Welding defect detection method and system and storage medium

Abstract

The invention provides a welding defect detection method and system and a storage medium, and the method comprises the steps: obtaining a bonding pad welding detection region based on a first battery image of a to-be-detected battery obtained by a lower camera, and obtaining a weld penetration detection result based on the bonding pad welding detection region; obtaining a second battery image of the battery to be detected through the upper camera, and obtaining a welding spot detection result and a welding deviation detection result according to the bonding pad welding detection area and the second battery image; and obtaining a third battery image of the battery to be detected through the lower camera, and obtaining a point explosion detection result and a welding slag detection result according to the second battery image and the third battery image. According to the method, the images shot by different cameras are effectively associated and integrated, so that the detection result is more accurate and reliable; by reasonably arranging the shooting sequence and the detection process of the camera, detection of multiple welding defects can be completed in one detection process at the same time, the tedious process of multiple independent detection is avoided, the detection efficiency is improved, and the requirement for large-scale production is met.

Description

Technical Field

[0001] The present application relates to the technical field of battery detection, and in particular to a welding defect detection method, system and storage medium. Background Art

[0002] The quality of the weld between the battery tab and the pad plays a crucial role in the battery assembly process. This welding step directly determines whether the battery can achieve smooth connection with the external circuit. If welding problems occur, such as weld deviation, spotting, or weld penetration, the battery will not be able to properly supply power to the external circuit, seriously affecting its normal use. Therefore, it is necessary to accurately inspect the welding condition of the battery tab and pad.

[0003] Currently, the conventional inspection method involves using a camera to capture a single image of the weld. This method is relatively simple to operate and can detect some obvious weld defects to a certain extent. However, it has significant limitations. A single image can only provide limited information, making it difficult to fully reflect the actual condition of the weld. It can easily miss hidden or subtle defects, making it impossible to guarantee the accuracy and reliability of the inspection results, hindering the efficient control of battery weld quality. Summary of the Invention

[0004] In order to solve the above technical problems, the present application provides a welding defect detection method, system and storage medium.

[0005] Specifically, the present application provides a welding defect detection method, in which an upper camera and a lower camera are coaxially mounted on the upper and lower sides of a battery to be inspected. The welding defect detection method includes: A first battery image of the battery to be inspected is acquired through the lower camera, and a pad welding inspection area is acquired based on the first battery image, so as to obtain a weld penetration inspection result based on the pad welding inspection area; a second battery image of the battery to be inspected is acquired through the upper camera, and a weld spot inspection result and a weld deviation inspection result are obtained based on the pad welding inspection area and the second battery image; a third battery image of the battery to be inspected is acquired through the lower camera, and a spot explosion inspection result and a weld slag inspection result are obtained based on the second battery image and the third battery image.

[0006] In the above technical solution, the images taken by different cameras are effectively associated and integrated, making the detection results more accurate and reliable; by reasonably arranging the camera shooting sequence and detection process, multiple welding defects can be detected simultaneously during a single inspection process, avoiding the tedious process of multiple independent inspections, improving detection efficiency, and being suitable for the needs of large-scale production.

[0007] Furthermore, obtaining the pad welding detection area includes: obtaining the first battery image by backlighting the lower camera, and performing a first morphological analysis based on the first battery image to obtain the pad area and the tab area; and using the intersection area of ​​the pad area and the tab area as the pad welding detection area.

[0008] In the above technical solution, backlighting can significantly enhance the contrast of pads and tabs in the image, making their edges clearer. This area recognition method based on morphological analysis can accurately focus on the actual welding position, reduce unnecessary interference, and improve the pertinence and accuracy of subsequent detection.

[0009] Furthermore, obtaining the solder penetration detection result includes: performing a second morphological analysis based on the pad soldering detection area to determine whether there are holes in the pad soldering detection area; if so, it is determined that the battery to be tested has a solder penetration defect; otherwise, it is determined that the battery to be tested has passed the solder penetration test.

