Methods, apparatuses, devices, and media for deleting duplicate identified cell tab endpoints

Abstract

The application provides a method and device for deleting duplicate identified cell tab end points, equipment and medium, wherein the method comprises: identifying tab end points of each tab of a to-be-detected cell from a cell image containing the to-be-detected cell; taking a tab end point with an offset distance not greater than a preset offset distance as a first tab end point according to the offset distance between the tab end point and a center reference line; the center reference line is perpendicular to each tab; the distance between the center reference line and a target reference line having a parallel relationship with the center reference line is the average of the distance between each tab end point and the target reference line; deleting a first tab end point with an end point interval distance smaller than a standard end point interval distance in a first direction between each first tab end point to take the remaining first tab end points as target tab end points; the first direction is perpendicular to each tab. The method is beneficial to improving the accuracy of cell tab alignment detection.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of battery cells, and in particular to a method and device for deleting duplicate-identified end points of battery cell pole pieces, equipment and a medium. BACKGROUND

[0002] In the production process of battery cells, the alignment of the positive pole pieces and the negative pole pieces in the battery cells needs to be detected. Specifically, when the positive pole pieces and the negative pole pieces in the same battery cell are aligned, it means that the lengths of the positive pole pieces and the negative pole pieces are the same, and then in the use process, the battery cell is prone to short circuit. Therefore, in the production process of battery cells, the alignment of the positive pole pieces and the negative pole pieces in the battery cells is detected to screen out unqualified (i.e. prone to short circuit) battery cells.

[0003] At present, when the alignment of the positive pole pieces and the negative pole pieces in the battery cells is detected, the end points of the same battery cell pole piece are prone to be repeatedly identified, i.e. one battery cell pole piece may be identified with multiple pole piece end points (i.e. the identification of the pole piece end points is incorrect). The incorrect identification of the pole piece end points will affect the subsequent detection results of the alignment of the battery cell pole pieces, causing the problem of inaccurate detection of the alignment of the battery cell pole pieces. SUMMARY

[0004] Therefore, the purpose of the present application is to provide a method and device for deleting duplicate-identified end points of battery cell pole pieces, to delete the incorrectly identified pole piece end points and improve the accuracy of the detection of the alignment of the battery cell pole pieces.

[0005] In a first aspect, the embodiments of the present application provide a method for deleting duplicate-identified end points of battery cell pole pieces, comprising:

[0006] identifying the pole piece end points of each pole piece of a to-be-detected battery cell from a battery cell image containing the to-be-detected battery cell; the types of the pole piece end points include a positive pole piece end point type and a negative pole piece end point type;

[0007] for each type of the pole piece end points, deleting the pole piece end points with a displacement distance greater than a preset displacement distance according to the displacement distances between each of the pole piece end points of this type and a center reference line, to take the remaining pole piece end points as the first pole piece end points of this type; the center reference line is perpendicular to each pole piece; the distance between the center reference line and a target reference line having a parallel relationship with the center reference line is the average of the distances between each of the pole piece end points of this type and the target reference line;

[0008] For each type of the first pole piece endpoints, according to the inter-endpoint spacing distance between each of the first pole piece endpoints of the type in a first direction, the first pole piece endpoint with an inter-endpoint spacing distance less than a standard inter-endpoint spacing distance is deleted, so as to take the remaining first pole piece endpoints as target pole piece endpoints of the type; the first direction is perpendicular to each pole piece.

[0009] With reference to the first aspect, in a first possible implementation of the first aspect, before the pole piece endpoints of each pole piece of the to-be-detected battery cell are identified from the battery cell image containing the to-be-detected battery cell, the method further includes:

[0010] After the battery cell image of the to-be-detected battery cell is acquired, an average gray value of the battery cell image is calculated to determine whether the average gray value is greater than a preset gray threshold value;

[0011] If the average gray value is greater than the preset gray threshold value, it indicates that the to-be-detected battery cell is contained in the battery cell image;

[0012] If the average gray value is not greater than the preset gray threshold value, it indicates that the to-be-detected battery cell is not contained in the battery cell image, and the battery cell image of the to-be-detected battery cell is re-acquired until the average gray value of the acquired battery cell image is greater than the preset gray threshold value.

[0013] With reference to the first aspect, in a second possible implementation of the first aspect, the pole piece endpoints of each pole piece of the to-be-detected battery cell are identified from the battery cell image containing the to-be-detected battery cell, and the method further includes:

[0014] The battery cell image is converted into a gray image;

[0015] A first identification model pre-trained is used to identify a pole piece region containing each pole piece from the gray image;

[0016] The pole piece region is subjected to filtering processing to remove burrs, to obtain a filtered pole piece region;

[0017] According to the position of the filtered pole piece region in the gray image, a battery cell pole piece image corresponding to the filtered pole piece region is determined from the same position in the battery cell image;

[0018] A second identification model pre-trained is used to identify the pole piece endpoints of each pole piece from the battery cell pole piece image.

[0019] In conjunction with the first aspect, this application provides a third possible implementation of the first aspect, wherein, for each type of electrode endpoint, based on the offset distance between each electrode endpoint of that type and the center reference line, electrode endpoints with an offset distance greater than a preset offset distance are deleted, so that the remaining electrode endpoints are used as the first electrode endpoints of that type, including:

[0020] Determine the position coordinates of each electrode endpoint in the cell image; the position coordinates include a first position coordinate value of the electrode endpoint in a first direction and a second position coordinate value in a second direction; the second direction is parallel to each electrode.

[0021] For each type of electrode endpoint, the average coordinate value of all second position coordinate values ​​of that type is calculated based on the second position coordinate values ​​corresponding to each electrode endpoint of that type.

[0022] The straight line corresponding to the average coordinate value is used as the center reference line. Based on the average coordinate value and a preset first fluctuation threshold, the fluctuation range with the center reference line as the fluctuation center line is calculated in the second direction. The length of the fluctuation range in the second direction is twice the preset offset distance.

[0023] Remove the electrode endpoints whose second position coordinate values ​​are outside the fluctuation range from all electrode endpoints corresponding to this type, so that the remaining electrode endpoints are used as the first electrode endpoints of this type.

