Battery piece scratch type detection method and device based on image processing

Abstract

The invention discloses a battery piece scratch type detection method and device based on image processing, and the method comprises the steps: collecting a to-be-detected image of a to-be-detected battery piece in real time in the production process of the battery piece; detecting the to-be-detected battery piece through defect detection equipment, and determining whether the surface of the to-be-detected battery piece is scratched or not; if it is determined that the surface of the to-be-detected battery piece is scratched, gray processing is conducted on the to-be-detected image, and the gray degree value of the to-be-detected image is obtained; restoring the shape contour of the scratched mechanical clamp on the to-be-detected image according to the gray degree value, and obtaining a scratched contour image; and according to the scratch contour image and a preset scratch type standard image, determining the scratch type of the battery piece to be detected through a correlation coefficient matching method. According to the method, whether the battery piece is scratched or not and the scratch type can be judged by processing and analyzing the battery piece image, subjective errors in the manual detection process are reduced, the detection efficiency and accuracy are improved, and the labor cost is greatly reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of battery cell detection, and in particular, to a method and device for detecting battery cell scratch types based on image processing. Background Art

[0002] In the modern battery manufacturing process, due to the existence of various mechanical processes on the battery cell production line, it is inevitable that the battery cells will be damaged to varying degrees due to the clamping of mechanical fixtures, which will directly affect the performance and service life of the battery. Therefore, it is of great significance to accurately judge the cause of the scratches on the battery cells and take corresponding measures in time to improve the quality and production efficiency of the battery.

[0003] The existing technical solution mainly relies on manually observing the collected cell images and combining experience to judge the cause of cell scratches. Although this method can also judge the cause of cell scratches to a certain extent, it is very dependent on the experience and ability of the staff. The manual observation and judgment method is greatly affected by subjective factors and is prone to misjudgment. In addition, this method is inefficient and cannot meet the needs of large-scale production. It lacks unified standards and basis, and the results of judgments by different people may vary greatly.

[0004] Therefore, people in this field are in urgent need of finding a new technical solution to solve the above problems. Summary of the invention

[0005] In order to overcome the problems existing in the related art, the present invention discloses a method and device for detecting the type of scratches on a battery cell based on image processing.

[0006] According to a first aspect of the disclosed embodiments of the present invention, a method for detecting scratch types of battery cells based on image processing is provided, the method comprising:

[0007] During the production process of the battery cells, the images of the battery cells to be inspected are collected in real time;

[0008] Inspecting the battery cell to be inspected by a defect detection device to determine whether there are scratches on the surface of the battery cell to be inspected;

[0009] If it is determined that there are scratches on the surface of the battery cell to be inspected, grayscale processing is performed on the image to be inspected to obtain a grayscale value of the image to be inspected;

[0010] Restore the shape contour of the scratched mechanical fixture on the image to be detected according to the grayscale value to obtain a scratch contour image;

[0011] According to the scratch contour image and a preset scratch type standard image, the scratch type of the battery cell to be inspected is determined by a correlation coefficient matching method.

[0012] Optionally, determining the scratch type of the battery cell to be inspected by a correlation coefficient matching method according to the scratch contour image and a preset scratch type standard image includes:

[0013] The correlation coefficient ρ between the scratch contour image and the standard image of each scratch type is determined by the correlation coefficient calculation formula;

[0014] The correlation coefficient calculation formula is: in,

[0015] g(x,y) is the pixel value of the scratch type standard image, and g′(x,y) is the pixel value of the scratch contour image;

[0016] If the correlation coefficient between the scratch contour image and the scratch type standard image is greater than a preset coefficient threshold, the scratch type corresponding to the scratch type standard image is determined as the scratch type of the battery cell to be detected.

[0017] Optionally, the defect detection device is an EL tester, and the real-time acquisition of the image to be detected of the battery cell to be detected includes:

[0018] An industrial camera disposed above the battery cell is used to collect images of the battery cell at a frequency of 10 images per second;

[0019] The image with the highest definition is selected as the image to be inspected of the battery cell to be inspected.

[0020] Optionally, if it is determined that there are scratches on the surface of the battery cell to be inspected, grayscale processing is performed on the image to be inspected to obtain a grayscale value of the image to be inspected, including:

[0021] If it is determined that there are scratches on the surface of the battery cell to be inspected, grayscale processing is performed on the image to be inspected, and the grayscale value is divided into 0-100% to obtain the grayscale value of the image to be inspected.

