Battery cell detection method, device, storage medium and computer program product

Abstract

The present application discloses a method, device, storage medium and computer program product for detecting a battery cell. The method comprises: identifying a first area image where a battery cell pole piece is located from a battery cell cross-sectional image, wherein the first area image comprises a plurality of contours; filtering the plurality of contours of the first area image according to a first filtering threshold value to obtain a second area image including the pole piece contour, wherein the first filtering threshold value is determined by the pixel grayscale value of the first area image; identifying the cathode pole piece contour and the anode pole piece contour from the second area image according to the pole piece contour and the pixel grayscale in the second area image; detecting the spacing between adjacent cathode pole piece contours and anode pole piece contours to obtain the pole piece spacing. The scheme provided by the present application can improve the accuracy of the spacing between the cathode pole piece and the anode pole piece of the battery cell, thereby improving the accuracy of the battery cell defect detection.

Description

Technical Field

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

[0002] In order to improve battery performance, it is necessary to detect defects in the battery cells. For battery cells, if the distance between the corresponding adjacent cathode and anode plates is too large, it is easy to cause lithium deposition in the battery, thereby reducing battery performance and shortening battery life. It can be seen that detecting the distance between the adjacent cathode and anode plates of the battery cell and improving the detection accuracy of the distance between the cathode and anode plates are of great significance for defect detection of the battery cell. Summary of the invention

[0003] The present application provides a battery cell detection method, device, storage medium, computer program product, and device, which can improve the accuracy of the interval between the cathode electrode piece and the anode electrode piece of the battery cell, thereby improving the accuracy of battery cell defect detection.

[0004] In a first aspect, the present application provides a battery cell detection method, the method comprising: identifying a first area image where a battery cell pole piece is located from a battery cell cross-sectional image, the first area image comprising a plurality of contours; filtering the plurality of contours of the first area image according to a first filtering threshold to obtain a second area image comprising pole piece contours, wherein the first filtering threshold is determined by a pixel grayscale value of the first area image; identifying a cathode pole piece contour and an anode pole piece contour from the second area image respectively according to the pole piece contours and pixel grayscales in the second area image; detecting the spacing between adjacent cathode pole piece contours and anode pole piece contours to obtain a pole piece spacing.

[0005] In an embodiment of the present application, the cross-sectional image of the battery cell is filtered by image filtering to obtain a second area image containing only the cathode electrode piece and the anode electrode piece, thereby reducing the influence of other parts in the original cross-sectional image on the detection result and improving the accuracy of the detection result.

[0006] In addition, in an embodiment of the present application, the cathode pole piece contour and the anode pole piece contour are automatically extracted from the second area image, and the interval between the cathode pole pieces and the anode pole pieces of adjacent layers is automatically detected, thereby eliminating the need for manual extraction, reducing the risk of false detection and missed detection in manual detection of pole pieces, and improving the accuracy of battery cell detection.

[0007] It can be seen that the solution provided in the embodiment of the present application can improve the accuracy of the interval between the cathode electrode piece and the anode electrode piece of the battery cell, thereby improving the accuracy of battery cell defect detection.

[0008] In some embodiments, identifying a first area image where a cell pole piece is located from a cell cross-sectional image includes: filtering the cell cross-sectional image by a second filtering threshold to obtain a third area image containing multiple contours, wherein the second filtering threshold is determined by the pixel grayscale value of the cell cross-sectional image; determining a circumscribed graphic of the contours contained in the third area image; processing the cell cross-sectional image according to a first preset condition and the circumscribed graphic of the contours contained in the third area image to obtain a first area image containing the cell pole piece, wherein the first preset condition is determined according to the size of the circumscribed graphic.

[0009] By adopting threshold filtering, the first area image containing the battery cell pole pieces is identified from the battery cell cross-sectional image to filter out the data of the non-battery cell part in the battery cell cross-sectional image, thereby reducing the influence of the non-battery cell part data on the detection result, thereby improving the detection accuracy of the battery cell pole piece interval.

[0010] In some embodiments, before filtering the battery cell cross-section image through the second filtering threshold to obtain a third area image containing a contour, image convolution is performed on the battery cell cross-section image through the first convolution kernel to obtain first contour data corresponding to the battery cell cross-section image; the pixel grayscale standard deviation corresponding to the first contour data is calculated; when the first coefficient is greater than a preset first standard deviation threshold, the first coefficient is determined as the second filtering threshold, wherein the first coefficient is the product of a preset first standard deviation coefficient and the pixel grayscale standard deviation; when the first coefficient is less than or equal to the first standard deviation threshold, the first standard deviation threshold is determined as the second filtering threshold.