[0010] In the above technical solution, by directly focusing on the key welding areas for specific morphological analysis, it is possible to quickly and accurately detect weld penetration, a defect that seriously affects battery performance and safety. This image morphology-based detection method is intuitive and effective, avoiding complex physical detection methods and improving detection efficiency.

[0011] Furthermore, the obtaining of the weld detection result includes: obtaining the second battery image by means of front lighting by the upper camera, and intercepting the second battery image based on the pad welding detection area to obtain a weld image; performing target detection according to the weld image to obtain the number of welds and weld coordinate position information; judging whether the number of welds is a preset threshold, and if so, determining that the weld detection of the battery to be detected is qualified; otherwise, determining that the battery to be detected has a weld defect.

[0012] In the above technical solution, the front light can highlight the characteristics of the solder joints, making them more obvious in the image; the specific area is intercepted and the target is detected through morphological analysis, which reduces the amount of image data and improves the speed and accuracy of detection; and the method of comparing the number of solder joints with the preset threshold is simple and direct, which can quickly determine whether the number of solder joints meets the requirements.

[0013] Furthermore, obtaining the welding deviation detection result includes: obtaining the welding boundary coordinate position information based on the welding pad welding detection area, and judging whether each welding point is welded deviation according to the welding boundary coordinate position information and the welding point coordinate position information; if so, it is judged that the battery to be tested has a welding deviation defect; otherwise, it is judged that the welding deviation detection of the battery to be tested is qualified.

[0014] In the above technical solution, by performing comparative analysis through precise coordinate position information, it is possible to accurately determine whether the weld is offset, and the detection accuracy is high; this method of obtaining coordinate information based on morphological analysis is not affected by other factors of the welding appearance, and can effectively identify tiny weld offset defects to ensure welding quality.

[0015] Furthermore, the step of obtaining the spot explosion detection result and the welding slag detection result based on the second battery image and the third battery image includes: obtaining the third battery image by means of front light from the lower camera, and obtaining the front welding image and the back welding image respectively based on the second battery image and the third battery image.

[0016] In the above technical solution, the upper and lower cameras are used to respectively obtain the second and third battery images, and then obtain the front and back welding images, which can fully display the conditions of the battery welding parts. The quality of battery welding depends not only on the welding effect of the front, but also on the welding status of the back. Comprehensive image information helps to discover various potential welding defects and avoid missed detection problems caused by a single viewing angle.

[0017] Furthermore, obtaining the spot explosion detection result includes: performing a third morphological analysis based on the front welding image to determine whether there is a spot explosion in the front welding image; if so, determining that the battery to be inspected has a spot explosion defect; otherwise, determining that the battery to be inspected has passed the spot explosion detection.

[0018] In the above technical solution, targeted morphological analysis is directly performed on the front welding image to quickly identify obvious welding defects such as cracking. This specialized morphological analysis method is intuitive and highly accurate, and can promptly detect cracking problems that affect the appearance and performance of the battery.

[0019] Furthermore, obtaining the welding slag detection result includes: performing a fourth morphological analysis based on the back welding image to determine whether there is welding slag in the back welding image; if so, it is determined that the battery to be tested has a welding slag defect; otherwise, it is determined that the welding slag detection of the battery to be tested is qualified.

[0020] In the above technical solution, a special morphological analysis of weld slag detection is performed on the back welding image, which can accurately detect weld slag, a potential defect that affects battery performance and stability. The targeted morphological analysis method can effectively identify the characteristics of weld slag in the image and improve the reliability of detection.

[0021] Furthermore, based on the same concept, the present application also provides a system adopting the welding defect detection method, which at least includes: a controller, used to control the upper camera and the lower camera and the corresponding light source to detect the battery to be inspected, and obtain a first battery image, a second battery image and a third battery image respectively; a host computer, used to obtain a pad welding detection area based on the first battery image, to obtain a weld penetration detection result based on the pad welding detection area, and also to obtain a weld point detection result and a weld deviation detection result according to the pad welding detection area and the second battery image, and also to obtain a spot explosion detection result and a weld slag detection result according to the second battery image and the third battery image.