[0022] Optionally, restoring the shape contour of the scratched mechanical fixture on the image to be detected according to the grayscale value to obtain the scratch contour image includes:

[0023] Decomposing the image to be detected according to the grayscale value, and determining the area with a grayscale value of 0% as a scratch area;

[0024] The scratched mechanical fixture shape contour is restored on the image to be detected according to the contour of the scratched area to obtain a scratch contour image.

[0025] Optionally, the method further includes:

[0026] A standard image of each type of scratch is drawn according to the contact points between the mechanical fixture and the battery cell during the battery cell production process, wherein the scratch types include: dry flower basket card point print, wet flower basket card point print, belt print, suction cup print, positioning fixture adjustment print and boat frame print.

[0027] Optionally, the method further includes:

[0028] Obtain the total number of cells produced within a preset time period and the number of cells of each scratch type;

[0029] The degree of wear of the corresponding mechanical fixture within a preset time period is determined according to the ratio of the number of battery cells of each scratch type to the total number of battery cells produced.

[0030] According to a second aspect of the disclosed embodiment of the present invention, there is provided a battery cell scratch type detection device based on image processing, the device comprising:

[0031] An image acquisition module, which acquires images of the battery cells to be inspected in real time during the production process of the battery cells;

[0032] An EL detection module is connected to the image acquisition module, and detects the battery cell to be detected by a defect detection device to determine whether there are scratches on the surface of the battery cell to be detected;

[0033] A grayscale processing module is connected to the EL detection module, and performs grayscale processing on the image to be detected to obtain a grayscale value of the image to be detected if it is determined that there are scratches on the surface of the cell to be detected;

[0034] A contour restoration module, connected to the grayscale processing module, restores the shape contour of the scratched mechanical fixture on the image to be detected according to the grayscale value, and obtains a scratch contour image;

[0035] The scratch type determination module is connected to the contour restoration module, and determines the scratch type of the battery cell to be detected by a correlation coefficient matching method according to the scratch contour image and a preset scratch type standard image.

[0036] Optionally, the scratch type determination module includes:

[0037] A correlation coefficient calculation unit, which determines the correlation coefficient ρ between the scratch contour image and the standard image of each scratch type through a correlation coefficient calculation formula;

[0038] The correlation coefficient calculation formula is: in,

[0039]

[0040] g(x,y) is the pixel value of the scratch type standard image, and g′(x,y) is the pixel value of the scratch contour image;

[0041] The scratch type determination unit is connected to the correlation coefficient calculation unit. If the correlation coefficient between the scratch contour image and the scratch type standard image is greater than a preset coefficient threshold, the scratch type corresponding to the scratch type standard image is determined as the scratch type of the battery cell to be detected.

[0042] Optionally, the contour restoration module includes:

[0043] a scratch region determining unit, which decomposes the image to be detected according to the grayscale value, and determines a region with a grayscale value of 0% as a scratch region;

[0044] The scratch contour acquisition unit is connected to the scratch area determination unit, and restores the scratched mechanical fixture shape contour on the image to be detected according to the contour of the scratch area to acquire a scratch contour image.

[0045] In summary, the present invention discloses a method and device for detecting the type of scratches on a battery cell based on image processing, the method comprising: in the production process of the battery cell, real-time acquisition of the image to be detected of the battery cell to be detected; detecting the battery cell to be detected by a defect detection device to determine whether there is a scratch on the surface of the battery cell to be detected; if it is determined that there is a scratch on the surface of the battery cell to be detected, grayscale processing is performed on the image to be detected to obtain the grayscale value of the image to be detected; the shape contour of the scratched mechanical fixture is restored on the image to be detected according to the grayscale value to obtain the scratch contour image; according to the scratch contour image and the preset scratch type standard image, the scratch type of the battery cell to be detected is determined by the correlation coefficient matching method. It is possible to determine whether the battery cell is scratched and the type of scratch by processing and analyzing the battery cell image, thereby reducing subjective errors in the manual detection process, improving detection efficiency and accuracy, and greatly reducing labor costs.

