Industrial product quality detection method and system based on machine vision

Abstract

The invention discloses an industrial product quality detection method and system based on machine vision, and relates to the technical field of quality detection.During operation of the system, through an industrial camera and an optimized light source layout, high-resolution image acquisition is performed on electronic components in real time by adopting multi-angle shooting, a series of optimization processing is performed on the acquired images, and the quality of the electronic components is detected. The method comprises the following steps: extracting shape, texture and color features according to geometric characteristics of an electronic component to form key parameters for judging defects, identifying potential defects of the electronic component by using a deep learning model algorithm, calculating to obtain a quality evaluation index Q, and calculating the quality evaluation index Q according to calculation results of feature extraction and defect detection. And comprehensively evaluating the quality of each component, comparing the quality evaluation index Q with a first preset threshold value M and a second preset threshold value N to obtain a quality evaluation grade, feeding unqualified detection information back to a production line, and removing unqualified components.

Description

Technical Field

[0001] The present invention relates to the technical field of quality inspection, and in particular to a method and system for industrial product quality inspection based on machine vision. Background Art

[0002] Electronic components are widely used in modern industrial products, and the stability and reliability of their quality directly affect the overall performance of the product. However, due to the small size and complex structure of electronic components, as well as the precision requirements in their production process, traditional quality inspection methods often cannot meet the needs of high-precision and high-efficiency inspection. In this context, machine vision technology has gradually attracted attention. By using image acquisition and analysis technology to realize automatic recognition of product appearance features, it provides high-resolution, multi-angle real-time quality inspection methods for electronic components. The application of machine vision technology has significantly improved the accuracy, efficiency and consistency of the inspection process, and has gradually become an important means of industrial product quality inspection.

[0003] Traditional inspection methods mostly rely on manual labor or are completed through relatively inefficient mechanical means. They are not only inefficient but also inaccurate, and cannot guarantee high consistency in product quality. During the real-time inspection process, the system can identify potential defects such as poor solder joints, missing components, and pin misalignment, effectively avoiding omissions and misjudgments in traditional inspections, and improving the yield and stability of the production line. The shortcomings of traditional quality inspection methods mainly come from the lack of inspection accuracy and efficiency, as well as the lack of real-time monitoring, which makes it difficult to detect some minor defects, and even makes it impossible to achieve closed-loop feedback control of product quality. When abnormal conditions or defects accumulate during the production process, they are often not identified and measures cannot be taken in a timely manner, which may eventually lead to problems such as poor product consistency and high rework rate. This not only has a negative impact on production efficiency, but also increases production costs and affects the competitiveness of enterprises in the market. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides an industrial product quality inspection method and system based on machine vision, which solves the problems mentioned in the background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: an industrial product quality inspection system based on machine vision, including an image acquisition module, an image preprocessing module, a feature extraction module, a defect detection module, a quality assessment module and a control feedback module; The image acquisition module is used to acquire high-resolution images of electronic components in real time by using industrial cameras and optimized light source layout, using multi-angle shooting. The arrangement of light sources takes into account the small size and high precision requirements of electronic components, and can highlight image pixels, clarity, product edges, defect frequencies and subtle features of welding points; The image preprocessing module is used to perform a series of optimization processes on the collected images, including filtering and noise reduction, edge enhancement and grayscale conversion, and adopts background difference technology to eliminate the interference of ambient light and improve the contrast of the image; The feature extraction module is used to extract key features of electronic components, including the shape of solder joints, the arrangement of pins and the position of components. According to the geometric characteristics of electronic components, shape, texture and color features are extracted to form key parameters for identifying defects. The defect detection module is used to identify potential defects of electronic components using a deep learning model algorithm, including poor solder joints, missing components, pin misalignment and scratches, and obtains after calculation: a quality assessment index Q; The quality assessment module is used to make a comprehensive evaluation of the quality of each component based on the calculation results of feature extraction and defect detection, and compare the quality assessment index Q with the first preset threshold M and the second preset threshold N to evaluate the size deviation, defect type and quantity, and obtain the quality assessment grade; The control feedback module is used to feed back unqualified detection information to the production line, remove unqualified components, and adjust production parameters to improve yield. By connecting with the production management system, a closed-loop feedback is formed to continuously optimize the production process.

