Quality inspection strategy intelligent selection method and device, equipment and medium

Abstract

The invention relates to an intelligent quality inspection strategy selection method and device, equipment and a medium. The method comprises the following steps: acquiring historical data; analyzing the historical data to generate an accident analysis table; performing principal component analysis on the data in the accident analysis table to obtain main influence factors; and for the to-be-detected products of the same type as the historical data, judging the process configuration parameters of the to-be-detected products based on the main influence factors, and generating a quality inspection strategy recommendation list. According to the method, the factors influencing the product quality are comprehensively obtained through the historical data, and all related information related to the to-be-detected product is integrated into the process configuration parameters, so that the change information influencing the product quality can be grasped in time, the personalized quality inspection strategy recommendation list can be adaptively generated according to the change information, and the quality inspection efficiency is improved. A basis is provided for quality inspection personnel to objectively select a quality inspection strategy during quality inspection, and the quality risk of products is reduced.

Description

Technical Field

[0001] The present invention relates to the field of intelligent technology, and in particular to a quality inspection strategy intelligent selection method, device, equipment and medium. Background Art

[0002] Quality inspection is crucial in the production process, as it directly affects product quality and corporate reputation. By implementing an effective quality inspection strategy, companies can promptly detect and correct defects in the production process to ensure that the final product meets standards and customer expectations. This not only helps reduce the incidence of defective products, but also reduces returns and repair costs, thereby improving customer satisfaction and market competitiveness.

[0003] However, in current MES devices, users need to manually select quality inspection strategies during the process configuration stage. This configuration is usually based on information such as production scale and batch. However, product quality is affected by many factors, including not only production scale and batch, but also material characteristics, production equipment status, and operator skills. These complex factors make it difficult for configuration personnel to grasp all the key information that affects quality, resulting in the quality inspection strategy may not be optimized under all production conditions.

[0004] Insufficient configuration of quality inspection strategies may cause potential quality risks in the production process. For example, when there are major changes in production equipment or processes, the level of quality inspection should be increased, and more stringent sampling or full inspection measures should be selected. However, manual configuration often cannot quickly adapt to these changes, which may result in quality problems not being discovered or corrected in time, thereby increasing quality risks. Summary of the invention

[0005] Based on this, it is necessary to provide a quality inspection strategy intelligent selection method, device, equipment and medium for application in MES devices, which can intelligently configure quality inspection strategies based on comprehensive information, in response to the above technical problems.

[0006] A quality inspection strategy intelligent selection method, characterized in that the method comprises: Acquire historical data; analyze the historical data to generate an accident analysis table; Perform principal component analysis on the data in the accident analysis table to obtain the main influencing factors; For the products to be inspected of the same type as the historical data, the process configuration parameters of the products to be inspected are judged based on the main influencing factors, and a recommended list of quality inspection strategies is generated.

[0007] In one embodiment, the historical data is analyzed to generate an accident analysis table, including: Obtain quality accident records of historical products and construct accident record tables based on factors affecting the accidents; The accident record table is subjected to data conversion to generate an accident analysis table for data analysis.

[0008] In one embodiment, principal component analysis is performed on the data in the accident analysis table to obtain the main influencing factors, including: Performing correlation analysis on the factors in the accident analysis table to obtain a thermal table of accident influencing factors; Analyze the thermal table of factors affecting the accident to obtain relevant factors; Filtering the accident analysis table according to the related factors to obtain an analysis base table; Set a cumulative variance explanation threshold, perform calculations based on the analysis base table, and take factors greater than the cumulative variance explanation threshold as principal components; The relationship between the principal components and influencing factors was analyzed through factor loading coefficients and commonality indexes to obtain the main influencing factors.

[0009] In one of the embodiments, the process configuration parameters of the product to be inspected include production orders, processes, production and processing activities, and quality activities.

[0010] In one embodiment, the process configuration parameters of the product to be inspected are judged based on the main influencing factors, and a quality inspection strategy recommendation list is generated, including: Obtaining a production order, and configuring production and processing activities of a process according to the production order; During the production and processing activities, quality inspection strategies are configured for the quality activities of the products to be inspected according to the main influencing factors, and a recommended list of quality inspection strategies is generated.

[0011] In one of the embodiments, a quality inspection plan is generated according to the quality inspection strategy recommendation list; The quality inspection plan includes: quality inspection strategy, random inspection items, inspection time, and inspection personnel.

