AI-based inspection method multi-dimensional quality management system

Abstract

The application discloses an AI-based multi-dimensional quality management system for inspection mode, and belongs to the technical field of inspection supervision. The system is used to solve the technical problem of poor multi-dimensional quality supervision and management effect of the inspection mode in the prior art. The system monitors and counts the inspection results of each implementation of the inspection mode, processes and classifies the inspection results of each implementation, performs inspection failure processing of abnormal inspection sets in different dimensions, obtains first inspection failure total values and second inspection failure total values corresponding to different dimensions, performs multi-dimensional quality management data processing and analysis on the first inspection failure total values and the second inspection failure total values obtained through multi-dimensional supervision processing, obtains an inspection quality value corresponding to the existing inspection mode, and optimizes the inspection content of the existing inspection mode and / or optimizes the existing inspection mode according to the analysis result of the inspection quality value.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of inspection supervision, in particular to an AI-based inspection mode multi-dimensional quality management system. BACKGROUND

[0002] Inspection mode multi-dimensional quality management is a quality management strategy that combines multiple technologies and methods, aiming to check and monitor each link in the production or service process through comprehensive and systematic means to ensure that the product or service meets the predetermined quality standards. This management mode not only focuses on the quality of the final product, but also emphasizes the implementation of quality control at each stage of the production process, including raw material procurement, production processing, assembly, testing, and other links.

[0003] The existing inspection mode multi-dimensional quality management scheme mostly stays at the single-level inspection result and management during implementation, for example, only manages the corresponding inspection defects according to the inspection results, cannot implement multi-dimensional evaluation of the existing inspection mode from different aspects, and cannot adaptively implement diversified mining analysis and management of the existing inspection mode and the inspection content involved according to the multi-dimensional evaluation results, resulting in poor multi-dimensional quality supervision and evaluation effect and multi-dimensional quality management effect of the inspection mode. SUMMARY

[0004] The purpose of the present application is to provide an AI-based inspection mode multi-dimensional quality management system to solve the technical problem of poor multi-dimensional quality supervision and evaluation effect and multi-dimensional quality management effect of the inspection mode in the existing scheme.

[0005] The purpose of the present application can be achieved by the following technical solutions:

[0006] The AI-based inspection mode multi-dimensional quality management system comprises:

[0007] An inspection mode implementation supervision processing module is used to monitor and count the inspection results of each implementation of the inspection mode, process and classify the inspection results of each implementation, obtain a normal inspection set and an abnormal inspection set, perform inspection failure processing of the abnormal inspection set in different dimensions, obtain corresponding first inspection failure total value and second inspection failure total value, and upload them to a cloud platform;

[0008] An inspection mode multi-dimensional quality management module is used to perform multi-dimensional quality management data processing analysis on the first inspection failure total value and the second inspection failure total value obtained by multi-dimensional supervision processing, obtain the inspection quality value corresponding to the existing inspection mode, and perform optimization management on the inspection content of the existing inspection mode and / or the existing inspection mode according to the analysis result of the inspection quality value.

[0009] Preferably, the inspection result of each implementation of the inspection mode is traversed and analyzed, if there is no abnormal inspection item in the inspection result, the inspection corresponding to the inspection result is marked as normal inspection;

[0010] If there is at least one inspection item in the inspection result, the inspection corresponding to the inspection result is marked as abnormal inspection, and the inspection component and the first abnormal reason corresponding to the abnormal inspection item are obtained;

[0011] All normal inspection corresponding inspection results are sorted and combined according to the inspection time sequence to obtain a normal inspection set; and all abnormal inspection corresponding inspection results are sorted and combined according to the inspection time sequence to obtain an abnormal inspection set.

[0012] Preferably, all inspection components and first abnormal reasons appearing in the abnormal inspection set are counted, and all first abnormal reasons corresponding to the same inspection component are sorted and combined to obtain an inspection component active processing sequence;

[0013] All inspection component active processing sequences are sorted and combined to obtain an inspection component active processing sequence set;

[0014] In addition, all device components that appear abnormally and corresponding second abnormal reasons are obtained, and different device components and their corresponding second abnormal reasons are analyzed by the inspection implementation identification model to output corresponding component inspection values;

[0015] The component inspection value contains a numerical value of 0, 1 or 2.

