Intelligent accessory evaluation method, system and equipment based on visual inspection and medium

Abstract

The invention provides an intelligent accessory evaluation method, system and equipment based on visual detection and a medium, and relates to the technical field of accessory detection, and the method comprises the steps: detecting a main body part and a plurality of accessories to be assembled in the main body part through a visual detection system, and generating the detection data of the main body part and each accessory; according to the detection data, determining abnormal accessories with abnormities in the plurality of accessories, and calculating a first adaptation index of the abnormal accessories and the associated accessories and a second adaptation index of the abnormal accessories and the main body part; according to the detection data, influence coefficients of the abnormal accessories on other accessories are calculated, and the other accessories are accessories except the abnormal accessories and the associated accessories in the multiple accessories; and when the first adaptation index is greater than a first preset index, the second adaptation index is greater than a second preset index, and the influence coefficient is smaller than a preset coefficient, taking the abnormal accessory as a normal accessory. The technical effect of the invention is that resource waste is reduced.

Description

Intelligent evaluation methods, systems, equipment, and media for accessories based on vision inspection Technical Field

[0001] This application relates to the field of parts inspection technology, specifically to a visual inspection-based intelligent evaluation method, system, equipment, and medium for parts. Background Technology

[0002] In modern manufacturing, product assembly requires the precise attachment of multiple components to the main body. However, in actual production, components may exhibit abnormalities such as dimensional deviations, surface defects, and shape deformations. Accurately identifying these abnormal components and assessing their continued usability to avoid resource waste due to excessive discarding is a significant technical challenge for the manufacturing industry.

[0003] Existing technologies typically employ visual inspection systems to inspect components, using image processing and pattern recognition to identify anomalies and determine their conformity based on preset quality standards. However, once an anomaly is detected, these methods often directly classify the component as a defective product and discard it, without considering its actual suitability in the specific assembly environment. In reality, some components with minor anomalies may still function normally under certain assembly configurations. Therefore, these methods may lead to the erroneous discarding of a large number of usable components, resulting in resource waste. Summary of the Invention

[0004] This application provides a visual inspection-based intelligent evaluation method, system, device, and medium for accessories, which aims to reduce resource waste.

[0005] In a first aspect, this application provides a visual inspection-based intelligent evaluation method for accessories. The method includes: inspecting a main component and multiple accessories to be assembled into the main component using a visual inspection system to generate inspection data for the main component and each accessory; identifying abnormal accessories among the multiple accessories based on the inspection data, and calculating a first compatibility index between the abnormal accessory and associated accessories, and a second compatibility index between the abnormal accessory and the main component; wherein, the associated accessories are accessories that come into contact with the abnormal accessory during assembly; calculating the influence coefficient of the abnormal accessory on other accessories based on the inspection data, wherein the other accessories are accessories other than the abnormal accessory and the associated accessories; and classifying the abnormal accessory as a normal accessory when the first compatibility index is greater than a first preset index, the second compatibility index is greater than a second preset index, and the influence coefficient is less than a preset coefficient.

[0006] By employing the aforementioned technical solution, a visual inspection system generates inspection data for the main components and various accessories, accurately identifying abnormal accessories. Building upon this, the method innovatively introduces a multi-dimensional evaluation mechanism. By calculating the first compatibility index between the abnormal accessory and related accessories, and the second compatibility index with the main component, the system comprehensively assesses the matching degree of the abnormal accessory within the assembly environment. Simultaneously, by calculating the influence coefficient of the abnormal accessory on other accessories, the system quantitatively analyzes the potential impact of the abnormal accessory on the overall assembly system. When the first compatibility index is greater than a first preset index, the second compatibility index is greater than a second preset index, and the influence coefficient is less than a preset coefficient, the system intelligently reclassifies the abnormal accessory as a normal accessory, thus avoiding the one-size-fits-all rejection judgment found in traditional inspection methods. This comprehensive evaluation strategy significantly improves accessory utilization and reduces resource waste.

[0007] Secondly, this application provides a visual inspection-based intelligent evaluation system for accessories, the system comprising: a detection module, a first calculation module, a second calculation module, and a judgment module; wherein, the detection module is used to inspect a main component and multiple accessories to be assembled into the main component using a visual inspection system, generating detection data for the main component and each accessory; the first calculation module is used to determine abnormal accessories among the multiple accessories based on the detection data, and calculate a first compatibility index between the abnormal accessory and associated accessories, and a second compatibility index between the abnormal accessory and the main component; wherein, the associated accessories are accessories among the multiple accessories that come into contact with the abnormal accessory during assembly; the second calculation module is used to calculate the influence coefficient of the abnormal accessory on other accessories based on the detection data, wherein the other accessories are accessories among the multiple accessories excluding the abnormal accessory and the associated accessories; the judgment module is used to classify the abnormal accessory as a normal accessory when the first compatibility index is greater than a first preset index, the second compatibility index is greater than a second preset index, and the influence coefficient is less than a preset coefficient.

[0008] Thirdly, this application provides an electronic device that adopts the following technical solution: including a processor, a memory, a user interface, and a network interface, wherein the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory to enable the electronic device to execute a computer program such as any of the above-mentioned intelligent evaluation methods for accessories based on visual inspection.

[0009] Fourthly, this application provides a computer-readable storage medium that employs the following technical solution: storing a computer program capable of being loaded by a processor and executing any of the aforementioned visual inspection-based intelligent evaluation methods for accessories.

[0010] In summary, this application includes at least one of the following beneficial technical effects: By generating inspection data for the main component and various accessories through a visual inspection system, it can accurately identify abnormal accessories. Based on this, the method innovatively introduces a multi-dimensional evaluation mechanism. By calculating a first fit index between the abnormal accessory and related accessories, and a second fit index with the main component, it comprehensively evaluates the matching degree of the abnormal accessory in the assembly environment. Simultaneously, by calculating the influence coefficient of the abnormal accessory on other accessories, it quantitatively analyzes the potential impact of the abnormal accessory on the overall assembly system. When the first fit index is greater than a first preset index, the second fit index is greater than a second preset index, and the influence coefficient is less than a preset coefficient, the system intelligently reclassifies the abnormal accessory as a normal accessory, thus avoiding the one-size-fits-all rejection judgment in traditional inspection methods. This comprehensive evaluation strategy significantly improves accessory utilization and reduces resource waste. Attached Figure Description

[0011] Figure 1 is a flowchart illustrating a visual inspection-based intelligent evaluation method for accessories provided in an embodiment of this application; Figure 2 is a structural diagram illustrating a visual inspection-based intelligent evaluation system for accessories provided in an embodiment of this application; Figure 3 is a structural diagram illustrating an electronic device provided in an embodiment of this application.

[0012] Explanation of reference numerals in the attached figures: 1000, electronic device; 1001, processor; 1002, communication bus; 1003, user interface; 1004, network interface; 1005, memory. Detailed Implementation

[0013] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0014] In the description of the embodiments in this application, words such as "illustrative," "for example," or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "illustrative," "for example," or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Rather, the use of words such as "illustrative," "for example," or "for example" is intended to present the relevant concepts in a specific manner.

[0015] Figure 1 is a flowchart illustrating a visual inspection-based intelligent evaluation method for accessories provided in an embodiment of this application. As shown in Figure 1, the method includes S101-S109: S101, the main component and multiple accessories to be assembled into the main component are inspected using a visual inspection system to generate inspection data for the main component and each accessory.