[0024] In conjunction with the third possible implementation of the first aspect, this application provides a fourth possible implementation of the first aspect, wherein, for each type of first electrode endpoint, based on the endpoint spacing distance between the respective first electrode endpoints of that type in a first direction, the first electrode endpoints with endpoint spacing distances smaller than the standard endpoint spacing distance are deleted, so that the remaining first electrode endpoints are used as the target electrode endpoints of that type, including:

[0025] For each type, based on the first position coordinate values ​​corresponding to each first electrode endpoint of that type, the minimum coordinate value among all the first electrode endpoints of that type is selected, and the first electrode endpoint corresponding to the minimum coordinate value is used as the reference electrode endpoint, and the other first electrode endpoints besides the reference electrode endpoint are used as the second electrode endpoints.

[0026] Based on the minimum coordinate value and the pre-set second fluctuation threshold, the standard endpoint interval distance corresponding to the endpoint of the reference electrode is calculated;

[0027] Based on the first position coordinates of each second electrode endpoint and the minimum coordinates, the endpoint spacing distance between each second electrode endpoint and the reference electrode endpoint in the first direction is calculated;

[0028] The second electrode endpoints whose endpoint spacing distance is less than the standard endpoint spacing distance are deleted to obtain the remaining second electrode endpoints. The remaining second electrode endpoints are used as new first electrode endpoints. The process continues to execute the first position coordinate values ​​corresponding to each first electrode endpoint of this type. The minimum coordinate value among all the first electrode endpoints of this type is selected, and the first electrode endpoint corresponding to the minimum coordinate value is used as the reference electrode endpoint. The other first electrode endpoints besides the reference electrode endpoint are used as second electrode endpoints and subsequent steps, until the number of remaining second electrode endpoints is less than or equal to 1. The reference electrode endpoints corresponding to each cycle are used as the target electrode endpoints corresponding to this type.

[0029] In conjunction with the first aspect or the fourth possible implementation of the first aspect, this application provides a fifth possible implementation of the first aspect, wherein the target electrode endpoint of the positive electrode endpoint type is a positive target electrode endpoint, and the target electrode endpoint of the negative electrode endpoint type is a negative target electrode endpoint. After obtaining each of the positive electrode endpoints and each of the negative electrode endpoints, the implementation further includes:

[0030] Calculate the distance difference between the endpoints of the positive electrode and the negative electrode.

[0031] The quality of the battery cell under test is determined based on the distance difference.

[0032] In conjunction with the first aspect or the fourth possible implementation of the first aspect, this application provides a sixth possible implementation of the first aspect, wherein, after obtaining the target electrode endpoints corresponding to each type, it further includes:

[0033] For each type of target electrode endpoint, determine the alignment between the individual target electrode endpoints of that type;

[0034] Based on the alignment degree corresponding to each type, determine whether the battery cell to be tested is qualified.

[0035] Secondly, embodiments of this application also provide an apparatus for deleting duplicately identified cell electrode endpoints, comprising:

[0036] The identification module is used to identify the electrode endpoints of each electrode of the battery cell to be tested from a battery cell image containing the battery cell to be tested; the types of electrode endpoints include positive electrode endpoint type and negative electrode endpoint type;

[0037] The first deletion module is used to delete, for each type of electrode endpoint, electrode endpoints whose offset distance is greater than a preset offset distance according to the offset distance between each electrode endpoint of that type and the center reference line, so that the remaining electrode endpoints are used as the first electrode endpoints of that type; the center reference line is perpendicular to each electrode; the distance between the center reference line and a target reference line that is parallel to it is the average of the distances between each electrode endpoint of that type and the target reference line;

[0038] The second deletion module is used to delete first electrode endpoints whose endpoint spacing distance is less than the standard endpoint spacing distance for each type of first electrode endpoint, based on the endpoint spacing distance between each first electrode endpoint of that type in a first direction, so as to use the remaining first electrode endpoints as the target electrode endpoints of that type; the first direction is perpendicular to each electrode.

[0039] In conjunction with the second aspect, embodiments of this application provide a first possible implementation of the second aspect, which further includes:

[0040] The calculation module is used to calculate the average gray value of the cell image after obtaining the cell image of the cell to be tested, before the recognition module identifies the electrode endpoints of each electrode of the cell to be tested from the cell image containing the cell to be tested, so as to determine whether the average gray value is greater than a preset gray value threshold.

[0041] The first representation module is used to indicate that the cell image contains the cell to be detected if the average gray value is greater than the preset gray value threshold.

[0042] The second representation module is used to indicate that the cell image does not contain the cell to be detected if the average gray value is not greater than the preset gray value threshold, and to re-acquire the cell image of the cell to be detected until the average gray value of the acquired cell image is greater than the preset gray value threshold.

[0043] In conjunction with the second aspect, this application provides a second possible implementation of the second aspect, wherein the identification module, when identifying the electrode endpoints of each electrode of the battery cell to be tested from a battery cell image containing the battery cell to be tested, is specifically used for:

[0044] Convert the battery cell image into a grayscale image;

[0045] Using a pre-trained first recognition model, the electrode regions containing each of the electrodes are identified from the grayscale image;

[0046] The electrode region is filtered to remove burrs, resulting in a filtered electrode region.

[0047] Based on the position of the filtered electrode region in the grayscale image, the cell electrode image corresponding to the filtered electrode region is determined from the same position in the cell image;

[0048] Using a pre-trained second recognition model, the electrode endpoints of each electrode are identified from the cell electrode image.

[0049] In conjunction with the second aspect, this application provides a third possible implementation of the second aspect, wherein the first deletion module, when used to delete electrode endpoints with offset distances greater than a preset offset distance for each type of electrode endpoint based on the offset distance between each electrode endpoint of that type and the center reference line, so as to use the remaining electrode endpoints as the first electrode endpoints of that type, is specifically used for:

[0050] Determine the position coordinates of each electrode endpoint in the cell image; the position coordinates include a first position coordinate value of the electrode endpoint in a first direction and a second position coordinate value in a second direction; the second direction is parallel to each electrode.

[0051] For each type of electrode endpoint, the average coordinate value of all second position coordinate values ​​of that type is calculated based on the second position coordinate values ​​corresponding to each electrode endpoint of that type.

