A method and system for detecting and analyzing defects in a PCB production line based on an identification model

Abstract

The present invention discloses a method and system for detecting and analyzing incomplete PCBs in a PCB production line based on an identification model, specifically relating to the technical field of PCB quality detection, and is used to solve the problems of low detection accuracy and high missed detection rate of incomplete PCB detection in the prior art; by scanning the entire surface of the PCB board to generate a thickness distribution map, using a threshold segmentation algorithm to identify areas with uneven thickness and mark key detection areas; by analyzing historical production data, identifying potential defects unrelated to process fluctuations; adjusting the polarization angle of the light source to analyze the reflectivity difference, and combining the microscopic structure of the material to identify hidden defect areas. The union of the potential defect area and the hidden defect area is marked as a suspected incomplete area, and its impact on the PCB performance is analyzed according to the quality standard, so as to improve the detection accuracy and comprehensiveness and achieve high-quality control of the PCB board.

Description

Technical Field

[0001] The present invention relates to the technical field of PCB quality inspection, and more specifically, the present invention relates to a method and system for detecting and analyzing PCB production line defects based on an identification model. Background Art

[0002] With the rapid development of electronic devices, the production quality of PCB boards has become an important link in ensuring product performance. At present, defect detection in PCB board production lines mostly uses traditional optical detection and simple thickness measurement methods. These methods have great limitations in dealing with subtle defects in mass production, especially in detecting hidden defects caused by production process fluctuations and material property changes, and it is difficult to ensure the comprehensiveness and accuracy of detection.

[0003] In the prior art, PCB defect detection mostly focuses on surface feature recognition and thickness difference detection. However, these methods can usually only detect obvious surface defects, and have poor detection effects on minor defects caused by uneven thickness and hidden defects caused by the optical reflection characteristics of the material structure, resulting in a high false detection rate in the production process, affecting the detection efficiency and finished product quality.

[0004] To solve the above problems, a technical solution is provided now. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a method and system for detecting and analyzing PCB production line defects based on an identification model to solve the problems raised in the above background art.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A method for detecting and analyzing PCB production line defects based on an identification model includes the following steps:

[0008] Scan the entire surface of the PCB board to be detected, obtain the thickness distribution data of the board, and generate a corresponding thickness distribution map;

[0009] Use a threshold segmentation algorithm to identify the uneven thickness area, judge whether the thickness change exceeds a preset threshold, and if so, mark the corresponding area as the key detection area;

[0010] Analyze the deformation trend of the key detection area through historical production data, and identify potential defects in the key detection area that are not related to process fluctuations;

[0011] Analyze the reflectivity difference of the key detection area by adjusting the light source polarization angle, and combine the material microstructure to evaluate the change of the reflection characteristics to identify the hidden defects in the key detection area;

[0012] Based on potential defects unrelated to process fluctuations and hidden defects within the key detection area, preliminarily detect the suspected defective areas in the key detection area;

[0013] Further analyze the suspected defective areas according to the preset quality standards to judge the degree of their impact on the PCB performance.

[0014] In a preferred embodiment, scan the entire surface of the PCB board to be detected, obtain the thickness distribution data of the board, and generate the corresponding thickness distribution map. Specifically:

[0015] Start the scanning device to ensure that it can cover the entire surface of the PCB board to be detected, and set the scanning resolution and sampling frequency;

[0016] Use the scanning device to perform a full-surface scan on the PCB board to obtain the original thickness data at each position;

[0017] Denoise and normalize the collected original thickness data;

[0018] Based on the processed thickness data, generate the corresponding thickness distribution map to visually display the thickness change trend of each area.

[0019] In a preferred embodiment, use the threshold segmentation algorithm to identify the areas with uneven thickness, and judge whether the thickness change exceeds the preset threshold. If so, mark the corresponding area as the key detection area. Specifically:

[0020] Perform data analysis on the generated thickness distribution map, extract the thickness values of each area from the map, and convert them into the form of a digital matrix;

[0021] Select the threshold segmentation algorithm suitable for thickness detection and set the thickness detection threshold suitable for the PCB board;

[0022] Use the threshold segmentation algorithm to process the thickness data to identify the areas with obvious thickness changes; analyze the areas where the values in the thickness distribution are significantly higher or lower than the normal range through the threshold segmentation algorithm to determine the areas with uneven thickness;

[0023] For the identified areas with uneven thickness, judge whether their thickness changes exceed their corresponding preset thresholds; if the thickness change exceeds its corresponding preset threshold, mark this area as the key detection area.

