Battery cell top cover detection method and detection system, electronic equipment and readable storage medium

By acquiring two images of the battery cell top cover, identifying and correcting the area to be detected, the problem of low detection accuracy in the prior art is solved, and comprehensive detection and high-precision detection of the battery cell top cover are achieved.

CN119023670APending Publication Date: 2024-11-26CONTEMPORARY AMPEREX TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310588166.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-23
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

The existing battery cell top cover detection method requires multiple shooting stations, resulting in low detection accuracy, missing some areas, and it is impossible to fully detect all areas of the battery cell top cover.

Method used

By acquiring two images containing all areas of the battery cell top cover, the corresponding relationship of the area to be detected is determined using image recognition technology, defect detection is performed, distortion error is eliminated, and detection accuracy is improved.

Benefits of technology

It enables comprehensive inspection of all areas of the battery cap without multiple shooting stations, improves detection accuracy and reliability, and reduces leakage detection rate.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119023670A_ABST
    Figure CN119023670A_ABST
Patent Text Reader

Abstract

The embodiment of the invention provides a battery cell top cover detection method and system, electronic equipment and a readable storage medium. The cell top cover detection method comprises the following steps: acquiring a first image and a second image of a to-be-detected cell top cover; identifying the first image and the second image to obtain a first to-be-detected area in the first image and a second to-be-detected area corresponding to the first to-be-detected area in the second image; and obtaining a detection result of the battery cell top cover according to the first to-be-detected area and the second to-be-detected area. Through the method, the detection accuracy of the battery cell top cover can be effectively improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of battery detection, and in particular to a battery cell top cover detection method, a detection system, an electronic device and a readable storage medium. Background Art

[0002] The top cover of the battery cell includes multiple areas such as the explosion-proof valve, top patch and pole. At present, the stop-shooting method is usually adopted to obtain the shooting image of the top cover of the battery cell, that is, the battery cell is controlled to reach different shooting stations in turn, and the camera at each shooting station is controlled to shoot the top cover of the battery cell. In this way, the camera at each shooting station can only shoot part of the top cover of the battery cell. In order to meet the needs of production rhythm, it is usually necessary to reduce the number of shooting stations, which will miss some areas of the top cover of the battery cell, resulting in low accuracy of the top cover detection of the battery cell. Summary of the invention

[0003] The present application provides a battery cell top cover detection method, a detection system, an electronic device and a readable storage medium, which solve the problem of low accuracy in battery cell top cover defect detection.

[0004] In order to achieve the above objectives, this application adopts the following technical solutions:

[0005] In a first aspect, a method for detecting a battery cell top cover is provided, comprising:

[0006] Acquire a first image and a second image of a top cover of a battery cell to be tested;

[0007] Identify the first image and the second image to obtain a first area to be detected in the first image and a second area to be detected corresponding to the first area to be detected in the second image;

[0008] A detection result of the battery cell top cover is obtained according to the first area to be detected and the second area to be detected.

[0009] In the embodiment of the present application, the first image and the second image containing all areas of the cell top cover can be obtained, and the areas to be detected in the first image and the second image correspond to each other, and each area on the cell top cover is detected according to the corresponding areas to be detected in the first image and the second image. Through the above method, the two images captured contain all areas of the cell top cover, and there is no need to set up multiple shooting stations, which meets the production cycle requirements; at the same time, the detection accuracy is guaranteed by using two images for detection.

[0010] In an implementation of the first aspect, the component types of the battery cell top cover include a top patch, a pole, and an explosion-proof valve, and the identifying the first image to obtain a first area to be detected in the first image includes:

[0011] Recognize the first image to obtain at least one first target area in the first image;

[0012] The first area to be inspected is confirmed according to the corresponding component type of each first target area; wherein, at least one of the first areas to be inspected includes a first top patch area, a first pole area, a first explosion-proof valve area, and position information of each of the first areas to be inspected on the top cover of the battery cell.

[0013] In an implementation of the first aspect, the component types of the battery cell top cover include a top patch, a pole, and an explosion-proof valve, and the identifying the second image to obtain a second area to be detected corresponding to the first area to be detected in the second image includes:

[0014] recognizing the second image to obtain at least one second target area;

[0015] The second area to be inspected is confirmed according to the corresponding component type of each second target area; wherein at least one of the second areas to be inspected includes a second top patch area, a second pole area, a second explosion-proof valve area, and depth information of each second area to be inspected.

[0016] Through the method in the above embodiment, the corresponding areas to be inspected in the first image and the second image can be accurately determined, providing a reliable data basis for subsequent defect detection and helping to improve detection accuracy.

[0017] In an implementation of the first aspect, the step of confirming the second area to be inspected according to the component type corresponding to each of the second target areas includes:

[0018] Correcting each of the second target areas to obtain a corrected second target area;

[0019] The second area to be inspected is confirmed according to the component type corresponding to each of the second target areas and the corrected second target areas.

[0020] By correcting the second target area through the above method, the error of depth information caused by the distortion of the second image can be eliminated, thereby providing a reliable data basis for subsequent defect detection.

[0021] In an implementation of the first aspect, correcting each of the second target regions to obtain a corrected second target region includes:

[0022] Performing plane deformation correction on the second image to obtain a corrected second image; wherein the corrected second image includes a horizontal second top patch area, a horizontal second pole area, and a horizontal second explosion-proof valve area.

[0023] By performing plane deformation correction on the second image through the above method, the error of depth information caused by plane distortion of the second image can be eliminated, thereby providing a reliable data basis for subsequent defect detection.

[0024] In an implementation manner of the first aspect, when the component type corresponding to the second target area is a top patch or a pole, performing plane deformation correction on the second image to obtain a corrected second image includes:

[0025] Performing plane fitting on the second image according to the least squares method to obtain a fitting result;

[0026] The depth value of each pixel in the second image is adjusted according to the fitting result to obtain a corrected second image.

[0027] In an implementation of the first aspect, when the component type corresponding to the second target area is an explosion-proof valve, performing plane deformation correction on the second image to obtain a corrected second image includes:

[0028] Calculating an average value of depth values ​​of a preset area corresponding to the second explosion-proof valve area in the second image, wherein the preset area is connected to or spaced from the second explosion-proof valve area, and the spacing distance when spaced is within a preset distance range;

[0029] Determine the reference plane of the battery cell top cover according to the average value;

[0030] The depth value of each pixel in the second image is adjusted according to the reference plane of the battery cell top cover to obtain a corrected second image.

[0031] In the embodiment of the present application, different plane deformation correction methods can be used for the second target areas of different component types. First, the depth information of the second target area is corrected, and then defect detection is performed based on the corrected depth information of the second target area, which can effectively remove the interference of the overall tilt of the battery top cover on the detection result and improve the detection accuracy.

[0032] In an implementation of the first aspect, obtaining the detection result of the battery cell top cover according to the first area to be detected and the second area to be detected includes:

[0033] According to the first top patch area, the first pole area and / or the first explosion-proof valve area, and the horizontal second top patch area, the horizontal second pole area and / or the horizontal second explosion-proof valve area, defect detection results of the top patch, the pole and / or the explosion-proof valve are obtained.

[0034] In the embodiment of the present application, different detection methods can be used for different component types, thereby improving the detection accuracy of each component type.

[0035] In an implementation of the first aspect, the step of obtaining a defect detection result of the top patch according to the first top patch area and the horizontal second top patch area includes:

[0036] Detecting the first top patch area to obtain a first defect position in the first top patch area;

[0037] Verifying the first defect position according to the horizontal second top patch area to obtain a defect detection result of the top patch;

[0038] The step of obtaining a defect detection result of the pole according to the first pole region and the horizontal second pole region comprises:

[0039] Detecting the first pole region to obtain a second defect position in the first pole region;

[0040] The second defect position is verified according to the horizontal second pole area to obtain a defect detection result of the pole.

[0041] In an implementation of the first aspect, verifying the first defect position according to the horizontal second top patch area to obtain a defect detection result of the top patch includes:

[0042] Obtaining depth information corresponding to the first defect position from the horizontal second top patch area;

[0043] Obtaining a defect detection result of the top patch according to the depth information corresponding to the first defect position;

[0044] The verifying the second defect position according to the horizontal second pole area to obtain the pole defect detection result includes:

[0045] Obtaining depth information corresponding to the second defect position from the horizontal second pole region;

[0046] A defect detection result of the pole is obtained according to the depth information corresponding to the second defect position.

[0047] In the embodiment of the present application, the plane information of the area to be detected is first used for detection, and then the depth information of the area to be detected is used for re-judgment, which can effectively reduce the probability of misjudgment and effectively improve the accuracy of defect detection.

[0048] In an implementation of the first aspect, the step of obtaining a defect detection result of the explosion-proof valve according to the first explosion-proof valve area and the horizontal second explosion-proof valve area includes:

[0049] Detecting the horizontal second explosion-proof valve area to obtain a third defect position of the explosion-proof valve;

[0050] According to the third defect position, a defect detection result of the explosion-proof valve is obtained.

