Flexible circuit board testing method and system

Abstract

The invention relates to the field of circuit board testing, in particular to a flexible circuit board testing method and system. The method comprises the following steps: obtaining a high-definition detection image of a to-be-tested flexible circuit board; detail sharpening enhancement processing is carried out on the high-definition detection image, welding defect visual visualization processing is carried out, and welding defect visual feature data is generated; performing three-dimensional structure topology modeling on the high-definition detection image, and performing dynamic mapping rendering according to welding defect visual feature data to construct a three-dimensional defect rendering model; obtaining an operation monitoring log of the to-be-tested flexible circuit board; performing multi-scene operation simulation based on the operation monitoring log to obtain simulation monitoring data in different temperature scenes; and performing scene-by-scene circuit board abnormal thermal expansion identification on the simulation monitoring data under different temperature scenes to generate an abnormal thermal expansion temperature simulation evaluation report. According to the invention, comprehensive, efficient and accurate flexible circuit board testing is realized.

Description

Technical Field

[0001] The present invention relates to the field of circuit board testing, and particularly to a flexible printed circuit board testing method and system. Background Art

[0002] With the continuous miniaturization, functionalization of electronic products and the development of flexible electronic technology, flexible printed circuit boards (FPCs) are widely used in many fields such as smart phones, wearable devices, medical devices, and automotive electronics due to their advantages of being thin, flexible, and easy to integrate. As an important connection and conduction component in electronic products, flexible printed circuit boards undertake core functions such as circuit signal transmission and power supply. However, during their production, use, and recycling processes, flexible printed circuit boards may face many challenges, such as surface damage, soldering defects, thermal expansion, unstable electrical performance, etc., which may seriously affect their performance, reliability, and service life.

[0003] Traditional flexible printed circuit board testing methods mainly rely on manual visual inspection and traditional electrical performance testing. These methods usually rely on manual operation, which is not only inefficient but also easily affected by human factors, resulting in inaccurate test results or missed inspections. At the same time, existing detection means mainly focus on the detection of surface defects and electrical performance, lacking comprehensiveness and systematicness in monitoring the physical and electrical performance changes of flexible printed circuit boards in a changing temperature environment and after long-term use. Especially in the comprehensive analysis of multi-dimensional factors such as high-frequency electromagnetic, thermal expansion, and current signals, traditional testing methods are difficult to meet the detection requirements of modern flexible printed circuit boards.

[0004] With the continuous development of automated and intelligent detection technologies, the market's testing requirements for flexible printed circuit boards are gradually moving towards high precision, real-time performance, and multi-dimensional analysis. In order to improve the production efficiency and product quality of flexible printed circuit boards, there is an urgent need for an intelligent testing method that can comprehensively detect various defects, dynamic performance changes, and multi-dimensional environmental impacts of flexible printed circuit boards to meet the industry's detection requirements for high-efficiency and high-quality flexible printed circuit boards. Summary of the Invention

[0005] In order to solve the above technical problems, the present invention proposes a flexible printed circuit board testing method and system to solve at least one of the above technical problems.

[0006] To achieve the above object, the present invention provides a flexible printed circuit board testing method, including the following steps: Step S1: Obtain a high-definition detection image of the flexible printed circuit board to be tested; perform detail sharpening enhancement processing on the high-definition detection image and perform visual visualization processing of soldering defects to generate visual feature data of soldering defects; Step S2: Perform 3D structural topology modeling on the high-definition detection image, and perform dynamic texture mapping rendering based on the visual feature data of welding defects to construct a 3D defect rendering model; Step S3: Obtain the operation monitoring log of the flexible circuit board to be tested; perform multi-scenario operation simulation based on the operation monitoring log to obtain simulation monitoring data under different temperature scenarios; Step S4: Identify abnormal thermal expansion of the circuit board for each scenario of the simulation monitoring data under different temperature scenarios, and evaluate the abnormal temperature distribution in the operating state to generate an abnormal thermal expansion temperature simulation evaluation report; Step S6: Calculate the electrical performance of the circuit board based on the simulation monitoring data under different temperature scenarios to obtain the electrical performance in the operating state; Step S8: Perform multi-dimensional circuit board test evaluation according to the electrical performance in the operating state, the abnormal thermal expansion temperature simulation evaluation report, and the 3D defect rendering model to obtain multi-dimensional test results.

[0007] Through high-definition image acquisition, the present invention can comprehensively capture the minute defects and soldering defects on the surface of the flexible printed circuit board. The high-definition images contribute to high-precision detection, making it difficult to miss details, thus ensuring the high quality of the testing process. By performing sharpening and enhancement processing on the images, the key details can be highlighted, making the soldering defects more obvious. This step improves the visibility of details, reduces the misjudgment that may occur during manual observation, and enhances the reliability of detection. Using visual visualization processing technology, the soldering defects can be significantly marked, enabling these defects to be visually displayed in the images. This provides a clear basis for subsequent defect analysis and repair, helping engineers identify and locate problems at an early stage. By performing three-dimensional structure modeling on the high-definition images, the overall structure of the circuit board and the layout of each component can be accurately simulated, enhancing the understanding of the complexity of the circuit board. This modeling method helps to comprehensively understand the geometric features of the circuit board and provides real basic data for subsequent testing and analysis. According to the visual feature data of the soldering defects, dynamic texture mapping rendering is performed, enabling each soldering defect to be clearly presented in three-dimensional space. This not only makes the defects more intuitive and visible but also allows the problem to be observed from multiple angles, helping engineers accurately judge the nature and location of the defects. The generated three-dimensional defect rendering model can not only clearly display the soldering defects but also assist in conducting more simulations and performance tests subsequently, ensuring the accuracy and comprehensiveness of the detection results. By obtaining the operation monitoring logs of the circuit board to be tested and combining with multi-scenario operation simulations, the actual performance of the circuit board under different working conditions can be reproduced. This process makes the testing closer to the actual usage scenario, ensuring the representativeness and reliability of the simulation results. Simulating the operation state of the circuit board under different temperature scenarios can analyze the impact of temperature changes on the performance of the circuit board, especially on the solder joints and electrical performance. This makes the test results more diverse and enables a comprehensive evaluation of the stability and reliability of the circuit board in a complex environment. By identifying abnormal thermal expansion for each scenario in the simulated monitoring data, thermal expansion problems caused by uneven temperature or design defects can be detected in advance. Thermal expansion may cause the circuit board to crack, break, or the solder joints to fail. Through this step, potential structural problems can be identified early. Conducting abnormal evaluations of the temperature distribution in different scenarios helps to identify areas with uneven temperature distribution, which may become weak links in the circuit board failure. Through the temperature evaluation report, the design can be further optimized to reduce failures caused by temperature imbalance. The generated simulation evaluation report through thermal expansion analysis helps engineers clearly understand the impact of temperature changes and provides a basis for subsequent design improvement and quality control. Based on the simulated monitoring data, the calculation of electrical performance can be performed to accurately evaluate the electrical stability of the circuit board under different temperature conditions. The evaluation of electrical performance can effectively identify potential problems such as unstable current and signal attenuation, ensuring the reliability of the circuit board during actual operation. Through the analysis of electrical performance, signs of electrical faults such as short circuits, overloads, and poor contacts can be detected early.This enables problems to be solved during the production stage, thereby reducing the maintenance cost after product delivery. The comprehensive evaluation of electrical performance provides data support for subsequent stability analysis and fault prediction, further improving the quality control level of the circuit board. By comprehensively analyzing the three-dimensional defect rendering model, the abnormal thermal expansion temperature simulation evaluation report, and the electrical performance evaluation report, the ability to conduct test evaluations from multiple dimensions is provided. This multi-dimensional evaluation method can comprehensively grasp the quality status of the circuit board and provide accurate decision-making basis for engineers. Through the integration of test results from multiple angles, the final evaluation result is not only more reliable but also can comprehensively reflect the performance characteristics of the circuit board from different aspects. This comprehensive analysis can effectively identify potential problems that cannot be captured by a single test method, improving the comprehensiveness and depth of the test. The test results obtained through multi-dimensional evaluation provide an important basis for design optimization, production adjustment, and quality control. Engineers can adjust the circuit board according to the comprehensive evaluation result to further improve its stability and performance.

[0008] In this specification, a flexible circuit board test system is provided for performing the flexible circuit board test method described above, including: A defect vision detection module for obtaining a high-definition detection image of the flexible circuit board to be tested; performing detail sharpening enhancement processing on the high-definition detection image and performing welding defect vision visualization processing to generate welding defect vision feature data; A dynamic rendering module for performing three-dimensional structure topology modeling on the high-definition detection image and performing dynamic texture mapping rendering based on the welding defect vision feature data to construct a three-dimensional defect rendering model; A multi-scenario operation analysis module for obtaining the operation monitoring log of the flexible circuit board to be tested; performing multi-scenario operation simulation based on the operation monitoring log to obtain simulated monitoring data under different temperature scenarios; A thermal expansion evaluation module for identifying abnormal thermal expansion of the circuit board in each scenario for the simulated monitoring data under different temperature scenarios and performing abnormal evaluation of the temperature distribution in the operating state to generate an abnormal thermal expansion temperature simulation evaluation report; An electrical performance evaluation module for calculating the electrical performance of the circuit board based on the simulated monitoring data under different temperature scenarios to obtain the electrical performance in the operating state; A multi-dimensional test evaluation module for performing multi-dimensional circuit board test evaluation according to the electrical performance in the operating state, the abnormal thermal expansion temperature simulation evaluation report, and the three-dimensional defect rendering model to obtain multi-dimensional test results.

