Battery defect detection method and device and computer readable storage medium

Abstract

The invention provides a battery defect detection method and device and a computer readable storage medium, relates to the technical field of batteries, and can improve the defect detection efficiency of a battery cell. The method comprises the following steps: acquiring an original image of each of a plurality of surfaces of a coated battery cell; for each original image in the plurality of images, executing preset processing on the original image to obtain a binary image; and determining the defects of the battery cell according to the binary image and a preset model.

Description

Technical Field

[0001] The present application relates to the field of battery technology, and in particular to a battery defect detection method, device and computer-readable storage medium. Background Art

[0002] After the battery cell is coated, it is usually necessary to identify defects on its surface and detect defective battery cells.

[0003] The existing solution is usually to use manual visual inspection, where the person manually observes whether there are defects on the surface of the battery cell, and the efficiency of defect detection is low. Summary of the invention

[0004] The present application provides a battery defect detection method, device and computer-readable storage medium, which can improve the efficiency of defect detection on battery cells.

[0005] In order to achieve the above objectives, this application adopts the following technical solutions:

[0006] In a first aspect, a battery defect detection method is provided, the method comprising: acquiring an original image of each of multiple surfaces of a coated battery cell; for each original image in the multiple images, performing preset processing on the original image to obtain a binary image; and determining the defects of the battery cell based on the binary image and a preset model.

[0007] Based on this solution, compared with the existing solution of manually observing whether there are defects on the surface of the battery cell through manual visual inspection, the solution of the present application obtains the original image of each of the multiple surfaces of the battery cell after coating; for each original image in the multiple images, performs preset processing on the original image to obtain a binary image; determines the defects of the battery cell based on the binary image and the preset model. Since the defects of the battery cell can be shown in the image of the surface of the battery cell, after obtaining the original image, the defects of the battery cell can be determined based on the original image without manual visual inspection, thereby improving the efficiency of defect detection.

[0008] In combination with the first aspect, in certain embodiments of the first aspect, an original image of each of the multiple surfaces of the coated battery cell is obtained, including: for a target surface among the multiple surfaces, target information of the target surface is obtained; the target surface is any one of the multiple surfaces, and the target information includes target position information of the target surface, a minimum detection size of defects corresponding to the target surface, and a target defect type of defects corresponding to the target surface; a target camera type, a target single pixel accuracy, and a target light source type are determined according to the target information; an original image of the target surface is captured by the target camera and the light source corresponding to the target light source type; the camera type of the target camera is the target camera type, and the single pixel accuracy of the target camera is the target single pixel accuracy.

[0009] Based on this scheme, by targeting a target surface among multiple surfaces, target information of the target surface is acquired; the target surface is any one of the multiple surfaces, and the target information includes target position information of the target surface, a minimum detection size of defects corresponding to the target surface, and a target defect type of defects corresponding to the target surface; thereafter, a target camera type, a target single pixel accuracy, and a target light source type are determined according to the target information; thereafter, an original image of the target surface is captured by the target camera and a light source corresponding to the target light source type; the camera type of the target camera is the target camera type, and the single pixel accuracy of the target camera is the target single pixel accuracy, thereby realizing a scheme for acquiring the original image of each of the multiple surfaces of the coated battery cell.

[0010] In combination with the first aspect, in certain embodiments of the first aspect, determining a target camera type, a target single pixel accuracy, and a target light source type according to target information includes: determining a target camera type according to a first mapping relationship and target position information of a target surface; the first mapping relationship includes a one-to-one correspondence between multiple position information and multiple camera types, the position information includes first position information or second position information, the first position information includes a large surface or a side surface, the second position information includes a top cover surface, and the camera type includes an area array camera or a line scan camera; determining a target single pixel accuracy according to a minimum detection size of a defect corresponding to the target surface; determining a target light source type according to a second mapping relationship and a target defect type of a defect corresponding to the target surface; the second mapping relationship includes a one-to-one correspondence between multiple defect types and multiple light source types, and the defect type includes a first Defect type, second defect type, third defect type, fourth defect type or fifth defect type, the first defect type includes envelope damage, foreign matter in the membrane, envelope bubble or envelope pit, the second defect type includes envelope edge damage, the third defect type includes patch displacement, patch lift, pole scratch or pole rubber ring damage, the fourth defect type includes explosion-proof valve damage, the fifth defect type includes pole side defects, the light source type includes the first light source type, the second light source type, the third light source type, the fourth light source type and the fifth light source type, the first light source type includes XY direction high-speed switching light source, the second light source type includes the default light source, the third light source type includes a white spherical light source and a coaxial light source, the fourth light source type includes a prism light source, the fifth light source type includes a coaxial light source and a white surface light source, or the fifth light source type includes a coaxial light source and a three-color light source.

[0011] Based on this scheme, the target camera type is determined according to a first mapping relationship including a one-to-one correspondence between multiple position information and multiple camera types and the target position information of the target surface, and then the target single-pixel accuracy is determined according to the minimum detection size of the defect corresponding to the target surface. Thereafter, the target light source type is determined according to a second mapping relationship including a one-to-one correspondence between multiple defect types and multiple light source types and the target defect type of the defect corresponding to the target surface. The target camera type, target single-pixel accuracy and target light source type can be determined according to the target information.

[0012] In combination with the first aspect, in certain embodiments of the first aspect, determining the target single pixel accuracy according to the minimum detection size of the defect corresponding to the target surface includes: determining that the minimum detection size and the target single pixel accuracy satisfy the following relationship:

[0013] X≥Y*K

[0014] Where X represents the minimum detection size, Y represents the target single pixel accuracy, and K represents the preset defect recognition coefficient.

[0015] In combination with the first aspect, in certain embodiments of the first aspect, preset processing is performed on the original image to obtain a binary image, including: increasing the brightness and contrast of the original image to obtain a first image; grayscale processing and edge enhancement processing are performed on the first image to obtain a second image; and binarization processing is performed on the second image to obtain a binary image.