[0051] In an implementation of the first aspect, obtaining a defect detection result of the explosion-proof valve according to the third defect position includes:

[0052] Counting the number of the third defect positions to obtain the number of the third defect positions;

[0053] If the number of the third defect positions exceeds a preset number, detecting the third image of the explosion-proof valve to obtain the defect area of ​​the explosion-proof valve;

[0054] A defect detection result of the explosion-proof valve is obtained according to the third defect position and the defect area.

[0055] In the embodiment of the present application, the defect position is first detected based on the depth information, and then the plane information (two-dimensional image) is used for auxiliary judgment. The depth information of the area to be detected can be fully utilized to dig out the deformation defects at the height, effectively reducing the probability of missed detection; the plane information is used to assist in judgment, which improves the comprehensiveness of the detection and thus improves the reliability of the detection results. In addition, considering the two dimensions of defect degree and defect area, this method can effectively avoid misjudgment and help improve detection accuracy.

[0056] In an implementation of the first aspect, detecting a third defect position of the explosion-proof valve according to the horizontal second explosion-proof valve area includes:

[0057] Determining reference plane information of the explosion-proof valve according to the horizontal second explosion-proof valve area;

[0058] A third defect position of the explosion-proof valve is obtained according to the reference plane information of the explosion-proof valve.

[0059] In the embodiment of the present application, the reference plane of the explosion-proof valve is determined according to the depth information of the target area itself, which can reduce the false detection caused by the overall tilt of the explosion-proof valve area and effectively improve the detection accuracy.

[0060] In an implementation of the first aspect, determining the reference plane information of the explosion-proof valve according to the horizontal second explosion-proof valve area includes:

[0061] Performing statistics on the depth information in the horizontal second explosion-proof valve area to obtain statistical data on the depth information in the horizontal second explosion-proof valve area;

[0062] The reference plane of the explosion-proof valve is determined according to the statistical data of the depth information of the horizontal second explosion-proof valve area.

[0063] In the embodiment of the present application, the statistical data can reflect the values ​​of a group of data having an obvious central trend point. Therefore, the reference plane of the explosion-proof valve area determined based on the statistical data is more accurate.

[0064] In an implementation of the first aspect, the performing statistics on the depth information in the horizontal second explosion-proof valve area to obtain statistical data of the depth information in the horizontal second explosion-proof valve area includes:

[0065] Performing statistics on depth information in the horizontal second explosion-proof valve region to obtain a histogram;

[0066] The statistical data of the depth information of the horizontal second explosion-proof valve area is obtained according to the histogram.

[0067] In an implementation of the first aspect, the explosion-proof valve includes a protective film, and the second explosion-proof valve area includes a first protective film area, wherein the protective film is a film covering the explosion-proof valve; and the method further includes:

[0068] The defect detection result of the protective film is determined according to the positional relationship between the first protective film region and the second pole region in the second image.

[0069] In the embodiment of the present application, the positional relationship between the protective film and the pole is used to determine whether the protective film is offset. This detection method can detect the offset defect of the protective film on the one hand, and on the other hand, when the pole position is offset, it can also be detected as the offset of the protective film, which effectively reduces the probability of missed detection, thereby improving the detection reliability.

[0070] In an implementation of the first aspect, determining the defect detection result of the protective film according to the positional relationship between the first protective film region and the second pole region in the second image includes:

[0071] The defect detection result of the protective film region is determined according to the positional relationship between the center position of the first protective film region and the center position of the second pole region.

[0072] In an implementation of the first aspect, determining the defect detection result of the protective film region according to the positional relationship between the center position of the first protective film region and the center position of the second pole region includes:

[0073] Obtaining an offset distance between the protective film and the pole according to a center position of the first protective film region and a center position of the second pole region;

[0074] A defect detection result of the protective film is determined according to an offset distance between the protective film and the pole.

[0075] In the embodiment of the present application, whether the protective film is offset is determined by the offset angle between the center of the protective film and the reference point of the reference line center. This detection method can detect the offset defect of the protective film on the one hand, and on the other hand, when the pole position is offset, it can also be detected as the offset of the protective film, which effectively reduces the probability of missed detection, thereby improving the detection reliability.

[0076] In an implementation of the first aspect, the identifying the first image to obtain at least one first target area in the first image includes:

[0077] Acquire a trained detection model, where the detection model is used to segment at least one first target area from the first image;

[0078] Image detection is performed on the first image according to the trained detection model to obtain at least one first target area in the first image.

[0079] In an implementation of the first aspect, the method further includes:

[0080] Acquire a sample data set, wherein the sample data set includes a region sample corresponding to the first target region;

[0081] The detection model is trained according to the sample data set to obtain the trained detection model.

[0082] In the embodiment of the present application, a pre-trained detection model can be used to quickly and accurately identify the target area in the first image or the second image, thereby improving the efficiency of defect detection.

[0083] In a second aspect, a method for detecting a battery cell top cover is provided, comprising:

[0084] Acquire a fourth image of the top cover of the battery cell to be tested;

[0085] Recognize the fourth image to obtain a third area to be detected in the fourth image;

[0086] According to the third area to be inspected, a detection result of the battery cell top cover is obtained.

[0087] In an implementation of the second aspect, the component types of the battery cell top cover include a pole and a protective film, and the protective film is a film of an explosion-proof valve covered on the battery cell top cover;

[0088] The step of identifying the fourth image to obtain a third area to be detected in the fourth image includes:

[0089] recognizing the fourth image to obtain at least one third target area in the fourth image;

[0090] The third area to be detected is confirmed according to the component type corresponding to each of the third target areas; wherein at least one of the third areas to be detected includes a third pole area, a second protective film area, and depth information of each of the third areas to be detected on the top cover of the battery cell.

[0091] In an implementation of the second aspect, the step of confirming the third area to be inspected according to the component type corresponding to each of the third target areas includes:

[0092] Correcting each of the third target areas to obtain the corrected third target areas;

[0093] The third area to be inspected is confirmed according to the component type corresponding to each of the third target areas and the corrected third target area.

[0094] In an implementation manner of the second aspect, correcting each of the third target regions to obtain the corrected third target regions includes:

[0095] Performing plane deformation correction on the fourth image to obtain a corrected fourth image; wherein the corrected fourth image includes a horizontal third pole region and a horizontal second protective film region.

[0096] In an implementation of the second aspect, obtaining the detection result of the battery cell top cover according to the third area to be detected includes:

[0097] A defect detection result of the protective film is obtained according to the horizontal third pole region and the horizontal second protective film region.

[0098] In an implementation of the second aspect, the step of obtaining a defect detection result of the protective film according to the horizontal third pole region and the horizontal second protective film region includes:

[0099] The defect detection result of the protective film is determined according to the positional relationship between the horizontal third pole region and the horizontal second protective film region.

[0100] In an implementation of the second aspect, determining the defect detection result of the protective film according to the positional relationship between the horizontal third pole region and the horizontal third protective film region includes:

[0101] The defect detection result of the protective film region is determined according to the positional relationship between the center position of the horizontal second protective film region and the center position of the horizontal third pole region.

[0102] In an implementation of the second aspect, determining the defect detection result of the protective film region according to the positional relationship between the center position of the horizontal second protective film region and the center position of the horizontal third pole region includes:

[0103] Obtaining an offset distance between the protective film and the pole according to the center position of the horizontal second protective film area and the center position of the horizontal third pole area;

[0104] A defect detection result of the protective film is determined according to an offset distance between the protective film and the pole.

[0105] In a third aspect, a battery cell top cover detection device is provided, comprising:

[0106] The acquisition unit is used to acquire a first image and a second image of a top cover of a battery cell to be tested.

[0107] The recognition unit is used to recognize the first image and the second image to obtain a first area to be detected in the first image and a second area to be detected corresponding to the first area to be detected in the second image.

[0108] A detection unit is used to obtain a detection result of the battery cell top cover according to the first area to be detected and the second area to be detected.

[0109] In a third aspect, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the battery cell top cover detection method as described in any one of the first aspect or the battery cell top cover detection method as described in any one of the second aspect is implemented.

[0110] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the battery cell top cover detection method as described in any one of the first aspect or the battery cell top cover detection method as described in any one of the second aspect is implemented.

[0111] In a fifth aspect, a detection system is provided, comprising a carrying device, an imaging device and an electronic device; the carrying device is used to carry a battery cell to be tested; the imaging device is used to photograph a battery cell top cover of the battery cell to be tested on the carrying device; and the electronic device is used to perform defect detection on the battery cell top cover of the battery cell to be tested based on the image photographed by the imaging device.

[0112] In an implementation of the fifth aspect, the imaging device includes a first camera, which is used to obtain a first image, a second image or a fourth image of the top cover of the battery cell.

[0113] In an implementation of the fifth aspect, the imaging device includes a second camera for acquiring a third image of the battery cell top cover.

[0114] 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.