[0016] Preferably, the device component corresponding to the component inspection value with a numerical value of 0 is associated with a first inspection abnormal label;

[0017] The device component corresponding to the component inspection value with a numerical value of 1 is associated with a second inspection abnormal label;

[0018] The device component corresponding to the component inspection value with a numerical value of 2 is associated with a third inspection abnormal label;

[0019] All device components corresponding to the first inspection abnormal label are counted and marked as first components, and all device components corresponding to the second inspection abnormal label are counted and marked as second components.

[0020] Preferably, the total number of all first abnormal reasons corresponding to different first components, and the total number of all second abnormal reasons matching the first abnormal reasons, are sequentially obtained by calculation to obtain corresponding first inspection failure values;

[0021] All first inspection failure values are sorted and combined, and the sum of all first inspection failure values after sorting and combining is obtained to obtain a first inspection failure total value.

[0022] Preferably, the total number of all second abnormal causes corresponding to different second components is obtained by calculation to obtain a corresponding second inspection failure value;

[0023] All second inspection failure values are sorted and combined, and all second inspection failure values of the sorted and combined second inspection failure values are summed to obtain a second inspection failure total value.

[0024] Preferably, when the inspection method is subjected to multi-dimensional quality management, the obtained first inspection failure total value and second inspection failure total value are processed through an inspection quality identification model for data analysis, and a corresponding inspection quality value is outputted;

[0025] The inspection quality value contains a numerical value of 0, -1, -2 or -3.

[0026] Preferably, according to the inspection quality value with the numerical value of 0, it is prompted that the inspection quality of the existing inspection method is normal, and the subsequent normal implementation is maintained;

[0027] According to the inspection quality value with the numerical value of -1, it is prompted that the inspection quality of the existing inspection method is first abnormal, and it is prompted to perform optimization management on the corresponding inspection content of the existing inspection method;

[0028] According to the inspection quality value with the numerical value of -2, it is prompted that the inspection quality of the existing inspection method is second abnormal, and it is prompted to perform optimization management on the existing inspection method;

[0029] According to the inspection quality value with the numerical value of -3, it is prompted that the inspection quality of the existing inspection method is third abnormal, and it is prompted to perform optimization management on the existing inspection method and the existing inspection content.

[0030] Compared with the prior art, the present application has the following beneficial effects:

[0031] The present application realizes the following beneficial effects:

[0032] The application obtains the inspection quality value corresponding to the existing inspection mode through the multi-dimensional quality management data processing analysis of the first inspection failure total value and the second inspection failure total value obtained by the multi-dimensional supervision processing, and optimizes the inspection content of the existing inspection mode and / or optimizes the existing inspection mode according to the analysis result of the inspection quality value, realizes the multi-dimensional supervision processing and the optimization management of multiple objects of the existing inspection mode, and improves the multi-dimensional quality supervision evaluation effect and the multi-dimensional quality management effect of the inspection mode. BRIEF DESCRIPTION OF DRAWINGS

[0033] The application will be further described below with reference to the accompanying drawings.

[0034] Fig. 1 The module block diagram of the AI-based multi-dimensional quality management system of the inspection mode of the application.

[0035] Fig. 2 The flowchart of the operation of the AI-based multi-dimensional quality management system of the inspection mode of the application.

[0036] Fig. 3 The flowchart of the multi-dimensional quality management in the application. DETAILED DESCRIPTION

[0037] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, not all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the application.

[0038] As shown in Figs. 1-2 The application is an AI-based multi-dimensional quality management system of the inspection mode, which comprises an inspection mode implementation supervision processing module for monitoring and counting the inspection results of each implementation of the inspection mode, processing and classifying the inspection results of each implementation, obtaining a normal inspection set and an abnormal inspection set, performing inspection failure processing of different dimensions on the abnormal inspection set, obtaining corresponding first inspection failure total value and second inspection failure total value and uploading to the cloud platform; comprising:

[0039] The object of the implementation of the inspection mode can be a device in particular; the specific inspection content corresponding to the inspection mode can be determined according to the actual inspection equipment and the actual inspection requirement data, and is not limited in particular;

[0040] The inspection results of each implementation of the inspection mode are analyzed iteratively, and if there is no abnormal inspection item in the inspection results, the inspection mark corresponding to the inspection results is marked as normal inspection;

[0041] If there is at least one inspection item in the inspection result, the inspection result corresponding to the inspection mark is marked as an abnormal inspection, and the inspection component and the first abnormal reason corresponding to the abnormal inspection item appearing in the abnormal inspection are obtained; the first abnormal reason is determined by the existing verification of the professional technical personnel in the field;

[0042] All normal inspection corresponding inspection results are sorted and combined according to the inspection time sequence to obtain a normal inspection set; and all abnormal inspection corresponding inspection results are sorted and combined according to the inspection time sequence to obtain an abnormal inspection set;

[0043] According to the abnormal inspection set, all inspection components and first abnormal reasons appearing are counted, and all first abnormal reasons corresponding to the same inspection component are sorted and combined to obtain an inspection component active processing sequence;

[0044] All inspection component active processing sequences are sorted and combined to obtain an inspection component active processing sequence set;

[0045] In the embodiment of the application, by processing and classifying all abnormal inspection data, reliable screening data support can be provided for subsequent data analysis of all device components corresponding to different aspects of the abnormal data.

