Methods, apparatus, and electronic equipment for inspecting the appearance of the tabs in battery cell assemblies

By using computer vision technology to inspect the appearance of the battery cell assembly tabs, the problems of low inspection efficiency and insufficient accuracy in existing technologies have been solved, achieving efficient and accurate tab appearance inspection and improving the yield rate of battery production.

CN117751381BActive Publication Date: 2026-11-10CONTEMPORARY AMPEREX TECHNOLOGY CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202280006741.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-07-21
Publication Date
2026-11-10
Estimated Expiration
2042-07-21

AI Technical Summary

Technical Problem

In existing technologies, the efficiency and accuracy of the appearance inspection of the battery cell assembly tabs are low, which affects the yield rate of battery production.

Method used

Using computer vision technology, the root corner of the electrode stacking area, the side of the main body area, and the reference edge line are determined by acquiring images of the battery cell assembly, and the appearance of the electrode is inspected based on this information.

Benefits of technology

This improved the efficiency and accuracy of electrode appearance inspection, thereby increasing the yield rate of cell components and batteries.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117751381B_ABST
    Figure CN117751381B_ABST
Patent Text Reader

Abstract

A method, apparatus, electronic device, computer-readable storage medium, and computer program product for detecting the appearance of tabs in a battery cell assembly are provided. The method includes: acquiring a detection image including a background area and a battery cell assembly image area, wherein the battery cell assembly image area includes a main body area and multiple tab stack areas, each tab stack area being adjacent to the top or bottom edge of the main body area; determining each root corner point of the multiple tab stack areas in the detection image; determining two sides of the main body area in the detection image; determining at least one reference edge line in the detection image based on the two sides of the main body area; and determining detection result information of the tab appearance based on each root corner point of the multiple tab stack areas and the at least one reference edge line in the detection image.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This disclosure relates to the field of battery manufacturing technology, and in particular to a method and apparatus for detecting the appearance of the tabs of a battery cell assembly, an electronic device, a computer-readable storage medium, and a computer program product. Background Technology

[0002] In related technologies, a rechargeable battery (referring to a battery that can be recharged after discharge to activate its active materials and continue to be used, also known as a secondary battery, hereinafter referred to as a battery) includes a battery case and multiple battery cells connected in series and / or parallel within the battery case. A battery cell is the smallest unit in a battery that provides energy, while the cell assembly is the key component where electrochemical reactions occur within the battery cell. Defect detection of the tabs on the cell assembly is a crucial step in battery production. Summary of the Invention

[0003] This disclosure aims to at least address one of the technical problems existing in the related art. Therefore, one object of this disclosure is to provide a method and apparatus, electronic device, computer-readable storage medium, and computer program product for detecting the appearance of the tabs of a battery cell assembly.

[0004] An embodiment of the first aspect of this disclosure provides a method for detecting the appearance of tabs in a battery cell assembly, comprising: acquiring a detection image including a background area and a battery cell assembly image area, wherein the battery cell assembly image area includes a main body area and a plurality of tab stack areas, each tab stack area being adjacent to the top edge or bottom edge of the main body area; determining each root corner point of the plurality of tab stack areas in the detection image; determining two sides of the main body area in the detection image; determining at least one reference edge line in the detection image based on the two sides of the main body area in the detection image; and determining detection result information of the tab appearance based on each root corner point of the plurality of tab stack areas in the detection image and at least one reference edge line.

[0005] The method of this disclosure, based on the image of the battery cell assembly, uses computer vision technology to inspect the appearance of the stacked tabs of the battery cell assembly. Compared with the detection methods in related technologies that rely on manual measurement or special fixtures, it not only has higher detection efficiency and is applicable to a wide range of product specifications, but also significantly improves the accuracy of detection, thereby improving the production yield of battery cell assemblies and batteries.

[0006] In some embodiments, acquiring a detection image includes: binarizing the detection image to obtain a binarized image, wherein the battery cell component image area is used as the region of interest in the binarized image. Binarizing the detection image facilitates accurate extraction of the battery cell component image area in subsequent steps.

[0007] In some embodiments, determining each root corner point of multiple electrode stacking regions in a detected image includes: in a binarized image, matching and locating a corresponding template image in each local search region based on a template image configured for each root corner point and a local search region; and determining each root corner point of multiple electrode stacking regions in a binarized image based on the matching and locating results of the template image in each local search region.

[0008] In some embodiments, the template image is obtained based on a cell assembly image template.

[0009] The local search region is a small pre-defined search area for a binarized image. Matching and locating the template image within the local search region can greatly reduce the amount of matching calculations and improve the speed and accuracy of matching calculations.

