Determination method

Abstract

To provide a technique in which a work quality is determined to be good or bad using a machine learning model that is applicable to even different types of workpieces.SOLUTION: A determination system comprises: a detection unit for detecting work-state information about a production facility; a first machine learning model in which a quality determination of a work result is made by inputting images of the work result of the production facility; and a second machine learning model in which learning is performed using teaching data in such a way that the work-state information about the production facility is denoted as good-labeled teaching data when the first machine learning model determines it to be good, and that the work-state information about the production facility is denoted as bad-labeled teaching data when the first machine learning model determines it to be bad.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to a technique for determining whether work in production equipment is good or bad. [Background technology]

[0002] Patent Document 1 discloses a state determination device that determines the operating state of an injection molding machine. In this conventional technology, a wide variety of equipment data is collected as training data, and a machine learning model is trained using the collected data. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2020-44718 Summary of the Invention [Problem to be solved by the invention]

[0004] However, depending on the equipment, the occurrence frequency of abnormal values may be low, and in such cases, collecting training data may require a significant amount of time. On the other hand, when performing quality assessment using an image-based machine learning model, it is easy to collect training data, but when the workpiece is changed, the same machine learning model cannot be used; instead, a machine learning model must be created and trained for each type of workpiece. Therefore, there is still room for further study on how to create a machine learning model that can be applied to different types of workpieces. Note that this issue is not limited to injection molding machines, but is also common to quality assessment of work in other production equipment. [Means for solving the problem]

[0005] The present disclosure can be realized in the following forms. The judgment method disclosed herein is a judgment method for judging the quality of work performed on workpieces in production equipment, and includes the steps of: (a) using images of the work results of the production equipment as training data to train a first machine learning model that judges the quality of the work results; (b) using work status information of the production equipment when the trained first machine learning model judges the work to be quality as training data labeled with a quality label, and using work status information of the production equipment when the first machine learning model judges the work to be quality as training data labeled with a quality label to train a second machine learning model that uses the work status information as input and outputs the quality of the work results; and (c) inputting work status information of the production equipment for work performed on new workpieces having the same specifications as the workpieces into the trained second machine learning model to judge the quality of the work performed on the new workpieces.

[0006] (1) According to a first aspect of the present disclosure, there is provided a judgment system for judging the quality of work performed on workpieces in a production facility, the judgment system including: a detection unit for detecting work status information of the production facility; a first machine learning model for judging the quality of the work results using an image of the work results of the production facility as input; and a second machine learning model that is trained using the work status information of the production facility when the first machine learning model judges the work results to be quality as teacher data labeled with quality, and the work status information of the production facility when the first machine learning model judges the work results to be quality as teacher data labeled with quality. According to this judgment system, the quality of the work results of the production equipment is judged using a first machine learning model trained using images for which training data is relatively easy to collect, and the work status information at that time is used as training data to train a second machine learning model, making it easy to build a judgment system that judges the quality of work from the work status information of the production equipment.In addition, the second machine learning model can be applied to different types of work. (2) In the above-described determination system, the production equipment may be a coating equipment equipped with an injection unit that injects a coating liquid onto the workpiece, and the work status information may include the injection pressure of the injection unit and driving information of a driving unit that changes the relative position between the workpiece and the injection unit. According to this determination system, it is possible to easily construct a determination system that determines whether work is good or bad based on work status information of the coating equipment. (3) According to a second aspect of the present disclosure, there is provided a method for determining whether work performed on a workpiece in a production facility is acceptable, the method including: (a) using images of work results of the production facility as training data to train a first machine learning model that determines whether the work results are acceptable; (b) using work status information of the production facility when the trained first machine learning model determines the work is acceptable as training data labeled with a good label, and work status information of the production facility when the first machine learning model determines the work is unacceptable as training data labeled with a bad label to train a second machine learning model; and (c) inputting work status information of the production facility for work performed on a new workpiece having the same specifications as the workpiece into the trained second machine learning model to determine whether the work on the new workpiece is acceptable. According to this judgment method, the quality of the work results of the production equipment is judged using a first machine learning model trained using images for which training data is relatively easy to collect, and the work status information at that time is used as training data to train a second machine learning model, so the quality of the work can be easily judged from the work status information of the production equipment. In addition, the second machine learning model can be applied to different types of work. (4) The above judgment method may further include (d) a step of inputting work status information of the production equipment when working on other work having specifications different from the work into the trained second machine learning model, and performing a judgment on the quality of the work on the other work. According to this determination method, it is possible to easily determine whether work performed on other workpieces with different specifications is good or bad. [Brief explanation of the drawings]

