Defect detection method, defect detection system and apparatus, device, and storage medium

Abstract

The present application relates to a defect detection method, a defect detection system and apparatus, a device, and a storage medium. The method comprises: acquiring a first battery cell image of a battery cell to be detected before adhesive film application and a second battery cell image of said battery cell after adhesive film application; on the basis of the type of a defect to be detected and related parameters of said battery cell, determining the size of a battery cell detection area in the first battery cell image, and on the basis of the size of the battery cell detection area and the related parameters of said battery cell, determining the position of the battery cell detection area in the first battery cell image; on the basis of the type of the defect to be detected and the related parameters of said battery cell, determining the size of a blue adhesive film detection area in the second battery cell image, and on the basis of the size of the blue adhesive film detection area and the related parameters of said battery cell, determining the position of the blue adhesive film detection area in the second battery cell image; and performing defect detection on the battery cell detection area and the blue adhesive film detection area to obtain a detection result. The method can improve the accuracy of defect detection to a certain extent.

Description

Defect detection method, defect detection system, device, equipment and storage medium

[0001] Cross-references

[0002] This application refers to Chinese Patent Application No. 2024102012276, filed on February 23, 2024, entitled “Defect Detection Method, Defect Detection System, Device, Equipment and Storage Medium”, which is incorporated into this application in its entirety by reference. Technical Field

[0003] The present application relates to the field of visual inspection of lithium battery processes, and in particular to a defect detection method, defect detection system, device, equipment and storage medium. Background Art

[0004] At present, in the production process of lithium batteries, due to the manufacturing process and equipment of lithium batteries, lithium batteries will have certain defects. In particular, the bare cells in the lithium battery need to be ultrasonically welded after pairing. There will be various defects in the tab area after welding, such as the number of weld marks, tab folding, blue glue coverage and other defects. Tab defects may cause overcurrent problems and the risk of tab insertion is high, making it a necessary test item for the current lithium battery testing.

[0005] In the related art, after the battery cell is subjected to ultrasonic tab welding and blue glue pasting, various types of defects in the tab area are usually detected.

[0006] However, the above-mentioned defect detection method has the problem of low detection accuracy, which seriously affects the quality and safety of battery cells.

[0007] Summary of the Invention

[0008] Based on this, it is necessary to provide a defect detection method, defect detection system, device, equipment and storage medium that can improve detection accuracy in response to the above technical problems.

[0009] In a first aspect, the present application provides a defect detection method. The method comprises:

[0010] Obtain a first cell image of the cell to be tested before gluing and a second cell image of the cell to be tested after gluing; the first cell image includes the tab of the cell to be tested;

[0011] Determine a cell inspection area from the first cell image and a blue glue inspection area from the second cell image based on the type of defect to be inspected;

[0012] Perform defect detection on the battery cell detection area and the blue glue detection area to obtain the detection results.

[0013] The defect detection method described in the embodiment of the present application obtains a first cell image of the cell to be tested before gluing and a second cell image of the cell to be tested after gluing, and determines the cell detection area from the first cell image and the blue glue detection area from the second cell image according to the type of defect to be detected, performs defect detection on the electric detection area and the blue glue detection area to obtain a detection result. The above-mentioned defect detection method realizes defect detection on the cell to be tested after ultrasonic welding of the tabs of the cell to be tested and before gluing the cell to be tested. Compared with the defect detection after traditional ultrasonic welding, which is completed after gluing blue glue, the above-mentioned method can remove interference such as blue glue color and reflection during defect identification to a certain extent, and can improve the accuracy of defect detection to a certain extent. Moreover, the above-mentioned defect detection method also provides a defect detection for the presence or absence of blue glue, blue glue offset, and blue glue leakage tab of the cell after welding, and by quickly locating the blue glue detection area, the detection accuracy and efficiency can be improved to a certain extent. In some embodiments, the above method determines the battery cell detection area and the blue glue detection area according to the type of defect to be detected, that is, different types of defects to be detected correspond to different battery cell detection areas and blue glue detection areas, so the above method can realize the detection of multiple types of defects.

[0014] In one embodiment, determining a cell inspection area from a first cell image and determining a blue glue inspection area from a second cell image according to a type of defect to be inspected includes:

[0015] According to the type of defect to be detected and relevant parameters of the battery cell to be tested, the battery cell detection area in the first battery cell image and the blue glue detection area in the second battery cell image are determined.

[0016] The detection method described in the embodiment of the present application determines the corresponding battery cell detection area and blue glue detection area by different types of defects to be detected, so as to detect different types of defects and improve the comprehensiveness of detection to a certain extent.

[0017] In one embodiment, determining a cell detection area in a first cell image and a blue glue detection area in a second cell image according to the type of defect to be detected and relevant parameters of the cell to be tested includes:

[0018] Determine the size of the battery cell inspection area in the first battery cell image according to the type of defect to be inspected and relevant parameters of the battery cell to be inspected;

[0019] Determine the size of the blue glue detection area in the second battery cell image based on the type of defect to be detected and the relevant parameters of the battery cell to be tested;

[0020] Determine the position of the battery cell detection area in the first battery cell image according to the size of the battery cell detection area and relevant parameters of the battery cell to be tested;

[0021] Determine the position of the blue glue detection area in the second battery cell image based on the size of the blue glue detection area and the relevant parameters of the battery cell to be tested.

[0022] The method described in the embodiments of the present application determines the size and position of the battery cell detection area, as well as the size and position of the blue glue detection area, by the type of defect to be detected. This can improve the accuracy of determining the battery cell detection area and the blue glue detection area to a certain extent, thereby improving the accuracy of defect detection.

[0023] In one embodiment, determining the size of the inspection area in the first battery cell image according to the type of the defect to be inspected and relevant parameters of the battery cell to be inspected includes:

[0024] If the type of defect to be detected is a tab eversion defect, the cell detection area is determined to be the eversion area, and the size of the eversion area is determined according to the size parameters of the tab of the cell to be tested, the size parameters of the adapter of the cell to be tested, and the size parameters of the weld mark of the adapter of the cell to be tested;

[0025] If the type of defect to be detected is a tab fold defect, the battery cell detection area is determined to be a fold area, and the size of the fold area is determined according to the size parameters of the tab of the battery cell to be tested and the size parameters of the adapter of the battery cell to be tested;

[0026] If the type of the defect to be detected is a weld mark defect, the battery cell detection area is determined to be a weld mark detection area, and the size of the weld mark detection area is determined according to the size parameters of the weld mark on the adapter in the battery cell to be tested.

[0027] The method described in the embodiments of the present application can detect the tab eversion defect, the tab folding defect, or the weld mark defect by determining the size of the eversion area corresponding to the type of the tab eversion defect, or determining the size of the folding area corresponding to the type of the tab folding defect, or determining the size of the weld mark detection area corresponding to the type of the weld mark defect.

[0028] In one embodiment, the eversion area includes a first detection area and a second detection area, and determining the size of the eversion area according to the size parameters of the tab of the battery cell to be tested, the size parameters of the adapter of the battery cell to be tested, and the size parameters of the weld mark of the adapter of the battery cell to be tested includes:

[0029] Determine the size of the first detection area according to the size parameters of the tab of the battery cell to be tested and the size parameters of the adapter;

[0030] The size of the second detection area is determined according to the size parameters of the weld mark of the adapter of the battery cell to be tested.

[0031] The method described in the embodiments of the present application can detect white and black tab eversion defects by determining the sizes of the first and second detection areas in the eversion area corresponding to the type of tab eversion defect.

[0032] In one embodiment, determining the size of the first detection area according to the size parameters of the tab of the battery cell to be tested and the size parameters of the adapter includes:

[0033] The size of the first detection area is determined according to the length of the tab of the battery cell to be tested and the width of the gap between the adapter and the battery cell to be tested.

[0034] The method described in the embodiment of the present application can detect white tab eversion defects in tab eversion defects by determining the size of the first detection area in the eversion area corresponding to the type of tab eversion defect.

[0035] In one embodiment, determining the size of the second inspection area according to the size parameters of the weld mark of the adapter of the battery cell to be tested includes:

[0036] The size of the second inspection area is determined according to the length and width of the weld mark of the adapter of the battery cell to be tested.

[0037] The method described in the embodiment of the present application can detect black tab eversion defects in tab eversion defects by determining the size of the second detection area in the eversion area corresponding to the type of tab eversion defect.

[0038] In one embodiment, determining the size of the folded area according to the size parameters of the tab of the battery cell to be tested and the size parameters of the adapter of the battery cell to be tested includes:

[0039] The size of the folded area is determined based on the length of the tab of the cell to be tested and the width of the gap between the adapter and the cell to be tested.

[0040] The method described in the embodiments of the present application can detect the tab fold defect by determining the size of the folded area corresponding to the type of the tab fold defect.

[0041] In one embodiment, determining a position of a cell detection area in a first cell image according to a size of the detection area and relevant parameters of the cell to be tested includes:

[0042] The battery cell detection area in the first battery cell image is positioned according to the position of the intersection of the first side and the second side and combined with the size of the battery cell detection area to determine the position of the battery cell detection area in the first battery cell image; the first side and the second side are two intersecting sides of the adapter in the first battery cell image.

[0043] The detection method described in the embodiment of the present application locates the battery cell detection area by grasping the edge, which is simple and efficient to implement and can improve the efficiency of locating the battery cell detection area to a certain extent, thereby improving the detection efficiency.

[0044] In one embodiment, determining the size of the blue glue detection area in the second battery cell image according to the type of the defect to be detected and relevant parameters of the battery cell to be tested includes:

[0045] If the type of defect to be detected is whether the blue glue has defects, the blue glue detection area is determined to be the glue area, and the size of the glue area is determined according to the size parameters of the weld mark of the adapter of the battery cell to be tested;

[0046] If the type of defect to be detected is a blue glue offset defect or an adapter polarity defect, the blue glue detection area is determined to be the pad area, and the size of the pad area is determined based on the size parameters of the pad in the adapter of the battery cell to be tested;

[0047] If the type of defect to be detected is a drain tab defect, the blue glue detection area is determined to be the area around the tab, and the size of the area around the tab is determined based on the size parameters and position of the pad in the adapter of the battery cell to be tested.

[0048] The method described in the embodiments of the present application can detect whether there are defects in the blue glue, or defects in the tab folding, or defects in the blue glue offset, or defects in the polarity of the adapter, or defects in the drain tab by determining the size of the glue area, or determining the size of the pad area, or determining the size of the area around the tab.

[0049] In one embodiment, determining the size of the adhesive area according to the size parameters of the weld mark of the adapter of the battery cell to be tested includes:

[0050] The size of the adhesive bonding area is determined according to the length of the area where the welding mark of the adapter is located and the width of the area where the welding mark of the adapter is located.

[0051] The method described in the embodiment of the present application can detect whether the blue glue has defects by determining the size of the glue-applying area corresponding to the type of blue glue defects.

[0052] In one embodiment, determining the position of the blue glue detection area in the second battery cell image according to the size of the blue glue detection area and relevant parameters of the battery cell to be tested includes:

[0053] The glue area in the second battery cell image is located based on the intersection of the third and fourth sides and the size of the glue area to determine the position of the glue area in the second battery cell image; the third and fourth sides are the two intersecting sides of the adapter in the second battery cell image;

[0054] Alternatively, the position of the glue-attached area in the second battery cell image is determined according to the position of the area where the weld mark of the battery cell to be tested is located.

[0055] The detection method described in the embodiment of the present application locates the glued area by grabbing the edge, which is simple and efficient to implement and can improve the efficiency of locating the glued area to a certain extent, thereby improving the detection efficiency.

[0056] In one embodiment, determining the size of the pad area according to the size parameters of the pad in the adapter of the battery cell to be tested includes:

[0057] Determine the raised area or recessed area of ​​the solder pad in the adapter of the battery cell to be tested;

[0058] If the protrusion area or the recess area is a circular area, the size of the pad area is determined according to the diameter of the protrusion area or the recess area;

[0059] If the protrusion area or the recess area is a rectangular area, the size of the pad area is determined according to the length of the protrusion area or the recess area and the width of the protrusion area or the recess area.

[0060] The method described in the embodiments of the present application can detect blue glue offset defects or adapter polarity defects by determining the size of the pad area corresponding to the type of blue glue offset defects or adapter polarity defects.

[0061] In one embodiment, determining the size of the pad area according to the size parameters of the pad in the adapter of the battery cell to be tested includes:

[0062] Determine the size of the pad area based on the length of the area where the pad is located in the adapter of the battery cell to be tested and the width of the area where the pad is located in the adapter;

[0063] Alternatively, the size of the pad area is determined according to the size parameters of the protrusion area or the recess area of ​​the pad in the adapter.

[0064] The method described in the embodiments of the present application can detect blue glue offset defects or adapter polarity defects by determining the size of the pad area corresponding to the type of blue glue offset defects or adapter polarity defects.

[0065] In one embodiment, determining the position of the blue glue detection area in the second battery cell image according to the size of the blue glue detection area and relevant parameters of the battery cell to be tested includes:

[0066] The pad area in the second cell image is located according to the position of the pad of the adapter in the cell to be tested and in combination with the size of the pad area, to determine the position of the pad area in the second cell image.

[0067] The detection method described in the embodiment of the present application locates the pad area by identifying the pad. The implementation is simple and efficient, and can improve the efficiency of locating the pad area to a certain extent, thereby improving the detection efficiency.

[0068] In one embodiment, determining the size of the area around the tab according to the size parameters and position of the pad in the adapter of the battery cell to be tested includes:

[0069] Determine the size of the area around the tab based on the length of the area where the pad is located in the adapter of the battery cell to be tested and the distance between the pad and the battery cell to be tested.

[0070] The method described in the embodiments of the present application can detect drain ear defects by determining the size of the area around the ear corresponding to the type of drain ear defect.

[0071] In one embodiment, the area around the tab includes a first surrounding area of ​​the first tab, a second surrounding area of ​​the first tab, a first surrounding area of ​​the second tab, and a second surrounding area of ​​the second tab. The size of the area around the tab is determined according to the length of the area where the pad is located in the adapter of the battery cell to be tested and the distance between the pad and the battery cell to be tested, including:

[0072] Determine the length of the first surrounding area of ​​the first tab, the length of the second surrounding area of ​​the first tab, the length of the first surrounding area of ​​the second tab, and the length of the second surrounding area of ​​the second tab according to the length of the area where the solder pad is located in the adapter of the battery cell to be tested;

[0073] Determining a width of a first surrounding area of ​​the first tab and a width of a second surrounding area of ​​the first tab according to a first distance between the welding pad and the battery cell to be tested;

[0074] The width of the first surrounding area of ​​the second tab and the width of the second surrounding area of ​​the second tab are determined according to the second distance between the welding pad and the battery cell to be tested.

[0075] The method described in the embodiment of the present application can detect leakage tab defects by determining the size of the area around the tab, and the area around the tab basically covers all areas where the tab may leak.

[0076] In one embodiment, determining the position of the blue glue detection area in the second battery cell image according to the size of the blue glue detection area and relevant parameters of the battery cell to be tested includes:

[0077] Based on the position of the intersection of the fifth and sixth sides and in combination with the size of the first surrounding area of ​​the first tab, the first surrounding area of ​​the first tab in the second battery cell image is located to determine the position of the first surrounding area of ​​the first tab; the fifth and sixth sides are the two intersecting sides of the adapter in the second battery cell image;

[0078] Determine the position of the second surrounding area of ​​the first tab according to the length of the first blue glue in the battery cell to be tested and the position of the first surrounding area of ​​the first tab;

[0079] The first surrounding area of ​​the second tab in the second battery cell image is located according to the position of the intersection of the seventh side and the eighth side and in combination with the size of the first surrounding area of ​​the second tab to determine the position of the first surrounding area of ​​the second tab; the seventh side and the eighth side are two intersecting sides of the adapter in the second battery cell image;

[0080] The position of the second surrounding area of ​​the second electrode tab is determined according to the length of the second blue glue in the battery cell to be tested and the position of the first surrounding area of ​​the second electrode tab.