[0010] In some embodiments, determining two sides of the main body region in the detected image includes: extracting a cell component image region from a binarized image; scrolling the cell component image region along a row column in the binarized image by one pixel column to obtain a comparison image; determining multiple edge pixels of the cell component image region in the binarized image based on the grayscale difference between the binarized image and the comparison image; and filtering out edge pixels arranged in a first direction but with a spacing less than a distance threshold from the multiple edge pixels to obtain two sides of the main body region in the binarized image, wherein the first direction is approximately the same as the extension direction of the top and bottom edges of the main body region.

[0011] By adopting this embodiment, on the one hand, edge pixels that are not related to the two sides of the main body area can be filtered out, and on the other hand, image feature loss or errors caused by poor hardware or shooting environment can be avoided as much as possible, thereby further improving the accuracy of detection.

[0012] In some embodiments, determining at least one reference edge line in the detection image based on two sides of the main body region in the detection image includes: performing straight line fitting on each of the two sides of the main body region in the binarized image to obtain two fitted sides extending from straight lines; and determining at least one reference edge line in the binarized image based on the two fitted sides. Determining the reference edge line based on the fitted sides obtained from straight line fitting can further improve the accuracy of detection.

[0013] In some embodiments, extracting the cell component image region from a binarized image includes: extracting the cell component image region from a binarized image based on at least one of a threshold segmentation algorithm, an image segmentation algorithm, and a maximum connected component algorithm.

[0014] In some embodiments, acquiring a detection image includes: performing rotational correction on the detection image so that the top and bottom edges of the main body region are approximately parallel to the row direction, and the two side edges of the main body region are approximately orthogonal to the row direction.

[0015] In some embodiments, the exposure time for capturing the detection image is not less than 8000 microseconds and not more than 12000 microseconds. Obtaining a high-exposure detection image makes the grayscale of the cell assembly image area and the background area clearly distinguishable, which is beneficial to further improve the accuracy of detection.

[0016] In some embodiments, the inspection result information of the tab appearance includes: the distance between the two root corner points of each tab stack area; and / or, the pass or fail evaluation result of the tab appearance.

[0017] In some embodiments, the cell assembly image area includes two electrode stacking areas, namely a positive electrode stacking area and a negative electrode stacking area, wherein the positive electrode stacking area and the negative electrode stacking area are both adjacent to the top edge or bottom edge of the main body area, or the positive electrode stacking area is adjacent to the top edge of the main body area and the negative electrode stacking area is adjacent to the bottom edge of the main body area.

[0018] An embodiment of the second aspect of this disclosure provides an apparatus for detecting the appearance of tabs in a battery cell assembly, comprising: an acquisition unit configured to acquire a detection image including a background area and a battery cell assembly image area, wherein the battery cell assembly image area includes a main body area and a plurality of tab stack areas, each tab stack area being adjacent to the top edge or bottom edge of the main body area; a first determination unit configured to determine each root corner point of the plurality of tab stack areas in the detection image; a second determination unit configured to determine two sides of the main body area in the detection image; a third determination unit configured to determine at least one reference edge line in the detection image based on the two sides of the main body area in the detection image; and a fourth determination unit configured to determine detection result information of the tab appearance based on each root corner point of the plurality of tab stack areas in the detection image and at least one reference edge line.

[0019] An embodiment of the third aspect of this disclosure provides a computer-readable storage medium storing computer instructions configured to cause a computer to perform the methods of the foregoing aspects.

[0020] An embodiment of the third aspect of this disclosure provides a computer program product, including a computer program that, when executed by a processor, implements the methods of the foregoing aspects.

[0021] The above embodiments of this disclosure are used to inspect the appearance of the stacked tabs of the battery cell assembly. This method not only has high inspection efficiency and is applicable to a wide range of product specifications, but also significantly improves the accuracy of inspection, thereby increasing the production yield of the battery cell assembly and battery.

[0022] The above description is merely an overview of the technical solution disclosed herein. In order to better understand the technical means of this disclosure and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this disclosure more apparent and understandable, specific embodiments of this disclosure are described below. Attached Figure Description

[0023] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the various drawings denote the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings depict only some embodiments disclosed in this disclosure and should not be construed as limiting the scope of this disclosure.