[0016] In one specific embodiment, a vision inspection system inspects a main component and multiple accessories to be assembled into the main component, generating inspection data for the main component and each accessory. Specifically, the vision inspection system includes multiple industrial cameras, a lighting device, and an image processing device. The industrial cameras are positioned above and to the side of the assembly station to acquire multi-angle images of the main component and each accessory; the lighting device provides a uniform and stable light source to ensure that the acquired images are clear and distinguishable; the image processing device processes and analyzes the acquired images using image recognition algorithms.

[0017] The visual inspection system in this embodiment uses a high-precision camera with a resolution of 0.01mm, capable of accurately capturing the dimensional features of the components. During the inspection process, the main component is first placed on a preset inspection platform. The visual inspection system performs a full-range scan of the main component, acquiring its three-dimensional structural information, key dimensional data, and assembly position parameters. Subsequently, multiple components to be assembled are placed sequentially into the inspection area, and the system scans each component to acquire information such as its size, shape, and surface features. The image processing device processes the images acquired by the camera in real time, using algorithms such as edge detection and feature matching to accurately extract the key dimensional parameters of each component, such as length, width, height, diameter, and hole positions, and compares them with preset standard parameters to generate inspection data.

[0018] The test data mainly includes two categories: dimensional data and positional data. Dimensional data includes the actual measured dimensions of each component and its deviation from the standard dimensions; positional data includes the expected assembly position, assembly direction, and relative positional relationship of the component to other components. This data constitutes the basic information for subsequent evaluation of component compatibility.

[0019] The reason for needing to obtain this inspection data through a vision inspection system is that traditional parts screening methods typically rely solely on simple dimensional measurements, treating any parts outside the standard range as defective, leading to resource waste and increased production costs. In contrast, the precise inspection data obtained through a vision inspection system provides a comprehensive and accurate information foundation for subsequent intelligent evaluation, enabling the system to consider the compatibility between parts comprehensively, rather than relying solely on the standard compliance of individual parts.

[0020] S102, based on the test data, identify the abnormal parts among the multiple parts, and calculate the first compatibility index between the abnormal parts and the associated parts, and the second compatibility index between the abnormal parts and the main body; wherein, the associated parts are the parts among the multiple parts that have contact with the abnormal parts during assembly.

[0021] First, the system evaluates each component based on the detection data to determine if any abnormal components exist. In this embodiment, abnormal components refer to components whose dimensional parameters are outside the preset size range. For example, when the diameter of a shaft component is 19.92mm, while its preset size range is 20.00±0.05mm, the component is initially identified as an abnormal component. Traditional quality inspection methods would then classify this component as a defective product and discard it, but the method in this embodiment further considers the actual compatibility of the abnormal component.

[0022] To further evaluate the actual compatibility of abnormal components, the system needs to calculate two key indicators: a first compatibility index and a second compatibility index. The first compatibility index reflects the fit between the abnormal component and related components, while the second compatibility index reflects the assembly compatibility between the abnormal component and the main component. Here, "related components" specifically refers to components that have direct contact with the abnormal component during assembly, such as bearings and bushings that mate with shaft-type abnormal components.

[0023] When calculating the first fit index, the system first determines the associated components of the abnormal component based on the position data of each component. In this embodiment, the system analyzes the assembly position relationships in the detection data to identify components that overlap or contact the abnormal component in three-dimensional space and marks them as associated components. For example, for a shaft-type abnormal component with a diameter of 19.92 mm, the system identifies its associated component as a bushing with an inner diameter of 20.05 mm.

[0024] Subsequently, the system acquires the first dimension of the abnormal component (e.g., the diameter of the shaft is 19.92 mm), the second dimension of the associated component (e.g., the inner diameter of the bushing is 20.05 mm), and the third dimension of the main component (e.g., the dimensions of the mounting holes on the main component). Based on these dimensional parameters, the system calculates the first fit index between the abnormal component and the associated component. The specific calculation method is as follows: First, obtain the standard mating dimensions of both (e.g., the standard interference fit value between the shaft and the bushing); then calculate the deviation between the actual dimensions and the standard mating dimensions; further, calculate the actual mating clearance value; finally, determine the value of the first fit index based on whether the mating clearance value is within the preset mating clearance range and the degree of deviation from the center of the range. This index value is typically set between 0 and 1, with a value closer to 1 indicating better fit.

[0025] Similarly, the system calculates a second compatibility index between the defective accessory and the main component. This index reflects whether the defective accessory can be properly installed on the main component, as well as its stability and functionality after installation. The calculation method is similar to the first compatibility index, but it focuses on the assembly gap value and assembly stability between the defective accessory and the main component.

[0026] Based on the above embodiments, as an optional implementation method, in S1002, the detection data includes size and position. According to the detection data, abnormal parts with abnormality are identified among multiple parts, and the first adaptation index between the abnormal part and the associated parts and the second adaptation index between the abnormal part and the main body are calculated. Specifically, this includes S21-S25: ​​S21, when the size of the target part is not within the preset size range among multiple parts, the target part is regarded as an abnormal part.

[0027] The system evaluates the dimensions of multiple components. If the target component's dimensions deviate from the preset size range, it is classified as an abnormal component. The preset size range refers to the allowable dimensional variation range specified in the component's design specifications, typically expressed as nominal size ± tolerance. For example, for a shaft component with a nominal diameter of 50.00 mm, its preset size range might be 50.00 ± 0.05 mm, i.e., between 49.95 mm and 50.05 mm. When the vision inspection system measures the actual diameter of a component to be 49.92 mm, since this value is less than the lower limit of the preset size range (49.95 mm), the system will initially classify the component as an abnormal component. This step provides an evaluation target for subsequent compatibility assessments, ensuring that the system only performs in-depth analysis on components with genuine dimensional abnormalities, thus improving processing efficiency.

[0028] S22, determine the associated parts of the abnormal parts based on the location of each part.

[0029] Here, "position" refers to the spatial relationship between the components in their final assembled state, information contained in the inspection data generated by the vision inspection system. The system analyzes the assembly topology to identify components that are in direct contact with the abnormal component in its assembled state, marking them as associated components. For example, for a shaft-type abnormal component, its associated components might include mating bearings, bushings, gears, etc. The purpose of this step is to clarify the direct interaction objects of the abnormal component within the assembly system, providing a clear evaluation scope for subsequent compatibility assessments.

[0030] S23, obtain the first dimension of the abnormal accessory, the second dimension of the associated accessory, and the third dimension of the main component.

[0031] The system acquires the first dimension of the abnormal component, the second dimension of the associated components, and the third dimension of the main component. Here, "first dimension" refers to the critical dimensional parameters of the abnormal component, such as the diameter of a shaft or the module of a gear; "second dimension" refers to the mating dimensional parameters of the associated components, such as the inner diameter of a bearing or the mating dimensions of a gear; and "third dimension" refers to the dimensional parameters of the main component directly related to the abnormal component, such as the diameter of a mounting hole or the flatness of a support surface. This dimensional data is extracted from the inspection data of the vision inspection system, ensuring high accuracy and reliability. The purpose of acquiring these three types of dimensional data is to provide the foundational data for subsequent calculations of the fit index, ensuring the accuracy and credibility of the evaluation results.