[0081] The detection method described in the embodiment of the present application locates the first surrounding area of ​​the first pole lug, the second surrounding area of ​​the first pole lug, the first surrounding area of ​​the second pole lug, and the second surrounding area of ​​the second pole lug by grasping the edges. The implementation method is simple and efficient, and can improve the efficiency of locating the areas around the pole lugs to a certain extent, thereby improving the detection efficiency.

[0082] In one embodiment, the test results include a first test result and a second test result, and the defect detection is performed on the battery cell detection area and the blue glue detection area to obtain the test results, including:

[0083] Performing a first defect detection on the battery cell detection area to obtain a first detection result; the first defect includes one of a tab eversion defect, a tab folding defect, a tab cracking defect, and a weld mark defect;

[0084] The blue glue detection area is detected for a second defect to obtain a second detection result; the second defect includes one of a blue glue defect, a blue glue offset defect, a transfer sheet polarity defect, and a drain ear defect.

[0085] The method described in the embodiment of the present application realizes a series of defect detections before the tested battery cell is glued, as well as a series of defect detections after the glue is glued, with clear division of labor, and can realize comprehensive detection of the tested battery cell.

[0086] In one embodiment, the battery cell detection area includes a tab fold detection area, the tab fold detection area includes an outward-turning area, the outward-turning area includes a first battery cell detection area and a second battery cell detection area, and the battery cell detection area is detected for a first defect to obtain a first detection result, including:

[0087] Binarization is performed on the image of the first battery cell detection area and the image of the second battery cell detection area to obtain a first processed image and a second processed image;

[0088] Performing a first-category defect detection on the first processed image, among the tab eversion defects, to obtain an intermediate detection result;

[0089] If the intermediate test result indicates that a first type of defect is detected, determining that the first test result indicates that the tested battery cell has a first type of defect;

[0090] If the intermediate detection result indicates that the first type of defect is not detected, the second type of defect detection in the tab eversion defect is performed on the second processed image to obtain the first detection result.

[0091] The detection method described in the embodiment of the present application can realize the detection of the white eversion defect of the pole lug and the black eversion defect of the pole lug, and the battery cell detection area corresponding to the white eversion defect of the pole lug is different from the detection area corresponding to the black eversion defect of the pole lug. Therefore, the battery cell detection area corresponding to the white eversion defect of the pole lug is detected first, and in the scenario where the white eversion defect of the pole lug is not detected, the battery cell detection area corresponding to the black eversion defect of the pole lug is detected, which can improve the detection efficiency to a certain extent.

[0092] In one embodiment, the first processed image is subjected to a first type of defect detection of tab eversion defects to obtain an intermediate detection result, including:

[0093] Determine whether the battery cell detection area of ​​the first processed image contains pixels whose grayscale values ​​are within the first grayscale threshold range. If the battery cell detection area contains pixels whose grayscale values ​​are within the first grayscale threshold range, determine that the intermediate detection result indicates that a first type of defect is detected; if the battery cell detection area does not contain pixels whose grayscale values ​​are within the first grayscale threshold range, determine that the intermediate detection result indicates that no first type of defect is detected.

[0094] The detection method described in the embodiment of the present application realizes the detection of the white eversion defect of the tab by setting a first grayscale threshold range corresponding to the white eversion defect of the tab. The method is easy to implement and can improve the detection efficiency to a certain extent.

[0095] In one embodiment, the second processed image is subjected to a second type of defect detection of tab eversion defects to obtain a first detection result, including:

[0096] Determine whether the battery cell detection area of ​​the second processed image contains pixels whose grayscale values ​​are within the second grayscale threshold range. If the battery cell detection area contains pixels whose grayscale values ​​are within the second grayscale threshold range, determine that the first detection result indicates that the battery cell to be tested has a second type of defect; if the battery cell detection area does not contain pixels whose grayscale values ​​are within the second grayscale threshold range, determine that the first detection result indicates that the battery cell to be tested does not have a second type of defect.

[0097] The detection method described in the embodiment of the present application realizes the detection of the black tab eversion defect by setting a second grayscale threshold range corresponding to the black tab eversion defect. The method is easy to implement and can improve the detection efficiency to a certain extent.

[0098] In one embodiment, the detection area includes a tab fold detection area, and the tab fold detection area includes the fold area. A first defect detection is performed on the battery cell detection area to obtain a first detection result, including:

[0099] Binarization is performed on the image in the folded area to obtain a processed third image;

[0100] The third processed image is inspected for tab folding defects to obtain a first inspection result.

[0101] The detection method described in the embodiment of the present application realizes a method for detecting whether the tabs of the adapter sheet on the battery cell cover the glue-coated area. Compared with the traditional tab detection method, new detection items are added, which can improve the product yield.

[0102] In one embodiment, the battery cell inspection area includes a tab shielding inspection area, and the first defect inspection of the battery cell inspection area to obtain a first inspection result includes:

[0103] The image of the tab blocking the detection area is input into a preset detection model to detect the tab cracking defect and obtain a first detection result; the first detection result includes the tab cracking confidence.

[0104] The embodiment of the present application provides a method for detecting cracking defects on the back tab, and by quickly locating the tab-blocked detection area and realizing detection through a trained deep learning model, the detection accuracy and efficiency can be improved to a certain extent.

[0105] In one embodiment, the battery cell inspection area includes a weld mark inspection area, and performing a first defect inspection on the inspection area to obtain a first inspection result includes:

[0106] Detecting spots in the battery cell detection area to determine the spots in the battery cell detection area;

[0107] According to the number and area of ​​pixels occupied by each spot, the battery cell detection area is subjected to defect detection to obtain a first detection result; the first detection result includes the number and weld print area of ​​welding points in the battery cell detection area.

[0108] The embodiments of the present application provide a method for detecting weld mark defects, and by quickly locating the weld mark detection area and implementing detection through a trained deep learning model, the detection accuracy and efficiency can be improved to a certain extent.

[0109] In one embodiment, the blue glue detection area includes the glue application area, the second defect includes whether the blue glue has a defect, and the blue glue detection area is detected for the second defect to obtain a second detection result, including:

[0110] Determine whether the pixel values ​​of all pixels in the blue glue detection area are greater than a first preset pixel threshold;

[0111] If the pixel values ​​of all pixels in the blue glue detection area are greater than the first preset pixel threshold, it is determined that the second detection result indicates that blue glue is affixed to the adapter in the second battery cell image;

[0112] If the pixel values ​​of all pixels in the blue glue detection area are not greater than the first preset pixel threshold, it is determined that the second detection result indicates that no blue glue is pasted on the adapter in the second battery cell image.

[0113] The embodiment of the present application provides a defect detection method for detecting the presence of blue glue in battery cells after welding, and by quickly locating the blue glue detection area, the detection accuracy and efficiency can be improved to a certain extent.

[0114] In one embodiment, the blue glue detection area includes a pad area, the second defect includes a blue glue offset defect, and the blue glue detection area is detected for the second defect to obtain a second detection result, including:

[0115] Determine whether there is a pixel point in the pad area whose pixel value is greater than a second preset pixel threshold;

[0116] If so, it is determined that the second test result indicates that the blue glue attached to the adapter in the second battery cell picture has an offset defect;

[0117] If not, it is determined that the second detection result indicates that the blue glue pasted on the adapter sheet in the second battery cell picture does not have an offset defect.

[0118] The embodiment of the present application provides a method for detecting blue glue offset defects in battery cells after welding, especially detecting whether there is blue glue offset in the pad area, which can improve the detection safety of battery cells to a certain extent.

[0119] In one embodiment, the blue glue detection area includes a pad area, the second defect includes a polarity defect of the adapter, and the blue glue detection area is detected for the second defect to obtain a second detection result, including:

[0120] Determine a first color value and a second color value of a pad area in a second battery cell image;

[0121] Determining the polarity of the adapter in the second battery cell image based on a difference between the first color value and the second color value;

[0122] A second detection result is determined according to the polarity of the adapter in the second battery cell picture; the second detection result indicates whether the polarity of the adapter in the second battery cell picture is reversed.

[0123] The embodiment of the present application provides a method for detecting the polarity defects of the solder pads of the battery cells after welding, especially detecting whether the polarity of the solder pads has a reverse polarity defect, which can improve the detection safety of the battery cells to a certain extent.

[0124] In one embodiment, the blue glue detection area includes the area around the tab, the second defect includes a drain tab defect, and the blue glue detection area is inspected for the second defect to obtain a second inspection result, including:

[0125] Determine whether the area around the tab in the second battery cell image includes an area with a grayscale difference greater than a preset grayscale threshold;

[0126] If it is included, it is determined that the second test result indicates that the blue glue affixed to the adapter in the second battery cell picture has a leakage ear defect;

[0127] If not included, it is determined that the second detection result indicates that the blue glue pasted on the adapter sheet in the second battery cell picture does not have a drain ear defect.

[0128] The embodiments of the present application provide a method for detecting defects in drain tabs of battery cells after welding, which can improve the comprehensiveness of battery cell detection to a certain extent.

[0129] In a second aspect, the present application further provides a defect detection system. The system includes: a control device, a camera, a drive device, a welding device, and a gluing device; the control device is connected to the camera, the drive device, the welding device, and the gluing device respectively; and the control device is configured to execute the defect detection method described in the first aspect.

[0130] In a third aspect, the present application also provides a defect detection device. The device comprises:

[0131] The acquisition module is used to obtain a first cell image of the cell to be tested before gluing and a second cell image of the cell to be tested after gluing; the first cell image includes the tab of the cell to be tested.

[0132] The determination module is used to determine the battery cell detection area from the first battery cell image and the blue glue detection area from the second battery cell image according to the type of the defect to be detected.

[0133] The detection module is used to perform defect detection on the battery cell detection area and the blue glue detection area to obtain the detection results.

[0134] In a fourth aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the defect detection method described in the first aspect when executing the computer program.

[0135] In a fifth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the defect detection method described in the first aspect.

[0136] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0137] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments of the present application. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on the drawings without inventive work. In the drawings:

[0138] FIG1 is a schematic structural diagram of a detection system in one embodiment;

[0139] FIG2 is a schematic diagram of a defect detection method according to an embodiment;

[0140] FIG3 is a schematic diagram of a battery cell image in one embodiment;

[0141] FIG4 is a schematic diagram of a battery cell image in another embodiment;

[0142] FIG5 is a schematic flow chart of a defect detection method in another embodiment;

[0143] FIG6 is a schematic flow chart of a defect detection method according to another embodiment;

[0144] FIG7 is a schematic flow chart of a defect detection method according to another embodiment;

[0145] FIG8 is a schematic diagram of a battery cell image in another embodiment;

[0146] FIG9 is a schematic diagram of a battery cell image in another embodiment;

[0147] FIG10 is a schematic diagram of a battery cell image in another embodiment;

[0148] FIG11 is a schematic diagram of a battery cell image in another embodiment;

[0149] FIG12 is a schematic flow chart of a defect detection method according to another embodiment;

[0150] FIG13 is a schematic diagram of a battery cell image in another embodiment;

[0151] FIG14 is a schematic diagram of a battery cell image in another embodiment;

[0152] FIG15 is a schematic flow chart of a defect detection method according to another embodiment;

[0153] FIG16 is a schematic diagram of a battery cell image in another embodiment;

[0154] FIG17 is a schematic diagram of a battery cell image in another embodiment;

[0155] FIG18 is a schematic flow chart of a defect detection method according to another embodiment;

[0156] FIG19 is a schematic diagram of a battery cell image in another embodiment;

[0157] FIG20 is a schematic flow chart of a defect detection method according to another embodiment;

[0158] FIG21 is a schematic flow chart of a defect detection method according to another embodiment;

[0159] FIG22 is a schematic flow chart of a defect detection method according to another embodiment;

[0160] FIG23 is a schematic flow chart of a defect detection method according to another embodiment;

[0161] FIG24 is a schematic diagram of a battery cell image in another embodiment;

[0162] FIG25 is a schematic flow chart of a defect detection method according to another embodiment;

[0163] FIG26 is a schematic flow chart of a defect detection method according to another embodiment;

[0164] FIG27 is a schematic flow chart of a defect detection method according to another embodiment;

[0165] FIG28 is a schematic flow chart of a defect detection method according to another embodiment;

[0166] FIG29 is a schematic flow chart of a defect detection method according to another embodiment;

[0167] FIG30 is a block diagram of a defect detection system according to an embodiment;

[0168] FIG31 is a schematic structural diagram of a defect detection device according to an embodiment;

[0169] FIG32 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0170] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0171] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned figure descriptions are intended to cover non-exclusive inclusions.

[0172] In the description of the embodiments of this application, the technical terms "first" and "second" are used only to distinguish different objects and should not be understood to indicate or imply relative importance or implicitly specify the quantity, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, the meaning of "plurality" is more than two, unless otherwise clearly and specifically defined.

[0173] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0174] The defect detection method provided in the embodiment of the present application can be applied to the detection system shown in Figure 1. The detection system includes a control device 102, a camera 104, a drive device 106, a welding device 108 and a gluing device 110, and the control device 102 is connected to the camera 104, the drive device 106, the welding device 108 and the gluing device 110 respectively, wherein the camera 104 can be divided into an upper camera and a lower camera; when the detection system is used to perform defect detection on the battery cell to be tested, the control device 102 can control the welding device 108 to perform ultrasonic welding of the tabs on the battery cell to be tested at the welding station 112 of the production line 111, and then the control device 102 can control the drive device 106 to drive the battery cell to be tested 100 to move to the first detection station 113 on the production line 111, and control the camera 104 to capture the battery cell to be tested 100 at the first detection station 113. 00, and perform relevant defect detection (for example, tab eversion defect, tab folding defect, weld mark defect) based on the picture of the battery cell to be tested 100, and then the control device 102 controls the driving device 106 to drive the battery cell to be tested 100 to move to the gluing station 114 on the production line 111, and controls the gluing device 110 to glue the battery cell to be tested 100, and after gluing, the control device 102 controls the driving device 106 to drive the battery cell to be tested 100 to move to the second inspection station 115, and controls the camera 104 to capture the picture of the battery cell to be tested on the second inspection station 115, and perform relevant defect detection (for example, whether there is any one of blue glue defect, blue glue offset defect, adapter polarity defect, and drain ear defect) based on the picture of the battery cell to be tested 100. The control device 102 may be a programmable logic controller (PLC), an integrated circuit chip, or a personal computer, a laptop computer, a smart phone, a tablet computer, a server, etc.

[0175] Those skilled in the art will understand that the structure shown in FIG1 is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0176] In one embodiment, as shown in FIG2 , a defect detection method is provided. The method is described by taking the control device in FIG1 as an example, and includes the following steps:

[0177] S201 , obtaining a first cell image of the cell to be tested before gluing and a second cell image of the cell to be tested after gluing.

[0178] The first cell picture includes the tabs of the cell to be tested, and the second cell picture includes the tabs of the cell to be tested, as well as the blue glue pasted on the cell to be tested and the adapter.

[0179] In an embodiment of the present application, after the control device controls the welding device to perform ultrasonic lug welding on the battery cell to be tested, it can control the driving device to move the welded battery cell to be tested to the first inspection station, and give the camera a trigger signal to take a picture, so that the camera captures the first battery cell picture of the battery cell to be tested after welding and before gluing, and the first battery cell picture includes the welded lug, the battery cell to be tested, and the adapter of the battery cell to be tested. For example, see the schematic diagram of the first battery cell picture shown in Figure 3, wherein the area marked with 1 represents the battery cell to be tested, the area marked with 2 represents the adapter, and the area marked with 3 represents the lug. It should be noted that Figure 3 shows a schematic diagram of two adapters of different polarities, the adapter for the aluminum pole on the left and the adapter for the copper pole on the right.

[0180] After the control device controls the camera to capture the first picture of the battery cell to be tested before gluing, the drive device can be further controlled to move the battery cell to be tested after gluing to the second inspection station, and the camera trigger signal can be given to take a picture, so that the camera can capture the second picture of the battery cell to be tested after welding and gluing. The second battery cell picture includes the welded tabs, the battery cell to be tested, the adapter and the blue glue of the battery cell to be tested. For example, refer to the schematic diagram of the second battery cell picture shown in Figure 4, where the area marked with 1 represents the battery cell to be tested, the area marked with 2 represents the adapter, the area marked with 3 represents the tabs, and the area marked with 4 represents the blue glue.