[0022] In the above technical solution, the host computer can realize comprehensive detection of battery welding defects based on different image data. This multi-dimensional detection method can cover various defects that may occur in the battery welding process, greatly improving the accuracy and reliability of detection; and the entire detection process is automatically completed by the controller and the host computer without human intervention, reducing the impact of human factors on the detection results and improving the consistency and detectability of the detection.

[0023] Furthermore, based on the same concept, the present application also provides a storage medium, in which a computer program is stored, wherein the computer program is configured to execute the welding defect detection method when running.

[0024] Compared with the prior art, the present invention has the following advantages: This application obtains the pad welding detection area based on the first battery image of the battery to be tested acquired by the lower camera, and obtains the weld penetration detection result based on the pad welding detection area; obtains the second battery image of the battery to be tested by the upper camera, and obtains the solder joint detection result and the weld deviation detection result based on the pad welding detection area and the second battery image; obtains the third battery image of the battery to be tested by the lower camera, and obtains the spot explosion detection result and the welding slag detection result based on the second battery image and the third battery image. This application effectively associates and integrates the images taken by different cameras, making the detection results more accurate and reliable; by reasonably arranging the shooting sequence and detection process of the cameras, it can complete the detection of multiple welding defects simultaneously in a single detection process, avoiding the tedious process of multiple independent detections, improving the detection efficiency, and being suitable for the needs of large-scale production. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 This is a flow chart of the welding defect detection method described in this application.

[0026] Figure 2 This is a schematic diagram of the camera and light source arrangement described in this application.

[0027] Figure 3Schematic diagram of the pad area of ​​the battery to be tested described in this application.

[0028] Figure 4 Schematic diagram of the tab area of ​​the battery to be tested described in this application.

[0029] Figure 5 Schematic diagram of the pad welding inspection area of ​​the battery to be inspected as described in this application.

[0030] Figure 6 Schematic diagram of the welding penetration condition and normal condition of the battery to be tested described in this application.

[0031] Figure 7 This is a schematic diagram of the welding point image of the battery to be tested described in this application.

[0032] Figure 8 Schematic diagram of the welding deviation detection area of ​​the battery to be tested described in this application.

[0033] Figure 9 This is a schematic diagram of the explosion detection mark of the battery to be tested as described in this application.

[0034] Figure 10 This is a schematic diagram of the welding slag detection mark of the battery to be tested as described in this application.

[0035] Figure 11 This is a framework diagram of the welding defect detection system described in this application. DETAILED DESCRIPTION

[0036] The following is a further detailed description of a welding defect detection method, system and storage medium of the present application in conjunction with specific embodiments and drawings.

[0037] The present application provides a welding defect detection method, in which an upper camera and a lower camera are coaxially mounted on the upper and lower sides of a battery to be inspected. The welding defect detection method includes: A first battery image of the battery to be inspected is acquired through the lower camera, and a pad welding inspection area is acquired based on the first battery image, so as to obtain a weld penetration inspection result based on the pad welding inspection area; a second battery image of the battery to be inspected is acquired through the upper camera, and a weld spot inspection result and a weld deviation inspection result are obtained based on the pad welding inspection area and the second battery image; a third battery image of the battery to be inspected is acquired through the lower camera, and a spot explosion inspection result and a weld slag inspection result are obtained based on the second battery image and the third battery image.

[0038] In some embodiments, a light source is provided on the upper and lower sides of the battery production line, and a 2D camera of the same model is provided on both sides of the light source (see Figure 2); The battery to be inspected is conveyed on the production line. When the battery to be inspected reaches the inspection position where the camera is located, the lighting mode of the light source is controlled, and the upper and lower cameras are controlled to perform shooting. After obtaining the captured image, the inspection is carried out based on the corresponding inspection rules to determine whether the battery to be inspected has welding defects; the welding defects at least include weld penetration, abnormal number of welds, weld deviation, spot explosion and / or welding slag.