[0006] Preferably, the image acquisition module includes an image acquisition unit, a defect type unit and a feature parameter synchronization storage unit; The image acquisition unit is used to acquire clear, low-noise component images through an industrial camera and an optimized light source setting, and obtain: the total number of pixels N in the image, the gray value I(i) of the i-th pixel, and the gray value I(i+1) of the adjacent pixel; The defect type unit is used to extract defect frequencies and features based on production history and real-time image data, use a known sample library, mark the frequency of occurrence of different defects, record the distribution of various defects in the production process, extract the original data of key feature parameters, including solder joints, pin positions and arrangements, and obtain: the number of defect types M; The characteristic parameter synchronous storage unit is used to synchronously store the image data and characteristic parameters, generate a unique identification for each component, classify and archive the data, and store the image data, defect mark, and characteristic data separately.

[0007] Preferably, the image preprocessing module includes an image preprocessing unit; The image preprocessing unit is used to perform denoising on the collected image, reduce interference noise in the image, ensure image quality, enhance the edges in the image, make the boundaries and welding points of components clearer for feature extraction, use background difference technology to eliminate the influence of ambient light, improve image contrast, and make component features more obvious.

[0008] Preferably, the feature extraction module includes a geometric feature extraction unit, a texture feature extraction unit and a color feature extraction unit; The geometric feature extraction unit is used to extract the geometric features of components, such as the shape of soldering points and pin arrangement, and provide feature parameters; The texture feature extraction unit is used to analyze the texture features in the image, including the texture differences between the solder joint and the component surface, to provide support for defect detection; The color feature extraction unit is used to extract color distribution features and record component color information for use in determining surface contamination or other abnormal conditions.

[0009] Preferably, the defect detection module includes a deep learning model unit and a quality assessment index calculation unit; The deep learning model unit is used to apply the trained deep learning model to automatically identify various defects in the image and classify the identified defects, including poor solder joints, missing components, pin misalignment, and surface scratches; The quality assessment index calculation unit is used to train a convolutional neural network (CNN) or a deep residual network (ResNet) model to automatically identify surface scratches, pits and cracks, and obtain the following after calculation: image clarity coefficient C, defect probability coefficient P defect And the quality assessment index Q of components.

[0010] Preferably, the image clarity coefficient C is calculated by the following formula: ; Where C represents the image clarity coefficient, N represents the total number of pixels in the image, I(i) represents the grayscale value of the i-th pixel, and I(i+1) represents the grayscale value of the adjacent pixel; The defect probability coefficient P defect Calculated by the following formula: ; Where P defect represents the defect probability coefficient, M represents the number of defect types, and w j represents the weight of the j-th defect, F j Represents the occurrence frequency of the jth type of defect.

[0011] Preferably, the quality assessment index Q of the component is calculated by the following formula: ; In the formula, Q represents the quality evaluation index of components, C represents the image clarity coefficient, P defect Denotes the defect probability coefficient, T krepresents the quality evaluation value of the characteristic parameter k, K represents the number of key features for quality detection, Represents the weight coefficient.

[0012] Preferably, the quality assessment module includes an assessment grade unit; The evaluation grade unit is used to compare the calculated quality evaluation index Q with the preset first threshold value M and second threshold value A, determine whether the component is qualified, evaluate the size deviation, defect type and quantity of the component, generate quality analysis data, and classify the quality of the component based on the comprehensive evaluation results to provide a specific basis for production quality control; If the quality assessment index Q ≥ the first threshold M, the first assessment level is obtained, indicating that the quality of the components meets the qualified standard, the solder joint shape, pin arrangement and color uniformity meet the requirements, and no further operation is required. The components in this batch are marked as qualified and recorded in the system database; If the second threshold value A≤quality assessment index Q<first threshold value M, the second assessment level is obtained. This interval is the warning level, indicating that the components have defects within 25%, which are manifested as minor poor solder joints or uneven color distribution, but do not affect the overall function. It is marked as a warning level, and the components of this batch are divided into independent areas and the maintenance procedure is triggered. The quality inspection system issues a warning and feedback is fed back to the production line for adjustment; If the quality assessment index Q is less than the second threshold value A, the third assessment level is obtained. Such components have serious defects and cannot meet functional requirements. Unqualified components are immediately eliminated, the specific types of defects are recorded, and the data is fed back to the production management system for defect analysis. The production equipment and process parameters are further adjusted through the control feedback module. Defect prevention strategies are formulated based on the identified defect types and characteristic parameters. For surface scratches and cracks, the quality inspection frequency is increased.