[0181] S202 : Determine a battery cell detection area from the first battery cell image and a blue glue detection area from the second battery cell image according to the type of the defect to be detected.

[0182] The cell inspection area can include a tab inspection area and a welding inspection area. The tab inspection area includes an outward-turning area and a folding area. The outward-turning area includes a first white object detection area and a first black object detection area. The folding area includes a second white object detection area and a second black object detection area. The types of defects to be detected include tab outward-turning defects, tab folding defects, tab cracking defects, and welding defects. Different types of defects correspond to cell inspection areas of different sizes and locations.

[0183] In an embodiment of the present application, when the control device obtains the first battery cell image, it can further determine the type of defect to be detected. If the type of the defect to be detected is a tab eversion defect, the battery cell detection area corresponding to the tab eversion defect type is determined from the first battery cell image; if the type of the defect to be detected is a tab folding defect type, the battery cell detection area corresponding to the tab folding defect type is determined from the first battery cell image; if the type of the defect to be detected is a tab cracking defect type, the battery cell detection area corresponding to the tab cracking defect type is determined from the first battery cell image; if the type of the defect to be detected is a welding defect type, the battery cell detection area corresponding to the welding defect type is determined from the first battery cell image. It should be noted that when determining the battery cell detection area corresponding to the above-mentioned various defect types, it can be determined based on the correspondence between the pre-set defect type and the battery cell detection area information, and the battery cell detection area information includes the size and position of the battery cell detection area.

[0184] S203: Perform defect detection on the battery cell detection area and the blue glue detection area to obtain detection results.

[0185] Among them, the detection result can indicate whether a defect is detected. In some embodiments, the detection result can also include relevant attribute information of the detected defect (the type and / or location of the defect). The detection result can be determined according to the defect type contained in the battery cell detection area or the battery cell detection area. For example, if the battery cell detection area includes the tab detection area, and the tab detection area includes the eversion area, the corresponding detection result includes whether there is a tab eversion defect; if the battery cell detection area includes the tab detection area, and the tab detection area includes the folding area, the corresponding detection result includes whether there is a tab folding defect; if the battery cell detection area includes the tab detection area, and the tab detection area includes the tab shielding area, the corresponding detection result includes whether there is a tab cracking defect; if the battery cell detection area includes the welding detection area, the corresponding detection result includes whether there is a welding defect, and the number and welding area of ​​the welding points contained in the welding detection area.

[0186] In an embodiment of the present application, when the control device determines the battery cell detection area based on the aforementioned steps, it can further extract the image of the battery cell detection area in the first battery cell image, and perform defect detection based on the image of the battery cell detection area to obtain a detection result. Specifically, the control device can input the image of the battery cell detection area into a preset detection model for defect detection and output the detection result; other defect detection algorithms can also be used to detect the image of the battery cell detection area to obtain a detection result; in some embodiments, when the control device determines the battery cell detection area based on the aforementioned steps, the control device can perform defect detection on the battery cell detection area by comparing the grayscale values ​​of each pixel point in the battery cell detection area, or by comparing based on a standard defect image to obtain a detection result.

[0187] When the control device obtains the second battery cell image, it can further determine the type of defect to be detected. If the type of defect to be detected is the type of blue glue defect, the blue glue detection area corresponding to the type of blue glue defect is determined from the second battery cell image, and specifically the size and position of the blue glue detection area can be determined. When the control device determines the blue glue detection area based on the aforementioned steps, it can further extract an image of the blue glue detection area, and perform defect detection based on the image of the blue glue detection area to obtain a detection result. Specifically, the control device can input the image of the blue glue detection area into a preset detection model for defect detection and output the detection result; other defect detection algorithms can also be used to detect the image of the blue glue detection area to obtain a detection result; in some embodiments, when the control device determines the blue glue detection area based on the aforementioned steps, the control device can perform defect detection on the blue glue detection area by comparing the grayscale values ​​of each pixel in the blue glue detection area, or by comparing based on a standard defect image to obtain a detection result.

[0188] The defect detection method described in the embodiment of the present application obtains a first cell image of the cell to be tested before gluing and a second cell image of the cell to be tested after gluing, and determines the cell detection area from the first cell image and the blue glue detection area from the second cell image according to the type of defect to be detected, performs defect detection on the electric detection area and the blue glue detection area to obtain a detection result. The above-mentioned defect detection method realizes defect detection on the cell to be tested after ultrasonic welding of the tabs of the cell to be tested and before gluing the cell to be tested. Compared with the defect detection after traditional ultrasonic welding, which is completed after gluing blue glue, the above-mentioned method can remove interference such as blue glue color and reflection during defect identification to a certain extent, and can improve the accuracy of defect detection to a certain extent. Moreover, the above-mentioned defect detection method also provides a defect detection for the presence or absence of blue glue, blue glue offset, and blue glue leakage tab of the cell after welding, and by quickly locating the blue glue detection area, the detection accuracy and efficiency can be improved to a certain extent. In some embodiments, the above method determines the battery cell detection area and the blue glue detection area according to the type of defect to be detected, that is, different types of defects to be detected correspond to different battery cell detection areas and blue glue detection areas, so the above method can realize the detection of multiple types of defects.

[0189] In one embodiment, when the control device specifically executes the above S202 "determining the battery cell detection area from the first battery cell image and determining the blue glue detection area from the second battery cell image according to the type of defect to be detected", the specific execution steps are: determining the battery cell detection area in the first battery cell image and the blue glue detection area in the second battery cell image according to the type of defect to be detected and the relevant parameters of the battery cell to be tested.

[0190] Among them, the relevant parameters of the battery cell to be tested include the size parameters of the tabs of the battery cell to be tested, the size parameters of the adapter of the battery cell to be tested, the size parameters of the weld marks of the adapter of the battery cell to be tested, and the size parameters of the pads on the adapter of the battery cell to be tested.

[0191] In an embodiment of the present application, when the control device obtains the first battery cell image, it can further determine the type of defect to be detected, and identify and locate the battery cell detection area in the first battery cell image in combination with the relevant parameters of the battery cell to be tested, so as to determine the position and size of the battery cell detection area in the first battery cell image. In some embodiments, the control device can also identify or locate the battery cell detection area of ​​the first battery cell image based on a pre-trained recognition or positioning model to determine the position and size of the battery cell detection area in the first battery cell image. Specifically, the recognition or positioning model can be trained based on the battery cell image samples and the corresponding defect labeled samples during the training phase, wherein the defect labeled samples can be determined using the relevant parameters of the battery cell in the image sample, so that the trained recognition or positioning model can identify or locate the battery cell detection area in the battery cell image according to the type of defect and the relevant parameters of the battery cell. In the stage of using the trained recognition or positioning model, the relevant parameters of the battery cell to be tested and the battery cell image can be input into the recognition or positioning model to identify or locate the detection area. In some embodiments, a recognition or positioning model for identifying or locating battery cell detection areas corresponding to different types of defects can also be pre-trained, that is, different defect types correspond to different recognition or positioning models. When used, the corresponding recognition or positioning model can be first determined according to the type of defect to be detected, and the first battery cell image and the relevant parameters of the battery cells in the first battery cell image can be input into the determined recognition or positioning model, and the position and size of the battery cell detection area in the first battery cell image can be output.

[0192] When the control device obtains the second battery cell image, it can further determine the type of defect to be detected, and identify and locate the blue glue detection area in the second battery cell image in combination with the relevant parameters of the battery cell to be tested, so as to determine the position and size of the blue glue detection area in the second battery cell image. In some embodiments, the control device can also identify or locate the blue glue detection area of ​​the second battery cell image based on the recognition or positioning model obtained by pre-training to determine the position and size of the blue glue detection area in the second battery cell image. Specifically, the recognition or positioning model can be trained based on the image samples of the battery cells and the labeled samples of the corresponding defects during the training phase, wherein the labeled samples of the defects can be determined using the relevant parameters of the battery cells in the image samples, so that the trained recognition or positioning model can identify or locate the blue glue detection area in the battery cell image according to the type of defect and the relevant parameters of the battery cells. In the stage of using the trained recognition or positioning model, the relevant parameters of the battery cell to be tested and the battery cell image can be input into the recognition or positioning model to identify or locate the blue glue detection area. In some embodiments, a recognition or positioning model for identifying or locating blue glue detection areas corresponding to different types of defects can also be pre-trained, that is, different defect types correspond to different recognition or positioning models. When used, the corresponding recognition or positioning model can be first determined according to the type of defect to be detected, and the second battery cell image and the relevant parameters of the battery cells in the second battery cell image can be input into the determined recognition or positioning model, and the position and size of the blue glue detection area in the second battery cell image can be output.

[0193] The detection method described in the embodiment of the present application determines the corresponding battery cell detection area and blue glue detection area by different types of defects to be detected, so as to detect different types of defects and improve the comprehensiveness of detection to a certain extent.

[0194] In one embodiment, an implementation method for determining the battery cell detection area and the blue glue detection area is provided, as shown in FIG5 , and the implementation method includes:

[0195] S301 : Determine a size of a cell inspection area in a first cell image according to a type of a defect to be inspected and relevant parameters of the cell to be inspected.

[0196] In an embodiment of the present application, when the control device obtains the first battery cell image, it can further determine the type of defect to be detected, and perform size identification of the battery cell detection area in the first battery cell image in combination with the relevant parameters of the battery cell to be tested, so as to determine the size of the battery cell detection area. In some embodiments, the control device can also perform size identification of the battery cell detection area on the first battery cell image based on a pre-trained recognition model to determine the size of the battery cell detection area in the first battery cell image. Specifically, the recognition model can be trained based on the battery cell image samples and the labeled samples of the corresponding defects during the training phase, wherein the labeled samples of the defects can be determined using the relevant parameters of the battery cell in the image samples, so that the trained recognition model can perform size identification of the battery cell detection area in the battery cell image according to the type of defect and the relevant parameters of the battery cell. In the stage of using the trained recognition model, the relevant parameters of the battery cell to be tested and the battery cell image can be input into the recognition model to perform size identification of the battery cell detection area. In some embodiments, a recognition model for identifying the cell detection areas corresponding to different types of defects can also be pre-trained, that is, different defect types correspond to different recognition or positioning models. When used, the corresponding recognition model can be first determined according to the type of defect to be detected, and the first cell image and the relevant parameters of the cell in the first cell image can be input into the determined recognition model, and the size of the cell detection area in the first cell image can be output.

[0197] S302 : Determine the size of the blue glue detection area in the second battery cell image according to the type of the defect to be detected and relevant parameters of the battery cell to be tested.

[0198] In an embodiment of the present application, when the control device obtains the second battery cell image, it can further determine the type of defect to be detected, and perform size identification on the blue glue detection area in the second battery cell image in combination with the relevant parameters of the battery cell to be tested to determine the size of the blue glue detection area. In some embodiments, the control device can also perform size identification on the blue glue detection area of ​​the second battery cell image based on a pre-trained recognition model to determine the size of the blue glue detection area in the second battery cell image. Specifically, the recognition model can be trained based on the image samples of the battery cells and the labeled samples of the corresponding defects during the training phase, wherein the labeled samples of the defects can be determined using the relevant parameters of the battery cells in the image samples, so that the trained recognition model can perform size identification on the battery cell detection area in the battery cell image according to the type of defect and the relevant parameters of the battery cells. In the stage of using the trained recognition model, the relevant parameters of the battery cell to be tested and the battery cell image can be input into the recognition model to perform size identification of the blue glue detection area. In some embodiments, a recognition model for identifying the blue glue detection areas corresponding to different types of defects can also be pre-trained, that is, different defect types correspond to different recognition or positioning models. When used, the corresponding recognition model can be first determined according to the type of defect to be detected, and the second battery cell image and the relevant parameters of the battery cells in the second battery cell image can be input into the determined recognition model, and the size of the blue glue detection area in the second battery cell image can be output.

[0199] S303 : Determine a position of the battery cell detection area in the first battery cell image according to a size of the battery cell detection area and relevant parameters of the battery cell to be tested.

[0200] In an embodiment of the present application, when the control device obtains the first battery cell image and determines the size of the battery cell detection area based on the aforementioned steps, the battery cell detection area in the first battery cell image can be located in combination with the relevant parameters of the battery cell to be tested to determine the position of the battery cell detection area. In some embodiments, the control device can also locate the battery cell detection area in the first battery cell image based on a pre-trained positioning model to determine the position of the battery cell detection area in the first battery cell image. Specifically, the positioning model can be trained based on the battery cell image samples and the labeled samples of the corresponding battery cell detection areas during the training phase, wherein the labeled samples of the battery cell detection areas can be determined using the relevant parameters of the battery cells in the image samples and the size of the battery cell detection area, so that the trained positioning model can locate the battery cell detection area in the battery cell image according to the size of the battery cell detection area and the relevant parameters of the battery cell to be tested. In the stage of using the trained positioning model, the size of the battery cell detection area and the relevant parameters of the battery cell to be tested can be input into the positioning model to locate the battery cell detection area and output the position of the battery cell detection area. In some embodiments, a recognition model for identifying the cell detection areas corresponding to different types of defects can also be pre-trained, that is, cell detection areas of different defect types correspond to different positioning models. When used, the corresponding positioning model can be first determined according to the cell detection area corresponding to the type of defect to be detected, and the size of the cell detection area and the relevant parameters of the cell to be tested can be input into the determined positioning model, and the position of the cell detection area in the first cell image can be output.

[0201] S304 : Determine a position of the blue glue detection area in the second battery cell image according to the size of the blue glue detection area and relevant parameters of the battery cell to be tested.

[0202] In an embodiment of the present application, when the control device obtains the second battery cell image and determines the size of the blue glue detection area based on the aforementioned steps, the blue glue detection area in the second battery cell image can be located in combination with the relevant parameters of the battery cell to be tested to determine the position of the blue glue detection area. In some embodiments, the control device can also locate the blue glue detection area in the second battery cell image based on a pre-trained positioning model to determine the position of the blue glue detection area in the second battery cell image. Specifically, the positioning model can be trained based on the battery cell image samples and the corresponding annotated samples of the blue glue detection area during the training phase, wherein the annotated samples of the blue glue detection area can be determined using the relevant parameters of the battery cell in the image sample and the size of the blue glue detection area, so that the trained positioning model can locate the blue glue detection area in the battery cell image according to the size of the blue glue detection area and the relevant parameters of the battery cell to be tested. In the stage of using the trained positioning model, the size of the blue glue detection area and the relevant parameters of the battery cell to be tested can be input into the positioning model to locate the blue glue detection area, and the position of the blue glue detection area is output. In some embodiments, a recognition model for identifying blue glue detection areas corresponding to different types of defects can also be pre-trained, that is, blue glue detection areas of different defect types correspond to different positioning models. When used, the corresponding positioning model can be first determined according to the blue glue detection area corresponding to the type of defect to be detected, and the size of the blue glue detection area and the relevant parameters of the battery cell to be tested can be input into the determined positioning model, and the position of the blue glue detection area in the second battery cell image can be output.

[0203] The method described in the embodiments of the present application determines the size and position of the battery cell detection area, as well as the size and position of the blue glue detection area, by the type of defect to be detected. This can improve the accuracy of determining the battery cell detection area and the blue glue detection area to a certain extent, thereby improving the accuracy of defect detection.

[0204] In one embodiment, an implementation of determining the size of the cell detection area in the first cell image according to the type of defect to be detected and relevant parameters of the cell to be tested is shown in FIG6 , and the method includes:

[0205] S401, if the type of defect to be detected is a tab eversion defect, the battery cell detection area is determined to be the eversion area, and the size of the eversion area is determined according to the size parameters of the tab of the battery cell to be tested, the size parameters of the adapter of the battery cell to be tested and the size parameters of the weld mark of the adapter of the battery cell to be tested.