[0032] S24, combining the first and second dimensions, calculate the first compatibility index between the abnormal accessory and the associated accessory.

[0033] The system combines the first and second dimensions to calculate the first fit index between the abnormal component and its associated component. The specific calculation method is as follows: First, determine the standard fit type (e.g., interference fit, transition fit, clearance fit, etc.) and its corresponding standard fit clearance range for the abnormal component and its associated component; then, calculate the actual fit clearance value based on the measured first and second dimensions; finally, evaluate whether the actual fit clearance value is within the allowable clearance range and the degree of deviation from the center of the range, thereby generating the first fit index. For example, for a shaft with an actual diameter of 49.92 mm and a bushing with an inner diameter of 50.00 mm, the calculated actual clearance value is 0.08 mm; if its standard clearance range is 0.05 mm to 0.15 mm, then the fit is still within the allowable range, but leans towards the lower limit of the range, and the possible first fit index value is 0.85 (assuming a full score of 1). The first fit index is an important indicator for measuring the actual fit quality between the abnormal component and its associated component, directly affecting the stability and reliability of the assembly.

[0034] Based on the above embodiments, as an optional implementation method, in S24, the calculation of the first fit index between the abnormal accessory and the associated accessory by combining the first size and the second size specifically includes S241-S246: S241, obtaining the standard fit size between the abnormal accessory and the associated accessory.

[0035] The system retrieves the standard mating dimensions of abnormal components and related components. "Standard mating dimensions" refer to the dimensional values ​​that two components should ideally have according to engineering design specifications. For example, for a pair of shafts and bearings, if the design uses a transition fit, the standard mating dimensions might be a shaft diameter of 50.00 mm and a bearing inner diameter of 49.98 mm. These standard mating dimensions are usually stored in the product design database, and the system can automatically retrieve relevant data based on the component model and assembly relationship. The purpose of retrieving standard mating dimensions is to provide a benchmark for subsequent evaluation of the deviation between actual dimensions and standard dimensions; this is the first fundamental step in calculating the fit index.

[0036] S242, calculate the first deviation value between the first dimension and the standard fit dimension, and the second deviation value between the second dimension and the standard fit dimension.

[0037] The system calculates the first deviation value between the first dimension and the standard fit dimension, and the second deviation value between the second dimension and the standard fit dimension. Specifically, the system subtracts the measured dimension of the abnormal component (i.e., the first dimension) from its corresponding standard fit dimension to obtain the first deviation value; similarly, it subtracts the measured dimension of the associated component (i.e., the second dimension) from its corresponding standard fit dimension to obtain the second deviation value. For example, if the actual diameter of the abnormal component (shaft) is 49.92mm and the standard fit dimension is 50.00mm, the first deviation value is -0.08mm (indicating that the actual dimension is smaller than the standard dimension); if the actual inner diameter of the associated component (bearing) is 49.96mm and the standard fit dimension is 49.98mm, the second deviation value is -0.02mm. These deviation values ​​directly reflect the difference between the actual dimensions and the design requirements and are key parameters for subsequent calculation of the fit clearance value.

[0038] S243, calculate the fit clearance value based on the first deviation value and the second deviation value.

[0039] The system calculates the clearance value based on the first and second deviation values. The "clearance value" refers to the actual clearance (positive value) or interference (negative value) between the mating surfaces of two components after assembly. The calculation method varies depending on the type of component, but the basic principle is to comprehensively consider the impact of the dimensional deviations of the two components on the final fit. Taking the fit between a shaft and a bearing as an example, the clearance value equals the bearing's inner diameter minus the shaft's outer diameter, i.e., the difference between the actual inner diameter of the bearing and the actual outer diameter of the shaft. In the example above, the clearance value is 49.96mm - 49.92mm = 0.04mm, indicating a 0.04mm clearance between the shaft and the bearing. This calculation step transforms the dimensional deviations of the two components into a comprehensive index, directly reflecting the actual assembly state of the components.

[0040] S244, when the mating clearance value is less than the minimum value of the preset mating clearance range or greater than the maximum value of the preset mating clearance range, the first compatibility index between the abnormal accessory and the associated accessory is set to 0.

[0041] When the clearance value is less than the minimum value of the preset clearance range or greater than the maximum value of the preset clearance range, the system sets the first compatibility index between the abnormal component and its associated component to 0. The "preset clearance range" refers to an acceptable clearance range pre-defined based on product performance and reliability requirements, typically determined by product engineers based on experience and product characteristics. For example, for a certain bearing fit, the preset clearance range might be 0.03mm to 0.08mm. If the calculated clearance value is 0.02mm, less than the minimum value of 0.03mm, or 0.09mm, greater than the maximum value of 0.08mm, the system determines that the fit is completely unsuitable and sets the first compatibility index to 0. This step is the initial screening for fit suitability, ensuring that obviously non-compliant fits are directly excluded.

[0042] S245, when the fit clearance value is within the preset fit clearance range, calculate the first clearance deviation value between the fit clearance value and the center value of the preset fit clearance range.

[0043] The first clearance deviation value is calculated between the actual fit clearance value and the center value of the preset fit clearance range. The center value of the preset fit clearance range is the arithmetic mean of the minimum and maximum values, representing the most ideal fit. For example, for a range of 0.03mm to 0.08mm, the center value is (0.03+0.08) / 2=0.055mm. The first clearance deviation value is the absolute difference between the actual fit clearance value and the center value. If the actual fit clearance value is 0.04mm, then the first clearance deviation value is |0.04-0.055|=0.015mm. This deviation value reflects the degree to which the actual fit deviates from the ideal state and is the direct basis for calculating the fit index.

[0044] S246, Based on the first gap deviation value, determine the first compatibility index between the abnormal part and the associated part; wherein, the deviation value is inversely proportional to the first compatibility index.

[0045] The system determines the first fitting index between the abnormal component and its associated components based on the first gap deviation value; the deviation value and the first fitting index are inversely proportional. The specific calculation method typically uses a function mapping to convert the first gap deviation value into a fitting index value between 0 and 1. A commonly used formula is: First Fitting Index = 1 - (First Gap Deviation Value / (Maximum Value of Preset Fit Gap Range - Minimum Value of Preset Fit Gap Range) * 2). This formula ensures that when the first gap deviation value is 0 (i.e., in an ideal center state), the first fitting index is 1; when the first gap deviation value reaches half the range width, the first fitting index is 0.

[0046] Based on the example above, the first fit index = 1 - (0.015 / (0.08-0.03)*2) = 1 - (0.015 / 0.05*2) = 1 - 0.6 = 0.4. This step converts the deviation value into a fit score, making the evaluation results more intuitive and standardized.

[0047] S25, combining the first and third dimensions, calculate the second fit index between the abnormal accessory and the main component.

[0048] The system combines the first and third dimensions to calculate a second compatibility index between the defective accessory and the main component. The calculation method is similar to the first compatibility index, but it focuses on evaluating whether the defective accessory can be stably and reliably installed on the main component, and the degree of functional achievement after installation. For example, for a shaft with a diameter of 49.92 mm and a mounting hole with a diameter of 50.10 mm on the main component, the system will assess whether this fit will cause excessive wobble or instability, thus affecting overall functionality. The second compatibility index is also represented by a value between 0 and 1, with a higher value indicating better compatibility.

