above, if the product cannot be produced according to the production plan, it is presumed that some kind of abnormality has occurred. may be delayed.

For example, in addition to equipment failures in the manufacturing plant, the reasons for not being able to produce according to the production plan may include the omission of products by employees, the improper operation of the manufacturing plant, and the like.

In one aspect, an object of the present invention is to provide an abnormality detection device, an abnormality detection method, and an abnormality detection program capable of detecting an abnormality in a manufacturing plant.

In the first plan, the anomaly detection device has an acquisition unit and a detection unit. The acquisition unit acquires a planned production volume that indicates the production volume of the product that is produced in a predetermined period using the equipment installed in the factory, and that indicates the production volume of the product planned in advance, and the actual production volume that is produced in the predetermined period. Acquire the actual production volume that indicates the production volume of the manufactured product. The detection unit corrects the planned production volume by the yield rate of the product, and detects an abnormality in the factory based on the corrected planned production volume and the actual production volume.

Abnormalities in manufacturing plants can be detected.

FIG. 1 is a diagram showing an anomaly detection system according to this embodiment. FIG. 2 is a diagram illustrating an example of a data structure of a management DB; FIG. 3 is a functional block diagram showing the configuration of the abnormality detection device according to this embodiment. FIG. 4 is a diagram showing an example of the data structure of the work table. FIG. 5 is a flowchart (1) showing the processing procedure of the abnormality detection device according to the present embodiment. FIG. 6 is a flowchart (2) showing the processing procedure of the abnormality detection device according to the present embodiment. FIG. 7 is a diagram showing an example of a hardware configuration of a computer that implements functions similar to those of the abnormality detection device.

Hereinafter, embodiments of an abnormality detection device, an abnormality detection method, and an abnormality detection program disclosed in the present application will be described in detail based on the drawings. In addition, this invention is not limited by this Example.

FIG. 1 is a diagram showing an anomaly detection system according to this embodiment. As shown in FIG. 1, this system has a manufacturing plant 3, an administrator terminal 10, a server 20, and an abnormality detection device 100. FIG. The server 20 is connected to the manufacturing plant 3 (a terminal device (not shown) installed in the manufacturing plant 3). The administrator terminal 10 , the server 20 and the abnormality detection device 100 are interconnected via the network 5 . Note that the abnormality detection device 100 may be directly connected to the server 20 without going through the network 5 .

The manufacturing factory 3 is a factory where equipment is installed and employees operate the equipment to produce products. A terminal device is installed in the manufacturing factory 3, and the terminal device records the actual production amount for each predetermined period. In the following description, the production volume of products actually produced in a predetermined period is referred to as "actual production volume". The terminal device of the manufacturing plant 3 records the actual production amount on a daily basis, and transmits the dated actual production amount information to the server 20 .

In addition, the terminal device of the manufacturing plant 3 records the actual operating time of the equipment for each predetermined period. In the following description, the actual operating time during a predetermined period is referred to as "actual operating time". The terminal device of the manufacturing plant 3 records the actual operating hours for each day and transmits the dated information of the actual operating hours to the server 20 .

The manager terminal 10 is a terminal device used by the manager of the manufacturing plant 3 . The manager operates the manager terminal 10 to input the planned production volume. The planned production volume is the production volume of the product to be produced in a predetermined period, and indicates the production volume of the product planned in advance. For example, the manager enters planned production volume for each day. The administrator terminal 10 transmits the dated planned production volume to the server 20 . Also, when there is a change in the planned production volume, the server 20 is notified of information including the date and the fact that the planned production volume has been changed.

Also, the administrator operates the administrator terminal 10 to input the scheduled operating time. The scheduled operating time is the operating time of the device scheduled in advance for one day. The administrator terminal 10 transmits the dated scheduled operating time to the server 20 .

The server 20 registers the information received from the terminal device of the manufacturing plant 3 and the administrator terminal 10 in the management DB 141 . The server 20 transmits information in the management DB 141 to the abnormality detection device 100 .

FIG. 2 is a diagram illustrating an example of a data structure of a management DB; As shown in FIG. 2, this management DB 141 has an item number, date, planned production volume, scheduled operation time, actual production volume, actual operation time, and a plan change flag.