[0206] The "outward-turned area" is a cell inspection area used to detect whether a tab outward-turned defect exists in the first cell image, or to detect the type of outward-turned defect if an outward-turned defect exists. Tab dimensional parameters include the length and width of the tab; adapter dimensional parameters include the length and width of the gap between the tab and the cell; the length and width of the adapter's welding pad; the length and width of the adapter's welding pad; the length and position of any side of the tab; and the weld mark dimensional parameters of the cell under test include the number of weld points contained in the weld mark, the length of the weld mark area, and the width of the weld mark area.

[0207] The embodiment of the present application relates to a scenario where the type of defect to be detected is a tab eversion defect. In this scenario, the battery cell detection area is the eversion area. When the control device determines that the type of defect to be detected is a tab eversion defect, the area where the tab is located can be further determined on the first battery cell image, and the area around the tab close to the battery cell is used as the eversion area. The size of the area around the tab can be determined based on the size parameters of the adapter of the battery cell to be tested, the size parameters of the tab of the battery cell to be tested, and the size parameters of the weld mark of the adapter of the battery cell to be tested.

[0208] S402: If the type of the defect to be detected is a tab fold defect, the cell detection area is determined to be a fold area, and the size of the fold area is determined according to the size parameters of the tab of the cell to be tested and the size parameters of the adapter of the cell to be tested.

[0209] The folded area is another battery cell detection area, which is used to detect whether there is a tab folded defect in the first battery cell image, or to detect the type of the folded defect if there is a folded defect.

[0210] The embodiments of the present application relate to a scenario where the type of defect to be detected is a tab fold defect. In this scenario, the battery cell detection area is the fold area. When the control device determines that the type of defect to be detected is a tab fold defect, the area where the tab is located can be further determined on the first battery cell image, and the glue-coated area on the adapter can be used as the flip area, that is, the cathode tab AT11 area is used as the flip area. The size of the flip area can be determined based on the size parameters of the tab of the battery cell to be tested and the size parameters of the adapter of the battery cell to be tested.

[0211] S403: If the type of the defect to be detected is a weld mark defect, the battery cell detection area is determined to be a weld mark detection area, and the size of the weld mark detection area is determined according to the size parameters of the weld mark on the adapter in the battery cell to be tested.

[0212] The weld mark detection area is another battery cell detection area, which is used to detect whether there is a defect in the weld mark on the adapter of the battery cell in the first battery cell picture, or to detect the type of defect in the weld mark if there is a defect.

[0213] The embodiments of the present application relate to a scenario where the type of defect to be detected is a weld mark defect. In this scenario, the battery cell inspection area is a weld mark inspection area. When the control device determines that the type of defect to be detected is a weld mark defect, the control device can further determine the area where the weld mark is located on the first battery cell image and use the area where the weld mark is located as the weld mark inspection area. The size of the weld mark inspection area can be determined based on the size parameters of the weld mark on the adapter of the battery cell to be tested.

[0214] The method described in the embodiments of the present application can detect the tab eversion defect, the tab folding defect, or the weld mark defect by determining the size of the eversion area corresponding to the type of the tab eversion defect, or determining the size of the folding area corresponding to the type of the tab folding defect, or determining the size of the weld mark detection area corresponding to the type of the weld mark defect.

[0215] In one embodiment, when the type of defect to be detected is the type of tab eversion defect, the type of tab eversion defect can be divided into white eversion defect and black eversion defect, wherein the white eversion defect can refer to the angle between the everted part of the tab and the battery cell being less than or equal to 30° (the angle between the tab surface and the battery cell surface is less than or equal to 30°), and the black eversion defect can refer to the angle between the everted part of the tab and the battery cell being greater than 30° and less than 90° (the angle between the tab surface and the battery cell surface is greater than 30° and less than 90°). Therefore, the eversion area may include a first detection area and a second detection area, the first detection area being used to detect whether there is a white eversion defect of the tab in the first battery cell picture, and the second detection area being used to detect whether there is a black eversion defect of the tab in the first battery cell picture. Based on this, an implementation method of the above-mentioned S401 is provided, namely, the above-mentioned S401 "determines the size of the eversion area according to the size parameters of the tab of the battery cell to be tested, the size parameters of the adapter of the battery cell to be tested, and the size parameters of the weld mark of the adapter of the battery cell to be tested", as shown in Figure 7, the method includes:

[0216] S501 : Determine the size of a first detection area according to the size parameters of the tab of the battery cell to be tested and the size parameters of the adapter.

[0217] The tab dimensions include the tab length and tab width; the adapter dimensions include the adapter's solder pad dimensions, which include the length and position of all edges on the solder pad; and the first detection area dimensions include the first detection area's length and width.

[0218] In an embodiment of the present application, when the control device obtains the size parameters of the tab of the battery cell to be tested and the size parameters of the adapter plate based on the aforementioned steps, it can further determine the area of ​​the tab close to the battery cell to be tested based on the size parameters of the tab and the size parameters of the adapter plate to determine the size of the first detection area. For example, the size of the first detection area can be set to be consistent with or close to the size of the tab; or the size of the preset range area close to the battery cell on the adapter plate is set to the size of the first detection area. In some embodiments, the control device can determine the size of the first detection area based on the length of the tab of the battery cell to be tested and the width of the gap between the adapter plate and the battery cell to be tested; specifically, the length of the first detection area can be selected to be about 2 millimeters (mm) longer than the length of the tab, and the width of the first detection area can be selected to be consistent with or 2 mm wider than the width of the gap between the adapter plate and the battery cell to be tested. For example, refer to the schematic diagram of the eversion area shown in Figure 8, where ROI1 represents the first detection area.

[0219] S502 : Determine the size of the second inspection area according to the size parameters of the weld mark of the adapter of the battery cell to be tested.

[0220] The size parameters of the weld mark include the length and width of the area where the weld mark is located; the length of the second detection area is less than the length of the first detection area; the width of the second detection area can be the same as the width of the first detection area. The size of the second detection area includes the length and width of the second detection area.

[0221] In an embodiment of the present application, when the control device obtains the size parameters of the weld mark of the adapter sheet of the battery cell to be tested based on the aforementioned steps, it can further refer to the size parameters of the weld mark of the adapter sheet of the battery cell to be tested to determine the area of ​​the tab close to the battery cell to be tested, so as to determine the size of the second detection area. For example, the size of the second detection area can be set to be consistent with or close to the size of the area where the weld mark is located; or the size of another preset range area on the adapter sheet close to the battery cell is set to the size of the second detection area. In some embodiments, the control device can determine the size of the second detection area based on the length and width of the weld mark of the adapter sheet of the battery cell to be tested; specifically, the length of the second detection area can be selected to be equal to the length of the weld mark, and the width of the second detection area can be selected to be equal to the width of the weld mark. Alternatively, the length of the second detection area can be selected to be 2 mm longer than the length of the weld mark, and the width of the second detection area can be selected to be 2 mm longer than the width of the weld mark; for example, see the schematic diagram of the eversion area shown in Figure 9, where ROI2 represents the second detection area.

[0222] The method described in the embodiments of the present application can detect white and black tab eversion defects by determining the sizes of the first and second detection areas in the eversion area corresponding to the type of tab eversion defect.

[0223] In one embodiment, when the type of defect to be detected is a tab fold defect, an implementation method for determining the size of the folding area is provided, namely, determining the size of the folding area based on the length of the tab of the battery cell to be tested and the width of the gap between the adapter and the battery cell to be tested.

[0224] In some embodiments, the control device can determine the size of the folded region based on the length of the tab of the cell to be tested and the width of the gap between the adapter and the cell to be tested. Specifically, the length of the folded region can be selected to be approximately 2 mm longer than the tab length, and the width of the folded region can be selected to be the same as or 2 mm wider than the width of the gap between the adapter and the cell to be tested. For example, referring to the schematic diagram of the folded region shown in FIG10 , ROI3 represents the folded region.

[0225] The method described in the embodiments of the present application can detect the tab fold defect by determining the size of the folded area corresponding to the type of the tab fold defect.

[0226] In one embodiment, when the control device determines the size of the battery cell detection area based on the method described in any of the aforementioned embodiments, the position of the battery cell detection area on the first battery cell image can be further located. Based on this, an implementation method for determining the position of the battery cell detection area in the first battery cell image is provided, that is, when the control device executes S303 in the embodiment of Figure 5 "Determine the position of the battery cell detection area in the first battery cell image according to the size of the battery cell detection area and the relevant parameters of the battery cell to be tested", the specific execution steps are: according to the position of the intersection of the first side and the second side, and combined with the size of the battery cell detection area, the battery cell detection area in the first battery cell image is located to determine the position of the battery cell detection area in the first battery cell image; the first side and the second side are two intersecting sides of the adapter in the first battery cell image.

[0227] Among them, the two edges are any two intersecting edges on the adapter. For example, see the two intersecting edges of L1 and L2 on the left adapter in Figure 11, the corresponding intersection point is A1; the two intersecting edges of L3 and L4 on the right adapter, the corresponding intersection point is A2.

[0228] An embodiment of the present application relates to a method for locating a battery cell detection area using a grabbing method. Specifically, the control device can binarize the first battery cell image, process the first battery cell image into a black and white image, and then grab the edges of the processed image from left to right and from black to white to grab the first edge (see the L1 edge shown in Figure 11); then grab the edges of the processed image from top to bottom and from black to white to grab the second edge (see the L2 edge shown in Figure 11), and then determine the first edge and the second edge and the intersection point (see the intersection A1 of L1 and L2 shown in Figure 11); or, the control device can grab the edges of the processed image from right to left and from black to white to grab the third edge (see the L3 edge shown in Figure 11), and then grab the edges of the processed image from top to bottom and from black to white to grab the fourth edge (see the L4 edge shown in Figure 11), and then determine the third edge and the fourth edge and the intersection point (see the intersection A2 of L3 and L4 shown in Figure 11). Finally, the position of the intersection (A1 or A2), the distance between the intersection and the tab, and the size of the cell detection area are used to locate the cell detection area and determine the position of the cell detection area in the first cell image. Specifically, the position coordinates of the pixel points can be used. The distance between the intersection and the tab can be predetermined based on the type or size of the cell in the first cell image.

[0229] The detection method described in the embodiment of the present application locates the battery cell detection area by grasping the edge, which is simple and efficient to implement and can improve the efficiency of locating the battery cell detection area to a certain extent, thereby improving the detection efficiency.

[0230] In one embodiment, an implementation method for determining the size of the blue glue detection area in the second battery cell image according to the type of defect to be detected and relevant parameters of the battery cell to be tested is shown in FIG12 , and the method includes:

[0231] S601: If the type of defect to be detected is whether the blue glue has defects, determine the blue glue detection area as the glue area, and determine the size of the glue area according to the size parameters of the weld mark of the adapter of the battery cell to be tested.

[0232] The glue area is a blue glue detection area used to detect whether there is a blue glue defect in the second battery cell image. The size parameters of the weld mark include the length and width of the area where the weld mark is located.

[0233] The embodiments of the present application relate to a scenario where the type of defect to be detected is the presence or absence of a blue adhesive defect. In this scenario, the blue adhesive detection area is the adhesive bonding area. When the control device determines that the type of defect to be detected is the presence or absence of a blue adhesive defect, the adhesive bonding area can be further determined on the first battery cell image, and the size of the adhesive bonding area can be determined based on the size parameters of the weld mark on the adapter of the battery cell to be tested.

[0234] S602: If the type of the defect to be detected is a blue glue offset defect or an adapter polarity defect, the blue glue detection area is determined to be a pad area, and the size of the pad area is determined according to the size parameters of the pad in the adapter of the battery cell to be tested.

[0235] Among them, the pad area is another blue glue detection area, which is used to detect whether there is a blue glue offset defect or an adapter polarity defect in the second battery cell image.

[0236] The embodiments of the present application relate to a scenario where the type of defect to be detected is a blue glue offset defect or an adapter polarity defect. In this scenario, the blue glue detection area is the pad area. When the control device determines that the type of defect to be detected is a blue glue offset defect or an adapter polarity defect, the pad area can be further determined on the second battery cell image, and the size of the pad area can be determined based on the size parameters of the pad in the adapter of the battery cell to be tested.

[0237] S603: If the type of defect to be detected is a drain tab defect, the blue glue detection area is determined to be the area around the tab, and the size of the area around the tab is determined based on the size parameters and position of the pad in the adapter of the battery cell to be tested.

[0238] Among them, the area around the tab is another blue glue detection area, which is used to detect whether there is a leakage tab defect in the second battery cell image.

[0239] The embodiments of the present application relate to a scenario where the type of defect to be detected is a drain tab defect. In this scenario, the blue glue detection area is the area around the tab. When the control device determines that the type of defect to be detected is a drain tab defect, the area around the tab can be further determined on the second battery cell image, and the size of the area around the tab can be determined based on the size parameters and position of the pads on the adapter of the battery cell to be tested.

[0240] The method described in the embodiments of the present application can detect whether there are defects in the blue glue, or defects in the tab folding, or defects in the blue glue offset, or defects in the polarity of the adapter, or defects in the drain tab by determining the size of the glue area, or determining the size of the pad area, or determining the size of the area around the tab.

[0241] In one embodiment, when the type of defect to be detected is the type of whether the blue glue has defects, the corresponding blue glue detection area is the glue area. Based on this, an implementation method of the above-mentioned S601 is provided, that is, the above-mentioned S601 "determines the size of the glue area according to the size parameters of the weld mark of the adapter of the battery cell to be tested", including: determining the size of the glue area according to the length of the area where the weld mark of the adapter is located, and the width of the area where the weld mark of the adapter is located.

[0242] In an embodiment of the present application, when the control device obtains the size parameters of the weld mark of the adapter of the battery cell to be tested based on the aforementioned steps, the length of the area where the weld mark is located can be directly used as the length of the glue area, and the width of the area where the weld mark is located can be used as the width of the glue area. In some embodiments, the length of the glue area can also be set based on the length of the area where the weld mark is located, combined with a preset length threshold, and the width of the glue area can be set based on the width of the area where the weld mark is located, combined with a preset width threshold. For example, the length of the glue area can be selected to be about 2 mm longer than the length of the area where the weld mark is located, and the width of the glue area can be selected to be about 2 mm longer than the width of the area where the weld mark is located. For example, see the schematic diagram of the glue area shown in Figure 13, where ROI4 represents the glue area.

[0243] The method described in the embodiment of the present application can detect whether the blue glue has defects by determining the size of the glue-applying area corresponding to the type of blue glue defects.

[0244] In one embodiment, when the control device determines the size of the glue area based on the method described in any of the aforementioned embodiments, the position of the glue area on the second battery cell picture can be further located. Based on this, an implementation method for determining the position of the glue area in the second battery cell picture is provided, that is, when the control device executes S304 in the embodiment of Figure 5 "Determine the position of the blue glue detection area in the second battery cell picture according to the size of the blue glue detection area and the relevant parameters of the battery cell to be tested", the specific execution steps are: according to the position of the intersection of the third side and the fourth side, and in combination with the size of the glue area, locate the glue area in the second battery cell picture to determine the position of the glue area in the second battery cell picture; the third side and the fourth side are two intersecting sides of the adapter in the second battery cell picture. Alternatively, the position of the glue area in the second battery cell picture is determined according to the position of the area where the weld mark of the battery cell to be tested is located.

[0245] Among them, the two edges are any two intersecting edges on the adapter. For example, see the two edges of L5 and L6 intersecting on the left adapter in Figure 13, the corresponding intersection point is A3; the two edges of L7 and L8 intersecting on the right adapter, the corresponding intersection point is A4.

