Power battery busbar welding quality detection device and method

Abstract

The invention belongs to the technical field of welding quality detection, and discloses a power battery busbar welding quality detection device and method, and the device comprises an image collection module, an image enhancement module, a main control module, an identification module, an intelligent analysis module, a feedback adjustment module, a data management module, and a display module. According to the method, deep learning and machine learning algorithms are introduced, and the welding quality is intelligently analyzed. The algorithms can automatically identify and classify defects, and improve the accuracy and efficiency of detection. A rapid image processing technology is adopted, real-time detection and feedback are achieved, problems in the welding process can be found in time, and welding parameters are adjusted. And a plurality of cameras are arranged to carry out omnibearing detection from different angles, so that all surfaces and welding spots of the busbar are comprehensively evaluated, and the risk of missing detection is reduced. A machine vision system and welding equipment are integrated to form a closed-loop control system, and welding parameters are automatically adjusted to optimize the welding quality.

Description

Technical Field

[0001] The present invention belongs to the technical field of welding quality detection, and in particular relates to a device and method for detecting the welding quality of a power battery busbar. Background Art

[0002] Driven by my country's energy conservation and emission reduction efforts, electric vehicle production in the country has increased annually. As a crucial component of electric vehicles, the quality of power batteries directly impacts their operational safety. Therefore, quality testing of power batteries is an essential step in the automotive manufacturing process.

[0003] As an important component of power batteries, the quality inspection of busbars mainly focuses on the length, width and height of welds, whether there are broken welds, whether the weld position is deviated, whether there are breakdown holes or pits in the welds, and whether the gap between the busbar and the pole meets the standards.

[0004] Through the above analysis, the problems and defects of the existing technology are as follows:

[0005] Traditional manual inspection or single-use testing equipment often requires a long time to perform each inspection, impacting production efficiency. Manual inspection is susceptible to subjective factors of the operator, which may lead to missed inspections or misjudgments, making it difficult to ensure consistent inspection results. Summary of the Invention

[0006] In response to the problems existing in the prior art, the present invention provides a device and method for detecting the welding quality of a power battery busbar.

[0007] The present invention is implemented as follows: a power battery busbar welding quality detection device includes:

[0008] Image acquisition module, image enhancement module, main control module, recognition module, intelligent analysis module, feedback adjustment module, data management module, display module;

[0009] An image acquisition module, connected to the image enhancement module, is used to acquire welding images through a 2D camera and a 3D camera;

[0010] The image enhancement module is connected to the image acquisition module and the main control module and is used to enhance the acquired image;

[0011] The main control module is connected with the image enhancement module, recognition module, intelligent analysis module, feedback adjustment module, data management module, and display module to control the normal operation of each module;

[0012] The recognition module is connected to the main control module and is used to automatically identify and classify welding defects based on the image data collected by the 2D camera and the 3D camera;

[0013] Intelligent analysis module, connected to the main control module, for real-time processing and analysis of the collected image data.

[0014] Feedback regulation module, connected to the main control module, for real-time detection and feedback; when problems are found during the welding process, adjustment signals are sent to the welding equipment in a timely manner to adjust the welding parameters.

[0015] Data management module, connected to the main control module, for managing the detection data.

[0016] Display module, connected to the main control module, for displaying the collected images, recognition results, analysis results, and feedback information.

[0017] Furthermore, the image acquisition module:

[0018] 2D camera and accessories: Select one 2D camera, equipped with a light source and a lens, and installed perpendicular to the product; the 2D camera takes pictures at the left and right welds respectively, for detecting broken welds, the width of the welds, and unwelded defects.

[0019] 3D camera: Equip one 3D camera, for scanning the entire welding surface during movement, collecting the height information of the measured object, and performing height item detection.

[0020] Multi-angle cameras: Set up multiple cameras to conduct all-round detection from different angles to ensure a comprehensive evaluation of each surface and solder joints of the busbar.