[0013] Preferably, the control feedback module includes a non-conforming feedback unit and a production parameter adjustment unit; The unqualified feedback unit is used to feed back the detected unqualified components information to the production line, timely remove products that do not meet the quality standards, transmit unqualified information in real time, effectively prevent defective products from flowing into the downstream links, and ensure that the production line takes prompt measures when quality problems occur; The production parameter adjustment unit is used to adjust the process parameters of the production line, including welding temperature, equipment pressure or light source layout, according to the defect type, frequency and distribution data in the quality assessment results, to ensure that the production process meets the product quality requirements, form a closed-loop feedback system, and gradually reduce the defect rate by adjusting the production parameters.

[0014] A method for detecting industrial product quality based on machine vision comprises the following steps: Step 1: Use industrial cameras and optimized light source layout to capture high-resolution images of electronic components in real time using multi-angle shooting. The arrangement of light sources takes into account the small size and high-precision requirements of electronic components, and can highlight image pixels, clarity, product edges, defect frequencies, and subtle features of welding points; Step 2: Perform a series of optimization processes on the collected images, including filtering and noise reduction, edge enhancement and grayscale conversion, and use background difference technology to eliminate the interference of ambient light and improve the contrast of the image; Step 3: Extract key features of electronic components, including the shape of solder joints, arrangement of pins and component positions. According to the geometric characteristics of electronic components, extract shape, texture and color features to form key parameters for identifying defects. Step 4: Use the deep learning model algorithm to identify potential defects of electronic components, including poor solder joints, missing components, pin misalignment, and scratches, and calculate and obtain the quality assessment index Q; Step 5: Based on the calculation results of feature extraction and defect detection, make a comprehensive evaluation of the quality of each component, compare the quality evaluation index Q with the first preset threshold M and the second preset threshold N, evaluate the size deviation, defect type and quantity, and obtain the quality evaluation grade; Step 6: Feedback unqualified inspection information to the production line, remove unqualified components, and adjust production parameters to improve yield. By connecting with the production management system, a closed-loop feedback is formed to continuously optimize the production process.

[0015] The present invention provides an industrial product quality inspection method and system based on machine vision, which has the following beneficial effects: (1) When the system is running, it uses industrial cameras and optimized light source layout to capture high-resolution images of electronic components in real time using multi-angle shooting. It then performs a series of optimization processing on the captured images. It extracts shape, texture, and color features based on the geometric characteristics of the electronic components to form key parameters for identifying defects. It uses a deep learning model algorithm to identify potential defects in electronic components. After calculation, it obtains the quality assessment index Q. Based on the calculation results of feature extraction and defect detection, it makes a comprehensive evaluation of the quality of each component. It compares the quality assessment index Q with the first preset threshold M and the second preset threshold N to obtain the quality assessment grade. It then feeds back unqualified detection information to the production line to remove unqualified components.

[0016] (2) Through the coordinated operation of modules such as image acquisition, image preprocessing, feature extraction, defect detection, quality assessment and control feedback, all-round, multi-dimensional, high-precision quality inspection of electronic components is achieved. The image acquisition module and image preprocessing module enable the system to obtain clear, high-resolution image data and eliminate environmental interference to highlight the detailed features of components; the feature extraction module further analyzes and records the product geometry, texture and color features as important parameter basis for defect identification. These steps lay a solid foundation for subsequent defect detection and quality assessment.

[0017] (3) Through the introduction of deep learning models, the system enables the defect detection module to quickly and accurately identify multiple defect types and further generate a quality assessment index Q. This index combines parameters such as image clarity coefficient and defect probability coefficient to quantitatively evaluate the quality of components, thereby realizing the comprehensive evaluation capability of the quality assessment module. On this basis, the system outputs quality grades in a hierarchical manner according to different evaluation results to support precise production quality control. Compared with traditional detection methods, this evaluation mechanism not only improves the accuracy of defect identification and classification precision through the application of deep learning technology, but also realizes the automation and real-time nature of the detection process, allowing the production line to adjust the process in a timely manner based on the evaluation data.