[0115] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0116] Figure 1 is a schematic diagram of a battery cell top cover provided in an embodiment of the present application;

[0117] Figure 2 is a schematic diagram of a detection system provided in an embodiment of the present application;

[0118] Figure 3 is a schematic diagram of the 3D camera detection principle provided in an embodiment of the present application;

[0119] Figure 4 is a schematic diagram of line scan shooting provided by an embodiment of the present application;

[0120] Figure 5 It is a flow chart of a method for detecting a battery cell top cover provided in an embodiment of the present application;

[0121] Figure 6 It is a schematic diagram of plane correction of the explosion-proof valve area provided in an embodiment of the present application;

[0122] Figure 7 is a schematic diagram of a top patch defect detection process provided by an embodiment of the present application;

[0123] Figure 8 is a schematic diagram of a histogram provided in an embodiment of the present application;

[0124] Fig. 9It is a schematic diagram of the explosion-proof valve defect detection process provided by the embodiment of the present application;

[0125] Fig.10 is a schematic diagram of protective film deviation defect detection provided by an embodiment of the present application;

[0126] Fig.11 is a schematic diagram of a protective film defect detection process provided by an embodiment of the present application;

[0127] Fig.12 is a structural block diagram of a battery cell top cover detection device provided in an embodiment of the present application;

[0128] Fig.13 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0129] The following embodiments of the technical solution of the present application are described in detail in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application, and are therefore only used as examples, and cannot be used to limit the scope of protection of the present application.

[0130] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field 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" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0131] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0132] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0133] In the description of the embodiments of the present application, the term "and / or" is only a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0134] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0135] background

[0136] The cell top cover consists of several areas. Figure 1 , is a schematic diagram of a battery cell top cover provided in an embodiment of the present application. Figure 1 As shown, the battery cell top cover includes a top patch area 111, an explosion-proof valve area 112 and a pole area 113. There is a height difference between these areas. For example, taking the top patch as the reference horizontal plane, the top surface of the pole is higher than the top patch, and the aluminum foil surface of the explosion-proof valve is lower than the top patch. Among them, the battery cell top cover also includes a protective film area. A protective film is usually provided on the surface of the explosion-proof valve to protect the explosion-proof valve. The protective film can be a PP film (a film made of polypropylene as raw material).

[0137] At present, the shooting image of the battery cell top cover is usually obtained by stopping shooting, that is, the battery cell is controlled to reach different shooting stations in turn, and the camera at each shooting station is controlled to shoot the battery cell top cover. In this way, the camera at each shooting station can only shoot part of the battery cell top cover. In order to meet the needs of production tact, it is usually necessary to reduce the shooting stations, which will miss some areas of the battery cell top cover, resulting in low accuracy of battery cell top cover detection.

[0138] In order to solve the above problems, an embodiment of the present application provides a method for detecting the top cover of a battery cell. In the embodiment of the present application, a first image and a second image containing all areas of the top cover of the battery cell can be obtained, and the areas to be detected in the first image and the second image correspond to each other. The various areas on the top cover of the battery cell are detected according to the corresponding areas to be detected in the first image and the second image. Through the above method, both images taken contain all areas of the top cover of the battery cell, and there is no need to set up multiple shooting stations, which meets the requirements of production rhythm; at the same time, the detection accuracy is guaranteed by using two images for detection.

[0139] First, the detection system is introduced.

[0140] See also Figure 2 , is a schematic diagram of a detection system provided in an embodiment of the present application. Figure 2As shown, the detection system may include a carrying device 21, an imaging device 22 and an electronic device 23. The carrying device 21 is used to carry the battery cell to be tested; the imaging device 22 is used to photograph the battery cell top cover of the battery cell to be tested on the carrying device 21; and the electronic device 23 is used to perform defect detection on the battery cell top cover of the battery cell to be tested based on the image photographed by the imaging device 22.

[0141] The imaging device 22 and the electronic device 23 may exchange data in a wired or wireless manner.

[0142] In one implementation, a conveyor belt may be provided on the carrier device 21, and the battery cell to be tested is placed on the conveyor belt and is conveyed to the shooting station as the conveyor belt moves. An imaging device 22 is provided at the shooting station. When the battery cell to be tested arrives at the shooting station, the imaging device 22 shoots the battery cell top cover of the battery cell to be tested on the shooting station to obtain a first image and a second image, and then sends the first image and the second image to the electronic device 23. After receiving the first image and the second image, the electronic device 23 performs defect detection on the battery cell top cover of the battery cell to be tested using the battery cell top cover detection method provided in the following embodiment of the present application.

[0143] In some embodiments, the imaging device 22 includes a first camera for acquiring a first image, a second image, or a fourth image of the top cover of the battery cell.

[0144] There are height differences in various areas of the battery cell top cover. For example, taking the top patch as the reference horizontal plane, the top surface of the pole is higher than the top patch, while the aluminum foil surface of the explosion-proof valve is lower than the top patch. It can be seen that the defects of the battery cell top cover include deformation defects based on height. However, in the related art, only deformation defects based on area can be detected, and all defects of the battery cell top cover cannot be detected. The detection is not comprehensive, resulting in low reliability of the detection results.

[0145] In order to solve the above problem, in one embodiment, the first camera may be a 3D camera. A 3D camera is also called a depth camera, which can detect the depth of field of the shooting space, that is, it can obtain the distance between each point on the photographed object and the camera. Figure 3 , is a schematic diagram of the 3D camera detection principle provided by the embodiment of the present application. Figure 3 As shown, the 3D camera 31 reconstructs the surface contour of the object by capturing the laser line information projected by the built-in laser generator on the surface of the object 32.

[0146] The scanned image captured by the 3D camera includes not only the plane information of the object being photographed (such as Figure 3 The x-axis and y-axis coordinates shown in FIG. 1 ) also include the depth information of the photographed object (such as Figure 3, where each set of plane information corresponds to a depth value. For example, each (x, y) coordinate corresponds to a z coordinate, that is, (x, y, z) constitutes the three-dimensional information of a point on the object being measured. In practical applications, the scanned image can be represented as a grayscale image or a pseudo-color image, and each pixel in the grayscale image or pseudo-color image corresponds to a depth value.

[0147] In the embodiment of the present application, the first image may be a grayscale image or a pseudo-color image taken by a 3D camera, and the second image and the fourth image may be depth images (such as point cloud images) taken by a 3D camera. In other words, the first image includes the position information of each area on the top cover of the battery cell, and the second image and the fourth image include the depth information (such as depth value) of each area on the top cover of the battery cell.

[0148] In the embodiment of the present application, the depth information of the object to be measured is obtained by a 3D camera, which can not only detect deformation defects on the top cover of the battery cell based on the area standard, but also detect deformation defects based on the height standard. The detection is more comprehensive and the reliability of the detection results is effectively improved.

[0149] In one implementation, the first camera can shoot the top cover of the battery cell in a linear scanning manner. The linear scanning shooting method is that when shooting, like scanning, there is a phase uniform motion between the camera and the object being shot. Figure 4 , is a schematic diagram of line scan shooting provided by an embodiment of the present application. Figure 4 As shown, the moving direction 44 of the battery cell 42 is perpendicular to the shooting direction 43 of the camera 41 . During the movement of the battery cell, the camera acquires a two-dimensional image line by line through continuous single-line scanning.

[0150] Compared with the area array shooting method, the linear scanning method not only has a fast acquisition speed but also a higher resolution. Therefore, the use of the linear scanning method can not only meet the needs of production rhythm, but also ensure the clarity of the captured image, thereby ensuring the detection accuracy.

[0151] Optionally, in the embodiment of the present application, the first camera may be a charge coupled device (CCD) camera. CCD is a semiconductor device that can convert optical images into digital signals. CCD cameras have the characteristics of small size, light weight, unaffected by magnetic fields, and resistant to vibration and impact.

[0152] In some other embodiments, the imaging device 22 includes a second camera for acquiring a third image of the top cover of the battery cell.

[0153] In the embodiment of the present application, the second camera may be a 2D camera, and the third image may be a two-dimensional image captured by the 2D camera, such as an RGB image.

[0154] Some two-dimensional information (such as RGB information) of the battery cell top cover may be ignored in the image captured by the first camera. Using the image captured by the second camera to assist in detection is equivalent to more comprehensively considering the feature information of the battery cell top cover, which is conducive to improving detection accuracy.

[0155] Based on the above detection system, the electronic device 23 can obtain the first image and the second image of the battery cell top cover to be tested, and perform defect detection on the battery cell top cover according to the first image and the second image. The battery cell top cover detection method is described below.

[0156] See also Figure 5 , is a flow chart of a method for detecting a battery cell top cover provided in an embodiment of the present application. As an example and not a limitation, Figure 5 As shown, the battery cell top cover detection method may include the following steps:

[0157] Right 1

[0158] S501, acquiring a first image and a second image of a top cover of a battery cell to be tested.

[0159] like Figure 2 In the embodiment, the first image is a grayscale image or a pseudo-color image obtained by the first camera, and the second image is a depth map obtained by the first camera. Wherein, the grayscale image refers to an image represented by grayscale, and the grayscale is divided into 256 grayscales. For example, pixels with the same depth value in the grayscale image are represented as the same grayscale. Pseudo-color image refers to the use of color images to represent monochrome images, and each pixel value in the pseudo-color image corresponds to an index value or code. For example, pixels with the same depth value in the pseudo-color image are expressed as the same color, and the depth of each pixel can be distinguished by the color in the pseudo-color image. Each pixel in the grayscale image or pseudo-color image corresponds to a pixel in the depth map. In other words, each pixel of the battery cell top cover taken by the first camera has its corresponding position information (such as (x, y) coordinates) in the grayscale image and a particularly corresponding depth value (such as z coordinate) in the depth map. In this way, the three-dimensional coordinate information of each pixel on the battery cell top cover can be obtained by the first camera.