[0039] Among them, the two light sources can be controlled independently, and the upper camera, lower camera and corresponding light source are installed coaxially, so that the position of the welding area in the upper and lower images remains consistent; before implementing welding defect detection, the camera parameters (such as focal length, aperture, exposure time, etc.) need to be adjusted to ensure a clear image with appropriate contrast.

[0040] Furthermore, obtaining the pad welding detection area includes: obtaining the first battery image by backlighting the lower camera, and performing a first morphological analysis based on the first battery image to obtain the pad area and the tab area; and using the intersection area of ​​the pad area and the tab area as the pad welding detection area.

[0041] In some embodiments, when the battery to be inspected is transported to the inspection position, the controller of the production line triggers the lower camera to take a picture. At this time, the backlight source lights up to provide backlight for the lower camera, so that the pads and tabs can be clearly displayed in the image. The lower camera takes an image of the battery to be inspected (i.e., the first battery image) and transmits the first battery image to the image processing system in the upper computer to perform a first morphological analysis.

[0042] The first morphological analysis includes: pre-processing the first battery image, including at least grayscale conversion, filtering, threshold segmentation, etc.; then performing contour detection on the binary image obtained by threshold segmentation to find the contours of the objects in the image, and screening the contours of the pad area and the tab area based on the area, perimeter, shape and other characteristics of the contours, and marking the screened pad area and the tab area; further marking the marked pad area (such as Figure 3 as shown) and the tab area (as shown Figure 4 The overlap analysis is performed to find out their intersection area. The pixels of the two areas can be compared by image processing algorithm to determine the pixel position of the intersection part, and then the pad welding detection area (as shown) can be obtained. Figure 5 shown).

[0043] In the above technical solution, backlighting can significantly enhance the contrast of pads and tabs in the image, making their edges clearer. This area recognition method based on morphological analysis can accurately focus on the actual welding position, reduce unnecessary interference, and improve the pertinence and accuracy of subsequent detection.

[0044] Furthermore, obtaining the solder penetration detection result includes: performing a second morphological analysis based on the pad soldering detection area to determine whether there are holes in the pad soldering detection area; if so, it is determined that the battery to be tested has a solder penetration defect; otherwise, it is determined that the battery to be tested has passed the solder penetration test.

[0045] In some embodiments, see Figure 6 After determining the pad welding inspection area, further analysis is performed on the area. The grayscale value distribution, connectivity and other characteristics of the pixels in the area can be calculated to find possible hole features. For example, the grayscale value of the hole area is usually significantly lower than the surrounding normal welding area. Appropriate thresholds and rules are set to determine whether there are holes. If the grayscale value of a certain area is continuously fixed at the set threshold, and the area has certain shape and size characteristics (such as circle, ellipse, etc.), it is considered that there is a hole in the area, and the battery to be inspected is determined to have a welding through defect. At this time, the battery is marked as a welding through detection unqualified product, and relevant inspection information, such as the location and size of the hole, is recorded. If no hole is detected, the battery to be inspected is determined to have passed the welding through detection and is marked as a welding through detection qualified product.

[0046] In the above technical solution, by directly focusing on the key welding areas for specific morphological analysis, it is possible to quickly and accurately detect weld penetration, a defect that seriously affects battery performance and safety. This image morphology-based detection method is intuitive and effective, avoiding complex physical detection methods and improving detection efficiency.

[0047] Furthermore, the obtaining of the weld detection result includes: obtaining the second battery image by means of front lighting by the upper camera, and intercepting the second battery image based on the pad welding detection area to obtain a weld image; performing target detection according to the weld image to obtain the number of welds and weld coordinate position information; judging whether the number of welds is a preset threshold, and if so, determining that the weld detection of the battery to be detected is qualified; otherwise, determining that the battery to be detected has a weld defect.