[0009] Through the acquisition of high-definition images, the present invention can capture minute defects or irregularities on the surface and inside of the circuit board. Detail sharpening and enhancement processing further highlight minute soldering defects, cracks, scratches, etc., ensuring the accuracy of detection. Automatically identify soldering defects, avoiding errors caused by manual operation, and being able to detect minute defects that cannot be discovered by conventional detection means. The visualization processing of soldering defects can visually present the detection results, helping engineers more clearly understand the location and nature of the defects, facilitating further analysis and repair. Automated defect visual recognition reduces the interference of human factors, improves the accuracy of defect detection, and reduces the possibility of missed and false detections. Using three-dimensional structure topology modeling technology, the flexible circuit board and its various components can be accurately modeled, reflecting the true physical structure of the circuit board. In this way, engineers can more intuitively understand the relationship between components and the form of each part. Through dynamic texture mapping rendering with the visual feature data of soldering defects, the soldering defects are accurately attached to the three-dimensional model. This not only enhances the visualization effect of the defects but also enables engineers to clearly see the impact of the defects on the entire circuit board structure, helping decision-makers formulate more accurate repair plans. The dynamically rendered model can provide a highly realistic visual effect, making the problem more three-dimensional and clear, helping to understand the behavior of the circuit board in actual use. Especially in multi-layer circuit boards, the positioning and display of soldering defects are more intuitive. By simulating the operating conditions at different working temperatures, the performance of the flexible circuit board under various environmental conditions can be comprehensively evaluated. This includes extreme temperatures, humidity, and current changes, etc., ensuring that requirements can be met in various application scenarios. Based on the operation monitoring log, the real working scenario and historical data can be restored, providing more data support that conforms to the actual use situation for subsequent tests. Engineers can predict the performance of the circuit board in actual work and discover potential problems in advance. Through multi-scenario simulation, the response and performance of the circuit board under different working conditions can be quickly evaluated, helping to adjust the design or optimize the production process in a timely manner. The analysis of abnormal thermal expansion can help identify thermal failure problems caused by uneven heat distribution or improper design, and predict the areas that may lead to solder joint rupture, circuit board deformation, or electrical failures. By analyzing the temperature distribution and thermal expansion behavior in different temperature scenarios, it helps to optimize the thermal design of the circuit board. Ensure that the circuit board can still operate stably in extreme environments and reduce the risk of temperature-induced failures. The generated thermal expansion temperature simulation evaluation report provides engineers with a detailed analysis of thermal problems, helping to take measures to avoid possible quality problems in advance and extend the service life of the circuit board. By performing simulation calculations on the electrical performance of the circuit board, its electrical conductivity, anti-interference ability, current stability, etc. can be comprehensively evaluated. This is particularly important for high-frequency circuits or complex circuit boards. Considering the impact of temperature changes on electrical performance, this module can evaluate the electrical stability of the circuit board at different temperatures, providing a basis for the stable operation of the product in high and low temperature environments.Based on the calculation and analysis of electrical performance, potential risks of electrical faults can be detected in advance, such as signal attenuation, electrical failure caused by overheating, etc., helping designers to optimize in the early stage. Integrate multiple independent evaluation results (such as electrical performance, thermal expansion, defect identification, etc.) into one to provide comprehensive test results. It can evaluate the overall performance of the circuit board from multiple dimensions to ensure that it can meet the design requirements under various working conditions. The multi-dimensional comprehensive test results can help engineers accurately predict the performance of the circuit board under different environments and working states, thus providing strong decision-making support for product design, production and optimization. This evaluation module helps to timely detect potential problems in multiple aspects of the circuit board and provides specific optimization suggestions to ensure the quality, stability and reliability of the final product. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 It is a schematic diagram of the step flow of a flexible circuit board testing method of the present invention; Figure 2 It is a schematic diagram of the detailed implementation steps of step S1; Figure 3 It is a schematic diagram of the detailed implementation steps of step S2; Figure 4 It is a schematic diagram of the detailed implementation steps of step S3. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0011] 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.

[0012] The embodiments of the present application provide a flexible circuit board testing method and system. The execution subjects of the flexible circuit board testing method and system include but are not limited to: mechanical equipment, data processing platforms, cloud server nodes, network upload devices, etc. that can be regarded as general computing nodes of the present application. The data processing platform includes but is not limited to: at least one of an audio and image management system, an information management system, and a cloud data management system.

[0013] Please refer to Figures 1 to 4 , the present invention provides a flexible circuit board testing method, and the flexible circuit board testing method includes the following steps: Step S1: Obtain a high-definition detection image of the flexible circuit board to be tested; perform detail sharpening and enhancement processing on the high-definition detection image, and perform visual visualization processing of welding defects to generate welding defect visual feature data; Step S2: Perform three-dimensional structure topology modeling on the high-definition detection image, and perform dynamic texture mapping rendering according to the welding defect visual feature data to construct a three-dimensional defect rendering model; Step S3: Obtain the operation monitoring log of the flexible printed circuit board to be tested; perform multi-scenario operation simulation based on the operation monitoring log to obtain simulated monitoring data under different temperature scenarios; Step S4: Identify abnormal thermal expansion of the circuit board for each scenario of the simulated monitoring data under different temperature scenarios, and evaluate the abnormal temperature distribution in the operating state to generate an abnormal thermal expansion temperature simulation evaluation report; Step S5: Calculate the electrical performance of the circuit board based on the simulated monitoring data under different temperature scenarios to obtain the electrical performance in the operating state; Step S6: Conduct multi-dimensional circuit board test evaluation according to the electrical performance in the operating state, the abnormal thermal expansion temperature simulation evaluation report, and the three-dimensional defect rendering model to obtain multi-dimensional test results.

[0014] Through high-definition image acquisition, the present invention can comprehensively capture the minute defects and soldering defects on the surface of flexible printed circuit boards. High-definition images facilitate high-precision detection, making it difficult to miss details, thus ensuring the high quality of the testing process. Sharpening and enhancing the images can highlight key details and make soldering defects more obvious. This step improves the visibility of details, reduces the misjudgment that may occur during manual observation, and enhances the reliability of detection. Using visual visualization processing technology, soldering defects can be significantly marked, enabling these defects to be visually displayed in the images. This provides a clear basis for subsequent defect analysis and repair, helping engineers identify and locate problems at an early stage. By performing three-dimensional structure modeling on high-definition images, the overall structure of the circuit board and the layout of each component can be accurately simulated, enhancing the understanding of the complexity of the circuit board. This modeling method helps to comprehensively understand the geometric features of the circuit board and provides real basic data for subsequent testing and analysis. According to the visual feature data of soldering defects, dynamic texture mapping rendering is performed, enabling each soldering defect to be clearly presented in three-dimensional space. This not only makes the defects more intuitively visible but also allows the problem to be observed from multiple angles, helping engineers accurately judge the nature and location of the defects. The generated three-dimensional defect rendering model can not only clearly display soldering defects but also assist in subsequent more simulations and performance tests to ensure the accuracy and comprehensiveness of the detection results. By obtaining the operation monitoring logs of the circuit board to be tested and combining multi-scenario operation simulations, the actual performance of the circuit board under different working conditions can be reproduced. This process makes the testing closer to the actual usage scenario and ensures the representativeness and reliability of the simulation results. Simulating the operation state of the circuit board under different temperature scenarios can analyze the impact of temperature changes on the performance of the circuit board, especially on solder joints and electrical performance. This makes the test results more diverse and enables a comprehensive evaluation of the stability and reliability of the circuit board in a complex environment. By identifying abnormal thermal expansion for each scenario in the simulated monitoring data, thermal expansion problems caused by uneven temperature or design defects can be detected in advance. Thermal expansion may cause the circuit board to crack, break, or solder joint failure, and potential structural problems can be identified early through this step. Evaluating the abnormality of the temperature distribution in different scenarios helps to identify areas with uneven temperature distribution, which may become weak links in the circuit board failure. Through the temperature evaluation report, the design can be further optimized to reduce failures caused by temperature imbalance. The generated simulation evaluation report through thermal expansion analysis helps engineers clearly understand the impact of temperature changes and provides a basis for subsequent design improvement and quality control. Based on the simulated monitoring data, electrical performance calculations can be performed to accurately evaluate the electrical stability of the circuit board under different temperature conditions. The evaluation of electrical performance can effectively identify potential problems such as unstable current and signal attenuation, ensuring the reliability of the circuit board in actual operation. Through the analysis of electrical performance, signs of electrical faults such as short circuits, overloads, and poor contacts can be detected early.This enables problems to be solved during the production stage, thereby reducing the maintenance cost after product delivery. The comprehensive evaluation of electrical performance provides data support for subsequent stability analysis and fault prediction, further improving the quality control level of the circuit board. By comprehensively analyzing the three-dimensional defect rendering model, abnormal thermal expansion temperature simulation evaluation report, and electrical performance evaluation report, the ability to conduct test evaluations from multiple dimensions is provided. This multi-dimensional evaluation method can comprehensively grasp the quality status of the circuit board and provide accurate decision-making basis for engineers. Through the integration of test results from multiple angles, the final evaluation result is not only more reliable but also can comprehensively reflect the performance characteristics of the circuit board from different aspects. This comprehensive analysis can effectively identify potential problems that cannot be captured by a single test method, improving the comprehensiveness and depth of testing. The test results obtained through multi-dimensional evaluation provide an important basis for design optimization, production adjustment, and quality control. Engineers can adjust the circuit board according to the comprehensive evaluation results to further improve its stability and performance.

[0015] In the embodiments of the present invention, refer to Figure 1 , which is a schematic diagram of the step flow of a flexible circuit board testing method of the present invention. In this example, the steps of the flexible circuit board testing method include: Step S1: Obtain a high-definition detection image of the flexible circuit board to be tested; perform detail sharpening enhancement processing on the high-definition detection image and conduct visual visualization processing of welding defects to generate visual feature data of welding defects; In this embodiment, a suitable high-definition detection device is selected. Usually, an industrial camera with a high resolution (such as over 20 million pixels) is used for shooting to ensure that tiny details on the circuit board can be captured. Ensure that the lens of the camera is clean and free of scratches to avoid affecting the image quality. According to the size and complexity of the circuit board, select a suitable shooting angle and distance. Usually, the distance is required to be 30 - 50 cm to obtain the best clarity. Before shooting, set appropriate lighting conditions. Use a uniform light source (such as an LED lamp) to avoid shadows and reflections, and ensure that the light is evenly distributed so that the entire surface of the circuit board can be adequately illuminated. Control the temperature and humidity of the shooting environment to reduce the impact of external factors on the image quality. It is recommended to shoot in an environment with a temperature of 20 - 25°C and a relative humidity of 40 - 60%. Start the camera and use professional image acquisition software for shooting. Set an appropriate exposure time (usually between 1 / 60 second and 1 / 120 second) to capture clear images. Ensure that the camera remains stable during shooting to prevent image blurring. Take multiple shots and record the images under different angles and lighting conditions for subsequent selection of the best image for processing. Each image should contain information such as a timestamp, shooting parameters (such as aperture, shutter speed), and camera settings. Store the captured high-definition detection images in a specified folder using a clear naming rule (such as "circuit_board_date_number.jpg") for easy subsequent management and retrieval. Ensure that the image format is a lossless compression format (such as PNG) to retain the image quality. Create a database or document to record the shooting parameters and environmental conditions of each image for subsequent analysis reference. Before performing detail sharpening, use image processing software (such as Adobe Photoshop or GIMP) to preprocess the high-definition detection images, including denoising and color correction. Apply Gaussian blur to remove random noise in the image to improve the subsequent processing effect. Perform histogram equalization on the image to enhance the contrast and make the details more clearly visible. According to the characteristics of the image, adjust the brightness and contrast parameters to obtain the best effect. Apply a sharpening filter (such as Unsharp Mask or Smart Sharpen) to enhance the details of the image. Select appropriate radius and intensity parameters to highlight the edge details of the circuit board. Usually, the radius is set to 1 - 2 pixels and the intensity is set between 50 - 150% to obtain clear details without introducing excessive noise. Use a high-pass filter to further enhance the details. Perform a frequency domain transformation on the image, extract the high-frequency components, and then apply them to the original image to enhance the edges and details. Observe the sharpened image to ensure that the details are clear and there are no obvious artifacts or signs of oversharpening. The effect of detail enhancement can be evaluated by comparing the original image and the sharpened image. Record the parameter settings and effect evaluation results of the sharpening process for subsequent batch processing and effect comparison. Method (such as convolutional neural network). According to the requirements, set appropriate algorithm parameters to ensure that the algorithm can effectively identify welding defects.Determine the characteristic indexes of welding defects, such as holes, cracks, false soldering, etc., to ensure that the algorithm can accurately distinguish different types of defects. Input the sharpened image into the selected defect detection algorithm and run the algorithm to identify welding defects. Record the position, size and type of each defect to generate the visual feature data of welding defects. Use visualization tools (such as OpenCV, MATLAB, etc.) to annotate the detection results, mark the identified defects on the image with different colors or shapes for intuitive display. Store the generated visual feature data of welding defects in the database to ensure the integrity and traceability of the data. Each record should include the defect type, position, size and related parameters. Generate a welding defect analysis report, outlining the detection results and possible improvement suggestions, providing a basis for subsequent quality control and improvement.