[0046] In addition, all device components appearing abnormally and corresponding second abnormal reasons are obtained, and different device components appearing and corresponding second abnormal reasons are analyzed by an inspection implementation identification model to output corresponding component inspection values BX;

[0047] Wherein, the expression of the inspection implementation identification model is In the formula, a and b are device components and corresponding second abnormal reasons respectively; U1 is a set corresponding to all inspection components; U2 is a set of all abnormal reasons of historical inspection of the device components;

[0048] The component inspection value contains a numerical value of 0, 1 or 2;

[0049] According to the component inspection value with a numerical value of 0, the device component is associated with a first inspection abnormal label;

[0050] According to the component inspection value with a numerical value of 1, the device component is associated with a second inspection abnormal label;

[0051] According to the component inspection value with a numerical value of 2, the device component is associated with a third inspection abnormal label;

[0052] It can be understood that the first inspection abnormality label represents that the corresponding equipment component and the second abnormality reason have been historically inspected and are the same as the first abnormality reason obtained by inspection; the second inspection abnormality label represents that the corresponding equipment component and the second abnormality reason have been historically inspected but are different from all the first abnormality reasons obtained by inspection; and the third inspection abnormality label represents that the corresponding equipment component has not been historically inspected;

[0053] All equipment components corresponding to the first inspection abnormality label are counted and marked as first components, and all equipment components corresponding to the second inspection abnormality label are counted and marked as second components;

[0054] In the embodiment of the application, by performing data processing on all equipment components that have appeared abnormality and corresponding second abnormality reasons, corresponding component inspection values are obtained, and different equipment components that have appeared abnormality are dynamically classified and marked according to the component inspection values, which can provide reliable abnormality classification data support for subsequent existing inspection mode corresponding to different dimension inspection failure data processing;

[0055] The first inspection failure value XSYi corresponding to different first components is calculated by the formula ; in the formula, i is different first components, i = 1, 2, 3, …, n; n is a positive integer; represents the total number of all first components; ai is a component influence coefficient corresponding to different first components, and the specific value can be determined by a person skilled in the art according to inspection experience or according to the total number of historical inspections that have appeared abnormality corresponding to different first components; Ni is the total number of all second abnormality reasons matching the first abnormality reason corresponding to different first components; N0i is the total number of all first abnormality reasons corresponding to different first components;

[0056] All first inspection failure values are sorted and combined, and the sum of all first inspection failure values after sorting and combination is obtained as a first inspection failure total value XSY0;

[0057] And the second inspection failure value XSEj corresponding to different second components is calculated by the formula XSEj = bj × e N1j ; in the formula, j is different second components, j = 1, 2, 3, …, m; m is a positive integer; represents the total number of all second components; bj is a component influence coefficient corresponding to different second components, and the specific value can be determined by a person skilled in the art according to inspection experience or according to the total number of historical inspections that have appeared abnormality corresponding to different first components; N1j is the total number of all second abnormality reasons corresponding to different second components; e is a constant;

[0058] Sort and combine all the second patrol failure values, and sum all the sorted and combined second patrol failure values to obtain a second patrol failure total value XSE0;

[0059] It should be noted that the first patrol failure total value and the second patrol failure total value are used to digitally represent the influence of corresponding patrol failure from different patrol failure types;

[0060] In the embodiment of the application, the patrol results of each implementation of the patrol mode are monitored and counted, and each implementation of the patrol results is processed and classified, and the abnormal patrol set is processed for different dimensions of patrol failure, to obtain the first patrol failure total value and the second patrol failure total value corresponding to different dimensions, which can realize digital processing of patrol failure data of the existing patrol mode from different dimensions, and can provide reliable multi-dimensional data support for subsequent analysis of multi-dimensional quality management of the existing patrol mode.