The item number is a number that identifies a record in the management DB. The date is the date corresponding to the record. The planned production volume and scheduled operating time are information transmitted from the administrator terminal 10 and are associated with dates. The actual production volume and the actual operating time are information transmitted from the terminal device of the manufacturing plant 3, and are associated with dates.

The plan change flag indicates whether or not there was a change in the planned production volume on the relevant date. For example, it is "on" when there is a change in the planned production volume, and "off" when there is no change in the planned production volume.

The abnormality detection device 100 receives the management DB 141 from the server 20 and detects an abnormality in the manufacturing plant 3 based on the management DB 141 . The abnormality detection device 100 notifies the administrator that an abnormality has been detected in the manufacturing plant 3 by displaying a warning screen on the administrator terminal 10 when an abnormality is detected.

For example, the abnormality detection device 100 corrects the planned production volume by the yield rate of the product, and detects an abnormality in the manufacturing plant 3 based on the corrected planned production volume and the actual production volume. Moreover, the abnormality detection device 100 detects an abnormality in the manufacturing plant 3 when the actual operation time is longer than the scheduled operation time and there is no change in the production plan at the relevant date and time.

The abnormality detection device 100 can detect an abnormality in the manufacturing plant 3 by executing the above process. In addition, since the abnormality detection device 100 notifies the administrator of the occurrence of an abnormality, the administrator can efficiently take measures to deal with the abnormality.

Next, an example of the configuration of the abnormality detection device 100 shown in FIG. 1 will be described. FIG. 3 is a functional block diagram showing the configuration of the abnormality detection device according to this embodiment. As shown in FIG. 3 , the abnormality detection device 100 has a communication section 110 , an input section 120 , a display section 130 , a storage section 140 and a control section 150 .

The communication unit 110 is a processing unit that executes data communication with the administrator terminal 10 and the server 20 via the network 5 . Communication unit 110 is an example of a communication device. The communication unit 110 may receive data from another external device (not shown).

The input unit 120 is an input device that inputs various types of information to the control unit 150 of the abnormality detection device 100 . The input unit 120 corresponds to a keyboard, mouse, touch panel, or the like.

The display unit 130 is a display device that displays information output from the control unit 150 . For example, the display unit 130 displays screen information such as skill certification and scoring results for various competitions. The display unit 130 corresponds to a liquid crystal display, an organic EL (Electro-Luminescence) display, a touch panel, or the like.

Storage unit 140 has management DB 141 , work table 142 , and yield information 143 . The storage unit 140 corresponds to semiconductor memory devices such as RAM (Random Access Memory) and flash memory, and storage devices such as HDD (Hard Disk Drive).

The management DB 141 is information received from the server 20 . The data structure of the management DB 141 is the same as the data structure of the management DB 141 illustrated in FIG.

The work table 142 is a table that holds work information of each employee. FIG. 4 is a diagram showing an example of the data structure of the work table. As shown in FIG. 4, this work table 142 associates an employee ID with work information. The employee ID is information that uniquely identifies an employee working at the manufacturing plant 3 . In the work information, the time of arrival and the time of departure for each date are set. For example, a date for an employee with no clock-in and clock-out times indicates that the employee is absent. For some reason, the time of arrival at work may be recorded but the time of departure may not be recorded.

Yield information 143 is information on the yield rate of products produced by equipment in the manufacturing plant 3 . The yield rate in this embodiment is the rate at which the products produced by the equipment in the manufacturing plant 3 are properly produced. As the yield rate approaches 1, the actual production volume approaches the planned production volume.

The control unit 150 has an acquisition unit 151 , a detection unit 152 and a warning unit 153 . The control unit 150 is implemented by hardwired logic such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an ASIC (Application Specific Integrated Circuit), and an FPGA (Field Programmable Gate Array).

The acquisition unit 151 acquires information of the management DB 141 from the server 20 . The acquisition unit 151 stores the acquired information of the management DB 141 in the storage unit 140 . The acquisition unit 151 also acquires work information corresponding to each employee ID from the server 20 or another external device, and updates the work table 142 .

The detection unit 152 detects an abnormality in the manufacturing plant 3 based on the management DB 141 . An example of the processing of the detection unit 152 will be described below.

