PCBA circuit board defect detection system based on AI

Abstract

The invention discloses an AI-based PCBA circuit board defect detection system. The AI-based PCBA circuit board defect detection system comprises the following steps: S1, an image acquisition module, wherein the image acquisition module comprises a camera shooting assembly and a light source assembly; wherein the camera shooting assembly comprises a high-resolution camera, and the high-resolution camera is used for capturing an image of a PCBA circuit board to be detected; s2, an image processing module, wherein the image processing module comprises image preprocessing, image segmentation and image recognition; according to the invention, automatic defect detection is carried out on the PCBA circuit board by using an artificial intelligence technology, the system combines image processing and deep learning technologies to realize rapid and accurate detection of surface defects of the circuit board, and meanwhile, through an automatic and intelligent detection means, the detection precision, efficiency and consistency are greatly improved; and the system not only can meet the current production requirements, but also can be continuously optimized and expanded through data driving, and has remarkable competitive advantages.

Description

Technical Field

[0001] The present invention relates to the technical field of PCBA circuit board defect detection, and in particular to an AI-based PCBA circuit board defect detection system. Background Art

[0002] A Chinese patent with announcement number CN213337398U discloses a PCBA circuit board defect detection device, including a carrier plate and a circuit board, a workpiece groove is provided on the surface of the carrier plate, a rubber gasket is provided on the bottom surface of the workpiece groove, a circuit board is provided inside the workpiece groove, a rubber limiting ring is provided at the opening of the workpiece groove, a through opening is provided on the bottom surface of the workpiece groove, a push plate is plugged into the inside of the through opening, a silicone pad is provided on the top surface of the push plate, and the push plate is fixed on the surface of a lifting frame, a guide rod is plugged into the surface of the lifting frame, and the top surface of the guide rod is fixed on the bottom surface of the carrier plate; the beneficial effect is: the PCBA circuit board defect detection device proposed by the utility model opens a workpiece groove on the surface of the carrier plate to independently store the circuit board, and after the circuit board is placed in the workpiece groove, the rubber limiting ring is on the upper part of the circuit board, at this time, the rubber limiting ring cooperates with the rubber gasket to clamp and limit the circuit board, so as to prevent the circuit board from shaking inside the workpiece groove and affecting the shooting accuracy.

[0003] The PCBA circuit board detection system in the prior art has a low degree of automation, which reduces the detection efficiency of the PCBA circuit board. Therefore, it is difficult to meet the current production needs and has no competitive advantage. Summary of the invention

[0004] The purpose of the present invention is to provide an AI-based PCBA circuit board defect detection system to solve the technical problems of low automation and low detection efficiency of existing PCBA circuit board detection systems.

[0005] In order to achieve the above object, the present invention adopts the following technical solution: An AI-based PCBA circuit board defect detection system includes the following steps: S1, image acquisition module: the image acquisition module includes a camera component and a light source component; The camera assembly includes a high-resolution camera, which is used to capture images of the PCBA circuit board to be inspected; S2, image processing module: The image processing module includes image preprocessing, image segmentation and image recognition; Among them, image preprocessing is used to perform denoising, enhancement, and smoothing operations on images collected by high-resolution cameras to improve image quality and facilitate subsequent processing; S3. Deep learning model: The deep learning model is used for defect detection. The model uses a convolutional neural network architecture to input the pre-processed image into a pre-trained deep learning model, and then outputs the defect detection results after comparison. Among them, deep learning models include data preparation, model construction, loss function and optimizer settings, training cycles, and model saving and evaluation; S4, defect classification and positioning module: The defect classification and positioning module is used to classify and locate the detected defects and output the specific location and type of the defects; S5. User interface: The user interface is used to display the inspection results, including defect type, location, severity information, generate inspection reports, and allow users to make manual adjustments or re-inspections.

[0006] As a further solution of the present invention, the light source assembly includes an illuminating lamp, which is used to provide uniform lighting for the PCBA circuit board, thereby ensuring the image quality of the PCBA circuit board.

[0007] As a further solution of the present invention, the image acquisition module also includes a motion control system, which includes a movable detection table for placing the PCBA circuit board to be detected, and the movable detection table is used for placing and moving the PCBA circuit board, and is used to scan the PCBA circuit board frame by frame under a high-resolution camera.

[0008] As a further solution of the present invention, image preprocessing includes graying, filtering and binarization of the image.

[0009] As a further solution of the present invention, graying is used to convert a color image into a graying image, filtering is used to remove noise in the image, and binarization is used to convert the image into an image containing only black and white colors.

[0010] As a further solution of the present invention, image segmentation is used to separate the target area from the background area in the image to facilitate subsequent feature extraction and recognition.

[0011] As a further solution of the present invention, image recognition uses AI algorithms to perform defect detection on preprocessed and segmented images, determine whether defects exist, and classify them.

[0012] As a further solution of the present invention, data preparation includes data collection, preprocessing and data enhancement to ensure the quality and diversity of the data, and conversion into a format acceptable to the model. Model construction is achieved by selecting a suitable network architecture, such as CNN, RNN, and defining the input layer, hidden layer and output layer of the model. The loss function and optimizer are achieved by selecting a loss function suitable for the task, such as cross entropy or mean square error, and selecting an optimization algorithm, such as Adam or SGD.