[0061] The patrol mode multi-dimensional quality management module is used for multi-dimensional quality management data processing and analysis of the first patrol failure total value and the second patrol failure total value obtained by the multi-dimensional supervision processing, to obtain the patrol quality value corresponding to the existing patrol mode, and to optimize the management of the patrol content of the existing patrol mode and / or to optimize the management of the existing patrol mode according to the analysis result of the patrol quality value; comprising:

[0062] As shown in Fig. 3 When the patrol mode is subjected to multi-dimensional quality management, the first patrol failure total value and the second patrol failure total value obtained by processing are subjected to data analysis by a patrol quality identification model, and the corresponding patrol quality value XZ is outputted;

[0063] The expression of the patrol quality identification model is In the formula, A, B, and C are respectively the first patrol failure limit value, the second patrol failure limit value, and the third patrol failure limit value, and the specific values can be determined according to actual patrol requirement data, or can be determined according to test data of the existing patrol mode in the early implementation stage, and the specific values are not limited; XSS0 is the third patrol failure value;

[0064] The third patrol failure value is calculated by the formula In the formula, N2 is the total number of occurrences of the third patrol abnormal label; NZ is the total number of all patrol components subjected to patrol by the existing patrol mode;

[0065] The patrol quality value contains the values of 0, -1, -2, or -3;

[0066] It is worth noting that by integrating the digital data of the previous different dimension inspection failure processing, the corresponding inspection quality value is obtained, and in the calculation process, due to the processing and calculation of the inspection method and the inspection content, the subsequent analysis and utilization of the corresponding aspects can be realized, and the multi-dimensional quality management of the inspection method and the inspection content is realized.

[0067] According to the inspection quality value of 0, the inspection quality of the existing inspection method is prompted to be normal, and the subsequent normal implementation is maintained.

[0068] According to the inspection quality value of-1, the first abnormality of the inspection quality of the existing inspection method is prompted, and the optimization management of the corresponding inspection content of the existing inspection method is prompted.

[0069] According to the inspection quality value of-2, the second abnormality of the inspection quality of the existing inspection method is prompted, and the optimization management of the existing inspection method is prompted.

[0070] According to the inspection quality value of-3, the third abnormality of the inspection quality of the existing inspection method is prompted, and the optimization management of the existing inspection method and the existing inspection content is prompted.

[0071] Among them, the optimization management of the inspection content can be specifically adding, deleting or modifying on the basis of the existing inspection content; the optimization management of the existing inspection method can be specifically replacing the existing inspection method, or synchronously combining the existing inspection method with other inspection methods, and can be customized according to the actual application requirements of the actual application scene.

[0072] It is worth noting that by analyzing the data of the integrated inspection quality value, the optimization management of the inspection content level and the inspection method level can be realized, and the diversified processing, analysis and utilization of the inspection quality value are realized.

[0073] In the embodiment of the application, by performing multi-dimensional quality management data processing and analysis on the first inspection failure total value and the second inspection failure total value obtained by the multi-dimensional supervision processing, the inspection quality value corresponding to the existing inspection method is obtained, and according to the analysis result of the inspection quality value, the inspection content of the existing inspection method is optimized and / or the existing inspection method is optimized, the multi-dimensional supervision processing of the existing inspection method and the optimization management of multiple objects are realized, and the multi-dimensional quality supervision evaluation effect and the multi-dimensional quality management effect of the inspection method are improved.

[0074] In several embodiments provided by the present application, it should be understood that the disclosed system can be implemented in other ways. For example, the above-described embodiments of the application are merely illustrative, for example, the division of the modules is only a logical function division, and other division manners can be used in actual implementation.

[0075] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed over multiple network modules. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment.

[0076] In addition, each functional module in each embodiment of the present application can be integrated into one processing module, or each module can exist physically alone, or two or more modules can be integrated into one module. The integrated module can be realized in the form of hardware or in the form of hardware plus software functional module.

[0077] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the essential characteristics of the present application.