[0021] Furthermore, the method of the image enhancement module:

[0022] 1) Change the gray value range of the image through a linear function to expand the contrast of the image.

[0023] Let the gray value of the original image be f(x, y), and the gray value after transformation be g(x, y).

[0024] The linear gray transformation formula is g(x, y) = a × f(x, y) + b.

[0025] Where a is the slope, controlling the contrast; b is the intercept, controlling the brightness; when a > 1, the contrast is enhanced; when 0 < a < 1, the contrast is reduced.

[0026] 2) Use the logarithmic function to expand the contrast of the low gray value area and compress the contrast of the high gray value area.

[0027] g(x, y) = c × log(1 + f(x, y)), where c is a constant, used to adjust the gray range after transformation.

[0028] 3) Contrary to the logarithmic transformation, expand the contrast of the high gray value area and compress the contrast of the low gray value area; g(x, y) = bc ×[f(x,y) / a] c -1, b is used to adjust the grayscale range, and c controls the steepness of the transformation;

[0029] 4) By adjusting the grayscale histogram of the image to make it evenly distributed, the contrast of the image is enhanced;

[0030] Calculate the grayscale probability distribution of the original image where r k is the kth gray level, n k is the gray level r k The number of pixels, N is the total number of pixels in the image;

[0031] Calculate the cumulative distribution function

[0032] Map the grayscale value rk of the original image to the new grayscale value s k ×(L-1), where L is the number of gray levels.

[0033] Furthermore, the identification module method:

[0034] (1) Separate the welding area from the background;

[0035] (2) Feature extraction;

[0036] (3) Feature recognition.

[0037] Further, the welding area is separated from the background;

[0038] For 2D images, a threshold segmentation method is used, such as the Otsu algorithm; the Otsu algorithm determines the optimal threshold t by maximizing the inter-class variance, the inter-class variance The calculation formula is:

[0039]

[0040] Among them, w0(t) and w1(t) are the pixel ratios of foreground and background, μ0(t) and μ1(t) are the average grayscale values of foreground and background respectively;

[0041] For 3D point cloud data, the region growing algorithm is used to segment the data based on the curvature and normal vector features of the points.

[0042] Furthermore, the feature extraction:

[0043] 2D image features

[0044] Texture features: Texture features are extracted using the gray-level co-occurrence matrix; the calculation formula for contrast CON is:

[0045]

[0046] Among them, N g is the number of gray levels, P(i, j) is the probability of occurrence of the gray level pair (i, j) in the gray level co-occurrence matrix;

[0047] Shape features: Extract the contour of the welding defect and calculate the perimeter, area, and circularity shape features; the calculation formula for circularity C is:

[0048]

[0049] Where A is the area of the region and P is the perimeter of the region.

[0050] Another object of the present invention is to provide a method for detecting the welding quality of a power battery busbar, comprising:

[0051] Step 1: Using a 2D camera and a 3D camera to acquire welding images through an image acquisition module; and performing enhancement processing on the acquired images through an image enhancement module;

[0052] Step 2: The main control module automatically identifies and classifies welding defects based on the image data collected by the 2D camera and the 3D camera through the recognition module;

[0053] Step 3: The collected image data is processed and analyzed in real time through the intelligent analysis module.

[0054] Step 4: Real-time detection and feedback are performed through the feedback adjustment module; when problems are found in the welding process, adjustment signals are sent to the welding equipment to adjust the welding parameters;

[0055] Step 5: Manage the detection data through the data management module; display the collected images, recognition results, analysis results, and feedback information through the display module.

[0056] Another object of the present invention is to provide a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the power battery busbar welding quality detection method.

[0057] Another object of the present invention is to provide a computer-readable storage medium storing a computer program, which, when executed by a processor, enables the processor to perform the steps of the power battery busbar welding quality detection method.

[0058] Another object of the present invention is to provide an information data processing terminal, which is used to implement the power battery busbar welding quality detection device.