[0007] [Figure 1] FIG. 2 is a functional block diagram of a determination system. [Figure 2] FIG. 1 is an explanatory diagram showing a configuration example of a coating facility. [Figure 3] 1 is a flowchart showing a processing procedure according to an embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0008] 1 is a functional block diagram of a determination system according to an embodiment of the present disclosure. This determination system includes an image-based automatic determination device 100, a production status information-based machine learning device 200, and a coating facility 300 as production equipment. The automatic determination device 100, the machine learning device 200, and the coating facility 300 can transmit and receive various data via their respective communication units 110, 210, and 310. Facilities other than the coating facility 300 can also be used as production equipment.

[0009] The image-based automatic judgment device 100 includes a communication unit 110, a control unit 120, first teacher data 130, a learning execution unit 140, a first machine learning model 150, a judgment execution unit 160, and an imaging device 170. The first teacher data 130 and the first machine learning model 150 are stored in a storage device such as a hard disk. The control unit 120 includes a processor and memory, and executes control of the automatic judgment device 100. The learning execution unit 140 executes learning of the first machine learning model 150 using the first teacher data 130. The judgment execution unit 160 executes a pass / fail judgment using the trained first machine learning model 150, taking as input an image of a workpiece that has been coated by coating equipment 300. The functions of the learning execution unit 140 and the judgment execution unit 160 may be implemented by the processor of the control unit 120 executing a computer program, or may be implemented by a hardware circuit.

[0010] The first teacher data 130 is image-based teacher data. That is, the first teacher data 130 is data in which a workpiece coated by the coating equipment 300 is photographed by the imaging device 170 and the image is labeled as good or bad by an operator. The first machine learning model 150 is trained using the first teacher data 130. Therefore, the first machine learning model 150 is a model that uses an image of the work result of the coating equipment 300 as input and judges whether the work result is good or bad. The judgment execution unit 160 uses an image of a new workpiece as input data for the trained first machine learning model 150 and judges whether the workpiece is good or bad. This input data is an image of the workpiece after the coating work, photographed by the imaging device 170.

[0011] The production status information-based machine learning device 200 includes a communication unit 210, a control unit 220, second teacher data 230, a learning execution unit 240, and a second machine learning model 250. The second teacher data 230 and the second machine learning model 250 are stored in a storage device such as a hard disk. The control unit 220 includes a processor and a memory, and executes control of the machine learning device 200. The learning execution unit 240 executes learning of the second machine learning model 250 using the second teacher data 230. The function of the learning execution unit 240 may be implemented by the processor of the control unit 220 executing a computer program, or may be implemented by a hardware circuit.

[0012] The second training data 230 is training data based on production status information. That is, the second training data 230 is training data in which the work status information of the coating equipment 300 is judged as good by the first machine learning model 150 in the above-described automatic judgment device 100 as good-labeled work status information, and the work status information of the coating equipment 300 is judged as bad by the first machine learning model 150 as bad-labeled work status information. The second machine learning model 250 is trained using the second training data 230. Therefore, the second machine learning model 250 is a model that uses the work status information of the coating equipment 300 as input and judges the quality of the work results. The trained second machine learning model 250 is transferred from the machine learning device 200 to the coating equipment 300 via the communication unit 210 and stored in a storage device.

[0013] The coating equipment 300 includes a communication unit 310, a control unit 320, a trained second machine learning model 330, a judgment execution unit 340, a work state detection unit 350, a drive unit 360, and a coating liquid ejection unit 370. The second machine learning model 330 is transferred to the coating equipment 300 and stored in a storage device after learning in the machine learning device 200 is completed. The work state detection unit 350 detects work state information indicating the work state of the coating equipment 300. The judgment execution unit 340 inputs the work state information detected by the work state detection unit 350 into the second machine learning model 330 and judges whether the work is good or bad. The drive unit 360 moves the members and workpieces of the coating equipment 300. The coating liquid ejection unit 370 ejects the coating liquid onto the workpiece.