[0013] As a further solution of the present invention, the training cycle calculates the output through forward propagation, uses the loss function to calculate the error, back propagates to calculate the gradient, and the optimizer updates the parameters. This process is repeated to minimize the error. The model is saved and evaluated to save the model parameters after the training is completed, and the model performance is evaluated using a validation set or a test set.

[0014] As a further solution of the present invention, the defect classification and positioning module classifies the defects detected on the PCBA circuit board, including short circuits, open circuits, and solder joint defects, and accurately locates the defects to conveniently output the specific locations of the defects.

[0015] Compared with the prior art, the PCBA circuit board defect detection system based on AI in the present invention has the following beneficial effects: 1. Utilize artificial intelligence technology to automatically detect defects on PCBA circuit boards. The system will combine image processing and deep learning technology to achieve fast and accurate detection of circuit board surface defects. At the same time, through automated and intelligent detection methods, the detection accuracy, efficiency and consistency are greatly improved. The system can not only meet current production needs, but also be continuously optimized and expanded through data-driven, with significant competitive advantages; 2. Through deep learning model technology, the system can achieve high-precision detection of tiny defects, greatly improving the accuracy of PCBA detection; 3. Eliminate the subjective errors of manual testing and ensure the consistency and reliability of the test results; 4. The deep learning model can be continuously updated and optimized as needed to adapt to new types of defect detection requirements; 5. Use the automated detection system to reduce labor costs, improve production efficiency, and have higher economic benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. Obviously, the drawings described below are only examples of the embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 The figure is a flowchart of an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0019] In the description of the embodiments of the present invention, it should be understood that the terms "upper", "lower", "front", "back", "inside", "outside", etc. indicate directions or positional relationships based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the embodiments of the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore should not be understood as a limitation on the embodiments of the present invention.

[0020] In the description of the embodiments of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installation", "connection" and "connection" should be understood in a broad sense. For example, it can be a fixed connection, an integral connection, or a detachable connection; it can be the internal connection of two components; it can be directly connected or indirectly connected through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms in the embodiments of the present invention can be understood according to specific circumstances.

[0021] See also Figure 1 As shown, an AI-based PCBA circuit board defect detection system according to an embodiment of the present invention includes the following steps: S1, image acquisition module: the image acquisition module includes a camera component and a light source component; Among them, the camera component includes a high-resolution camera, which is used to capture the image of the PCBA circuit board to be inspected; the light source component includes a lighting lamp, which is used to provide uniform lighting for the PCBA circuit board, thereby ensuring the image quality of the PCBA circuit board; the image acquisition module also includes a motion control system, which includes a movable inspection table for placing the PCBA circuit board to be inspected, and the movable inspection table is used for placing and moving the PCBA circuit board, and is used to scan the PCBA circuit board frame by frame under the high-resolution camera.

[0022] S2, image processing module: The image processing module includes image preprocessing, image segmentation and image recognition; Among them, image preprocessing is used to denoise, enhance, and smooth images captured by high-resolution cameras to improve image quality and facilitate subsequent processing; image preprocessing includes grayscale, filtering, and binarization of images; grayscale is used to convert color images into grayscale images, filtering is used to remove noise in images, and binarization is used to convert images into images containing only black and white colors; image segmentation is used to separate the target area from the background area in the image to facilitate subsequent feature extraction and recognition; image recognition uses AI algorithms to perform defect detection on preprocessed and segmented images, determine whether there are defects, and classify them.

[0023] The above steps eliminate the subjective errors of manual inspection and ensure the consistency and reliability of each test result.

[0024] S3. Deep learning model: The deep learning model is used for defect detection. The model uses a convolutional neural network architecture to input the pre-processed image into a pre-trained deep learning model, and then outputs the defect detection results after comparison. Among them, deep learning models include data preparation, model construction, loss function and optimizer settings, training cycles, and model saving and evaluation; Data preparation includes data collection, preprocessing and data enhancement to ensure the quality and diversity of the data, as well as conversion into a format acceptable to the model. Model construction is done by selecting a suitable network architecture, such as CNN, RNN, and defining the input layer, hidden layer and output layer of the model. The loss function and optimizer select a loss function suitable for the task, such as cross entropy or mean square error, and select an optimization algorithm, such as Adam or SGD. The training cycle calculates the output through forward propagation, calculates the error using the loss function, calculates the gradient through back propagation, and updates the parameters through the optimizer. This process is repeated to minimize the error. Model saving and evaluation saves the model parameters after training, and uses the validation set or test set to evaluate the model performance.

[0025] The above steps not only use deep learning model technology to enable the system to achieve high-precision detection of tiny defects, greatly improving the accuracy of PCBA detection, but also use deep learning models to continuously update and optimize deep learning models as needed to adapt to new types of defect detection needs.