[0016] Based on this scheme, by graying the first image, the data volume of the image can be reduced and the image can better reflect the brightness information. By edge enhancement processing the first image, the edge information in the first image can be enhanced to highlight the defect information. The second image is converted into a binary image, which can facilitate the identification and segmentation of specific defect areas in the image, thereby improving the efficiency of defect detection.

[0017] In combination with the first aspect, in certain embodiments of the first aspect, the defects of the battery cell are determined based on the binary image and the preset model, including: extracting feature information of suspected defects in the binary image based on a preset feature algorithm; inputting the feature information of the suspected defects into the preset model to obtain the real defects in the suspected defects.

[0018] Based on this solution, feature information of suspected defects in binary images is extracted based on a preset feature algorithm, and then the feature information of suspected defects is input into a preset model to obtain the real defects in the suspected defects, thereby realizing a solution for determining defects of battery cells based on binary images and preset models.

[0019] In combination with the first aspect, in certain embodiments of the first aspect, the method also includes: obtaining defect information of the real defect; the defect information includes the size and angle of the real defect; in the case where a target real defect exists in the real defect, generating target information; the defect information of the target real defect meets preset conditions, and the target information includes unqualified indication information of the battery cell, the number of target real defects and the defect information of the target real defect.

[0020] Based on this solution, by acquiring the defect information of the real defects and generating target information when the target real defects exist in the real defects, it is possible to determine whether the battery cell is qualified.

[0021] In a second aspect, a battery defect detection device is provided for implementing the battery defect detection method of the first aspect. The battery defect detection device includes a module, unit, or means corresponding to the above method, and the module, unit, or means can be implemented by hardware, software, or by hardware executing corresponding software. The hardware or software includes one or more modules or units corresponding to the above functions.

[0022] In combination with the second aspect, in certain embodiments of the second aspect, the device includes: an acquisition module and a processing module; the acquisition module is used to acquire an original image of each of the multiple surfaces of the battery cell after coating; the processing module is used to perform preset processing on the original image in each of the multiple images to obtain a binary image; the processing module is also used to determine the defects of the battery cell based on the binary image and the preset model.

[0023] In combination with the second aspect, in certain embodiments of the second aspect, an acquisition module is used to acquire the original image of each of the multiple surfaces of the coated battery cell, including: for a target surface among the multiple surfaces, acquiring target information of the target surface; the target surface is any one of the multiple surfaces, and the target information includes target position information of the target surface, a minimum detection size of defects corresponding to the target surface, and a target defect type of defects corresponding to the target surface; determining a target camera type, a target single pixel accuracy, and a target light source type based on the target information; capturing the original image of the target surface by using the target camera and the light source corresponding to the target light source type; the camera type of the target camera is the target camera type, and the single pixel accuracy of the target camera is the target single pixel accuracy.

[0024] In combination with the second aspect, in certain embodiments of the second aspect, an acquisition module is used to determine a target camera type, a target single pixel accuracy, and a target light source type according to target information, including: determining the target camera type according to a first mapping relationship and target position information of a target surface; the first mapping relationship includes a one-to-one correspondence between multiple position information and multiple camera types, the position information includes first position information or second position information, the first position information includes a large surface or a side surface, the second position information includes a top cover surface, and the camera type includes an area array camera or a line scan camera; determining the target single pixel accuracy according to a minimum detection size of a defect corresponding to the target surface; determining the target light source type according to a second mapping relationship and a target defect type of a defect corresponding to the target surface; the second mapping relationship includes a one-to-one correspondence between multiple defect types and multiple light source types, and the type of the defect Including the first defect type, the second defect type, the third defect type, the fourth defect type or the fifth defect type, the first defect type includes envelope damage, foreign matter in the membrane, envelope bubbles or envelope pits, the second defect type includes envelope edge damage, the third defect type includes patch displacement, patch lift, pole scratches or pole rubber ring damage, the fourth defect type includes explosion-proof valve damage, the fifth defect type includes pole side defects, the light source type includes the first light source type, the second light source type, the third light source type, the fourth light source type and the fifth light source type, the first light source type includes XY direction high-speed switching light source, the second light source type includes the default light source, the third light source type includes a white spherical light source and a coaxial light source, the fourth light source type includes a prism light source, the fifth light source type includes a coaxial light source and a white surface light source, or the fifth light source type includes a coaxial light source and a three-color light source.

[0025] In conjunction with the second aspect, in certain embodiments of the second aspect, the acquisition module is used to determine the target single pixel accuracy according to the minimum detection size of the defect corresponding to the target surface, including: determining that the minimum detection size and the target single pixel accuracy satisfy the following relationship:

[0026] X≥Y*K

[0027] Where X represents the minimum detection size, Y represents the target single pixel accuracy, and K represents the preset defect recognition coefficient.

[0028] In combination with the second aspect, in certain embodiments of the second aspect, the processing module is used to perform preset processing on the original image to obtain a binary image, including: increasing the brightness and contrast of the original image to obtain a first image; performing grayscale processing and edge enhancement processing on the first image to obtain a second image; and performing binarization processing on the second image to obtain a binary image.

[0029] In combination with the second aspect, in certain embodiments of the second aspect, a processing module is used to determine defects of a battery cell based on a binary image and a preset model, including: extracting feature information of suspected defects in the binary image based on a preset feature algorithm; inputting the feature information of the suspected defects into the preset model to obtain the real defects in the suspected defects.

[0030] In combination with the second aspect, in certain embodiments of the second aspect, the processing module is also used to: obtain defect information of the real defect; the defect information includes the size and angle of the real defect; when there is a target real defect in the real defect, generate target information; the defect information of the target real defect meets preset conditions, and the target information includes unqualified indication information of the battery cell, the number of target real defects and the defect information of the target real defect.

[0031] In a third aspect, a battery defect detection device is provided, comprising: at least one processor and a memory for storing instructions executable by the processor; wherein the processor is configured to execute instructions to implement the method provided in the first aspect and any possible implementation manner thereof.

[0032] In a fourth aspect, a computer-readable storage medium is provided. When the instructions in the computer-readable storage medium are executed by a processor of a battery defect detection device, the battery defect detection device is enabled to perform the method provided in the first aspect and any possible implementation manner thereof.