[0014] FIG. 2 is an explanatory diagram showing an example configuration of a coating equipment 300. This coating equipment 300 includes a base 10, a support mechanism 20 having a support portion 22 that supports the workpiece WK, a motor 30 that moves the support mechanism 20, and an injection nozzle 40 that injects a coating liquid onto the surface of the workpiece WK. The support mechanism 20 and motor 30 are installed on the base 10. FIG. 2 shows the X-axis and Y-axis, which indicate horizontal directions, and the Z-axis, which indicates a vertically upward direction. A drive unit 360 including the motor 30 changes the relative position between the workpiece WK and the injection nozzle 40 at least in the horizontal direction, thereby positioning the tip of the injection nozzle 40 in a predetermined coating area on the surface of the workpiece WK. If the workpiece WK is curved, the drive unit 360 including the motor 30 moves the relative position between the workpiece WK and the injection nozzle 40 three-dimensionally. By injecting the coating liquid from the injection nozzle 40 while moving the workpiece WK, the coating liquid can be applied to the entire coating area of the workpiece WK. Instead of using such a motor 30, an articulated robot may be used to position the injection nozzle 40 at a desired position on the workpiece WK. In this embodiment, the workpiece WK is a vehicle glass, and the coating liquid is a urethane adhesive for glass. The motor 30 constitutes a part of the drive unit 360 in FIG. 1, and the injection nozzle 40 constitutes a part of the coating liquid injection unit 370 in FIG. 1.

[0015] The work status detection unit 350 of the coating equipment 300 in FIG. 1 detects work status information indicating the status of the drive unit 360 and the coating liquid ejection unit 370 during the coating operation. As information indicating the status of the drive unit 360, for example, drive information such as the current value of the motor 30 is detected. As information indicating the status of the coating liquid ejection unit 370, for example, the injection pressure of the injection nozzle 40 is detected. The work status detection unit 350 may further detect the distance between the tip of the injection nozzle 40 and the surface of the workpiece WK as work status information. The work status detection unit 350 is preferably configured to include sensors for detecting these various pieces of work status information.

[0016] Generally, urethane is often used as an adhesive for glass attached to vehicle bodies. In application equipment that applies urethane to glass, defects such as the urethane breaking or chipping can occur when air or foreign matter gets mixed in. When performing quality assessments for such work using a machine learning model, two possible inputs are available: one is to use an image of the glass after urethane application as input to the machine learning model, and the other is to use work status information of the application equipment during the application work as input to the machine learning model. Of these, the method using work status information as input is considered more versatile when producing multiple vehicle models because it is not affected by changes in the shape of the glass. However, due to factors such as the low frequency of abnormalities, it is difficult to train a machine learning model using work status information as training data. Therefore, in this embodiment, as described below, a quality assessment of the work results is performed using an image-based first machine learning model 150 based on visual inspection, and the quality assessment results are used to create second training data 230, which is labelled with quality or non-quality, and the second training data 230 is used to train the second machine learning model 250. By using the trained second machine learning model, it is possible to build a highly versatile judgment system that can judge whether the coating work is good or bad based on work status information.

[0017] The first machine learning model 150 and the second machine learning model 250 can be various types of models that can make pass / fail judgments, such as a model that uses a neural network or a model that uses a decision tree.

[0018] 1 can be arbitrarily changed. For example, the function of the machine learning device 200 may be implemented in the automatic determination device 100 or the application equipment 300. Alternatively, the functions of the three devices 100, 200, and 300 may all be implemented in the application equipment 300.

[0019] FIG. 3 is a flowchart showing the processing procedure of the embodiment. In step S110, the learning execution unit 140 of the automatic judgment device 100 uses image-based first teacher data 130 to train the first machine learning model 150 for a coating operation on a workpiece WK with specific specifications. For example, the windshield of a specific vehicle model is used as the workpiece WK with specific specifications. In this case, it is preferable to specify a vehicle model with a high production volume and for which a large amount of first teacher data 130 can be prepared as the specific vehicle model. The first teacher data 130 is an image of the workpiece WK coated with urethane, labeled with a pass / fail judgment result obtained through visual inspection. It is preferable to capture the image at an angle of view that captures the urethane defect to be detected. If the number of images containing abnormalities is small, it is preferable to create several defective products that can serve as a standard for determining defects in visual inspection by humans and photograph these as well. Once the required amount of first teacher data 130 for machine learning has been collected, the first machine learning model 150 is trained. It is preferable that the first machine learning model 150 after learning has improved judgment accuracy to the point where it can detect various defects while satisfying the standards of visual inspection by humans.