[0018] (4) The system feeds back the inspection information to the production line in real time through the control feedback module, realizes the elimination of defective products and the optimization adjustment of production parameters, and forms a closed-loop feedback control system. Compared with traditional methods, this system significantly reduces the error rate and missed detection rate of human intervention, while improving the overall production quality and consistency. By reducing the defective rate and rework costs, the system effectively improves production efficiency and yield rate, enhances the reliability and automation of the production process, and achieves the goal of improving product quality and optimizing production efficiency. This intelligent quality inspection system not only improves the limitations of traditional inspection methods, but also promotes the quality control level of high-precision products such as electronic components in industrial production. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a block diagram of an industrial product quality inspection system based on machine vision of the present invention; Figure 2 The present invention is a schematic diagram of the steps of an industrial product quality detection method based on machine vision. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] Example 1 The present invention provides an industrial product quality inspection system based on machine vision. Figure 1 , including image acquisition module, image preprocessing module, feature extraction module, defect detection module, quality assessment module and control feedback module; The image acquisition module is used to acquire high-resolution images of electronic components in real time by using industrial cameras and optimized light source layout, using multi-angle shooting. The arrangement of light sources takes into account the small size and high precision requirements of electronic components, and can highlight image pixels, clarity, product edges, defect frequencies and subtle features of welding points; The image preprocessing module is used to perform a series of optimization processes on the collected images, including filtering and noise reduction, edge enhancement and grayscale conversion, and adopts background difference technology to eliminate the interference of ambient light and improve the contrast of the image; The feature extraction module is used to extract key features of electronic components, including the shape of solder joints, the arrangement of pins and the position of components. According to the geometric characteristics of electronic components, shape, texture and color features are extracted to form key parameters for identifying defects. The defect detection module is used to identify potential defects of electronic components using a deep learning model algorithm, including poor solder joints, missing components, pin misalignment and scratches, and obtains after calculation: a quality assessment index Q; The quality assessment module is used to make a comprehensive evaluation of the quality of each component based on the calculation results of feature extraction and defect detection, and compare the quality assessment index Q with the first preset threshold M and the second preset threshold N to evaluate the size deviation, defect type and quantity, and obtain the quality assessment grade; The control feedback module is used to feed back unqualified detection information to the production line, remove unqualified components, and adjust production parameters to improve yield. By connecting with the production management system, a closed-loop feedback is formed to continuously optimize the production process.

[0022] In this embodiment, through industrial cameras and optimized light source layout, multi-angle shooting is used to collect high-resolution images of electronic components in real time. The arrangement of light sources takes into account the small size and high-precision requirements of electronic components, and can highlight image pixels, clarity, product edges, defect frequencies and subtle features of welding points. A series of optimization processes are performed on the collected images, including filtering and noise reduction, edge enhancement and grayscale. Background difference technology is used to eliminate the interference of ambient light, improve the contrast of the image, and extract the key features of electronic components, including the shape of the welding point, the arrangement of the pins and the position of the components. According to the geometric characteristics of the electronic components, the shape, texture and color features are extracted to form The key parameters for distinguishing defects are used. The deep learning model algorithm is used to identify potential defects of electronic components, including poor solder joints, missing components, pin misalignment and scratches. After calculation, the quality assessment index Q is obtained. According to the calculation results of feature extraction and defect detection, a comprehensive evaluation is made on the quality of each component. The quality assessment index Q is compared with the first preset threshold M and the second preset threshold N to evaluate the dimensional deviation, defect type and quantity, obtain the quality assessment grade, feed back the unqualified inspection information to the production line, eliminate the unqualified components, and adjust the production parameters to improve the yield. By connecting with the production management system, a closed-loop feedback is formed to continuously optimize the production process.

[0023] Example 2 This embodiment is explained in Example 1, please refer to Figure 1 , specifically: the image acquisition module includes an image acquisition unit, a defect type unit and a feature parameter synchronization storage unit; The image acquisition unit is used to acquire clear, low-noise component images through an industrial camera and an optimized light source setting, and obtain: the total number of pixels N in the image, the gray value I(i) of the i-th pixel, and the gray value I(i+1) of the adjacent pixel; The defect type unit is used to extract defect frequencies and features based on production history and real-time image data, use a known sample library, mark the frequency of occurrence of different defects, record the distribution of various defects in the production process, extract the original data of key feature parameters, including solder joints, pin positions and arrangements, and obtain: the number of defect types M; The characteristic parameter synchronous storage unit is used to synchronously store the image data and characteristic parameters, generate a unique identification for each component, classify and archive the data, and store the image data, defect mark, and characteristic data separately.

[0024] The image preprocessing module includes an image preprocessing unit; The image preprocessing unit is used to perform denoising on the collected image, reduce interference noise in the image, ensure image quality, enhance the edges in the image, make the boundaries and welding points of components clearer for feature extraction, use background difference technology to eliminate the influence of ambient light, improve image contrast, and make component features more obvious.