[0046] Other features and advantages disclosed in the present invention will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings:

[0048] Figure 1 is a flow chart showing a method for detecting the type of battery cell scratches based on image processing according to an exemplary embodiment;

[0049] Figure 2 is based on Figure 1 A schematic diagram of gray scale is shown;

[0050] Figure 3 is based on Figure 1 A schematic diagram showing various scratch types on the surface of a battery cell;

[0051] Figure 4 is based on Figure 1 A flow chart of a method for analyzing the scratch ratio of a battery cell is shown;

[0052] Figure 5 is a structural block diagram of a battery cell scratch type detection device based on image processing according to an exemplary embodiment;

[0053] Figure 6 is based on Figure 5 A structural block diagram of a scratch type determination module is shown;

[0054] Figure 7 is based on Figure 5 A structural block diagram of a contour restoration module is shown. DETAILED DESCRIPTION

[0055] The specific embodiments disclosed in the present invention are described in detail below in conjunction with the accompanying drawings. It should be understood that the specific embodiments described herein are only used to illustrate and explain the present disclosure, and are not used to limit the present disclosure.

[0056] Figure 1 FIG. 1 is a flow chart showing a method for detecting a type of battery cell scratch based on image processing according to an exemplary embodiment. Figure 1 As shown, the method includes:

[0057] In step 101, during the production process of the battery cell, images of the battery cell to be inspected are collected in real time.

[0058] Specifically, an industrial camera disposed above the battery cell collects images of the battery cell at a frequency of 10 images per second; and the image with the highest definition is selected as the image to be inspected of the battery cell to be inspected.

[0059] For example, in the disclosed embodiment of the present invention, an industrial camera is installed directly above the battery cell, and the battery cells on the production line are photographed continuously and at high speed by the industrial camera, and an image with the highest definition is selected from the photographed images as the image to be detected, so as to obtain the status information of the battery cell through the subsequent image analysis step. Preferably, the resolution of the image is 1920*1080.

[0060] In step 102, the battery cell to be inspected is inspected by a defect inspection device to determine whether there are scratches on the surface of the battery cell to be inspected.

[0061] Preferably, the defect detection equipment is: an EL tester.

[0062] For example, the full name of the EL tester is an electroluminescent tester, which is an internal defect detection device for solar cells or battery modules. The defect detection device is often used to detect internal defects, hidden cracks, fragments, cold solder joints, broken grids, and abnormal phenomena of single-chip cells with different conversion efficiencies in solar cell modules. It can be understood that in the disclosed embodiment of the present invention, the EL tester performs an "initial inspection" on the appearance of the battery cell to be inspected to determine whether there are defects (i.e. scratches) on the surface of the battery cell to be inspected. If the initial inspection result shows that there are no defects on the surface of the battery cell to be inspected, the processing and analysis process of the following steps 103-105 will not be performed on the image of the battery cell to be inspected, and the production and processing process of the battery cell on the production line will continue.

[0063] In step 103, if it is determined that there are scratches on the surface of the battery cell to be inspected, grayscale processing is performed on the image to be inspected to obtain a grayscale value of the image to be inspected.

[0064] For example, according to the above step 102, after the EL detector performs an "initial inspection" on the battery cell to be inspected, if the initial inspection result shows that there are defects on the surface of the battery cell, it is necessary to continue processing the image of the battery cell to be inspected to obtain the type of scratches on the battery cell to be inspected.

[0065] Specifically, if it is determined that there are scratches on the surface of the battery cell to be inspected, grayscale processing is performed on the image to be inspected, and the grayscale value is divided into 0-100% to obtain the grayscale value of the image to be inspected.

[0066] like Figure 2 As shown, the grayscale value of the image is divided into grayscale gradients of 0%, 5%, 10%, 15%, ..., 85%, 90%, 95%, and 100%. The image to be detected is gray-processed, and the grayscale value is obtained to determine within which grayscale gradient range the grayscale value is.

[0067] In step 104, the shape contour of the scratched mechanical fixture is restored on the image to be detected according to the grayscale value to obtain a scratch contour image.

[0068] For example, according to Figure 2It can be seen that the area with a grayscale value of 0% on the image to be tested has the darkest color, and the corresponding area on the battery to be tested has scratches. The specific position of the area with a grayscale value of 0% on the battery to be tested is determined (which can be represented by the horizontal and vertical coordinates in the battery coordinate system), and the division contour is determined according to the contour of the area with a grayscale value of 0%, that is, the shape contour of the mechanical fixture.

[0069] Specifically, the method restores the shape outline of the scratched mechanical fixture on the image to be detected according to the grayscale value to obtain the scratch outline image, including: disassembling the image to be detected according to the grayscale value, and determining the area with a grayscale value of 0% as the scratch area; restoring the shape outline of the scratched mechanical fixture on the image to be detected according to the outline of the scratch area to obtain the scratch outline image.