[0059] In combination with the above technical solutions and the technical problems solved, please analyze the advantages and positive effects of the technical solutions to be protected by the present invention from the following aspects:

[0060] First, in view of the technical problems existing in the above-mentioned prior art and the difficulty of solving these problems, this paper closely combines the technical solutions to be protected by the present invention and the results and data during the research and development process, and analyzes in detail and in depth how the technical solutions of the present invention solve the technical problems and some creative technical effects brought about by solving the problems. The specific description is as follows:

[0061] Deep learning and machine learning algorithms are introduced to intelligently analyze welding quality. These algorithms can automatically identify and classify defects, improving the accuracy and efficiency of inspections.

[0062] The use of fast image processing technology can achieve real-time detection and feedback, which can promptly detect problems in the welding process and adjust the welding parameters.

[0063] Multiple cameras are set up to conduct all-round inspections from different angles to ensure a comprehensive assessment of every surface and solder point of the busbar, reducing the risk of missed inspections.

[0064] Integrate the machine vision system with the welding equipment to form a closed-loop control system to automatically adjust welding parameters to optimize welding quality.

[0065] Establish a complete data management system to automatically record inspection results and defect types, conduct data analysis and trend forecasting, and provide decision support for subsequent production.

[0066] The flexible design of the inspection system can adapt to different types of busbars and welding processes, ensuring effectiveness under different production conditions.

[0067] 1. Improve detection accuracy

[0068] Machine vision systems can accurately identify welding defects such as pores, cracks, and incomplete penetration, ensuring that welding quality meets standards.

[0069] 2. Real-time monitoring and feedback

[0070] The system can monitor the welding process in real time, detect and feedback problems in a timely manner, facilitate immediate adjustment of welding parameters, and reduce the production of unqualified products.

[0071] 3. High degree of automation

[0072] Automated inspection reduces manual intervention, reduces human errors, improves production efficiency, and frees up workers to focus on more complex tasks.

[0073] 4. Data Recording and Analysis

[0074] The system can record test data, conduct analysis and statistics, and help enterprises understand potential quality problems in the production process and optimize production processes.

[0075] 6. Reduce costs

[0076] By improving inspection efficiency and accuracy, rework and scrap caused by quality issues are reduced, lowering overall production costs.

[0077] Second, as auxiliary evidence for the inventiveness of the claims of the present invention, it is also reflected in the following important aspects:

[0078] (1) The expected benefits and commercial value of the technical solution of the present invention after transformation are:

[0079] (2) The technical solution of the present invention fills the technical gap in the industry at home and abroad:

[0080] (3) Whether the technical solution of the present invention solves the technical problems that people have been eager to solve but have not been able to solve successfully:

[0081] (4) Whether the technical solution of the present invention overcomes technical prejudice: BRIEF DESCRIPTION OF THE DRAWINGS

[0082] Figure 1 This is a structural block diagram of a power battery busbar welding quality detection device provided by an embodiment of the present invention.

[0083] Figure 2 This is a flow chart of the image enhancement module method provided by an embodiment of the present invention.

[0084] Figure 3 This is a flow chart of a method for detecting welding quality of a power battery busbar provided by an embodiment of the present invention.

[0085] Figure 1 In: 1. Image acquisition module; 2. Image enhancement module; 3. Main control module; 4. Recognition module; 5. Intelligent analysis module; 6. Feedback adjustment module; 7. Data management module; 8. Display module. DETAILED DESCRIPTION

[0086] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0087] like Figure 1 As shown, an embodiment of the present invention provides a power battery busbar welding quality detection device comprising:

[0088] Image acquisition module 1, image enhancement module 2, main control module 3, recognition module 4, intelligent analysis module 5, feedback adjustment module 6, data management module 7, display module 8.