[0052] The straight line corresponding to the average coordinate value is used as the center reference line. Based on the average coordinate value and a preset first fluctuation threshold, the fluctuation range with the center reference line as the fluctuation center line is calculated in the second direction. The length of the fluctuation range in the second direction is twice the preset offset distance.

[0053] Remove the electrode endpoints whose second position coordinate values ​​are outside the fluctuation range from all electrode endpoints corresponding to this type, so that the remaining electrode endpoints are used as the first electrode endpoints of this type.

[0054] In conjunction with the third possible implementation of the second aspect, this application provides a fourth possible implementation of the second aspect, wherein the second deletion module, when used to delete first electrode endpoints with endpoint spacing less than a standard endpoint spacing distance in a first direction for each type of first electrode endpoint, so as to use the remaining first electrode endpoints as target electrode endpoints of that type, is specifically used for:

[0055] For each type, based on the first position coordinate values ​​corresponding to each first electrode endpoint of that type, the minimum coordinate value among all the first electrode endpoints of that type is selected, and the first electrode endpoint corresponding to the minimum coordinate value is used as the reference electrode endpoint, and the other first electrode endpoints besides the reference electrode endpoint are used as the second electrode endpoints.

[0056] Based on the minimum coordinate value and the pre-set second fluctuation threshold, the standard endpoint interval distance corresponding to the endpoint of the reference electrode is calculated;

[0057] Based on the first position coordinates of each second electrode endpoint and the minimum coordinates, the endpoint spacing distance between each second electrode endpoint and the reference electrode endpoint in the first direction is calculated;

[0058] The second electrode endpoints whose endpoint spacing distance is less than the standard endpoint spacing distance are deleted to obtain the remaining second electrode endpoints. The remaining second electrode endpoints are used as new first electrode endpoints. The process continues to execute the first position coordinate values ​​corresponding to each first electrode endpoint of this type. The minimum coordinate value among all the first electrode endpoints of this type is selected, and the first electrode endpoint corresponding to the minimum coordinate value is used as the reference electrode endpoint. The other first electrode endpoints besides the reference electrode endpoint are used as second electrode endpoints and subsequent steps, until the number of remaining second electrode endpoints is less than or equal to 1. The reference electrode endpoints corresponding to each cycle are used as the target electrode endpoints corresponding to this type.

[0059] In conjunction with the second aspect or the fourth possible implementation of the second aspect, this application provides a fifth possible implementation of the second aspect, wherein the target electrode endpoint of the positive electrode endpoint type is a positive target electrode endpoint, and the target electrode endpoint of the negative electrode endpoint type is a negative target electrode endpoint, and the device further includes:

[0060] The second calculation module is used to calculate the distance difference between the endpoints of the positive target electrode and the endpoints of the negative target electrode after the second deletion module obtains the endpoints of each positive target electrode and each negative target electrode.

[0061] The first judgment module is used to determine whether the battery cell to be tested is qualified based on the distance difference.

[0062] In conjunction with the second aspect or the fourth possible implementation of the second aspect, this application provides a sixth possible implementation of the second aspect, which further includes:

[0063] The determination module is used to determine the alignment between the target electrode endpoints of each type after the second deletion module obtains the target electrode endpoints corresponding to each type.

[0064] The second judgment module is used to determine whether the battery cell to be tested is qualified based on the alignment degree corresponding to each type.

[0065] Thirdly, embodiments of this application also provide an electronic device, including: a processor, a memory, and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the memory via the bus, and when the machine-readable instructions are executed by the processor, the steps in any of the possible implementations of the first aspect described above are performed.

[0066] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps in any of the possible implementations of the first aspect described above.

[0067] This application provides a method, apparatus, device, and medium for deleting duplicate-identified electrode endpoints in a battery cell. After identifying the electrode endpoints of each electrode in a battery cell image, considering that electrode endpoints with excessive offset distances from the center reference line may be incorrectly identified (duplicated), electrode endpoints with offset distances greater than a preset offset distance are deleted to remove incorrectly identified (duplicated) electrode endpoints, resulting in first electrode endpoints of various types. Furthermore, considering that there is actually a certain interval between electrodes of the same type in a first direction, if the endpoint interval between first electrode endpoints of the same type in the first direction is too close, it may also be an incorrectly identified (duplicated) electrode endpoint. Therefore, first electrode endpoints with endpoint intervals smaller than the standard endpoint interval are deleted to remove incorrectly identified (duplicated) electrode endpoints, resulting in target electrode endpoints. In this embodiment, considering that if the identified electrode endpoint is incorrect, it will affect the detection result of the subsequent detection of the alignment of the cell electrode, the incorrectly identified electrode endpoint is deleted by means of this application, so as to improve the accuracy of the cell electrode alignment detection when calculating the alignment of the cell electrode in the future.

[0068] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0069] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0070] Figure 1 A flowchart illustrating a method for deleting duplicately identified cell electrode endpoints provided in an embodiment of this application is shown.

[0071] Figure 2 A schematic diagram of a battery cell image provided in an embodiment of this application is shown;

[0072] Figure 3 This illustration shows a schematic diagram of an electrode region provided in an embodiment of this application;

[0073] Figure 4 A schematic diagram showing an image of a battery cell electrode provided in an embodiment of this application is illustrated;

[0074] Figure 5 A schematic diagram of the same type of electrode endpoint provided in the embodiments of this application is shown;

[0075] Figure 6 This illustration shows a schematic diagram of a center reference line provided in an embodiment of this application;

[0076] Figure 7 A schematic diagram of a rectangular coordinate system provided in an embodiment of this application is shown;

[0077] Figure 8 A schematic diagram of a reference electrode endpoint provided in an embodiment of this application is shown;

[0078] Figure 9 This illustration shows a schematic diagram of a device for deleting duplicately identified cell electrode endpoints according to an embodiment of this application.

[0079] Figure 10 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown. Detailed Implementation

[0080] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0081] Considering that incorrect identification of electrode endpoints (duplicate identification) can affect the detection results of cell electrode alignment, this application provides a method, apparatus, device, and medium for deleting duplicately identified cell electrode endpoints to remove incorrectly identified electrode endpoints and improve the accuracy of cell electrode alignment detection. The following embodiments describe these embodiments.