[0020] In step S120, work status information of the coating equipment 300 during coating operations for a large number of workpieces WK is detected and recorded. The coating results are then evaluated for quality using the trained first machine learning model 150, and the evaluation results are recorded. First, work status information detected by the work status detection unit 350 during coating operations for each workpiece WK is recorded. As described above, the work status information preferably includes drive information, such as the current value of the drive unit 360, and the injection pressure of the coating liquid injection unit 370. In step S120, an image of the urethane-coated workpiece WK is captured by the imaging device 170, and the image is input to the first machine learning model 150 for quality evaluation, and the evaluation results are recorded. This evaluation result is linked to work status information for the same workpiece WK. To perform this association, it is preferable to record the quality evaluation results and work status information from the first machine learning model 150 together with information such as the detailed date and time and the serial number of the vehicle being produced.

[0021] In step S130, the second teacher data 230 is created by assigning a label to the work status information obtained in step S120 according to the pass / fail judgment result by the first machine learning model 150. For example, a good label "1" is assigned to work status information relating to a workpiece judged to be a good product, and a bad label "0" is assigned to work status information relating to a workpiece judged to be a defective product.

[0022] In step S140, learning execution unit 240 of machine learning device 200 executes learning of second machine learning model 250 using second teacher data 230. The learned second machine learning model 250 is transferred from machine learning device 200 to coating equipment 300 and stored in a storage device as second machine learning model 330.

[0023] In step S150, the judgment execution unit 340 of the coating equipment 300 applies the judgment made by the trained second machine learning model 330 to the coating work on a workpiece WK with the same specifications as the workpiece used in steps S110 and S120. Because the learning of the second machine learning model 250 is performed using the work results of many workpieces WK with the same specifications, it is possible to judge with high accuracy whether the coating work is good or bad on a new workpiece WK with the same specifications.

[0024] In step S160, the judgment execution unit 340 of the coating equipment 300 applies the judgment made by the trained second machine learning model 330 to the coating work of a workpiece having specifications different from those of the workpiece that was the subject of judgment in step S150. The pass / fail judgment using the second machine learning model 330 is a highly versatile judgment that is not affected by differences in the appearance of the workpiece, so by applying this judgment to workpieces having different specifications, it is possible to prevent defective products from being released from the coating equipment 300. However, it is preferable that the "workpiece having different specifications" is a part of the same type as the workpiece that was the subject of judgment in step S150, such as glass.

[0025] As described above, in the above-described embodiment, the quality of the work results of the coating equipment 300 is determined using the first machine learning model 150 trained using images for which training data is relatively easy to collect, and the second machine learning model 250 is trained using the work status information at that time as the second training data 230, so that the quality of the work can be easily determined from the work status information of the coating equipment 300. Furthermore, the trained second machine learning model 330 can also be applied to workpieces with different specifications.

[0026] The present disclosure is not limited to the above-described embodiments, embodiments, and variations, and can be realized in various configurations without departing from the spirit thereof. For example, the technical features in the embodiments, embodiments, and variations corresponding to the technical features in each aspect described in the Summary of the Disclosure section can be appropriately replaced or combined to solve some or all of the above-described problems or achieve some or all of the above-described effects. Furthermore, if a technical feature is not described as essential in this specification, it can be deleted as appropriate. [Explanation of symbols]

[0027] 10... stand, 20... support mechanism, 22... support unit, 30... motor, 40... injection nozzle, 100... automatic judgment device, 110... communication unit, 120... control unit, 130... first teacher data, 140... learning execution unit, 150... first machine learning model, 160... judgment execution unit, 170... imaging device, 200... machine learning device, 210... communication unit, 220... control unit, 230... second teacher data, 240... learning execution unit, 250... second machine learning model, 300... coating equipment, 310... communication unit, 320... control unit, 330... second machine learning model, 340... judgment execution unit, 350... work state detection unit, 360... drive unit, 370... coating liquid injection unit

Claims

[Claim 1] A method for determining whether work performed on a workpiece in a production facility is acceptable or not, comprising: (a) using images of work results of the production equipment as training data to perform learning of a first machine learning model that determines whether the work results are good or bad; (b) using the work status information of the production equipment when the trained first machine learning model judges it to be good as teacher data labeled as good, and the work status information of the production equipment when the trained first machine learning model judges it to be bad as teacher data labeled as bad, to train a second machine learning model that uses the work status information as input and outputs the pass / fail of the work result; (c) inputting work status information of the production equipment in work on a new workpiece having the same specifications as the workpiece into the trained second machine learning model, and performing a quality judgment on the work on the new workpiece; A determination method including:

Images