[0011] Since the second filtering threshold adaptively changes according to the different cross-sectional images of the battery cell, that is, in the embodiment of the present application, a filtering threshold adapted to the cross-sectional image of the battery cell is used to filter the cross-sectional image of the battery cell, therefore, the above-mentioned scheme can improve the accuracy of image filtering and provide a basis for accurate detection of the spacing between battery cell pole pieces.

[0012] In some embodiments, when the battery cell is a wound battery cell, the battery cell cross-sectional image is processed according to the first preset condition and the circumscribed graphics of the contour contained in the third area image to obtain a first area image containing the battery cell pole piece, including: filtering out the contour of the circumscribed graphics that meets the first preset condition from the third area image to obtain multiple pole piece contours; obtaining a first target pole piece contour with the largest circumscribed graphics area from the multiple pole piece contours; and cropping out the area where the first target circumscribed graphics is located from the battery cell cross-sectional image to obtain the first area image, wherein the first target circumscribed graphics is the circumscribed graphics determined by the first target pole piece contour.

[0013] By determining the external graphics corresponding to the pole piece contour and using the external graphics to crop the battery cell cross-sectional graphics, the non-battery cell part is filtered out to obtain the first area image where the battery cell pole piece is located, thereby reducing the influence of the non-battery cell part on the battery cell detection results and providing a basis for the accurate detection of the battery cell pole piece interval.

[0014] In some embodiments, after obtaining the first target pole piece contour with the largest external graphic area from multiple pole piece contours, the external graphic of the first target pole piece contour is expanded in area to obtain the first target external graphic, so that the first target external graphic can accommodate all battery cell pole pieces, ensuring that all battery cell pole pieces can be tested for pole piece spacing.

[0015] In some embodiments, the first preset condition includes at least one of the following: the size of the circumscribed figure of the pole piece contour in the first direction is smaller than a first value, wherein the first value is determined by the physical properties of the battery cell and the magnification of the image acquisition device in the first direction; the size of the circumscribed figure of the pole piece contour in the second direction is smaller than a second value, wherein the first direction is perpendicular to the second direction, the first direction is the extension direction of the pole piece, and the second value is determined by the physical properties of the battery cell and the magnification of the image acquisition device in the second direction; the difference between the size of the circumscribed figure of the pole piece contour in the first direction and the size of the battery cell cross-sectional image in the first direction is smaller than a third value, wherein the third value Determined by the physical properties of the battery cell and the magnification of the image acquisition device in the first direction; the ratio of the size of the circumscribed figure of the pole piece contour in the first direction to the size of the battery cell cross-sectional image in the first direction is less than the first target ratio; when the size of the circumscribed figure of the pole piece contour in the second direction is less than a fourth value, the size ratio of the circumscribed figure of the pole piece contour is less than the second target ratio, wherein the size ratio of the circumscribed figure of the pole piece contour is the ratio of the size of the circumscribed figure of the pole piece contour in the first direction to the size in the second direction, the first target ratio is less than the second target ratio, and the fourth value is determined by the physical properties of the battery cell and the magnification of the image acquisition device in the second direction.

[0016] The above-mentioned first preset condition is used to screen the external graphics of the contour in the third area image, so as to retain the first target external graphics that can accommodate all battery cell pole pieces, ensuring that all battery cell pole pieces can be detected for pole piece spacing, thereby improving the integrity of the battery cell pole piece spacing detection and reducing the risk of missed detection.

[0017] In some embodiments, the first area image is filtered according to a first filtering threshold to obtain a second area image containing a pole piece contour, including: rotating the first area image with the pole piece center point of the first area image as the rotation center to obtain a rotated first area image, wherein the pole piece center point is the center point of the pole piece contour with the smallest circumscribed graphic area in the first area image; filtering the rotated first area image by the first filtering threshold to obtain a filtered first area image; capturing the filtered first area image within a preset angle range determined by the pole piece center point to obtain a fourth area image; filtering the fourth area image by the circumscribed graphic of the contour contained in the fourth area image to obtain a second area image.