[0033] In a fifth aspect, a computer program product comprising instructions is provided, which, when executed on a computer, enables the computer to execute the method provided in the first aspect and any possible implementation manner thereof.

[0034] Among them, the technical effects brought about by any implementation of the second to fifth aspects can refer to the technical effects brought about by different implementations of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 A schematic diagram of the architecture of a battery defect detection system provided in this application;

[0036] Figure 2 A schematic diagram of the structure of a battery cell provided in this application;

[0037] Figure 3 A schematic diagram of a battery defect detection method provided in this application;

[0038] Figure 4 A flowchart of another battery defect detection method provided in this application;

[0039] Figure 5A flowchart of another battery defect detection method provided in this application;

[0040] Figure 6 A flowchart of another battery defect detection method provided in this application;

[0041] Figure 7 A flowchart of another battery defect detection method provided in this application;

[0042] Figure 8 A flowchart of another battery defect detection method provided in this application;

[0043] Fig. 9 A schematic diagram of the structure of a battery defect detection device provided in this application;

[0044] Fig.10 A schematic diagram of the structure of another battery defect detection device provided in the present application. DETAILED DESCRIPTION

[0045] In the description of this application, unless otherwise specified, "plurality" means two or more than two. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0046] In addition, in order to clearly describe the technical solutions of the embodiments of the present application, in the embodiments of the present application, words such as "first" and "second" are used to distinguish the same items or similar items with substantially the same functions and effects. Those skilled in the art can understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit the difference.

[0047] Meanwhile, in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete manner for ease of understanding.

[0048] It is understood that the "embodiment" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, the various embodiments in the entire specification do not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It is understood that in various embodiments of the present application, the size of the sequence number of each process does not mean the order of execution, and 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 embodiment of the present application.

[0049] It can be understood that in the present application, "when", "if" and "if" all mean that corresponding processing will be carried out under certain objective circumstances, but do not limit the time, nor do they require judgment actions when implementing them, nor do they mean the existence of other limitations.

[0050] It can be understood that some optional features in the embodiments of the present application may be implemented independently in certain scenarios without relying on other features, such as the solution on which they are currently based, to solve corresponding technical problems and achieve corresponding effects, or may be combined with other features according to needs in certain scenarios. Accordingly, the devices provided in the embodiments of the present application may also realize these features or functions accordingly, which will not be elaborated here.

[0051] In this application, unless otherwise specified, the same or similar parts between the various embodiments can refer to each other. In the various embodiments in this application, and the various implementation methods in each embodiment, if there is no special description and logical conflict, the terms and / or descriptions between different embodiments and the various implementation methods in each embodiment are consistent and can be referenced to each other. The technical features in different embodiments and the various implementation methods in each embodiment can be combined to form new embodiments, implementation methods, implementation methods, or implementation methods according to their inherent logical relationships. The following implementation methods of this application do not constitute a limitation on the scope of protection of this application.

[0052] Figure 1 This is a schematic diagram of the architecture of a battery defect detection system provided in this application. The technical solution of the embodiment of this application can be applied to Figure 1 The battery defect detection system shown in FIG. Figure 1 As shown, the battery defect detection system 10 includes a battery defect detection device 11, an image acquisition device 12 and a coating machine 13.

[0053] Among them, the battery defect detection device 11 is used to execute the battery defect detection method provided in this application.

[0054] The image acquisition device 12 and the battery defect detection device 11 may be connected via a wired connection or a wireless connection, and this application does not impose any specific restrictions on this.

[0055] The image acquisition device 12 is provided with at least one type of camera and at least one type of light source. The number of cameras can be 1 or plural, and the number of light sources can be 1 or plural. The present application does not impose any specific restrictions on this.

[0056] The image acquisition device 12 can acquire images of various surfaces of the coated battery cells and transmit them to the battery defect detection device 11 .

[0057] The coating machine 13 is used to coat the battery cells.

[0058] The number of the film coating machine 13 can be 1 (eg Figure 1 As shown), alternatively, the number of the coating machines 13 may be two.

[0059] When there is one coating machine 12 , one image acquisition device 12 acquires images of the battery cells in one coating machine 12 . This layout can be called a dual-channel layout.

[0060] When there are two coating machines 12 , one image acquisition device 12 acquires images of cells in two coating machines 12 . This layout can be called a single-channel layout.

[0061] Figure 2 A schematic diagram of the structure of a battery cell provided in this application, such as Figure 2 As shown, the surface of the battery cell can be divided into 2 large surfaces, 2 side surfaces and 2 top cover surfaces.

[0062] Among them, the two large surfaces are large surface A and large surface B, the two side surfaces are side surface C and side surface D, and the two top cover surfaces are top cover surface E and top cover surface F.

[0063] The two large surfaces and the two side surfaces are wrapped with a film, the top cover surface A is provided with a positive electrode column and an explosion-proof valve, and the top cover surface B is provided with a negative electrode column.

[0064] In some embodiments, the large surface and the side surfaces may also be collectively referred to as large surfaces, that is, the surface of the battery cell may be divided into four large surfaces and two top cover surfaces.

[0065] In practical applications, the battery defect detection method provided in the embodiment of the present application can be applied to the battery defect detection device 11, and can also be applied to the device included in the battery defect detection device 11.

[0066] The battery defect detection method provided in the embodiment of the present application is described below with reference to the accompanying drawings, taking the battery defect detection method applied to the battery defect detection device 11 as an example.

[0067] Figure 3 A flow chart of a battery defect detection method provided in this application, such as Figure 3 As shown, the battery defect detection method provided by the present application includes the following steps:

[0068] S301. A battery defect detection device obtains an original image of each of multiple surfaces of a coated battery cell.

[0069] It should be noted that the number of original images for each surface may be one, or the number of original images for each surface may be multiple, and this application does not impose any specific limitation on this.

[0070] In some embodiments, if the types of defects corresponding to the surface are different, different types of light sources are used to capture the original image of the surface, and thus the number of original images of the surface is the same as the number of types of defects corresponding to the surface.