[0016] Step S2: Perform three-dimensional structural topology modeling on the high-definition detection image and perform dynamic texture mapping rendering according to the visual feature data of welding defects to construct a three-dimensional defect rendering model; In this embodiment, select a suitable 3D modeling software, such as Blender, Maya or SolidWorks, which support the function of generating 3D models from 2D images. Ensure that the software version is up-to-date to utilize its latest features and optimizations. Before starting the modeling, collect the data of high-definition detection images, including the resolution, shooting angle and lighting conditions of the images. This information will help maintain accuracy during the modeling process. Import the high-definition detection images into the 3D modeling software, use image processing tools to analyze the images, and extract the outline and main features of the circuit board. Edge detection algorithms (such as the Canny algorithm) can be applied to identify the edges of the circuit board for accurate contour drawing. During the analysis process, confirm the positions, shapes and other features of the solder joints to ensure that these details can be accurately reflected in the subsequent modeling. According to the extracted features, create a 3D structural topology model in the modeling software. First, draw the basic shape of the circuit board, including edges, holes and welding areas. Use polygon modeling techniques to create a base surface and gradually refine it. During the modeling process, always refer to the visual feature data of welding defects to ensure that the model can accurately display the positions and forms of welding defects. Subdivision modeling techniques can be used to enhance the details of the model to make it more in line with the actual situation. After completing the preliminary modeling, optimize the model to ensure that there are no performance issues during rendering. Simplification tools can be used to reduce the number of polygons while maintaining visual quality. Conduct an overall inspection of the model to ensure that all details have been accurately represented, especially in the areas of welding defects. If necessary, adjust the scale and position of the model to ensure its accuracy in 3D space. Dynamic texture mapping rendering based on the visual feature data of welding defects According to the visual feature data of welding defects, prepare the corresponding texture maps. Image editing software (such as Photoshop) can be used to create defect texture maps, including features such as the color, shape and glossiness of the defects. When making the texture, ensure that the texture resolution is high enough to maintain clarity when applied to the 3D model. Generally, the selected texture resolution should be 1024x1024 pixels or higher. Import the prepared texture maps into the 3D modeling software and apply them to the model. During the mapping process, ensure that the texture mapping method is correct. Usually, UV mapping technology is used to ensure that the texture can accurately cover the corresponding area of the model. According to the characteristics of the welding defects, adjust the transparency and reflectivity of the texture so that the nature of the defects can be realistically displayed during rendering. For example, a higher transparency may be set for bubbles, while a stronger reflection may be set for cracks.

[0017] Configure the parameters of the rendering engine and select a suitable rendering method (such as physically based rendering [PBR]) to achieve high-quality visual effects. Set the position, type, and intensity of the light source to simulate the lighting conditions in a real environment. During the rendering process, test the performance of the model under different lighting conditions and observe the visualization effect of the welding defects to ensure that the defects are clearly visible at different angles and lighting conditions. After the rendering is completed, store the generated 3D defect rendering model in an appropriate file format (such as FBX or OBJ) to ensure compatibility with other software. Evaluate the quality of the final rendering result by comparing it with the image of the actual circuit board and check whether the performance of the defects is accurate. Record the evaluation results and make necessary adjustments to the model and textures to optimize the final effect.

[0018] Step S3: Obtain the operation monitoring log of the flexible circuit board to be tested; perform multi-scenario operation simulation based on the operation monitoring log to obtain simulation monitoring data under different temperature scenarios; In this embodiment, ensure that the flexible printed circuit board to be tested is correctly connected to the monitoring system. The system should include multiple sensors, such as temperature sensors, current sensors, and voltage sensors, to monitor the operating status of the circuit board in real time. Configure the data acquisition device and set the sampling frequency. Generally, it is recommended that the sampling frequency be once per second to ensure that sufficient operating data can be captured. Ensure that the data acquisition system can process multi-channel data to monitor multiple parameters simultaneously. Start the monitoring system and begin to record the operating status of the circuit board, focusing on key parameters such as temperature, voltage, current, and operating time. During the recording process, monitor the status of the device in real time to ensure the integrity of data acquisition. Set an appropriate monitoring time period, usually choose to continuously monitor for 24 hours to capture the operating status of the circuit board at different time periods. This time period should cover multiple stages such as the startup, operation, and stop of the circuit board to obtain comprehensive data. Store the collected operating monitoring log data in a database to ensure the security and traceability of the data. Each record should include a timestamp, monitoring parameters (such as current, temperature, operating voltage), and their units. Conduct a preliminary collation of the data and screen out the required fields, such as temperature changes, load conditions, etc. Simple statistical analysis of the data can be performed using data analysis tools (such as Excel or Python) to ensure the integrity and consistency of the data. Scenario setting: According to the obtained operating monitoring log, set different temperature scenarios and working conditions. Define multiple simulation scenarios according to the actual operating conditions, such as a high-temperature scenario (e.g., 70°C), a normal-temperature scenario (e.g., 25°C), and a low-temperature scenario (e.g., -20°C). Determine the key parameters under each scenario, including the temperature change rate, current load, and operating voltage, etc. These parameters will be used as inputs for the simulation model. Select appropriate simulation tools, such as thermal simulation software (such as Ansys or COMSOL Multiphysics) or electrical simulation tools (such as LTspice). These tools can simulate the operating status of the circuit board under different temperature scenarios. Determine the boundary conditions and initial conditions of the simulation to ensure that the simulation environment can truly reflect the actual working conditions. For example, set the ambient temperature, heat dissipation conditions, and material properties, etc., to ensure the accuracy of the simulation results. Input the data in the operating monitoring log into the simulation tool and perform simulation runs for each scenario one by one. During the simulation process, monitor the changes in various parameters in real time and record the current, voltage, power consumption, etc. data under different temperature scenarios. After running the simulation, generate the monitoring data under different scenarios and record the key performance indicators for each scenario, such as the operating temperature, maximum current, and power loss, etc. These data will be used for subsequent performance analysis and evaluation.

[0019] Step S4: Identify the abnormal thermal expansion of the circuit board for each scenario of the simulation monitoring data under different temperature scenarios, and evaluate the abnormal temperature distribution in the operating state to generate an abnormal thermal expansion temperature simulation evaluation report; In this embodiment, simulated monitoring data under different temperature scenarios are collected, including temperature, expansion rate, material properties, etc. Ensure the integrity of the data, with particular attention to temperature changes and corresponding expansion data. Establish a data collation process to integrate data from different scenarios into a unified format for subsequent analysis. Preprocess the data, including removing outliers and filling in missing values. Statistical methods (such as mean filling or interpolation) can be used to handle the missing data to ensure the reliability of the dataset. At the same time, standardize the data for subsequent comparison and analysis. Determine the identification criteria for abnormal thermal expansion, including the threshold of thermal expansion (usually depending on the thermal expansion coefficient of the material) and the corresponding temperature change range. The thermal expansion coefficient of a flexible printed circuit board is usually between 10 - 20 ppm / °C. Set a reasonable threshold (such as 20 ppm / °C) to facilitate the identification of abnormal situations. Set the identification method, for example, use control charts or statistical analysis methods (such as Z-score) to identify whether there are expansion values beyond the set range. Ensure the effective distinction between normal expansion and abnormal expansion. Analyze the data for each temperature scenario one by one, and extract the relationship between temperature changes and the expansion of the circuit board. Use data analysis tools (such as MATLAB or Python) to calculate the actual thermal expansion value for each scenario and compare it with the set threshold. Record the analysis results for each scenario, including whether abnormal expansion is identified, the degree of abnormality, and possible reasons (such as sudden temperature changes or material defects). Classify and organize the results for subsequent report generation. Store the identified abnormal thermal expansion data in a database to ensure the integrity and traceability of the data. Each record should contain information such as scenario number, abnormal type, expansion value, and its change trend. Before evaluating the abnormal temperature distribution, ensure there is reliable temperature distribution data. These data can be obtained through thermal imagers or sensor networks, and record the real-time temperature changes of each component under different temperature scenarios. Collate these data and combine them with the expansion identification results for a comprehensive analysis of the operating state of the circuit board. Ensure that the temperature data of each component can be matched with its corresponding expansion data. Determine the criteria for abnormal temperature distribution assessment, including the allowable temperature fluctuation range and the method for abnormal identification. Set a reasonable threshold (such as ±5°C) to facilitate the identification of abnormal temperature distribution. Select a suitable assessment method, such as a control chart based on statistical analysis or a machine learning model, to facilitate the automatic identification of abnormal temperature distribution. Use the collated temperature distribution data to conduct abnormal assessments for each component one by one. Apply the set detection algorithm to identify possible temperature abnormal areas, record the temperature change trend of each component and its deviation from the normal state. When analyzing the results, pay particular attention to areas with too high or too low temperatures, record possible abnormal reasons (such as insufficient heat dissipation or design defects), and conduct correlation analysis between these data and the thermal expansion identification results.

[0020] Step S5: Calculate the electrical performance of the circuit board based on the simulated monitoring data under different temperature scenarios to obtain the electrical performance in the operating state; In this embodiment, collect the simulated monitoring data under different temperature scenarios, mainly including key electrical parameters such as temperature, current, voltage, and power. Ensure the integrity and accuracy of the data, and pay special attention to the impact of temperature on electrical performance. Organize the data, classify it according to temperature scenarios, and ensure that the data for each scenario is in the same format for subsequent analysis. You can use Excel or a database management system to organize the key parameters for each scenario into a table, including temperature, input voltage, output current, and power loss. Calculate the electrical performance of the simulated data for each temperature scenario. Input the temperature, voltage, and resistance values, and calculate the corresponding current and power according to the above formula. During the calculation process, pay attention to the impact of temperature changes on resistance, especially for conductor materials, whose resistance usually increases with the increase in temperature. Store the calculated electrical performance data in the operating state in the database, including the current, power, and related parameters for each temperature scenario. Ensure the integrity and traceability of the data. Conduct a preliminary analysis of the calculation results, compare the electrical performance under different temperature scenarios, and record possible anomalies. For example, pay attention to whether the power peak at certain temperatures exceeds the design requirements, or whether the change in current is within the expected range. You can use visualization tools (such as charts or heat maps) to display the changes in electrical performance under different temperature scenarios to help identify potential performance bottlenecks or problem areas. Based on the analysis results, evaluate whether the electrical performance of the circuit board meets the design requirements. Pay special attention to the performance in extreme temperature scenarios and judge whether there are risks such as overheating and overload. Generate an evaluation report on the electrical performance in the operating state, detailing the electrical performance data, calculation methods, and analysis results for each temperature scenario. The report should include a discussion of potential problems and improvement suggestions for subsequent design optimization and quality control.