[0018] By rotating the first area image, each area to be processed in the first area image is parallel to the first direction and within the preset angle range determined by the center point of the pole piece, so that all areas to be processed in the first area image have the same filtering parameters, ensuring the same filtering effect on the anode and cathode poles at different angles in the first area image, thereby improving the accuracy of the detection of the contours of the anode and cathode poles, and further improving the detection accuracy of the interval between the pole pieces of the battery cell.

[0019] In some embodiments, the battery cell detection method also includes: performing image convolution on the battery cell cross-sectional image through a second convolution kernel to obtain second contour data; filtering the battery cell cross-sectional image through a third filtering threshold to obtain a fifth area image, wherein the third filtering threshold is determined by the second contour data; cropping an image corresponding to a target cropping area from the fifth area image to obtain a cropped fifth area image, wherein the target cropping area is a cropping range determined by a center line of the fifth area image; identifying a pole piece contour with the smallest circumscribed graphic area from the cropped fifth area image to obtain a second target pole piece contour; and determining the intersection of the center line of the fifth area image and the second target pole piece contour as the pole piece center point.

[0020] By confirming the center point of the pole piece and then rotating the first area image with the pole piece center point, each area in the first area image has the same filtering parameters and filtering effect, thereby improving the accuracy of positive and negative pole piece contour detection, and thus improving the detection accuracy of the battery cell pole piece interval.

[0021] In some embodiments, the cathode pole piece contour and the anode pole piece contour are respectively identified from the second area image based on the pole piece contour and the pixel grayscale in the second area image, including: identifying the pole piece contour of the external graphic that meets the second preset condition from the second area image to obtain the cathode pole piece contour; filtering the second area image based on a target grayscale threshold to obtain a processed second area image, wherein the target grayscale threshold is determined by the pixel grayscale value in the second area image; using the cathode pole piece contour as a mask to extract the anode pole piece contour from the processed second area image.

[0022] By identifying the cathode electrode contour from the second area image by means of an external graphic, and then extracting the anode electrode contour from the second area image based on the cathode electrode contour and the pixel grayscale value, the accuracy of the extraction of the positive and negative electrodes can be improved, thereby improving the accuracy of the detection of the positive and negative electrode intervals.

[0023] In some embodiments, a pole piece contour whose circumscribed graphic satisfies a second preset condition is identified from the second area image to obtain a cathode pole piece contour, including: obtaining the target coordinates in the first direction and the graphic width of the target point of the circumscribed graphic of each pole piece contour contained in the second area image, wherein the graphic width is the size of the circumscribed graphic of the pole piece contour in the second direction, and the first direction is perpendicular to the second direction; calculating the sum of the target coordinates and the graphic width to obtain the target width corresponding to each pole piece contour; sorting all pole piece contours in the first area image based on the target width corresponding to each pole piece contour to obtain a contour sequence; extracting the cathode pole piece contour that satisfies the second preset condition from the first area image based on the contour sequence and the contour area corresponding to each pole piece contour in the first area image.

[0024] By screening the pole piece contour through the external graphics corresponding to the pole piece contour, the accuracy of cathode pole piece identification can be improved, and then the accuracy of anode and cathode pole piece contour identification can be improved, providing a basis for the subsequent accurate detection of the anode and cathode pole piece interval.

[0025] In some embodiments, based on the contour sequence and the contour area corresponding to each pole piece contour in the first area image, a cathode pole piece contour that meets the second preset condition is extracted from the first area image, including: removing the first pole piece contour and the last two pole piece contours in the contour sequence to obtain an updated contour sequence; removing the pole piece contour whose contour area meets the second preset condition from the updated contour sequence to obtain the cathode pole piece contour; wherein the pole piece contour that meets the second preset condition includes any of the following items: a pole piece contour whose contour area difference corresponding to the contour group is greater than the first area and is located at the front of the contour group, wherein the contour group includes two adjacent pole piece contours in the updated contour sequence; a pole piece contour whose contour area difference between two adjacent contour groups is greater than the second area, and the pole piece contour shared by the two adjacent contour groups, wherein the first area is greater than the second area.

[0026] The pole piece contour in the first region image is filtered by the contour area corresponding to the pole piece contour, so as to obtain the cathode pole piece contour, which can improve the extraction accuracy of the cathode pole piece contour.