[0082] Example 1:

[0083] To facilitate understanding of this embodiment, a method for deleting duplicately identified cell electrode endpoints disclosed in this application will first be described in detail. Figure 1 A flowchart illustrating a method for deleting duplicately identified cell electrode endpoints provided in an embodiment of this application is shown, as follows: Figure 1 As shown, the process includes the following steps S101-S103:

[0084] S101: Identify the electrode endpoints of each electrode of the battery cell to be tested from the battery cell image containing the battery cell to be tested; the types of electrode endpoints include positive electrode endpoint type and negative electrode endpoint type.

[0085] In this embodiment, the battery cell to be tested contains multiple electrodes, and the types of electrodes include positive electrodes and negative electrodes, that is, the battery cell to be tested contains multiple positive electrodes and multiple negative electrodes. Figure 2 A schematic diagram of a battery cell image provided in an embodiment of this application is shown, such as... Figure 2 As shown, each electrode corresponds to its own electrode endpoint.

[0086] In one possible implementation, before executing step S101, the following steps S1001-S1003 may also be performed:

[0087] S1001: After obtaining the cell image of the cell to be detected, calculate the average gray value of the cell image to determine whether the average gray value is greater than the preset gray value threshold.

[0088] In this embodiment, an image of the battery cell to be tested is detected using an x-ray device, and then the image is acquired from the x-ray device. To confirm whether the battery cell image detected by the x-ray device contains the battery cell to be tested, this embodiment calculates the average grayscale value of the battery cell image and determines whether the average grayscale value is greater than a preset grayscale threshold.

[0089] S1002: If the average gray value is greater than the preset gray value threshold, it means that the cell image contains the cell to be detected.

[0090] In this embodiment, if the average grayscale value is greater than a preset grayscale threshold, it is then determined whether the average grayscale value is less than a second preset grayscale threshold. If the average grayscale value is greater than the preset grayscale threshold and less than the second preset grayscale threshold, it indicates that the cell image contains the cell to be detected. The preset grayscale threshold is less than the second preset grayscale threshold. This method helps avoid obtaining a completely black or completely white cell image.

[0091] S1003: If the average gray value is not greater than the preset gray value threshold, it means that the cell image does not contain the cell to be detected. Reacquire the cell image of the cell to be detected until the average gray value of the acquired cell image is greater than the preset gray value threshold.

[0092] For example, when the cell image is completely black, the average grayscale value of the cell image should be 0, meaning the average grayscale value is no greater than a preset grayscale threshold, indicating that the cell image does not contain the cell to be detected. In this case, the X-ray device needs to re-detect the cell image of the cell to be detected. This method helps to filter out cell images that are incorrectly imaged by the X-ray device.

[0093] In this embodiment, after acquiring the cell image from the x-ray device, the cell image is rotated to make the cell image rotate to... Figure 2 The directions shown are for subsequent processing.

[0094] In one possible implementation, when performing step S101, the following steps S1011-S1015 can be specifically performed:

[0095] S1011: Convert the cell image to a grayscale image.

[0096] S1012: Using a pre-trained first recognition model, identify the electrode regions containing each electrode from the grayscale image.

[0097] Figure 3 A schematic diagram of an electrode region provided in an embodiment of this application is shown, such as... Figure 3 As shown, the electrode region includes a positive electrode region and a negative electrode region.

[0098] S1013: Filter the electrode area to remove burrs and obtain the filtered electrode area.

[0099] S1014: Based on the position of the filtered electrode region in the grayscale image, determine the cell electrode image corresponding to the filtered electrode region from the same position in the cell image.

[0100] Figure 4 This illustration shows a schematic diagram of a battery cell electrode image provided in an embodiment of this application, such as... Figure 4 As shown, the position of the filtered electrode region in the grayscale image is the same as the position of the electrode image in the cell image.

[0101] S1015: Using a pre-trained second recognition model, identify the electrode endpoints of each electrode from the cell electrode image.

[0102] In this embodiment, a pre-trained second recognition model is used to identify the positive electrode endpoints of each positive electrode and the negative electrode endpoints of each negative electrode from the cell electrode image. Figure 5 A schematic diagram of the same type of electrode endpoint provided in the embodiments of this application is shown.

[0103] S102: For each type of electrode endpoint, based on the offset distance between each electrode endpoint of that type and the center reference line, delete the electrode endpoints whose offset distance is greater than a preset offset distance, so that the remaining electrode endpoints are used as the first electrode endpoints of that type; the center reference line is perpendicular to each electrode; the distance between the center reference line and the target reference line that is parallel to it is the average of the distances between each electrode endpoint of that type and the target reference line.

[0104] In this embodiment, Figure 6 A schematic diagram of a center reference line provided in an embodiment of this application is shown, such as... Figure 6 As shown, the center reference line is parallel to the target reference line. Specifically, when calculating the offset distance between each electrode endpoint and the center reference line, the perpendicular distance between the center point of each electrode endpoint and the center reference line can be calculated.

[0105] In one possible implementation, when performing step S102, the following steps S1021-S1024 can be specifically performed:

[0106] S1021: Determine the position coordinates of each electrode endpoint in the cell image; the position coordinates include the first position coordinate value of the electrode endpoint in a first direction and the second position coordinate value in a second direction; the second direction is parallel to each electrode.

[0107] In this embodiment, a rectangular coordinate system is established with the point corresponding to the lower left corner of the battery cell image as the center point. Figure 7 A schematic diagram of a rectangular coordinate system provided in an embodiment of this application is shown, as follows: Figure 7 As shown, the horizontal (x) axis of this rectangular coordinate system is parallel to each electrode, and the vertical (y) axis is perpendicular to each electrode. The position coordinates of the electrode endpoints in the cell image are specifically the position coordinates of the electrode endpoints in this rectangular coordinate system. Here, the first direction is the vertical direction of the rectangular coordinate system, and the second direction is the horizontal direction of the rectangular coordinate system.

[0108] S1022: For each type of electrode endpoint, calculate the average coordinate value of all second position coordinate values ​​of that type based on the second position coordinate values ​​corresponding to each electrode endpoint of that type.

[0109] When the electrode endpoint type is a positive electrode endpoint, taking the positive electrode endpoint as an example, the average coordinate value of the second position coordinate values ​​corresponding to all positive electrode endpoints is calculated based on the second position coordinate values ​​corresponding to each positive electrode endpoint. The second position coordinate value is the distance of each positive electrode endpoint from the y-axis. In this embodiment, the target reference line can specifically be the y-axis of a Cartesian coordinate system.