[0024] In a preferred embodiment, analyze the deformation trend of the key detection area through historical production data to identify potential defects unrelated to process fluctuations within the key detection area. Specifically:

[0025] Extract the historical production thickness data of the key detection area;

[0026] Calculate the dynamic deformation index of the key detection area based on the historical production thickness data, and quantify the deformation amplitude and trend based on the dynamic deformation index;

[0027] Establish a multi-dimensional recurrent neural network model, input the dynamic deformation index, and perform time series modeling on the deformation trend;

[0028] Use the multi-dimensional recurrent neural network model to predict the deformation trend of the key detection area;

[0029] Identify abnormal deformations unrelated to process fluctuations based on the predicted deformation trend, and identify potential defect areas of the deformation.

[0030] In a preferred embodiment, calculate the dynamic deformation index of the key detection area based on the historical production thickness data, and quantify the deformation amplitude and trend based on the dynamic deformation index, specifically:

[0031] The dynamic deformation index is defined as the thickness change rate in time and space, and the calculation formula is as follows:

[0032] ; where represents the dynamic deformation index of the th batch, is the th thickness measurement value of the th batch, represents the average thickness of the th batch, represents the number of thickness measurement positions in each production batch, is the batch sequence in time, is the measurement position within each batch;

[0033] Calculate the increment: ; where is the increment.

[0034] In a preferred embodiment, analyze the reflectance difference of the key detection area by adjusting the polarization angle of the light source, combine the material microstructure to evaluate the change of the reflection characteristics, and identify the hidden defects in the key detection area, specifically:

[0035] Adjust the polarization angle of the light source according to the material characteristics of the key detection area;

[0036] Collect multi-angle reflection data of the key detection area at different polarization angles;

[0037] Analyze the multi-angle reflection data in combination with the material microstructure characteristics to identify abnormal changes in the reflection characteristics;

[0038] Identify the concealed defect areas within the key detection areas based on abnormal changes in reflection characteristics.

[0039] In a preferred embodiment, based on potential defects unrelated to process fluctuations and concealed defects within the key detection areas, preliminarily detect the suspected defective areas in the key detection areas, specifically:

[0040] Within the key detection areas, mark the area corresponding to the union of the deformed potential defect areas and the concealed defect areas as the suspected defective areas.

[0041] In a preferred embodiment, further analyze the suspected defective areas according to the preset quality standards to determine the degree of their impact on the PCB performance, specifically:

[0042] Conduct a preliminary screening of the marked suspected defective areas to determine the detection parameters that meet the preset quality standards;

[0043] For the screened suspected defective areas, extract performance parameters, where the performance parameters include physical characteristics and structural characteristics;

[0044] According to the extracted performance parameters and in combination with the preset quality standards, conduct a quantitative analysis of the impact degree of the suspected defective areas;

[0045] Compare the evaluation results with the quality standards to determine whether the impact of the suspected defective areas exceeds the allowable range and make a qualification determination;

[0046] Mark the unqualified suspected defective areas and record the location information to generate a detection report.

[0047] On the other hand, the present invention provides a PCB production line defective detection and analysis system based on an identification model, including a board surface scanning module, a thickness distribution identification module, a deformation trend analysis module, a polarization reflection analysis module, a suspected defect marking module, and a quality standard evaluation module;

[0048] Board surface scanning module: Scan the entire surface of the PCB board to be detected, obtain the thickness distribution data of the board, and generate the corresponding thickness distribution map;

[0049] Thickness distribution identification module: Use the threshold segmentation algorithm to identify the areas with uneven thickness, determine whether the thickness change exceeds the preset threshold, and if so, mark the corresponding areas as the key detection areas;

[0050] Deformation trend analysis module: Analyze the deformation trend of the key detection areas through historical production data to identify potential defects unrelated to process fluctuations within the key detection areas;

[0051] Polarization reflection analysis module: By adjusting the polarization angle of the light source, analyze the reflectivity difference in the key detection area, combine with the microscopic structure of the material to evaluate the change of reflection characteristics, and identify the hidden defects in the key detection area;

[0052] Suspected incomplete mark module: Based on the potential defects unrelated to process fluctuations and the hidden defects in the key detection area, preliminarily detect the suspected incomplete area in the key detection area;

[0053] Quality standard evaluation module: Further analyze the suspected incomplete area according to the preset quality standard to judge its influence degree on the PCB performance.

[0054] Technical effects and advantages of a method and system for detecting and analyzing incomplete parts on a PCB production line based on an identification model according to the present invention:

[0055] 1. The present invention proposes a method for detecting and analyzing incomplete parts on a PCB production line based on an identification model, which can effectively improve the accuracy and comprehensiveness of PCB board detection. In this method, by scanning the thickness data of the entire surface of the board, a thickness distribution map is generated, and the threshold segmentation algorithm is used to identify the areas with uneven thickness, and the key detection areas are accurately marked. This way ensures the effective identification of key areas, making the detection range not only limited to surface features, but also covering potential incomplete areas caused by thickness changes. In addition, by analyzing the production history data, the present invention identifies potential defects unrelated to process fluctuations in the key detection area, further reducing the false detection rate caused by process fluctuations and providing data support for the accurate calibration of incomplete areas.