Records of planned production volume, scheduled operation time, actual production volume, actual operation time, and plan change flag corresponding to the same date are acquired from the detection unit 152, and the following processing is executed. The detection unit 152 may preferentially select the latest date, or may select records in ascending order of date and execute the following process.

The detector 152 corrects the planned production volume based on the yield information 143 . For example, the detection unit 152 corrects the planned production volume by multiplying the planned production volume by the yield rate set in the yield information 143 . In the following description, the corrected planned production volume is referred to as "corrected production volume".

The detection unit 152 detects the presence or absence of an abnormality in the manufacturing plant 3 and the content of the abnormality based on the following combination of conditions. When the detection unit 152 detects an abnormality, the detection unit 152 outputs the detection result to the warning unit 153 . The detection result includes the date and details of the abnormality. The thresholds th1, th2, and th3 are set in advance by an administrator.

Corrected production volume ≤ actual production volume (Condition 1)
actual operating time/scheduled operating time>threshold th1 (condition 2)
Operating rate actual hours < scheduled operating hours (Condition 3)
Actual production volume/corrected production volume<threshold th2 (Condition 4)
actual operating time−scheduled operating time>threshold th3 (Condition 5)
The plan change flag is "off" (Condition 6)

The detection unit 152 detects an abnormality in the manufacturing plant 3 when the conditions 1 and 2 are satisfied. In this case, the detection unit 152 detects the content of the abnormality in the manufacturing plant 3, “unauthorized operation of the manufacturing plant”.

The detection unit 152 detects an abnormality in the manufacturing plant 3 when the conditions 1 and 3 are satisfied. In this case, the detection unit 152 detects the content of the abnormality in the manufacturing plant 3, “equipment failure”.

The detection unit 152 detects an abnormality in the manufacturing plant 3 when the conditions 1 and 4 are satisfied and the condition 3 is not satisfied. In this case, the detection unit 152 detects the content of the abnormality in the manufacturing plant 3, ie, the content of the product being cut out.

The detection unit 152 detects an abnormality in the manufacturing plant 3 when the conditions 5 and 6 are satisfied. In this case, the detection unit 152 detects the content of the abnormality in the manufacturing plant 3, “malfunctioning of the plant”. In addition, the detection unit 152 scans the work information of the work table 142 using the date of the selected record as a key. Determine whether an employee ID exists.

The detection unit 152 detects the employee ID when there is an employee ID in which the time of arrival at the office is recorded and the time of leaving the office is not recorded in the date used as the key. The detection unit 152 outputs the detected employee ID to the warning unit 153 as the “employee ID of the person who has not left the company”.

The detection unit 152 repeatedly executes the above-described processing for each date record (planned production volume, scheduled operation time, actual production volume, actual operation time, plan change flag) included in the management DB 141, and outputs the detection result to the warning unit. 153.

The warning unit 153 issues a warning to the administrator terminal 10 based on the detection result from the detection unit 152 . For example, the warning unit 153 transmits information of a warning screen indicating the content of the abnormality to the administrator terminal 10 and causes it to be displayed. If the detection result includes the employee ID of the person who has not left the company, the warning unit 153 sets the employee ID of the person who has not left the company on the warning screen.

Next, an example of the processing procedure of the abnormality detection device 100 according to this embodiment will be described. FIG. 5 is a flowchart (1) showing the processing procedure of the abnormality detection device according to the present embodiment. The acquisition unit 151 of the abnormality detection device 100 acquires information of the management DB 141 from the server 20 and stores it in the storage unit 140 (step S101).

The detection unit 152 of the abnormality detection device 100 acquires the planned production volume, the actual production volume, the scheduled operating time, and the actual operating time for a certain date from the management DB 141 (step S102).

The detection unit 152 corrects the planned production volume according to the yield rate (step S103). If condition 1 (corrected production volume≦actual production volume) is satisfied (step S104, Yes), the detection unit 152 proceeds to step S105. On the other hand, if the condition 1 is not satisfied (step S104, No), the detection unit 152 proceeds to step S107.

A description will be given after step S105. The detection unit 152 determines whether condition 2 (actual operation time/scheduled operation time>threshold th1) is satisfied (step S105). If the condition 2 is satisfied (step S105, Yes), the detection unit 152 detects unauthorized operation of the factory, and the warning unit 153 warns the administrator terminal 10 (step S106). On the other hand, if the condition 2 is not satisfied (step S105, No), the detection unit 152 ends the process.