[0025] The feature extraction module includes a geometric feature extraction unit, a texture feature extraction unit and a color feature extraction unit; The geometric feature extraction unit is used to extract the geometric features of components, such as the shape of soldering points and pin arrangement, and provide feature parameters; The texture feature extraction unit is used to analyze the texture features in the image, including the texture differences between the solder joint and the component surface, to provide support for defect detection; The color feature extraction unit is used to extract color distribution features and record component color information for use in determining surface contamination or other abnormal conditions.

[0026] In this embodiment, the system significantly improves the accuracy and efficiency of electronic component quality inspection through the close cooperation of image acquisition, preprocessing and feature extraction modules. The image acquisition unit in the image acquisition module is combined with the optimized light source setting to ensure that the collected component image is clear and low in noise, which helps to highlight the tiny features of the product. The introduction of the defect type unit enables the system to extract the defect type and distribution frequency based on the production history and real-time image data. Through the management of the feature parameter synchronization storage unit, the system can generate a unique identifier for each component, realizing the effective classification and archiving of data. The image preprocessing module further improves the image quality, and through denoising and edge enhancement, the key details such as the boundaries and welding points in the image are clearer. In particular, the application of background difference technology effectively eliminates the interference of ambient light, making the features of components more distinct, thereby improving the reliability of subsequent detection. The geometric feature, texture feature and color feature extraction unit in the feature extraction module provide multi-dimensional feature support for defect detection, which can not only extract the geometric and surface information of components, but also monitor color anomalies and quickly judge surface contamination or other potential problems.

[0027] Example 3 This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the defect detection module includes a deep learning model unit and a quality assessment index calculation unit; The deep learning model unit is used to apply the trained deep learning model to automatically identify various defects in the image and classify the identified defects, including poor solder joints, missing components, pin misalignment, and surface scratches; The quality assessment index calculation unit is used to train a convolutional neural network (CNN) or a deep residual network (ResNet) model to automatically identify surface scratches, pits and cracks, and obtain the following after calculation: image clarity coefficient C, defect probability coefficient P defect And the quality assessment index Q of components.

[0028] The image clarity coefficient C is calculated by the following formula: ; Where C represents the image clarity coefficient, N represents the total number of pixels in the image, I(i) represents the grayscale value of the i-th pixel, and I(i+1) represents the grayscale value of the adjacent pixel; The defect probability coefficient P defect Calculated by the following formula: ; Where P defect represents the defect probability coefficient, M represents the number of defect types, and w j represents the weight of the j-th defect, F j Represents the occurrence frequency of the jth type of defect.

[0029] The quality assessment index Q of the components is calculated by the following formula: ; In the formula, Q represents the quality evaluation index of components, C represents the image clarity coefficient, P defect Denotes the defect probability coefficient, T k represents the quality evaluation value of the characteristic parameter k, K represents the number of key features for quality detection, Represents the weight coefficient.

[0030] In this embodiment, the defect detection module of the system realizes the automatic and high-precision identification of defects of electronic components through the combination of deep learning model unit and quality assessment index calculation unit. The deep learning model unit uses the trained model to quickly classify various defects in the image, covering key defect types such as poor solder joints, missing components, pin misalignment and surface scratches. The quality assessment index calculation unit further uses convolutional neural network (CNN) or deep residual network (ResNet) to accurately identify more subtle defects such as surface scratches, pits and cracks, and generate clarity coefficient C and defect probability coefficient P defect And other key indicators provide a quantitative basis for comprehensive quality assessment.

[0031] Example 4 This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the quality assessment module includes an assessment grade unit; The evaluation grade unit is used to compare the calculated quality evaluation index Q with the preset first threshold value M and second threshold value A, determine whether the component is qualified, evaluate the size deviation, defect type and quantity of the component, generate quality analysis data, and classify the quality of the component based on the comprehensive evaluation results to provide a specific basis for production quality control; If the quality assessment index Q ≥ the first threshold M, the first assessment level is obtained, indicating that the quality of the components meets the qualified standard, the solder joint shape, pin arrangement and color uniformity meet the requirements, and no further operation is required. The components in this batch are marked as qualified and recorded in the system database; If the second threshold value A≤quality assessment index Q<first threshold value M, the second assessment level is obtained. This interval is the warning level, indicating that the components have defects within 25%, which are manifested as minor poor solder joints or uneven color distribution, but do not affect the overall function. It is marked as a warning level, and the components of this batch are divided into independent areas and the maintenance procedure is triggered. The quality inspection system issues a warning and feedback is fed back to the production line for adjustment; If the quality assessment index Q is less than the second threshold value A, the third assessment level is obtained. Such components have serious defects and cannot meet functional requirements. Unqualified components are immediately eliminated, the specific types of defects are recorded, and the data is fed back to the production management system for defect analysis. The production equipment and process parameters are further adjusted through the control feedback module. Defect prevention strategies are formulated based on the identified defect types and characteristic parameters. For surface scratches and cracks, the quality inspection frequency is increased.