[0021] Step S6: Conduct multi-dimensional circuit board test evaluations based on the electrical performance in the operating state, the simulation evaluation report of abnormal thermal expansion temperature, and the three-dimensional defect rendering model to obtain multi-dimensional test results.

[0022] In this embodiment, the criteria and key performance indicators for multi-dimensional test evaluation are determined. These indicators may include electrical performance indicators (such as maximum current, power loss), thermal expansion indicators (such as maximum expansion value), and visual characteristics of defects (such as the number and location of defects). The allowable range for each indicator is set. For example, the current should be within the design specification range, the thermal expansion should not exceed the safety threshold of the material, and the number of defects should be below the acceptable level. These criteria will help identify potential problems and provide a basis for evaluating the results. The operating electrical performance data is correlated with the abnormal thermal expansion data to observe whether the electrical performance is affected by the thermal expansion. Correlation analysis (such as Pearson correlation coefficient) can be used to evaluate whether there is a significant relationship between temperature change and electrical performance degradation. Combining with the three-dimensional defect rendering model, the location and type of defects under specific electrical performance and thermal expansion conditions are identified. Using three-dimensional visualization tools, observe the relationship between defects, thermal expansion, and performance changes to determine which defects are most likely to cause electrical performance problems. A comprehensive analysis of the evaluation results of each indicator is carried out. Identify which indicators are in the danger zone during the evaluation and record the possible reasons. For example, if the current rises significantly in a high-temperature scenario and there are multiple defects at the same time, special attention should be paid to the impact of these defects on the electrical performance. Generate a comprehensive evaluation matrix and summarize all the evaluation results in a visual table to facilitate the quick identification of problem areas and the performance of key performance indicators.

[0023] In this embodiment, refer to Figure 2 , which is a schematic diagram of the detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include: Step S11: Perform a full-range image scanning process on the flexible circuit board to be tested to obtain a high-definition detection image of the flexible circuit board to be tested; Step S12: Perform a detail sharpening and enhancement process on the high-definition detection image to obtain a sharpened and balanced circuit board image; Step S13: Perform deep surface texture recognition on the sharpened and balanced circuit board image to extract the surface texture data of the circuit board; Step S14: Perform distortion texture monitoring on the surface texture data of the circuit board and mark the surface distortion texture; Step S15: Perform a quantitative analysis of the surface defect morphology on the surface distortion texture to generate surface defect morphology data; Step S16: Perform a visual visualization process on the surface defect morphology data for welding defects to generate visual feature data of welding defects.

[0024] In this embodiment, select a suitable imaging scanning device, such as a high-resolution camera or a laser scanner. These devices should have high pixels and fast acquisition capabilities to ensure obtaining high-definition images of the circuit board. Ensure that the device is in good calibration condition to avoid image distortion caused by device errors. Perform device calibration regularly to ensure image quality. Before performing imaging scanning, set up a suitable environment to reduce light interference and reflection. Diffuse light sources can be used to evenly illuminate the surface of the circuit board, avoiding the influence of shadows and highlight areas on the image quality. Ensure that the scanning area is clean and tidy to avoid dust and debris contaminating the circuit board. Fix the flexible circuit board to be tested on the scanning platform to ensure its stable position. During the scanning process, gradually change the angle of the camera or scanner to obtain images of the circuit board from different directions. Usually, multiple scans are required to ensure coverage of all details of the circuit board, especially important circuit connections and soldering parts. Ensure the overlapping part of the image for each scan for subsequent image stitching and processing. After scanning, store the obtained high-definition images in a high-performance storage device to ensure the integrity and security of the image files. Use a lossless compression format to protect the image quality. Conduct a preliminary inspection of the obtained images to ensure there are no blurred or missing parts and prepare to enter the next processing step. Before performing detail sharpening, first preprocess the high-definition detection images. This includes removing background noise and adjusting the contrast of the images so that subsequent sharpening processing can effectively extract details. Use filters (such as high-pass filters) to remove low-frequency noise and enhance the clarity of the images. Select a suitable image sharpening algorithm, such as Laplacian sharpening, Unsharp Mask, or high-frequency enhancement method. These algorithms can effectively enhance the edges and details of the images, making the features of the circuit board more obvious. Adjust the sharpening parameters (such as sharpening coefficient and radius) according to different image features to obtain the best sharpening effect. Apply the selected sharpening algorithm to process the high-definition detection images. Monitor the processing results in real time to ensure the effect of detail enhancement. During the sharpening process, pay attention to avoiding oversharpening to prevent artifacts or noise from appearing in the images. The sharpening effect can be evaluated by comparing the images before and after processing. Select a suitable texture recognition algorithm, such as local binary pattern (LBP), gray-level co-occurrence matrix (GLCM), or convolutional neural network (CNN). These algorithms can effectively extract the surface texture features in the images. Select a suitable algorithm according to the requirements. LBP is suitable for simple texture extraction, while CNN is suitable for complex texture analysis. Before performing texture recognition, segment the sharpened circuit board images to remove unnecessary background information and focus on the surface area of the circuit board. Perform image normalization processing to ensure that the size and format of the input images meet the requirements of the texture recognition algorithm. Apply the selected texture recognition algorithm to process the sharpened and balanced circuit board images to extract the surface texture data. Monitor the output of the algorithm in real time to ensure that the extracted features accurately reflect the actual situation of the circuit board.Record the parameters and features used in the extraction process for subsequent analysis and comparison. Set the criteria for surface distortion texture monitoring, including what kind of texture changes are considered distortions. For example, set criteria such as the continuity, uniformity, and symmetry of the texture. Determine the monitoring method, such as by comparing the differences between the extracted texture features and normal texture features. Analyze the extracted texture data to identify possible distorted areas. Algorithms such as anomaly detection or statistics-based methods can be used to compare the differences between normal textures and the textures to be measured. Mark all detected distorted texture areas and record their locations, types, and severities. Verify the marked distorted textures to ensure their accuracy. The marked areas can be confirmed through manual inspection or further image analysis methods. Evaluate the effectiveness of the monitoring results to ensure that the monitoring method can accurately identify surface distortion textures. Record the monitoring results in a database, including the detailed information of the distorted textures and the corresponding images, for subsequent analysis and auditing. Based on the monitoring results, continuously optimize the texture monitoring criteria and methods to improve the accuracy and efficiency of monitoring. Determine the morphological analysis criteria for surface defects, including features such as the type, shape, size, and distribution of the defects. These criteria will provide a basis for subsequent quantitative analysis. Set up a defect classification system, for example, classify defects into scratches, dents, cracks, etc., to ensure the systematicness of the analysis. Conduct morphological analysis on the marked surface distortion textures to extract the quantitative features of the defects, including the area, perimeter, and shape factor of the defects. Image processing software can be used for morphological analysis to obtain quantitative data. Record the detailed information of each defect, including the defect type, size, and location, for subsequent statistics and analysis. Evaluate the results of the quantitative analysis to ensure the accuracy and consistency of the data. The effectiveness of the analysis can be verified by comparing the results of manual measurement and automatic analysis. Evaluate the representativeness of the defect morphological data to ensure that it can reflect the actual situation of the printed circuit board surface. Record the results of the quantitative analysis in a database, including the detailed information and statistical data of each defect, for subsequent reference and analysis. Determine the visualization processing criteria for welding defects, including selecting appropriate visualization techniques (such as heat maps, 3D modeling, or marked diagrams) to display defect information. Set the visualization goals, for example, clearly display the location and severity of the defects to assist subsequent analysis and decision-making. Based on the extracted surface defect morphological data, use the selected visualization technique to generate the visual feature data of the welding defects. Image processing software can be used to generate heat maps to display the distribution and severity of the defects. Monitor the visualization effect in real time to ensure that it can clearly convey the defect information for subsequent analysis and discussion. Evaluate the generated visualization results to ensure their accuracy and effectiveness. The reliability of the visualization results can be verified by comparing them with the actual defects. Based on the evaluation results, continuously optimize the visualization techniques and parameters to ensure that they can better display the welding defect information.

[0025] In this embodiment, the specific steps of step S12 are as follows: Perform equal-sized region image segmentation on the high-definition detection image to obtain multiple equal-sized region sub-images; Calculate the average brightness of each of the multiple equal-sized region sub-images one by one to generate the average brightness value of each region sub-image; Perform sub-image brightness difference analysis based on adaptive local histogram equalization to extract the brightness difference features of different regions; Perform adaptive local histogram equalization according to the brightness difference features of different regions, thereby generating an adaptive brightness-enhanced detection image; Perform image detail visual recognition on the adaptive brightness-enhanced detection image to extract the details on the surface of the circuit board; Perform detail sharpening on the details on the surface of the circuit board, thereby generating a detail-sharpened detection image; Perform oversharpening balance on the detail-sharpened detection image to obtain a sharpness-balanced circuit board image.