[0070] For example, after determining the grayscale value of the image to be detected, the image to be detected can be disassembled into different areas according to the grayscale value, wherein the area with a grayscale value of 0% is the scratch area, and the specific position and area size of the scratch area are determined according to the coordinate value of the scratch area, and the outline of the scratch area is drawn. It can be understood that the outline of the scratch area is the shape outline of the mechanical fixture that causes the scratch, and the image to be detected that restores the shape outline of the mechanical fixture is the scratch outline image. By comparing and analyzing the scratch outline image with the scratch type standard image, the scratch type of the battery cell to be detected can be determined.

[0071] In step 105, the scratch type of the battery cell to be inspected is determined by a correlation coefficient matching method based on the scratch contour image and a preset scratch type standard image.

[0072] Specifically, the correlation coefficient ρ between the scratch contour image and each scratch type standard image is determined by a correlation coefficient calculation formula; the correlation coefficient calculation formula is: in,

[0073] g(x,y) is the pixel value of the scratch type standard image, and g′(x,y) is the pixel value of the scratch contour image; if the correlation coefficient between the scratch contour image and the scratch type standard image is greater than the preset coefficient threshold, the scratch type corresponding to the scratch type standard image is determined as the scratch type of the battery cell to be tested.

[0074] For example, after obtaining the scratch contour image through the above steps, the correlation coefficient between the two is calculated based on the pixel values ​​of the scratch type standard image and the pixel values ​​of the scratch contour image. If the correlation coefficient is greater than the preset coefficient threshold, it means that the contour on the scratch contour image is the same as the scratch contour of the scratch type standard image, thereby determining the scratch type. If the correlation coefficient is less than or equal to the preset coefficient threshold, it means that the contour on the scratch contour image is different from the scratch contour of the scratch type standard image, then continue to compare the scratch type standard image corresponding to the next scratch type with the scratch contour image of the battery cell to be detected until the scratch type of the battery cell to be detected is determined.

[0075] Optionally, the method further includes:

[0076] A standard image of each type of scratch is drawn according to the contact points between the mechanical fixture and the battery cell during the battery cell production process, where the scratch types include: dry flower basket card point print, wet flower basket card point print, belt print, suction cup print, positioning fixture adjustment print and boat frame print.

[0077] For example, Figure 3 Schematic diagram of various scratch types on the surface of the battery cell, such as Figure 3 As shown, the standard images of scratch types represented from left to right are dry / wet basket card point prints, belt prints, suction cup prints and positioning fixture adjustment prints. Preferably, the process of drawing each of the above scratch types is: through computer-aided design software (preferably CAD), simulate and draw various possible mechanical process contact point graphics (draw according to the contact points between the real object and the battery cell, with an accuracy of 0.01mm, for example, draw the outline of the scratch image that the belt may cause on the battery cell according to the exit point between the belt and the battery cell). Store these graphics in a library with a capacity of 1GB (i.e., establish a mechanical process contact point library) to facilitate subsequent comparison and analysis.

[0078] Figure 4 is based on Figure 1 A flow chart of a method for analyzing the scratch ratio of a battery cell is shown, and optionally, the method further includes:

[0079] In step 401, the total number of battery cells produced within a preset time period and the number of battery cells of each scratch type are obtained.

[0080] In step 402, the wear degree of the corresponding mechanical fixture within a preset time period is determined according to the ratio of the number of battery cells with each scratch type to the total number of battery cells produced.

[0081] For example, the total number of cells produced in a preset time period and the number of cells with each scratch type are obtained, and statistics are performed in units of day / week / month / quarter / year. The proportion of the number of cells with each scratch type in this time period to the total number of cells produced is calculated, so as to determine the proportion of each scratch type. In addition, the wear degree of the mechanical fixture corresponding to the scratch type in the preset time period can also be determined according to the proportion of the scratch type in the total number of cells, so as to accurately maintain the machine.

[0082] The above steps can realize automatic judgment of the cause of battery cell scratches through computer programs, so as to improve the efficiency and accuracy of fault diagnosis, and also meet the needs of large-scale production. Specifically, by writing corresponding computer programs, the above steps are automatically run. The operating environment of the computer program is Windows 10, the processor is Intel Core i7, the memory is 8GB, and the hard disk is 500GB.