[0056] 2. The present invention also combines the light source polarization angle adjustment technology to identify the hidden defects in the key detection area through multi-angle reflection analysis. By analyzing the reflection characteristics in the key detection area and combining with the microscopic structure characteristics of the material, the hidden defect areas that are difficult to capture in conventional detection are identified. Finally, this method combines the potential defect areas unrelated to process fluctuations with the hidden defect areas, preliminarily marks the suspected incomplete areas, and further evaluates their influence degree according to the preset quality standard. This detection method significantly improves the sensitivity and accuracy of the detection system, reduces the possibility of missed detection and false detection, enhances the overall quality control ability of the PCB production line, and provides a reliable guarantee for high-quality PCB production. Description of the Drawings

[0057] Figure 1 It is a schematic diagram of a method for detecting and analyzing incomplete parts on a PCB production line based on an identification model according to the present invention;

[0058] Figure 2 It is a schematic diagram of the structure of a system for detecting and analyzing incomplete parts on a PCB production line based on an identification model according to the present invention. Detailed implementation manners

[0059] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0060] Embodiment 1

[0061] Figure 1 A method for detecting and analyzing incomplete parts on a PCB production line based on an identification model of the present invention is given, which includes the following steps:

[0062] Scan the entire surface of the PCB board to be detected, obtain the thickness distribution data of the board, and generate a corresponding thickness distribution map.

[0063] Use the threshold segmentation algorithm to identify the areas with uneven thickness, and judge whether the thickness change exceeds the preset threshold. If so, mark the corresponding area as the key detection area.

[0064] Analyze the deformation trend of the key detection area through historical production data, and identify potential defects in the key detection area that are not related to process fluctuations.

[0065] Analyze the reflectivity difference of the key detection area by adjusting the light source polarization angle, and evaluate the change of the reflection characteristics in combination with the material microstructure to identify the hidden defects in the key detection area.

[0066] Based on the potential defects in the key detection area that are not related to process fluctuations and the hidden defects in the key detection area, preliminarily detect the suspected incomplete areas in the key detection area.

[0067] Further analyze the suspected incomplete areas according to the preset quality standards, and judge the degree of influence on the PCB performance.

[0068] Scan the entire surface of the PCB board to be detected, obtain the thickness distribution data of the board, and generate a corresponding thickness distribution map. Specifically:

[0069] Start the scanning device to ensure that it can cover the entire surface of the PCB board to be detected, and set the scanning resolution and sampling frequency:

[0070] First, start the scanning device (such as an optical scanner or a laser rangefinder) and set the working parameters of the scanning device, including the scanning resolution, sampling frequency, and scanning angle. The resolution should be set according to the detail requirements of the PCB board material. Usually, high-precision scanning at the micron level can be selected to ensure the accuracy of the thickness data. The sampling frequency needs to be reasonably configured according to the size and requirements of the PCB board material to be measured to ensure full surface coverage and a high enough data density. The device should be able to ensure that the scan covers the entire area of the PCB board to be detected through an automatic adjustment function or manual calibration without missing any corner.

[0071] The design of the scanning device should ensure that it can automatically adjust the scanning range during the scanning process to ensure that the entire PCB surface is within the coverage area of the scanner. For larger PCB boards, the scanning device can adopt a method of block scanning to ensure the integrity of the scanning range and the continuity of the data. During the scanning process, the device needs to record the coordinate information of each scanning area and adjust it in real time to cover the entire board surface.

[0072] Use the scanning device to perform a full-surface scan of the PCB board to obtain the original thickness data at each position:

[0073] The device gradually scans the surface of the PCB board according to the previously set scanning range and parameters. Each time it scans, the device will capture the height data of the PCB board surface through a high-precision sensor and calculate the thickness value at each position. The thickness data consists of multiple scanning points, and each scanning point represents the thickness at a certain position on the PCB surface. All the collected thickness data will be combined into a complete thickness data set.

[0074] According to different types of PCB board materials and their surface conditions, the device may need to adjust the scanning accuracy in a timely manner during the scanning process. For example, for thinner or smoother PCB board materials, a higher-resolution scanning mode can be used; for thicker or uneven-surface PCB board materials, the scanning accuracy can be appropriately reduced to improve the stability of data collection.

[0075] Perform denoising and normalization processing on the collected original thickness data:

[0076] Preprocess the original thickness data, including removing the noise that may be introduced during the scanning process. For example, due to the device may be affected by environmental factors (such as temperature, light, etc.), resulting in certain fluctuations or abnormal points in the collected thickness data. At this time, algorithms such as median filtering and Kalman filtering can be used to smooth the data, thereby removing the influence of noise.