[0110] S1023: Using the straight line corresponding to the average coordinate value as the center reference line, calculate the fluctuation range in the second direction with the center reference line as the fluctuation center line based on the average coordinate value and the preset first fluctuation threshold; the length of the fluctuation range in the second direction is twice the preset offset distance.

[0111] In this embodiment, the center reference line is located in the middle of the fluctuation range, dividing the fluctuation range into two parts.

[0112] S1024: Remove the electrode endpoints whose second position coordinate values ​​are outside the fluctuation range from all electrode endpoints corresponding to this type, so that the remaining electrode endpoints can be used as the first electrode endpoints of this type.

[0113] In this embodiment, the electrode endpoints whose second position coordinate values ​​are within the fluctuation range are retained as the first electrode endpoints. In this way, redundant electrode endpoints in the x-axis direction (i.e., the second direction) can be removed.

[0114] S103: For each type of first electrode endpoint, based on the endpoint spacing distance between each first electrode endpoint of that type in the first direction, delete the first electrode endpoints whose endpoint spacing distance is less than the standard endpoint spacing distance, so that the remaining first electrode endpoints are used as the target electrode endpoints of that type; the first direction is perpendicular to each electrode.

[0115] In one possible implementation, when performing step S103, the following steps S1031-S1034 can be specifically performed:

[0116] S1031: For each type, based on the first position coordinate values ​​corresponding to each first electrode endpoint of that type, select the minimum coordinate value among all the first position coordinate values ​​of that type, and use the first electrode endpoint corresponding to the minimum coordinate value as the reference electrode endpoint, and use the other first electrode endpoints other than the reference electrode endpoint as the second electrode endpoints.

[0117] In this embodiment, each type of first electrode has multiple endpoints. For example, Figure 8 A schematic diagram of a reference electrode endpoint provided in an embodiment of this application is shown, as follows: Figure 8 As shown, the origins in the rectangular coordinate system represent the endpoints of the first electrode of the same type (A, B, C, D, E, F, and G, respectively) (for example, they are all endpoints of the first positive electrode, or they are all endpoints of the first negative electrode). The first position coordinates of the first electrode endpoints are the coordinates on the y-axis (first direction).

[0118] For each type, the minimum coordinate value among all first electrode endpoints of that type is selected, and the first electrode endpoint corresponding to the minimum coordinate value is taken as the reference electrode endpoint. That is, the reference electrode endpoint is the first electrode endpoint closest to the x-axis. In this case, first electrode endpoint A is the reference electrode endpoint. The other first electrode endpoints (B, C, D, E, F, G) are taken as second electrode endpoints.

[0119] S1032: Calculate the standard endpoint spacing distance corresponding to the reference electrode endpoint based on the minimum coordinate value and the pre-set second fluctuation threshold.

[0120] Following the above embodiment, the minimum coordinate value is the first position coordinate value of the reference electrode endpoint A in the first direction. In this embodiment, the length of the standard endpoint spacing distance is the same as the second fluctuation threshold, and the starting value of the standard endpoint spacing distance is the first position coordinate value (i.e., the minimum coordinate value) corresponding to the reference electrode endpoint A. Therefore, in this embodiment, as... Figure 8 As shown, the standard endpoint spacing distance corresponding to the reference electrode endpoint A is illustrated.

[0121] S1033: Calculate the endpoint spacing distance between each second electrode endpoint and the reference electrode endpoint in the first direction based on the first position coordinate value and the minimum coordinate value of each second electrode endpoint.

[0122] In this embodiment, the endpoint spacing distance between each second electrode endpoint (B, C, D, E, F, G) and the reference electrode endpoint A is calculated.

[0123] S1034: Delete the second pole piece endpoints whose endpoint spacing distance is less than the standard endpoint spacing distance to obtain the remaining second pole piece endpoints. Use the remaining second pole piece endpoints as new first pole piece endpoints. Continue to execute the process of selecting the minimum coordinate value from all first pole piece endpoints of this type based on the first position coordinate values ​​corresponding to each first pole piece endpoint. Use the first pole piece endpoint corresponding to the minimum coordinate value as the reference pole piece endpoint. Use the other first pole piece endpoints besides the reference pole piece endpoint as second pole piece endpoints and subsequent steps until the number of remaining second pole piece endpoints is less than or equal to 1. Use the reference pole piece endpoints corresponding to each cycle as the target pole piece endpoints corresponding to this type.

[0124] like Figure 8 As shown, the endpoint spacing between the second electrode endpoints B and C and the reference electrode endpoint A is less than the standard endpoint spacing, therefore the second electrode endpoints B and C are deleted. Then, the remaining second electrode endpoints (D, E, F, G) are used as the new first electrode endpoints.

[0125] Continuing the process, based on the first position coordinates corresponding to each first electrode endpoint of this type, the minimum coordinate value is selected from all first electrode endpoints of this type. The first electrode endpoint corresponding to the minimum coordinate value is then used as the reference electrode endpoint, which is now D. The other first electrode endpoints (E, F, G) are used as new second electrode endpoints. Based on the minimum coordinate value (the first position coordinate value corresponding to reference electrode endpoint D) and a pre-set second fluctuation threshold, the standard endpoint spacing distance corresponding to reference electrode endpoint D is calculated. Then, the endpoint spacing distance between each second electrode endpoint (E, F, G) and the reference electrode endpoint D is calculated. Figure 8 As shown, the endpoint spacing between the second electrode endpoints E and F and the reference electrode endpoint D is less than the standard endpoint spacing, therefore, the second electrode endpoints E and F are deleted. Then, the remaining second electrode endpoint (G) is used as the new first electrode endpoint. Since the number of remaining second electrode endpoints is less than or equal to 1, the loop is stopped, and the reference electrode endpoints (A and D) corresponding to each loop round are used as the target electrode endpoints for that type.

[0126] It is worth noting that the above description is merely illustrative, and there can actually be multiple target electrode endpoints for each type.