[0024] Figure 1A A simplified schematic diagram of the main structure of a wound battery cell assembly;

[0025] Figure 1B A simplified top view of a wound battery cell assembly;

[0026] Figure 2 This is a flowchart illustrating a method for detecting the appearance of the tabs of a battery cell assembly according to some embodiments of this disclosure;

[0027] Figure 3 This is a flowchart illustrating a method for detecting the appearance of the tabs of a battery cell assembly according to some embodiments of this disclosure;

[0028] Figure 4 This is a flowchart illustrating a method for detecting the appearance of the tabs of a battery cell assembly according to some embodiments of this disclosure;

[0029] as well as, Figure 5 This is a structural block diagram of an apparatus for detecting the appearance of the tabs of a battery cell assembly according to some embodiments of the present disclosure.

[0030] Explanation of reference numerals in the attached figures: 100-cell assembly 10-Main Body 101-Negative electrode sheet 11-Negative electrode tab 102-Positive electrode sheet 12-Positive electrode tab 103-Diaphragm 2000-Detection Image 201-Background Area 202-Cell Assembly Image Area 20-Main Area 21-Negative electrode stacked tab region 22-Positive stacked tab region 230-Binarized Image 231-Local Search Area 232-Template Image Detailed Implementation

[0031] The embodiments of the technical solutions disclosed herein will now be described in detail with reference to the accompanying drawings. These embodiments are merely illustrative of the technical solutions disclosed herein and are therefore intended to limit the scope of protection of this disclosure.

[0032] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of this disclosure; the terms “comprising” and “having”, and any variations thereof, in the specification, claims and foregoing description of the drawings of this disclosure are intended to cover non-exclusive inclusion.

[0033] In the description of the embodiments of this disclosure, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary or secondary relationship of the indicated technical features. In the description of the embodiments of this disclosure, "a plurality of" means two or more, unless otherwise explicitly defined.

[0034] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this disclosure. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0035] In the description of the embodiments of this disclosure, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0036] In the description of the embodiments of this disclosure, the term "multiple" refers to two or more (including two), similarly, "multiple groups" refers to two or more (including two groups), and "multiple pieces" refers to two or more (including two pieces).

[0037] In the description of the embodiments of this disclosure, the technical terms "center," "column direction," "row direction," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing the embodiments of this disclosure and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the embodiments of this disclosure.

[0038] In the description of the embodiments of this disclosure, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in the embodiments of this disclosure according to the specific circumstances.

[0039] Common battery cell assemblies mainly include two types: laminated and wound. Laminated battery cell assemblies consist of multiple alternating positive and negative electrode plates, and a separator placed between any adjacent positive and negative electrode plates. Wound battery cell assemblies consist of laminated positive and negative electrode plates wound together, and a separator located between the positive and negative electrode plates. Taking a lithium-ion battery cell as an example, inside the battery cell casing, the cell assembly is wetted with electrolyte. Lithium ions move between the negative and positive electrodes using the electrolyte as a medium, thus enabling the battery cell to charge and discharge. The separator's function is to allow lithium ions to pass freely but not electrons, thereby preventing a short circuit between the negative and positive electrodes of the battery cell through the electrolyte.

[0040] Figure 1A The diagram shown is a simplified front view of a wound battery cell assembly. Figure 1B The diagram shown is a simplified top view of the battery cell assembly. Figure 1A and Figure 1BAs shown, the battery cell assembly 100 includes a negative electrode 101, a positive electrode 102, and a separator 103 located between the negative electrode 101 and the positive electrode 102, which are stacked and wound together. The negative electrode 101 includes a negative electrode body (not shown) with an active material layer and a plurality of negative electrode tabs 11 without an active material layer. The plurality of negative electrode tabs 11 are arranged at intervals along one side edge of the negative electrode body and are stacked after winding to serve as the negative electrode of the battery cell assembly 100. The positive electrode 102 includes a positive electrode body (not shown) with an active material layer and a plurality of positive electrode tabs 12 without an active material layer. The plurality of positive electrode tabs 12 are arranged at intervals along one side edge of the positive electrode body and are stacked after winding to serve as the positive electrode of the battery cell assembly 100 and are spaced apart from the negative electrode.

[0041] During the production of battery cells, various defects may occur due to environmental, process, and equipment factors. Therefore, defect detection of battery cells is necessary to ensure a certain yield rate. Among these, defect detection of the tab appearance is an extremely important step, and the validity of the detection results directly affects the safety of the battery upon leaving the factory. In this embodiment, defect detection of the tab appearance mainly refers to visually inspecting the multiple negative tabs and multiple positive tabs stacked in a wound battery cell assembly to determine whether the overall dimensions of the stacked tabs meet the design requirements.

[0042] Based on the above considerations, the inventors, through in-depth research, have provided a method and apparatus, electronic device, computer-readable storage medium, and computer program product for detecting the appearance of the tabs of a battery cell assembly, in order to improve the accuracy of appearance inspection of the tabs, thereby improving the production yield of battery cell assemblies and batteries.