[0077] Normalize the denoised thickness data to map the data values to a unified range. For example, normalize the thickness values to the range between 0 and 1. The normalization operation helps to eliminate the thickness data deviation caused by equipment precision differences or environmental changes, making the subsequent analysis more consistent.

[0078] Based on the processed thickness data, generate the corresponding thickness distribution map to visually display the thickness change trend of each region:

[0079] According to the preprocessed thickness data, use visualization tools or algorithms (such as heat map drawing, contour map, etc.) to generate the thickness distribution map. This map shows the thickness differences of each region and can help inspectors visually observe the thickness changes between the surface regions of the PCB. For example, thicker regions can be represented in red, and thinner regions in blue.

[0080] The thickness distribution map not only visually displays the thickness value of each region but also can reflect the thickness change trend through color changes. These trends are crucial for subsequent defect analysis and can help identify potential problem areas that may arise due to uneven thickness, such as problems like decreased mechanical properties caused by local insufficient thickness.

[0081] Adopt a threshold segmentation algorithm to identify regions with uneven thickness, and judge whether the thickness change exceeds a preset threshold. If so, mark the corresponding region as a key detection region, specifically:

[0082] Perform data parsing on the generated thickness distribution map, extract the thickness values of each region from the map, and convert them into the form of a digital matrix to provide standardized thickness data input for subsequent threshold segmentation processing.

[0083] Select a threshold segmentation algorithm suitable for thickness detection (such as histogram-based threshold segmentation or region growing algorithm), and set the thickness detection threshold suitable for the PCB board material.

[0084] Among them, the thickness detection threshold is determined based on experimental or historical data to ensure the scientificity and applicability of the threshold.

[0085] Use the threshold segmentation algorithm to process the thickness data and identify regions with obvious thickness changes. Automatically analyze the regions in the thickness distribution where the values are significantly higher or lower than the normal range through the threshold segmentation algorithm, so as to determine the regions with uneven thickness.

[0086] For the identified regions with uneven thickness, judge whether their thickness changes exceed their corresponding preset thresholds. If the thickness change exceeds its corresponding preset threshold, mark this region as a key detection region to provide a clear area of concern for subsequent detailed inspection.

[0087] Among them, the preset threshold corresponding to the thickness change is determined according to the production standards and historical data of the PCB board material, comprehensively considering the normal process fluctuation range and the allowable error of the board material thickness, and the value most suitable for the detection accuracy is obtained through experimental calibration.

[0088] By analyzing the historical production data, the deformation trend of the key detection area is detected, and potential defects unrelated to process fluctuations in the key detection area are identified. Specifically:

[0089] Extract the historical production thickness data of the key detection area:

[0090] Extract the historical thickness data related to the key detection area from the production database to ensure that the analyzed data can accurately reflect the long-term trend of deformation. The data should include the thickness measurement values of the key detection area in each historical production batch to ensure the integrity and temporal continuity of the data. In addition, to ensure the accuracy and consistency of the data, data cleaning steps are adopted to remove outliers or data missing phenomena.

[0091] Calculate the dynamic deformation index of the key detection area based on the historical production thickness data, and quantify the deformation amplitude and trend based on the dynamic deformation index:

[0092] Let each thickness data point be , where is the batch sequence in time, is the measurement position within each batch. The dynamic deformation index is defined as the thickness change rate in time and space, and the calculation formula is as follows:

[0093] ; where, represents the dynamic deformation index of the th batch, is the rd thickness measurement value of the th batch, represents the average thickness of the th batch, represents the number of thickness measurement positions in each production batch.

[0094] The value of the dynamic deformation index obtained through this calculation can reflect the deformation amplitude and its trend of the key detection area in each batch.

[0095] To further accurately reflect the amplitude of the dynamic deformation, calculate the increment: ; where, is the increment, which represents the increment of the dynamic deformation index between the current batch and the previous batch, and reflects the deformation change rate of the key detection area.

[0096] If If there is a significant increase or decrease, it indicates that there may be a large - scale deformation change at this time point, and further attention is required.

[0097] Build a multi - dimensional recurrent neural network model, input the dynamic deformation index, and perform time - series modeling on the deformation trend:

[0098] Select the Long Short - Term Memory (LSTM) network as the basic unit of the multi - dimensional recurrent neural network to ensure its long - term memory ability. The input layer is and , and the number of nodes in each layer is determined according to the data complexity. The network structure includes an input layer, a hidden layer, and an output layer, and the hidden layer is composed of multiple LSTM units to enhance the ability to capture long - term data trends.