[0160] S502: Identify the first image and the second image to obtain a first area to be detected in the first image and a second area to be detected corresponding to the first area to be detected in the second image.

[0161] like Figure 1 In the embodiment, the top cover of the battery cell includes a top patch area, an explosion-proof valve area and a pole area. Accordingly, in the embodiment of the present application, the area to be detected includes a top patch area, an explosion-proof valve area and a pole area.

[0162] Right 2-3

[0163] In some embodiments, the step of identifying the first image in S502 to obtain the first area to be detected in the first image includes: identifying the first image to obtain at least one first target area in the first image; confirming the first area to be detected according to the corresponding component type of each first target area; wherein at least one first area to be detected includes a first top patch area, a first pole area, a first explosion-proof valve area, and position information of each first area to be detected on the top cover of the battery cell.

[0164] The step of identifying the second image in S502 to obtain the second area to be detected in the second image includes: identifying the second image to obtain at least one second target area; confirming the second area to be detected according to the component type corresponding to each second target area; wherein at least one second area to be detected includes a second top patch area, a second pole area, a second explosion-proof valve area, and depth information of each second area to be detected.

[0165] Among them, the component types include top patch, explosion-proof valve and pole. Accordingly, at least one first target area identified from the first image may include the top patch area, explosion-proof valve area and pole area, and at least one second target area identified from the second image may include the top patch area, explosion-proof valve area and pole area. Since the top cover of the battery cell includes multiple areas, in order to ensure the accuracy of subsequent detection, in the embodiment of the present application, the corresponding first area to be detected and the second area to be detected are confirmed according to the component type of each target area.

[0166] For example, three first target areas A, B and C are identified from the first image, and three second target areas a, b and c are identified from the second image. Among them, A and a have the same component type, both are top patches; B and b have the same component type, both are explosion-proof valves; C and c have the same component type, both are poles. Then A and a are confirmed as the corresponding first and second areas to be detected, B and b are confirmed as the corresponding first and second areas to be detected, and C and c are confirmed as the corresponding first and second areas to be detected.

[0167] Of course, it is also possible to perform defect detection on only one of the identified target areas, in which case a set of corresponding first to-be-detected areas and second to-be-detected areas are identified. Continuing with the above example, assuming that defect detection is required for the top patch, A is identified as the first to-be-detected area, and a is identified as the second to-be-detected area.

[0168] Through the method in the above embodiment, the corresponding areas to be inspected in the first image and the second image can be accurately determined, providing a reliable data basis for subsequent defect detection and helping to improve detection accuracy.

[0169] Right 19-20

[0170] In some embodiments, the method of identifying the first image to obtain the first target area, or identifying the second image to obtain the second target area may include:

[0171] Acquire a trained detection model, where the detection model is used to segment at least one first target area from the first image, or segment at least one second target area from the second image; perform image detection on the first image or the second image according to the trained detection model to obtain at least one first target area in the first image or at least one second target area in the second image.

[0172] It can be understood that the detection model can be used to identify only one of the first image or the second image, or can be used to identify both the first image and the second image.

[0173] Accordingly, the method further includes:

[0174] A sample data set is obtained, wherein the sample data set includes area samples corresponding to the first target area; and the detection model is trained according to the sample data set to obtain the trained detection model.

[0175] For example, when the detection model is used to identify the first image, the sample data set includes the top patch area, the explosion-proof valve area, and the pole area, and the area samples are grayscale images or pseudo-color images. When the detection model is used to identify the second image, the sample data set includes the top patch area, the explosion-proof valve area, and the pole area, and the area samples are depth images.

[0176] Through the pre-trained detection model, the target area in the first image or the second image can be quickly and accurately identified, which is conducive to improving the efficiency of defect detection.

[0177] In some other embodiments, the method of identifying the first image to obtain the first target area, or identifying the second image to obtain the second target area may include:

[0178] A preset template may be used to compare with the first image or the second image, and a region matching the template may be identified from the first image or the second image and recorded as a target region.

[0179] Right 4-7

[0180] In some embodiments, according to the component type corresponding to each of the second target areas, the step of confirming the second area to be inspected may include:

[0181] Correcting each of the second target areas to obtain a corrected second target area;

[0182] The second area to be inspected is confirmed according to the component type corresponding to each of the second target areas and the corrected second target areas.

[0183] By correcting the second target area through the above method, the error of depth information caused by the distortion of the second image can be eliminated, thereby providing a reliable data basis for subsequent defect detection.

[0184] In actual applications, due to certain installation errors in the shooting device, the shooting direction of the shooting device and the plane where the battery cell top cover is located are not perpendicular, resulting in planar distortion of the captured second image, thereby affecting the accuracy of the depth information of each pixel in the second image.

[0185] The above correction step includes: performing plane deformation correction on the second image to obtain a corrected second image; wherein the corrected second image includes a horizontal second top patch area, a horizontal second pole area, and a horizontal second explosion-proof valve area.

[0186] By performing plane deformation correction on the second image through the above method, the error of depth information caused by plane distortion of the second image can be eliminated, thereby providing a reliable data basis for subsequent defect detection.

[0187] In the embodiment of the present application, different plane deformation correction methods may be used for second target areas of different component types.

[0188] In one implementation, when the component type corresponding to the second target area is a top patch or a pole, a plane fitting is performed on the second image according to the least squares method to obtain a fitting result; the depth value of each pixel point in the second image is adjusted according to the fitting result to obtain a corrected second image.

[0189] Optionally, HALCON machine vision software can be used for calibration. HALCON is a complete set of standard machine vision algorithm packages with a widely used machine vision integrated development environment. Specifically, the fit_surface_first_order operator in HALCON (the principle is the least squares method) is used for surface fitting, and then the value in the z direction (depth value) is adjusted by the scale_image operator. This implementation method can be applied to the case where the second target area is the top patch area or the pole area.

[0190] In another implementation, when the component type corresponding to the second target area is an explosion-proof valve, the average value of the depth value of a preset area corresponding to the second explosion-proof valve area in the second image is calculated, wherein the preset area is connected to or spaced apart from the second explosion-proof valve area, and the spacing distance during the spacing is within a preset distance range; the reference plane of the battery cell top cover is determined based on the average value; the depth value of each pixel point in the second image is adjusted based on the reference plane of the battery cell top cover to obtain a corrected second image.

[0191] This method can be applied to the case where the second target area is an explosion-proof valve area. Figure 6 , is a schematic diagram of the plane correction of the explosion-proof valve area provided in the embodiment of the present application. Figure 6 As shown, the average depth value of the top patch area 62 (the area in the dotted box) around the explosion-proof valve area 61 is first calculated, and the depth value of each pixel in the explosion-proof valve area 61 is subtracted from the average value to obtain the corrected depth information of the explosion-proof valve area 61.

[0192] In the embodiment of the present application, the depth information of the second target area is first corrected, and then defect detection is performed based on the corrected depth information of the second target area. This can effectively remove the interference of the overall tilt of the battery cell top cover on the detection result, thereby improving the detection accuracy.

[0193] S503: Obtain a detection result of the battery cell top cover according to the first area to be detected and the second area to be detected.

[0194] As described in step S502, the second target area is first calibrated. Accordingly, S503 includes:

[0195] According to the first top patch area, the first pole area and / or the first explosion-proof valve area, and the horizontal second top patch area, the horizontal second pole area and / or the horizontal second explosion-proof valve area, defect detection results of the top patch, the pole and / or the explosion-proof valve are obtained.

[0196] In the embodiment of the present application, the first image and the second image containing all areas of the cell top cover can be obtained, and the areas to be detected in the first image and the second image correspond to each other, and each area on the cell top cover is detected according to the corresponding areas to be detected in the first image and the second image. Through the above method, the two images captured contain all areas of the cell top cover, and there is no need to set up multiple shooting stations, which meets the production cycle requirements; at the same time, the detection accuracy is guaranteed by using two images for detection.

[0197] In the embodiment of the present application, different detection methods can be used for different component types, which are introduced below according to the component type.

[0198] Right 9-10

[0199] 1. Top patch or pole

[0200] In some embodiments, the step of obtaining a defect detection result of the top patch according to the first top patch area and the horizontal second top patch area includes:

[0201] The first top patch area is detected to obtain a first defect position in the first top patch area; the first defect position is verified according to the horizontal second top patch area to obtain a defect detection result of the top patch.

[0202] In an embodiment of the present application, an image detection method can be used to obtain the first defect position. In one implementation, the first top patch area is input into a trained image detection model, and the first defect position in the first top patch area is output. The image detection model is an algorithm model that can realize the image detection function, such as a semantic segmentation model, a deep learning model that can realize the image detection function, etc., which is not specifically limited here.