[0048] In some embodiments, see Figure 7, use the upper camera to shoot the battery to be tested in a front-lighting manner to obtain a second battery image; according to the previously determined pad welding detection area, intercept the second battery image to obtain a solder joint image; further use the target detection algorithm to identify the solder joints in the solder joint image, and distinguish the solder joints from the background based on the shape, grayscale value and other features of the solder joints. After identifying the solder joints, count the number of solder joints and record the coordinate position information of each solder joint; if the number of detected solder joints is equal to the preset threshold, it is determined that the solder joint inspection of the battery to be tested is qualified, and the battery is marked as a qualified product for solder joint inspection; if the number of solder joints is not equal to the preset threshold (more or less than), it is determined that the battery to be tested has solder joint defects, and the battery is marked as an unqualified product for solder joint inspection, and the deviation of the number of solder joints is recorded.

[0049] In the above technical solution, the front light can highlight the characteristics of the solder joints, making them more obvious in the image; the specific area is intercepted and the target is detected through morphological analysis, which reduces the amount of image data and improves the speed and accuracy of detection; and the method of comparing the number of solder joints with the preset threshold is simple and direct, which can quickly determine whether the number of solder joints meets the requirements.

[0050] Furthermore, obtaining the welding deviation detection result includes: obtaining the welding boundary coordinate position information based on the welding pad welding detection area, and judging whether each welding point is welded deviation according to the welding boundary coordinate position information and the welding point coordinate position information; if so, it is judged that the battery to be tested has a welding deviation defect; otherwise, it is judged that the welding deviation detection of the battery to be tested is qualified.

[0051] In some embodiments, see Figure 8 Based on the previously determined pad welding detection area, the coordinate position information of the welding boundary is extracted through contour detection and other methods, and the coordinate position information of each solder point is compared with the coordinate position information of the welding boundary; the relative position relationship between the column coordinates of the solder point and the coordinates on the left and right sides of the pad welding detection area is calculated to determine whether the solder point exceeds the specified welding range; for example, by comparing whether the X coordinate value of the solder point, i.e., X3, falls within the range of X1 and X2, it can be determined whether the solder point is offset. If a solder point is detected to be offset, it is determined that the battery to be tested has a solder offset defect, and the battery is marked as a failed solder offset test product, and the position and deviation degree of the offset solder point are recorded; if the position deviation of all solder points is within the allowable range, the battery to be tested is determined to have passed the solder offset test, and the battery is marked as a qualified solder offset test product.

[0052] In the above technical solution, by performing comparative analysis through precise coordinate position information, it is possible to accurately determine whether the weld is offset, and the detection accuracy is high; this method of obtaining coordinate information based on morphological analysis is not affected by other factors of the welding appearance, and can effectively identify tiny weld offset defects to ensure welding quality.

[0053] Furthermore, the step of obtaining the spot explosion detection result and the welding slag detection result based on the second battery image and the third battery image includes: obtaining the third battery image by means of front light from the lower camera, and obtaining the front welding image and the back welding image respectively based on the second battery image and the third battery image.

[0054] In the above technical solution, the upper and lower cameras are used to respectively obtain the second and third battery images, and then obtain the front and back welding images, which can fully display the conditions of the battery welding parts. The quality of battery welding depends not only on the welding effect of the front, but also on the welding status of the back. Comprehensive image information helps to discover various potential welding defects and avoid missed detection problems caused by a single viewing angle.

[0055] Furthermore, obtaining the spot explosion detection result includes: performing a third morphological analysis based on the front welding image to determine whether there is a spot explosion in the front welding image; if so, determining that the battery to be inspected has a spot explosion defect; otherwise, determining that the battery to be inspected has passed the spot explosion detection.

[0056] In some embodiments, the front welding image is preprocessed, including grayscale conversion, filtering and denoising. In the preprocessed front welding image, spot explosions are usually manifested as areas with abnormally high brightness and irregular shapes. By setting a suitable brightness threshold, areas with brightness higher than the threshold are screened out. Connectivity analysis is then performed on the screened high-brightness areas to determine whether they meet the morphological characteristics of spot explosions. Spot explosion areas are generally relatively independent and have irregular boundaries. If a high-brightness area meets these characteristics, it is marked as a suspected spot explosion area (e.g., Figure 9 If a suspected spot-blow area is identified in the front welding image, the battery under test is determined to have a spot-blow defect. The location, size, and other information of the spot-blow area are recorded in detail for subsequent analysis and processing. If no area meeting the spot-blow characteristics is detected, the battery under test is determined to have passed the spot-blow test.