[0127] In one possible implementation, the target electrode endpoint of the positive electrode endpoint type is the positive target electrode endpoint, and the target electrode endpoint of the negative electrode endpoint type is the negative target electrode endpoint. After obtaining each positive target electrode endpoint and each negative target electrode endpoint, the following steps S1041-S1042 can be performed:

[0128] S1041: Calculate the distance difference between the endpoints of the positive target electrode and the negative target electrode.

[0129] In this embodiment, there are multiple endpoints for both the positive and negative target electrodes. Therefore, to calculate the distance difference between the endpoints of the positive and negative target electrodes, the difference between the minimum and maximum second position coordinates of each positive target electrode endpoint and the maximum second position coordinates of each negative target electrode endpoint can be calculated and used as the distance difference. Alternatively, the distance difference can be calculated by comparing the average positive second position coordinates of each positive target electrode endpoint with the average negative second position coordinates of each negative target electrode endpoint, and using the difference between the average positive and average negative second position coordinates as the distance difference.

[0130] S1042: Determine whether the battery cell under test is qualified based on the distance difference.

[0131] In this embodiment, when the distance difference is greater than the first preset distance difference, it indicates that the battery cell under test is qualified. When the distance difference is not greater than the first preset distance difference, it indicates that the battery cell under test is unqualified.

[0132] In this embodiment, considering that if the distance between the positive target electrode end point and the negative target electrode end point is too close (e.g., the same length), the cell under test may short-circuit. Therefore, in order to avoid the cell under test from short-circuiting, it is necessary to have a certain distance between the positive target electrode end point and the negative target electrode end point.

[0133] In one possible implementation, after obtaining the target electrode endpoints corresponding to each type, the following steps S1051-S1052 can be performed:

[0134] S1051: For each type of target electrode endpoint, determine the alignment between the individual target electrode endpoints of that type.

[0135] In this embodiment, for each type of target electrode endpoint, the difference between the largest and smallest second position coordinate values ​​among all second position coordinate values ​​is calculated based on the second position coordinate values ​​corresponding to each target electrode endpoint of that type, and this difference is used as the alignment between the various target electrode endpoints of that type.

[0136] S1052: Determine whether the battery cell to be tested is qualified based on the alignment degree corresponding to each type.

[0137] In this embodiment, it is determined whether the difference between each type is greater than a second preset distance difference. If the difference between any one or two types is greater than the second preset distance difference, the battery cell to be tested is unqualified. If the difference between the two types is not greater than the second preset distance difference, the battery cell to be tested is qualified.

[0138] In this embodiment, a larger difference indicates a worse alignment between the endpoints of the target electrode, and a less qualified cell. A smaller difference indicates a better alignment between the endpoints of the target electrode, and a more qualified cell.

[0139] In one possible implementation, the target electrode endpoint of the positive electrode endpoint type is the positive target electrode endpoint, and the target electrode endpoint of the negative electrode endpoint type is the negative target electrode endpoint. After obtaining each positive target electrode endpoint and each negative target electrode endpoint, specifically:

[0140] Calculate the distance difference between the endpoints of the positive target electrode and the endpoints of the negative target electrode; and calculate the alignment (i.e., difference) between the endpoints of the positive target electrode and the alignment (i.e., difference) between the endpoints of the negative target electrode.

[0141] If the distance difference is greater than the first preset distance difference, and the alignment between the endpoints of the positive target electrode (the aforementioned difference) is not greater than the second preset distance difference, and the alignment between the endpoints of the negative target electrode (the aforementioned difference) is also not greater than the second preset distance difference, then the cell to be tested is qualified.

[0142] If the distance difference is not greater than the first preset distance difference, the alignment between the endpoints of the positive target electrode (the aforementioned difference) is greater than the second preset distance difference, and / or the alignment between the endpoints of the negative target electrode (the aforementioned difference) is greater than the second preset distance difference, then the cell to be tested is unqualified.

[0143] The specific calculation process is as described above, and will not be repeated here.

[0144] Example 2:

[0145] Based on the same technical concept, this application also provides a device for deleting duplicate-identified cell electrode endpoints.Figure 9 This invention provides a schematic diagram of a device for deleting duplicately identified cell electrode endpoints according to an embodiment of this application. Figure 9 As shown, the device includes:

[0146] The identification module 901 is used to identify the electrode endpoints of each electrode of the battery cell to be tested from a battery cell image containing the battery cell to be tested; the types of electrode endpoints include positive electrode endpoint type and negative electrode endpoint type;

[0147] The first deletion module 902 is used to delete, for each type of electrode endpoint, the electrode endpoints whose offset distance is greater than a preset offset distance according to the offset distance between each electrode endpoint of that type and the center reference line, so that the remaining electrode endpoints are used as the first electrode endpoints of that type; the center reference line is perpendicular to each electrode; the distance between the center reference line and the target reference line that is parallel to it is the average value of the distances between each electrode endpoint of that type and the target reference line;

[0148] The second deletion module 903 is used to delete first electrode endpoints whose endpoint spacing distance is less than the standard endpoint spacing distance for each type of first electrode endpoint, based on the endpoint spacing distance between each first electrode endpoint of that type in a first direction, so as to use the remaining first electrode endpoints as the target electrode endpoints of that type; the first direction is perpendicular to each electrode.

[0149] Optional, also includes:

[0150] The calculation module is used to calculate the average gray value of the cell image after obtaining the cell image of the cell to be tested before the identification module 901 identifies the electrode endpoints of each electrode of the cell to be tested from the cell image containing the cell to be tested, so as to determine whether the average gray value is greater than a preset gray value threshold.

[0151] The first representation module is used to indicate that the cell image contains the cell to be detected if the average gray value is greater than the preset gray value threshold.

[0152] The second representation module is used to indicate that the cell image does not contain the cell to be detected if the average gray value is not greater than the preset gray value threshold, and to re-acquire the cell image of the cell to be detected until the average gray value of the acquired cell image is greater than the preset gray value threshold.

[0153] Optionally, when the identification module 901 identifies the electrode endpoints of each electrode of the battery cell to be tested from an image containing the battery cell to be tested, it is specifically used for:

[0154] Convert the battery cell image into a grayscale image;

[0155] Using a pre-trained first recognition model, the electrode regions containing each of the electrodes are identified from the grayscale image;

[0156] The electrode region is filtered to remove burrs, resulting in a filtered electrode region.