[0203] Optionally, a method of verifying the first defect position may include:

[0204] Depth information corresponding to the first defect position is obtained from the horizontal second top patch area; and a defect detection result of the top patch is obtained according to the depth information corresponding to the first defect position.

[0205] Exemplarily, a depth value corresponding to the first defect position is obtained from the horizontal second top patch area; if the depth value corresponding to the first defect position is greater than a first threshold, the detection result is determined to be that the top patch has a defect; if the depth value corresponding to the first defect position is less than or equal to the first threshold, the detection result is determined to be that the top patch is normal. The first threshold can be preset according to actual production requirements.

[0206] Typically, the first defect position corresponds to multiple pixels. In one implementation, the average value of the depth values ​​of the multiple pixels corresponding to the first defect position is calculated, and the average value is determined as the depth value corresponding to the first defect position. In another implementation, the mode of the depth values ​​of the multiple pixels corresponding to the first defect position is counted, and the mode is determined as the depth value corresponding to the first defect position. Of course, in practical applications, other calculation methods can also be used. The above are just two examples of calculation and are not intended to be specific limitations.

[0207] For example, see Figure 7 , is a schematic diagram of the top patch defect detection process provided by the embodiment of the present application. Figure 7As shown, as an example and not limitation, the defect detection process of the top patch may include the following steps:

[0208] 7-1, obtaining a first image and a second image of a top cover of a battery cell to be tested.

[0209] 7-2. Perform plane deformation correction on the second image to obtain a horizontal second top patch area.

[0210] The details of steps 7-1 to 7-2 can be found in the description of S501-S502 above, which will not be repeated here.

[0211] 7-3. Detect the first top patch area in the first image to obtain a first defect position in the first top patch area.

[0212] 7-4. Verify the first defect position based on the horizontal second top patch area.

[0213] 7-5. If the depth value corresponding to the first defect position is greater than the first threshold, it is determined that the detection result is that there is a defect in the top patch.

[0214] 7-6. If the depth value corresponding to the first defect position is less than or equal to the first threshold, the detection result is determined to be that the top patch is normal.

[0215] Similarly, for the pole, the step of obtaining the defect detection result of the pole according to the first pole area and the horizontal second pole area includes:

[0216] The first pole region is detected to obtain a second defect position in the first pole region; the second defect position is verified according to the horizontal second pole region to obtain a defect detection result of the pole.

[0217] The verifying the second defect position according to the horizontal second pole area to obtain the pole defect detection result includes:

[0218] Depth information corresponding to the second defect position is obtained from the horizontal second pole region; and a defect detection result of the pole is obtained according to the depth information corresponding to the second defect position.

[0219] The method of detecting pole defects is the same as the method of detecting top patch defects described above. For details, please refer to the above-mentioned method of detecting top patch defects, which will not be repeated here.

[0220] In the embodiment of the present application, the plane information of the area to be detected is first used for detection, and then the depth information of the area to be detected is used for re-judgment, which can effectively reduce the probability of misjudgment and effectively improve the accuracy of defect detection.

[0221] The detection method in the above embodiment is suitable for detecting target areas with larger areas or more obvious planar features, such as top patch areas or pole areas. However, for target areas with smaller areas or less obvious planar features, the detection accuracy of the method in the above embodiment is low.

[0222] Right 11-15

[0223] 2. Explosion-proof valve

[0224] In some embodiments, the step of obtaining a defect detection result of the explosion-proof valve according to the first explosion-proof valve area and the horizontal second explosion-proof valve area includes:

[0225] I. Detect the horizontal second explosion-proof valve area to obtain a third defect position of the explosion-proof valve.

[0226] II. Obtaining defect detection results of the explosion-proof valve according to the third defect position.

[0227] In one implementation, step I may include:

[0228] The reference plane information of the explosion-proof valve is determined according to the horizontal second explosion-proof valve area; and the third defect position of the explosion-proof valve is obtained according to the reference plane information of the explosion-proof valve.

[0229] In the embodiment of the present application, the reference plane of the explosion-proof valve area is determined according to the depth information of the explosion-proof valve area itself, which can reduce the false detection caused by the overall tilt of the explosion-proof valve area and effectively improve the detection accuracy.

[0230] A method for determining the reference plane of the explosion-proof valve includes: performing statistics on the depth information in the horizontal second explosion-proof valve area to obtain statistical data on the depth information of the horizontal second explosion-proof valve area; and determining the reference plane of the explosion-proof valve based on the statistical data on the depth information of the horizontal second explosion-proof valve area.

[0231] Optionally, the statistic may be mode or median, etc.

[0232] Specifically, the method for acquiring the statistical data includes: performing statistics on the depth information in the horizontal second explosion-proof valve area to obtain a histogram; and obtaining the statistical data of the depth information in the horizontal second explosion-proof valve area according to the histogram.

[0233] For example, see Figure 8 , is a schematic diagram of a histogram provided in an embodiment of the present application. Figure 8 As shown in FIG. 1 , the horizontal axis is the depth value (in μm) and the vertical axis is the number of position points. As can be seen from the figure, the number of position points corresponding to the depth value -250 is the largest, so -250 is the mode of the histogram.

[0234] In practical applications, the reference plane is determined based on the mode and actual needs. For example, the plane corresponding to the mode can be determined as the reference plane of the explosion-proof valve area, such as Figure 8 In this example, the plane corresponding to -250 can be determined as the reference plane of the explosion-proof valve area. For another example, the plane corresponding to the sum of the mode and the preset value can be determined as the reference plane of the explosion-proof valve area, such as Figure 8 In the example, the plane corresponding to -250+(-150)=-400 can be determined as the reference plane of the explosion-proof valve area.

[0235] In the embodiment of the present application, since the mode can reflect the value of a group of data having an obvious central trend point, the reference plane of the explosion-proof valve area determined according to the mode is more accurate.

[0236] In one implementation of the detection method for the third defect position, the depth value of each pixel in the explosion-proof valve area is compared with the depth value of the reference plane of the explosion-proof valve area; if the depth value of the pixel is less than the depth value of the reference plane, the position of the pixel is determined to be the third defect position; if the depth value of the pixel is greater than or equal to the depth value of the reference plane, the pixel is determined to be normal.

[0237] Exemplary, continue Figure 8 In the example, if the depth value of the reference plane is -400, if the depth value of the pixel point in the explosion-proof valve area is less than -400, it means that the position of the pixel point is the second defect position; if the depth value of the pixel point in the explosion-proof valve area is greater than -400, it means that the pixel point is normal.

[0238] In some other implementations of the third defect position detection, the depth value of each pixel point in the explosion-proof valve area is compared with the depth value of the reference plane of the explosion-proof valve area; the number of pixel points whose depth values ​​are less than the depth value of the reference plane is counted; if the number reaches a preset number, the position of the pixel point whose depth value is less than the depth value of the reference plane is determined to be the third defect position; if the number does not reach the preset number, the explosion-proof valve area is determined to be normal, that is, there is no third defect position.

[0239] Compared with the first implementation, in the second implementation, when the number of pixel points whose depth value is less than the depth value of the reference surface reaches a preset number, the third defect position is determined to exist. This method can effectively avoid misjudgment caused by inaccurate detection or the influence of individual position points, and improve the detection accuracy.

[0240] In one implementation of step II, as long as the number of the third defect positions exceeds a preset number, it is determined that the explosion-proof valve has defects. However, this method is prone to ignoring the situation where the explosion-proof valve area is overall depressed or overall convex.

[0241] In one implementation, step II includes:

[0242] The number of the third defect positions is counted to obtain the number of the third defect positions; if the number of the third defect positions exceeds a preset number, the third image of the explosion-proof valve is detected to obtain the defect area of ​​the explosion-proof valve; based on the third defect positions and the defect area, a defect detection result of the explosion-proof valve is obtained.

[0243] The third image can be an RGB image or a two-dimensional grayscale image. The use of an RGB image can more accurately and clearly reflect the planar features of the area to be detected. Figure 2 As described in the embodiment, the third image can be taken by the second camera. Unlike the first camera, the first camera shoots the entire area of ​​the battery cell top cover, while the second camera shoots the area to be inspected (such as the explosion-proof valve area). In other words, the shooting range of the second camera is smaller and more targeted. In addition, since the second camera only shoots the area to be inspected, there is no need to have excessively high requirements on the shooting accuracy of the second camera while meeting the production rhythm, which reduces the detection cost.

[0244] Optionally, in step II, the defect area in the third image can be detected using an existing image detection method. In one implementation, the third image is input into a trained image detection model, and the defect area in the third image is output. In another implementation, the third image is input into a trained image detection model, and the defect position in the third image is output, and then the defect area is calculated based on the defect position. Among them, the image detection model is an algorithm model that can realize the image detection function, such as a semantic segmentation model, a deep learning model that can realize the image detection function, etc., which is not specifically limited here.

[0245] Optionally, obtaining the defect detection result of the explosion-proof valve according to the third defect position and the defect area may include: if the defect degree satisfies the first condition and the defect area satisfies the second condition, then it is determined that there is a defect in the explosion-proof valve area; if the defect degree does not satisfy the first condition and / or the defect area does not satisfy the second condition, then it is determined that the explosion-proof valve area is normal, that is, there is no defect. The first condition is that the number of pixels contained in the third defect position reaches a preset number, and the second condition is that the defect area reaches a preset area.