[0246] The embodiment of the present application relates to a method for locating the blue glue detection area by using the edge-grabbing method. Specifically, the control device can binarize the second battery cell image, process the second battery cell image into a black and white image, and then perform edge-grabbing on the processed image from left to right and from black to white to grab the third edge (see edge L6 shown in Figure 13); then perform edge-grabbing on the processed image from top to bottom and from black to white to grab the fourth edge (see edge L5 shown in Figure 13), and then determine the third edge and the fourth edge and the intersection point (see intersection A3 of L5 and L6 shown in Figure 13); or, the control device can perform edge-grabbing on the processed image from right to left and from black to white to grab the fifth edge (see edge L8 shown in Figure 13), and then perform edge-grabbing on the processed image from top to bottom and from black to white to grab the sixth edge (see edge L7 shown in Figure 13), and then determine the fifth edge and the sixth edge and the intersection point (see intersection A4 of L7 and L8 shown in Figure 13). Finally, the position of the intersection (A3 or A4) is used, the distance relationship between the intersection and the location of the weld mark is considered, and the size of the glue area is combined to realize the positioning of the glue area, and the position of the glue area in the second battery cell image is determined, which can be specifically represented by the position coordinates of the pixel points. The distance relationship between the above-mentioned intersection and the location of the weld mark can be predetermined based on the type of battery cell, the type of adapter, the size of the battery cell and the size of the adapter in the second battery cell image. In some embodiments, since the size and position of the glue area are basically the same or similar to the area where the weld mark is located, the control device can directly determine the position of the area where the weld mark of the battery cell to be tested is located as the position of the glue area in the second battery cell image.

[0247] The detection method described in the embodiment of the present application locates the glued area by grabbing the edge, which is simple and efficient to implement and can improve the efficiency of locating the glued area to a certain extent, thereby improving the detection efficiency.

[0248] In one embodiment, when the type of defect to be detected is a blue glue offset defect or a adapter polarity defect, an implementation method for determining the size of the pad area is provided, that is, the size of the pad area is determined according to the size parameters of the pad in the adapter of the battery cell to be tested.

[0249] In some embodiments, the control device can determine the size of the pad area according to the size of the area where the pad is located on the cell to be tested, for example, the size of the pad area is set to be consistent with the size of the area where the pad is located on the cell to be tested; in some embodiments, the size of the pad area can also be set to be within a certain range smaller than the size of the area where the pad is located on the cell to be tested. For example, the length of the pad area can be selected to be smaller than the size of the area where the pad is located to determine the size of the pad area. For example, the length of the pad area is set to be about 1mm shorter than the length of the solder joint on the cell to be tested, and the width of the pad area is selected to be about 1mm shorter than the width of the solder joint on the cell to be tested. In some embodiments, the control device can divide the area where the pad is located into an area of ​​a preset range, which can be a circular area, a rectangular area, or an area of ​​other shapes; and then use the divided area as the pad area, and determine the size of the pad area according to the size parameters of the divided area. For example, see the schematic diagram shown in Figure 14, where ROI5 represents the pad area.

[0250] In some embodiments, an implementation method for determining the size of a pad area is further provided, as shown in FIG15 . The implementation method includes:

[0251] S701, determine the protrusion area or the pit area of ​​the pad in the adapter of the battery cell to be tested; if the protrusion area or the pit area is a circular area, execute step S702; if the protrusion area or the pit area is a rectangular area, execute step S703.

[0252] In an embodiment of the present application, the control device can identify or detect the raised features or recessed features of the image of the area where the solder pad is located in the second battery cell image. The specific method can be implemented using an existing image feature recognition or detection algorithm, or other methods.

[0253] S702 , determining the size of the pad area according to the diameter of the protrusion area or the recess area.

[0254] The embodiments of the present application relate to a scenario where the pad area is a protrusion area or a pit area, and the protrusion area or the pit area is a circular area. In this scenario, parameters such as the area or perimeter of the protrusion area or the pit area can be directly calculated based on the diameter of the protrusion area or the pit area, and the size of the pad area can be determined based on these parameters.

[0255] S703 , determining the size of the pad region according to the length of the protrusion region or the concave region and the width of the protrusion region or the concave region.

[0256] The embodiments of the present application relate to a scenario where the pad area is a protrusion area or a pit area, and the protrusion area or the pit area is a rectangular area. In this scenario, parameters such as the area or perimeter of the protrusion area or the pit area can be directly calculated based on the length of the protrusion area or the pit area and the width of the protrusion area or the pit area, and the size of the pad area can be determined based on these parameters.

[0257] The method described in the embodiments of the present application can detect blue glue offset defects or adapter polarity defects by determining the size of the pad area corresponding to the type of blue glue offset defects or adapter polarity defects.

[0258] In some embodiments, another implementation method for determining the size of the pad area is provided, as shown in Figure 15. The implementation method includes: determining the size of the pad area based on the length of the area where the pad is located in the adapter of the battery cell to be tested, and based on the width of the area where the pad is located in the adapter; or, determining the size of the pad area based on the size parameters of the protrusion area or the pit area of ​​the pad in the adapter.

[0259] In an embodiment of the present application, the control device can directly set the size of the area where the pad is located to be consistent with the size of the pad area, for example, directly set the length of the area where the pad is located to be consistent with the length of the pad area, and directly set the width of the area where the pad is located to be consistent with the width of the pad area; in some embodiments, the control device can determine the size of the pad area by detecting the size parameters of the protrusion area or the pit area of ​​the pad in the adapter based on the method described in the aforementioned embodiments.

[0260] The method described in the embodiments of the present application can detect blue glue offset defects or adapter polarity defects by determining the size of the pad area corresponding to the type of blue glue offset defects or adapter polarity defects.

[0261] In one embodiment, when the control device determines the size of the pad area based on the method described in any of the aforementioned embodiments, the position of the pad area on the second battery cell image can be further located. Based on this, an implementation method for determining the position of the pad area in the second battery cell image is provided, that is, when the control device executes S304 in the embodiment of Figure 5 "Determine the position of the blue glue detection area in the second battery cell image according to the size of the blue glue detection area and the relevant parameters of the battery cell to be tested", the specific execution steps are: according to the position of the pad of the adapter in the battery cell to be tested, and combined with the size of the pad area, the pad area in the second battery cell image is located to determine the position of the pad area in the second battery cell image.

[0262] In an embodiment of the present application, after the control device determines the size of the pad area, it can further determine the position of the pad and the position of the area where the pad is located by identifying the pad in the second battery cell image, and then determine the position of the pad area based on the position of the pad or the position of the area where the pad is located. For example, referring to the figure shown in Figure 16, ROI5 represents the pad area, and the rectangular area ROI6 where the circular ROI5 area is located represents the area where the pad is located.

[0263] The detection method described in the embodiment of the present application locates the pad area by identifying the pad. The implementation is simple and efficient, and can improve the efficiency of locating the pad area to a certain extent, thereby improving the detection efficiency.

[0264] In one embodiment, when the type of defect to be detected is a drain ear defect, the corresponding blue glue detection area is the area around the ear. Based on this, an implementation method of the above-mentioned S603 is provided, that is, the above-mentioned S603 "determines the size of the area around the ear according to the size parameters of the pad in the adapter of the battery cell to be tested and the position of the pad", including: determining the size of the area around the ear according to the length of the area where the pad is located in the adapter of the battery cell to be tested and the distance between the pad and the battery cell to be tested.

[0265] In an embodiment of the present application, when the control device obtains the size parameters of the area where the weld mark of the adapter of the battery cell to be tested is located based on the aforementioned steps, the length of the area where the weld mark is located can be directly used as the length of the area around the tab, and the distance between the pad and the battery cell to be tested can be used as the width of the area around the tab. In some embodiments, the length of the area around the tab can also be set based on the length of the area where the weld mark is located, combined with a preset length threshold, and the width of the area around the tab can be set based on the distance between the pad and the battery cell to be tested, combined with a preset width threshold. For example, the length of the area around the tab can be selected to be about 2 mm shorter than the length of the area where the weld mark is located, and the width of the area around the tab can be selected to be about 1 mm shorter than the distance between the pad and the battery cell to be tested. For example, see the schematic diagram of the area around the tab shown in Figure 17, where ROI7 represents the area around the tab.

[0266] The method described in the embodiments of the present application can detect drain ear defects by determining the size of the area around the ear corresponding to the type of drain ear defect.

[0267] In some embodiments, the area around the tab may include a first area around the first tab, a second area around the first tab, a first area around the second tab, and a second area around the second tab. The method of “determining the size of the area around the tab based on the length of the area where the pad is located in the adapter of the battery cell to be tested and the distance between the pad and the battery cell to be tested” is provided, as shown in FIG18 , and includes:

[0268] S801, determining the length of the first surrounding area of ​​the first tab, the length of the second surrounding area of ​​the first tab, the length of the first surrounding area of ​​the second tab, and the length of the second surrounding area of ​​the second tab based on the length of the area where the solder pad is located in the adapter of the battery cell to be tested.

[0269] S802, determining a width of a first surrounding area of ​​the first tab and a width of a second surrounding area of ​​the first tab according to a first distance between the welding pad and the battery cell to be tested;

[0270] S803 : Determine a width of a first peripheral region of the second tab and a width of a second peripheral region of the second tab according to a second distance between the welding pad and the battery cell to be tested.

[0271] In the embodiment of the present application, referring to the schematic diagram shown in FIG19 , ROI8 or ROI13 represents a first peripheral region of the first tab, ROI9 or ROI12 represents a second peripheral region of the first tab, ROI10 or ROI15 represents a first peripheral region of the second tab, and ROI11 or ROI14 represents a second peripheral region of the second tab. The sizes of these regions may be the same or different. Specifically, the length of the area where the pad is located in the adapter of the battery cell to be tested can be directly determined as the length of the first surrounding area (ROI8 or ROI13) of the first pole lug, the length of the second surrounding area (ROI9 or ROI12) of the first pole lug, the length of the first surrounding area (ROI10 or ROI15) of the second pole lug, and the length of the second surrounding area (ROI11 or ROI14) of the second pole lug; in some embodiments, based on the length of the area where the pad is located, combined with the incremental or decremental length threshold, the length of the first surrounding area of ​​the first pole lug, the length of the second surrounding area of ​​the first pole lug, the length of the first surrounding area of ​​the second pole lug, and the length of the second surrounding area of ​​the second pole lug can be set respectively. It should be noted that each surrounding area can correspond to the same incremental or decremental length threshold, or can correspond to a different incremental or decremental length threshold;

[0272] In some embodiments, the first distance between the solder pad and the cell to be tested can be directly determined as the width of the first surrounding area (ROI8 or ROI13) of the first tab and the width of the second surrounding area (ROI9 or ROI12) of the first tab; in some embodiments, the width of the first surrounding area of ​​the first tab and the width of the second surrounding area of ​​the first tab can be set based on the first distance between the solder pad and the cell to be tested, combined with the incremental or decremental first width threshold. It should be noted that each surrounding area can correspond to the same incremental or decremental width threshold, or can correspond to a different incremental or decremental width threshold. Refer to the schematic diagram shown in Figure 19, where D1 represents the first distance, 1 represents the cell to be tested, 2 represents the adapter, 3 represents the tab, and 4 represents the blue glue. The first width threshold can be determined in advance according to actual detection requirements.

[0273] In some embodiments, the second distance between the pad and the cell to be tested can be directly determined as the width of the first surrounding area (ROI10 or ROI15) of the second tab and the width of the second surrounding area (ROI11 or ROI14) of the second tab; in some embodiments, the width of the first surrounding area (ROI10 or ROI15) of the second tab and the width of the second surrounding area (ROI11 or ROI14) of the second tab can be set based on the second distance between the pad and the cell to be tested, combined with the incremental or decremental second width threshold. It should be noted that each surrounding area can correspond to the same incremental or decremental width threshold, or can correspond to a different incremental or decremental width threshold. Refer to the schematic diagram shown in Figure 19, where D1 represents the first distance, 1 represents the cell to be tested, 2 represents the adapter, 3 represents the tab, and 4 represents the blue glue. The second width threshold can be determined in advance according to actual detection requirements.

[0274] The method described in the embodiment of the present application can detect leakage tab defects by determining the size of the area around the tab, and the area around the tab basically covers all areas where the tab may leak.

[0275] In one embodiment, when the control device determines the size of the area around the tab based on the method described in any of the foregoing embodiments, the position of the area around the tab on the second battery cell image can be further located. Based on this, an implementation method for determining the position of the area around the tab in the second battery cell image is provided, that is, when the control device executes S304 in the embodiment of Figure 5 "Determining the position of the blue glue detection area in the second battery cell image according to the size of the blue glue detection area and the relevant parameters of the battery cell to be tested", as shown in Figure 20, the specific execution steps are:

[0276] S901, locate the first surrounding area of ​​the first tab in the second battery cell image based on the position of the intersection of the fifth side and the sixth side and in combination with the size of the first surrounding area of ​​the first tab, and determine the position of the first surrounding area of ​​the first tab; the fifth side and the sixth side are two intersecting sides of the adapter in the second battery cell image.

[0277] Among them, the two edges are any two intersecting edges of the head or pad part on the adapter. For example, see the two intersecting edges of L11 and L12 on the adapter on the left in Figure 19, the corresponding intersection point is AL1; or, the two intersecting edges of L14 and L15 on the adapter on the right in the figure, the corresponding intersection point is AL3.

[0278] The embodiment of the present application relates to a method for locating the first surrounding area of ​​the first electrode by using the edge grabbing method. Specifically, the control device can perform binarization processing on the second battery cell image, process the second battery cell image into a black and white image, and then perform edge grabbing from left to right and from black to white on the processed image to grab the fifth edge (see the L12 edge shown in Figure 19); then perform edge grabbing from top to bottom and from black to white on the processed image to grab the sixth edge (see the L11 edge shown in Figure 19), and then determine the first edge. The fifth and sixth sides and the intersection point (see the intersection AL1 of L11 and L12 shown in Figure 19); or, the control device can grab the edges of the processed image from right to left and from black to white, grab the fifth side (see the L15 side shown in Figure 19), and then grab the edges of the processed image from top to bottom and from black to white, grab the sixth side (see the L14 side shown in Figure 19), and then determine the fifth and sixth sides and the intersection point (see the intersection AL3 of L14 and L15 shown in Figure 19). Finally, using the position of the intersection point (AL1 or AL3), considering the distance relationship between the intersection point and the position of the first tab, and combining the size of the first surrounding area of ​​the first tab to achieve the positioning of the first surrounding area of ​​the first tab, the position of the first surrounding area of ​​the first tab in the second battery cell image is determined, which can be specifically represented by the position coordinates of the pixel points. The distance relationship between the above-mentioned intersection and the position of the first tab can be predetermined based on the type of battery cell, the type of adapter, the type of tab, the size of the battery cell, the size of the adapter and the size of the tab in the second battery cell picture.

[0279] S902 : Determine the position of the second surrounding area of ​​the first tab according to the length of the first blue glue in the battery cell to be tested and the position of the first surrounding area of ​​the first tab.

[0280] The length of the first blue glue refers to the blue glue covering the first tab of the battery cell to be tested, and the length can be determined according to the pasting requirements of the blue glue covering the first tab.

[0281] In the embodiment of the present application, when the control device determines the position of the first surrounding area of ​​the first tab based on the aforementioned steps, the control device can further determine the position of the second surrounding area of ​​the first tab based on the length of the first blue glue on the basis of the position. For example, referring to FIG19 , after the position of the first surrounding area ROI8 of the first tab is determined, the first blue glue length can be moved rightward based on the position, and the position after the movement is determined as the position of the second surrounding area ROI9 of the first tab. Alternatively, after the position of the first surrounding area ROI13 of the first tab is determined, the first blue glue length can be moved rightward based on the position, and the position after the movement is determined as the position of the second surrounding area ROI12 of the first tab.

[0282] S903, positioning the first surrounding area of ​​the second electrode tab in the second battery cell image according to the position of the intersection of the seventh side and the eighth side and in combination with the size of the first surrounding area of ​​the second electrode tab, and determining the position of the first surrounding area of ​​the second electrode tab; the seventh side and the eighth side are two intersecting sides of the adapter in the second battery cell image.

[0283] Among them, the two edges are any two intersecting edges of the head or pad part on the adapter. For example, see the two intersecting edges of L12 and L13 on the adapter on the left in Figure 19, the corresponding intersection point is AL2; or, the two intersecting edges of L15 and L16 on the adapter on the right in the figure, the corresponding intersection point is AL4.