[0089] Image acquisition module 1, connected to image enhancement module 2, for acquiring welding images through 2D camera and 3D camera;

[0090] The image enhancement module 2 is connected to the image acquisition module 1 and the main control module 3 and is used to enhance the acquired image;

[0091] The main control module 3 is connected to the image enhancement module 2, the recognition module 4, the intelligent analysis module 5, the feedback adjustment module 6, the data management module 7, and the display module 8, and is used to control the normal operation of each module;

[0092] Identification module 4, connected to main control module 3, for automatically identifying and classifying welding defects based on image data collected by 2D camera and 3D camera;

[0093] The intelligent analysis module 5 is connected to the main control module 3 and is used to process and analyze the collected image data in real time.

[0094] The feedback adjustment module 6 is connected to the main control module 3 and is used for real-time detection and feedback. When a problem is found in the welding process, an adjustment signal is sent to the welding equipment to adjust the welding parameters.

[0095] The data management module 7 is connected to the main control module 3 and is used to manage the detection data;

[0096] The display module 8 is connected to the main control module 3 and is used to display the collected images, recognition results, analysis results, and feedback information.

[0097] The image acquisition module provided by the embodiment of the present invention:

[0098] 2D camera and accessories: A 2D camera equipped with a light source and lens is installed perpendicular to the product. The 2D camera takes pictures at both the left and right welds to detect broken welds, weld width, and unwelded defects.

[0099] 3D camera: equipped with a 3D camera to scan the entire welding surface during movement, collect the height information of the object being measured, and perform height detection;

[0100] Multi-angle cameras: Multiple cameras are set up to conduct all-round inspections from different angles to ensure a comprehensive assessment of every surface and solder joint of the busbar.

[0101] like Figure 2 As shown, the image enhancement module method provided by the embodiment of the present invention:

[0102] S101. Change the grayscale value range of the image through a linear function to expand the contrast of the image;

[0103] Let the grayscale value of the original image be f(x, y), and the grayscale value after transformation be g(x, y);

[0104] The linear grayscale transformation formula is g(x, y) = a × f(x, y) + b;

[0105] Where a is the slope, controlling the contrast; b is the intercept, controlling the brightness; when a > 1, the contrast is enhanced; when 0 < a < 1, the contrast is reduced;

[0106] S102. Use the logarithmic function to expand the contrast of the low grayscale value area and compress the contrast of the high grayscale value area;

[0107] g(x, y) = c × log(1 + f(x, y)), where c is a constant used to adjust the grayscale range after transformation;

[0108] S103. Contrary to the logarithmic transformation, expand the contrast of the high grayscale value area and compress the contrast of the low grayscale value area;

[0109] g(x, y) = b c × [f(x, y) / a] c -1, b is used to adjust the grayscale range, and c controls the steepness of the transformation;

[0110] S104. Enhance the contrast of the image by adjusting the grayscale histogram of the image to make it evenly distributed;

[0111] Calculate the grayscale probability distribution of the original image Where r k is the k-th grayscale level, n k is the number of pixels of the grayscale level r k and N is the total number of pixels of the image;

[0112] Calculate the cumulative distribution function

[0113] Map the grayscale value rk of the original image to the new grayscale value s k × (L - 1), where L is the number of grayscale levels.

[0114] The recognition module method provided by the embodiments of the present invention:

[0115] (1) Separate the welding area from the background;

[0116] (2) Feature extraction;

[0117] (

[0118] The embodiment of the present invention provides separation of the welding area from the background;

[0119] For 2D images, a threshold segmentation method is used, such as the Otsu algorithm; the Otsu algorithm determines the optimal threshold t by maximizing the inter-class variance, the inter-class variance The calculation formula is:

[0120]

[0121] Among them, w0(t) and w1(t) are the pixel ratios of foreground and background, μ0(t) and μ1(t) are the average grayscale values of foreground and background respectively;

[0122] For 3D point cloud data, the region growing algorithm is used to segment the data based on the curvature and normal vector features of the points.