[0099] Input the historical and into the multi - dimensional recurrent neural network to establish a time - series model. The input data for each time step includes and , so the input data form of the network is , which is used to predict the dynamic deformation trend of future time steps.

[0100] Use the backpropagation algorithm to train the multi - dimensional recurrent neural network to minimize the loss function. The loss function uses the Mean Squared Error (MSE), and the calculation formula is as follows:

[0101] ; where, represents the Mean Squared Error, which is used to quantify the average error between the predicted value and the actual value; represents the total number of time batches, that is, the number of batches included in the entire time series; is the predicted dynamic deformation index value of the th batch, which is calculated by the multi - dimensional recurrent neural network model and is used to estimate the deformation state of the key detection area at this time step; is the actual dynamic deformation index value of the th batch, that is, the true deformation index value obtained from historical data, representing the actual deformation situation of the key detection area at this time step.

[0102] Use the multi - dimensional recurrent neural network model to predict the deformation trend of the key detection area:

[0103] After completing the training of the multi - dimensional recurrent neural network model, input the current and As input, predict the future deformation trend to obtain the predicted dynamic deformation index. The sequence of the predicted dynamic deformation index can characterize the future deformation changes in the key detection area and help predict possible abnormal deformations.

[0104] The predicted dynamic deformation index not only includes the thickness change amplitude of a specific future batch, but also covers the acceleration or deceleration trend of deformation. Through this model, possible future deformation patterns can be identified, providing a basis for subsequent defect detection.

[0105] Identify abnormal deformations unrelated to process fluctuations based on the predicted deformation trend, and identify potential defect areas of deformation:

[0106] Analyze the change trend and increment pattern of the future deformation trend sequence predicted by the multi-dimensional recurrent neural network model to identify abnormal deformations unrelated to process fluctuations.

[0107] If the predicted dynamic deformation index or its increment at a certain time point in the key detection area exceeds the normal process fluctuation range, then this area is identified as a potential defect area of deformation.

[0108] Analyze the reflectivity difference in the key detection area by adjusting the light source polarization angle, and combine the material microstructure evaluation to identify the change of reflection characteristics, and identify the hidden defects in the key detection area, specifically:

[0109] Adjust the polarization angle of the light source according to the material characteristics of the key detection area to ensure the reflection capture effect within the best angle range:

[0110] Analyze the material characteristics of the key detection area to determine its surface microstructure and reflection characteristics. The surface structures of different materials (such as copper, nickel, gold, etc.) will produce different polarization responses to the reflected light. Therefore, adjusting the light source polarization angle to the best range can ensure the accurate capture of the reflected light. In specific implementation, a light source polarization adjustment device (such as a polarization filter or a variable angle polarizer) is used to adjust the incident angle of the light source.

[0111] Polarization angle setting: According to the material characteristics, initially set the polarization angle range. Assume the best incident angle range is to , and gradually adjust the polarization angle within this range, and measure the reflection effect at each angle one by one.

[0112] Optimal angle determination: Gradually narrow the angle range according to the reflection capture effect, and finally determine an optimal polarization angle , so that the intensity and accuracy of the reflection signal are the best at this angle. The setting of the angle takes into account the microscopic characteristics and multi-layer structure of the material to ensure the acquisition of effective reflectivity data.

[0113] Collect multi - angle reflection data of the key detection area at different polarization angles:

[0114] After determining the optimal polarization angle range, collect multi - angle reflection data of the key detection area by scanning angle by angle. At each angle, record the intensity of the reflected light at that angle to generate a sequence of reflection data at different polarization angles for comparing the changes in reflection characteristics in subsequent analysis.

[0115] Angle - by - angle data collection: Set the polarization angle to multiple different angles, such as the first angle, the second angle, etc. At each angle, collect the intensity of the reflected light from the key detection area and record the corresponding reflectivity data respectively.

[0116] Data recording format: Organize the collected reflected light intensity data into a matrix form, where one part represents different polarization angles and the other part represents the reflected light intensity at different sampling points, ensuring that the reflection data at each angle can be used for subsequent analysis.

[0117] Analyze the multi - angle reflection data in combination with the micro - structural characteristics of the material to identify abnormal changes in the reflection characteristics:

[0118] After the multi - angle reflection data collection is completed, analyze the data in combination with the micro - structural characteristics of the material to identify abnormalities in the reflection characteristics. During the analysis process, the surface roughness of the material, the layered structure, and the differences in the reflection responses of different micro - particles at different polarization angles need to be considered.

[0119] Calculation of reflectivity difference: Calculate the difference in reflectivity at different angles to identify the changes in the reflection characteristics. Specifically, compare the reflectivity data at different angles to determine whether the reflection difference between two angles is significant. If the reflection data shows large changes between certain angles, it may indicate abnormalities in the surface or subsurface structure of the material.