[0049] Based on the above embodiments, as an optional implementation method, in S25, the calculation of the second adaptation index between the abnormal accessory and the main component in combination with the first dimension and the third dimension specifically includes S251-S256: S251, obtaining the standard assembly dimensions of the abnormal accessory and the main component.

[0050] The system retrieves the standard assembly dimensions of the defective accessory and the main component. "Standard assembly dimensions" refer to the dimensional values ​​that the defective accessory and the main component should have in an ideal assembly state, according to product design specifications. Unlike the standard mating dimensions of related accessories, standard assembly dimensions focus more on the stable installation and functional realization of the accessory on the main component. For example, for a shaft accessory that needs to be installed on a main component bracket, its standard assembly dimensions might include a shaft diameter of 50.00 mm and a corresponding bracket mounting hole diameter of 50.10 mm, ensuring smooth installation of the shaft and maintaining a certain amount of movement allowance. These standard assembly dimensions are also stored in the product design database, and the system can automatically retrieve relevant data based on accessory model and assembly relationship. Retrieving standard assembly dimensions is a fundamental step in assessing the compatibility between the defective accessory and the main component, providing a reference benchmark for subsequent deviation calculations.

[0051] S252, calculate the third deviation value between the first dimension and the standard assembly dimension, and the fourth deviation value between the third dimension and the standard assembly dimension.

[0052] The system calculates the third deviation value between the first dimension and the standard assembly dimension, and the fourth deviation value between the third dimension and the standard assembly dimension. Specifically, the system subtracts the measured dimension of the abnormal accessory (i.e., the first dimension) from its corresponding standard assembly dimension to obtain the third deviation value; similarly, it subtracts the measured dimension of the main component (i.e., the third dimension) from its corresponding standard assembly dimension to obtain the fourth deviation value. For example, if the actual diameter of the abnormal accessory (shaft) is 49.92mm and the standard assembly dimension is 50.00mm, the third deviation value is -0.08mm; if the actual diameter of the mounting hole of the main component (bracket) is 50.12mm and the standard assembly dimension is 50.10mm, the fourth deviation value is 0.02mm. These deviation values ​​directly reflect the difference between the actual dimensions and the design requirements and are key input parameters for subsequent calculations of assembly clearance values.

[0053] S253, calculate the assembly clearance value based on the third and fourth deviation values.

[0054] The system calculates the assembly clearance value based on the third and fourth deviation values. The "assembly clearance value" refers to the actual gap or interference between the contact surfaces of the defective component and the main component after assembly. The calculation method varies depending on the type of component, but the basic principle is to comprehensively consider the impact of the dimensional deviations of both on the final assembly state. Taking the assembly of a shaft and a bracket mounting hole as an example, the assembly clearance value equals the diameter of the bracket mounting hole minus the outer diameter of the shaft, i.e., the difference between the actual size of the main component and the actual size of the defective component. In the example above, the assembly clearance value is 50.12mm - 49.92mm = 0.20mm, indicating a 0.20mm gap between the shaft and the mounting hole. This calculation step transforms the dimensional deviations of the defective component and the main component into a comprehensive index, directly reflecting their actual assembly state and stability.

[0055] S254, when the assembly gap value is less than the minimum value of the preset assembly gap range or greater than the maximum value of the preset assembly gap range, the second adaptation index between the abnormal accessory and the main component is set to 0.

[0056] When the assembly clearance value is less than the minimum value of the preset assembly clearance range or greater than the maximum value of the preset assembly clearance range, the system sets the second fit index between the abnormal accessory and the main component to 0. The "preset assembly clearance range" refers to an acceptable range of assembly clearances pre-set according to product function and reliability requirements. For example, for the assembly of the shaft and bracket mentioned above, the preset assembly clearance range may be 0.08mm to 0.15mm. If the calculated assembly clearance value is 0.20mm, which is greater than the maximum value of 0.15mm, the system determines that the assembly is unsuitable and sets the second fit index to 0. This is because an excessively large assembly clearance will cause the shaft to wobble in the bracket, affecting the stability and accuracy of the overall assembly. This step is a preliminary screening of assembly compatibility, ensuring that assembly states that clearly do not meet the requirements are directly eliminated.

[0057] S255, when the assembly gap value is within the preset assembly gap range, calculate the second gap deviation value between the assembly gap value and the center value of the preset assembly gap range.

[0058] The second clearance deviation value is calculated between the assembly clearance value and the center value of the preset assembly clearance range. The "center value of the preset assembly clearance range" is the arithmetic mean of the minimum and maximum values, representing the ideal assembly state. For example, for a range of 0.08mm to 0.15mm, the center value is (0.08+0.15) / 2=0.115mm. The "second clearance deviation value" is the absolute difference between the assembly clearance value and the center value. If we assume that the actual assembly clearance value is 0.10mm in another example, then the second clearance deviation value is |0.10-0.115|=0.015mm. This deviation value reflects the degree to which the actual assembly state deviates from the ideal state and is the direct basis for calculating the second fit index.

[0059] S256, Based on the second gap deviation value, determine the second fitting index between the abnormal accessory and the main component; wherein, the second gap deviation value and the second fitting index are inversely proportional.

[0060] The system determines a second fit index between the abnormal component and the main component based on the second gap deviation value; the second gap deviation value and the second fit index are inversely proportional. The specific calculation method typically employs a function mapping similar to the first fit index, converting the second gap deviation value into a fit index value between 0 and 1. A commonly used formula is: Second Fit Index = 1 - (Second Gap Deviation Value / (Maximum Value of Preset Assembly Gap Range - Minimum Value of Preset Assembly Gap Range) * 2). This formula ensures that when the second gap deviation value is 0 (i.e., in the ideal center state), the second fit index is 1; when the second gap deviation value reaches half the range width, the second fit index is 0. In the example above, the second fit index = 1 - (0.015 / (0.15 - 0.08) * 2) = 1 - (0.015 / 0.07 * 2) ≈ 1 - 0.43 = 0.57. This step realizes the conversion from deviation value to fit score, making the evaluation results more intuitive and standardized.

[0061] S103, Based on the test data, calculate the influence coefficient of the abnormal part on other parts, where other parts are those other than the abnormal part and related parts.

[0062] In complex assembly systems, an anomaly in the size of a component can affect not only related components in direct contact with it, but also other components in the system through a chain reaction. For example, in a precision mechanical device, if the diameter of a support shaft is slightly smaller than the standard size, although it may still fit well with its directly mating bushing (i.e., have a high first fit index), this deviation may cause a slight shift in the position of the entire mechanism, thus affecting the assembly accuracy of distant components. Therefore, it is necessary to calculate the impact coefficient of the abnormal component on other components to comprehensively assess the usability of the abnormal component.

[0063] In this embodiment, the influence coefficient is calculated using a virtual assembly simulation method. The system first constructs a digital assembly model based on the precise dimensions and positions of all components acquired by the vision inspection system. In this model, the system simulates the assembly process of sequentially installing the abnormal component and other components onto the main body component. For example, for a product containing 15 components, if component number 3 is identified as abnormal and component number 7 is its associated component, the system will simulate the sequential installation of the abnormal component (number 3) and the remaining components (numbers 1, 2, 4, 5, 6, 8...15) onto the main body component.