[0026] In this embodiment, before image segmentation, the size of the segmented area is first set. For example, the high-definition detection image is segmented into a 4x4 grid to obtain 16 equal-sized regional sub-images. The size of each sub-image should be determined according to the resolution of the original image and actual requirements. For example, each sub-image is 1280x720 pixels. Ensure that the image segmentation process does not introduce edge effects, and select a suitable segmentation strategy, such as using a uniform segmentation method. Use an image processing software or library (such as OpenCV) to segment the high-definition detection image. According to the set parameters, divide the original image into multiple sub-images according to the grid, ensuring that the content of each sub-image is uniform and contains important features. During the segmentation process, monitor the generation of each sub-image in real time to ensure that there are no missing or duplicate areas. Save the generated multiple equal-sized regional sub-images as independent files, ensuring that each sub-image has a clear naming rule for subsequent processing. Conduct a preliminary inspection of the generated sub-images to ensure that each area is clear and there is no loss of information. Select a suitable brightness calculation method, usually the grayscale averaging method, convert each sub-image into a grayscale image, and calculate its average brightness value. This method is simple and effective and can reflect the overall brightness of each area. Process each equal-sized regional sub-image. First, convert the sub-image into a grayscale image, then traverse each pixel and calculate its brightness value. Accumulate the brightness values and calculate the average value. During the calculation process, record the average brightness value of each sub-image in real time for subsequent analysis. Contrast Limited Adaptive Histogram Equalization (CLAHE) is an effective image enhancement technique that can improve the brightness distribution of an image while maintaining local contrast. Set the size of the adaptive region (such as 8x8 or 16x16 pixels) and the contrast limit to prevent noise amplification. Select a suitable equalization method to ensure that it can effectively process the lighting differences in different areas. Apply the Contrast Limited Adaptive Histogram Equalization method to each equal-sized regional sub-image. During the processing, monitor the equalization effect of each sub-image in real time to ensure that the local brightness can be effectively enhanced. Analyze the equalized image and extract the brightness differentiation features of different areas. For example, record the brightness distribution of each area after the equalization process. According to the previously extracted brightness differentiation features, select appropriate areas for Contrast Limited Adaptive Histogram Equalization. Ensure that the selected areas have obvious features in terms of brightness difference for subsequent image enhancement. Determine the equalization parameters of each area, such as the block size and the contrast limit, to ensure the equalization effect. Perform Contrast Limited Adaptive Histogram Equalization processing on the selected areas. By adjusting the equalization parameters of each area, ensure that the brightness of each area is effectively enhanced. During the processing, monitor the equalization effect in real time to ensure that the image is not distorted due to overprocessing. Save the adaptively equalized image as a new file to ensure that the original image is not overwritten. Evaluate the processing results and observe whether the enhanced image effectively improves the brightness and contrast.Select a suitable detailed visual recognition algorithm, such as edge detection (e.g., Canny edge detection) or feature extraction algorithms (e.g., SIFT or SURF). These algorithms can effectively extract important detailed features in the image. Determine the goal of detailed recognition, such as identifying solder joints, connecting wires, and other key structures on the circuit board. Perform detailed recognition processing on the detected image with adaptive brightness enhancement. Apply the selected algorithm to extract the important detailed areas in the image. During the processing, monitor the recognition effect in real time to ensure that the extracted details can effectively reflect the structural features of the circuit board. Record the recognized detailed features in the database, including the position, type, and importance of each feature. The extracted details can be visually displayed for subsequent analysis. Before performing detailed sharpening processing, set the sharpening parameters, such as the sharpening intensity and radius. Generally, the sharpening intensity can be set to 1.5 to 2.0, and the radius can be set to 1 to 2 pixels to ensure clear details. Select a suitable sharpening algorithm, such as Unsharp Mask or Laplacian sharpening, to ensure that the details can be effectively enhanced. Perform sharpening processing on the extracted surface details of the circuit board. Apply the set sharpening algorithm and monitor the processing effect in real time to ensure that the details are effectively enhanced without generating artifacts. During the processing, combine visual evaluation and numerical evaluation to ensure that the sharpening effect meets the expectations. Determine the criteria for oversharpening, including identifying artifacts and unnatural edge situations in the sharpened image. The details can be observed by comparing the images before and after sharpening. Set the processing threshold to balance the processing when the sharpening effect is too strong and avoid detail distortion. Perform balancing processing on the detailed sharpening detection image. Image subtraction or blurring can be used to reduce the adverse effects caused by oversharpening and ensure that the details look natural visually. During the processing, monitor the balancing effect in real time to ensure that the image details remain clear and are not oversharpened.

[0027] In this embodiment, refer to Figure 3 , which is a schematic diagram of the detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include: Step S21: Identify circuit board components on the sharpened and balanced circuit board image and mark multiple circuit board component nodes; Step S22: Calculate the in-board position of multiple circuit board component nodes to generate the position coordinates of each component node; Step S23: Analyze the geometric size and shape of multiple circuit board component nodes to generate the geometric size and shape parameters of each component; Step S24: Perform three-dimensional structural topology modeling based on the geometric size and shape parameters of each component and the position coordinates of each component node to generate a three-dimensional structural topology model of the circuit board; Step S25: Dynamically map and render the three-dimensional structure topology model of the circuit board based on the visual feature data of welding defects to construct a three-dimensional defect rendering model.

[0028] In this embodiment, a suitable circuit board component recognition algorithm is selected, such as template matching, machine learning classifiers (such as support vector machines or convolutional neural networks), or shape recognition algorithms. These algorithms can effectively identify various components on the circuit board, such as resistors, capacitors, chips, etc. Determine the recognition criteria, such as the shape, size, and color characteristics of the components, to facilitate classification by the algorithm. Process the sharpened and balanced circuit board image. First, convert the image to a grayscale image, and then apply an edge detection algorithm (such as Canny edge detection) to extract the edge features of the components. Analyze the image using the selected algorithm to identify multiple circuit board component nodes. During the processing, monitor the output of the algorithm in real time to ensure the accuracy and integrity of the recognition. Mark the recognized component nodes and record their position and type information. Different colors or symbols can be used to represent different types of components for easy subsequent identification and analysis. Determine the calculation method for component position positioning. Usually, an image coordinate system can be adopted to convert the pixel positions of the component nodes into actual coordinates. Set the origin (such as the upper left corner of the image) and unit (such as millimeters) of the image coordinate system. Set the conversion formula to convert the image coordinates into actual position coordinates: actual coordinate = pixel coordinate × actual size / image size, and calculate the positions of the multiple recognized circuit board component nodes. Extract the pixel coordinates of each component node one by one and calculate the actual position coordinates according to the set conversion formula. During the calculation process, record the actual positions of each component node in real time for subsequent analysis and modeling. Store the position coordinates of each component node in the database to ensure the integrity and consistency of the data. The component positions can be displayed through a visualization tool for easy verification and analysis. Determine the criteria for component geometric dimension analysis, including the width, height, and depth of the components, etc. Set the dimension calculation formula for each component and ensure that the units used are consistent (such as millimeters). Select a suitable analysis method, such as dimension measurement based on edge detection or contour analysis, to extract the geometric features of the components. Measure the geometric dimensions of each recognized component node. Use image processing algorithms to extract the contours of the components and calculate the geometric dimension parameters of the components based on the contour information. During the analysis process, monitor the dimension calculation of each component in real time to ensure its accuracy and consistency. Select a suitable 3D modeling method, such as mesh-based modeling or parametric modeling. Determine the modeling software (such as Blender, SolidWorks, or AutoCAD) to achieve a high-quality 3D model. Set the basic parameters of the modeling, including the geometric features and position coordinates of the components, to ensure the accuracy of the model. Create 3D models one by one according to the geometric dimension morphology parameters and position coordinates of each component. Use the tools of the selected modeling software to input the parameters of each component into the modeling system. During the modeling process, pay attention to adjusting the relative positions between the components to ensure the accuracy and visualization effect of the model. Save the generated 3D structural topology model of the circuit board to ensure the integrity and traceability of the model file.Use an appropriate file format (such as STL or OBJ) for subsequent use. Determine the criteria for dynamic texture rendering, including the texture resolution, texture features, and rendering effects. Ensure that the texture can accurately reflect the visual characteristics of welding defects. Select a suitable rendering software or engine (such as Unity, Unreal Engine, or Blender) for dynamic texture rendering. Apply the visual characteristic data of welding defects to the generated 3D structural topology model. Adjust the transparency, color, and lighting effects of the texture according to the defect characteristics to enhance the authenticity and visual effect of the model. During the rendering process, monitor the effect in real time to ensure that the texture can effectively display welding defects and maintain the overall aesthetics of the model. Evaluate the accuracy of the rendering results to ensure that the dynamic texture can truly reflect the situation of welding defects. The reliability of the rendering effect can be verified by comparing with the actual defects. Save the generated 3D defect rendering model in an appropriate file format for subsequent display and analysis.

[0029] In this embodiment, the specific steps of step S25 are as follows: Obtain the actual material properties of the flexible printed circuit board to be tested; Conduct optical property analysis of the printed circuit board based on the actual material properties to obtain the surface optical properties; Perform defect area light irradiation tracking on the visual characteristic data of welding defects according to the surface optical properties to obtain defect area light path tracking data; Calculate the optimal light rendering parameters based on the defect area light path tracking data, thereby generating the optimal light rendering parameters; Perform high-fidelity visual rendering fitting based on the optimal light rendering parameters, thereby generating a high-fidelity visual rendering texture; Use the high-fidelity visual rendering texture to optimize the texture rendering of the printed circuit board 3D structural topology model to construct a 3D defect rendering model.

[0030] In this embodiment, before conducting the material property test, necessary instrument and equipment are prepared, such as spectrometers, microscopes, and material hardness testers. These devices can help comprehensively evaluate the actual material properties of the flexible printed circuit board, including physical and chemical components. Ensure the stability of the test environment to avoid the influence of external factors (such as humidity and temperature) on the test results. Use a spectrometer to measure the reflectivity and transmittance of the flexible printed circuit board, and obtain the optical properties of the material by analyzing the spectral data in different wavelength ranges. Use a microscope to observe the surface structure of the material and evaluate its smoothness and texture characteristics. At the same time, conduct a hardness test to understand the mechanical properties of the material. Record the test results in the experimental log, including the specific values of each measurement and relevant parameters (such as measurement angle, environmental conditions, etc.). Analyze the obtained data to extract the actual material properties of the flexible printed circuit board, such as refractive index, absorption rate, and surface roughness. These properties will provide basic data for subsequent optical property analysis. Determine the method for optical property analysis. Usually, the ray tracing method or the finite element method (FEM) is used for analysis. These methods can effectively simulate the propagation and reflection characteristics of light in the material. Set the analysis parameters, such as the angle of incident light, wavelength range, and light source type (such as point light source or parallel light source). Combine the actual material property data to conduct optical property simulation. Use the selected optical analysis software to input parameters such as the refractive index and reflectivity of the material into the model. Conduct multiple simulation experiments, observe the optical performance of the flexible printed circuit board under different lighting conditions, and record the reflection, refraction, and scattering behaviors of light. Organize the analysis results to generate a surface optical property report, including information such as reflectivity, transmittance, and color characteristics. The optical property changes under different lighting conditions can be presented in the form of charts. Store the optical property data in a database to ensure the integrity and traceability of the data and provide support for subsequent analysis. Determine the target of light irradiation tracking, set the tracking criteria, including the identification of defect areas, light intensity, and light angle. Select a suitable light irradiation simulation method, such as the ray tracing algorithm, to achieve dynamic light irradiation analysis of the defect areas. Use the surface optical property data to conduct light irradiation tracking on the welding defects. Set the light source at different positions and angles to simulate how the light irradiates the defect areas. Record the light path, including the incident angle, reflection angle of the light, and its intensity change in the defect area, to ensure the accuracy and integrity of the tracking data. Organize the tracking results to generate a light path tracking data report for the defect areas. Record the detailed information of each light path, including the incident angle, reflection angle, and intensity value. According to the light path tracking data of the defect areas, set the calculation criteria for the rendering parameters, including light source intensity, shadow effect, and reflectivity. Determine the rendering algorithm, such as the physically based rendering (PBR) method, to achieve a high-fidelity lighting effect. Calculate the optimal light ray rendering parameters according to the tracking data. Consider the reflection and refraction characteristics of light in the defect areas, and adjust the intensity and position of the light source to obtain the best visual effect.Conduct multiple tests, adjust various rendering parameters to ensure that the finally generated parameters can effectively highlight the visual characteristics of welding defects. Record the calculated optimal light rendering parameters in the experimental log, including the specific values of each parameter and the adjustment process. Determine the standards for high-fidelity visual rendering, including rendering resolution, texture quality, and lighting accuracy, etc. Set corresponding rendering goals to ensure that the final effect is clear and realistic. Select a suitable rendering engine (such as V-Ray, Arnold, or Blender Cycles) for high-fidelity rendering. Use the optimal light rendering parameters to perform high-fidelity visual rendering on the defect area. According to the set resolution and quality standards, perform rendering calculations to generate high-quality images or videos. During the rendering process, monitor the rendering effect in real time to ensure compliance with the set high-fidelity standards. You can observe the changes in the rendering effect through frame-by-frame preview. Save the generated high-fidelity visual rendering map as an appropriate file format (such as PNG or EXR) to ensure that the image quality is not damaged. Evaluate the quality of the rendering result. By comparing with the actual welding defects, verify the authenticity and accuracy of the rendering effect. Determine the standards for map rendering, including the resolution of the map, mapping method, and lighting effect, etc. Ensure that the map can accurately reflect the high-fidelity visual effect. Select a suitable 3D modeling software or engine (such as Unity, Unreal Engine, or Maya) for map rendering optimization. Apply the high-fidelity visual rendering map to the 3D structure topology model of the circuit board. According to the UV mapping of the model, accurately map the map to the model surface. During the rendering process, monitor the effect in real time to ensure that the map can effectively display the welding defects and maintain the overall beauty of the model. Evaluate the effect of the rendering optimization to ensure that the map can truly reproduce the situation of the welding defects. You can verify the reliability of the rendering effect by comparing with the actual defects. Save the finally generated 3D defect rendering model as an appropriate file format for subsequent display and analysis.