[0123] The feature extraction provided by the embodiment of the present invention:

[0124] 2D image features

[0125] Texture features: Texture features are extracted using the gray-level co-occurrence matrix; the calculation formula for contrast CON is:

[0126]

[0127] Among them, N g is the number of gray levels, P(i,j) is the probability of occurrence of the gray level pair (i,j) in the gray level co-occurrence matrix;

[0128] Shape features: Extract the contour of the welding defect and calculate the perimeter, area, and circularity shape features; the calculation formula for circularity C is:

[0129]

[0130] Where A is the area of the region and P is the perimeter of the region.

[0131] like Figure 3 As shown, a method for detecting the welding quality of a power battery busbar provided by an embodiment of the present invention includes:

[0132] S201, using a 2D camera and a 3D camera to acquire welding images through an image acquisition module; and performing enhancement processing on the acquired images through an image enhancement module;

[0133] S202, automatically identifying and classifying welding defects from image data collected by the 2D camera and the 3D camera through the recognition module of the main control module;

[0134] S203, the collected image data is processed and analyzed in real time by the intelligent analysis module.

[0135] S204, real-time detection and feedback through the feedback adjustment module; when problems are found in the welding process, an adjustment signal is sent to the welding equipment to adjust the welding parameters;

[0136] S205, managing the detection data through the data management module; displaying the collected images, recognition results, analysis results, and feedback information through the display module.

[0137] Another object of the present invention is to provide a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the power battery busbar welding quality detection method.

[0138] Another object of the present invention is to provide a computer-readable storage medium storing a computer program, which, when executed by a processor, enables the processor to perform the steps of the power battery busbar welding quality detection method.

[0139] Another object of the present invention is to provide an information data processing terminal, which is used to implement the power battery busbar welding quality detection device.

[0140] It should be noted that the embodiments of the present invention can be implemented by hardware, software, or a combination of software and hardware. The hardware portion can be implemented using dedicated logic; the software portion can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated design hardware. Those skilled in the art will appreciate that the above-mentioned devices and methods can be implemented using computer-executable instructions and / or contained in processor control code, for example, such as a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The devices and modules of the present invention can be implemented by hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., can also be implemented by software executed by various types of processors, or can be implemented by a combination of the above-mentioned hardware circuits and software, such as firmware.

[0141] The above description is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications, equivalent substitutions and improvements made by any technician familiar with this technical field within the technical scope disclosed by the present invention and within the spirit and principles of the present invention should be covered by the scope of protection of the present invention.

Claims

1. A power battery busbar welding quality detection device, characterized in that: Including: An image acquisition module, connected to the image enhancement module, for acquiring welding images through a 2D camera and a 3D camera; An image enhancement module, connected to the image acquisition module and the main control module, for enhancing the acquired images; A main control module, connected to the image enhancement module, the recognition module, the intelligent analysis module, the feedback adjustment module, the data management module, and the display module, for controlling the normal operation of each module; A recognition module, connected to the main control module, for automatically recognizing and classifying welding defects in the image data acquired by the 2D camera and the 3D camera; An intelligent analysis module, connected to the main control module, for real-time processing and analysis of the acquired image data, A feedback adjustment module, connected to the main control module, for real-time detection and feedback; when problems are found during the welding process, an adjustment signal is sent to the welding equipment to adjust the welding parameters; A data management module, connected to the main control module, for managing the detection data; A display module, connected to the main control module, for displaying the acquired images, recognition results, analysis results, and feedback information.

2. The power battery busbar welding quality inspection device according to claim 1, characterized in that: The image acquisition module: 2D camera and accessories: Select one 2D camera, equipped with a light source and a lens, and installed perpendicular to the product; the 2D camera takes pictures once at the left and right welds respectively, for detecting broken welds, the width of the weld, and unwelded defects; 3D camera: Equip one 3D camera, for scanning the entire welding surface during movement, acquiring the height information of the measured object, and performing height item detection; Multi-angle cameras: Set up multiple cameras to conduct all-round detection from different angles to ensure a comprehensive evaluation of each surface and solder joints of the busbar.