[0120] Set a reflectivity difference threshold. If the reflectivity difference between two angles exceeds the reflectivity difference threshold, it is determined that there are abnormal reflection characteristics. The setting of the reflectivity difference threshold is based on experimental data or historical data to ensure the reliability of the detection results.

[0121] Based on the abnormal changes in the reflection characteristics, identify the hidden defect areas in the key detection area:

[0122] On the basis of identifying the abnormal reflectivity, further judge the hidden defects in the key detection area according to the abnormal changes in the reflection characteristics. Hidden defects usually manifest as abnormal reflection characteristics at certain angles or inconsistent reflection changes in certain specific material micro - structures.

[0123] Mark the area with abnormal reflection characteristics as the hidden defect area, and record the polarization angle and reflection intensity change characteristics of this area to generate a defect distribution map within the key detection area, providing data reference for subsequent steps.

[0124] Based on the potential defects unrelated to process fluctuations and the hidden defects within the key detection area, preliminarily detect the suspected defective areas within the key detection area, specifically:

[0125] Within the key detection area, mark the area corresponding to the union of the deformation potential defect area and the hidden defect area as the suspected defective area, and generate the coordinate information and area range of this area for subsequent analysis.

[0126] Specifically, the deformation potential defect area and the hidden defect area respectively mark the defects caused by different factors. The former is the unstable area identified through dynamic deformation analysis, while the latter is the abnormal area on the surface or subsurface identified based on reflection characteristics. By performing the union operation on these two defect areas, all possible defective areas can be more comprehensively covered, ensuring the integrity of the detection.

[0127] Further analyze the suspected defective areas according to the preset quality standards to judge their influence on the PCB performance, specifically:

[0128] Conduct a preliminary screening on the marked suspected defective areas to determine the detection parameters that meet the preset quality standards for detailed analysis:

[0129] The screening is based on the preset quality standards, which usually include the area, depth, position, and defect type of the area. The screening process identifies the basic parameters (such as area size, depth range, etc.) of each suspected defective area and retains the areas that meet the detection standards for subsequent detailed analysis. This can reduce unnecessary analysis and focus on the suspected defective areas that actually affect the PCB performance.

[0130] Basis for screening: According to the requirements for the area, depth, and position of the area in the preset quality standards, judge which suspected defective areas may have a greater impact on the performance and thus require further analysis.

[0131] Parameter determination: Determine the detection parameters after screening, such as measuring the area size and average depth of the defective area, etc., to ensure meeting the requirements of the quality standards.

[0132] Extract performance parameters for the suspected defective areas after screening:

[0133] The performance parameters include physical characteristics and structural characteristics.

[0134] Physical feature collection: Obtain detailed information of the suspected defective area through imaging equipment, such as the outline and edge shape of the defect, to visually display the physical features of the defect.

[0135] Structural feature extraction: Use 3D scanning equipment or structural analysis equipment to obtain structural feature parameters such as depth, width, and density of the defective area, providing detailed feature data for subsequent analysis.

[0136] Record the collected physical features and structural feature parameters in the database, and normalize the parameter values of each suspected defective area for subsequent data analysis.

[0137] According to the extracted performance parameters and combined with the preset quality standards, conduct a quantitative analysis of the impact degree of the suspected defective area:

[0138] The preset quality standards may include minimum requirements for structural integrity, thickness uniformity, edge strength, etc. By comparing the performance parameters with the quality standards, quantify the impact degree of the defective area. This analysis can use calculation models or simulation techniques to evaluate the performance of each suspected defective area under extreme working conditions one by one to ensure the accuracy and reliability of the analysis results.

[0139] Quality standard parameter comparison: Compare the extracted performance parameters with the quality standards. For example, compare whether the depth of the defective area exceeds the standard value to judge its impact degree on structural integrity.

[0140] Establish a quantitative analysis model: Establish a quantitative analysis model, taking physical and structural feature parameters as input variables, and calculate the impact index of each suspected defective area to ensure the scientificity and objectivity of the quantitative analysis.

[0141] Calculate the impact degree: Use the calculation model to calculate the impact index of each suspected defective area, and use a numerical value to represent the potential impact size on the overall performance of the PCB.

[0142] Compare the evaluation results with the quality standards to judge whether the impact of the suspected defective area exceeds the allowable range and make a pass / fail determination:

[0143] If the impact index of a certain suspected defective area exceeds the preset allowable range, then this area is regarded as a defect that has a negative impact on performance, and further judge that the PCB board is unqualified.

[0144] Pass / fail determination criteria: Set the maximum value of the impact index according to the allowable range of the quality standards; if the impact index of a certain suspected defective area exceeds this value, then this area is determined to be unqualified.