[0031] In this embodiment, refer to Figure 4 , which is a schematic diagram of the detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include: Step S31: Obtain the operation monitoring log of the flexible circuit board to be tested; extract multi-dimensional operation state parameters based on the operation monitoring log; Step S32: Perform multi-operation scenario perception according to the multi-dimensional operation state parameters to obtain the operation scenarios of multiple circuit boards; Step S33: Simulate the working temperature of each operation scenario of multiple circuit boards to generate different simulated working scenario temperature parameters; Step S34: Based on different simulated working scenario temperature parameters, perform multi-scenario operation simulation on the flexible circuit board to be tested, and conduct real-time working temperature monitoring and high-frequency electromagnetic detection to obtain simulated monitoring data under different temperature scenarios.

[0032] In this embodiment, before obtaining the operation monitoring log, ensure that the flexible printed circuit board to be tested is connected to the monitoring system and the data acquisition devices are configured. These devices should include a temperature sensor, a current sensor, and other necessary monitoring instruments, which can record the working state of the circuit board in real time. Determine the acquisition frequency of the monitoring log, for example, set it to once per second, so as to ensure that sufficient operation data can be captured for subsequent analysis. Start the monitoring system and begin to record the operation state of the circuit board, including temperature, voltage, working current, operation time, and other key parameters. These data will form a comprehensive operation monitoring log. During the acquisition process, check the integrity and accuracy of the data in real time to ensure that there is no data loss or error. Store the obtained monitoring log data in the database to ensure the security and traceability of the data. Each log record should include a timestamp and relevant parameters for subsequent analysis and query. Conduct a preliminary collation of the collected data, filter out the required fields, and prepare for the extraction of multi-dimensional operation state parameters. Determine the multi-dimensional operation state parameters to be extracted, including temperature change, power consumption, working current, and environmental conditions, etc. These parameters will be used to analyze the performance of the circuit board under different operation scenarios. Set the analysis method for the parameters, for example, use statistical analysis or machine learning algorithms to extract effective operation state features from the monitoring log. Use data processing tools (such as Python, MATLAB, etc.) to analyze the monitoring log and extract the defined multi-dimensional operation state parameters. This process may include steps such as data cleaning, normalization, and feature selection. Record the extracted parameters in a unified database to ensure that each parameter corresponds to the corresponding timestamp and operation state. Based on the extracted multi-dimensional operation state parameters, perceive and classify the operation scenarios of different circuit boards. Clustering algorithms (such as K-means) can be used to group similar operation states to obtain the operation scenarios of multiple circuit boards. Each scenario should include similar temperature, current, and power consumption characteristics to ensure the effectiveness of the scenario. Determine the range and standard of the working temperature simulation, including the minimum temperature, the maximum temperature, and the simulation time. Set the simulated environmental conditions, such as environmental humidity and air flow speed, to ensure the authenticity of the simulation. Select a suitable simulation tool or software, such as thermal simulation software (such as Ansys, COMSOL Multiphysics), to achieve high-precision temperature simulation. For each extracted operation scenario, use the selected thermal simulation software to conduct a one-by-one working temperature simulation for each scenario. Input the extracted operation state parameters, set the corresponding boundary conditions and initial conditions. Run the simulation, monitor the temperature change in real time, and record the working temperature parameters under different scenarios. This process may require multiple iterations to ensure the accuracy of the simulation results. Record the temperature parameters of each simulated working scenario in the database, including the scenario number, the working temperature, and the relevant operation state parameters. Ensure the integrity and traceability of the data.Evaluate the rationality of the simulation results to ensure that the temperature simulation can accurately reflect the actual operating conditions and compare with historical data. According to the working temperature parameters simulated above, prepare for the multi-scenario operation simulation. Set the simulation time frame, for example, select to run continuously for 24 hours to observe the impact of long-term operation on the circuit board. Determine the parameters for real-time monitoring, including temperature, current, voltage, etc., in order to comprehensively evaluate the performance of the circuit board under different temperature scenarios. Start the multi-scenario operation simulation and execute the simulation tasks one by one for each scenario. Under each scenario, monitor the working temperature and other electrical parameters in real time to ensure the accuracy and timeliness of the data. During the simulation process, use high-frequency electromagnetic detection equipment to monitor the electromagnetic interference and radiation conditions of the circuit board and record the electromagnetic data that may affect the performance of the circuit board. Record the simulation monitoring data under different temperature scenarios in the database, including parameters such as real-time temperature, power consumption, and frequency response. Ensure the integrity and traceability of the data.

[0033] In this embodiment, step S4 includes the following steps: Step S41: Identify the abnormal thermal expansion of the circuit board for each scenario of the simulation monitoring data under different temperature scenarios and extract the simulation monitoring data of the scenarios with abnormal thermal expansion; Step S42: Analyze the temperature distribution of the simulation monitoring data of the scenarios with abnormal thermal expansion to generate temperature distribution data; Step S43: Mine the temperature fluctuations at multiple time points based on the temperature distribution data to obtain the temporal temperature distribution fluctuation field; Step S44: Detect the temperature mutation regions based on the temporal temperature distribution fluctuation field and then perform regional division to obtain the temperature mutation regions; Step S45: Calculate the regional temperature change gradient for the temperature mutation regions to generate regional temperature change gradient features; Step S46: Evolve the temperature distribution imbalance for the regional temperature change gradient features to generate temperature distribution imbalance evolution data; Step S47: Evaluate the abnormal temperature distribution in the operating state for the temperature distribution imbalance evolution data to generate an evaluation report on the abnormal thermal expansion temperature simulation.

[0034] In this embodiment, the identification criteria for abnormal thermal expansion are determined, including the threshold of thermal expansion (such as the coefficient of thermal expansion of the material) and the corresponding temperature change range. Generally, the coefficient of thermal expansion of a flexible printed circuit board is between 10 - 20 ppm / °C, and a reasonable threshold is set to facilitate the identification of abnormal situations. Characteristic indicators of abnormal thermal expansion are defined, such as temperature difference, expansion rate, and degree of deformation, etc., for subsequent data analysis. The simulated monitoring data under different temperature scenarios are analyzed one by one to extract the relationship between temperature change and the change in the size of the circuit board. Data analysis tools (such as Python or MATLAB) are used to process the data for each scenario. By comparing the actually measured expansion value with the set threshold, the scenarios with abnormal thermal expansion are identified. The specific data for each abnormal scenario are recorded, including temperature, expansion value, and possible reasons. A suitable temperature distribution analysis method is selected, usually using thermal analysis software or data visualization tools (such as Ansys, COMSOL, or MATLAB) for analysis. The analysis parameters are set, including mesh division and calculation accuracy, etc. The analysis scope is determined, for example, the area where abnormal thermal expansion occurs is selected for focused analysis. The simulated monitoring data of the abnormal thermal expansion scenario are input into the selected analysis tool to run the temperature distribution simulation. During the analysis process, the temperature changes in different regions are concerned, and a temperature distribution map is generated. The temperature values and change trends of each region are recorded to ensure the accuracy and validity of the data. The criteria for mining temperature fluctuations at multiple time points are determined, including the fluctuation range, frequency, and time window, etc. A suitable time interval (such as every minute or every hour) is set for data collection and analysis. A suitable data mining algorithm is selected, such as time series analysis or wavelet transform, to extract the temperature fluctuation characteristics. The temperature distribution data are analyzed point by point in time to calculate the temperature fluctuations in each time period. The set mining algorithm is applied to extract and analyze the temperature fluctuations to generate fluctuation data. The laws and trends of temperature fluctuations are identified, and the temperature change conditions at each time point are recorded. The data of the time-series temperature distribution fluctuation field are recorded in the database, including timestamps, temperature fluctuation values, and change trends. Ensure the integrity and traceability of the data. The criteria for detecting temperature mutation regions are determined, including the mutation threshold and the detection range. A suitable mutation threshold (such as the temperature change exceeds 10% of the set value) is set to facilitate the identification of mutation regions. A suitable detection method is selected, such as a change point detection algorithm (such as CUSUM or Pettitt test), to identify temperature mutation regions. The time-series temperature distribution fluctuation field data are analyzed to identify temperature mutation regions. Using the selected detection algorithm, mutation detection is performed for each time period, and the time and region where the mutation occurs are recorded. The detection results are compared with the temperature distribution data to ensure the accuracy of the identified mutation regions. The detection results of the temperature mutation regions are recorded in the database, including the numbers of the mutation regions, the degree of change, and relevant parameters. Ensure the integrity and traceability of the data.According to the detection results, divide the temperature mutation area, generate a regional division report, and provide a basis for subsequent analysis. Determine the criteria for calculating the regional temperature change gradient, including the calculation method and threshold. The temperature change gradient = ΔT / Δx, where ΔT is the temperature change and Δx is the distance. Set the calculation range to ensure that the calculation can cover all mutation areas. Calculate the temperature change gradient for each temperature mutation area. Use data analysis tools to extract the temperature change data for each area and calculate the temperature change gradient according to the set formula. Record the temperature change gradient characteristics of each area, including the area number, temperature change value, and calculation result. Determine the criteria for the evolution of temperature distribution imbalance, including the evolution index and threshold. Set an appropriate imbalance threshold to identify the imbalance of temperature distribution. Select a suitable evolution analysis method, such as dynamic time warping or state transition analysis, to evaluate the evolution characteristics of temperature distribution. Analyze the temperature change gradient characteristics of the area to identify the evolution process of temperature distribution imbalance. Record the evolution characteristics of each area, including the temperature change trend and the degree of imbalance. Generate temperature distribution imbalance evolution data to ensure the accuracy and effectiveness of the data. Record the temperature distribution imbalance evolution data in the database, including the detailed information of the evolution process and related parameters. Ensure the integrity and traceability of the data. Evaluate the rationality of the evolution results by visually displaying the evolution of temperature distribution imbalance to ensure that the evolution data can reflect the actual situation. Determine the criteria for evaluating the abnormality of the operating state temperature distribution, including the abnormality detection threshold and evaluation method. Set an appropriate threshold to facilitate the identification of abnormal temperature distribution. Select a suitable abnormality detection algorithm, such as a statistical control chart or a machine learning classifier, to evaluate the abnormality of temperature distribution. Evaluate the abnormality of the temperature distribution imbalance evolution data, apply the selected algorithm, and identify possible abnormal temperature areas. Record the detailed information of each abnormal area, including temperature, gradient, and change trend. Generate an abnormal thermal expansion temperature simulation evaluation report, outlining the identified abnormal conditions and related data.