[0027] In some embodiments, detecting the spacing between adjacent cathode pole piece contours and anode pole piece contours to obtain the pole piece spacing includes: obtaining a ray diagram, wherein the ray diagram contains a plurality of rays, and the rays are perpendicular to the tangent direction of the pole piece contour, or perpendicular to the extension direction of the pole piece contour; determining a cathode pole piece coordinate set of the cathode pole piece contour according to the intersection of the same ray of the ray diagram with the cathode pole piece contour; determining an anode pole piece coordinate set of the anode pole piece contour according to the intersection of the same ray of the ray diagram with the anode pole piece contour; and determining the pole piece spacing between adjacent cathode pole piece contours and anode pole piece contours according to the cathode pole piece coordinate set and the anode pole piece coordinate set.

[0028] By setting the ray diagram, the intersection coordinates of the positive and negative electrodes on the same ray can be obtained, which is convenient for the subsequent calculation of the electrode spacing between adjacent positive and negative electrodes and can improve the detection accuracy of the electrode spacing.

[0029] In some embodiments, the pole piece interval between adjacent cathode pole piece contours and anode pole piece contours is determined based on a cathode pole piece coordinate set and an anode pole piece coordinate set, including: sorting the coordinates in the cathode pole piece coordinate set and the anode pole piece coordinate set according to the positional relationship of the intersection points in the second area image to obtain a target coordinate sequence; and determining the pole piece interval based on the interval between two adjacent coordinates in the target coordinate sequence.

[0030] By sorting the coordinates in the cathode and anode electrode coordinate sets, the electrode spacing between adjacent cathode and anode electrodes can be calculated based on the sorting results, thereby reducing the risk of false detection and missed detection of the electrode spacing, thereby improving the detection accuracy of the electrode spacing.

[0031] In some embodiments, when the battery cell is a stacked battery cell, the contours of the external graphics in the battery cell cross-sectional image that meet the first preset condition are filtered out to obtain a first area image containing the battery cell pole pieces, including: filtering out the contours of the external graphics in the battery cell cross-sectional image that meet the first preset condition to obtain multiple pole piece contours; merging the external graphics of the multiple contours according to the sizes and / or positions of the external graphics corresponding to the multiple contours to obtain second target external graphics corresponding to the multiple contours; and cropping the area where the second target external graphics is located from the battery cell cross-sectional image to obtain the first area image.

[0032] The first area image containing only the cell pole pieces is extracted by using a method for extracting the cell pole piece area corresponding to the laminated cell, which provides a basis for the subsequent accurate detection of the pole piece interval of the laminated cell.

[0033] In the second aspect, the present application also provides a battery cell detection device, which includes: a region identification module, used to identify a first region image where a battery cell pole piece is located from a battery cell cross-sectional image, the first region image including multiple contours; a filtering module, used to filter the multiple contours of the first region image according to a first filtering threshold value to obtain a second region image including the pole piece contour, wherein the first filtering threshold value is determined by the pixel grayscale value of the first region image; a pole piece identification module, used to identify the cathode pole piece contour and the anode pole piece contour from the second region image according to the pole piece contour and the pixel grayscale in the second region image; an interval detection module, used to detect the spacing between adjacent cathode pole piece contours and anode pole piece contours to obtain the pole piece interval.

[0034] In a third aspect, the present application provides a readable storage medium having computer program instructions stored thereon, and when the computer program instructions are executed by a processor, the battery cell detection method as described in the first aspect is implemented.

[0035] In a fourth aspect, the present application provides a computer program product. When instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the battery cell detection method as described in the first aspect.

[0036] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The features, advantages and technical effects of exemplary embodiments of the present application will be described below with reference to the accompanying drawings.

[0038] Figure 1 This is a flow chart of a battery cell detection method according to an embodiment of the present application;

[0039] Figure 2 A schematic diagram of a cross-sectional image of a wound battery cell according to an embodiment of the present application;

[0040] Figure 3 A schematic diagram of a first region image according to an embodiment of the present application;

[0041] Figure 4 A schematic diagram of a second region image according to an embodiment of the present application;

[0042] Figure 5 A schematic diagram of a cathode electrode image according to an embodiment of the present application;

[0043] Figure 6 A schematic diagram of a third region image according to an embodiment of the present application;

[0044] Figure 7 A schematic flow chart of a method for determining a second filtering threshold value according to an embodiment of the present application;