[0246] In the embodiment of the present application, considering the two dimensions of defect degree and defect area, this method can effectively avoid misjudgment and help improve detection accuracy.

[0247] For example, see Fig. 9 , is a schematic diagram of the explosion-proof valve defect detection process provided by the embodiment of the present application. Fig. 9As shown, the detection process may include the following steps:

[0248] 9-1, obtaining a first image and a second image of a top cover of a battery cell to be tested.

[0249] 9-2, perform plane deformation correction on the second image to obtain a horizontal second explosion-proof valve area.

[0250] The details of steps 9-1 to 9-2 can be found in the description of S501-S502 above, which will not be repeated here.

[0251] 9-3. Determine a reference plane of the explosion-proof valve according to the horizontal second explosion-proof valve area.

[0252] 9-4. Detect the third defect position of the horizontal second explosion-proof valve area according to the reference plane of the explosion-proof valve.

[0253] 9-5. Detect the third image of the explosion-proof valve to obtain the defect area of ​​the explosion-proof valve.

[0254] 9-6. According to the third defect position and defect area, the defect detection result of the explosion-proof valve is obtained.

[0255] 9-7, if the degree of defect meets the first condition and the area of ​​defect meets the second condition, it is determined that the explosion-proof valve has defects.

[0256] 9-8, if the degree of the defect does not satisfy the first condition, and / or the area of ​​the defect does not satisfy the second condition, it is determined that the explosion-proof valve is normal.

[0257] The details of steps 9-3 to 9-8 can be found in the description of the above explosion-proof valve embodiment, which will not be repeated here.

[0258] The detection method in the above embodiment is suitable for detecting a target area with a relatively small detection area or unclear planar features, such as an explosion-proof valve area.

[0259] Figure 7 In the detection method shown in the embodiment, the defect position is first detected based on the plane information (grayscale image or pseudo-color image), and then the defect position is re-judged using the depth information. Figure 7 The detection method shown in the embodiment is different in that: Fig. 9 The detection method in the embodiment first detects the defect location based on the depth information, and then uses the plane information (two-dimensional image) for auxiliary judgment. In the embodiment of the present application, different detection methods are used for different areas on the top cover of the battery cell, which is more targeted. Specifically, for target areas with larger areas or more obvious plane features, such as the top patch area or the pole area, the detection method is used. Figure 7Detection method in the embodiment. Since the top patch area is large and may be engraved with information such as a QR code, it is not possible to accurately locate the defect by using a histogram statistical method, and false detection is prone to occur. For the pole area, the center of the top surface is concave and the material itself is not smooth. In other words, the height of the pole cannot be unified by a reference plane. Therefore, it is not possible to accurately locate the defect by using a histogram statistical method, and false detection is also prone to occur. Figure 7 The detection method in the embodiment can make full use of the plane information of the top patch area or the pole area to discover the deformation defects on the area; in addition, the plane information is used to detect the defect position, and the depth information is used to re-judge the defect, which is conducive to improving the detection efficiency. For target areas with smaller areas or less obvious plane features, such as the explosion-proof valve area, the Fig. 9 The detection method in the embodiment. Since the explosion-proof valve area is small and its concave surface is relatively smooth, it is difficult to detect the area deformation. Fig. 9 The detection method in the embodiment can make full use of the depth information of the area to be detected, explore the deformation defects at the height, and effectively reduce the probability of missed detection; use plane information to assist judgment, improve the comprehensiveness of detection, and thus improve the reliability of the detection result.

[0260] Right 16-18

[0261] 3. Protective film

[0262] like Figure 1 As described in the embodiment, a protective film, such as a PP film, is provided on the surface of the explosion-proof valve to protect the explosion-proof valve. In the actual production process, the protective film may have an offset defect, which will cause the protective film to fail to protect the explosion-proof valve well.

[0263] In some embodiments, the first image further includes a first protective film area.

[0264] The method further comprises:

[0265] The defect detection result of the protective film is determined according to the positional relationship between the first protective film region and the second pole region in the second image.

[0266] In one implementation, the positional relationship is a positional relationship between a center position of the first protective film region and a center position of the second pole region.

[0267] Of course, other position points may also be used to calculate the position relationship, such as boundary points, etc. However, in practical applications, the detection of the center position is relatively simple, which is conducive to improving the detection efficiency.

[0268] The step of determining the defect detection result of the protective film region according to the positional relationship between the center position of the first protective film region and the center position of the second pole region comprises:

[0269] According to the center position of the first protective film area and the center position of the second pole area, the offset distance between the protective film and the pole is obtained; according to the offset distance between the protective film and the pole, the defect detection result of the protective film is determined.

[0270] In one implementation, according to the formula and Calculate the center position of the first protective film area, where (x c ,y c ) represents the coordinates of the center position of the first protective film area, M 10 represents the sum of the x coordinates of each pixel in the first protective film area, M 01 represents the sum of the y coordinates of each pixel in the first protective film area, M 00 Represents the area of ​​the first protective film region.

[0271] Usually, the center position of the pole top surface is concave. In one implementation, the plane information of the pole top surface can be used for image detection to obtain the center position of the second pole area. For example, the second pole area can be segmented from the second image, and then image detection can be performed based on the plane information of the second pole area (such as a grayscale image or a pseudo-color image).

[0272] Optionally, determining the defect detection result of the protective film based on the offset distance between the protective film and the pole may include: calculating the connecting line segment between the center positions of the two second pole regions; calculating the center of the connecting line segment as a reference point; calculating the offset distance between the center position of the first protective film region and the reference point; if the offset distance is within a preset distance range, it is determined that the protective film is normal, that is, there is no defect; if the offset distance exceeds the preset distance range, it is determined that the protective film has a defect.

[0273] For example, see Fig.10 , is a schematic diagram of the protection film offset defect detection provided by the embodiment of the present application. The protection film is usually a transparent film covering the explosion-proof valve area, such as Fig.10 As shown, the edge of the protective film 101 is a black ring, and the area covered by the protective film 101 is the explosion-proof valve. The center point 102 is the center point of the pole 113, and the center point 103 is the center point of the explosion-proof valve 112. Point 104 is the reference point.

[0274] For example, see Fig.11 , is a schematic diagram of a protective film defect detection process provided by an embodiment of the present application. Fig.11As shown, the detection process may include the following steps:

[0275] 11-1, obtaining a first image and a second image of a top cover of a battery cell to be tested.

[0276] 11-2, perform plane deformation correction on the second image to obtain a horizontal second pole region and a horizontal first protective film region.

[0277] The details of steps 11-1 to 11-2 can be found in the description of S501-S502 above, which will not be repeated here.

[0278] 11-3, according to the center position of the first protective film area and the center position of the second pole area, the offset distance between the protective film and the pole is obtained.

[0279] 11-4, if the offset distance is within the preset distance range, the protective film is determined to be normal.

[0280] 11-6, if the offset distance exceeds the preset distance range, it is determined that the protective film has defects.

[0281] In the embodiment of the present application, whether the protective film is offset is determined by the offset angle between the center of the protective film and the reference point of the reference line center. This detection method can detect the offset defect of the protective film on the one hand, and on the other hand, when the pole position is offset, it can also be detected as the offset of the protective film, which effectively reduces the probability of missed detection, thereby improving the detection reliability.

[0282] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0283] Corresponding to the battery cell top cover detection method described in the above embodiment, Fig.12 : is a structural block diagram of a battery cell top cover detection device provided in an embodiment of the present application. For the sake of convenience of explanation, only the parts related to the embodiment of the present application are shown.

[0284] Reference Fig.12 , the device 12 comprises:

[0285] The acquisition unit 121 is used to acquire a first image and a second image of a top cover of a battery cell to be tested.

[0286] The recognition unit 122 is used to recognize the first image and the second image to obtain a first area to be detected in the first image and a second area to be detected corresponding to the first area to be detected in the second image.

[0287] The detection unit 123 is used to obtain the detection result of the battery cell top cover according to the first area to be detected and the second area to be detected.

[0288] Optionally, the component types of the battery cell top cover include a top patch, a pole and an explosion-proof valve, and the identification unit 122 is further used for:

[0289] Recognize the first image to obtain at least one first target area in the first image;

[0290] The first area to be inspected is confirmed according to the corresponding component type of each first target area; wherein, at least one of the first areas to be inspected includes a first top patch area, a first pole area, a first explosion-proof valve area, and position information of each of the first areas to be inspected on the top cover of the battery cell.

[0291] Optionally, the component types of the battery cell top cover include a top patch, a pole and an explosion-proof valve, and the identification unit 122 is further used for:

[0292] recognizing the second image to obtain at least one second target area;

[0293] The second area to be inspected is confirmed according to the corresponding component type of each second target area; wherein at least one of the second areas to be inspected includes a second top patch area, a second pole area, a second explosion-proof valve area, and depth information of each second area to be inspected.

[0294] Optionally, the identification unit 122 is further configured to:

[0295] Correcting each of the second target areas to obtain a corrected second target area;

[0296] The second area to be inspected is confirmed according to the component type corresponding to each of the second target areas and the corrected second target areas.