[0078] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not limiting. Although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solutions of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. An AI-based inspection method multi-dimensional quality management system, characterized by, The method comprises the following steps: The inspection mode implements a supervision processing module for monitoring and counting the inspection results of each implementation of the inspection mode, and processing and classifying the inspection results of each implementation to obtain a normal inspection set and an abnormal inspection set, performing different dimension inspection failure processing on the abnormal inspection set to obtain corresponding first inspection failure total value and second inspection failure total value and upload to the cloud platform; Wherein, all inspection components and first abnormal reasons appearing in the abnormal inspection set are counted, and all first abnormal reasons appearing in the same inspection component are sorted and combined to obtain an inspection component active processing sequence; All inspection component active processing sequences are sorted and combined to obtain an inspection component active processing sequence set; And, all the device components that appear abnormal and the corresponding second abnormal reasons are obtained, and the different device components that appear and the corresponding second abnormal reasons are analyzed by a patrol implementation identification model to output corresponding component patrol values BX; wherein, the expression of the patrol implementation identification model is ; in the formula, a and b are device components and corresponding second abnormal reasons respectively; U1 is a set corresponding to all patrol components; U2 is a set of all abnormal reasons of historical patrol of device components. The device component associated with the first inspection abnormal label is associated with the device component according to the component inspection value of 0; the device component associated with the second inspection abnormal label is associated with the device component according to the component inspection value of 1; and the device component associated with the third inspection abnormal label is associated with the device component according to the component inspection value of 2; All device components associated with the first inspection abnormal label are counted and marked as first components, and all device components associated with the second inspection abnormal label are counted and marked as second components; all the total numbers of the first abnormal reasons corresponding to different first components, all the total numbers of the second abnormal reasons matched with the first abnormal reasons, are sequentially passed through the formula to obtain corresponding first inspection failure values XSYi; in the formula, i is different first components, i=1, 2, 3, …, n; n is a positive integer; ai is a component influence coefficient corresponding to different first components; Ni is all the total numbers of the second abnormal reasons matched with the first abnormal reasons corresponding to different first components; N0i is all the total numbers of the first abnormal reasons corresponding to different first components; All first inspection failure values are sorted and combined, and the sum of all sorted and combined first inspection failure values is obtained to obtain the first inspection failure total value XSY0; The total number of all second abnormal reasons corresponding to different second components is calculated by the formula The corresponding second inspection failure value XSEj is obtained; in the formula, j is different second components, j=1, 2, 3, …, m; m is a positive integer; bj is a component influence coefficient corresponding to different second components; N1j is the total number of all second abnormal reasons corresponding to different second components; e is a constant; All second inspection failure values are sorted and combined, and the sum of all sorted and combined second inspection failure values is obtained to obtain the second inspection failure total value XSE0; When performing multi-dimensional quality management on the inspection mode, the first inspection failure total value and the second inspection failure total value obtained by processing are analyzed by the inspection quality identification model, and the corresponding inspection quality value XZ is output; The expression of the patrol quality identification model is ; in the formula, A, B, and C are respectively a first patrol failure limit value, a second patrol failure limit value, and a third patrol failure limit value; XSS0 is a third patrol failure value; the third patrol failure value is calculated through a formula ; in the formula, N2 is a total number of occurrences of a third patrol abnormality label; and NZ is a total number of all patrol components that are patrolled by an existing patrol mode. The multi-dimensional quality management module of the inspection mode is used for multi-dimensional quality management data processing and analysis of the first inspection failure total value and the second inspection failure total value obtained by multi-dimensional supervision processing, to obtain the corresponding inspection quality value of the existing inspection mode, and according to the analysis result of the inspection quality value, the inspection content of the existing inspection mode is optimized and / or the existing inspection mode is optimized. 2.The AI-based inspection method multi-dimensional quality management system of claim 1, wherein, The inspection results of each implementation of the inspection mode are analyzed, if there is no abnormal inspection item in the inspection result, the corresponding inspection result of the inspection is marked as normal inspection; If there is at least one inspection item in the inspection result, the corresponding inspection result of the inspection is marked as abnormal inspection, and the inspection components and first abnormal reasons of the abnormal inspection items appearing in the abnormal inspection are obtained; All normal inspection corresponding inspection results are sorted and combined according to the inspection time sequence to obtain a normal inspection set; And all abnormal inspection corresponding inspection results are sorted and combined according to the inspection time sequence to obtain an abnormal inspection set. 3.The AI-based inspection method multi-dimensional quality management system of claim 2, wherein, According to the inspection quality value of 0, the inspection quality of the existing inspection mode is prompted to be normal, and its subsequent normal implementation is maintained; According to the inspection quality value of-1, the first abnormality of the inspection quality of the existing inspection mode is prompted, and the optimization management of the corresponding inspection content of the existing inspection mode is prompted. According to the numerical value of -2 of the inspection quality value, the second abnormality of the inspection quality of the existing inspection mode is prompted, and the existing inspection mode is prompted to be optimized and managed; According to the numerical value of -3 of the inspection quality value, the third abnormality of the inspection quality of the existing inspection mode is prompted, and the existing inspection mode and the existing inspection content are prompted to be optimized and managed.

Images