A description will be given after step S107. The detection unit 152 determines whether or not Condition 3 (actual operating rate time<scheduled operating time) is satisfied (step S107). If the condition 3 is satisfied (step S107, Yes), the detection unit 152 detects an equipment failure, and the warning unit 153 issues a warning to the administrator terminal 10 (step S108). On the other hand, if the condition 3 is not satisfied (step S107, No), the detection unit 152 proceeds to step S109.

A description will be given after step S109. The detection unit 152 determines whether condition 4 (actual production volume/corrected production volume<threshold th2) is satisfied (step S109). If the condition 4 is satisfied (step S109, Yes), the detection unit 152 detects the omission of the product, and the warning unit 153 warns the administrator terminal 10 (step S110). On the other hand, if the condition 4 is not satisfied (step S109, No), the detection unit 152 ends the process.

FIG. 6 is a flowchart (2) showing the processing procedure of the abnormality detection device according to the present embodiment. The detection unit 152 of the abnormality detection device 100 acquires the scheduled operation time, the actual operation time, and the plan change flag from the management DB 141 (step S201). The detection unit 152 determines whether or not condition 5 (actual operation time−scheduled operation time>threshold th3) is satisfied (step S202). If the condition 5 is not satisfied (step S202, No), the detection unit 152 terminates the process. On the other hand, when the condition 5 is satisfied (step S202, Yes), the detection unit 152 proceeds to step S203.

The detection unit 152 determines whether condition 6 is satisfied (step S203). If the condition 6 is not satisfied (step S203, No), the detection unit 152 ends the process. On the other hand, when the condition 6 is satisfied (step S203, Yes), the detection unit 152 refers to the work table 142 and determines whether or not there is a person who has not left on the date (step S204).

If there is a person who has not left (step S205, Yes), the detection unit 152 detects unauthorized operation of the manufacturing plant and the employee ID of the person who has not left, and the warning unit 153 issues a warning (step S206). On the other hand, when there is no person who has not left (step S205, No), the detection unit 152 detects unauthorized operation of the manufacturing plant, and the warning unit 153 issues a warning (step S207).

Next, the effects of the abnormality detection device according to this embodiment will be described. The abnormality detection device 100 acquires the planned production volume and the actual production volume from the management DB 141, and corrects the planned production volume by the yield. The abnormality detection device 100 detects an abnormality in the manufacturing plant 3 based on the corrected planned production volume and actual production volume. As a result, it is possible to detect an abnormality when the product cannot be produced according to the production plan in the manufacturing plant 3 .

The abnormality detection device 100 acquires the scheduled operation time and the actual operation time from the management DB 141, and if the actual operation time is longer than the scheduled operation time, identifies whether there is a change in the production plan of the product, Detect anomalies when there is no change in plan. As a result, unauthorized operation can be detected from the contents of a plurality of abnormalities that can occur in the manufacturing plant 3.

The abnormality detection device 100 detects unauthorized operation of equipment in the manufacturing plant 3 when the corrected planned production volume is equal to or less than the actual production volume and the value obtained by dividing the actual operation time by the scheduled operation time is greater than a predetermined value. do. As a result, unauthorized operation can be detected from the contents of a plurality of abnormalities that can occur in the manufacturing plant 3.

The abnormality detection device 100 detects a failure of equipment when the corrected planned production volume is greater than the actual production volume and the actual operating time is shorter than the scheduled operating time. As a result, it is possible to detect equipment failures from the contents of a plurality of abnormalities that may occur in the manufacturing plant 3 .

The abnormality detection device 100 determines that the corrected planned production volume is larger than the actual production volume, the actual operating time is equal to or longer than the scheduled operating time, and the value obtained by dividing the actual production volume by the planned production volume is larger than a predetermined value. If it is small, detect the hollowing out of the product. As a result, it is possible to detect the omission of the product from the content of a plurality of abnormalities that may occur in the manufacturing plant 3 .

In addition, when the abnormality detection device 100 detects an abnormality, the abnormality detection device 100 notifies the administrator terminal 10 of the detection result, so that the administrator can efficiently take measures to deal with the abnormality. be able to.