[0032] The control feedback module includes a non-conforming feedback unit and a production parameter adjustment unit; The unqualified feedback unit is used to feed back the detected unqualified components information to the production line, timely remove products that do not meet the quality standards, transmit unqualified information in real time, effectively prevent defective products from flowing into the downstream links, and ensure that the production line takes prompt measures when quality problems occur; The production parameter adjustment unit is used to adjust the process parameters of the production line, including welding temperature, equipment pressure or light source layout, according to the defect type, frequency and distribution data in the quality assessment results, to ensure that the production process meets the product quality requirements, form a closed-loop feedback system, and gradually reduce the defect rate by adjusting the production parameters.

[0033] In this embodiment, the quality assessment module and control feedback module of the system effectively improve the accuracy and response speed of product quality management through strict grade division and feedback mechanism. The quality assessment module compares the quality assessment index Q of each component with the preset thresholds M and A through the assessment grade unit, accurately divides the quality grade, and thus provides a clear operating basis for production control. For components with qualified grades, the system can automatically archive data; components at the warning level trigger the maintenance program to ensure that minor defects are repaired in time; unqualified components are immediately removed to prevent defective products from flowing into subsequent links and ensure product quality consistency. The unqualified feedback unit in the control feedback module transmits unqualified information in real time, enabling the production line to respond to quality problems quickly, greatly reducing the circulation of defective products. The production parameter adjustment unit dynamically optimizes production parameters such as welding temperature and equipment pressure based on defect data to form a closed-loop feedback system, effectively reducing the defect rate. Compared with traditional quality control methods, the system can significantly improve the adjustment speed and optimization ability of the production line through quantitative data and feedback mechanism, reduce the rework rate, further improve production efficiency and product yield, and achieve the beneficial effects of intelligent quality control and continuous optimization.

[0034] Example 5 A method for industrial product quality inspection based on machine vision, please refer to Figure 2 , specifically: including the following steps: Step 1: Use industrial cameras and optimized light source layout to capture high-resolution images of electronic components in real time using multi-angle shooting. The arrangement of light sources takes into account the small size and high-precision requirements of electronic components, and can highlight image pixels, clarity, product edges, defect frequencies, and subtle features of welding points; Step 2: Perform a series of optimization processes on the collected images, including filtering and noise reduction, edge enhancement and grayscale conversion, and use background difference technology to eliminate the interference of ambient light and improve the contrast of the image; Step 3: Extract key features of electronic components, including the shape of solder joints, arrangement of pins and component positions. According to the geometric characteristics of electronic components, extract shape, texture and color features to form key parameters for identifying defects. Step 4: Use the deep learning model algorithm to identify potential defects of electronic components, including poor solder joints, missing components, pin misalignment, and scratches, and calculate and obtain the quality assessment index Q; Step 5: Based on the calculation results of feature extraction and defect detection, make a comprehensive evaluation of the quality of each component, compare the quality evaluation index Q with the first preset threshold M and the second preset threshold N, evaluate the size deviation, defect type and quantity, and obtain the quality evaluation grade; Step 6: Feedback unqualified inspection information to the production line, remove unqualified components, and adjust production parameters to improve yield. By connecting with the production management system, a closed-loop feedback is formed to continuously optimize the production process.

[0035] In this embodiment, the system realizes efficient and accurate quality control of electronic components through six systematic steps, significantly improving the reliability of detection and the yield rate of the production line. First, through multi-angle image acquisition with industrial cameras and optimized light source layout, the subtle features in the image can be fully presented. In the following image preprocessing step, environmental interference is eliminated through denoising and edge enhancement to ensure that the image quality is more suitable for analysis and processing. The key feature extraction step lays a solid foundation for defect recognition in terms of shape, texture and color. The introduction of the deep learning model realizes automatic recognition in the defect detection process, quickly and accurately classifies defect types such as poor solder joints and missing components, and quantifies them into quality assessment index Q. In the comprehensive evaluation stage, the system compares Q with the preset threshold to determine the quality level of each component, so as to more efficiently determine the qualification of the product. Finally, by feeding back the detection information to the production line, unqualified components are eliminated and production parameters are optimized to form a closed-loop feedback process. Compared with traditional methods, the systematic detection process not only improves the detection accuracy and efficiency, but also realizes continuous production improvement through automatic feedback and real-time optimization, significantly improving product consistency and the level of intelligence in the production process.