[0071] Exemplarily, if the number of types of defects corresponding to the surface is 2, then the number of original images of the surface is 2.

[0072] As a possible implementation, combining Figure 1 The battery defect detection device sends a capture instruction for acquiring an original image of each of the multiple surfaces of the coated battery cell to the image capture device. Correspondingly, the image capture device receives the capture instruction of the battery defect detection device.

[0073] The image acquisition device responds to the acquisition instruction, acquires the original image of each of the multiple surfaces of the coated battery cell, and sends the response information including the original image of each of the multiple surfaces of the coated battery cell to the battery defect detection device. Correspondingly, the battery defect detection device receives the response information of the image acquisition device.

[0074] As another possible implementation method, the battery defect detection device obtains target information of a target surface among multiple surfaces; the target surface is any one of the multiple surfaces, and the target information includes target position information of the target surface, a minimum detection size of defects corresponding to the target surface, and a target defect type of defects corresponding to the target surface; the target camera type, target single pixel accuracy, and target light source type are determined according to the target information; the original image of the target surface is captured by the target camera and the light source corresponding to the target light source type; the camera type of the target camera is the target camera type, and the single pixel accuracy of the target camera is the target single pixel accuracy.

[0075] It should be noted that the specific description of this possible implementation method can refer to the relevant description in the subsequent part of the specific implementation method of this application, and this application will not explain it here.

[0076] S302: The battery defect detection apparatus performs preset processing on each original image among the multiple images to obtain a binary image.

[0077] As a possible implementation method, the battery defect detection device increases the brightness and contrast of the original image to obtain a first image; performs grayscale processing and edge enhancement processing on the first image to obtain a second image; and performs binarization processing on the second image to obtain a binary image.

[0078] It should be noted that the specific description of this possible implementation method can refer to the relevant description in the subsequent part of the specific implementation method of this application, and this application will not explain it here.

[0079] S303: The battery defect detection device determines the defects of the battery cell according to the binary image and the preset model.

[0080] It should be noted that the preset model may be an artificial intelligence (AI) model.

[0081] As a possible implementation method, the battery defect detection device extracts feature information of suspected defects in the second image based on a preset feature algorithm; inputs the feature information of the suspected defects into a preset model to obtain the real defects in the suspected defects.

[0082] It should be noted that the specific description of this possible implementation method can refer to the relevant description in the subsequent part of the specific implementation method of this application, and this application will not explain it here.

[0083] Based on this solution, compared with the existing solution of manually observing whether there are defects on the surface of the battery cell through manual visual inspection, the solution of the present application obtains the original image of each of the multiple surfaces of the battery cell after coating; for each original image in the multiple images, performs preset processing on the original image to obtain a binary image; determines the defects of the battery cell based on the binary image and the preset model. Since the defects of the battery cell can be shown in the image of the surface of the battery cell, after obtaining the original image, the defects of the battery cell can be determined based on the original image without manual visual inspection, thereby improving the efficiency of defect detection.

[0084] The above is a general description of the battery defect detection method provided in the present application. The battery defect detection method provided in the present application will be further described below in conjunction with the accompanying drawings.

[0085] In one design, Figure 4A flowchart of another battery defect detection method provided in this application is shown as follows: Figure 4 As shown, S301 provided in the specific implementation manner of the present application may specifically include the following multiple steps:

[0086] S401. A battery defect detection apparatus obtains target information of a target surface among multiple surfaces.

[0087] The target surface is any one of the multiple surfaces, and the target information includes target position information of the target surface, a minimum detection size of a defect corresponding to the target surface, and a target defect type of the defect corresponding to the target surface.

[0088] It should be noted that the target position information includes the large surface, side surface or top cover surface.

[0089] Each defect corresponds to a detection size. For example, if the defect is a damaged film, and the detection size corresponding to the damaged film is 1mm, then if the damaged film of the cell is larger than 1mm, it is considered that the cell has damaged film, and if the damaged film of the cell is smaller than 1mm, it is considered that the cell has no damaged film.

[0090] The minimum detection size of the defect corresponding to the target surface is the smallest detection size among at least one detection size corresponding to the target surface.

[0091] As a possible implementation manner, the battery defect detection apparatus receives information from its own input device, where the information includes target information of the target surface.

[0092] S402. The battery defect detection apparatus determines a target camera type, a target single pixel accuracy, and a target light source type according to target information.

[0093] As a possible implementation method, the battery defect detection device determines the target camera type according to the first mapping relationship and the target position information of the target surface; the first mapping relationship includes a one-to-one correspondence between multiple position information and multiple camera types, the position information includes the first position information or the second position information, the first position information includes the large surface or the side surface, the second position information includes the top cover surface, and the camera type includes an area array camera or a line scan camera; the target single pixel accuracy is determined according to the minimum detection size of the defect corresponding to the target surface; the target light source type is determined according to the second mapping relationship and the target defect type of the defect corresponding to the target surface; the first mapping relationship includes a one-to-one correspondence between multiple defect types and multiple light source types, and the defect type includes a first defect type, a second defect type, and a third defect type. type, the fourth defect type or the fifth defect type, the first defect type includes envelope damage, foreign matter in the membrane, envelope bubbles or envelope pits, the second defect type includes envelope edge damage, the third defect type includes patch displacement, patch lift, pole scratches or pole rubber ring damage, the fourth defect type includes explosion-proof valve damage, the fifth defect type includes pole side defects, the light source type includes the first light source type, the second light source type, the third light source type, the fourth light source type and the fifth light source type, the first light source type includes XY direction high-speed switching light source, the second light source type includes the default light source, the third light source type includes a white spherical light source and a coaxial light source, the fourth light source type includes a prism light source, the fifth light source type includes a coaxial light source and a white surface light source, or the fifth light source type includes a coaxial light source and a three-color light source.

[0094] It should be noted that the specific description of this possible implementation method can refer to the relevant description in the subsequent part of the specific implementation method of this application, and this application will not explain it here.

[0095] S403: The battery defect detection device captures an original image of the target surface through a target camera and a light source corresponding to the target light source type.

