JP2024039749A - Inspection management system - Google Patents

Abstract

[Problem] To provide an inspection management system capable of accurately identifying the cause of a defect. [Solution] The inspection management system includes an inspection information input unit for inputting inspection information, an inspection information database for storing the input inspection information, a defect information input unit for inputting the defect location and the defect cause, an estimation unit for estimating the defect cause using the input information on the defect location and the inspection information stored in the inspection information database, and a display unit for displaying the estimated defect cause. [Selected Figure] Figure 1

Description

The present disclosure relates to an examination management system.

For example, in the vehicle inspection management system described in Patent Document 1, it is possible to display a ranking of the cause of a defect with respect to a defect phenomenon, and also to display a ranking of how to correct the cause of the defect. Help identify rework options.

Japanese Patent Application Publication No. 2005-301872

However, in the vehicle inspection management system with the above configuration, estimating the cause of a problem depends on the knowledge and experience of the worker. However, there was a problem in that it was difficult to identify the correct cause of the problem.

The present disclosure can be realized as the following forms.

According to one form of the present disclosure, a test management system is provided. This inspection management system includes an inspection information input section for inputting inspection information, an inspection information database for storing the inputted inspection information, a defect information input section for inputting defect locations and causes of the defect, and an inspection information input section for inputting the inputted inspection information. comprising: an estimating unit that estimates the cause of the failure using location information and the inspection information stored in the inspection information database; and a display unit that displays the estimated cause of the failure;
According to this type of inspection management system, the estimating section estimates the cause of the defect using the input information on the defect location, and the display section displays the estimated cause of the defect. Therefore, the operator who manages the inspection can estimate the cause of the defect using past inspection information, and can accurately identify the cause of the defect.
Note that this system may be applied to, for example, a system using machine learning.

1 is a block diagram schematically showing the configuration of a test management system according to a first embodiment of the present disclosure. 4 is a flowchart showing each step of inspection management executed by the inspection management system. FIG. 6 is a diagram illustrating an example of a screen display of a result of estimating the cause of a problem.

A. First embodiment:
A1. Overall configuration of inspection management system 1:
A first embodiment of the present disclosure will be described below with reference to FIGS. 1 to 3. FIG. 1 is a block diagram schematically showing the configuration of a test management system 1 according to a first embodiment of the present disclosure. The inspection management system 1 of the first embodiment is placed, for example, in a line that manufactures vehicle parts, performs inspection management of manufactured parts, determines whether or not to rework parts for which defects have been detected, and This is a system that selects whether or not to send to the next process.

As shown in FIG. 1, the test management system 1 includes a control section 10, a storage section 20, and an input/output section 30. The inspection management system 1 is configured by a general computer having a processor and memory. More specifically, the inspection management system 1 may be a tablet or a mobile terminal with a touch panel. The control unit 10 is a calculation device that controls the functions of the test management system 1. The control unit 10 is configured by an arithmetic processing device such as a CPU (Central Processing Unit). The storage unit 20 is composed of a storage medium such as a RAM, a magnetic disk, or a flash memory. The input/output unit 30 includes input devices such as a keyboard, mouse, and touch panel, and output display devices such as a monitor and a liquid crystal display screen.

The storage unit 20 stores various data necessary for test management. Specifically, the storage unit 20 includes an examination information database 21. The inspection information database 21 accumulates inspection and manufacturing information as inspection information. Specifically, the inspection information includes various types of information such as the name of the worker conducting the inspection, inspection date and time, product information (serial number, processing date and time, etc.), equipment information (machine number, number of shots, etc.), and inspection results (rank, presence or absence of defects). Contains information.

The input/output section 30 includes an inspection information input section 31, a defect information input section 32, and a display section 33. The test information input unit 31 collects the test information. The defect information input unit 32 collects information on product defects, such as the location of the defect and the cause of the defect. The display unit 33 displays the probability of the cause of the failure estimated by the estimation unit 11, which will be described later, on a monitor or the like. An example of the display screen will be described in detail in the operation of the test management system 1, which will be described later.

The control unit 10 includes a functional module of the estimation unit 11. The estimation unit 11 is realized by executing a program stored in the storage unit 20 by the CPU. The estimating unit 11 estimates the cause of the defect and its probability using the input information on the defect location and the inspection information stored in the inspection information database 21 by statistical methods and machine learning.

A2. Operation of inspection management system 1:
FIG. 2 is a flowchart showing each process of test management executed by the test management system 1. In the test management of the first embodiment, the test management system 1 is operated in turn by two test workers, and a double-check test is performed. The first inspection operator is an unskilled person with relatively little inspection experience, and the second inspection operator is an expert who has more inspection experience than the unskilled person. Further, in this embodiment, a cylinder block manufactured by casting will be described as an example of a product to be inspected.

As shown in FIG. 2, first, in S11, a first inspection worker, an unskilled person, visually inspects the appearance of the product to be inspected. After the visual inspection, the inspection results are input via the inspection information input section 31 by an unskilled person in S12. The inspection results input here include the name of the inspection operator, the serial number of the product, the number of shots, the inspection results indicating the presence or absence of defects, and the like.

Next, in S13, an unskilled person determines whether or not there is a problem in the test results. If there is a defect in the inspection results (S13: Yes), the process proceeds to S14, where the non-skilled person inputs the defect location via the defect information input section 32. For example, the defective location is indicated by marking it with a pointer on the screen.

Then, in S15, the unskilled person confirms the fault cause estimation result estimated by the estimation unit 11, and inputs the fault cause via the fault information input unit 32. The estimating unit 11 estimates the ranking of the cause of the failure using past accumulated data and the information on the failure location input in S14.