[0064] In this virtual assembly process, the system focuses on detecting whether the abnormal component causes the installation positions of other components to shift. The system calculates the positional offset of each other component by comparing the assembly positions under normal conditions (i.e., all components conform to standard dimensions) with those under abnormal conditions (i.e., including the abnormal component). The positional offset is expressed as distance in a spatial coordinate system, in millimeters, and characterizes the degree of positional change of other components due to the presence of the abnormal component.

[0065] If the abnormal component causes the installation position of other components to shift, the system obtains the amount of this shift and calculates the influence coefficient of the abnormal component on the other components based on this amount. The influence coefficient is a dimensionless parameter, typically ranging from 0 to 1, with a larger value indicating a more significant impact.

[0066] When calculating the influence coefficient, the system also considers the differences in importance among different components. The system obtains the importance level of the other components and determines the corresponding weight coefficient based on the importance level. The importance level is preset based on factors such as the functional importance, replacement difficulty, and cost of the component, and is divided into three levels: high, medium, and low, with corresponding weight coefficients of 1.5, 1.0, and 0.5, respectively. For example, a critical sealing component has a high importance level and a weight coefficient of 1.5; while a common decorative cover has a low importance level and a weight coefficient of 0.5.

[0067] Subsequently, the system arithmetically multiplies the offsets of the other components with their corresponding weighting coefficients to generate a weighted offset. This weighting process ensures higher sensitivity to the positional offsets of important components. Finally, based on the weighted offset, the influence coefficient of the abnormal component on the other components is calculated; wherein, the weighted offset is directly proportional to the influence coefficient. The specific calculation formula is: Influence coefficient = Sum of the squares of the weighted offsets of all other components divided by a preset threshold; if the result is greater than 1, it is set to 1.

[0068] The purpose of calculating the influence coefficient is to more comprehensively assess the actual usability of defective parts. Traditional part evaluation methods often only focus on whether the part itself meets the standards, or at most consider its fit with directly contacting parts, while neglecting its impact on the overall assembly system. This method, by introducing the influence coefficient, overcomes this deficiency, making the evaluation more comprehensive and systematic.

[0069] Based on the above embodiments, as an optional implementation method, in S103, calculating the influence coefficient of abnormal parts on other parts according to the detection data specifically includes S31-S34: S31, based on the detection data, simulating the assembly process of sequentially installing abnormal parts and other parts onto the main body component.

[0070] Based on the inspection data, the system simulates the assembly process of sequentially installing abnormal components and other components into the main body. Here, "simulation" refers to using computer virtual assembly technology to reproduce the complete assembly process in a virtual environment based on the actual inspection dimensional data of the abnormal components and other components. The "inspection data" includes the first dimension of the abnormal component, the second dimension of related components, the third dimension of the main body, and the actual dimensional data of other components that need to be assembled with the abnormal component. The simulated assembly process follows the standard assembly sequence and method of the product, ensuring that the virtual assembly is consistent with the actual production process. For example, in a motor assembly system, if the shaft is an abnormal component, the system will first simulate installing the shaft into the motor housing (main body), and then sequentially simulate installing the bearings, stator, rotor, and other components until the entire assembly process is completed. This virtual assembly technology avoids the costs and risks of physical trial assembly, while accurately capturing the interactions between components, providing basic data for subsequent evaluation.

[0071] S32, during the assembly process, detect whether abnormal parts cause the installation position of other parts to shift.

[0072] During assembly, the system detects whether abnormal components cause misalignment in the installation positions of other components. "Installation position misalignment" refers to situations where dimensional deviations in abnormal components prevent other related components from being installed in their intended positions, or result in misalignment after installation. For example, if the shaft diameter is too small, it may cause a gap between the inner ring of the bearing and the shaft, resulting in an axial or radial misalignment of the bearing; if the shaft length is too long, it may prevent the end caps installed later from closing completely. The system determines whether installation position misalignment exists by comparing the actual installation positions of each component in the virtual assembly with their design standard positions. This detection method focuses on the cascading effects of abnormal components on the overall assembly system, rather than just the compatibility of the abnormal component itself, thus achieving a comprehensive assessment of the scope of influence of abnormal components.

[0073] S33, If the abnormal component causes the installation position of other components to shift, then obtain the amount of the shift in installation position.

[0074] If an abnormal component causes a shift in the installation position of other components, the system obtains the amount of this shift. "Offset" refers to the difference in distance between the actual installation position of the component and its design standard position, usually expressed as a linear distance (millimeters) or an angle (degrees). The system calculates the offset in different dimensions for each affected component, such as positional offsets along the X, Y, and Z axes, as well as angular offsets around each axis. For example, the system might detect that a 0.08mm discrepancy in shaft diameter causes a 0.04mm radial shift in bearing A, a 0.03mm radial shift in bearing B, and a 0.5mm axial shift in end cap C installed subsequently. These offset data directly reflect the degree of influence of the abnormal component on various related components and are crucial for calculating the influence coefficient.

[0075] S34, Calculate the influence coefficient of abnormal parts on other parts based on the offset.

[0076] The system calculates the influence coefficient of abnormal parts on other parts based on the offset. The "influence coefficient" is a comprehensive indicator used to quantify the degree of impact of abnormal parts on the overall assembly system. Its value typically ranges from 0 to 1, where 0 indicates no impact and 1 indicates the greatest impact. The calculation of the influence coefficient usually considers the following aspects: First, the number of affected parts, i.e., how many other parts are shifted due to the abnormal part; second, the magnitude of each offset, usually compared with its corresponding allowable deviation range to calculate the degree of deviation; third, the importance weight of the affected parts, as different parts have different degrees of impact on product function, and the system assigns different weights based on the functional importance of the parts. Taking all these factors into account, the system uses a weighted average or other appropriate mathematical model to calculate the final influence coefficient. For example, the influence coefficient can be expressed as: Influence Coefficient = Σ(Ratio of each part's offset to the allowable deviation × Part importance weight) / Σ(Part importance weight).

[0077] In the example above, if the allowable radial deviation of bearing A is 0.05 mm and its importance weight is 0.8; the allowable radial deviation of bearing B is 0.05 mm and its importance weight is 0.7; and the allowable axial deviation of end cap C is 0.3 mm and its importance weight is 0.5, then the influence coefficient can be calculated as: ((0.04 / 0.05)×0.8+ (0.03 / 0.05)×0.7+(0.5 / 0.3)×0.5) / (0.8+0.7+0.5)=(0.64+0.42+0.83) / 2≈0.95. This high influence coefficient indicates that the abnormal component has a significant impact on the overall assembly system and should be carefully considered in subsequent decisions.

[0078] Based on the above embodiments, as an optional implementation method, in S34, calculating the influence coefficient of abnormal parts on other parts according to the offset specifically includes S341-S343: S341, obtaining the importance level of other parts, and determining the weight coefficient corresponding to other parts according to the importance level.