[0096] The camera type of the target camera is the target camera type, and the single pixel accuracy of the target camera is the target single pixel accuracy.

[0097] As a possible implementation manner, the battery defect detection device captures an original image of the target surface through a target camera and a light source corresponding to the target light source type.

[0098] It should be noted that the target camera and the target light source can be integrated into the image acquisition device.

[0099] In some embodiments, if defect detection is performed on the same batch of coated battery cells, the scheme of S401-S403 can be executed when the defect of the first battery cell in the batch is determined. After that, the battery defect detection device no longer needs to execute S401-S402 and can directly execute S403.

[0100] Based on this scheme, by targeting a target surface among multiple surfaces, target information of the target surface is acquired; the target surface is any one of the multiple surfaces, and the target information includes target position information of the target surface, a minimum detection size of defects corresponding to the target surface, and a target defect type of defects corresponding to the target surface; thereafter, a target camera type, a target single pixel accuracy, and a target light source type are determined according to the target information; thereafter, an original image of the target surface is captured by the target camera and a light source corresponding to the target light source type; the camera type of the target camera is the target camera type, and the single pixel accuracy of the target camera is the target single pixel accuracy, thereby realizing a scheme for acquiring the original image of each of the multiple surfaces of the coated battery cell.

[0101] In one design, Figure 5 A flowchart of another battery defect detection method provided in this application is shown as follows: Figure 5 As shown, S402 provided in the specific implementation of the present application may specifically include the following multiple steps:

[0102] S501. A battery defect detection apparatus determines a target camera type according to a first mapping relationship and target position information of a target surface.

[0103] Among them, the first mapping relationship includes a one-to-one correspondence between multiple position information and multiple camera types, the position information includes the first position information or the second position information, the first position information includes the large surface or the side surface, the second position information includes the top cover surface, and the camera type includes an area array camera or a line scan camera.

[0104] It should be noted that, in the first mapping relationship, the first position information corresponds to the line scan camera, and the second position information corresponds to the area array camera.

[0105] The area array camera or the line scan camera may be a 2D camera.

[0106] As a possible implementation manner, the battery defect detection device searches for a camera type corresponding to the target position information in the first mapping relationship, and determines the camera type as the target camera type.

[0107] S502. The battery defect detection apparatus determines the target single pixel accuracy according to the minimum detection size of the defect corresponding to the target surface.

[0108] As a possible implementation method, the battery defect detection device determines that the minimum detection size and the target single pixel accuracy satisfy the following relationship:

[0109] X≥Y*K

[0110] Where X represents the minimum detection size, Y represents the target single pixel accuracy, and K represents the preset defect recognition coefficient.

[0111] It should be noted that the unit of the target single camera accuracy is mm / pixel.

[0112] The preset defect recognition coefficient can be 5-10.

[0113] It should be noted that, in some embodiments, for the accuracy requirement of the area array camera, assuming that the minimum detection size is D1*D2mm, the field of view of the area array camera should be greater than D1mm*D2mm. The pixel requirement of the area array camera is length>D1 / [0.1X, 0.2X]=[5D1 / X, 10D1 / X]pixel, width>D2 / [0.1X, 0.2X]=[5D2 / X, 10D2 / X]pixel, then at least (25D1D2 / X2)*10 －4 W or above.

[0114] Considering the minimum imaging effect, the line scan camera selects a resolution of (5A / X)*10 －3 K or above, the area array camera selects the resolution (25D1D2 / X2)*10 －4 W or above.

[0115] S503: The battery defect detection apparatus determines a target light source type according to the second mapping relationship and a target defect type of a defect corresponding to the target surface.

[0116] Among them, the second mapping relationship includes a one-to-one correspondence between multiple defect types and multiple light source types, the defect type includes a first defect type, a second defect type, a third defect type, a fourth defect type or a fifth defect type, the first defect type includes capsule damage, foreign matter in the membrane, capsule bubbles or capsule pits, the second defect type includes capsule edge damage, the third defect type includes patch displacement, patch warping, pole scratches or pole rubber ring damage, the fourth defect type includes explosion-proof valve damage, the fifth defect type includes pole side defects, the light source type includes a first light source type, a second light source type, a third light source type, a fourth light source type and a fifth light source type, the first light source type includes an XY direction high-speed switching light source, the second light source type includes a default light source, the third light source type includes a white spherical light source and a coaxial light source, the fourth light source type includes a prism light source, the fifth light source type includes a coaxial light source and a white surface light source, or the fifth light source type includes a coaxial light source and a three-color light source.

[0117] It should be noted that, in the second mapping relationship, the first defect type corresponds to the first light source type, the second defect type corresponds to the second light source type, the third defect type corresponds to the third light source type, the fourth defect type corresponds to the fourth light source type, and the fifth defect type corresponds to the fifth light source type.

[0118] In some embodiments, the light source corresponding to the first light source type may be a dedicated light source for high-speed switching in the XY directions, or may be a plurality of groups of independent light sources capable of achieving illumination in the XY directions.

[0119] In some embodiments, for defects corresponding to the first defect type, a 3D camera can also be used to photograph the surface of the battery cell. In this way, since the 3D camera can recognize height information, the 3D camera can directly determine whether there are defects corresponding to the first defect type on the surface of the battery cell without the need for subsequent identification through a preset model.

[0120] In some embodiments, for defects corresponding to the second defect type, an edge imaging solution can also be used to determine whether the coating of the battery cell has defects corresponding to the second defect type. The specific description of the edge imaging solution can refer to the existing solution, and this application will not explain it again.

[0121] As a possible implementation manner, the battery defect detection device searches for the light source type corresponding to the target defect type in the second mapping relationship, and determines the light source type as the target light source type.

[0122] Based on this scheme, the target camera type is determined according to a first mapping relationship including a one-to-one correspondence between multiple position information and multiple camera types and the target position information of the target surface, and then the target single-pixel accuracy is determined according to the minimum detection size of the defect corresponding to the target surface. Thereafter, the target light source type is determined according to a second mapping relationship including a one-to-one correspondence between multiple defect types and multiple light source types and the target defect type of the defect corresponding to the target surface. The target camera type, target single-pixel accuracy and target light source type can be determined according to the target information.