[0057] In the above technical solution, targeted morphological analysis is directly performed on the front welding image to quickly identify obvious welding defects such as cracking. This specialized morphological analysis method is intuitive and highly accurate, and can promptly detect cracking problems that affect the appearance and performance of the battery.

[0058] Furthermore, obtaining the welding slag detection result includes: performing a fourth morphological analysis based on the back welding image to determine whether there is welding slag in the back welding image; if so, it is determined that the battery to be tested has a welding slag defect; otherwise, it is determined that the welding slag detection of the battery to be tested is qualified.

[0059] In some embodiments, the back welding image is subjected to a similar preprocessing operation as the front welding image; welding slag in the back welding image is usually manifested as a grayscale value different from the surrounding normal welding area and has unique texture characteristics. By analyzing the grayscale distribution and texture information of the image, appropriate grayscale and texture thresholds are set to screen out areas where welding slag may exist; the screened areas are subjected to morphological feature analysis, such as area, perimeter, shape, etc. Among them, the welding slag area is generally small in area and irregular in shape, and these morphological features are used to further determine whether it is a welding slag area (such as Figure 10 If an area that meets the weld slag characteristics is identified in the back welding image, the battery to be tested is determined to have a weld slag defect, and information such as the location and size of the weld slag area is recorded so that appropriate treatment measures can be taken. If no weld slag area is detected, the battery to be tested is determined to have passed the weld slag inspection.

[0060] In the above technical solution, a special morphological analysis of weld slag detection is performed on the back welding image, which can accurately detect weld slag, a potential defect that affects battery performance and stability. The targeted morphological analysis method can effectively identify the characteristics of weld slag in the image and improve the reliability of detection.

[0061] It should also be noted that only when all the batteries to be tested are judged to be qualified in the above defect detection can they enter the next production / quality inspection process. If any defect detection is unqualified, the batteries to be tested will be judged as unqualified products and will flow into the rework process or scrap process according to the actual inspection conditions.

[0062] In summary, the above solution effectively correlates and integrates images captured by different cameras, making the inspection results more accurate and reliable. By rationally arranging the camera shooting sequence and inspection process, it can simultaneously complete the inspection of multiple welding defects during a single inspection process, avoiding the tedious process of multiple independent inspections, improving inspection efficiency, and being suitable for the needs of large-scale production.

[0063] Further, based on the same concept, see Figure 11 The present application also provides a system using the welding defect detection method, which at least includes: a controller, used to control the upper camera and the lower camera and the corresponding light source to detect the battery to be inspected, and obtain a first battery image, a second battery image and a third battery image respectively; a host computer, used to obtain a pad welding detection area based on the first battery image, to obtain a weld penetration detection result based on the pad welding detection area, and also to obtain a weld spot detection result and a weld deviation detection result based on the pad welding detection area and the second battery image, and also to obtain a spot explosion detection result and a weld slag detection result based on the second battery image and the third battery image.

[0064] In some embodiments, an upper camera, a lower camera, and corresponding light sources are installed at appropriate locations on the battery production line. The upper camera is used to capture images of the front of the battery, while the lower camera is used to capture images of the back of the battery. The light source provides stable and uniform illumination for the camera to ensure image quality. A controller adjusts the camera's focal length, aperture, exposure time, and other parameters, while also setting the light source's brightness, color, and other parameters to ensure that clear, contrast-appropriate images can be obtained in different production environments and battery types. It is usually also necessary to calibrate the system using standard battery samples to ensure the camera's shooting position and angle are accurate and that the light source's illumination effect is uniform and consistent.

[0065] Specifically, when the battery to be inspected is transported to the inspection position, the controller receives a trigger signal and immediately controls the upper camera, the lower camera and the corresponding light source to start working; the lower camera is backlit to obtain the first battery image, the upper camera is front-lit to obtain the second battery image, and the lower camera is front-lit again to obtain the third battery image; the controller transmits these images to the host computer for subsequent processing.