[0043] This disclosure embodiment uses computer vision technology to inspect the appearance of the stacked tabs of the battery cell assembly based on captured images. First, the root corner points of the tab stacking area are identified in the inspection image. Then, the two sides of the main body area of ​​the battery cell assembly image area are identified in the inspection image. Next, a reference edge line is identified in the inspection image based on these two sides. Finally, the inspection result information of the tab appearance can be obtained based on the relative positional relationship between the root corner points of the tab stacking area and the reference edge line. The tab stacking area reflects the overall shape of multiple tabs after stacking. Each tab stacking area includes two root corner points. If the distance between these two root corner points is too large, it indicates severe misalignment of the tabs after stacking, requiring review of product design and processes. Using the technical solution of this disclosure embodiment, the appearance of the stacked tabs can be inspected after the battery cell assembly is manufactured, allowing for timely detection of related defects with high accuracy, thereby improving the production yield of the battery cell assembly and the battery itself.

[0044] The battery disclosed in this embodiment can be a power battery or an energy storage battery. Applications of power batteries include, but are not limited to, vehicles, ships, aircraft, spacecraft, power tools, electric toys, and various mobile terminals. Applications of energy storage batteries include, but are not limited to, solar power systems, hydropower systems, and wind power systems.

[0045] like Figure 2 and Figure 3 As shown, the method 200 for detecting the appearance of the tabs of a battery cell assembly provided in this embodiment includes the following steps S21 to S25.

[0046] In step S21, a detection image 2000 including a background area 201 and a cell assembly image area 202 is acquired. The cell assembly image area 202 includes a main body area 20 and multiple electrode stacking areas (such as the negative electrode stacking area 21 and the positive electrode stacking area 22 shown in the figure). Each electrode stacking area is adjacent to the top or bottom edge of the main body area 20.

[0047] In step S22, each root corner point of the multiple tab stacking regions in the detection image is determined (root corner points P1, P2, P3, P4 as shown in the figure).

[0048] In step S23, the two sides of the main body region 20 in the detection image (sides S1 and S2 as shown in the figure) are determined.

[0049] In step S24, based on the two sides of the main body region 20 in the detection image, at least one reference edge line (reference edge lines L1, L2 as shown in the figure) is determined in the detection image.

[0050] In step S25, based on each root corner point of the multiple electrode stacking areas in the detection image and at least one reference edge line, the detection result information of the electrode appearance is determined (the detection result information includes, for example, the distances W1 and W2 shown in the figure).

[0051] The embodiments disclosed herein can be used for the visual inspection of stacked tabs in various battery cell assembly products. For example... Figure 1A and Figure 1B As shown, in some embodiments, the battery cell assembly 100 is a wound battery cell assembly, including a main body 10, a plurality of positive electrode tabs 12 (serving as the positive electrode of the battery cell assembly) stacked at the top of the main body 10, and a plurality of negative electrode tabs 11 (serving as the negative electrode of the battery cell assembly) stacked at the top of the main body 10. Figure 3As shown, the detection image 2000 obtained by taking a picture of the battery cell assembly 100 includes a background area 201 and a battery cell assembly image area 202. The battery cell assembly image area 202 includes a positive electrode tab stack area 22 and a negative electrode tab stack area 21. The positive electrode tab stack area 22 and the negative electrode tab stack area 21 are adjacent to the top edge of the main body area 20 (depending on the placement of the battery cell assembly, they may also be adjacent to the bottom edge of the main body area).

[0052] In other embodiments, the battery cell assembly is a wound battery cell assembly, and its structure can also be designed to include a main body, multiple positive electrode tabs (serving as the positive electrode of the battery cell assembly) stacked at the top of the main body, and multiple negative electrode tabs (serving as the negative electrode of the battery cell assembly) stacked at the bottom of the main body. The detection image obtained by photographing the battery cell assembly includes a background area and a battery cell assembly image area. The battery cell assembly image area includes a positive electrode tab stack area and a negative electrode tab stack area. The positive electrode tab stack area is adjacent to the top edge of the main body (or, depending on the placement of the battery cell assembly, to the bottom edge of the main body), and the negative electrode tab stack area is adjacent to the bottom edge of the main body (or, depending on the placement of the battery cell assembly, to the top edge of the main body).

[0053] The method 200 of this disclosure uses computer vision technology to inspect the appearance of the stacked tabs of the battery cell assembly based on the image of the battery cell assembly. Compared with the detection methods in related technologies that rely on manual measurement or special fixtures, it not only has higher detection efficiency and is applicable to a wide range of product specifications, but also significantly improves the accuracy of detection, thereby improving the production yield of battery cell assemblies and batteries.