[0145] Conformity judgment: Compare the influence index of each suspected defective area one by one to determine whether it is within the allowable range. If the influence indices of all areas are within the standard range, the PCB board is judged to be qualified; if any area exceeds the range, it is judged to be unqualified.

[0146] Mark the unqualified suspected defective areas and record the location information to generate a final inspection report for subsequent processing.

[0147] Defective area marking: Clearly mark the suspected defective areas judged to be unqualified so as to highlight them in the final inspection report.

[0148] Location information recording: Record the location information of the unqualified areas, including detailed parameters such as the specific location, shape, and size of the defects, to provide accurate data for subsequent processing.

[0149] Report generation: Summarize the information of all unqualified areas to generate a final inspection report, which includes the detailed data of each unqualified area and the conformity judgment result, so as to provide it to the relevant departments for processing and feedback.

[0150] Embodiment 2

[0151] The difference between Embodiment 2 and Embodiment 1 of the present invention is that this embodiment introduces a defective detection and analysis system for a PCB production line based on an identification model.

[0152] Figure 2 The structural schematic diagram of a defective detection and analysis system for a PCB production line based on an identification model of the present invention is given. A defective detection and analysis system for a PCB production line based on an identification model includes a board surface scanning module, a thickness distribution recognition module, a deformation trend analysis module, a polarization reflection analysis module, a suspected defect marking module, and a quality standard evaluation module.

[0153] Board surface scanning module: Scan the entire surface of the PCB board to be detected, obtain the thickness distribution data of the board, and generate a corresponding thickness distribution map.

[0154] Thickness distribution recognition module: Use the threshold segmentation algorithm to identify the areas with uneven thickness, and judge whether the thickness change exceeds the preset threshold. If so, mark the corresponding area as the key detection area.

[0155] Deformation trend analysis module: Analyze the deformation trend of the key detection areas through historical production data, and identify potential defects unrelated to process fluctuations within the key detection areas.

[0156] Polarization reflection analysis module: Analyze the reflectivity difference of the key detection areas by adjusting the polarization angle of the light source, evaluate the change of the reflection characteristics in combination with the microscopic structure of the material, and identify the hidden defects within the key detection areas.

[0157] Suspected incomplete mark module: Based on potential defects unrelated to process fluctuations and hidden defects within the key detection area, initially detect the suspected incomplete area of the key detection area.

[0158] Quality standard evaluation module: Further analyze the suspected incomplete area according to the preset quality standards to determine its impact on the PCB performance.

[0159] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to obtain a formula closest to the actual situation. The preset parameters and threshold selection in the formulas are set by those skilled in the art according to the actual situation.

[0160] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server or data center that contains one or more collections of available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0161] Those of ordinary skill in the art can realize that the modules and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0162] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and modules described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0163] In several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division, and there can be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of the devices or modules can be in electrical, mechanical, or other forms.

[0164] The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules. They can be located in one place or distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0165] In addition, in each embodiment of the present application, the functional modules can be integrated in a processing module, or each module can exist physically alone, or two or more modules can be integrated in one module.

[0166] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0167] As described above, it is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

[0168] Finally, the above are only the preferred embodiments of the present invention and are not used to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A PCB production line defect detection and analysis method based on a recognition model, characterized in that: The steps include: Scan the entire surface of the PCB board to be inspected, obtain the thickness distribution data of the board, and generate the corresponding thickness distribution map; The threshold segmentation algorithm is used to identify the area with uneven thickness and determine whether the thickness change exceeds the preset threshold. If so, the corresponding area is marked as the key detection area; Analyze the deformation trend of key inspection areas through historical production data to identify potential defects in key inspection areas that are not related to process fluctuations; By adjusting the polarization angle of the light source to analyze the reflectivity difference in the key inspection area, combined with the material microstructure to evaluate the change in reflective characteristics, hidden defects in the key inspection area can be identified, specifically: Adjust the polarization angle of the light source according to the material characteristics of the key detection area; Collect multi-angle reflection data of key detection areas at different polarization angles; Analyze multi-angle reflection data in combination with material microstructural properties to identify abnormal changes in reflection characteristics; Identify hidden defect areas within key inspection areas based on abnormal changes in reflection characteristics; Based on the potential defects unrelated to process fluctuations in the key inspection area and the hidden defects in the key inspection area, the suspected defective areas in the key inspection area are preliminarily detected, specifically: In the key inspection area, the area corresponding to the union of the deformation potential defect area and the hidden defect area is marked as a suspected defect area; Further analysis is performed on suspected defective areas based on preset quality standards to determine the extent of their impact on PCB performance.