[0079] The system acquires the importance level of other components and determines their corresponding weight coefficients based on this level. "Importance level" refers to the classification of components according to their impact on product functionality, reliability, and safety. Typically, importance levels are divided into four categories: critical, important, general, and auxiliary. "Critical" components directly determine the core function of the product, such as cylinders and pistons in an engine; "important" components significantly affect the main performance of the product, such as bearings and gears in a transmission system; "general" components have some impact on product functionality but are not core components, such as certain connectors and fasteners; and "auxiliary" components have a minor impact on product functionality, such as exterior covers and decorative parts. These importance levels are usually determined during the product design phase and recorded in the product technical documentation. The "weight coefficient" is a numerical weight assigned to the component based on its importance level, used to quantify the relative importance of the component. For example, the system might assign a weight coefficient of 1.0 to critical components, 0.8 to important components, 0.5 to general components, and 0.2 to auxiliary components. This weighting ensures that the offsets of important components receive greater attention and influence in subsequent calculations.

[0080] S342, multiply the offsets of other components arithmetically by their corresponding weighting coefficients to generate a weighted offset.

[0081] The system arithmetically multiplies the offsets of other components by their corresponding weighting coefficients to generate a weighted offset. The "weighted offset" refers to the actual offset impact after considering the importance of the component; it combines the original offset and the weighting coefficient to form a comprehensive index. The calculation formula is: Weighted Offset = Offset × Weighting Coefficient. For example, if an abnormal component (such as a shaft with a smaller diameter) causes positional shifts in three components of different importance levels: critical bearing A shifts by 0.04mm (weighting coefficient 1.0), important bearing B shifts by 0.03mm (weighting coefficient 0.8), and general end cap C shifts by 0.5mm (weighting coefficient 0.5), then their corresponding weighted offsets are: 0.04mm × 1.0 = 0.04mm, 0.03mm × 0.8 = 0.024mm, and 0.5mm × 0.5 = 0.25mm, respectively. This weighted processing mechanism ensures that when assessing the impact of abnormal components, the system can simultaneously consider the physical value of the offset and the functional importance of the location where the offset occurs, thereby achieving a comprehensive and targeted assessment of the impact of abnormal components.

[0082] S343, Calculate the influence coefficient of abnormal parts on other parts based on the weighted offset; where the weighted offset is directly proportional to the influence coefficient.

[0083] The system calculates the influence coefficient of abnormal parts on other parts based on the weighted offset; the weighted offset is directly proportional to the influence coefficient. The "influence coefficient" is a normalized index used to represent the overall impact of abnormal parts on the assembly system, typically ranging from 0 to 1, where 0 represents no impact and 1 represents the maximum impact. The influence coefficient is usually calculated using a comprehensive evaluation method based on weighted offsets, considering the sum of the weighted offsets of all affected parts and the number of parts. Common calculation methods include: the maximum value method: taking the maximum value among all weighted offsets as the benchmark and mapping it to the influence coefficient range. For example, if the maximum weighted offset is 0.25mm and the preset critical influence value is 0.3mm (i.e., when the weighted offset reaches 0.3mm, the impact is considered to be at its maximum), then the influence coefficient can be calculated as min(0.25 / 0.3, 1) = 0.83. This method focuses on examining the most severe single-point impact.

[0084] Average value method: Calculate the arithmetic mean of all weighted offsets and map it to the range of influence coefficients. For example, if the weighted offsets of the three components are 0.04mm, 0.024mm, and 0.25mm respectively, then the average weighted offset is (0.04 + 0.024 + 0.25) / 3 ≈ 0.105mm. Assuming the preset critical influence value is 0.2mm, the influence coefficient is min(0.105 / 0.2, 1) = 0.525. This method considers the overall average influence level.

[0085] Cumulative method: All weighted offsets are summed and compared with a preset system total threshold. For example, if the sum of the weighted offsets of the three components is 0.04 + 0.024 + 0.25 = 0.314 mm, and the system total threshold is 0.5 mm, then the influence coefficient is min(0.314 / 0.5, 1) = 0.628. This method focuses on examining the cumulative total influence of abnormal components.

[0086] Comprehensive Evaluation Method: This method combines the above methods and considers factors such as the quantity and distribution of affected parts to form a comprehensive impact coefficient. For example, the impact coefficient can be calculated as: Impact Coefficient = 0.4 × (Maximum Weighted Offset / Preset Single-Point Critical Value) + 0.3 × (Average Weighted Offset / Preset Average Critical Value) + 0.3 × (Total Weighted Offset / Preset Total Critical Value). In this example, if this comprehensive method is used, the impact coefficient = 0.4 × 0.83 + 0.3 × 0.525 + 0.3 × 0.628 ≈ 0.67. This method can comprehensively consider various impact modes of abnormal parts, resulting in a more balanced and comprehensive evaluation.

[0087] Depending on the actual application scenario and product characteristics, the system can flexibly choose one or more of the above methods to calculate the impact coefficient. Regardless of the calculation method used, the weighted offset and the impact coefficient are directly proportional; that is, the larger the weighted offset, the more severe the impact of the abnormal component on the system, and the higher the corresponding impact coefficient. This direct proportionality ensures the intuitiveness and rationality of the evaluation results, facilitating understanding and application in subsequent decision-making processes.

[0088] S104, when the first adaptation index is greater than the first preset index, the second adaptation index is greater than the second preset index, and the influence coefficient is less than the preset coefficient, the abnormal part is treated as a normal part.

[0089] In this embodiment, the first preset index, the second preset index, and the preset coefficient are three threshold parameters preset by the system to determine whether an abnormal part can be considered a normal part. Specifically, the first preset index is a threshold for the compatibility between the abnormal part and related parts, typically set to 0.85; the second preset index is a threshold for the compatibility between the abnormal part and the main component, typically set to 0.80; and the preset coefficient is a threshold for the degree of influence of the abnormal part on other parts, typically set to 0.30. These threshold parameters can be adjusted according to different product types and different precision requirements to adapt to different production scenarios.

[0090] In practical applications, the system first obtains the three index values ​​calculated in the aforementioned steps, and then compares them with the corresponding thresholds. For example, for an abnormal shaft component with a diameter of 19.92mm, assuming the calculated first fit index is 0.92 (indicating good fit with the bushing), the second fit index is 0.88 (indicating stable assembly with the main component), and the influence coefficient is 0.15 (indicating minimal impact on other components), the system compares these three indicators with preset thresholds: 0.92 > 0.85 (first preset index), 0.88 > 0.80 (second preset index), and 0.15 < 0.30 (preset coefficient). Since all three conditions are met, the system reclassifies the abnormal component as a normal component, allowing it to continue to be used on the production line.

[0091] The reason for adopting this three-dimensional comprehensive evaluation decision-making mechanism is that traditional parts evaluation methods have significant limitations. Traditional methods typically judge only based on the dimensional conformity of the parts themselves, classifying any parts with abnormal dimensions but fully functional as defective, leading to a significant waste of resources. This method, however, breaks away from the simple binary judgment model by comprehensively evaluating the actual compatibility and system impact of defective parts, achieving a more accurate parts evaluation.

[0092] Specifically, the first compatibility index is greater than the first preset index, ensuring a good fit between the abnormal component and its directly contacting related components, enabling normal assembly. The second compatibility index is greater than the second preset index, ensuring the abnormal component can be stably installed on the main component without loosening or shifting due to dimensional abnormalities. The impact coefficient is less than the preset coefficient, ensuring that the abnormal component will not have a significant negative impact on other components in the system, and will not compromise the overall assembly accuracy and stability. Only when all three conditions are met will the system reclassify the abnormal component as a normal component. This rigorous triple-protection mechanism ensures the reliability and security of the evaluation results.