[0012] In one embodiment, the quality inspection strategy includes initial inspection, random inspection, and full inspection; Among them, random inspection also includes the proportion and quantity of random inspection.

[0013] A quality inspection strategy intelligent selection device, the device comprising: An accident analysis table generation module is used to obtain historical data; analyze the historical data and generate an accident analysis table; A main influencing factor determination module is used to perform principal component analysis on the data in the accident analysis table to obtain the main influencing factors; The quality inspection strategy recommendation list generation module is used to judge the process configuration parameters of the products to be inspected that are of the same type as the historical data based on the main influencing factors, and generate a quality inspection strategy recommendation list.

[0014] A computer device includes a memory and a processor, wherein the memory stores a computer program, and is characterized in that the processor implements the steps of the quality inspection strategy intelligent selection method when executing the computer program.

[0015] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the quality inspection strategy intelligent selection method.

[0016] The above-mentioned quality inspection strategy intelligent selection method, device, equipment and medium obtain historical data; analyze the historical data to generate an accident analysis table; perform principal component analysis on the data in the accident analysis table to obtain the main influencing factors; for the products to be inspected of the same type as the historical data, the process configuration parameters of the products to be inspected are judged based on the main influencing factors to generate a quality inspection strategy recommendation list. The present invention comprehensively obtains the factors affecting product quality through historical data, and integrates all relevant information related to the products to be inspected into the process configuration parameters, so that the change information affecting product quality can be grasped in time, and then the personalized quality inspection strategy recommendation list can be adaptively generated according to the change information, which provides a basis for quality inspectors to objectively select quality inspection strategies during quality inspection and reduce product quality risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.

[0018] Figure 1 A schematic diagram of a process for intelligently selecting a quality inspection strategy in one embodiment; Figure 2 A schematic diagram of the association of various systems in an embodiment; Figure 3 It is a structural block diagram of a quality inspection strategy intelligent selection device in one embodiment; Figure 4 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment.

[0019] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0021] It should be noted that the technical solutions between the various embodiments of the present invention can be combined with each other, but it must be based on the fact that ordinary technicians in the field can implement it. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0022] The following will describe the implementation of the present invention in detail with reference to the accompanying drawings in the embodiment diagram of the present invention.

[0023] Example 1 In the MES management system, quality inspection is a key link to ensure that product quality meets standards. By performing quality inspection activities, various performance indicators of the product can be strictly inspected and tested. In daily production activities, before the quality inspector conducts quality inspection on a certain material, it is necessary to configure the quality inspection plan in the process configuration stage. The quality inspection plan is a work arrangement for quality inspection work according to the production plan, the basis for assigning the work of quality inspectors, and a guide for correctly collecting quality data.

[0024] The quality inspection plan is usually composed of quality inspection classification, sampling inspection items, etc. Among them, the quality inspection classification includes incoming material quality inspection, process quality inspection, warehouse inspection and outgoing inspection. Specifically, incoming material quality inspection refers to the quality inspection after the material is delivered to the warehouse, and the quality is determined according to the inspection standards. Process quality inspection refers to the quality inspection of the product from the material into production to the final packaging of the product, mainly to prevent a large number of unqualified products from flowing into the next process for further processing. Process quality inspection includes first inspection, sampling inspection, full inspection, etc. The first inspection is to conduct quality inspection on the first work-in-progress of the same batch of generated orders. Sampling inspection is to conduct sampling quality inspection on the work-in-progress with a certain sampling strategy. Full inspection is to conduct quality inspection on all the work-in-progress of the batch. Incoming inspection refers to the quality inspection required for the finished product after the last process of the work-in-progress is completed. Outgoing inspection refers to the quality inspection required before the product is shipped out of the sales link.

[0025] The quality inspection strategy of the present invention is mainly used for the configuration strategy of process quality inspection, that is, how to choose the first inspection, random inspection and full inspection. Different industries and different customers have different production methods and types, and their quality standards are also different. When formulating the quality inspection strategy, the present invention compiles the quality inspection plan and quality inspection strategy according to the production scale, product complexity, process, product characteristics and batch size. By balancing the relationship between quality, cost and efficiency, comprehensively evaluating the factors affecting quality in historical data, automatically configuring the quality inspection strategy, and reducing quality risks.