[0083] Figure 5 is a structural block diagram of a battery cell scratch type detection device based on image processing according to an exemplary embodiment. Figure 5 As shown, the device 500 includes:

[0084] An image acquisition module 510 is used to acquire images of the battery cells to be inspected in real time during the production process of the battery cells;

[0085] The EL detection module 520 is connected to the image acquisition module 510, and detects the battery cell to be detected by a defect detection device to determine whether there is a scratch on the surface of the battery cell to be detected;

[0086] The grayscale processing module 530 is connected to the EL detection module 520. If it is determined that there are scratches on the surface of the battery cell to be detected, grayscale processing is performed on the image to be detected to obtain the grayscale value of the image to be detected.

[0087] The contour restoration module 540 is connected to the grayscale processing module 530, and restores the shape contour of the scratched mechanical fixture on the image to be detected according to the grayscale value to obtain a scratch contour image;

[0088] The scratch type determination module 550 is connected to the contour restoration module 540, and determines the scratch type of the battery cell to be detected by a correlation coefficient matching method according to the scratch contour image and a preset scratch type standard image.

[0089] Figure 6 is based on Figure 5 A structural block diagram of a scratch type determination module is shown in FIG. Figure 6 As shown, the scratch type determination module 550 includes:

[0090] A correlation coefficient calculation unit 551 determines the correlation coefficient ρ between the scratch contour image and each scratch type standard image through a correlation coefficient calculation formula;

[0091] The correlation coefficient calculation formula is: in,

[0092] g(x,y) is the pixel value of the scratch type standard image, and g′(x,y) is the pixel value of the scratch contour image;

[0093] The scratch type determination unit 552 is connected to the correlation coefficient calculation unit 551. If the correlation coefficient between the scratch contour image and the scratch type standard image is greater than a preset coefficient threshold, the scratch type corresponding to the scratch type standard image is determined as the scratch type of the battery cell to be detected.

[0094] Figure 7 is based on Figure 5 A structural block diagram of a contour restoration module is shown in FIG. Figure 7 As shown, the contour restoration module 540 includes:

[0095] The scratch region determining unit 541 decomposes the image to be detected according to the grayscale value, and determines the region with a grayscale value of 0% as the scratch region;

[0096] The scratch contour acquisition unit 542 is connected to the scratch area determination unit 541, and restores the scratched mechanical fixture shape contour on the image to be detected according to the contour of the scratch area to acquire a scratch contour image.

[0097] In summary, the present invention discloses a method and device for detecting the type of scratches on a battery cell based on image processing, the method comprising: in the production process of the battery cell, real-time acquisition of the image to be detected of the battery cell to be detected; detecting the battery cell to be detected by a defect detection device to determine whether there is a scratch on the surface of the battery cell to be detected; if it is determined that there is a scratch on the surface of the battery cell to be detected, grayscale processing is performed on the image to be detected to obtain the grayscale value of the image to be detected; the shape contour of the scratched mechanical fixture is restored on the image to be detected according to the grayscale value to obtain the scratch contour image; according to the scratch contour image and the preset scratch type standard image, the scratch type of the battery cell to be detected is determined by the correlation coefficient matching method. It is possible to determine whether the battery cell is scratched and the type of scratch by processing and analyzing the battery cell image, thereby reducing subjective errors in the manual detection process, improving detection efficiency and accuracy, and greatly reducing labor costs.

[0098] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0099] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0100] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

Claims

1. A method for detecting cell scratch types based on image processing, characterized in that: The method comprises: During the production process of the battery cells, the images of the battery cells to be inspected are collected in real time; Inspecting the battery cell to be inspected by a defect detection device to determine whether there are scratches on the surface of the battery cell to be inspected; If it is determined that there are scratches on the surface of the battery cell to be inspected, grayscale processing is performed on the image to be inspected to obtain a grayscale value of the image to be inspected; Restore the shape contour of the scratched mechanical fixture on the image to be detected according to the grayscale value to obtain a scratch contour image; According to the scratch contour image and a preset scratch type standard image, the scratch type of the battery cell to be inspected is determined by a correlation coefficient matching method.