[0066] Acquisition of pad welding detection area: After receiving the first battery image, the host computer performs preprocessing on it, such as grayscale conversion, filtering and denoising, and then obtains the pad welding detection area through image analysis algorithms, such as edge detection and threshold segmentation.

[0067] Solder penetration detection: Based on the acquired solder pad inspection area, the host computer performs a secondary morphological analysis to determine whether there are holes in the area. If holes are present, the battery under inspection is considered to have a solder penetration defect; otherwise, the solder penetration test is considered qualified.

[0068] Solder spot detection: The host computer intercepts the second battery image based on the pad welding area to obtain a solder spot image. Then, through the target detection algorithm, it identifies the solder spots and obtains the number and coordinate position information of the solder spots. The number of solder spots is compared with the preset threshold. If they are equal, the solder spot detection is judged to be qualified; otherwise, it is judged that there is a solder spot defect.

[0069] Welding deviation detection: The host computer obtains the welding boundary coordinate position information based on the welding detection area of ​​the pad, compares it with the welding point coordinate position information, and determines whether each welding point is welded. If welding deviation exists, it is determined that the battery to be tested has welding deviation defects; otherwise, the welding deviation detection is determined to be qualified.

[0070] Spot burst detection: The host computer performs a third morphological analysis based on the front welding image (extracted from the second battery image) to determine whether there is a spot burst by detecting areas with abnormally high brightness and irregular shapes in the image. If so, the battery to be tested is determined to have a spot burst defect; otherwise, the spot burst test is determined to be qualified.

[0071] Weld slag detection: The host computer performs a fourth morphological analysis based on the back welding image (extracted from the third battery image) and determines whether there is weld slag by analyzing the grayscale and texture features of the image. If so, it is determined that the battery to be tested has a weld slag defect; otherwise, the weld slag test is determined to be qualified.

[0072] Furthermore, the host computer displays various test results on the display screen in an intuitive manner, such as marking qualified and unqualified batteries with different colors, and displaying specific defect type and location information; the test results of each battery to be tested are recorded in detail, including image data, test results, test time, etc., for subsequent quality traceability and data analysis.

[0073] In the above technical solution, the host computer can realize comprehensive detection of battery welding defects based on different image data. This multi-dimensional detection method can cover various defects that may occur in the battery welding process, greatly improving the accuracy and reliability of detection; and the entire detection process is automatically completed by the controller and the host computer without human intervention, reducing the impact of human factors on the detection results and improving the consistency and detectability of the detection.

[0074] Furthermore, based on the same concept, the present application also provides a storage medium, in which a computer program is stored, wherein the computer program is configured to execute the welding defect detection method when running.

[0075] In some embodiments, the storage medium stores a number of computer programs that enable the welding defect detection system to perform all or part of the steps of the methods described in various embodiments of the present application. The medium may include a USB flash drive, a mobile hard drive, a read-only memory, a random access memory, a magnetic disk, or an optical disk, among other media capable of storing program code.

[0076] Although example embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above example embodiments are merely illustrative and are not intended to limit the scope of the present application. Various changes and modifications may be made therein by those skilled in the art without departing from the scope and spirit of the present application. All such changes and modifications are intended to be included within the scope of the present application as required by the appended claims.

[0077] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0078] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units described is merely a logical function division. In actual implementation, other division methods may be used, such as combining or integrating multiple units or components into another device, or ignoring or not performing some features.

[0079] The various component embodiments of the present application can be implemented in hardware, or in a software module running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all of the functions of some modules according to the embodiments of the present application. The application can also be implemented as a part or all of a device program (e.g., a computer program and a computer program product) for performing the method described herein. Such a program implementing the present application can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0080] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0081] Although the present application is described in conjunction with the above specific embodiments, it is obvious that those skilled in the art can make many substitutions, modifications and variations based on the above content. Therefore, all such substitutions, improvements and variations are included in the spirit and scope of the appended claims.