[0054] The detection results of the electrode appearance may include, for example, the distance between the two root corner points of each electrode stack area (i.e., Figure 3 The distances W1, W2 shown, and / or the pass / fail assessment results for the appearance of the electrode ears.

[0055] In some embodiments, when the distance between the two root corners of the tab stacking area exceeds a distance threshold, the tab appearance can be determined to be unqualified, thereby timely detection of the defective cell assembly and preventing it from flowing into subsequent production processes, thereby improving the production yield of cell assemblies and batteries.

[0056] In some embodiments, the assemblability of the battery cell assembly can also be evaluated based on the distance between the two root corner points of the tab stacking area. For example, when the distance between the two root corner points of the tab stacking area exceeds a distance threshold, it indicates that the electrode winding is too loose or too tight, causing severe misalignment of the tabs after stacking. This can be used to review the relevant aspects of product design and manufacturing processes.

[0057] The detection image in step S21 can be obtained by taking a picture of the battery cell assembly using an image acquisition device such as an industrial camera. In some embodiments, when the shooting environment is of average or low brightness, the aperture of the image acquisition device can be adjusted to the maximum as much as possible, and the shooting exposure time can be set to not less than 8000 microseconds and not more than 12000 microseconds, so as to obtain a high-exposure detection image, making the grayscale of the image area of ​​the battery cell assembly and the background area clearly different.

[0058] In some embodiments of this disclosure, the image acquisition device and the battery cell assembly can be precisely positioned before shooting, and then the image acquisition device can be started to shoot the battery cell assembly. This allows the top and bottom edges of the main area in the detected image to be approximately parallel to the row direction (i.e., the pixel row direction in the image), and the two side edges to be approximately orthogonal to the row direction (i.e., the pixel column direction in the image).

[0059] In some other embodiments of this disclosure, the requirements for the positioning accuracy of the image acquisition device and the battery cell assembly are not high. After the detection image is captured, rotation correction can be performed on the detection image. In this embodiment, the above step S21 includes: rotating the detection image so that the top and bottom edges of the main body area are approximately parallel to the row direction (i.e., the pixel row direction in the image), and the two side edges are approximately orthogonal to the row direction (i.e., the pixel column direction in the image).

[0060] In the embodiments disclosed herein, "row direction" and "column direction" are relative terms and do not represent absolute directions. "Approximately parallel" and "approximately orthogonal" can be understood as acceptable within a certain error range, and are not required to be absolutely parallel or orthogonal.

[0061] It should be noted that in this embodiment, even if the top and bottom edges of the main body area are not parallel to each other in the relative row direction, the above method 200 is still applicable and can still obtain relatively accurate detection result information. This is because, in step S25, the detection result information of the tab appearance is determined based on the relative positional relationship between the root corner point of the tab stacking area and the reference edge line in the detection image, and the detection result information is almost unaffected by the relative position of the main body area in the detection image.

[0062] In some embodiments of this disclosure, such as Figure 3 As shown, step S21 includes: performing binarization processing on the detection image 2000 to obtain a binarized image 230, wherein the cell assembly image area 202 is the region of interest of the binarized image 230.

[0063] Image binarization, based on a set grayscale threshold, sets the grayscale value of pixels in an image to 0 or 255, thus presenting the entire image with a distinct black and white visual effect. Figure 3In the binarized image 230, the background area has a grayscale value of 0 (shown as a shadow). After binarization, the cell assembly image area 202 is selected as the region of interest in the binarized image 230. Binarizing the detection image facilitates accurate extraction of the cell assembly image area 202 in subsequent steps.

[0064] In some embodiments, such as Figure 3 As shown, step S22 includes: in the binarized image 230, based on the template image 232 configured for each root corner point and the local search region 231, matching and locating the corresponding template image 232 in each local search region 231; and, based on the matching and locating results of the template image 232 in each local search region 231, determining each root corner point (root corner points P1, P2, P3, P4 as shown in the figure) of the multiple tab stacking regions in the binarized image 230.

[0065] Template image 232 can be obtained based on cell assembly image template. Cell assembly image template refers to a standard image of a cell assembly used as a reference. Template image 232 is a portion cropped from the cell assembly image template and includes the root corner point P', which can be used as a reference for image feature matching and comparison. For ease of calculation, the root corner point P' in template image 232 can be set at the center point of the template image.

[0066] The local search region 231 is a small search area pre-defined for the binarized image 230. Matching and locating the template image 232 in the local search region 231 can greatly reduce the amount of matching calculation and improve the speed and accuracy of matching calculation.