[0123] In one design, Figure 6 A flowchart of another battery defect detection method provided in this application is shown as follows: Figure 6 As shown, S302 provided in the specific implementation of this application specifically includes the following multiple steps:

[0124] S601. The battery defect detection apparatus increases the brightness and contrast of an original image to obtain a first image.

[0125] As a possible implementation manner, the battery defect detection device increases the brightness and contrast of the original image through a brightness and contrast enhancement tool to obtain a first image.

[0126] This application does not impose any specific restrictions on the specific names of the brightness and contrast enhancement tools.

[0127] S602: The battery defect detection apparatus performs grayscale processing and edge enhancement processing on the first image to obtain a second image.

[0128] As a possible implementation manner, the battery defect detection device performs grayscale processing on the first image through a grayscale processing tool, and performs edge enhancement processing on the first image through an edge enhancement processing tool to obtain a second image.

[0129] This application does not impose any specific restrictions on the specific names of the grayscale processing tool and the edge enhancement processing tool.

[0130] S603: The battery defect detection apparatus performs binarization processing on the second image to obtain a binary image.

[0131] As a possible implementation manner, the battery defect detection device performs binarization processing on the second image through a binarization processing tool to obtain a binary image.

[0132] This application does not impose any specific restrictions on the specific name of the binarization processing tool.

[0133] Based on this scheme, by graying the first image, the data volume of the image can be reduced and the image can better reflect the brightness information. By edge enhancement processing the first image, the edge information in the first image can be enhanced to highlight the defect information. The second image is converted into a binary image, which can facilitate the identification and segmentation of specific defect areas in the image, thereby improving the efficiency of defect detection.

[0134] In one design, Figure 7 A flowchart of another battery defect detection method provided in this application is shown as follows: Figure 7 As shown, S303 provided in the specific implementation mode of this application specifically includes the following steps:

[0135] S701. The battery defect detection device extracts feature information of suspected defects in a binary image based on a preset feature algorithm.

[0136] It should be noted that the preset feature algorithm can be a scale-invariant feature transform (SIFT) algorithm, a speeded up robust feature (SURF) algorithm or a histogram of oriented gradients (HOG) algorithm. Of course, the preset feature algorithm can also be a feature extraction algorithm with other names, and this application does not make any specific restrictions on this.

[0137] It should be noted that the characteristic information may include the location, angle, length or area of ​​the suspected defect.

[0138] As a possible implementation method, the battery defect detection device inputs the binary image into a preset feature algorithm to obtain feature information of suspected defects in the binary image.

[0139] S702. The battery defect detection device inputs characteristic information of suspected defects into a preset model to obtain real defects from the suspected defects.

[0140] It should be noted that, since suspected defects are not necessarily real defects, the real defects can be judged based on the characteristic information of the suspected defects through the preset model to obtain the real defects in the suspected defects.

[0141] Based on this solution, feature information of suspected defects in binary images is extracted based on a preset feature algorithm, and then the feature information of suspected defects is input into a preset model to obtain the real defects in the suspected defects, thereby realizing a solution for determining defects of battery cells based on binary images and preset models.

[0142] In one design, Figure 8 A flowchart of another battery defect detection method provided in this application is shown as follows: Figure 8 As shown, after S702, the battery defect detection method provided by the present application may further include the following steps:

[0143] S801. A battery defect detection device obtains defect information of a real defect.

[0144] The defect information includes the size and angle of the actual defect.

[0145] As a possible implementation method, the battery defect detection device obtains defect information from characteristic information of real defects.

[0146] S802. When a target real defect exists among real defects, the battery defect detection apparatus generates target information.

[0147] The defect information of the target real defects meets the preset conditions, and the target information includes the unqualified indication information of the battery cell, the number of the target real defects and the defect information of the target real defects.

[0148] It should be noted that the preset conditions include that the size is greater than a preset size threshold and the angle is within a preset angle range.

[0149] As a possible implementation, for each real defect in the real defects, the battery defect detection device determines whether the defect information of the real defect meets the preset conditions. If yes, the real defect is the target real defect, and if no, the real defect is not the target real defect.

[0150] The battery defect detection device determines whether there is a target real defect among the real defects, and generates target information when the target real defect exists among the real defects.

[0151] Based on this solution, by acquiring the defect information of the real defects and generating target information when the target real defects exist in the real defects, it is possible to determine whether the battery cell is qualified.

[0152] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of a battery defect detection device executing a battery defect detection method. In order to achieve the above functions, the battery defect detection device includes a hardware structure and / or software module corresponding to each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the embodiments of the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware 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 exceed the scope of this application.

[0153] The embodiment of the present application can divide the functional modules of the battery defect detection device according to the above method example. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of software functional modules. Optionally, the division of modules in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, the "module" here may refer to a specific application-specific integrated circuit (ASIC), a circuit, a processor and memory that executes one or more software or firmware programs, an integrated logic circuit, and / or other devices that can provide the above functions.

[0154] In the case of functional module division, Fig. 9 FIG. 1 shows a schematic diagram of the structure of a battery defect detection device. Fig. 9 As shown, the battery defect detection device 90 includes an acquisition module 901 and a processing module 902 .

[0155] In some embodiments, the battery defect detection device 90 may further include a storage module ( Fig. 9 ), for storing program instructions and data.

[0156] Among them, the acquisition module 901 is used to obtain the original image of each of the multiple surfaces of the battery cell after coating; the processing module 902 is used to perform preset processing on each original image in the multiple images to obtain a binary image; the processing module 902 is also used to determine the defects of the battery cell based on the binary image and the preset model.

[0157] Optionally, an acquisition module 901 is used to acquire the original image of each of the multiple surfaces of the coated battery cell, including: acquiring target information of the target surface for a target surface among the multiple surfaces; the target surface is any one of the multiple surfaces, and the target information includes target position information of the target surface, a minimum detection size of defects corresponding to the target surface, and a target defect type of defects corresponding to the target surface; determining a target camera type, a target single-pixel accuracy, and a target light source type according to the target information; capturing the original image of the target surface by using the target camera and the light source corresponding to the target light source type; the camera type of the target camera is the target camera type, and the single-pixel accuracy of the target camera is the target single-pixel accuracy.