2. The method for detecting cell scratch types based on image processing according to claim 1, characterized in that: The method of determining the scratch type of the battery cell to be inspected by a correlation coefficient matching method according to the scratch contour image and a preset scratch type standard image includes: The correlation coefficient ρ between the scratch contour image and the standard image of each scratch type is determined by the correlation coefficient calculation formula; The correlation coefficient calculation formula is: in, g(x,y) is the pixel value of the scratch type standard image, and g′(x,y) is the pixel value of the scratch contour image; If the correlation coefficient between the scratch contour image and the scratch type standard image is greater than a preset coefficient threshold, the scratch type corresponding to the scratch type standard image is determined as the scratch type of the battery cell to be detected.

3. The method for detecting cell scratch types based on image processing according to claim 1, characterized in that: The defect detection equipment is: an EL tester, and the real-time acquisition of the image to be detected of the battery cell to be detected includes: An industrial camera disposed above the battery cell is used to collect images of the battery cell at a frequency of 10 images per second; The image with the highest definition is selected as the image to be inspected of the battery cell to be inspected.

4. The method for detecting cell scratch types based on image processing according to claim 1, characterized in that: If it is determined that there are scratches on the surface of the battery cell to be detected, grayscale processing is performed on the image to be detected to obtain a grayscale value of the image to be detected, including: If it is determined that there are scratches on the surface of the battery cell to be inspected, grayscale processing is performed on the image to be inspected, and the grayscale value is divided into 0-100% to obtain the grayscale value of the image to be inspected.

5. The method for detecting cell scratch types based on image processing according to claim 4, characterized in that: The method of restoring the shape contour of the scratched mechanical fixture on the image to be detected according to the grayscale value to obtain the scratch contour image includes: Decomposing the image to be detected according to the grayscale value, and determining the area with a grayscale value of 0% as the scratch area; The scratched mechanical fixture shape contour is restored on the image to be detected according to the contour of the scratched area to obtain a scratch contour image.

6. The method for detecting cell scratch types based on image processing according to claim 1, characterized in that: The method further comprises: A standard image of each type of scratch is drawn according to the contact points between the mechanical fixture and the battery cell during the battery cell production process, wherein the scratch types include: dry flower basket card point print, wet flower basket card point print, belt print, suction cup print, positioning fixture adjustment print and boat frame print.

7. The method for detecting cell scratch types based on image processing according to claim 1, characterized in that: The method further comprises: Obtain the total number of cells produced within a preset time period and the number of cells of each scratch type; The degree of wear of the corresponding mechanical fixture within a preset time period is determined according to the ratio of the number of battery cells of each scratch type to the total number of battery cells produced.

8. A battery cell scratch type detection device based on image processing, characterized in that: The device comprises: An image acquisition module, which acquires images of the battery cells to be inspected in real time during the production process of the battery cells; An EL detection module is connected to the image acquisition module, and detects the battery cell to be detected by a defect detection device to determine whether there are scratches on the surface of the battery cell to be detected; A grayscale processing module is connected to the EL detection module, and performs grayscale processing on the image to be detected to obtain a grayscale value of the image to be detected if it is determined that there are scratches on the surface of the cell to be detected; A contour restoration module, connected to the grayscale processing module, restores the shape contour of the scratched mechanical fixture on the image to be detected according to the grayscale value, and obtains a scratch contour image; The scratch type determination module is connected to the contour restoration module, and determines the scratch type of the battery cell to be detected by a correlation coefficient matching method according to the scratch contour image and a preset scratch type standard image.

9. The battery cell scratch type detection device based on image processing according to claim 8, characterized in that: The scratch type determination module comprises: A correlation coefficient calculation unit, which determines the correlation coefficient ρ between the scratch contour image and the standard image of each scratch type through a correlation coefficient calculation formula; The correlation coefficient calculation formula is: in, g(x,y) is the pixel value of the scratch type standard image, and g′(x,y) is the pixel value of the scratch contour image; The scratch type determination unit is connected to the correlation coefficient calculation unit. If the correlation coefficient between the scratch contour image and the scratch type standard image is greater than a preset coefficient threshold, the scratch type corresponding to the scratch type standard image is determined as the scratch type of the battery cell to be detected.

10. The battery cell scratch type detection device based on image processing according to claim 8, characterized in that: The contour restoration module comprises: a scratch region determining unit, which decomposes the image to be detected according to the grayscale value, and determines a region with a grayscale value of 0% as a scratch region; The scratch contour acquisition unit is connected to the scratch area determination unit, and restores the scratched mechanical fixture shape contour on the image to be detected according to the contour of the scratch area to acquire a scratch contour image.

Images