[0157] Based on the position of the filtered electrode region in the grayscale image, the cell electrode image corresponding to the filtered electrode region is determined from the same position in the cell image;

[0158] Using a pre-trained second recognition model, the electrode endpoints of each electrode are identified from the cell electrode image.

[0159] Optionally, when the first deletion module 902 is used to delete electrode endpoints with offset distances greater than a preset offset distance for each type of electrode endpoint based on the offset distance between each electrode endpoint of that type and the center reference line, so as to use the remaining electrode endpoints as the first electrode endpoints of that type, it is specifically used for:

[0160] Determine the position coordinates of each electrode endpoint in the cell image; the position coordinates include a first position coordinate value of the electrode endpoint in a first direction and a second position coordinate value in a second direction; the second direction is parallel to each electrode.

[0161] For each type of electrode endpoint, the average coordinate value of all second position coordinate values ​​of that type is calculated based on the second position coordinate values ​​corresponding to each electrode endpoint of that type.

[0162] The straight line corresponding to the average coordinate value is used as the center reference line. Based on the average coordinate value and a preset first fluctuation threshold, the fluctuation range with the center reference line as the fluctuation center line is calculated in the second direction. The length of the fluctuation range in the second direction is twice the preset offset distance.

[0163] Remove the electrode endpoints whose second position coordinate values ​​are outside the fluctuation range from all electrode endpoints corresponding to this type, so that the remaining electrode endpoints are used as the first electrode endpoints of this type.

[0164] Optionally, when the second deletion module 903 is used to delete first electrode endpoints whose endpoint spacing distance is less than the standard endpoint spacing distance for each type of first electrode endpoint, based on the endpoint spacing distance between the respective first electrode endpoints of that type in a first direction, so as to use the remaining first electrode endpoints as the target electrode endpoints of that type, it is specifically used for:

[0165] For each type, based on the first position coordinate values ​​corresponding to each first electrode endpoint of that type, the minimum coordinate value among all the first electrode endpoints of that type is selected, and the first electrode endpoint corresponding to the minimum coordinate value is used as the reference electrode endpoint, and the other first electrode endpoints besides the reference electrode endpoint are used as the second electrode endpoints.

[0166] Based on the minimum coordinate value and the pre-set second fluctuation threshold, the standard endpoint interval distance corresponding to the endpoint of the reference electrode is calculated;

[0167] Based on the first position coordinates of each second electrode endpoint and the minimum coordinates, the endpoint spacing distance between each second electrode endpoint and the reference electrode endpoint in the first direction is calculated;

[0168] The second electrode endpoints whose endpoint spacing distance is less than the standard endpoint spacing distance are deleted to obtain the remaining second electrode endpoints. The remaining second electrode endpoints are used as new first electrode endpoints. The process continues to execute the first position coordinate values ​​corresponding to each first electrode endpoint of this type. The minimum coordinate value among all the first electrode endpoints of this type is selected, and the first electrode endpoint corresponding to the minimum coordinate value is used as the reference electrode endpoint. The other first electrode endpoints besides the reference electrode endpoint are used as second electrode endpoints and subsequent steps, until the number of remaining second electrode endpoints is less than or equal to 1. The reference electrode endpoints corresponding to each cycle are used as the target electrode endpoints corresponding to this type.

[0169] Optionally, the target electrode endpoint of the positive electrode endpoint type is a positive target electrode endpoint, and the target electrode endpoint of the negative electrode endpoint type is a negative target electrode endpoint. The device further includes:

[0170] The second calculation module is used to calculate the distance difference between the endpoints of the positive target electrode and the endpoints of the negative target electrode after the second deletion module 903 obtains each endpoint of the positive target electrode and each endpoint of the negative target electrode.

[0171] The first judgment module is used to determine whether the battery cell to be tested is qualified based on the distance difference.

[0172] Optional, also includes:

[0173] The determination module is used to determine the alignment between the target electrode endpoints of each type after the second deletion module 903 obtains the target electrode endpoints corresponding to each type.

[0174] The second judgment module is used to determine whether the battery cell to be tested is qualified based on the alignment degree corresponding to each type.

[0175] Example 3:

[0176] Figure 10 A schematic diagram of an electronic device provided in this application embodiment includes: a processor 1001, a memory 1002, and a bus 1003. The memory 1002 stores machine-readable instructions executable by the processor 1001. When the electronic device runs the above-described information processing method, the processor 1001 communicates with the memory 1002 via the bus 1003. The processor 1001 executes the machine-readable instructions to perform the steps of the method described in Embodiment 1.

[0177] Example 4:

[0178] Embodiment 4 of this application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps described in Embodiment 1.

[0179] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, electronic devices, and computer-readable storage media described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0180] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the coupling or direct coupling or communication connection shown or discussed may be through some communication interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0181] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0182] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0183] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0184] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The scope of protection of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this application. Such modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of protection of the claims.

Claims

1. A method for deleting duplicate-identified cell electrode endpoints, characterized in that, include: Identify the electrode endpoints of each electrode of the battery cell to be tested from an image of the battery cell containing the battery cell to be tested; The types of electrode endpoints include positive electrode endpoint types and negative electrode endpoint types; For each type of electrode endpoint, based on the offset distance between each electrode endpoint of that type and the center reference line, electrode endpoints with an offset distance greater than a preset offset distance are deleted, so that the remaining electrode endpoints are used as the first electrode endpoints of that type; the center reference line is perpendicular to each electrode. The distance between the center reference line and its parallel target reference line is the average of the distances between the endpoints of each of the electrodes of this type and the target reference line; For each type of first electrode endpoint, based on the endpoint spacing distance between each first electrode endpoint of that type in the first direction, first electrode endpoints with an endpoint spacing distance less than the standard endpoint spacing distance are deleted, so that the remaining first electrode endpoints are used as the target electrode endpoints of that type. The first direction is perpendicular to each electrode; The step of identifying the electrode endpoints of each electrode of the battery cell under test from a battery cell image containing the battery cell under test includes: Convert the battery cell image into a grayscale image; Using a pre-trained first recognition model, the electrode regions containing each of the electrodes are identified from the grayscale image; The electrode region is filtered to remove burrs, resulting in a filtered electrode region. Based on the position of the filtered electrode region in the grayscale image, the cell electrode image corresponding to the filtered electrode region is determined from the same position in the cell image; Using a pre-trained second recognition model, the electrode endpoints of each electrode are identified from the cell electrode image.