[0045] Figure 8 A schematic diagram of a first target external graphic according to an embodiment of the present application;

[0046] Fig. 9 A schematic diagram of a filtered first region image according to an embodiment of the present application;

[0047] Fig.10 A schematic diagram of a fourth region image according to an embodiment of the present application;

[0048] Fig.11 A schematic diagram of a flow chart of a method for determining a pole piece center point according to an embodiment of the present application;

[0049] Fig.12 A schematic diagram of a cropped fifth region image according to an embodiment of the present application;

[0050] Fig.13 A schematic diagram of a cathode electrode profile according to an embodiment of the present application;

[0051] Fig.14 A schematic diagram of the outline of an anode electrode sheet according to an embodiment of the present application;

[0052] Fig.15 A schematic diagram of the intersection of a laminated battery core and a ray diagram according to an embodiment of the present application;

[0053] Fig.16 A schematic diagram of a process of acquiring a first region image according to an embodiment of the present application;

[0054] Fig.17 This is a schematic diagram of a battery cell detection device according to another embodiment of the present application.

[0055] In the drawings, the drawings are not necessarily drawn to scale. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0057] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0058] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0059] Mentioning "embodiment" in the embodiments of the present application means that the specific features, structures or characteristics described in conjunction with the embodiment may be included in at least one embodiment of the present application. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiment described in the embodiments of the present application can be combined with other embodiments.

[0060] In the description of the embodiments of the present application, the term "and / or" is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0061] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0062] In the description of the embodiments of the present application, the technical terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, which are only for the convenience of describing the embodiments of the present application and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the embodiments of the present application.

[0063] In the description of the embodiments of the present application, unless otherwise clearly specified and limited, technical terms such as "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the internal connection of two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0064] In the production process of lithium batteries, it is necessary to inspect the appearance and internal structure of the lithium battery cells. In the defect inspection of the cells, if the interval between the adjacent anode and cathode plates in the cell is greater than the specified value, the cell is prone to lithium deposition, and lithium deposition will cause the appearance of metallic lithium inside the battery, which will not only reduce the performance of the battery, but also limit the battery capacity, significantly shorten the battery life, and cause safety hazards for lithium batteries. In severe cases, it may even cause major safety accidents such as battery short circuit and explosion.

[0065] In the related art, a fast CT (Computed Tomography) device is used to obtain a CT cross-sectional image of a large surface of a battery, and then the measurement function of the software provided on the CT device is used to manually calculate the intervals between adjacent anode and cathode plates.

[0066] In this method, the accuracy of the test results obtained by manual calculation is low, and the test personnel for each test may be different, resulting in differences in the test results for each test. The consistency of the test results is poor, and it is impossible to measure strictly in the prescribed direction. There is a large degree of subjectivity in human measurement. Moreover, as the number of tests increases, the number of test personnel required also increases, which increases the cost of battery cell testing.

[0067] In response to the problems existing in the related technologies, the embodiments of the present application provide a battery cell detection method, device, storage medium and computer program product. Among them, the battery cell detection method provided in the embodiments of the present application pre-processes the battery cell cross-sectional image, and based on technical means such as adaptive local threshold filtering, grayscale threshold and pole piece contour extraction, processes the battery cell cross-sectional image into a regional image containing only the anode and cathode pole pieces, and then calculates the pole piece spacing between the anode and cathode pole pieces in the regional image based on rays at different angles, thereby realizing automatic detection of the battery cell pole piece spacing without manual calculation, thereby improving the accuracy and detection efficiency of the battery cell pole piece spacing detection.

[0068] The following is an introduction to the battery cell detection method provided in the embodiments of the present application.

[0069] In one embodiment, Figure 1 The flowchart of the battery cell detection method is shown. The method can be applied to a battery cell detection system. The battery cell detection system may include an image acquisition device for acquiring a battery cell cross-sectional image and a host computer. The host computer may process (for example, filter) the battery cell cross-sectional image acquired by the image acquisition device, and identify the cathode and anode plates in the processed battery cell cross-sectional image, and then detect the interval between adjacent cathode and anode plates. Figure 1 As shown, the method may include the following steps S101 to S104:

[0070] Step S101 , identifying a first region image where a cell electrode piece is located from a cell cross-sectional image.