[0026] S4, defect classification and positioning module: The defect classification and positioning module is used to classify and locate the detected defects and output the specific location and type of the defects; Among them, the defect classification and positioning module classifies the defects detected on the PCBA circuit board, including short circuits, open circuits, and solder joint defects, and accurately locates the defects to conveniently output the specific location of the defects.

[0027] The above steps utilize an automated detection system to reduce labor costs, improve production efficiency, and have high economic benefits.

[0028] S5. User interface: The user interface is used to display the inspection results, including defect type, location, severity information, generate inspection reports, and allow users to make manual adjustments or re-inspections.

[0029] The above steps use artificial intelligence technology to perform automated defect detection on PCBA circuit boards. The system will combine image processing and deep learning technology to achieve fast and accurate detection of circuit board surface defects.

[0030] The working principle of the embodiment of the present invention is that through the deep learning model technology, the system can achieve high-precision detection of tiny defects, greatly improving the accuracy of PCBA detection; at the same time, it eliminates the subjective errors of manual detection, ensures the consistency and reliability of each detection result, and uses the deep learning model to continuously update and optimize the deep learning model as needed to adapt to new types of defect detection needs, and can use automated detection systems to reduce labor costs. The system will combine image processing and deep learning technology to achieve fast and accurate detection of circuit board surface defects. At the same time, through automated and intelligent detection methods, it greatly improves detection accuracy, efficiency and consistency.

[0031] The above shows and describes the basic principles of the present invention. The above are only preferred embodiments of the present invention and are not intended to limit the present invention. The above embodiments and descriptions in the specification are only intended to illustrate the principles of the present invention. Without departing from the scope of the present invention, any modifications, equivalent substitutions and improvements made within the spirit and scope of the present invention should be included in the protection scope of the present invention.

Claims

1. A PCBA circuit board defect detection system based on AI, characterized in that: The steps include: S1, image acquisition module: the image acquisition module includes a camera component and a light source component; Wherein, the camera assembly includes a high-resolution camera, and the high-resolution camera is used to capture the image of the PCBA circuit board to be inspected; S2, image processing module: the image processing module includes image preprocessing, image segmentation and image recognition; The image preprocessing is used to perform denoising, enhancement and smoothing operations on the images collected by the high-resolution camera, so as to improve the quality of the image and facilitate subsequent processing; S3. Deep learning model: The deep learning model is used for defect detection. The model uses a convolutional neural network architecture to input the pre-processed image into a pre-trained deep learning model, and the model outputs the defect detection result after comparison; The deep learning model includes data preparation, model construction, loss function and optimizer settings, training cycles, and model storage and evaluation; S4, defect classification and positioning module: the defect classification and positioning module is used to classify and locate the detected defects and output the specific location and type of the defects; S5. User interface: The user interface is used to display the inspection results, including defect type, location, and severity information, generate an inspection report, and allow the user to make manual adjustments or re-inspections.

2. According to the AI-based PCBA circuit board defect detection system of claim 1, it is characterized by: The light source assembly includes an illuminating lamp, which is used to provide uniform illumination for the PCBA circuit board to ensure the image quality of the PCBA circuit board.

3. The AI-based PCBA circuit board defect detection system according to claim 2, characterized in that: The image acquisition module also includes a motion control system, which includes a movable detection platform for placing the PCBA circuit board to be detected. The movable detection platform is used for placing and moving the PCBA circuit board and for scanning the PCBA circuit board frame by frame under a high-resolution camera.

4. The AI-based PCBA circuit board defect detection system according to claim 3, characterized in that: The image preprocessing includes graying, filtering and binarization of the image.

5. The AI-based PCBA circuit board defect detection system according to claim 4, characterized in that: The grayscale conversion is used to convert a color image into a grayscale image, the filtering is used to remove noise in the image, and the binarization is used to convert the image into an image containing only black and white colors.

6. The AI-based PCBA circuit board defect detection system according to claim 5, characterized in that: The image segmentation is used to separate the target area from the background area in the image, so as to facilitate the subsequent feature extraction and recognition.

7. The AI-based PCBA circuit board defect detection system according to claim 6, characterized in that: The image recognition uses AI algorithms to perform defect detection on preprocessed and segmented images, determine whether defects exist, and classify them.

8. The AI-based PCBA circuit board defect detection system according to claim 7, characterized in that: The data preparation includes data collection, preprocessing and data enhancement to ensure the quality and diversity of the data, as well as conversion into a format acceptable to the model. The model construction selects a suitable network architecture and defines the input layer, hidden layer and output layer of the model. The loss function and optimizer select a loss function suitable for the task.

9. The AI-based PCBA circuit board defect detection system according to claim 8, characterized in that: The training cycle calculates the output through forward propagation, calculates the error using the loss function, calculates the gradient through back propagation, and the optimizer updates the parameters, and repeats this process to minimize the error. The model saving and evaluation saves the model parameters after the training is completed, and evaluates the model performance using a validation set or a test set.

10. The AI-based PCBA circuit board defect detection system according to claim 9, characterized in that: The defect classification and positioning module classifies the defects detected on the PCBA circuit board, including short circuits, open circuits, and solder joint defects, and accurately locates the defects to conveniently output the specific locations of the defects.

Images