2. The method according to claim 1, characterized in that, Before identifying the electrode endpoints of each electrode of the battery cell to be tested from the battery cell image containing the battery cell to be tested, the method further includes: After obtaining the cell image of the cell to be tested, the average gray value of the cell image is calculated to determine whether the average gray value is greater than a preset gray value threshold. If the average gray value is greater than the preset gray value threshold, it indicates that the cell image contains the cell to be detected. If the average gray value is not greater than the preset gray value threshold, it means that the cell image does not contain the cell to be detected. The cell image of the cell to be detected is then re-acquired until the average gray value of the acquired cell image is greater than the preset gray value threshold.

3. The method according to claim 1, characterized in that, For each type of electrode endpoint, based on the offset distance between each electrode endpoint of that type and the center reference line, electrode endpoints with an offset distance greater than a preset offset distance are deleted, so that the remaining electrode endpoints are used as the first electrode endpoints of that type, including: Determine the position coordinates of each electrode endpoint in the cell image; the position coordinates include a first position coordinate value of the electrode endpoint in a first direction and a second position coordinate value in a second direction; the second direction is parallel to each electrode. For each type of electrode endpoint, the average coordinate value of all second position coordinate values ​​of that type is calculated based on the second position coordinate values ​​corresponding to each electrode endpoint of that type. The straight line corresponding to the average coordinate value is used as the center reference line. Based on the average coordinate value and a preset first fluctuation threshold, the fluctuation range with the center reference line as the fluctuation center line is calculated in the second direction. The length of the fluctuation range in the second direction is twice the preset offset distance. Remove the electrode endpoints whose second position coordinate values ​​are outside the fluctuation range from all electrode endpoints corresponding to this type, so that the remaining electrode endpoints are used as the first electrode endpoints of this type.

4. The method according to claim 3, characterized in that, For each type of first electrode endpoint, based on the endpoint spacing distance between the various first electrode endpoints of that type in a first direction, the first electrode endpoints with endpoint spacing distances smaller than the standard endpoint spacing distance are deleted, so that the remaining first electrode endpoints are used as the target electrode endpoints of that type, including: For each type, based on the first position coordinate values ​​corresponding to each first electrode endpoint of that type, the minimum coordinate value among all the first electrode endpoints of that type is selected, and the first electrode endpoint corresponding to the minimum coordinate value is used as the reference electrode endpoint, and the other first electrode endpoints besides the reference electrode endpoint are used as the second electrode endpoints. Based on the minimum coordinate value and the pre-set second fluctuation threshold, the standard endpoint interval distance corresponding to the endpoint of the reference electrode is calculated; Based on the first position coordinates of each second electrode endpoint and the minimum coordinates, the endpoint spacing distance between each second electrode endpoint and the reference electrode endpoint in the first direction is calculated; The second electrode endpoints whose endpoint spacing distance is less than the standard endpoint spacing distance are deleted to obtain the remaining second electrode endpoints. The remaining second electrode endpoints are used as new first electrode endpoints. The process continues to execute the first position coordinate values ​​corresponding to each first electrode endpoint of this type. The minimum coordinate value among all the first electrode endpoints of this type is selected, and the first electrode endpoint corresponding to the minimum coordinate value is used as the reference electrode endpoint. The other first electrode endpoints besides the reference electrode endpoint are used as second electrode endpoints and subsequent steps, until the number of remaining second electrode endpoints is less than or equal to 1. The reference electrode endpoints corresponding to each cycle are used as the target electrode endpoints corresponding to this type.

5. The method according to claim 1 or 4, characterized in that, The target electrode endpoint of the positive electrode endpoint type is a positive target electrode endpoint, and the target electrode endpoint of the negative electrode endpoint type is a negative target electrode endpoint. After obtaining each of the positive target electrode endpoints and each of the negative target electrode endpoints, the method further includes: Calculate the distance difference between the endpoints of the positive target electrode and the negative target electrode; The quality of the battery cell under test is determined based on the distance difference.

6. The method according to claim 1 or 4, characterized in that, After obtaining the target pole endpoints for each type, the process also includes: For each type of target electrode endpoint, determine the alignment between the individual target electrode endpoints of that type; Based on the alignment degree corresponding to each type, it is determined whether the battery cell to be tested is qualified.

7. A device for deleting duplicate-identified cell electrode endpoints, characterized in that, include: The identification module is used to identify the electrode endpoints of each electrode of the battery cell to be tested from a battery cell image containing the battery cell to be tested; The types of electrode endpoints include positive electrode endpoint types and negative electrode endpoint types; The first deletion module is used to delete, for each type of electrode endpoint, the electrode endpoints whose offset distance is greater than a preset offset distance according to the offset distance between each electrode endpoint of that type and the center reference line, so that the remaining electrode endpoints are used as the first electrode endpoints of that type; the center reference line is perpendicular to each electrode. The distance between the center reference line and its parallel target reference line is the average of the distances between the endpoints of each of the electrodes of this type and the target reference line; The second deletion module is used to delete first electrode endpoints whose endpoint spacing distance is less than the standard endpoint spacing distance for each type of first electrode endpoint, based on the endpoint spacing distance between each first electrode endpoint of that type in a first direction, so as to use the remaining first electrode endpoints as the target electrode endpoints of that type; the first direction is perpendicular to each electrode. When the identification module is used to identify the electrode endpoints of each electrode of the battery cell to be tested from an image containing the battery cell to be tested, it is specifically used for: Convert the battery cell image into a grayscale image; Using a pre-trained first recognition model, the electrode regions containing each of the electrodes are identified from the grayscale image; The electrode region is filtered to remove burrs, resulting in a filtered electrode region. Based on the position of the filtered electrode region in the grayscale image, the cell electrode image corresponding to the filtered electrode region is determined from the same position in the cell image; Using a pre-trained second recognition model, the electrode endpoints of each electrode are identified from the cell electrode image.

8. An electronic device, characterized in that, include: The device includes a processor, a memory, and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is in operation, the processor communicates with the memory via the bus, and the machine-readable instructions, when executed by the processor, perform the steps of the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the method as described in any one of claims 1 to 6.

Images