FIG. 3 is a diagram showing an example of a screen display of the result of estimating the cause of the problem. As shown in FIG. 3, the failure cause estimation results are displayed on the display unit 33 as an electronic screen, for example, in a ranking format such that there is a 75% possibility that it is a gas defect, and a 25% possibility that it is a sand drop defect. be done. In the example shown in FIG. 3, the defect is a "hole." A "gas defect" is a defect caused by excessive gas contained in the molten metal of the product material or gas absorbed during the flow of the molten metal in the mold. A "sand falling defect" is a defect caused by a part of the sand mold or core breaking and falling during mold covering when manufacturing a product using a mold. Further, in FIG. 3, the mark 41 indicated by a circle is a mark inputted by an unskilled person in S14, as described above, and indicates a defective location.

An unskilled person can refer to the result of estimating the cause of the problem when identifying the cause of the problem. If the cause of the defect can be clearly identified from the visual inspection of the defect in the product, the judgment of an unskilled person will take precedence; however, if it is difficult to identify the cause of the defect, the estimation results should be taken into consideration to determine the possibility of the defect. It is possible to identify the cause of a high number of defects. That is, by displaying the result of estimating the cause of the problem, it is possible to assist an unskilled person in determining the cause of the problem.

Next, in S16, the skilled person confirms the inspection results previously conducted by the unskilled person, and then visually inspects the product to be inspected. Thereafter, in S17, an expert determines whether or not there is a problem in the test results. If there is a defect in the inspection results (S17: Yes), the process proceeds to S18, where the expert confirms the defect location and inputs the cause of the defect via the defect information input section 32. Then, in S19, it is determined whether or not modification is possible. "Can be repaired" means that the defect in the product is minor or that the defect can be improved by repair.

If rework is possible (S19: Yes), the process proceeds to S20, and the product is shipped to a subsequent process. On the other hand, if modification is not possible (S19: No), the product cannot be shipped to a subsequent process, so the process proceeds to S21, where the product is melted again and sent for recycling.

If no defects are found in the visual inspection results in S13 (S13: No), the process proceeds to S16 without going through S14 and S15. If no defects are found in S17 (S17: No), the process proceeds to S20, and the product is shipped to the next process. This completes the product inspection management process.

In addition, in the process detailed above, various data inputted by each worker are accumulated in the inspection information database 21 as appropriate. The test results are then learned in the control unit 10. For example, if the estimation results of an unskilled person and an expert match and both indicate a "gas defect," the probability that the "gas defect" is the cause of the problem is increased from 75% to 80%, for example. Furthermore, if the estimation results of the non-expert and the expert do not match, the probability is lowered from 75% to 70%, for example. These probabilities are reflected in subsequent estimation by the estimation unit 11.

The inspection management system 1 of the first embodiment described in detail above can be operated as follows. First, at the preliminary preparation stage until a certain amount of data has been accumulated, an unskilled person (the first person inspects) inputs inspection information and defect information through a visual inspection, and then an expert person (the second person inspects) performs the inspection. By inputting information and defect information, various information is accumulated in the inspection information database 21.

Based on the data in the inspection information database 21, the estimating unit 11 estimates the probability of the cause of the failure and makes it possible to display it on the display unit 33. Note that the estimation of the cause of the failure includes probability calculation based on data in the inspection information database 21 or a learning model constructed using data in the inspection information database 21.

In the actual operation stage after data accumulation, an unskilled person (the first person inspects) inputs the inspection information during a visual inspection, and at the timing of selecting the defect location in S14, estimates are made based on that information. The unit 11 calculates the probability of the cause of the failure and displays the result on the display unit 33. When unskilled users are unsure about inputting the cause of a problem, they can select a more likely cause of the problem by checking the displayed error cause estimation results. Thereafter, the skilled person (second person inspecting) inputs the inspection information and defect information, and if the identification by the unskilled person (first person inspecting) is incorrect, corrects the cause of the defect.

Data input during actual operation is also accumulated in the inspection information database 21 and utilized for calculating the defect cause estimation, so that the more data is accumulated, the more the defect cause estimation accuracy can be improved. Furthermore, in this embodiment, not only the simple causes of defects but also the inspection tendencies of non-experts and information on the inspection object are stored in association with each other, so that estimation can be made more tailored to the individual worker or the object.

B. Other embodiments:
(B1)
In the first embodiment, the inspection management system 1 is installed on a line that manufactures vehicle parts, but it may be an inspection management system for other products instead of vehicle parts.

The present disclosure is not limited to the embodiments described above, and can be implemented in various configurations without departing from the spirit thereof. For example, the technical features in each embodiment that correspond to the technical features in each form described in the column of the summary of the invention may be used to solve some or all of the above-mentioned problems, or to achieve the above-mentioned effects. In order to achieve some or all of the above, it is possible to perform appropriate replacements or combinations. Further, unless the technical feature is described as essential in this specification, it can be deleted as appropriate.

DESCRIPTION OF SYMBOLS 1... Test management system, 10... Control unit, 11... Estimation unit, 20... Storage unit, 21... Test information database, 30... Input/output unit, 31... Test information input unit, 32...Fault information input section, 33...Display section, 41...Mark

Claims (1)

an inspection information input section for inputting inspection information;
a test information database that stores the input test information;
a defect information input section for inputting the defect location and cause of the defect;
an estimating unit that estimates the cause of the malfunction using the input information on the malfunction location and the inspection information stored in the inspection information database;
a display section that displays the estimated cause of the problem;
An inspection management system equipped with

Images