[0297] Optionally, the identification unit 122 is further configured to:

[0298] Performing plane deformation correction on the second image to obtain a corrected second image; wherein the corrected second image includes a horizontal second top patch area, a horizontal second pole area, and a horizontal second explosion-proof valve area.

[0299] Optionally, the identification unit 122 is further configured to:

[0300] When the component type corresponding to the second target area is a top patch or a pole, performing plane fitting on the second image according to a least square method to obtain a fitting result;

[0301] The depth value of each pixel in the second image is adjusted according to the fitting result to obtain a corrected second image.

[0302] Optionally, the identification unit 122 is further configured to:

[0303] In a case where the component type corresponding to the second target area is an explosion-proof valve, calculating an average value of depth values ​​of a preset area corresponding to the second explosion-proof valve area in the second image, wherein the preset area is connected to or spaced from the second explosion-proof valve area, and the spacing distance when spaced is within a preset distance range;

[0304] Determine the reference plane of the battery cell top cover according to the average value;

[0305] The depth value of each pixel in the second image is adjusted according to the reference plane of the battery cell top cover to obtain a corrected second image.

[0306] Optionally, the detection unit 123 is further configured to:

[0307] According to the first top patch area, the first pole area and / or the first explosion-proof valve area, and the horizontal second top patch area, the horizontal second pole area and / or the horizontal second explosion-proof valve area, defect detection results of the top patch, the pole and / or the explosion-proof valve are obtained.

[0308] Optionally, the detection unit 123 is further configured to:

[0309] Detecting the first top patch area to obtain a first defect position in the first top patch area;

[0310] Verifying the first defect position according to the horizontal second top patch area to obtain a defect detection result of the top patch;

[0311] Detecting the first pole region to obtain a second defect position in the first pole region;

[0312] The second defect position is verified according to the horizontal second pole area to obtain a defect detection result of the pole.

[0313] Optionally, the detection unit 123 is further configured to:

[0314] Obtaining depth information corresponding to the first defect position from the horizontal second top patch area;

[0315] Obtaining a defect detection result of the top patch according to the depth information corresponding to the first defect position;

[0316] Obtaining depth information corresponding to the second defect position from the horizontal second pole region;

[0317] A defect detection result of the pole is obtained according to the depth information corresponding to the second defect position.

[0318] Optionally, the detection unit 123 is further configured to:

[0319] Detecting the horizontal second explosion-proof valve area to obtain a third defect position of the explosion-proof valve;

[0320] According to the third defect position, a defect detection result of the explosion-proof valve is obtained.

[0321] Optionally, the detection unit 123 is further configured to:

[0322] Counting the number of the third defect positions to obtain the number of the third defect positions;

[0323] If the number of the third defect positions exceeds a preset number, detecting the third image of the explosion-proof valve to obtain the defect area of ​​the explosion-proof valve;

[0324] A defect detection result of the explosion-proof valve is obtained according to the third defect position and the defect area.

[0325] Optionally, the detection unit 123 is further configured to:

[0326] Determining reference plane information of the explosion-proof valve according to the horizontal second explosion-proof valve area;

[0327] A third defect position of the explosion-proof valve is obtained according to the reference plane information of the explosion-proof valve.

[0328] Optionally, the detection unit 123 is further configured to:

[0329] Performing statistics on the depth information in the horizontal second explosion-proof valve area to obtain statistical data on the depth information in the horizontal second explosion-proof valve area;

[0330] The reference plane of the explosion-proof valve is determined according to the statistical data of the depth information of the horizontal second explosion-proof valve area.

[0331] Optionally, the detection unit 123 is further configured to:

[0332] Performing statistics on depth information in the horizontal second explosion-proof valve region to obtain a histogram;

[0333] The statistical data of the depth information of the horizontal second explosion-proof valve area is obtained according to the histogram.

[0334] Optionally, the explosion-proof valve includes a protective film, and the second explosion-proof valve area includes a first protective film area, wherein the protective film is a film covering the explosion-proof valve; the detection unit 123 is also used to: determine the defect detection result of the protective film according to the positional relationship between the first protective film area and the second pole area in the second image.

[0335] Optionally, the detection unit 123 is further configured to:

[0336] The defect detection result of the protective film region is determined according to the positional relationship between the center position of the first protective film region and the center position of the second pole region.

[0337] Optionally, the detection unit 123 is further configured to:

[0338] Obtaining an offset distance between the protective film and the pole according to a center position of the first protective film region and a center position of the second pole region;

[0339] A defect detection result of the protective film is determined according to an offset distance between the protective film and the pole.

[0340] Optionally, the identification unit 122 is further configured to:

[0341] Acquire a trained detection model, where the detection model is used to segment at least one first target area from the first image;

[0342] Image detection is performed on the first image according to the trained detection model to obtain at least one first target area in the first image.

[0343] Optionally, the identification unit 122 is further configured to:

[0344] Acquire a sample data set, wherein the sample data set includes a region sample corresponding to the first target region;

[0345] The detection model is trained according to the sample data set to obtain the trained detection model.

[0346] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0347] in addition, Fig.12 The battery cell top cover detection device shown can be a software unit, a hardware unit, or a combination of software and hardware units built into an existing terminal device, or can be integrated into the terminal device as an independent pendant, or can exist as an independent terminal device.

[0348] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0349] Fig.13 Schematic diagram of the structure of the electronic device provided in the embodiment of the present application. Fig.13 As shown, the electronic device 13 of this embodiment includes: at least one processor 130 ( Fig.13 Only one is shown in the figure) a processor, a memory 131, and a computer program 132 stored in the memory 131 and executable on the at least one processor 130, and when the processor 130 executes the computer program 132, the steps in any of the above-mentioned battery cell top cover detection method embodiments are implemented.

[0350] The electronic device may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art will understand that Fig.13 It is only an example of the electronic device 13 and does not constitute a limitation on the electronic device 13. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, etc.

[0351] The processor 130 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0352] In some embodiments, the memory 131 may be an internal storage unit of the electronic device 13, such as a hard disk or memory of the electronic device 13. In other embodiments, the memory 131 may also be an external storage device of the electronic device 13, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 13. Further, the memory 131 may also include both an internal storage unit of the electronic device 13 and an external storage device. The memory 131 is used to store an operating system, an application program, a boot loader (Boot Loader), data, and other programs, such as the program code of the computer program, etc. The memory 131 may also be used to temporarily store data that has been output or is to be output.

[0353] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0354] An embodiment of the present application provides a computer program product. When the computer program product runs on a terminal device, the terminal device can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0355] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the device / terminal device, a recording medium, a computer memory, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), an electric carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0356] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0357] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0358] In the embodiments provided in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0359] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0360] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for detecting a battery cell top cover, characterized in that: include: Acquire a first image and a second image of a top cover of a battery cell to be tested; Identify the first image and the second image to obtain a first area to be detected in the first image and a second area to be detected corresponding to the first area to be detected in the second image; A detection result of the battery cell top cover is obtained according to the first area to be detected and the second area to be detected.

2. The battery cell top cover detection method according to claim 1, characterized in that: The component types of the battery cell top cover include a top patch, a pole and an explosion-proof valve. The first image is identified to obtain a first area to be detected in the first image, including: Recognize the first image to obtain at least one first target area in the first image; The first area to be inspected is confirmed according to the corresponding component type of each first target area; wherein, at least one of the first areas to be inspected includes a first top patch area, a first pole area, a first explosion-proof valve area, and position information of each of the first areas to be inspected on the top cover of the battery cell.

3. The battery cell top cover detection method according to claim 1 or 2, characterized in that: The component types of the battery cell top cover include a top patch, a pole and an explosion-proof valve, and the identifying the second image to obtain the second area to be detected corresponding to the first area to be detected in the second image includes: recognizing the second image to obtain at least one second target area; The second area to be inspected is confirmed according to the corresponding component type of each second target area; wherein at least one of the second areas to be inspected includes a second top patch area, a second pole area, a second explosion-proof valve area, and depth information of each second area to be inspected.

4. The battery cell top cover detection method according to claim 3, characterized in that: The step of confirming the second area to be detected according to the component type corresponding to each of the second target areas includes: Correcting each of the second target areas to obtain a corrected second target area; The second area to be inspected is confirmed according to the component type corresponding to each of the second target areas and the corrected second target areas.

5. The battery cell top cover detection method according to claim 4, characterized in that: The step of correcting each of the second target regions to obtain a corrected second target region includes: Performing plane deformation correction on the second image to obtain a corrected second image; wherein the corrected second image includes a horizontal second top patch area, a horizontal second pole area, and a horizontal second explosion-proof valve area.

6. The battery cell top cover detection method according to claim 5, characterized in that: In a case where the component type corresponding to the second target area is a top patch or a pole, performing plane deformation correction on the second image to obtain a corrected second image includes: Performing plane fitting on the second image according to the least squares method to obtain a fitting result; The depth value of each pixel in the second image is adjusted according to the fitting result to obtain a corrected second image.