[0035] In this embodiment, the specific steps of step S5 are as follows: Step S51: Extract high-frequency electromagnetic detection data based on the simulation monitoring data under different temperature scenarios; Step S52: Calculate the current signal of each component based on the high-frequency electromagnetic detection data; Step S53: Calculate the current intensity of the current signal of each component; Step S54: Calculate the current intensity deviation between components based on the current intensity to obtain the current intensity deviation value between components; Step S55: Conduct current signal interference analysis on the current intensity of the current signal of each component to generate current signal interference data; Step S56: Calculate the electrical performance of the circuit board based on the current signal interference data and the current intensity deviation value between components to obtain the operating state electrical performance.

[0036] In this embodiment, the standards and equipment configurations for high-frequency electromagnetic detection are determined. Select suitable high-frequency electromagnetic detection instruments (such as spectrum analyzers, oscilloscopes, etc.) to ensure that the equipment can cover the required frequency range (such as 30 MHz to 3 GHz). Before the detection, formulate a detection plan, including detection frequency, duration, and sampling rate. Set the sampling frequency to 1 GHz to ensure the integrity of the signal. In different temperature scenarios, start the high-frequency electromagnetic detection equipment and record the electromagnetic signals of the circuit board. Ensure consistent detection in each scenario for subsequent comparison. During the monitoring process, check the signal quality in real time to ensure that there is no signal loss or interference. For each scenario, record relevant environmental parameters such as temperature, humidity, etc. for subsequent analysis. Store the extracted high-frequency electromagnetic detection data in a database to ensure the integrity and traceability of the data. Each record should include a timestamp, temperature scenario, and detailed parameters of the detected signal. Determine the model for calculating the current signal, including the input parameters and calculation formula of the signal. Usually, Ohm's law (I = V / R) is used for basic current calculations, where I is the current, V is the voltage, and R is the resistance. Set the resistance values of the components to ensure that the resistance of each component is within the rated range and record the specific parameters of each component. Process the high-frequency electromagnetic detection data of each component, extract the voltage signal, and combine it with the set resistance value to calculate the current signal of each component. Data analysis tools (such as MATLAB or Python) can be used for batch calculations. During the calculation process, check the rationality of the results in real time to ensure that the calculation of the current signal meets the expectations. Record the current signal of each component in the database, including the component number, current signal value, and relevant parameters. Ensure the integrity and traceability of the data. Evaluate the rationality of the calculation results by comparing with the actual measured values to ensure the accuracy of the calculated current signal. Determine the calculation method and unit of the current intensity. Usually, the ampere (A) is used as the unit of current intensity, and the calculation formula is set so that the current intensity is directly equal to the calculated current signal value. Ensure that possible current fluctuations and noise effects are considered during the calculation, and set reasonable filtering parameters. Process the current signal of each component and directly extract the current value as the current intensity. If there are fluctuations, use a filtering algorithm (such as Kalman filtering) to smooth the signal to improve the calculation accuracy. Record the current intensity of each component, including the calculation method and parameter settings, for subsequent analysis. Record the current intensity of each component in the database, including the component number and intensity value. Ensure the integrity and traceability of the data. Calculate the average current intensity of all components using statistical analysis tools (such as the NumPy library in Python). Then, according to the set deviation formula, calculate the deviation of the current intensity of each component. Record the deviation value of each component and determine whether there are abnormal situations exceeding the set threshold. Record the current intensity deviation value of each component in the database, including the component number and deviation percentage.Ensure the integrity and traceability of data. Determine the methods for analyzing current signal interference, including noise types, identification of interference sources, and analysis metrics. Common interference types include electromagnetic interference (EMI), radio frequency interference (RFI), etc. Set the parameters for interference analysis, such as signal sampling frequency and time window, to ensure the accuracy of the analysis. Conduct interference analysis on the current signals of each component, use spectrum analysis tools to extract the signal frequency components, and identify the possible interference frequencies. Record the results of the interference analysis, including interference frequencies, amplitudes, and the components that may be affected, for subsequent evaluation. Determine the standards for calculating the electrical performance of the circuit board, including current intensity, interference effects, and performance metrics. Set appropriate performance evaluation metrics, such as power loss, efficiency, and stability. Select a suitable calculation model, usually using circuit theory and electrical engineering principles for analysis. Utilize the current signal interference data and the current intensity deviation values between components to calculate the electrical performance of the circuit board. According to the set model, calculate metrics such as power loss and electrical stability. Record the calculation results, including the values of each performance metric and related parameters, to ensure the accuracy of the data. Record the calculation results of the electrical performance of the circuit board in the database, including the detailed information of the performance metrics and related parameters. Ensure the integrity and traceability of the data. Evaluate the reasonableness of the calculated results of the electrical performance by comparing them with the design standards to ensure that the performance results can effectively reflect the actual situation of the circuit board.

[0037] In this embodiment, the specific steps of step S6 are as follows: Step S61: Conduct comprehensive electrical state diagnosis based on the operating electrical performance to generate comprehensive electrical state diagnosis data; Step S62: Perform circuit fault prediction on the comprehensive electrical state diagnosis data to generate circuit board circuit fault prediction data; Step S63: Conduct electrical reliability analysis based on the circuit board circuit fault prediction data to obtain an electrical reliability report of the circuit board; Step S64: Conduct multi-dimensional circuit board test evaluation based on the three-dimensional defect rendering model, the electrical reliability report of the circuit board, and the abnormal thermal expansion temperature simulation evaluation report to obtain multi-dimensional test results.

[0038] In this embodiment, the indicators for comprehensive electrical state diagnosis are determined, including current intensity, power loss, operating temperature, voltage change, etc. These indicators will be used to evaluate the overall electrical performance of the circuit board. Set the thresholds and criteria for diagnosis to ensure that potential problems can be effectively identified. For example, set the allowable fluctuation range of current intensity and the maximum value of power loss. Collect the electrical performance data in the operating state and use data analysis tools (such as MATLAB or Python) to comprehensively analyze each performance indicator. According to the set criteria and thresholds, determine whether each indicator is within the normal range. Identify any abnormal situations and record the corresponding diagnostic results. Statistical analysis methods (such as Z-score or standard deviation) can be used to evaluate the stability of electrical performance. Record the comprehensive electrical state diagnosis data in the database, including the values of each performance indicator, the judgment results, and relevant parameters. Ensure the integrity and traceability of the data. Determine the models for circuit fault prediction. Commonly used models include rule-based expert systems, machine learning models (such as decision trees, random forests), or deep learning models (such as neural networks). The selection of a suitable model depends on the complexity and availability of the data. Set the input features for fault prediction, usually including comprehensive electrical performance indicators such as current, temperature, and power. Use the comprehensive electrical state diagnosis data as input and run the fault prediction model. Train and validate the model to ensure its good prediction ability. Record the prediction results, including possible fault types, fault locations, and their occurrence probabilities. According to the prediction results, identify high-risk areas and components. Record the circuit board circuit fault prediction data in the database, including fault types, locations, prediction probabilities, and relevant parameters. Ensure the integrity and traceability of the data. Evaluate the accuracy of the fault prediction results by comparing with the actual fault records to ensure the effectiveness of the prediction model. Determine the standards and methods for electrical reliability analysis. Usually, methods such as accelerated life test (ALT), stress test, and fault tree analysis (FTA) are adopted. Set the key performance indicators for analysis, such as failure rate and mean time between failures (MTBF). Set the time frame and sample size for reliability analysis to ensure the representativeness of the analysis results. Based on the circuit fault prediction data, conduct electrical reliability analysis. Collect relevant data, including failure rate, operating cycle, and environmental factors, and use statistical analysis tools to evaluate the reliability of the system. Generate electrical reliability indicators by calculating the failure probability and life distribution, and evaluate the performance stability of the circuit board under different operating conditions. Record the electrical reliability analysis results of the circuit board in the database, including reliability indicators, analysis methods, and relevant parameters. Ensure the integrity and traceability of the data.

[0039] In this embodiment, a flexible circuit board test system is provided for performing the flexible circuit board test method as described above, including: A defect vision detection module, which is used to obtain a high-definition detection image of a flexible printed circuit board to be tested; perform detail sharpening and enhancement processing on the high-definition detection image, and perform visual processing of welding defects to generate welding defect visual feature data; A dynamic rendering module, which is used to perform three-dimensional structure topology modeling on the high-definition detection image, and perform dynamic texture mapping rendering according to the welding defect visual feature data to construct a three-dimensional defect rendering model; A multi-scenario operation analysis module, which is used to obtain the operation monitoring log of the flexible printed circuit board to be tested; perform multi-scenario operation simulation based on the operation monitoring log to obtain simulated monitoring data under different temperature scenarios; A thermal expansion evaluation module, which is used to identify abnormal thermal expansion of the circuit board for each scenario of the simulated monitoring data under different temperature scenarios, and perform evaluation of abnormal temperature distribution in the operating state to generate an abnormal thermal expansion temperature simulation evaluation report; An electrical performance evaluation module, which is used to calculate the electrical performance of the circuit board based on the simulated monitoring data under different temperature scenarios to obtain the electrical performance in the operating state; A multi-dimensional test evaluation module, which is used to perform multi-dimensional circuit board test evaluation according to the electrical performance in the operating state, the abnormal thermal expansion temperature simulation evaluation report and the three-dimensional defect rendering model to obtain multi-dimensional test results.