[0284] The embodiment of the present application relates to a method for locating the first surrounding area of ​​the second electrode by using the edge grabbing method. Specifically, the control device can perform binarization processing on the second battery cell image, process the second battery cell image into a black and white image, and then perform edge grabbing from left to right and from black to white on the processed image to grab the seventh edge (see the L12 edge shown in Figure 19); then perform edge grabbing from bottom to top and from black to white on the processed image to grab the eighth edge (see the L13 edge shown in Figure 19), and then determine the first edge. The seventh side and the eighth side and the intersection (see the intersection AL2 of L12 and L13 shown in Figure 19); or, the control device can grab the edge of the processed image from right to left, from black to white, grab the seventh side (see the L15 side shown in Figure 19), and then grab the edge of the processed image from bottom to top, from black to white, grab the eighth side (see the L16 side shown in Figure 19), and then determine the seventh side and the eighth side and the intersection (see the intersection AL4 of L15 and L16 shown in Figure 19). Finally, using the position of the intersection (AL2 or AL4), considering the distance relationship between the intersection and the position of the second pole lug, and combining the size of the first surrounding area of ​​the second pole lug to achieve the positioning of the first surrounding area of ​​the second pole lug, the position of the first surrounding area of ​​the second pole lug in the second battery cell image is determined, which can be specifically represented by the position coordinates of the pixel points. The distance relationship between the above-mentioned intersection and the position of the second tab can be predetermined based on the type of battery cell, the type of adapter, the type of tab, the size of the battery cell, the size of the adapter and the size of the tab in the second battery cell picture.

[0285] S904 : Determine the position of the second surrounding area of ​​the second electrode tab according to the length of the second blue glue in the battery cell to be tested and the position of the first surrounding area of ​​the second electrode tab.

[0286] Among them, the length of the second blue glue refers to the blue glue covering the second pole ear of the battery cell to be tested, and its length can be determined according to the pasting requirements of the blue glue covering the second pole ear.

[0287] In the embodiment of the present application, when the control device determines the position of the first surrounding area of ​​the second pole tab based on the aforementioned steps, the position of the second surrounding area of ​​the second pole tab can be further determined based on the length of the second blue glue on the basis of the position. For example, referring to FIG19 , after the position of the first surrounding area ROI10 of the second pole tab is determined, the first blue glue length can be moved rightward based on the position, and the position after the movement is determined as the position of the second surrounding area ROI11 of the second pole tab. Alternatively, after the position of the first surrounding area ROI15 of the second pole tab is determined, the second blue glue length can be moved rightward based on the position, and the position after the movement is determined as the position of the second surrounding area ROI14 of the second pole tab.

[0288] The detection method described in the embodiment of the present application locates the first surrounding area of ​​the first pole lug, the second surrounding area of ​​the first pole lug, the first surrounding area of ​​the second pole lug, and the second surrounding area of ​​the second pole lug by grasping the edges. The implementation method is simple and efficient, and can improve the efficiency of locating the areas around the pole lugs to a certain extent, thereby improving the detection efficiency.

[0289] In one embodiment, a method for performing defect detection on a cell detection area and a blue glue detection area is provided, as shown in FIG21 , and the method includes:

[0290] S1001, perform a first defect detection on the battery cell detection area to obtain a first detection result; the first defect includes one of a tab eversion defect, a tab folding defect, a tab cracking defect and a weld mark defect.

[0291] S1002, performing a second defect detection on the blue glue detection area to obtain a second detection result; the second defect includes one of a blue glue defect, a blue glue offset defect, a transfer sheet polarity defect, and a drain ear defect.

[0292] In an embodiment of the present application, when the control device determines the battery cell detection area and the blue glue detection area based on the above steps, it can detect the tab eversion defect, the tab folding defect, the tab cracking defect, or the weld mark defect based on the battery cell detection area; and detect the presence or absence of blue glue defects, blue glue offset defects, adapter polarity defects, and drain tab defects based on the blue glue detection area.

[0293] The method described in the embodiment of the present application realizes a series of defect detections before the tested battery cell is glued, as well as a series of defect detections after the glue is glued, with clear division of labor, and can realize comprehensive detection of the tested battery cell.

[0294] In one embodiment, when detecting a tab eversion defect, the cell detection area includes a tab fold detection area, and the tab fold detection area includes an eversion area, and the eversion area includes a first cell detection area for detecting white eversion defects and a second cell detection area for detecting black eversion defects. In this scenario, a method for defect detection based on the cell detection area is provided, as shown in FIG22 , that is, the above-mentioned S1001 “detecting a first defect in the cell detection area to obtain a first detection result” includes:

[0295] S1101 , performing binarization processing on the image of the first battery cell detection area and the image of the second battery cell detection area to obtain a first processed image and a second processed image.

[0296] In an embodiment of the present application, when the control device determines the first battery cell detection area and the second battery cell detection area in the first battery cell image, it can further extract the image of the first battery cell detection area and the image of the second battery cell detection area therefrom, and then binarize the image of the first battery cell detection area and the image of the second battery cell detection area, that is, convert the image of the first battery cell detection area and the image of the second battery cell detection area into black and white images (the grayscale value of each pixel on the image ranges from black to white 0-255), so that defect detection can be performed based on the black and white images later.

[0297] S1102, perform a first-category defect detection on the first processed image, and obtain an intermediate detection result; if the intermediate detection result indicates that the first-category defect is detected, execute step S1103; if the intermediate detection result indicates that the first-category defect is not detected, execute step S104.

[0298] The first type of defect detection is the detection of white eversion defects, that is, the detection of white objects. The first detection result in this scenario indicates whether the first type of defect can be detected, that is, whether the first type of defect exists in the first processed image.

[0299] S1103 , determining that the test result indicates that the battery cell to be tested has a first type of defect.

[0300] In an embodiment of the present application, when the control device obtains the first processed image, it may first perform a first-category defect detection on the first processed image. In some embodiments, a pre-trained detection model may be used to detect the first processed image to obtain an intermediate detection result. When the intermediate detection result indicates that a first-category defect has been detected, the detection may be stopped, and a final first detection result may be determined to indicate that the tested cell has a first-category defect, i.e., a white fold-over defect.

[0301] In some embodiments, the control device performs a first-category defect detection on the first processed image in the tab eversion defect. When an intermediate detection result is obtained, the following specific steps can be performed: determining whether the battery cell detection area of ​​the first processed image contains pixels whose grayscale values ​​are within the first grayscale threshold range; if the battery cell detection area contains pixels whose grayscale values ​​are within the first grayscale threshold range, then determining that the intermediate detection result indicates that the first-category defect is detected; if the battery cell detection area does not contain pixels whose grayscale values ​​are within the first grayscale threshold range, then determining that the intermediate detection result indicates that the first-category defect is not detected.

[0302] In an embodiment of the present application, the control device can set a first grayscale threshold range (for example, 230-255) for white flip-over defect detection. During specific detection, the control device can compare the grayscale value of each pixel point on the battery cell detection area in the first processed image with the first grayscale threshold range to determine whether the battery cell detection area contains pixels whose grayscale values ​​are within the first grayscale threshold range. If so, it means that a white flip-over defect is detected in the battery cell detection area, that is, it is determined that the intermediate detection result indicates that a first-class defect is detected; if not, it means that no white flip-over defect is detected in the battery cell detection area, that is, it is determined that the intermediate detection result indicates that no first-class defect is detected. In some embodiments, since false detection may occur when detecting the white tab defect, an area lower limit threshold may be set when performing first-type defect detection on the first battery cell detection area. The area lower limit threshold can be used to filter or eliminate interference for the first-type defects. Specifically, the control device may determine the area characteristics of the corresponding type of defect based on the characteristics of the actual white tab defect, and then determine an area lower limit threshold based on the area characteristics. Then, when detecting the white tab defect, the area corresponding to the characteristics of the white tab defect may be calculated first, and finally, whether the white tab defect is a true white tab defect may be determined based on the area and the area lower limit threshold. For example, when the area and the area lower limit threshold are inconsistent, or the difference value exceeds a preset range, it can be determined that the white tab defect is a true white tab defect; when the area and the area lower limit threshold are consistent, or the difference value does not exceed the preset range, it can be determined that the white tab defect is not a true white tab defect.

[0303] S1104 , performing a second type of defect detection of tab eversion defects on the second processed image to obtain a first detection result.

[0304] The second type of defect detection is the detection of black fold-over defects, that is, the detection of black objects. The first detection result in this scenario indicates whether the second type of defect can be detected, that is, whether the second type of defect exists in the second processed image.

[0305] In an embodiment of the present application, when the intermediate detection result indicates that a second type of defect is detected, detection can be continued. Specifically, the second type of defect detection is performed on the second processed image. In some embodiments, a pre-trained detection model can also be used to detect the second processed image to obtain the first detection result.

[0306] In some embodiments, the control device performs a second-type defect detection on the second processed image. When obtaining the first detection result, the following specific steps can be performed: determining whether the battery cell detection area of ​​the second processed image contains pixels whose grayscale values ​​are within the second grayscale threshold range (for example, 0-120); if the battery cell detection area of ​​the second processed image contains pixels whose grayscale values ​​are within the second grayscale threshold range, then determining that the first detection result indicates that a second-type defect is detected; if the battery cell detection area of ​​the second processed image does not contain pixels whose grayscale values ​​are within the second grayscale threshold range, then determining that the first detection result indicates that no second-type defect is detected.

[0307] In an embodiment of the present application, the control device can set a second grayscale threshold range (for example, 0-120) for black flip-over defect detection. During specific detection, the control device can compare the grayscale value of each pixel point on the battery cell detection area in the second processed image with the second grayscale threshold range to determine whether the battery cell detection area contains pixel points whose grayscale values ​​are within the second grayscale threshold range. If so, it means that a black flip-over defect is detected in the battery cell detection area, that is, it is determined that the first detection result indicates that a second type of defect is detected; if not, it means that a black flip-over defect is not detected in the battery cell detection area, that is, it is determined that the first detection result indicates that a second type of defect is detected. In some embodiments, since false detection may occur when detecting the black tab eversion defect, an area lower limit threshold may be set when detecting the second type of defects in the second battery cell detection area. The area lower limit threshold can be used to filter out or eliminate interference for the second type of defects. Specifically, the control device can determine the area characteristics of the corresponding type of defect based on the characteristics of the actual black tab eversion defect, and then determine an area lower limit threshold based on the area characteristics. Then, when detecting the black tab eversion defect, the area corresponding to the characteristics of the black tab eversion defect can be calculated first, and finally, whether the black tab eversion defect is a true black tab eversion defect can be determined based on the area and the area lower limit threshold. For example, when the area and the area lower limit threshold are inconsistent, or the difference value exceeds the preset range, it can be determined that the black tab eversion defect is a true black tab eversion defect; when the area and the area lower limit threshold are consistent, or the difference value does not exceed the preset range, it can be determined that the black tab eversion defect is not a true black tab eversion defect.

[0308] The detection method described in the embodiments of the present application can detect both white tab fold-out defects and black tab fold-out defects, and the detection areas corresponding to the white tab fold-out defects and the black tab fold-out defects are different. Therefore, the detection area corresponding to the white tab fold-out defect is first detected, and in the scenario where the white tab fold-out defect is not detected, the detection area corresponding to the black tab fold-out defect is then detected, which can improve the detection efficiency to a certain extent. In some embodiments, the above method detects both white tab fold-out defects and black tab fold-out defects by setting a first grayscale threshold range corresponding to the white tab fold-out defect and a second grayscale threshold range corresponding to the black tab fold-out defect. This method is easy to implement and can improve the detection efficiency to a certain extent.

[0309] In one embodiment, when the type of defect to be detected is a tab fold defect, the battery cell detection area includes a tab fold detection area, and the tab fold detection area includes a fold area. In this scenario, a method for defect detection based on the fold area is provided, as shown in FIG23 , that is, the above-mentioned S1001 “perform a first defect detection on the battery cell detection area to obtain a first detection result” includes:

[0310] S1201, performing binarization processing on the image in the folded area to obtain a processed third processed image.

[0311] In an embodiment of the present application, when the control device determines the folded area in the first battery cell image, it can further extract an image of the folded area therefrom, and then perform binarization processing on the image of the folded area, that is, convert the image of the folded area into a black and white image (the grayscale value of each pixel on the image ranges from black to white 0-255), so that defect detection can be performed based on the black and white image later.

[0312] In some embodiments, the fold area may also include a third battery cell detection area for detecting white fold defects, and a fourth battery cell detection area for detecting black fold defects. In this scenario, a method for defect detection based on the fold area may also be provided. This method is basically consistent with the detection method described in the embodiment of Figure 11. For detailed description, please refer to the above content and will not be repeated here.

[0313] S1202: Detect the tab folding defect on the third processed image to obtain a first detection result.

[0314] In an embodiment of the present application, when the control device obtains the third processed image, the third processed image can be subjected to tab fold defect detection. In some embodiments, a pre-trained fold defect detection model can be used to detect the third processed image to obtain a first detection result.

[0315] In some embodiments, when the folding area includes a third battery cell detection area and a fourth battery cell detection area, the control device may first perform a first type of defect detection (white folding defect detection) on the third processed image. In some embodiments, a pre-trained detection model may be used to detect the third processed image to obtain an intermediate detection result. When the intermediate detection result indicates that a first type of defect is detected, the detection may be stopped, and it may be determined that the final first detection result indicates that a first type of defect exists in the battery cell to be tested, i.e., a white folding defect exists. When the intermediate detection result indicates that a second type of defect is detected (black folding defect detection), the detection may continue. Specifically, the second type of defect detection may be performed on the third processed image. In some embodiments, a pre-trained detection model may also be used to detect the third processed image to obtain a first detection result. It should be noted that the specific white folding defect detection method and the black folding defect detection method are described in the aforementioned content. Please refer to the aforementioned description and will not be repeated here.

[0316] The detection method described in the embodiment of the present application realizes a method for detecting whether the tabs of the adapter sheet on the battery cell cover the glue-coated area. Compared with the traditional tab detection method, new detection items are added, which can improve the product yield.

[0317] In one embodiment, when the type of defect to be detected is a tab obstruction defect, the battery cell detection area includes a tab obstruction detection area. In this scenario, a method for defect detection based on the folded area is provided, that is, when the control device executes the above S1001 "detecting a first defect in the battery cell detection area to obtain a first detection result", the specific execution steps are: inputting a picture of the tab obstruction detection area into a preset detection model to detect a tab cracking defect and obtain a first detection result; the first detection result includes a tab cracking confidence.

[0318] The detection model is a pre-trained detection model used to detect cracks in tabs. During training, the detection model can be trained by collecting on-site defect samples, taking images to mark defects, and then training through deep learning to obtain a defect detection model.

[0319] In an embodiment of the present application, when the control device determines that the type of defect to be detected is a tab cracking defect, the cell detection area is determined to be a tab obstruction detection area, and the size of the tab obstruction detection area is determined based on the size parameters of the tab of the cell to be tested and the size parameters of the adapter of the cell to be tested; then, based on the size of the cell detection area and the relevant parameters of the cell to be tested, the position of the tab obstruction detection area in the first cell image is determined (see the schematic diagram of Figure 24, where ROI16 represents the tab obstruction detection area). When the control device determines the tab obstruction detection area, an image of the tab obstruction detection area can be extracted from the first cell image, and then the image of the tab obstruction detection area can be input into a pre-trained detection model to identify whether there is a cracking defect in the part not obstructed by the adapter, output the tab cracking confidence, and finally determine whether there is a back tab cracking defect based on the tab cracking confidence. For example, when the back tab cracking confidence is greater than 80%, it is determined that there is a cracking defect in the back tab, and at this time, the cell to be tested can be determined to be an NG product.

[0320] The embodiment of the present application provides a method for detecting cracking defects on the back tab, and by quickly locating the tab-blocked detection area and realizing detection through a trained deep learning model, the detection accuracy and efficiency can be improved to a certain extent.

[0321] In one embodiment, when the type of defect to be detected is a weld mark defect, the battery cell inspection area includes a weld mark inspection area. In this scenario, a method for defect detection based on the weld mark inspection area is provided, as shown in FIG25 , that is, the above-mentioned S1001 “perform a first defect detection on the battery cell inspection area to obtain a first detection result” includes:

[0322] S1301 , detecting spots in a cell detection area to determine the spots in the cell detection area.