Next, an example of the hardware configuration of a computer that implements the same functions as the abnormality detection device 100 shown in the above embodiment will be described. FIG. 7 is a diagram showing an example of a hardware configuration of a computer that implements functions similar to those of the abnormality detection device.

As shown in FIG. 7, the computer 200 has a CPU 201 that executes various arithmetic processes, an input device 202 that receives data input from the user, and a display 203 . The computer 200 also has a communication device 204 that receives data from the server 20, and an interface device 205 that connects with various devices. The computer 200 has a RAM 206 that temporarily stores various information and a hard disk device 207 . Each device 201 - 207 is then connected to a bus 208 .

The hard disk device 207 has an acquisition program 207a, a detection program 207b, and a warning program 207c. The CPU 201 reads out the acquisition program 207a, the detection program 207b, and the warning program 207c and develops them in the RAM 206. FIG.

Acquisition program 207a functions as acquisition process 206a. Detection program 207b functions as detection process 206b. Alert program 207c functions as alert process 206c.

The processing of the acquisition process 206 a corresponds to the processing of the acquisition unit 151 . The processing of the detection process 206 b corresponds to the processing of the detection unit 152 . Processing of the warning process 206 c corresponds to processing of the warning unit 153 .

Note that the programs 207a to 207c do not necessarily have to be stored in the hard disk device 207 from the beginning. For example, each program is stored in a “portable physical medium” such as a flexible disk (FD), CD-ROM, DVD disk, magneto-optical disk, IC card, etc. inserted into the computer 200 . Then, the computer 200 may read and execute each program 207a to 207c.

100 Abnormality detection device 110 Communication unit 120 Input unit 130 Display unit 140 Storage unit 141 Management DB
142 work table 143 yield information 150 control unit 151 acquisition unit 152 detection unit 153 warning unit

Claims (7)

A production volume of a product produced in a predetermined period using equipment installed in a factory, which is a planned production volume indicating a planned production volume of a product in advance, and a production volume actually produced in the predetermined period an acquisition unit that acquires an actual production volume that indicates the production volume of a product;
a detection unit that corrects the planned production volume by the yield rate of the product, and detects an abnormality in the factory based on the corrected planned production volume and the actual production volume;
An abnormality detection device comprising: The acquisition unit further acquires a scheduled operating time indicating a scheduled operating time of the device and an actual operating time indicating an actual operating time of the device,
The detection unit identifies whether or not there is a change in the production plan of the product when the time obtained by subtracting the expected operation time from the actual operation time is greater than a predetermined time, and determines whether or not there is a change in the production plan. 2. The abnormality detection device according to claim 1, further comprising a process for detecting an abnormality in said factory. The detection unit detects unauthorized operation of the equipment when the corrected planned production volume is equal to or less than the actual production volume and a value obtained by dividing the actual operation time by the scheduled operation time is greater than a predetermined value. 2. The abnormality detection device according to claim 1, wherein: The detection unit detects a failure of the device when the corrected planned production volume is greater than the actual production volume and the actual operation time is shorter than the scheduled operation time. The abnormality detection device according to claim 3. The detection unit detects that the corrected planned production volume is greater than the actual production volume, the actual operation time is equal to or greater than the scheduled operation time, and the actual production volume is divided by the planned production volume. 5. The anomaly detection device according to claim 4, wherein when the is smaller than a predetermined value, omission of the product is detected. A computer-implemented anomaly detection method comprising:
A production volume of a product produced in a predetermined period using equipment installed in a factory, which is a planned production volume indicating a planned production volume of a product in advance, and a production volume actually produced in the predetermined period Acquire the actual production volume that indicates the production volume of the product,
An abnormality detection method, comprising: correcting the planned production volume by the yield rate of the product; and detecting an abnormality in the factory based on the corrected planned production volume and the actual production volume. . to the computer,
A production volume of a product produced in a predetermined period using equipment installed in a factory, which is a planned production volume indicating a planned production volume of a product in advance, and a production volume actually produced in the predetermined period Acquire the actual production volume that indicates the production volume of the product,
An anomaly detection program characterized by correcting the planned production volume by the yield rate of the product, and executing a process of detecting anomalies in the factory based on the corrected planned production volume and the actual production volume. .

Images