[0093] After reclassifying eligible defective parts as normal parts, the system updates the part status flags and imports them into the normal production process. For defective parts that do not meet the criteria, the system may mark them as scrap or initiate a subsequent matching and evaluation process.

[0094] S105, when the first compatibility index is not greater than the first preset index, and / or the second compatibility index is not greater than the second preset index, and / or the influence coefficient is not less than the preset coefficient, the abnormal accessory is marked as a accessory to be matched and temporarily stored.

[0095] S106, continue to test the remaining parts and generate test data for the remaining parts.

[0096] The system continues to inspect the remaining components, generating inspection data for them. "Remaining components" refers to components that have not yet been inspected in the production process, or batches of components newly arriving at the inspection station. The inspection process is consistent with the method described in the previous embodiments, using dedicated inspection equipment to accurately measure the key dimensions and characteristics of the components, generating inspection data containing multiple dimensional parameters. The purpose of this step is to continuously acquire new component information, find potential "partners" for matching components, and achieve optimized combinations of abnormal components and maximize resource utilization.

[0097] S107, Based on the test data of the remaining parts, a new abnormal part is identified among the remaining parts.

[0098] Based on the inspection data of the remaining parts, the system identifies new abnormal parts among the remaining parts. "New abnormal parts" refer to parts that do not conform to standard specifications and are newly discovered during the remaining parts inspection process. The identification method is consistent with the aforementioned embodiments: by comparing the deviation between the inspection data and the standard specifications, it is determined whether the part is abnormal. These new abnormal parts also do not meet the conditions for individual use, but their dimensional characteristics may complement those of the temporarily stored parts to be matched, creating conditions for pairing and utilization. For example, a shaft with a slightly larger outer diameter and a bearing with a slightly larger inner diameter, although neither of them meet the standard requirements, may form a suitable fit clearance when matched to meet functional needs. The significance of this step is to continuously expand the library of potential matching objects and increase the probability of successful matching.

[0099] S108, perform a pairing evaluation between the accessory to be matched and the new abnormal accessory, and calculate the pairing compatibility index between the accessory to be matched and the new abnormal accessory.

[0100] The system performs pairing evaluations on the component to be matched and the new abnormal component, calculating the pairing compatibility index between them. "Pairing evaluation" refers to the system analyzing the compatibility and functionality of two abnormal components when used together, assessing whether they can compensate for each other's deficiencies and jointly meet product requirements. The "pairing compatibility index" is a quantitative indicator used to measure the overall compatibility of two abnormal components when used together, typically ranging from 0 to 1, where 1 represents perfect compatibility. The calculation of the pairing compatibility index usually considers the following aspects: First, physical compatibility, i.e., whether the two components can be correctly assembled in terms of size and shape; second, functional compatibility, i.e., whether the combination can achieve the expected function; third, reliability expectation, i.e., whether the combination will affect the long-term reliability of the product; and finally, system impact, i.e., whether the combination will have a negative impact on other components or the overall system. The calculation method typically employs a multi-index comprehensive scoring approach. For example: Pairing Compatibility Index = w1 × Physical Compatibility Score + w2 × Functional Compatibility Score + w3 × Reliability Expectation Score + w4 × System Impact Score; where w1, w2, w3, and w4 are the weighting coefficients of each index, and satisfy w1 + w2 + w3 + w4 = 1. Taking the pairing of a shaft and a bearing as an example, if a shaft with a diameter of 49.92mm (standard is 50.00mm) is paired with a bearing with an inner diameter of 50.12mm (standard is 50.05mm), although both are outside the standard deviation range, the resulting fit clearance is 50.12mm - 49.92mm = 0.20mm. If the functionally permissible clearance range for this product is 0.05mm to 0.25mm, then this combination is physically feasible. The system will further evaluate the impact of this clearance on functional parameters such as bearing operating speed, load capacity, noise, and lifespan, as well as its impact on the overall system, and comprehensively calculate the pairing compatibility index. This meticulous pairing assessment ensures the scientific validity and reliability of abnormal component combinations, avoiding quality risks caused by simple assembly.

[0101] S109: When the pairing compatibility index is greater than the preset pairing index, the accessory to be matched and the new abnormal accessory will be combined as normal accessories.

[0102] When the matching compatibility index exceeds the preset matching index, the system will combine the component to be matched and the new abnormal component as normal components. The "preset matching index" is a matching compatibility threshold pre-set by the enterprise based on product quality requirements and actual production conditions. It is usually slightly higher than the compatibility requirements of a single component to ensure the safety of combined use. For example, an enterprise might set the preset matching index to 0.8, meaning that only when the compatibility score of two abnormal components reaches 0.8 or higher will they be allowed to be used as a "normal component combination" in the product. The concept of "normal component combination" reflects the innovation of this method: through scientific matching, two individually unqualified abnormal components are transformed into a functional, reliable, and safe component combination, realizing the value extraction of abnormal components and the efficient utilization of resources. These matched and certified combinations will be marked with a special identifier and enter subsequent production stages according to the normal component process, but they are usually assigned to specific product batches for subsequent quality tracking and verification.

[0103] Based on the above method, this application also discloses a visual inspection-based intelligent evaluation system for accessories, as shown in Figure 2. Figure 2 is a structural schematic diagram of a visual inspection-based intelligent evaluation system for accessories provided in an embodiment of this application. The system includes: a detection module, a first calculation module, a second calculation module, and a judgment module. The detection module is used to inspect the main component and multiple accessories to be assembled into the main component using a visual inspection system, generating detection data for the main component and each accessory. The first calculation module is used to determine abnormal accessories among the multiple accessories based on the detection data, and calculate a first compatibility index between the abnormal accessory and associated accessories, and a second compatibility index between the abnormal accessory and the main component. Associated accessories are accessories among the multiple accessories that come into contact with the abnormal accessory during assembly. The second calculation module is used to calculate the influence coefficient of the abnormal accessory on other accessories based on the detection data. Other accessories are accessories among the multiple accessories excluding the abnormal accessory and associated accessories. The judgment module is used to classify the abnormal accessory as a normal accessory when the first compatibility index is greater than a first preset index, the second compatibility index is greater than a second preset index, and the influence coefficient is less than a preset coefficient.

[0104] It should be noted that the system provided in the above embodiments is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0105] Please refer to Figure 3, which is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. As shown in Figure 3, the electronic device 1000 may include: at least one processor 1001, at least one network interface 1004, a user interface 1003, a memory 1005, and at least one communication bus 1002.

[0106] The communication bus 1002 is used to realize the connection and communication between these components.

[0107] The user interface 1003 may include a display screen and a camera. Optionally, the user interface 1003 may also include a standard wired interface and a wireless interface.

[0108] The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0109] The processor 1001 may include one or more processing cores. The processor 1001 connects to various parts of the server using various interfaces and lines, and performs various server functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 1005, and by calling data stored in the memory 1005. Optionally, the processor 1001 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 1001 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content to be displayed on the screen; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 1001 and may be implemented as a separate chip.

[0110] The memory 1005 may include random access memory (RAM) or read-only memory. Optionally, the memory 1005 may include a non-transitory computer-readable storage medium. The memory 1005 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 1005 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 1005 may also be at least one storage device located remotely from the aforementioned processor 1001. As shown in FIG3, the memory 1005, as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for a visual inspection-based intelligent evaluation method for accessories.