[0036] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An industrial product quality inspection system based on machine vision, characterized in that: It includes image acquisition module, image preprocessing module, feature extraction module, defect detection module, quality assessment module and control feedback module; The image acquisition module is used to acquire high-resolution images of electronic components in real time by using industrial cameras and optimized light source layout, using multi-angle shooting. The arrangement of light sources takes into account the small size and high precision requirements of electronic components, and can highlight image pixels, clarity, product edges, defect frequencies and subtle features of welding points; The image preprocessing module is used to perform a series of optimization processes on the collected images, including filtering and noise reduction, edge enhancement and grayscale conversion, and adopts background difference technology to eliminate the interference of ambient light and improve the contrast of the image; The feature extraction module is used to extract key features of electronic components, including the shape of solder joints, the arrangement of pins and the position of components. According to the geometric characteristics of electronic components, shape, texture and color features are extracted to form key parameters for identifying defects. The defect detection module is used to identify potential defects of electronic components using a deep learning model algorithm, including poor solder joints, missing components, pin misalignment and scratches, and obtains after calculation: a quality assessment index Q; The quality assessment module is used to make a comprehensive evaluation of the quality of each component based on the calculation results of feature extraction and defect detection, and compare the quality assessment index Q with the first preset threshold M and the second preset threshold N to evaluate the size deviation, defect type and quantity, and obtain the quality assessment grade; The control feedback module is used to feed back unqualified detection information to the production line, remove unqualified components, and adjust production parameters to improve yield. By connecting with the production management system, a closed-loop feedback is formed to continuously optimize the production process.

2. The industrial product quality inspection system based on machine vision according to claim 1, characterized in that: The image acquisition module includes an image acquisition unit, a defect type unit and a feature parameter synchronization storage unit; The image acquisition unit is used to acquire clear, low-noise component images through an industrial camera and an optimized light source setting, and obtain: the total number of pixels N in the image, the gray value I(i) of the i-th pixel, and the gray value I(i+1) of the adjacent pixel; The defect type unit is used to extract defect frequencies and features based on production history and real-time image data, use a known sample library, mark the frequency of occurrence of different defects, record the distribution of various defects in the production process, extract the original data of key feature parameters, including solder joints, pin positions and arrangements, and obtain: the number of defect types M; The characteristic parameter synchronous storage unit is used to synchronously store the image data and characteristic parameters, generate a unique identification for each component, classify and archive the data, and store the image data, defect mark, and characteristic data separately.

3. The industrial product quality inspection system based on machine vision according to claim 1, characterized in that: The image preprocessing module includes an image preprocessing unit; The image preprocessing unit is used to perform denoising on the collected image, reduce interference noise in the image, ensure image quality, enhance the edges in the image, make the boundaries and welding points of components clearer for feature extraction, use background difference technology to eliminate the influence of ambient light, improve image contrast, and make component features more obvious.

4. The industrial product quality inspection system based on machine vision according to claim 1, characterized in that: The feature extraction module includes a geometric feature extraction unit, a texture feature extraction unit and a color feature extraction unit; The geometric feature extraction unit is used to extract the geometric features of components, such as the shape of soldering points and pin arrangement, and provide feature parameters; The texture feature extraction unit is used to analyze the texture features in the image, including the texture differences between the solder joint and the component surface, to provide support for defect detection; The color feature extraction unit is used to extract color distribution features and record component color information for use in determining surface contamination or other abnormal conditions.

5. The industrial product quality inspection system based on machine vision according to claim 1, characterized in that: The defect detection module includes a deep learning model unit and a quality assessment index calculation unit; The deep learning model unit is used to apply the trained deep learning model to automatically identify various defects in the image and classify the identified defects, including poor solder joints, missing components, pin misalignment, and surface scratches; The quality assessment index calculation unit is used to train a convolutional neural network (CNN) or a deep residual network (ResNet) model to automatically identify surface scratches, pits and cracks, and obtain the following after calculation: image clarity coefficient C, defect probability coefficient P defect And the quality assessment index Q of components.