2. The PCB production line defect detection and analysis method based on the recognition model according to claim 1 is characterized in that: Scan the entire surface of the PCB board to be tested, obtain the thickness distribution data of the board, and generate the corresponding thickness distribution map, specifically: Start the scanning device to ensure that it can cover the entire surface of the PCB to be tested, and set the scanning resolution and sampling frequency; Use scanning equipment to scan the entire surface of the PCB board to obtain the original thickness data of each position; De-noising and normalizing the collected raw thickness data; Based on the processed thickness data, the corresponding thickness distribution map is generated to intuitively display the thickness change trend of each area.

3. The PCB production line defect detection and analysis method based on recognition model according to claim 2 is characterized in that: The threshold segmentation algorithm is used to identify the area with uneven thickness and determine whether the thickness change exceeds the preset threshold. If so, the corresponding area is marked as the key detection area. Specifically: Perform data analysis on the generated thickness distribution map, extract the thickness value of each area from the map, and convert it into a digital matrix; Select a threshold segmentation algorithm suitable for thickness detection, and set a thickness detection threshold suitable for the PCB board; The thickness data is processed using a threshold segmentation algorithm to identify areas with significant thickness changes; the area where the value in the thickness distribution is significantly higher or lower than the normal range is analyzed using the threshold segmentation algorithm to determine the area with uneven thickness; For the identified uneven thickness area, determine whether its thickness change exceeds its corresponding preset threshold; if the thickness change exceeds its corresponding preset threshold, mark the area as a key detection area.

4. The PCB production line defect detection and analysis method based on recognition model according to claim 3 is characterized in that: Analyze the deformation trend of key inspection areas through historical production data, and identify potential defects in key inspection areas that are not related to process fluctuations, specifically: Extract historical production thickness data of key inspection areas; Calculate the dynamic deformation index of the key inspection area based on historical production thickness data, and quantify the deformation amplitude and trend based on the dynamic deformation index; A multi-dimensional recursive neural network model was established, and the dynamic deformation index was input to perform time series modeling of the deformation trend; A multi-dimensional recursive neural network model is used to predict the deformation trend of key inspection areas; Abnormal deformation that is not related to process fluctuations can be identified based on the predicted deformation trend, and potential defect areas of deformation can be identified.

5. The PCB production line defect detection and analysis method based on recognition model according to claim 4 is characterized in that: The dynamic deformation index of the key inspection area is calculated based on the historical production thickness data, and the deformation amplitude and trend are quantified based on the dynamic deformation index, specifically: The dynamic deformation index is defined as the thickness change rate in time and space, and is calculated as follows: ;in, Indicates The dynamic deformation index of the batch, For the Batch No. Thickness measurements, Indicates The average thickness of the batch, represents the number of locations where thickness measurements are made in each production batch, is the batch sequence in time, is the measurement position within each batch; Calculate the increment: ;in, It is an increment.

6. The PCB production line defect detection and analysis method based on recognition model according to claim 5 is characterized in that: Further analysis is performed on the suspected defective areas according to the preset quality standards to determine the degree of impact on the PCB performance, specifically: Conduct preliminary screening of the marked suspected defect areas to determine the detection parameters that meet the preset quality standards; For the suspected defective areas after screening, performance parameters are extracted, including physical characteristics and structural characteristics; Based on the extracted performance parameters and the preset quality standards, the impact of the suspected defective area is quantitatively analyzed; Compare the assessment results with the quality standards to determine whether the impact of the suspected defective area exceeds the allowable range and make a qualification determination; Mark the unqualified suspected defective areas and record the location information, and generate a test report.

7. A PCB production line defect detection and analysis system based on a recognition model, used to implement a PCB production line defect detection and analysis method based on a recognition model as described in any one of claims 1 to 6, characterized in that: It includes plate surface scanning module, thickness distribution recognition module, deformation trend analysis module, polarization reflection analysis module, suspected defect marking module and quality standard assessment module; Plate surface scanning module: scans the entire surface of the PCB plate to be tested, obtains the thickness distribution data of the plate, and generates the corresponding thickness distribution map; Thickness distribution identification module: uses the threshold segmentation algorithm to identify the area with uneven thickness and judge whether the thickness change exceeds the preset threshold. If so, the corresponding area is marked as the key detection area; Deformation trend analysis module: Analyzes the deformation trend of key inspection areas through historical production data, and identifies potential defects in key inspection areas that are not related to process fluctuations; Polarized reflection analysis module: By adjusting the polarization angle of the light source, the reflectivity difference in the key inspection area is analyzed, and the change of the reflection characteristics is evaluated in combination with the microstructure of the material to identify hidden defects in the key inspection area; Suspected defect marking module: Based on potential defects unrelated to process fluctuations and hidden defects in key inspection areas, it preliminarily detects suspected defect areas in key inspection areas; Quality standard assessment module: Further analyze the suspected defective areas according to the preset quality standards to determine the degree of impact on PCB performance.

Images