[0111] In the electronic device 1000 shown in Figure 3, the user interface 1003 is mainly used to provide an input interface for the user and obtain the user input data; while the processor 1001 can be used to call an application program stored in the memory 1005 for a visual inspection-based intelligent evaluation method for accessories. When executed by one or more processors, the electronic device performs one or more of the methods described in the above embodiments.

[0112] An electronic device readable storage medium stores instructions that, when executed by one or more processors, cause the electronic device to perform one or more of the methods described in the above embodiments.

[0113] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0114] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0115] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some service interfaces; indirect couplings or communication connections between devices or units may be electrical or other forms.

[0116] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0117] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0118] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0119] The foregoing description is merely an exemplary embodiment of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Other embodiments of this disclosure will be readily apparent to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described herein. The specification and embodiments are to be considered exemplary only, and the scope and spirit of this disclosure are defined by the claims.

Claims

1. A visual inspection-based intelligent evaluation method for accessories, characterized in that, The method includes: inspecting a main component and multiple accessories to be assembled into the main component using a visual inspection system to generate inspection data for the main component and each accessory; identifying abnormal accessories among the multiple accessories based on the inspection data, and calculating a first compatibility index between the abnormal accessory and associated accessories, and a second compatibility index between the abnormal accessory and the main component; wherein, the associated accessories are accessories among the multiple accessories that come into contact with the abnormal accessory during assembly; calculating the influence coefficient of the abnormal accessory on other accessories based on the inspection data, wherein the other accessories are accessories among the multiple accessories excluding the abnormal accessory and the associated accessories; and classifying the abnormal accessory as a normal accessory when the first compatibility index is greater than a first preset index, the second compatibility index is greater than a second preset index, and the influence coefficient is less than a preset coefficient.

2. The intelligent evaluation method for accessories based on vision inspection according to claim 1, characterized in that, The detection data includes size and position. The step of determining abnormal components among multiple components based on the detection data, and calculating a first compatibility index between the abnormal component and associated components, and a second compatibility index between the abnormal component and the main body component, includes: when the size of a target component among the multiple components is not within a preset size range, classifying the target component as an abnormal component; determining associated components of the abnormal component based on the position of each component; obtaining a first size of the abnormal component, a second size of the associated component, and a third size of the main body component; calculating the first compatibility index between the abnormal component and the associated component by combining the first size and the second size; and calculating the second compatibility index between the abnormal component and the main body component by combining the first size and the third size.

3. The intelligent evaluation method for accessories based on vision inspection according to claim 2, characterized in that, The step of calculating the first compatibility index between the abnormal accessory and the associated accessory by combining the first dimension and the second dimension includes: obtaining the standard mating dimensions of the abnormal accessory and the associated accessory; calculating a first deviation value between the first dimension and the standard mating dimensions, and a second deviation value between the second dimension and the standard mating dimensions; calculating a mating clearance value based on the first deviation value and the second deviation value; setting the first compatibility index between the abnormal accessory and the associated accessory to 0 when the mating clearance value is less than the minimum value of a preset mating clearance range or greater than the maximum value of the preset mating clearance range; calculating a first clearance deviation value between the mating clearance value and the center value of the preset mating clearance range when the mating clearance value is within the preset mating clearance range; and determining the first compatibility index between the abnormal accessory and the associated accessory based on the first clearance deviation value; wherein the deviation value is inversely proportional to the first compatibility index.

4. The intelligent evaluation method for accessories based on vision inspection according to claim 2, characterized in that, The step of calculating the second fit index between the abnormal accessory and the main component by combining the first dimension and the third dimension includes: obtaining the standard assembly dimensions of the abnormal accessory and the main component; calculating a third deviation value between the first dimension and the standard assembly dimensions, and a fourth deviation value between the third dimension and the standard assembly dimensions; calculating an assembly gap value based on the third deviation value and the fourth deviation value; setting the second fit index between the abnormal accessory and the main component to 0 when the assembly gap value is less than the minimum value of a preset assembly gap range or greater than the maximum value of the preset assembly gap range; calculating a second gap deviation value between the assembly gap value and the center value of the preset assembly gap range when the assembly gap value is within the preset assembly gap range; and determining the second fit index between the abnormal accessory and the main component based on the second gap deviation value; wherein the second gap deviation value is inversely proportional to the second fit index.

5. The intelligent evaluation method for accessories based on vision inspection according to claim 1, characterized in that, The step of calculating the influence coefficient of the abnormal component on other components based on the detection data includes: simulating the assembly process of sequentially installing the abnormal component and other components onto the main body component based on the detection data; during the assembly process, detecting whether the abnormal component causes the installation position of the other components to shift; if the abnormal component causes the installation position of the other components to shift, obtaining the amount of the shift; and calculating the influence coefficient of the abnormal component on the other components based on the amount of the shift.

6. The intelligent evaluation method for accessories based on vision inspection according to claim 5, characterized in that, The step of calculating the influence coefficient of the abnormal component on the other components based on the offset includes: obtaining the importance level of the other components; determining the weight coefficient corresponding to the other components based on the importance level; arithmetically multiplying the offset of the other components by the corresponding weight coefficient to generate a weighted offset; and calculating the influence coefficient of the abnormal component on the other components based on the weighted offset; wherein the weighted offset is directly proportional to the influence coefficient.

7. The intelligent evaluation method for accessories based on vision inspection according to claim 1, characterized in that, The method further includes: when the first adaptation index is not greater than the first preset index, and / or the second adaptation index is not greater than the second preset index, and / or the influence coefficient is not less than the preset coefficient, marking the abnormal accessory as a matching accessory and temporarily storing it; continuing to detect the remaining accessories to generate detection data for the remaining accessories; based on the detection data of the remaining accessories, identifying new abnormal accessories among the remaining accessories; performing pairing evaluation between the matching accessory and the new abnormal accessory, calculating the pairing adaptation index between the matching accessory and the new abnormal accessory; when the pairing adaptation index is greater than the preset pairing index, treating the matching accessory and the new abnormal accessory as a normal accessory combination.

8. A visual inspection-based intelligent evaluation system for accessories, characterized in that, The system includes a detection module, a first calculation module, a second calculation module, and a judgment module. The detection module is used to detect a main component and multiple accessories to be assembled into the main component using a visual inspection system, generating detection data for the main component and each accessory. The first calculation module is used to determine abnormal accessories among the multiple accessories based on the detection data, and calculate a first compatibility index between the abnormal accessory and associated accessories, and a second compatibility index between the abnormal accessory and the main component. The associated accessories are those that come into contact with the abnormal accessory during assembly. The second calculation module is used to calculate the influence coefficient of the abnormal accessory on other accessories based on the detection data. The other accessories are accessories other than the abnormal accessory and the associated accessories. The judgment module is used to classify the abnormal accessory as a normal accessory if the first compatibility index is greater than a first preset index, the second compatibility index is greater than a second preset index, and the influence coefficient is less than a preset coefficient.

9. An electronic device, characterized in that, The device includes a processor, a memory, a user interface, and a network interface. The memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory to cause the electronic device to perform the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer program is stored that can be loaded by a processor and executed as described in any one of claims 1-7.

Images