[0071] In step S101, the battery cell may be a wound battery cell or a laminated battery cell. The battery cell cross-sectional image may be a cross-sectional image of a large surface of the battery cell, for example, Figure 2 It is a cross-sectional image of a wound cell, such as Figure 2 As shown, the cross-sectional image of the battery cell includes not only the battery cell but also non-battery cell structures, such as the battery casing, etc. In order to improve the accuracy of battery cell detection, in the embodiment of the present application, the host computer removes the portion other than the battery cell from the cross-sectional image of the battery cell and extracts the first region image including the battery cell. Figure 2 The cell cross-section image shown in the figure can be used to identify the cell, and the Figure 3 The first region image is shown. Figure 3 As shown, the first region image includes multiple contours, including the contour of the battery cell anode electrode piece, the contour of the battery cell cathode electrode piece, and the contour of the battery shell.

[0072] It should be noted that in step S101, the battery cell cross-sectional image may be a CT image. In this scenario, the image acquisition device may be a CT device, that is, the battery cell cross-sectional image may be obtained by scanning the battery through the CT device to achieve non-destructive testing of the battery cell.

[0073] In addition, it should be noted that, in step S101, the host computer may filter the cell cross-section image by means of adaptive threshold filtering to obtain the first region image.

[0074] Step S102 , filtering the multiple contours of the first region image according to the first filtering threshold value to obtain a second region image including the pole piece contour.

[0075] In step S102, the first filtering threshold is determined by the pixel grayscale value of the first area image, wherein the first area image is an image of the area where the battery cells are located, that is, the first filtering threshold is adaptively obtained based on the first area image and is not a fixed value. By filtering the first area image using the first filtering threshold that matches the first area image, the pole piece contour can be more accurately identified, providing a basis for the subsequent accurate detection of the pole piece interval.

[0076] In step S102, the non-pole piece contours in the first region image are filtered out using the first filtering threshold, thereby obtaining a second region image containing only the pole piece contours. Figure 3 The first region image shown in FIG. 1 is filtered to obtain a second region image containing only the pole piece contour, such as Figure 4 shown.

[0077] Step S103 , identifying the cathode pole piece contour and the anode pole piece contour from the second region image respectively according to the pole piece contour and the pixel grayscale in the second region image.

[0078] In step S103, the host computer can Figure 4 The second area image shown in FIG. 1 is used to calculate the pole piece contour, and the preset cathode pole piece screening rule is used to select the cathode pole piece from the cathode pole piece. Figure 4 The cathode electrode contour is identified in the second area image shown in FIG. Figure 5 The cathode electrode piece image including the cathode electrode piece outline is shown. Then, the second region image is grayscale filtered using the average value of the pixel grayscale of the second region image as a threshold, and then the cathode electrode piece image is used as a mask to extract the anode electrode piece from the grayscale filtered second region image.

[0079] Step S104, detecting the distance between the adjacent cathode pole piece contours and anode pole piece contours to obtain the pole piece spacing.

[0080] After the cathode electrode piece contour and the anode electrode piece contour are identified through steps S101 to S104, a ray diagram can be set to multiply the ray diagram with the cathode electrode piece image to obtain the intersection coordinates of each cathode electrode piece with the rays in the ray diagram. At the same time, the ray diagram can be multiplied with the anode electrode piece image to obtain the intersection coordinates of each anode electrode piece with the rays in the ray diagram. The electrode piece spacing between adjacent cathode and anode electrode pieces can be determined by the intersection coordinates corresponding to the cathode electrode piece and the intersection coordinates corresponding to the anode electrode piece.

[0081] Based on the scheme defined by the above steps S101 to S104, it can be known that in the embodiment of the present application, the cross-sectional image of the battery cell is filtered by image filtering, so as to obtain a second area image containing only the cathode electrode piece and the anode electrode piece, thereby reducing the influence of other parts in the original cross-sectional image on the detection results and improving the accuracy of the detection results.

[0082] In addition, in an embodiment of the present application, the cathode pole piece contour and the anode pole piece contour are automatically extracted from the second area image, and the interval between the cathode pole pieces and the anode pole pieces of adjacent layers is automatically detected, thereby eliminating the need for manual extraction, reducing the risk of false detection and missed detection in manual detection of pole pieces, and improving the accuracy of battery cell detection.

[0083] It can be seen that the solution provided in the embodiment of the present application can improve the accuracy of the interval between the cathode electrode piece and the anode electrode piece of the battery cell, thereby improving the accuracy of battery cell defect detection.