[0158] Optionally, an acquisition module 901 is used to determine a target camera type, a target single pixel accuracy, and a target light source type according to target information, including: determining a target camera type according to a first mapping relationship and target position information of a target surface; the first mapping relationship includes a one-to-one correspondence between multiple position information and multiple camera types, the position information includes first position information or second position information, the first position information includes a large surface or a side surface, the second position information includes a top cover surface, and the camera type includes an area array camera or a line scan camera; determining a target single pixel accuracy according to a minimum detection size of a defect corresponding to the target surface; determining a target light source type according to a second mapping relationship and a target defect type of a defect corresponding to the target surface; the second mapping relationship includes a one-to-one correspondence between multiple defect types and multiple light source types, and the defect type includes a first defect type type, the second defect type, the third defect type, the fourth defect type or the fifth defect type, the first defect type includes envelope damage, foreign matter in the membrane, envelope bubbles or envelope pits, the second defect type includes envelope edge damage, the third defect type includes patch displacement, patch lift, pole scratches or pole rubber ring damage, the fourth defect type includes explosion-proof valve damage, the fifth defect type includes pole side defects, the light source type includes the first light source type, the second light source type, the third light source type, the fourth light source type and the fifth light source type, the first light source type includes XY direction high-speed switching light source, the second light source type includes the default light source, the third light source type includes a white spherical light source and a coaxial light source, the fourth light source type includes a prism light source, the fifth light source type includes a coaxial light source and a white surface light source, or the fifth light source type includes a coaxial light source and a three-color light source.

[0159] Optionally, the acquisition module 901 is used to determine the target single pixel accuracy according to the minimum detection size of the defect corresponding to the target surface, including: determining that the minimum detection size and the target single pixel accuracy satisfy the following relationship:

[0160] X≥Y*K

[0161] Where X represents the minimum detection size, Y represents the target single pixel accuracy, and K represents the preset defect recognition coefficient.

[0162] Optionally, the processing module 902 is used to perform preset processing on the original image to obtain a binary image, including: increasing the brightness and contrast of the original image to obtain a first image; performing grayscale processing and edge enhancement processing on the first image to obtain a second image; and performing binarization processing on the second image to obtain a binary image.

[0163] Optionally, processing module 902 is used to determine the defects of the battery cell based on the binary image and the preset model, including: extracting feature information of suspected defects in the binary image based on a preset feature algorithm; inputting the feature information of the suspected defects into the preset model to obtain the real defects in the suspected defects.

[0164] Optionally, the processing module 902 is also used to: obtain defect information of the real defect; the defect information includes the size and angle of the real defect; when a target real defect exists in the real defect, generate target information; the defect information of the target real defect meets preset conditions, and the target information includes unqualified indication information of the battery cell, the number of target real defects and the defect information of the target real defect.

[0165] All relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module, and will not be repeated here.

[0166] When the functions of the above functional modules are implemented in the form of hardware, Fig.10 FIG. 2 shows a schematic diagram of the structure of another battery defect detection device. Fig.10 As shown, the battery defect detection device 100 includes a processor 1001, a memory 1002 and a bus 1003. The processor 1001 and the memory 1002 may be connected via the bus 1003.

[0167] The processor 1001 is the control center of the battery defect detection device 100, which can be a processor or a general term for multiple processing elements. For example, the processor 1001 can be a general-purpose central processing unit (CPU) or other general-purpose processors. Among them, the general-purpose processor can be a microprocessor or any conventional processor.

[0168] As an embodiment, the processor 1001 may include one or more CPUs, such as Fig.10 CPU 0 and CPU 1 are shown in .

[0169] The memory 1002 may be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, an electrically erasable programmable read-only memory (EEPROM), a disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to these.

[0170] As a possible implementation, the memory 1002 may exist independently of the processor 1001, and the memory 1002 may be connected to the processor 1001 via the bus 1003 to store instructions or program codes. When the processor 1001 calls and executes the instructions or program codes stored in the memory 1002, the battery defect detection method provided in the embodiment of the present application can be implemented.

[0171] In another possible implementation, the memory 1002 may also be integrated with the processor 1001 .

[0172] The bus 1003 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.10 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0173] It should be pointed out that Fig.10 The structure shown does not constitute a limitation on the battery defect detection device 100. Fig.10 In addition to the components shown, the battery defect detection apparatus 100 may include more or fewer components than shown, or combine certain components, or arrange the components differently.

[0174] As an example, combining Fig. 9 The functions implemented by the acquisition module 901 and the processing module 902 in the battery defect detection device 90 are similar to those Fig.10 The function of processor 1001 in is the same.

[0175] Optional, such as Fig.10 As shown, the battery defect detection device 100 provided in the embodiment of the present application may further include a communication interface 1004 .

[0176] The communication interface 1004 is used to connect with other devices through a communication network. The communication network may be Ethernet, wireless access network, wireless local area network (WLAN), etc. The communication interface 1004 may include a receiving unit for receiving data and a sending unit for sending data.

[0177] In a possible implementation, in the battery defect detection device 100 provided in the embodiment of the present application, the communication interface 1004 may also be integrated in the processor 1001, and the embodiment of the present application does not specifically limit this.

[0178] As a possible product form, the battery defect detection device of the embodiment of the present application can also be implemented using the following: one or more field programmable gate arrays (FPGA), programmable logic devices (PLD), controllers, state machines, gate logic, discrete hardware components, any other suitable circuits, or any combination of circuits capable of performing the various functions described throughout the present application.

[0179] Through the description of the above implementation methods, those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above functional units is used as an example. In practical applications, the above functions can be assigned to different functional units as needed, that is, the internal structure of the device can be divided into different functional units to complete all or part of the functions described above. The specific working process of the system, device and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0180] An embodiment of the present application also provides a computer-readable storage medium on which a computer program or instruction is stored. When the computer program or instruction is executed, the computer executes each step in the method flow shown in the above method embodiment.