[0067] After finding a matching image corresponding to the template image 232 within the local search region 231 (e.g., the feature similarity between the template image and the matching image is greater than a set similarity threshold), the root corner point within the local search region 231 can be determined by coordinate offset based on the matching and positioning result of the template image 232 within the local search region 231 (e.g., the pixel coordinates of one of the corner points of the template image 232).

[0068] In some embodiments, step S23 above includes the following sub-steps one to four.

[0069] In sub-step one, the cell assembly image region is extracted from the binarized image. For example, the cell assembly image region can be extracted from the binarized image based on at least one of a threshold segmentation algorithm, an image segmentation algorithm, and a maximum connected component algorithm.

[0070] In sub-step two, the cell assembly image area is scrolled (i.e. translated) by one pixel column along the row direction in the binarized image to obtain a comparison image.

[0071] In sub-step three, based on the grayscale difference between the binarized image and the comparison image, multiple edge pixels of the cell component image area in the binarized image are determined (the grayscale difference between the edge pixels in the binarized image and the comparison image is 255 or -255).

[0072] In sub-step four, edge pixels arranged in the first direction but with a spacing T less than the distance threshold are filtered out from multiple edge pixels (e.g., ...). Figure 3 The pixels at points Q1 and Q2 (which can actually be multiple pairs of pixels arranged in the first direction) are used to obtain the two sides of the main body area (which can be discontinuous). The first direction is roughly the same as the extension direction of the top and bottom edges of the main body area (which is acceptable within a certain error range).

[0073] The distance threshold in the first direction can be determined based on the distance between the two sides of the main body area in the aforementioned cell assembly image template. For example, it can be equal to or slightly less than the distance between the two sides. By adopting this embodiment, on the one hand, edge pixels that are not related to the two sides of the main body area (such as edge pixels of the tab stack area) can be filtered out. On the other hand, it can also minimize the loss or error of image features caused by poor hardware or shooting environment, thereby further improving the accuracy of detection.

[0074] like Figure 3 As shown, in some embodiments, step S24 includes: performing line fitting (e.g., by the Ransac algorithm) on the two sides S1 and S2 of the main body region 20 in the binarized image 230 to obtain two fitted sides extending by a straight line; and determining at least one reference edge line (as shown in the figure, reference edge lines L1 and L2) in the binarized image based on the two fitted sides.

[0075] The Ransac algorithm is an iterative algorithm for stochastic parameter estimation. Its basic principle is as follows: First, two points are randomly selected on one side. This dataset is used to calculate the data model. Then, all the points on that side are substituted into the data model to calculate the number of all "interior points". Through continuous iteration, the number of "interior points" of the current model is compared with the number of "interior points" of the best model previously produced. The model parameters and the number of "interior points" with the maximum number of "interior points" are recorded. When the number of "interior points" is greater than a certain number, the parameters of the final fitted line are obtained.

[0076] Any fitted side can be selected as the reference edge line, or a parallel offset can be made based on any fitted side to obtain the reference edge line. Based on the relative distances between each root corner point A1, A2, A3, A4 determined in step S22 and the reference edge line (such as reference edge line L1), the distances W1 and W2 between the two root corner points of each tab stack area are calculated, and then the appearance of the tabs of the cell assembly is judged to be qualified. The detection accuracy is high.

[0077] In some embodiments, the two fitted sides may be used as the first reference edge line and the second reference edge line, respectively. Based on the relative distance between the two root corner points of the positive electrode stacking area and the adjacent first reference edge line, the distance between the two root corner points of the positive electrode stacking area is calculated. Based on the relative distance between the two root corner points of the negative electrode stacking area and the adjacent second reference edge line, the distance between the two root corner points of the negative electrode stacking area is calculated, and then it is determined whether the appearance of the electrode of the cell assembly is qualified.

[0078] like Figure 4 As shown, some embodiments of this disclosure provide a method for detecting the appearance of the tabs of a battery cell assembly, including the following steps S401 to S410.

[0079] In step S401, the detection image acquired by the image acquisition device is obtained.

[0080] In step S402, the detected image is binarized to obtain a binarized image with the cell assembly image area as the region of interest.

[0081] In step S403, in the binarized image, based on the template images and local search regions configured for each root corner point of the positive electrode stacking region and the negative electrode stacking region, a matching and local search is performed on the corresponding template image in each local search region.

[0082] In step S404, based on the matching and localization results of the template image within each local search region, each root corner point in the binarized image is determined.

[0083] In step S405, the battery cell component image region is extracted from the binarized image based on at least one of the threshold segmentation algorithm, image segmentation algorithm, and maximum connected component algorithm.