[0084] The following is an introduction to the implementation process of the method provided in the embodiment of the present application.

[0085] The battery cell cross-sectional image captured by the image acquisition device may include not only the battery cell but also the battery casing and other non-battery structures. Therefore, after obtaining the battery cell cross-sectional image captured by the image acquisition device, the host computer needs to identify the ROI (Region of Interest) where the battery cell pole piece is located from the battery cell cross-sectional image, that is, the first regional image.

[0086] In one embodiment, the host computer first filters the battery cell cross-sectional image through a second filtering threshold to obtain a third area image containing multiple contours; then, determines the circumscribed graphics of the contours contained in the third area image; and then processes the battery cell cross-sectional image according to the first preset condition and the circumscribed graphics of the contours contained in the third area image to obtain a first area image containing the battery cell pole pieces.

[0087] In the above embodiment, the host computer can filter the cross-sectional image of the battery cell by using an adaptive local threshold filtering method, wherein the second filtering threshold used in the adaptive local threshold filtering method can be determined by the pixel grayscale value of the cross-sectional image of the battery cell. By filtering the cross-sectional image of the battery cell by using the second filtering threshold, a third region image containing only the contour can be obtained. For example, Figure 2 The cell cross-section image shown in the figure is filtered to obtain Figure 6 The third region image is shown.

[0088] Depend on Figure 6 It can be seen that the third region image includes not only the contours of the cell pole pieces, but also other contours, such as the contour of the battery shell. The detection of the cell pole piece interval is mainly to detect the cell pole pieces. Therefore, it is necessary to determine the area where the cell pole pieces are located based on the distribution of the contours in the third region image, and then identify the first image area where the cell pole pieces are located from the cell cross-sectional image.

[0089] In the embodiment of the present application, the host computer determines it by means of a contour circumscribed graphic, wherein the contour circumscribed graphic may be a minimum circumscribed rectangle corresponding to the contour, and the first preset condition may be determined according to the size of the circumscribed graphic.

[0090] By adopting threshold filtering, the first area image containing the battery cell pole pieces is identified from the battery cell cross-sectional image to filter out the data of the non-battery cell part in the battery cell cross-sectional image, thereby reducing the influence of the non-battery cell part data on the detection result, thereby improving the detection accuracy of the battery cell pole piece interval.

[0091] In one embodiment, the second filtering threshold can be Figure 7 The method shown is to determine, Figure 7 As shown, the method for determining the second filtering threshold comprises the following steps:

[0092] Step S701, performing image convolution on the battery cell cross-section image using a first convolution kernel to obtain first contour data corresponding to the battery cell cross-section image;

[0093] Step S702, calculating the pixel grayscale standard deviation corresponding to the first contour data;

[0094] Step S703, when the first coefficient is greater than a preset first standard deviation threshold, determining the first coefficient as a second filtering threshold, wherein the first coefficient is a product of a preset first standard deviation coefficient and a pixel grayscale standard deviation;

[0095] Step S704: when the first coefficient is less than or equal to the first standard deviation threshold, determine the first standard deviation threshold as the second filtering threshold.

[0096] In the above steps S701 to S704, the first convolution kernel can be a convolution kernel along the horizontal direction, and its corresponding convolution kernel size can be 51*1. In the embodiment of the present application, the host computer traverses all pixels in the cross-sectional image of the battery cell with the above-mentioned first convolution kernel, and calculates the pixel grayscale standard deviation stdValue of the 51 pixel grayscales in each convolution kernel, and sets the first standard deviation coefficient StdDevScale to 0.3, the minimum standard deviation threshold (ie, the first standard deviation threshold) AbsThreshold to 1.0, and calculates the second filtering threshold by formula (1):

[0097] (1)

[0098] In formula (1), is the second filtering threshold, is the first standard deviation coefficient, is the pixel grayscale standard deviation, is the first standard deviation threshold; is the first coefficient.

[0099] In formula (1), the first standard deviation threshold and the first standard deviation coefficient can be set by the inspection personnel according to actual needs.

[0100] In step S701 to step S704, the first convolution kernel uses a larger convolution kernel, and there is no need to retain all the details in the battery cell cross-sectional image. Only the approximate outline of the battery cell pole piece in the battery cell cross-sectional image needs to be retained to identify the ROI where the battery cell pole piece is located.