[0026] See also Figure 1 , is a quality inspection strategy intelligent selection method disclosed in this embodiment, which comprehensively obtains factors affecting product quality through historical data, and integrates all relevant information related to the product to be inspected into the process configuration parameters, so as to timely grasp the change information affecting product quality, and then can adaptively generate a personalized quality inspection strategy recommendation list based on the change information, providing a basis for quality inspectors to objectively select quality inspection strategies during quality inspection and reduce product quality risks. Specifically, it includes the following steps: Step 201, obtaining historical data; analyzing the historical data to generate an accident analysis table.

[0027] Step 202, perform principal component analysis on the data in the accident analysis table to obtain the main influencing factors.

[0028] Step 203 , for the products to be inspected of the same type as the historical data, the process configuration parameters of the products to be inspected are judged based on the main influencing factors, and a quality inspection strategy recommendation list is generated.

[0029] Understandable, see Figure 2 The present invention associates the MES (manufacturing execution) system with the ERP (enterprise resource planning) system, the PLM (product lifecycle management) system, and the SCADA (data acquisition and monitoring system) so as to be able to fully obtain the information of the products to be inspected, and then integrate it into the process configuration parameters to generate a quality inspection strategy recommendation list. Among them, the ERP (enterprise resource planning) system is responsible for the planning and management of enterprise resources, including finance, procurement, sales, inventory, production and other aspects. The PLM (product lifecycle management) system is responsible for creating, distributing and managing information on the entire life cycle of the product, including drawings and document management and other aspects. The MES (manufacturing execution) system is responsible for monitoring and management of the production process, including production planning, process execution management, equipment management, quality management and other modules. SCADA (data acquisition and monitoring system) is responsible for monitoring and controlling the equipment running in the workshop, including functions such as data acquisition, equipment control, measurement, parameter adjustment and various signal alarms.

[0030] In the specific implementation process of step 201, historical data is analyzed to generate an accident analysis table, including: Obtain quality accident records of historical products, and construct an accident record table based on factors affecting the accidents; perform data conversion on the accident record table to generate an accident analysis table for data analysis.

[0031] In the specific implementation process of step 202, principal component analysis is performed on the data in the accident analysis table to obtain the main influencing factors, including: The factors in the accident analysis table are subjected to correlation analysis to obtain a thermal table of accident influencing factors; the thermal table of accident influencing factors is analyzed to obtain the factors with correlation; the accident analysis table is subjected to data filtering according to the factors with correlation to obtain an analysis base table; a cumulative variance explanation threshold is set, and calculations are performed based on the analysis base table, and factors greater than the cumulative variance explanation threshold are taken as principal components; the relationship between the principal component and the influencing factors is analyzed through the factor load coefficient and the commonality index to obtain the main influencing factors.

[0032] In the specific implementation process of step 203, the process configuration parameters of the product to be inspected are judged based on the main influencing factors, and a quality inspection strategy recommendation list is generated, including: Obtain a production order, and configure the production and processing activities of the process according to the production order.

[0033] During the production and processing activities, quality inspection strategies are configured for the quality activities of the products to be inspected according to the main influencing factors, and a recommended list of quality inspection strategies is generated.

[0034] It is worth noting that the present invention encapsulates the method in a modular manner and sets an "automatic matching" module in the MES system. In the process configuration stage, the user only needs to obtain the scheduled production order from the MES system; the user configures the production and processing activities of the process; the user configures the quality management activities of the process, and selects "automatic matching" when configuring the quality inspection strategy. The system will automatically generate a recommended list of quality inspection strategies for the user to choose; in the process execution stage, after completing a production and processing activity process, the system automatically issues a quality inspection task to the quality inspection station; the quality inspector performs quality inspection activities according to the quality inspection strategy selected by the user, and reports the quality inspection results through the inspection report.

[0035] That is to say, the process configuration parameters include production orders, processes, production and processing activities, and quality activities. Among them, the production order is a production task generated based on the customer's purchase order, preferably including the production order number, batch number, product name, product model, and the associated process number and process name. The process is various production and processing activities or quality activities in the workshop. Production and processing activities are various activities for producing and processing materials according to process requirements, preferably including patching, welding, dispensing, machining, assembly, packaging, etc. Quality activities are activities related to quality management in the process, preferably including incoming material inspection, process inspection, warehouse in and out inspection, etc. The inspection report is a form for recording the results of quality inspection activities, including quality inspection items, quality inspection targets, test values, results, etc.

[0036] In one of the embodiments, it further includes: generating a quality inspection plan based on the quality inspection strategy recommendation list.