7. The battery cell top cover detection method according to claim 5, characterized in that: In a case where the component type corresponding to the second target area is an explosion-proof valve, performing plane deformation correction on the second image to obtain a corrected second image includes: Calculating an average value of depth values ​​of a preset area corresponding to the second explosion-proof valve area in the second image, wherein the preset area is connected to or spaced from the second explosion-proof valve area, and the spacing distance when spaced is within a preset distance range; Determine the reference plane of the battery cell top cover according to the average value; The depth value of each pixel in the second image is adjusted according to the reference plane of the battery cell top cover to obtain a corrected second image.

8. The battery cell top cover detection method according to claim 5, characterized in that: The step of obtaining the detection result of the battery cell top cover according to the first area to be detected and the second area to be detected includes: According to the first top patch area, the first pole area and / or the first explosion-proof valve area, and the horizontal second top patch area, the horizontal second pole area and / or the horizontal second explosion-proof valve area, defect detection results of the top patch, the pole and / or the explosion-proof valve are obtained.

9. The battery cell top cover detection method according to claim 8, characterized in that: The step of obtaining a defect detection result of the top patch according to the first top patch area and the horizontal second top patch area comprises: Detecting the first top patch area to obtain a first defect position in the first top patch area; Verifying the first defect position according to the horizontal second top patch area to obtain a defect detection result of the top patch; The step of obtaining a defect detection result of the pole according to the first pole region and the horizontal second pole region comprises: Detecting the first pole region to obtain a second defect position in the first pole region; The second defect position is verified according to the horizontal second pole area to obtain a defect detection result of the pole.

10. The battery cell top cover detection method according to claim 9, characterized in that: The verifying the first defect position according to the horizontal second top patch area to obtain the defect detection result of the top patch includes: Obtaining depth information corresponding to the first defect position from the horizontal second top patch area; Obtaining a defect detection result of the top patch according to the depth information corresponding to the first defect position; The verifying the second defect position according to the horizontal second pole area to obtain the pole defect detection result includes: Obtaining depth information corresponding to the second defect position from the horizontal second pole region; A defect detection result of the pole is obtained according to the depth information corresponding to the second defect position.

11. The battery cell top cover detection method according to claim 8, characterized in that: The step of obtaining a defect detection result of the explosion-proof valve according to the first explosion-proof valve area and the horizontal second explosion-proof valve area comprises: Detecting the horizontal second explosion-proof valve area to obtain a third defect position of the explosion-proof valve; According to the third defect position, a defect detection result of the explosion-proof valve is obtained.

12. The battery cell top cover detection method according to claim 11, characterized in that: The step of obtaining a defect detection result of the explosion-proof valve according to the third defect position includes: Counting the number of the third defect positions to obtain the number of the third defect positions; If the number of the third defect positions exceeds a preset number, detecting the third image of the explosion-proof valve to obtain the defect area of ​​the explosion-proof valve; A defect detection result of the explosion-proof valve is obtained according to the third defect position and the defect area.

13. The battery cell top cover detection method according to claim 11, characterized in that: The detecting a third defect position of the explosion-proof valve according to the horizontal second explosion-proof valve area comprises: Determining reference plane information of the explosion-proof valve according to the horizontal second explosion-proof valve area; A third defect position of the explosion-proof valve is obtained according to the reference plane information of the explosion-proof valve.

14. The battery cell top cover detection method according to claim 13, characterized in that: The step of determining the reference plane information of the explosion-proof valve according to the horizontal second explosion-proof valve area comprises: Performing statistics on the depth information in the horizontal second explosion-proof valve area to obtain statistical data on the depth information in the horizontal second explosion-proof valve area; The reference plane of the explosion-proof valve is determined according to the statistical data of the depth information of the horizontal second explosion-proof valve area.

15. The battery cell top cover detection method according to claim 14, characterized in that: The step of collecting statistics on the depth information in the horizontal second explosion-proof valve region to obtain statistical data on the depth information in the horizontal second explosion-proof valve region includes: Performing statistics on depth information in the horizontal second explosion-proof valve region to obtain a histogram; The statistical data of the depth information of the horizontal second explosion-proof valve area is obtained according to the histogram.

16. The battery cell top cover detection method according to claim 3, characterized in that: The explosion-proof valve includes a protective film, and the second explosion-proof valve area includes a first protective film area, wherein the protective film is a film covering the explosion-proof valve; The method further comprises: The defect detection result of the protective film is determined according to the positional relationship between the first protective film region and the second pole region in the second image.

17. The battery cell top cover detection method according to claim 16, characterized in that: The step of determining the defect detection result of the protective film according to the positional relationship between the first protective film region and the second pole region in the second image includes: The defect detection result of the protective film region is determined according to the positional relationship between the center position of the first protective film region and the center position of the second pole region.

18. The battery cell top cover detection method according to claim 17, characterized in that: The step of determining the defect detection result of the protective film region according to the positional relationship between the center position of the first protective film region and the center position of the second pole region comprises: Obtaining an offset distance between the protective film and the pole according to a center position of the first protective film region and a center position of the second pole region; A defect detection result of the protective film is determined according to an offset distance between the protective film and the pole.

19. The battery cell top cover detection method according to any one of claims 2 to 18, characterized in that: The identifying the first image to obtain at least one first target area in the first image includes: Acquire a trained detection model, where the detection model is used to segment at least one first target area from the first image; Image detection is performed on the first image according to the trained detection model to obtain at least one first target area in the first image.

20. The battery cell top cover detection method according to claim 19, characterized in that: The method further comprises: Acquire a sample data set, wherein the sample data set includes a region sample corresponding to the first target region; The detection model is trained according to the sample data set to obtain the trained detection model.

21. A method for detecting a battery cell top cover, characterized in that: The method comprises: Acquire a fourth image of the top cover of the battery cell to be tested; Recognize the fourth image to obtain a third area to be detected in the fourth image; According to the third area to be inspected, a detection result of the battery cell top cover is obtained.

22. The battery cell top cover detection method according to claim 21, characterized in that: The component types of the battery cell top cover include poles and protective films, and the protective film is a film of an explosion-proof valve covered on the battery cell top cover; The step of identifying the fourth image to obtain a third area to be detected in the fourth image includes: recognizing the fourth image to obtain at least one third target area in the fourth image; The third area to be detected is confirmed according to the component type corresponding to each of the third target areas; wherein at least one of the third areas to be detected includes a third pole area, a second protective film area, and depth information of each of the third areas to be detected on the top cover of the battery cell.

23. The battery cell top cover detection method according to claim 22, characterized in that: The step of confirming the third area to be detected according to the component type corresponding to each of the third target areas includes: Correcting each of the third target areas to obtain the corrected third target areas; The third area to be inspected is confirmed according to the component type corresponding to each of the third target areas and the corrected third target area.

24. The battery cell top cover detection method according to claim 23, characterized in that: The step of correcting each of the third target regions to obtain the corrected third target regions includes: Performing plane deformation correction on the fourth image to obtain a corrected fourth image; wherein the corrected fourth image includes a horizontal third pole region and a horizontal second protective film region.

25. The battery cell top cover detection method according to claim 24, characterized in that: The step of obtaining the detection result of the battery cell top cover according to the third area to be detected includes: A defect detection result of the protective film is obtained according to the horizontal third pole region and the horizontal second protective film region.

26. The battery cell top cover detection method according to claim 25, characterized in that: The step of obtaining a defect detection result of the protective film according to the horizontal third pole region and the horizontal second protective film region comprises: The defect detection result of the protective film is determined according to the positional relationship between the horizontal third pole region and the horizontal second protective film region.

27. The battery cell top cover detection method according to claim 26, characterized in that: The step of determining the defect detection result of the protective film according to the positional relationship between the horizontal third pole region and the horizontal third protective film region comprises: The defect detection result of the protective film region is determined according to the positional relationship between the center position of the horizontal second protective film region and the center position of the horizontal third pole region.

28. The battery cell top cover detection method according to claim 27, characterized in that: The step of determining the defect detection result of the protective film region according to the positional relationship between the center position of the horizontal second protective film region and the center position of the horizontal third pole region comprises: Obtaining an offset distance between the protective film and the pole according to the center position of the horizontal second protective film area and the center position of the horizontal third pole area; A defect detection result of the protective film is determined according to an offset distance between the protective film and the pole.

29. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, it implements the battery cell top cover detection method as described in any one of claims 1 to 20, or implements the battery cell top cover detection method as described in any one of claims 21 to 28.

30. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, it implements the battery cell top cover detection method as described in any one of claims 1 to 20, or implements the battery cell top cover detection method as described in any one of claims 21 to 28.

31. A detection system, characterized in that: It includes a carrying device, an imaging device and an electronic device; The carrying device is used to carry the battery cell to be tested; The imaging device is used to photograph the cell top cover of the cell to be tested on the carrying device; The electronic device is used to perform defect detection on the cell top cover of the cell to be tested according to the image taken by the imaging device.

32. The detection system according to any one of claims 31, characterized in that: The imaging device comprises a first camera, which is used to obtain a first image, a second image or a fourth image of the top cover of the battery cell.

33. The detection system according to claim 31 or 32, characterized in that: The imaging device includes a second camera for acquiring a third image of the battery cell top cover.