3. The power battery busbar welding quality inspection device according to claim 1, characterized in that: The method of the image enhancement module: 1) Change the gray value range of the image through a linear function to expand the contrast of the image; Let the gray value of the original image be f(x, y), and the gray value after transformation be g(x, y); The linear gray transformation formula is g(x, y) = a × f(x, y) + b; Where a is the slope, controlling the contrast; b is the intercept, controlling the brightness; when a > 1, the contrast is enhanced; when 0 < a < 1, the contrast is reduced; 2) Use the logarithmic function to expand the contrast of the low gray value area and compress the contrast of the high gray value area; g(x, y) = c × log(1 + f(x, y)), where c is a constant, used to adjust the gray range after transformation; 3) Opposite to the logarithmic transformation, expand the contrast of the high gray value area and compress the contrast of the low gray value area; g(x,y)=b c ×[f(x,y) / a] c -1b is used to adjust the grayscale range, and c controls the steepness of the transformation; 4) Enhance the contrast of the image by adjusting the gray histogram of the image to make it evenly distributed; Calculate the grayscale probability distribution of the original image where r k is the kth gray level, n k is the gray level r k The number of pixels, N is the total number of pixels in the image; Calculate the cumulative distribution function Map the grayscale value rk of the original image to the new grayscale value s k ×(L-1), where L is the number of gray levels.

4. The power battery busbar welding quality inspection device according to claim 1, characterized in that: The method of the recognition module: (1) Separate the welding area from the background; (2) Feature extraction; (3) Feature recognition.

5. The power battery busbar welding quality inspection device according to claim 4, characterized in that: The separation of the welding area from the background; For 2D images, a threshold segmentation method is used, such as the Otsu algorithm; the Otsu algorithm determines the optimal threshold t by maximizing the inter-class variance, the inter-class variance The calculation formula is: Among them, w0(t) and w1(t) are the pixel ratios of the foreground and the background respectively, and μ0(t) and μ1(t) are the average gray values of the foreground and the background respectively; For 3D point cloud data, use the region growing algorithm to segment according to the curvature and normal vector features of the points.

6. The power battery busbar welding quality inspection device according to claim 4, characterized in that: The feature extraction: 2D image features Texture features: Use the gray level co-occurrence matrix to extract texture features; the calculation formula of the contrast CON is: Among them, N g is the number of gray levels, P(i,j) is the probability of occurrence of the gray level pair (i,j) in the gray level co-occurrence matrix; Shape features: Extract the contour of the welding defect and calculate the perimeter, area, and circularity shape features; the calculation formula for circularity C is: Where A is the area of the region and P is the perimeter of the region.

7. A method for detecting the welding quality of a power battery busbar using the device for detecting the welding quality of a power battery busbar according to any one of claims 1 to 6, characterized in that: The power battery busbar welding quality detection method includes: Step 1: Using a 2D camera and a 3D camera to acquire welding images through an image acquisition module; and performing enhancement processing on the acquired images through an image enhancement module; Step 2: The main control module automatically identifies and classifies welding defects based on the image data collected by the 2D camera and the 3D camera through the recognition module; Step 3: The collected image data is processed and analyzed in real time through the intelligent analysis module. Step 4: Real-time detection and feedback are performed through the feedback adjustment module; when problems are found in the welding process, adjustment signals are sent to the welding equipment to adjust the welding parameters; Step 5: Manage the detection data through the data management module; display the collected images, recognition results, analysis results, and feedback information through the display module.

8. A computer device, characterized in that: The computer device includes a memory and a processor, the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of the power battery busbar welding quality detection method as claimed in claim 7.

9. A computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor executes the steps of the power battery busbar welding quality inspection method according to claim 7.

10. An information data processing terminal, characterized in that: The information data processing terminal is used to implement the power battery busbar welding quality detection device as described in any one of claims 1-6.

Images