[0037] It can be understood that the quality inspection plan is the plan adopted by the quality inspector when conducting process inspection, preferably including quality inspection strategy, sampling inspection items, inspection time, and inspection personnel. The quality inspection plan needs to be configured before the quality inspection task is issued to the quality inspector.

[0038] The quality inspection strategy is the sampling strategy used in quality inspection, preferably including: a) first inspection (default); b) random inspection; c) full inspection. Furthermore, random inspection includes the proportion or quantity of random inspection, such as "10%", "10 pieces".

[0039] The recommended list of quality inspection strategies is a sampling strategy automatically recommended by the method of the present invention, including preferred and secondary strategies and reasons for recommendation, for example, "preferred strategy (recommended): full inspection; secondary strategy, random inspection. Reason: the product is a satellite payload product, the customer has high quality requirements, and full inspection is recommended."

[0040] In one of the embodiments, in order to make the solution of the present invention clearer, the method provided by the present invention is exemplified.

[0041] When obtaining a recommended list of quality inspection strategies, data analysis is mainly performed based on the historical data of the product type to obtain influencing factor events that affect product quality. When it is determined that an influencing factor event occurs, the quality standard level of the product quality inspection strategy is improved.

[0042] Specifically, firstly, based on historical data, we collect the production quality accident records of similar products and draw a table with various factors that may affect the accident, such as design changes, BOM changes, tooling changes, supplier changes, production equipment maintenance, team changes, etc. As shown below:

[0043] Then perform data transformation on the above table to generate an accident analysis table for data analysis, as shown below:

[0044] By using principal component analysis to study, we can obtain the factors that really affect the accident in the accident analysis table. It can be understood that principal component analysis is a statistical method that reduces multiple variables into a few principal components by means of dimensionality reduction. The components can reflect most of the information of the original variables. Before performing principal component analysis, we must first check whether there is a linear correlation between the variables.

[0045] Therefore, the factors in the accident analysis table are subjected to correlation analysis, the Pearon algorithm is used to process the above accident analysis table, and the thermal table of accident influencing factors can be obtained through thermal map display, as shown below:

[0046] Judging from the results of the thermal table of accident influencing factors, there is a correlation between design changes, tooling changes, supplier changes and team adjustments. These variables can be used as the basic data for principal component analysis.

[0047] Then filter the data in the accident analysis table to keep only the factors with relevant relationships, and get the basic analysis table as shown below:

[0048] The cumulative variance explanation threshold is set and calculated based on the analysis base table. From the analysis base table, it can be seen that the principal component analysis will construct 4 principal components, which are 5.13, 1.803, 1.25, and 0.982 respectively. The variance explanation rates of these 4 principal components are 42.749%, 15.028%, 10.413%, and 8.18%, respectively, and the cumulative variance explanation rate is 76.37%.

[0049] Furthermore, the relationship between the above principal components and influencing factors is analyzed through factor loading coefficients and commonality indexes. As follows:

[0050] From the results, it can be seen that the first principal component is related to design changes and tooling changes, the second principal component is related to supplier changes, the third principal component is related to production equipment maintenance, and the fourth principal component is related to team adjustments.

[0051] The above analysis results show that the above four factors will have an impact on the final product production quality, and these four factors are related to the accident influencing factors such as design changes, tooling changes, supplier changes and team adjustments. Furthermore, when these accident influencing factors occur, the probability of production accidents will increase, which means that more stringent quality inspection strategies should be adopted to reduce the risk of production accidents.

[0052] When one of the above accident influencing factors occurs, for example, when "design change" occurs, the quality inspection level can be raised by one level, such as changing "exemption from inspection" to "spot inspection" or "first inspection". If multiple accident influencing factors occur at the same time, the quality inspection level can be raised to the highest level, such as "full inspection".

[0053] Furthermore, after the MES system generates a recommended list of quality inspection strategies, the user can choose any one of the preferred and suboptimal strategies, or may not accept the strategy recommended by the system. At this time, the user can directly choose any one of "full inspection", "spot inspection" or "first inspection".

[0054] Example 2 Based on the quality inspection strategy intelligent selection method in Example 1, this embodiment discloses a quality inspection strategy intelligent selection device, such as Figure 3As shown, the quality inspection strategy intelligent selection device includes: an accident analysis table generation module 401, a main influencing factor determination module 402 and a quality inspection strategy recommendation list generation module 403, wherein: The accident analysis table generation module 401 is used to obtain historical data; analyze the historical data and generate an accident analysis table.