[0323] In an embodiment of the present application, when the control device determines that the type of defect to be detected is a weld mark defect, the battery cell detection area is determined to be a weld mark detection area, and the size of the weld mark detection area is determined based on the size parameters of the adapter of the battery cell to be tested; then, based on the size of the weld mark detection area and the relevant parameters of the battery cell to be tested, the position of the weld mark detection area in the first battery cell image is determined (see the schematic diagram shown in Figure 13, where ROI4 represents the weld mark detection area). When the control device determines the weld mark detection area, an image of the weld mark detection area can be extracted from the first battery cell image, and then the image of the weld mark detection area can be input into a pre-trained detection model to identify the number of spots in the detection area, the number of pixels corresponding to the spots, and the location of the spots.

[0324] In some embodiments, the control device may use a spot algorithm to identify the number of spots in the cell detection area, ie, the number of welding points, and may also identify the size of the spots, ie, the number of pixels corresponding to each spot.

[0325] S1302 , performing defect detection on the cell detection area according to the number and area of ​​pixels corresponding to each spot to obtain a first detection result; the first detection result includes the number and weld area of ​​welding points in the cell detection area.

[0326] In an embodiment of the present application, when the control device determines the number of welding points contained in the battery cell detection area and the number of pixels corresponding to each welding point, the area of ​​the weld mark detection area can be further calculated based on the number and area of ​​pixels corresponding to each spot. Afterwards, the control device can compare the number of welding points contained in the weld mark detection area with the number of welding points contained in the preset weld mark area. If the number of welding points contained in the two sides is consistent, it is determined that there is no weld mark defect in the first battery cell image; if the number of welding points contained in the two sides is inconsistent, it is determined that there is a weld mark defect in the first battery cell image; further, the control device can compare the area of ​​the weld mark detection area with the area of ​​the preset weld mark area. If the weld mark areas of the two sides are consistent, it is determined that there is no weld mark defect in the first battery cell image; if the weld mark areas of the two sides are inconsistent, it is determined that there is a weld mark defect in the first battery cell image.

[0327] The embodiments of the present application provide a method for detecting weld mark defects, and by quickly locating the weld mark detection area and implementing detection through a trained deep learning model, the detection accuracy and efficiency can be improved to a certain extent.

[0328] In one embodiment, the above-mentioned embodiments of Figures 2 to 25 realize the detection of tab eversion defects, tab folding defects, and weld mark defects, and all of the defect detection is performed before the blue glue is affixed to the battery cell to be tested. The embodiment of the present application also provides a defect detection method for the battery cell after gluing, and detects the presence or absence of blue glue after gluing, blue glue offset, blue glue leakage tab, and battery cell polarity reversal.

[0329] In one embodiment, when inspecting whether the blue glue has defects, the blue glue inspection area includes the adhesive bonding area, and the second defect includes whether the blue glue has defects. In this scenario, a method for defect detection based on the adhesive bonding area is provided, as shown in FIG26 , that is, the above-mentioned S1002 “performing a second defect inspection on the blue glue inspection area in the second battery cell image to obtain a second inspection result” includes:

[0330] S1401, determine whether the pixel values ​​of all pixels in the blue glue detection area are greater than a first preset pixel threshold. If so, execute step S1402; if not, execute step S1403.

[0331] S1402 , determining that the second detection result indicates that blue glue is adhered to the adapter in the second battery cell picture.

[0332] S1403 , determining that the second detection result indicates that no blue glue is adhered to the adapter in the second battery cell picture.

[0333] Among them, the first preset pixel threshold is the grayscale value of the pixel corresponding to the blue glue in the picture, which can be determined in advance according to the characteristics of the blue glue.

[0334] In an embodiment of the present application, the control device can determine a first preset pixel threshold in advance based on the characteristics of the blue glue, and during specific detection, compare the grayscale value of each pixel point in the blue glue detection area with the first preset pixel threshold, and when it is determined that the pixel values ​​of all pixels in the blue glue detection area are greater than the first preset pixel threshold, it indicates that there is blue glue on the second battery cell picture, that is, it is determined that the second detection result indicates that blue glue is pasted on the adapter in the second battery cell picture; when it is determined that the pixel values ​​of all pixels in the blue glue detection area are not greater than the first preset pixel threshold, it indicates that there is no blue glue on the second battery cell picture, that is, it is determined that the second detection result indicates that there is no blue glue on the adapter in the second battery cell picture.

[0335] The embodiment of the present application provides a defect detection method for detecting the presence of blue glue in battery cells after welding, and by quickly locating the blue glue detection area, the detection accuracy and efficiency can be improved to a certain extent.

[0336] In one embodiment, when detecting a blue glue defect, the blue glue detection area includes the pad area, and the second defect includes a blue glue offset defect. In this scenario, a method for defect detection based on the pad area is provided, namely, the above-mentioned S1002 "performing a second defect detection on the blue glue detection area in the second battery cell image to obtain a second detection result", as shown in FIG27, including:

[0337] S1501, determine whether there is a pixel point with a pixel value greater than a second preset pixel threshold in the pad area; if yes, execute step S1502; if no, execute step S1503.

[0338] S1502 , determining that the second detection result indicates that the blue glue attached to the adapter sheet in the second battery cell picture has an offset defect.

[0339] S1503 , determining that the second detection result indicates that the blue glue attached to the adapter sheet in the second battery cell picture does not have an offset defect.

[0340] The first preset pixel threshold is the grayscale value of the pixel corresponding to the blue glue in the image, which can be determined in advance based on the characteristics of the blue glue. The pad area can be referred to as the ROI6 area shown in FIG17 .

[0341] In an embodiment of the present application, the control device can determine the second preset pixel threshold in advance based on the characteristics of the blue glue, and during specific detection, compare the grayscale value of each pixel point in the blue glue detection area with the second preset pixel threshold, and when it is determined that there is a pixel point with a pixel value greater than the second preset pixel threshold in the blue glue detection area, it means that there is blue glue in the pad area on the adapter in the second battery cell image, that is, it is determined that the second detection result indicates that the blue glue pasted on the adapter in the second battery cell image has an offset defect, and it is offset to the pad area; when it is determined that there is a pixel point with a pixel value greater than the second preset pixel threshold in the blue glue detection area, it means that there is no offset defect in the blue glue pasted on the second battery cell image, that is, it is determined that the second detection result indicates that there is no offset defect in the blue glue pasted on the adapter in the second battery cell image.

[0342] The embodiment of the present application provides a method for detecting blue glue offset defects in battery cells after welding, especially detecting whether there is blue glue offset in the pad area, which can improve the detection safety of battery cells to a certain extent.

[0343] In one embodiment, when detecting polarity defects of a pad, the blue glue detection area includes the pad area, and the second defect includes the polarity defect of the adapter. In this scenario, a method for defect detection based on the pad area is provided, as shown in FIG28 , that is, the above-mentioned S1002 “detecting the second defect in the blue glue detection area to obtain a second detection result” includes:

[0344] S1601: Determine a first color value and a second color value of a pad area in a second battery cell image.

[0345] S1602: Determine the polarity of the adapter in the second battery cell image according to the difference between the first color value and the second color value.

[0346] S1603 , determining a second detection result according to the polarity of the adapter in the second battery cell picture; the second detection result indicates whether the polarity of the adapter in the second battery cell picture is reversed.

[0347] The first color value is the color value of red, that is, the R value in the RGB value; the second color value is the color value of blue, that is, the B value in the RGB value.

[0348] In an embodiment of the present application, when the control device specifically detects the polarity of the soldering pad, it is necessary to convert the second battery cell image into a color image, and extract the R value and B value from the color image based on the RGB value of each pixel point, and calculate the difference between the R value and the B value. Then, the polarity of the adapter in the second battery cell image is determined based on the difference. For example, if the difference is positive, it means that the soldering pad of the adapter is a copper soldering pad; if the difference is negative, it means that the soldering pad of the adapter is an aluminum soldering pad. When the polarity of the adapter in the second battery cell picture is determined, it is possible to further determine whether the polarity of the adapter in the current second battery cell picture is reversed based on the preset polarity of the battery cell to be tested, that is, the original polarity of the battery cell to be tested. For example, if the polarity of the adapter in the second battery cell picture is consistent with the preset polarity of the battery cell to be tested, it is determined that the polarity of the adapter in the second battery cell picture is not reversed; if the polarity of the adapter in the second battery cell picture is inconsistent with the preset polarity of the battery cell to be tested, it is determined that the polarity of the adapter in the second battery cell picture is reversed.

[0349] The embodiment of the present application provides a method for detecting the polarity defects of the solder pads of the battery cells after welding, especially detecting whether the polarity of the solder pads has a reverse polarity defect, which can improve the detection safety of the battery cells to a certain extent.

[0350] In one embodiment, when detecting polarity defects of a pad, the blue glue detection area includes the area around the tab, and the second defect includes the drain tab defect. In this scenario, a method for defect detection based on the area around the tab is provided, as shown in FIG29 , that is, the above-mentioned S1002 “detecting the second defect in the blue glue detection area to obtain a second detection result” includes:

[0351] S1701, determining whether the area around the tab in the second battery cell image contains an area with a grayscale difference greater than a preset grayscale threshold. If so, executing step S1702; if not, executing step S1703.

[0352] S1702 , determining that the second detection result indicates that the blue glue attached to the adapter sheet in the second battery cell picture has a drain tab defect.

[0353] S1703 , determining that the second detection result indicates that the blue glue attached to the adapter sheet in the second battery cell picture does not have a drain tab defect.

[0354] Among them, the preset grayscale threshold is the grayscale value of the pixel points corresponding to the transition area between the blue glue and the background, which can be determined in advance based on the characteristics of the pixel points in the transition area between the blue glue and the background. It should be noted that the area around the pole ear may include multiple leakage ear detection areas, and each leakage ear detection area can be set at the surrounding position of the pole ear on the adapter. For example, referring to the schematic diagram shown in Figure 17, ROI8 represents a leakage ear detection area, ROI9 represents a leakage ear detection area, ROI10 represents a leakage ear detection area, ROI11 represents a leakage ear detection area, ROI12 represents a leakage ear detection area, ROI13 represents a leakage ear detection area, ROI14 represents a leakage ear detection area, and ROI15 represents a leakage ear detection area. To determine the above-mentioned leakage ear detection areas, please refer to the method for determining the detection area in the aforementioned embodiment, that is, the size of each leakage ear detection area is determined according to the size parameters of the pole ear of the battery cell to be tested, the size parameters of the adapter of the battery cell to be tested, and the size parameters of the weld mark of the adapter of the battery cell to be tested, and based on the size of each leakage ear detection area, and in combination with the relevant parameters of the battery cell to be tested, the position of each leakage ear detection area is determined. The specific method can be referred to the aforementioned method, which is not repeated here.

[0355] In an embodiment of the present application, the control device can pre-determine a preset grayscale threshold based on the characteristics of the pixel points in the transition area between the blue glue and the background, and during specific detection, first calculate the grayscale difference of adjacent pixel points in the area around the pole ear, or calculate the grayscale difference of pixel points in adjacent areas around the pole ear, and then compare the grayscale difference with the preset grayscale threshold, and when it is determined that the area around the pole ear contains pixels or areas with a grayscale difference greater than the preset grayscale threshold, it means that the blue glue in the second battery cell image fails to completely cover the pole ear, that is, there is a defect of a leaking pole ear, that is, it is determined that the second detection result indicates that the blue glue pasted on the adapter sheet in the second battery cell image has a defect of a leaking pole ear; when it is determined that the area around the pole ear does not contain pixels or areas with a grayscale difference greater than the preset grayscale threshold, it means that the blue glue on the second battery cell image completely covers the pole ear, that is, it is determined that the second detection result indicates that the blue glue pasted on the adapter sheet in the second battery cell image does not have a defect of a leaking pole ear.

[0356] The embodiments of the present application provide a method for detecting defects in drain tabs of battery cells after welding, which can improve the comprehensiveness of battery cell detection to a certain extent.

[0357] Based on the defect detection method described in any of the above embodiments, the present application also provides a defect detection system, as shown in the system block diagram of Figure 30, the defect detection system includes a control device 102, a camera 104, a driving device 106, a welding device 108 and a gluing device 110; the control device 102 is respectively connected to the camera 104, the driving device 106, the welding device 108 and the gluing device 110; wherein, the control device 102 is used to execute the defect detection method described in any of the above embodiments of Figures 2 to 29.

[0358] The defect detection method described in the embodiment of the present application realizes taking pictures before gluing by adding a photo trigger signal before gluing to the original photo position after gluing. After the photo is taken, the battery cell enters the gluing station and returns to the photo position after gluing. The control device gives the camera a photo trigger signal, thereby completing the photo taking after gluing. In this process, the battery cell photographed "before gluing" and "after gluing" is the same battery cell. The ultrasonic post-weld visual inspection system includes two processing procedures, "before gluing" + "after gluing". After receiving the pre-glue signal, it enters the corresponding pre-glue processing flow. After the processing is completed, the result is temporarily stored. After waiting for the post-glue signal to be received, it enters the post-glue processing flow. After the processing is completed, the pre-glue results are summarized and the total result is sent to the control device. The main device performs waste treatment on this battery cell based on the total result determined by the camera. At the same time, the pre-glue photo + defect detection takes about 150ms in total, which does not affect the battery cell production rhythm. That is, after the control device executes the step of "defect detection of the detection area and obtaining a first detection result," it analyzes the first detection result to determine the operation for the battery cell under test. For example, if the first detection result indicates that a tab defect, tab folding defect, weld mark defect, or blue glue defect is detected, the battery cell under test is subjected to NG waste treatment; if the first detection result indicates that no tab defect, tab folding defect, weld mark defect, or blue glue defect is detected, the battery cell under test continues with the subsequent process flow. This method can improve the accuracy of battery cell detection, thereby improving the production quality of battery cells.

[0359] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0360] Based on the same inventive concept, the present application also provides a defect detection device for implementing the aforementioned defect detection method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more defect detection device embodiments provided below can be found in the above-mentioned limitations of the defect detection method and will not be repeated here.

[0361] In one embodiment, as shown in FIG31 , a defect detection device is provided, comprising:

[0362] The acquisition module 20 is used to acquire a first cell image of the cell to be tested before gluing and a second cell image of the cell to be tested after gluing; the first cell image includes the tab of the cell to be tested.

[0363] The determination module 21 is configured to determine a cell detection area from the first cell image and a blue glue detection area from the second cell image according to the type of the defect to be detected.

[0364] The detection module 22 is used to perform defect detection on the battery cell detection area and the blue glue detection area to obtain detection results.

[0365] Each module in the aforementioned defect detection device may be implemented in whole or in part through software, hardware, or a combination thereof. Each module may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a computer device memory in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0366] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure may be as shown in FIG32 . The computer device includes a processor, memory, a communication interface, a display screen, and an input device connected via a system bus. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal via wired or wireless communication. The wireless communication may be achieved via Wi-Fi, a mobile cellular network, NFC (near-field communication), or other technologies. When executed by the processor, the computer program implements a defect detection method. The display screen of the computer device may be a liquid crystal display or an electronic ink display. The input device of the computer device may be a touch screen covering the display screen, or may be buttons, a trackball, or a touchpad provided on the computer device housing, or may be an external keyboard, touchpad, or mouse.

[0367] Those skilled in the art will understand that the structure shown in Figure 32 is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0368] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0369] Obtain a first cell image of the cell to be tested before gluing and a second cell image of the cell to be tested after gluing; the first cell image includes the tab of the cell to be tested;

[0370] Determine a battery cell detection area from the first battery cell image and a blue glue detection area from the second battery cell image according to the type of defect to be detected;

[0371] Defect detection is performed on the battery cell detection area and the blue glue detection area to obtain detection results.

[0372] The computer device provided in the above embodiment has an implementation principle and technical effects similar to those of the above method embodiment, and will not be described in detail here.