[0084] In step S406, the cell assembly image area is scrolled one pixel column along the row direction in the binarized image to obtain a comparison image.

[0085] In step S407, based on the grayscale difference between the binarized image and the comparison image, multiple edge pixels of the cell component image area in the binarized image are determined.

[0086] In step S408, edge pixels arranged in the first direction but with a spacing less than a distance threshold are filtered out from multiple edge pixels to obtain two sides of the main body area, wherein the first direction is approximately the same as the extension direction of the top or bottom edge of the main body area.

[0087] In step S409, straight lines are fitted to the two sides of the main body region in the binarized image to obtain two fitted sides of the straight line extension, which are used as the first reference edge line and the second reference edge line, respectively.

[0088] In step S410, based on the distances from the two root corner points of the positive electrode stacking area to the first reference edge line and the distances from the two root corner points of the negative electrode stacking area to the second reference edge line, it is determined whether the appearance of the electrode tabs of the battery cell assembly is qualified.

[0089] like Figure 5 As shown in the embodiments of this disclosure, an apparatus 500 for detecting the appearance of tabs in a battery cell assembly is also provided, comprising: an acquisition unit 501 configured to acquire a detection image including a background area and a battery cell assembly image area, wherein the battery cell assembly image area includes a main body area and a plurality of tab stack areas, each tab stack area being adjacent to the top edge or bottom edge of the main body area; a first determination unit 502 configured to determine each root corner point of the plurality of tab stack areas in the detection image; a second determination unit 503 configured to determine two sides of the main body area in the detection image; a third determination unit 504 configured to determine at least one reference edge line in the detection image based on the two sides of the main body area in the detection image; and a fourth determination unit 505 configured to determine detection result information of the tab appearance based on each root corner point of the plurality of tab stack areas in the detection image and at least one reference edge line.

[0090] This disclosure also provides an electronic device, including at least one processor and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the steps of the aforementioned method.

[0091] Using the apparatus and electronic equipment described in the above embodiments of this disclosure, the stacked tabs of the battery cell assembly can be visually inspected with high accuracy, thereby improving the production yield of the battery cell assembly and the battery.

[0092] This disclosure also provides a computer-readable storage medium storing computer instructions, wherein the computer instructions are configured to cause a computer to perform the methods of any of the foregoing embodiments.

[0093] This disclosure also provides a computer program product, including a computer program, wherein the computer program, when executed by a processor, implements the method of any of the foregoing embodiments.

[0094] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this disclosure, and not to limit them. Although this disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this disclosure, and they should all be covered within the scope of the claims and specification of this disclosure. In particular, as long as there is no structural conflict, the various technical features mentioned in the various embodiments can be combined in any way. This disclosure is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. A method for detecting the appearance of the tabs in a battery cell assembly, comprising: Acquire a detection image including a background area and a cell assembly image area, wherein the cell assembly image area includes a main body area and multiple electrode stacking areas, and each electrode stacking area is adjacent to the top or bottom edge of the main body area; Identify each root corner point of multiple electrode stacking regions in the detection image; Determine the two sides of the main body region in the detected image; Based on the two sides of the main region in the detected image, at least one reference edge line is determined in the detected image; and Based on each root corner point of multiple electrode stacking areas in the detection image, at least one reference edge line, and the relative positional relationship between each root corner point of multiple electrode stacking areas in the detection image and the at least one reference edge line, the detection result information of electrode appearance is determined. The acquisition of the detection image includes: The detected image is binarized to obtain a binarized image, in which the image area of ​​the battery cell assembly is taken as the region of interest in the binarized image; Specifically, determining each root corner point of the multiple electrode stacking regions in the detection image includes: In the binarized image, based on the template image and local search region configured for each root corner point, the corresponding template image is matched and located in each local search region. The template image is a portion extracted from the cell assembly image template and includes the root corner points, serving as a reference for image feature matching and comparison; and Based on the matching and localization results of the template image within each local search region, where the template image is obtained based on the battery cell component image template, each root corner point of multiple tab stacking areas in the binarized image is determined; Among them, determining the two sides of the main body region in the detected image includes: Extract the battery cell assembly image region from the binarized image; The image area of ​​the battery cell assembly is scrolled one pixel column along the row direction in the binarized image to obtain a comparison image; Based on the grayscale difference between the binarized image and the contrast image, multiple edge pixels of the battery cell assembly image area in the binarized image are determined; and Filter out edge pixels arranged in a first direction but with a spacing less than a distance threshold from multiple edge pixels to obtain two sides of the main body area in the binarized image, wherein the first direction is approximately the same as the extension direction of the top and bottom edges of the main body area, and the distance threshold is determined based on the spacing between the two sides of the main body area in the cell assembly image template. The step of determining at least one reference edge line in the detected image based on the two sides of the main body region in the detected image includes: Line fitting is performed on the two sides of the main body region in the binarized image to obtain the two fitted sides of the extended lines; and Based on two fitted sides, at least one reference edge line is determined in the binarized image.