[0040] Through the acquisition of high-definition images, the present invention can capture minute defects or irregularities on the surface and inside of the circuit board. Detail sharpening and enhancement processing further highlights minute soldering defects, cracks, scratches, etc., ensuring the accuracy of detection. Automatically identify soldering defects, avoiding errors caused by manual operations, and capable of detecting minute defects that cannot be discovered by conventional detection means. The visualization processing of soldering defects can visually present the detection results, helping engineers to more clearly understand the location and nature of the defects, facilitating further analysis and repair. Automated defect visual recognition reduces the interference of human factors, improves the accuracy of defect detection, and reduces the possibility of missed and false detections. Using three-dimensional structure topology modeling technology, precise modeling can be carried out on the flexible circuit board and its various components, reflecting the true physical structure of the circuit board. In this way, engineers can more intuitively understand the relationship between components and the form of each part. Through dynamic texture mapping rendering based on the visual feature data of soldering defects, the soldering defects are accurately attached to the three-dimensional model. This not only improves the visualization effect of the defects but also enables engineers to clearly see the impact of the defects on the entire circuit board structure, helping decision-makers formulate more accurate repair plans. The dynamically rendered model can provide a highly realistic visual effect, making the problem more three-dimensional and clear, helping to understand the behavior of the circuit board in actual use. Especially in multi-layer circuit boards, the positioning and display of soldering defects are more intuitive. By simulating the operating conditions at different working temperatures, the performance of the flexible circuit board under various environmental conditions can be comprehensively evaluated. This includes extreme temperatures, humidity, and current changes, etc., ensuring that requirements can be met in various application scenarios. Based on the operation monitoring log, the real working scenario and historical data can be restored, providing more realistic data support for subsequent tests. Engineers can predict the performance of the circuit board in actual work and discover potential problems in advance. Through multi-scenario simulation, the response and performance of the circuit board under different working conditions can be quickly evaluated, helping to adjust the design or optimize the production process in a timely manner. The analysis of abnormal thermal expansion can help identify thermal failure problems caused by uneven heat distribution or improper design, and predict areas that may lead to solder joint rupture, circuit board deformation, or electrical faults. By analyzing the temperature distribution and thermal expansion behavior in different temperature scenarios, it helps to optimize the thermal design of the circuit board. Ensure that the circuit board can still operate stably in extreme environments, reducing the risk of temperature-induced failures. The generated thermal expansion temperature simulation evaluation report provides engineers with a detailed analysis of thermal problems, helping to take measures to avoid possible quality problems in advance and extend the service life of the circuit board. By simulating and calculating the electrical performance of the circuit board, its conductivity, anti-interference ability, current stability, etc. can be comprehensively evaluated. This is particularly important for high-frequency circuits or complex circuit boards. Considering the impact of temperature changes on electrical performance, this module can evaluate the electrical stability of the circuit board at different temperatures, providing a basis for the stable operation of the product in high and low temperature environments.Based on the calculation and analysis of electrical performance, potential risks of electrical failures can be detected in advance, such as signal attenuation, electrical failures caused by overheating, etc., helping designers to optimize in the early stage. Integrate multiple independent evaluation results (such as electrical performance, thermal expansion, defect identification, etc.) into one to provide comprehensive test results. It can evaluate the overall performance of the circuit board from multiple dimensions to ensure that it can meet the design requirements under various working conditions. The multi-dimensional comprehensive test results can help engineers accurately predict the performance of the circuit board under different environments and working states, thus providing strong decision-making support for product design, production and optimization. This evaluation module helps to timely detect potential problems in multiple aspects of the circuit board and provides specific optimization suggestions to ensure the quality, stability and reliability of the final product.

[0041] Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the application document are intended to be included in the present invention.

[0042] As described above are only the specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for testing a flexible circuit board, characterized in that: The following steps are involved: Step S1: obtaining a high-definition detection image of the flexible circuit board to be tested; performing detail sharpening and enhancement processing on the high-definition detection image, and performing visual visualization processing of welding defects to generate visual feature data of welding defects; Step S2: performing three-dimensional structural topological modeling on the high-definition detection image, and performing dynamic mapping rendering according to the welding defect visual feature data to construct a three-dimensional defect rendering model; Step S3: Obtaining the operation monitoring log of the flexible circuit board to be tested; Perform multi-scenario operation simulation based on the operation monitoring log to obtain simulated monitoring data under different temperature scenarios; Step S4: identifying abnormal thermal expansion of the circuit board in each scenario for the simulated monitoring data under different temperature scenarios, and evaluating the abnormal temperature distribution in the operating state to generate an abnormal thermal expansion temperature simulation evaluation report; Step S5: Calculate the electrical performance of the circuit board based on the simulated monitoring data under different temperature scenarios to obtain the operating electrical performance; Step S6: Perform multi-dimensional circuit board test evaluation according to the operating electrical performance, abnormal thermal expansion temperature simulation evaluation report and three-dimensional defect rendering model to obtain multi-dimensional test results.

2. The flexible circuit board testing method according to claim 1, characterized in that: The specific steps of step S1 are: Step S11: Performing omnidirectional image scanning processing on the flexible circuit board to be tested to obtain a high-definition detection image of the flexible circuit board to be tested; Step S12: performing detail sharpening and enhancement processing on the high-definition detection image to obtain a sharpened balanced circuit board image; Step S13: performing deep surface texture recognition on the sharpened and balanced circuit board image to extract circuit board surface texture data; Step S14: monitoring the distortion texture of the circuit board surface texture data and marking the surface distortion texture; Step S15: performing a quantitative analysis of the surface defect morphology on the surface distortion texture to generate surface defect morphology data; Step S16: Perform welding defect visual visualization processing on the surface defect morphology data to generate welding defect visual feature data.

3. The flexible circuit board testing method according to claim 2, characterized in that: The specific steps of step S12 are: Perform image segmentation of equal-sized areas on the high-definition detection image to obtain multiple equal-sized sub-images; Calculate the average brightness of each sub-image of a plurality of equal-sized sub-images one by one to generate an average brightness value of each sub-image of the region; Based on adaptive local histogram equalization, sub-image brightness difference analysis is performed to extract brightness difference features of different regions; Adaptive local histogram equalization is performed according to the brightness difference characteristics of different regions to generate an adaptive brightness enhanced detection image; Perform visual recognition of image details on the adaptive brightness enhancement detection image to extract the surface details of the circuit board; Perform detail sharpening processing on the surface details of the circuit board to generate a detail sharpening detection image; The oversharpening balance is performed on the detail sharpening detection image to obtain a sharpening balanced circuit board image.

4. The flexible circuit board testing method according to claim 1, characterized in that: The specific steps of step S2 are: Step S21: performing circuit board component recognition on the sharpened balanced circuit board image, and marking a plurality of circuit board component nodes; Step S22: performing on-board position location calculations on multiple circuit board component nodes to generate position coordinates of each component node; Step S23: performing component geometric size and morphology analysis on multiple circuit board component nodes to generate geometric size and morphology parameters of each component; Step S24: Calculate the position coordinates of each component node according to the geometric size and shape parameters of each component to perform three-dimensional structural topology modeling, thereby generating a three-dimensional structural topology model of the circuit board; Step S25: dynamically render the three-dimensional structural topology model of the circuit board based on the welding defect visual feature data to construct a three-dimensional defect rendering model.

5. The flexible circuit board testing method according to claim 4, characterized in that: The specific steps of step S25 are: Obtain the actual material properties of the flexible circuit board to be tested; Analyze the optical properties of the circuit board according to the actual material properties to obtain the surface optical properties; According to the surface optical properties, the visual feature data of the welding defect is subjected to light irradiation tracking of the defect area to obtain the light path tracking data of the defect area; Calculate the optimal light rendering parameters based on the light path tracing data of the defect area, thereby generating the optimal light rendering parameters; Perform high-fidelity visual rendering fitting based on the optimal light rendering parameters to generate high-fidelity visual rendering maps; The 3D structural topology model of the circuit board is optimized by using high-fidelity visual rendering textures to construct a 3D defect rendering model.

6. The method for testing a flexible circuit board according to claim 1, characterized in that: The specific steps of step S3 are: Step S31: obtaining an operation monitoring log of the flexible circuit board to be tested; extracting multi-dimensional operation state parameters based on the operation monitoring log; Step S32: performing multi-operation scenario perception according to the multi-dimensional operation state parameters to obtain operation scenarios of multiple circuit boards; Step S33: simulating the operating temperature of the operating scenarios of the multiple circuit boards one by one to generate different simulated operating scenario temperature parameters; Step S34: Based on different simulated working scene temperature parameters, multi-scenario operation simulation is performed on the flexible circuit board to be tested, and real-time working temperature monitoring and high-frequency electromagnetic detection are performed to obtain simulated monitoring data under different temperature scenes.

7. The flexible circuit board testing method according to claim 1, characterized in that: The specific steps of step S4 are: Step S41: identifying abnormal thermal expansion of the circuit board in each scenario for the simulated monitoring data under different temperature scenarios, and extracting the simulated monitoring data of the abnormal thermal expansion scenario; Step S42: performing temperature distribution analysis on the abnormal thermal expansion scenario simulation monitoring data to generate temperature distribution data; Step S43: performing multi-time point temperature fluctuation mining according to the temperature distribution data, thereby obtaining a time series temperature distribution fluctuation field; Step S44: performing temperature mutation area detection based on the time-series temperature distribution fluctuation field, and then performing area division to obtain temperature mutation areas; Step S45: Calculate the regional temperature change gradient for the temperature mutation area to generate the regional temperature change gradient feature; Step S46: performing temperature distribution imbalance evolution on the regional temperature gradient characteristics to generate temperature distribution imbalance evolution data; Step S47: Performing an operational temperature distribution anomaly assessment on the temperature distribution imbalance evolution data to generate an abnormal thermal expansion temperature simulation assessment report.

8. The flexible circuit board testing method according to claim 1, characterized in that: The specific steps of step S5 are: Step S51: extracting high-frequency electromagnetic detection data based on simulated monitoring data under different temperature scenarios; Step S52: Calculating the current signal of each component based on the high-frequency electromagnetic detection data; Step S53: calculating the current intensity of the current signal of each component; Step S54: calculating the current intensity deviation between components based on the current intensity to obtain the current intensity deviation value between components; Step S55: performing current signal interference analysis on the current intensity of the current signal of each component to generate current signal interference data; Step S56: Calculate the electrical performance of the circuit board based on the current signal interference data and the current intensity deviation value between components to obtain the operating electrical performance.

9. The flexible circuit board testing method according to claim 1, characterized in that: The specific steps of step S6 are: Step S61: Perform comprehensive electrical status diagnosis according to the operating state electrical performance to generate comprehensive electrical status diagnosis data; Step S62: performing circuit fault prediction on the comprehensive electrical status diagnosis data to generate circuit board circuit fault prediction data; Step S63: performing electrical reliability analysis according to the circuit board circuit fault prediction data to obtain a circuit board electrical reliability report; Step S64: Perform multi-dimensional circuit board test evaluation based on the three-dimensional defect rendering model, the circuit board electrical reliability report and the abnormal thermal expansion temperature simulation evaluation report to obtain multi-dimensional test results.

10. A flexible circuit board testing system, characterized in that: Used to perform the flexible circuit board testing method as claimed in claim 1, comprising: The defect visual detection module is used to obtain a high-definition detection image of the flexible circuit board to be tested; perform detail sharpening and enhancement processing on the high-definition detection image, and perform visual visualization processing of welding defects to generate visual feature data of welding defects; A dynamic rendering module is used to perform three-dimensional structural topology modeling on the high-definition detection image and perform dynamic mapping rendering according to the welding defect visual feature data to construct a three-dimensional defect rendering model; A multi-scenario operation analysis module is used to obtain the operation monitoring log of the flexible circuit board to be tested; based on the operation monitoring log, a multi-scenario operation simulation is performed to obtain simulated monitoring data under different temperature scenarios; The thermal expansion assessment module is used to identify abnormal thermal expansion of the circuit board in each scenario based on the simulated monitoring data under different temperature scenarios, and to conduct abnormal evaluation of the operating temperature distribution to generate an abnormal thermal expansion temperature simulation evaluation report; The electrical performance evaluation module is used to calculate the electrical performance of the circuit board based on the simulated monitoring data under different temperature scenarios to obtain the operating electrical performance; The multi-dimensional test evaluation module is used to perform multi-dimensional circuit board test evaluation based on the operating electrical performance, abnormal thermal expansion temperature simulation evaluation report and three-dimensional defect rendering model to obtain multi-dimensional test results.

Images