Claims

1. A welding defect detection method, characterized in that: The upper camera and the lower camera are coaxially mounted on the upper and lower sides of the battery to be inspected in advance. The welding defect detection method includes: Acquire a first battery image of the battery to be inspected through the lower camera, and acquire a pad welding inspection area based on the first battery image, so as to obtain a weld penetration inspection result based on the pad welding inspection area; Acquire a second battery image of the battery to be inspected through the upper camera, and obtain a solder joint inspection result and a solder misalignment inspection result based on the solder pad welding inspection area and the second battery image; A third battery image of the battery to be inspected is acquired through the lower camera, and a spot explosion detection result and a welding slag detection result are obtained according to the second battery image and the third battery image.

2. The welding defect detection method according to claim 1, characterized in that: The obtaining of the pad welding detection area includes: Obtaining the first battery image by using the lower camera in a backlighting manner, and performing a first morphological analysis based on the first battery image to obtain a pad area and a tab area; The intersection area of ​​the pad area and the tab area is used as the pad welding detection area.

3. The welding defect detection method according to claim 2, characterized in that: The obtaining of the weld penetration detection result comprises: A second morphological analysis is performed on the pad welding detection area to determine whether there is a hole in the pad welding detection area. If so, it is determined that the battery to be tested has a welding through defect; otherwise, it is determined that the battery to be tested has passed the welding through test.

4. The welding defect detection method according to claim 2, characterized in that: The obtaining of the solder joint detection result includes: Obtaining the second battery image by front-lighting the upper camera, and intercepting the second battery image based on the pad welding inspection area to obtain a welding point image; Performing target detection based on the solder joint image to obtain the number of solder joints and solder joint coordinate position information; It is determined whether the number of weld points is within a preset threshold value. If so, it is determined that the weld points of the battery to be tested are qualified; otherwise, it is determined that the battery to be tested has weld point defects.

5. The welding defect detection method according to claim 4, characterized in that: The obtaining of the welding deviation detection result includes: Based on the pad welding detection area, the welding boundary coordinate position information is obtained to determine whether each welding point is welded off-center according to the welding boundary coordinate position information and the welding point coordinate position information. If so, it is determined that the battery to be detected has a welding off-center defect; otherwise, it is determined that the welding off-center defect of the battery to be detected is qualified.

6. The welding defect detection method according to claim 4, characterized in that: The obtaining of a spot explosion detection result and a welding slag detection result according to the second battery image and the third battery image includes: The third battery image is obtained by the lower camera illuminating the battery with front light, and the front welding image and the back welding image are respectively obtained according to the second battery image and the third battery image.

7. The welding defect detection method according to claim 6, characterized in that: The step of obtaining the point explosion detection result includes: A third morphological analysis is performed based on the front welding image to determine whether there is a spot explosion in the front welding image. If so, it is determined that the battery to be inspected has a spot explosion defect; otherwise, it is determined that the battery to be inspected has passed the spot explosion test.

8. The welding defect detection method according to claim 6, characterized in that: The obtaining of welding slag detection results includes: A fourth morphological analysis is performed based on the back welding image to determine whether there is welding slag in the back welding image. If so, it is determined that the battery to be tested has a welding slag defect; otherwise, it is determined that the welding slag test of the battery to be tested is qualified.

9. A system using the welding defect detection method according to any one of claims 1 to 8, characterized in that: At least: A controller, configured to control the upper camera, the lower camera, and corresponding light sources to inspect the battery to be inspected and obtain a first battery image, a second battery image, and a third battery image, respectively; The host computer is used to obtain a pad welding detection area based on the first battery image, so as to obtain a weld penetration detection result based on the pad welding detection area, and is also used to obtain a weld spot detection result and a weld deviation detection result based on the pad welding detection area and the second battery image, and is also used to obtain a spot explosion detection result and a weld slag detection result based on the second battery image and the third battery image.

10. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program is configured to execute the welding defect detection method according to any one of claims 1 to 8 when running.

Images