[0181] An embodiment of the present application provides a computer program product including instructions. When the instructions are executed on a computer, the computer is caused to execute each step in the method flow shown in the above method embodiment.

[0182] An embodiment of the present application provides a chip system, including: a processor and an interface circuit; the interface circuit is used to receive a computer program or instruction and transmit it to the processor; the processor is used to execute the computer program or instruction so that the chip system executes each step in the method flow shown in the above method embodiment.

[0183] Among them, the computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, and a hard disk. Random Access Memory (RAM), Read-Only Memory (ROM), Erasable Programmable Read Only Memory (EPROM), registers, hard disks, optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any other form of computer-readable storage media in a suitable combination of the above, or numerical values ​​in the art. An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in a specific-purpose ASIC. In the embodiments of the present application, a computer-readable storage medium may be any tangible medium that contains or stores a program, which may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0184] Since the battery defect detection device, computer-readable storage medium, and computer program product provided in this embodiment can be applied to the battery defect detection method provided in this embodiment, the technical effects that can be obtained can also refer to the above-mentioned method embodiments, and the embodiments of this application will not be repeated here.

[0185] Although the present application is described herein in conjunction with various embodiments, in the process of implementing the claimed application, those skilled in the art may understand and implement other changes to the disclosed embodiments by viewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "one" or "an" does not exclude multiple situations. A single processor or other unit may implement several functions listed in the claims. Certain measures are recorded in different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0186] Although the present application has been described in conjunction with specific features and embodiments thereof, it is obvious that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the drawings are merely exemplary illustrations of the present application as defined by the appended claims, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art may make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A battery defect detection method, characterized in that: The method comprises: Acquire an original image of each of the multiple surfaces of the coated battery cell; For each original image among the multiple images, performing a preset process on the original image to obtain a binary image; Determine the defect of the battery cell according to the binary image and a preset model.

2. The method according to claim 1, characterized in that The step of acquiring an original image of each of the multiple surfaces of the coated battery cell comprises: For a target surface among the multiple surfaces, target information of the target surface is acquired; the target surface is any one of the multiple surfaces, and the target information includes target position information of the target surface, a minimum detection size of a defect corresponding to the target surface, and a target defect type of the defect corresponding to the target surface; Determine the target camera type, target single pixel accuracy and target light source type according to the target information; An original image of the target surface is captured by a target camera and a light source corresponding to the target light source type; the camera type of the target camera is the target camera type, and the single pixel accuracy of the target camera is the target single pixel accuracy.

3. The method according to claim 2, characterized in that The determining of the target camera type, the target single pixel accuracy and the target light source type according to the target information includes: Determine the target camera type according to a first mapping relationship and target position information of the target surface; the first mapping relationship includes a one-to-one correspondence between multiple position information and multiple camera types, the position information includes first position information or second position information, the first position information includes a large surface or a side surface, the second position information includes a top cover surface, and the camera type includes an area array camera or a line scan camera; Determining the single pixel accuracy of the target according to the minimum detection size of the defect corresponding to the target surface; The target light source type is determined according to the second mapping relationship and the target defect type of the defect corresponding to the target surface; the second mapping relationship includes a one-to-one correspondence between multiple defect types and multiple light source types, the defect type includes a first defect type, a second defect type, a third defect type, a fourth defect type or a fifth defect type, the first defect type includes capsule damage, foreign matter in the membrane, capsule bubbles or capsule pits, the second defect type includes capsule edge damage, the third defect type includes patch displacement, patch warping, pole scratches or pole rubber ring damage, the fourth defect type includes explosion-proof valve damage, the fifth defect type includes pole side defects, the light source type includes a first light source type, a second light source type, a third light source type, a fourth light source type and a fifth light source type, the first light source type includes an XY direction high-speed switching light source, the second light source type includes a default light source, the third light source type includes a white spherical light source and a coaxial light source, the fourth light source type includes a prism light source, the fifth light source type includes a coaxial light source and a white surface light source, or the fifth light source type includes a coaxial light source and a three-color light source.

4. The method according to claim 3, characterized in that The step of determining the target single pixel accuracy according to the minimum detection size of the defect corresponding to the target surface includes: Determine that the minimum detection size and the target single pixel accuracy satisfy the following relationship: X≥Y*K Wherein, X represents the minimum detection size, Y represents the target single pixel accuracy, and K represents the preset defect recognition coefficient.

5. The method according to any one of claims 1 to 4, characterized in that: The performing of a preset process on the original image to obtain a binary image comprises: Increasing the brightness and contrast of the original image to obtain a first image; Performing grayscale processing and edge enhancement processing on the first image to obtain a second image; The second image is binarized to obtain the binary image.

6. The method according to any one of claims 1 to 4, characterized in that: The determining the defect of the battery cell according to the binary image and a preset model includes: Extracting feature information of suspected defects in the binary image based on a preset feature algorithm; The characteristic information of the suspected defects is input into the preset model to obtain the real defects in the suspected defects.

7. The method according to claim 6, characterized in that The method further comprises: Acquire defect information of the real defect; the defect information includes the size and angle of the real defect; When there is a target real defect among the real defects, target information is generated; the defect information of the target real defect meets a preset condition, and the target information includes unqualified indication information of the battery cell, the number of the target real defects and the defect information of the target real defect.

8. A battery defect detection device, characterized in that: The device comprises: an acquisition module and a processing module; The acquisition module is used to acquire the original image of each surface of the multiple surfaces of the coated battery cell; The processing module is used to perform preset processing on each original image in the multiple images to obtain a binary image; The processing module is further used to determine the defects of the battery cell according to the binary image and a preset model.

9. A battery defect detection device, characterized in that: The device comprises: a processor, wherein the processor is coupled to a memory, wherein the memory is used to store programs or instructions. When the programs or instructions are executed by the processor, the device executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program or instruction is stored thereon, and when the computer program or instruction is executed, the computer is caused to perform the method according to any one of claims 1 to 7.

Images