[0055] The main influencing factor determination module 402 is used to perform principal component analysis on the data in the accident analysis table to obtain the main influencing factors; The quality inspection strategy recommendation list generation module 403 is used to judge the process configuration parameters of the products to be inspected that are of the same type as the historical data based on the main influencing factors, and generate a quality inspection strategy recommendation list.

[0056] In this embodiment, the specific working process and working principle of the accident analysis table generation module 401, the main influencing factor determination module 402 and the quality inspection strategy recommendation list generation module 403 are the same as those in the method of embodiment 1, so they are not described in detail in this embodiment. Each unit module can be implemented in whole or in part by software, hardware and a combination thereof, and each unit module can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above unit modules.

[0057] Example 3 like Figure 4 As shown, a computer device disclosed in this embodiment can be a server. It includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store computer execution instructions, and the processor is used to execute the computer execution instructions stored in the memory to implement the method in the above-mentioned embodiment 1.

[0058] Example 4 This embodiment discloses a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the method in the above-mentioned embodiment 1 is implemented.

[0059] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0060] The above-mentioned embodiments only express several implementation modes of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the invention. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the attached claims.

Claims

1. A quality inspection strategy intelligent selection method, characterized in that: The method comprises: Acquire historical data; analyze the historical data to generate an accident analysis table; Perform principal component analysis on the data in the accident analysis table to obtain the main influencing factors; For the products to be inspected of the same type as the historical data, the process configuration parameters of the products to be inspected are judged based on the main influencing factors, and a recommended list of quality inspection strategies is generated.

2. The quality inspection strategy intelligent selection method according to claim 1 is characterized in that: Analyze the historical data to generate an accident analysis table, including: Obtain quality accident records of historical products and construct accident record tables based on factors affecting the accidents; The accident record table is subjected to data conversion to generate an accident analysis table for data analysis.

3. The quality inspection strategy intelligent selection method according to claim 2 is characterized in that: The data in the accident analysis table are subjected to principal component analysis to obtain the main influencing factors, including: Performing correlation analysis on the factors in the accident analysis table to obtain a thermal table of accident influencing factors; Analyze the thermal table of factors affecting the accident to obtain relevant factors; Filtering the accident analysis table according to the related factors to obtain an analysis base table; Set a cumulative variance explanation threshold, perform calculations based on the analysis base table, and take factors greater than the cumulative variance explanation threshold as principal components; The relationship between the principal components and influencing factors was analyzed through factor loading coefficients and commonality indexes to obtain the main influencing factors.

4. The quality inspection strategy intelligent selection method according to any one of claims 1 to 3, characterized in that: The process configuration parameters of the products to be inspected include production orders, processes, production and processing activities, and quality activities.

5. The quality inspection strategy intelligent selection method according to claim 4 is characterized in that: Based on the main influencing factors, the process configuration parameters of the product to be inspected are judged and a quality inspection strategy recommendation list is generated, including: Obtaining a production order, and configuring production and processing activities of a process according to the production order; During the production and processing activities, quality inspection strategies are configured for the quality activities of the products to be inspected according to the main influencing factors, and a recommended list of quality inspection strategies is generated.

6. The quality inspection strategy intelligent selection method according to claim 5 is characterized in that: Also includes: Generate a quality inspection plan according to the quality inspection strategy recommendation list; The quality inspection plan includes: quality inspection strategy, random inspection items, inspection time, and inspection personnel.

7. The quality inspection strategy intelligent selection method according to claim 6 is characterized in that: The quality inspection strategy includes initial inspection, random inspection, and full inspection; Among them, random inspection also includes the proportion and quantity of random inspection.

8. A quality inspection strategy intelligent selection device, characterized in that: The device comprises: An accident analysis table generation module is used to obtain historical data; analyze the historical data and generate an accident analysis table; A main influencing factor determination module is used to perform principal component analysis on the data in the accident analysis table to obtain the main influencing factors; The quality inspection strategy recommendation list generation module is used to judge the process configuration parameters of the products to be inspected that are of the same type as the historical data based on the main influencing factors, and generate a quality inspection strategy recommendation list.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the quality inspection strategy intelligent selection method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the quality inspection strategy intelligent selection method described in any one of claims 1 to 7 are implemented.

Images