6. The industrial product quality inspection system based on machine vision according to claim 5, characterized in that: The image clarity coefficient C is calculated by the following formula: ； Where C represents the image clarity coefficient, N represents the total number of pixels in the image, I(i) represents the grayscale value of the i-th pixel, and I(i+1) represents the grayscale value of the adjacent pixel; The defect probability coefficient P defect Calculated by the following formula: ； Where P defect represents the defect probability coefficient, M represents the number of defect types, and w j represents the weight of the j-th defect, F j Represents the occurrence frequency of the jth type of defect.

7. The industrial product quality inspection system based on machine vision according to claim 6, characterized in that: The quality assessment index Q of the components is calculated by the following formula: ； In the formula, Q represents the quality evaluation index of components, C represents the image clarity coefficient, P defect Denotes the defect probability coefficient, T k represents the quality evaluation value of the characteristic parameter k, K represents the number of key features for quality detection, Represents the weight coefficient.

8. The industrial product quality inspection system based on machine vision according to claim 1, characterized in that: The quality assessment module includes an assessment grade unit; The evaluation grade unit is used to compare the calculated quality evaluation index Q with the preset first threshold value M and second threshold value A, determine whether the component is qualified, evaluate the size deviation, defect type and quantity of the component, generate quality analysis data, and classify the quality of the component based on the comprehensive evaluation results to provide a specific basis for production quality control; If the quality assessment index Q ≥ the first threshold M, the first assessment level is obtained, indicating that the quality of the components meets the qualified standard, the solder joint shape, pin arrangement and color uniformity meet the requirements, and no further operation is required. The components in this batch are marked as qualified and recorded in the system database; If the second threshold value A≤quality assessment index Q<first threshold value M, the second assessment level is obtained. This interval is the warning level, indicating that the components have defects within 25%, which are manifested as minor poor solder joints or uneven color distribution, but do not affect the overall function. It is marked as a warning level, and the components of this batch are divided into independent areas and the maintenance procedure is triggered. The quality inspection system issues a warning and feedback is fed back to the production line for adjustment; If the quality assessment index Q is less than the second threshold value A, the third assessment level is obtained. Such components have serious defects and cannot meet functional requirements. Unqualified components are immediately eliminated, the specific types of defects are recorded, and the data is fed back to the production management system for defect analysis. The production equipment and process parameters are further adjusted through the control feedback module. Defect prevention strategies are formulated based on the identified defect types and characteristic parameters. For surface scratches and cracks, the quality inspection frequency is increased.

9. The industrial product quality inspection system based on machine vision according to claim 1, characterized in that: The control feedback module includes a non-conforming feedback unit and a production parameter adjustment unit; The unqualified feedback unit is used to feed back the detected unqualified components information to the production line, timely remove products that do not meet the quality standards, transmit unqualified information in real time, effectively prevent defective products from flowing into the downstream links, and ensure that the production line takes prompt measures when quality problems occur; The production parameter adjustment unit is used to adjust the process parameters of the production line, including welding temperature, equipment pressure or light source layout, according to the defect type, frequency and distribution data in the quality assessment results, to ensure that the production process meets the product quality requirements, form a closed-loop feedback system, and gradually reduce the defect rate by adjusting the production parameters.

10. A method for detecting industrial product quality based on machine vision, applied to an industrial product quality detection system based on machine vision according to any one of claims 1 to 9, characterized in that: The following steps are involved: Step 1: Use industrial cameras and optimized light source layout to capture high-resolution images of electronic components in real time using multi-angle shooting. The arrangement of light sources takes into account the small size and high-precision requirements of electronic components, and can highlight image pixels, clarity, product edges, defect frequencies, and subtle features of welding points; Step 2: Perform a series of optimization processes on the collected images, including filtering and noise reduction, edge enhancement and grayscale conversion, and use background difference technology to eliminate the interference of ambient light and improve the contrast of the image; Step 3: Extract key features of electronic components, including the shape of solder joints, arrangement of pins and component positions. According to the geometric characteristics of electronic components, extract shape, texture and color features to form key parameters for identifying defects. Step 4: Use the deep learning model algorithm to identify potential defects of electronic components, including poor solder joints, missing components, pin misalignment, and scratches, and calculate and obtain the quality assessment index Q; Step 5: Based on the calculation results of feature extraction and defect detection, make a comprehensive evaluation of the quality of each component, compare the quality evaluation index Q with the first preset threshold M and the second preset threshold N, evaluate the size deviation, defect type and quantity, and obtain the quality evaluation grade; Step 6: Feedback unqualified inspection information to the production line, remove unqualified components, and adjust production parameters to improve yield. By connecting with the production management system, a closed-loop feedback is formed to continuously optimize the production process.

Images