2. The method according to claim 1, wherein, Extracting the cell assembly image region from the binarized image, including: Extract the battery cell component image region from a binarized image based on at least one of the threshold segmentation algorithm, image segmentation algorithm, and maximum connected component algorithm.

3. The method according to claim 1, wherein, Acquire the detection image, including: The detected image is rotated to make the top and bottom edges of the main body region approximately parallel to the row direction, and the two side edges of the main body region approximately orthogonal to the row direction.

4. The method according to claim 1, wherein, The exposure time for capturing the detection image shall be no less than 8000 microseconds and no more than 12000 microseconds.

5. The method according to claim 1, wherein, The inspection results for the appearance of the electrode include: The distance between the two root corner points of each electrode stack area; and / or The result of the pass / fail assessment of the appearance of the electrode tab.

6. The method according to any one of claims 1 to 5, wherein, The image area of ​​the battery cell assembly includes two electrode stacking areas, namely a positive electrode stacking area and a negative electrode stacking area. The positive electrode stacking area and the negative electrode stacking area are both adjacent to the top edge or bottom edge of the main body area, or the positive electrode stacking area is adjacent to the top edge of the main body area and the negative electrode stacking area is adjacent to the bottom edge of the main body area.

7. An apparatus for detecting the appearance of the tabs on a battery cell assembly, comprising: The acquisition unit is configured to acquire a detection image including a background area and a cell assembly image area, wherein the cell assembly image area includes a main body area and multiple electrode stacking areas, and each electrode stacking area is adjacent to the top or bottom edge of the main body area. The first determining unit is configured to determine each root corner point of multiple electrode stacking regions in the detection image; The second determining unit is configured to determine the two sides of the main body region in the detected image; The third determining unit is configured to determine at least one reference edge line in the detected image based on two sides of the main body region in the detected image; and The fourth determining unit is configured to determine the detection result information of the appearance of the electrode based on each root corner point of the multiple electrode stacking areas in the detection image, at least one reference edge line, and the relative positional relationship between each root corner point of the multiple electrode stacking areas in the detection image and the at least one reference edge line. The acquisition of the detection image includes: The detected image is binarized to obtain a binarized image, in which the image area of ​​the battery cell assembly is taken as the region of interest in the binarized image; Specifically, determining each root corner point of the multiple electrode stacking regions in the detection image includes: In the binarized image, based on the template image and local search region configured for each root corner point, the corresponding template image is matched and located in each local search region. The template image is a portion extracted from the cell assembly image template and includes the root corner points, serving as a reference for image feature matching and comparison; and Based on the matching and localization results of the template image within each local search region, where the template image is obtained based on the battery cell component image template, each root corner point of multiple tab stacking areas in the binarized image is determined; Among them, determining the two sides of the main body region in the detected image includes: Extract the battery cell assembly image region from the binarized image; The image area of ​​the battery cell assembly is scrolled one pixel column along the row direction in the binarized image to obtain a comparison image; Based on the grayscale difference between the binarized image and the contrast image, multiple edge pixels of the battery cell assembly image area in the binarized image are determined; and Filter out edge pixels arranged in a first direction but with a spacing less than a distance threshold from multiple edge pixels to obtain two sides of the main body area in the binarized image, wherein the first direction is approximately the same as the extension direction of the top and bottom edges of the main body area, and the distance threshold is determined based on the spacing between the two sides of the main body area in the cell assembly image template. The step of determining at least one reference edge line in the detected image based on the two sides of the main body region in the detected image includes: Line fitting is performed on the two sides of the main body region in the binarized image to obtain the two fitted sides of the extended lines; and Based on two fitted sides, at least one reference edge line is determined in the binarized image.

8. A computer-readable storage medium storing computer instructions configured to cause a computer to perform the method as described in any one of claims 1 to 6.

9. A computer program product comprising a computer program that, when executed by a processor, implements the method as described in any one of claims 1 to 6.

Citation Information

Patent Citations

  • Area-array camera-based PCB bare board defect detection method

    CN106651849A

  • Battery cell quality detection method

    CN107941805A

  • Lithium battery flexible positioning method based on battery tabs

    CN112184816A