[0373] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0374] Obtain a first cell image of the cell to be tested before gluing and a second cell image of the cell to be tested after gluing; the first cell image includes the tab of the cell to be tested;

[0375] Determine a battery cell detection area from the first battery cell image and a blue glue detection area from the second battery cell image according to the type of defect to be detected;

[0376] Defect detection is performed on the battery cell detection area and the blue glue detection area to obtain detection results.

[0377] The above embodiment provides a computer-readable storage medium, whose implementation principle and technical effects are similar to those of the above method embodiment, and will not be repeated here.

[0378] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0379] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0380] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A defect detection method, wherein: The method comprises: Obtain a first cell image of the cell to be tested before gluing and a second cell image of the cell to be tested after gluing; the first cell image includes the tab of the cell to be tested; Determining a size of a cell inspection area in the first cell image according to a type of defect to be detected and relevant parameters of the cell to be tested, and determining a position of the cell inspection area in the first cell image according to the size of the cell inspection area and relevant parameters of the cell to be tested; Determine the size of the blue glue detection area in the second battery cell image according to the type of the defect to be detected and the relevant parameters of the battery cell to be tested, and determine the position of the blue glue detection area in the second battery cell image according to the size of the blue glue detection area and the relevant parameters of the battery cell to be tested; Defect detection is performed on the battery cell detection area and the blue glue detection area to obtain detection results.

2. The method according to claim 1, wherein The determining, according to the type of the defect to be detected and the relevant parameters of the battery cell to be tested, the size of the battery cell detection area in the first battery cell image includes: If the type of the defect to be detected is a tab eversion defect, the battery cell detection area is determined to be an eversion area, and the size of the eversion area is determined according to the size parameters of the tab of the battery cell to be tested, the size parameters of the adapter of the battery cell to be tested, and the size parameters of the weld mark of the adapter of the battery cell to be tested; If the type of the defect to be detected is a tab fold defect, the battery cell detection area is determined to be a fold area, and the size of the fold area is determined according to the size parameters of the tab of the battery cell to be tested and the size parameters of the adapter of the battery cell to be tested; If the type of the detection defect is a weld mark defect, the battery cell detection area is determined to be a weld mark detection area, and the size of the weld mark detection area is determined according to the size parameters of the weld mark on the adapter in the battery cell to be tested.

3. The method according to claim 2, wherein: The outward-turned area includes a first detection area and a second detection area, and determining the size of the outward-turned area according to the size parameters of the tab of the battery cell to be tested, the size parameters of the adapter of the battery cell to be tested, and the size parameters of the weld mark of the adapter of the battery cell to be tested includes: Determine the size of the first detection area according to the size parameters of the tab of the battery cell to be tested and the size parameters of the adapter; The size of the second detection area is determined according to the size parameters of the weld mark of the adapter of the battery cell to be tested.

4. The method according to claim 3, wherein: The determining the size of the first detection area according to the size parameters of the tab of the battery cell to be tested and the size parameters of the adapter comprises: The size of the first detection area is determined according to the length of the tab of the battery cell to be tested and the width of the gap between the adapter and the battery cell to be tested.

5. The method according to claim 3, wherein: The determining the size of the second detection area according to the size parameters of the weld mark of the adapter of the battery cell to be tested includes: The size of the second detection area is determined according to the length and width of the weld mark of the adapter of the battery cell to be tested.

6. The method according to claim 2, wherein: The determining the size of the folded area according to the size parameters of the tab of the battery cell to be tested and the size parameters of the adapter of the battery cell to be tested includes: The size of the folded area is determined according to the length of the tab of the battery cell to be tested and the width of the gap between the adapter and the battery cell to be tested.

7. The method according to any one of claims 1 to 6, wherein: The determining, according to the size of the battery cell detection area and relevant parameters of the battery cell to be tested, a position of the battery cell detection area in the first battery cell image, includes: According to the position of the intersection of the first side and the second side and in combination with the size of the battery cell detection area, the battery cell detection area in the first battery cell picture is positioned to determine the position of the battery cell detection area in the first battery cell picture; the first side and the second side are two intersecting sides of the adapter in the first battery cell picture.

8. The method according to claim 1, wherein The determining, according to the type of the defect to be detected and the relevant parameters of the battery cell to be tested, the size of the blue glue detection area in the second battery cell image includes: If the type of defect to be detected is whether the blue glue is defective, the blue glue detection area is determined to be a glue-attaching area, and the size of the glue-attaching area is determined according to the size parameters of the weld mark of the adapter sheet of the battery cell to be tested; If the type of the defect to be detected is a blue glue offset defect or an adapter polarity defect, the blue glue detection area is determined to be a pad area, and the size of the pad area is determined according to the size parameters of the pad in the adapter of the battery cell to be tested; If the type of defect to be detected is a drain tab defect, the blue glue detection area is determined to be the area around the tab, and the size of the area around the tab is determined based on the size parameters of the pad in the adapter of the battery cell to be tested and the position of the pad.

9. The method according to claim 8, wherein The step of determining the size of the adhesive area according to the size parameters of the weld mark of the adapter of the battery cell to be tested includes: The size of the adhesive area is determined according to the length of the area where the welding mark of the adapter sheet is located and the width of the area where the welding mark of the adapter sheet is located.

10. The method according to claim 9, wherein: The blue glue detection area includes the glue application area, and determining a position of the blue glue detection area in the second battery cell image according to a size of the blue glue detection area and relevant parameters of the battery cell to be tested includes: Positioning the glue area in the second battery cell image according to the intersection of the third side and the fourth side and in combination with the size of the glue area to determine the position of the glue area in the second battery cell image; the third side and the fourth side are two intersecting sides of the adapter in the second battery cell image; Alternatively, the position of the glue-attached area in the second battery cell image is determined according to the position of the area where the weld mark of the battery cell to be tested is located.

11. The method according to claim 8, wherein The step of determining the size of the pad area according to the size parameters of the pad in the adapter of the battery cell to be tested includes: Determining a protruding area or a recessed area of ​​a pad in a transfer sheet of the battery cell to be tested; If the protrusion area or the concave area is a circular area, the size of the pad area is determined according to the diameter of the protrusion area or the concave area; If the protrusion area or the recess area is a rectangular area, the size of the pad area is determined according to the length of the protrusion area or the recess area and the width of the protrusion area or the recess area.

12. The method according to claim 8, wherein The step of determining the size of the pad area according to the size parameters of the pad in the adapter of the battery cell to be tested includes: Determine the size of the pad area according to the length of the area where the pad is located in the adapter of the battery cell to be tested and the width of the area where the pad is located in the adapter; Alternatively, the size of the pad area is determined according to the size parameters of the protrusion area or the recess area of ​​the pad in the adapter.

13. The method according to claim 11 or 12, wherein: The determining, according to the size of the blue glue detection area and the relevant parameters of the battery cell to be tested, a position of the blue glue detection area in the second battery cell image includes: The pad area in the second cell image is located according to the position of the pad of the adapter in the cell to be tested and in combination with the size of the pad area, so as to determine the position of the pad area in the second cell image.

14. The method according to claim 8, wherein The step of determining the size of the area around the tab according to the size parameters of the pad in the adapter of the battery cell to be tested and the position of the pad includes: The size of the area around the tab is determined according to the length of the area where the pad is located in the adapter of the battery cell to be tested and the distance between the pad and the battery cell to be tested.

15. The method according to claim 14, wherein The area around the tabs includes a first area around the first tab, a second area around the first tab, a first area around the second tab, and a second area around the second tab. Determining the size of the area around the tabs according to the length of the area where the pad is located in the adapter of the battery cell to be tested and the distance between the pad and the battery cell to be tested includes: Determine, according to the length of the area where the solder pad is located in the adapter of the battery cell to be tested, the length of the first surrounding area of ​​the first pole tab, the length of the second surrounding area of ​​the first pole tab, the length of the first surrounding area of ​​the second pole tab, and the length of the second surrounding area of ​​the second pole tab; Determining a width of a first surrounding area of ​​the first tab and a width of a second surrounding area of ​​the first tab according to a first distance between the welding pad and the battery cell to be tested; The width of the first surrounding area of ​​the second tab and the width of the second surrounding area of ​​the second tab are determined according to a second distance between the soldering pad and the battery cell to be tested.

16. The method according to claim 15, wherein The determining, according to the size of the blue glue detection area and the relevant parameters of the battery cell to be tested, a position of the blue glue detection area in the second battery cell image includes: The first surrounding area of ​​the first tab in the second battery cell image is located based on the position of the intersection of the fifth side and the sixth side and in combination with the size of the first surrounding area of ​​the first tab to determine the position of the first surrounding area of ​​the first tab; the fifth side and the sixth side are two intersecting sides of the adapter in the second battery cell image; Determine the position of the second surrounding area of ​​the first electrode tab according to the length of the first blue glue in the battery cell to be tested and the position of the first surrounding area of ​​the first electrode tab; The first surrounding area of ​​the second tab in the second battery cell image is located according to the position of the intersection of the seventh side and the eighth side and in combination with the size of the first surrounding area of ​​the second tab to determine the position of the first surrounding area of ​​the second tab; the seventh side and the eighth side are two intersecting sides of the adapter in the second battery cell image; The position of the second surrounding area of ​​the second electrode tab is determined according to the length of the second blue glue in the battery cell to be tested and in combination with the position of the first surrounding area of ​​the second electrode tab.

17. The method according to claim 1, wherein The test results include a first test result and a second test result. The defect detection is performed on the battery cell detection area and the blue glue detection area to obtain the test results, including: Performing a first defect detection on the battery cell detection area to obtain a first detection result; the first defect includes one of a tab eversion defect, a tab folding defect, a tab cracking defect, and a weld mark defect; The blue glue detection area is detected for a second defect to obtain a second detection result; the second defect includes one of a blue glue defect, a blue glue offset defect, a transfer plate polarity defect, and a drain ear defect.

18. The method according to claim 17, wherein The battery cell detection area includes a tab fold detection area, the tab fold detection area includes an outward-turning area, the outward-turning area includes a first battery cell detection area and a second battery cell detection area, and performing a first defect detection on the battery cell detection area to obtain the first detection result includes: performing binarization processing on the image of the first battery cell detection area and the image of the second battery cell detection area to obtain a first processed image and a second processed image; Performing a first type of defect detection of the tab eversion defect on the first processed image to obtain an intermediate detection result; If the intermediate test result indicates that the first type of defect is detected, determining that the first test result indicates that the battery cell to be tested has a first type of defect; If the intermediate detection result indicates that the first type of defect is not detected, the second type of defect detection in the tab eversion defect is performed on the second processed image to obtain the first detection result.

19. The method according to claim 18, wherein The performing a first type of defect detection of tab eversion defects on the first processed image to obtain an intermediate detection result includes: Determine whether the battery cell detection area of ​​the first processed image contains pixels whose grayscale values ​​are within the first grayscale threshold range. If the battery cell detection area contains pixels whose grayscale values ​​are within the first grayscale threshold range, determine that the intermediate detection result indicates that the first type of defect is detected; if the battery cell detection area does not contain pixels whose grayscale values ​​are within the first grayscale threshold range, determine that the intermediate detection result indicates that the first type of defect is not detected.

20. The method according to claim 18, wherein The performing the second type of defect detection of the tab eversion defect on the second processed image to obtain the first detection result includes: Determine whether the battery cell detection area of ​​the second processed image contains pixels whose grayscale values ​​are within the second grayscale threshold range. If the battery cell detection area contains pixels whose grayscale values ​​are within the second grayscale threshold range, determine that the first detection result indicates that the battery cell to be tested has the second type of defect; if the battery cell detection area does not contain pixels whose grayscale values ​​are within the second grayscale threshold range, determine that the first detection result indicates that the battery cell to be tested does not have the second type of defect.

21. The method according to claim 17, wherein The battery cell detection area includes a tab fold detection area, and the tab fold detection area includes a fold area. Detecting the first defect in the battery cell detection area to obtain the first detection result includes: performing a binarization process on the image in the folded area to obtain a processed third image; The third processed image is inspected for the tab folding defect to obtain the first inspection result.

22. The method according to claim 17, wherein The battery cell detection area includes a tab shielding detection area, and the detecting the first defect in the battery cell detection area to obtain the first detection result includes: The image of the tab obstructing the detection area is input into a preset detection model to detect the tab cracking defect, and the first detection result is obtained; the first detection result includes the tab cracking confidence.

23. The method according to claim 17, wherein The battery cell inspection area includes a weld mark inspection area, and the detecting the first defect in the battery cell inspection area to obtain the first inspection result includes: Detecting spots in the battery cell detection area to determine the spots in the battery cell detection area; The battery cell detection area is inspected for the weld mark defects according to the number and area of ​​the pixels corresponding to each of the spots to obtain the first inspection result; the first inspection result includes the number of welding points and the weld mark area in the battery cell detection area.

24. The method according to claim 17, wherein The blue glue detection area includes a glue-applying area, the second defect includes whether the blue glue has a defect, and the second defect detection of the blue glue detection area to obtain the second detection result includes: Determine whether the pixel values ​​of all pixels in the blue glue detection area are greater than a first preset pixel threshold; If the pixel values ​​of all pixels in the blue glue detection area are greater than the first preset pixel threshold, it is determined that the second detection result indicates that blue glue is affixed to the adapter in the second battery cell image; If the pixel values ​​of all pixels in the blue glue detection area are not greater than the first preset pixel threshold, it is determined that the second detection result indicates that no blue glue is pasted on the adapter in the second battery cell image.

25. The method according to claim 17, wherein The blue glue detection area includes a pad area, the second defect includes the blue glue offset defect, and the second defect detection is performed on the blue glue detection area to obtain the second detection result, including: Determine whether there is a pixel point in the pad area whose pixel value is greater than a second preset pixel threshold; If so, it is determined that the second detection result indicates that the blue glue affixed to the adapter in the second battery cell picture has an offset defect; If not, it is determined that the second detection result indicates that the blue glue pasted on the adapter in the second battery cell picture does not have an offset defect.

26. The method according to claim 17, wherein The blue glue detection area includes a pad area, the second defect includes a polarity defect of the adapter, and the second defect detection is performed on the blue glue detection area to obtain the second detection result, including: Determine a first color value and a second color value of a pad area in the second battery cell image; determining the polarity of the adapter in the second battery cell image according to a difference between the first color value and the second color value; The second detection result is determined according to the polarity of the adapter in the second battery cell picture; the second detection result indicates whether the polarity of the adapter in the second battery cell picture is reversed.

27. The method according to claim 17, wherein The blue glue detection area includes an area around the tab, the second defect includes the drain tab defect, and the second defect detection is performed on the blue glue detection area to obtain the second detection result, including: Determine whether the area around the tab in the second battery cell image contains a pixel point or area whose grayscale difference is greater than a preset grayscale threshold; If included, it is determined that the second detection result indicates that the blue glue affixed to the adapter in the second battery cell picture has a leakage ear defect; If not included, it is determined that the second detection result indicates that the blue glue pasted on the adapter in the second battery cell picture does not have a leakage ear defect.

28. A defect detection system, wherein: The system includes: a control device, a camera, a driving device, a welding device and a gluing device; the control device is connected to the camera, the driving device, the welding device and the gluing device respectively; The control device is used to execute the defect detection method according to any one of claims 1 to 27.

29. A defect detection device, wherein: The device comprises: An acquisition module, configured to acquire a first cell image of the cell to be tested before gluing and a second cell image of the cell to be tested after gluing; the first cell image includes a tab of the cell; A determination module, configured to determine the size of the cell detection area in the first cell image according to the type of defect to be detected and the relevant parameters of the cell to be tested, and determine the position of the cell detection area in the first cell image according to the size of the cell detection area and the relevant parameters of the cell to be tested; determine the size of the blue glue detection area in the second cell image according to the type of defect to be detected and the relevant parameters of the cell to be tested, and determine the position of the blue glue detection area in the second cell image according to the size of the blue glue detection area and the relevant parameters of the cell to be tested; The detection module is used to perform defect detection on the battery cell detection area and the blue glue detection area to obtain detection results.

30. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 27 are implemented.

31. A computer-readable storage medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 27 are implemented.

Images