[0101] It should be noted that, through steps S701 to S704, it can be seen that in the embodiment of the present application, the second filtering threshold is not fixed, but adaptively changes according to the different cross-sectional images of the battery cell. That is, in the embodiment of the present application, the cross-sectional image of the battery cell is filtered using a filtering threshold that is compatible with the cross-sectional image of the battery cell. This can improve the accuracy of image filtering and provide a basis for accurate detection of the spacing between battery cell pole pieces.

[0102] Further, after obtaining the second filtering threshold, the host computer uses the second filtering threshold to filter the cross-sectional image of the battery cell, thereby obtaining Figure 6 The third region image is shown. In the filtering process, the current pixel gray value in the cell cross-section image is recorded as pointGray, and the average value of the pixel gray in the first convolution kernel is average. Then the host computer can filter the pixels in the cell cross-section image by formula (2):

[0103] (2)

[0104] Furthermore, in order to obtain Figure 6After the third area image is shown, the host computer performs global trajectory calculation on the third area image to determine the circumscribed graphics corresponding to each contour in the third area image. For example, the host computer can use the findContours function in the opencv image library to perform global contour detection on the entire third area image to obtain the minimum circumscribed rectangle corresponding to each contour.

[0105] Furthermore, the host computer processes the third region image according to the first preset condition and the external graphics of the contour contained in the third region image to obtain a first region image containing the cell pole piece. Among them, for different types of cells, the host computer can use different methods to filter out the contours that do not meet the first preset condition in the cell cross-sectional image, thereby obtaining an ROI (i.e., the first region image) containing only the cell pole piece. In the embodiments of the present application, wound cells and laminated cells are introduced respectively.

[0106] For a wound battery cell, the host computer can filter out the contours of the external graphics that meet the first preset condition from the third area image to obtain multiple pole piece contours; then, obtain the first target pole piece contour with the largest external graphics area from the multiple pole piece contours; and then, crop the area where the first target external graphics is located from the battery cell cross-sectional image to obtain the first area image, wherein the first target external graphics is the external graphics determined by the first target pole piece contour.

[0107] Since the battery cell is a wound battery cell, the circumscribed pattern corresponding to the outline of the outermost electrode piece of the wound battery cell can surround the entire battery cell electrode piece, that is, the area surrounded by the circumscribed pattern with the largest area is the first area image.

[0108] In an embodiment of the present application, the host computer can use the third region image obtained by filtering to perform global trajectory calculation, delete image noise that does not belong to the battery cell part, and retain the outermost pole piece contour of the battery cell (i.e., the first target pole piece contour), without requiring whether other pole piece contours of the battery cell pole piece are retained. In one example, the pole piece contour with the largest span in the first direction and the second direction can be determined as the first target pole piece contour, and the first target pole piece contour is usually the anode pole piece contour of the outermost layer of the battery cell pole piece. The above-mentioned first direction and the second direction are mutually perpendicular directions. For example, the first direction is the X direction of the battery cell cross-sectional image, and the second direction is the Y direction of the battery cell cross-sectional image.

[0109] After determining the first target pole piece contour, the first target circumscribed figure can be obtained by obtaining the minimum circumscribed rectangle corresponding to the first target pole piece contour, for example, Figure 6 The first target external graphic corresponding to the third area image shown is as follows Figure 8 Cut out the area image corresponding to the first target external figure from the cross-sectional image of the battery cell, and you can get the following: Figure 3The first area image is shown.

[0110] It should be noted that by determining the external graphic corresponding to the pole piece contour and using the external graphic to crop the battery cell cross-sectional graphic, the non-battery cell part is filtered out to obtain the first area image where the battery cell pole piece is located, thereby reducing the influence of the non-battery cell part on the battery cell detection results, and providing a basis for the accurate detection of the battery cell pole piece interval.

[0111] In addition, in order to reduce the inaccuracy in the recognition of the pole piece contour, which causes the external graphics of the pole piece contour to be unable to accommodate all the battery cell pole pieces, therefore, after obtaining the first target pole piece contour with the largest external graphics area from the multiple pole piece contours, the external graphics of the first target pole piece contour are expanded in area to obtain the first target external graphics, so that the first target external graphics can accommodate all the battery cell pole pieces, ensuring that the pole piece intervals of all battery cell pole pieces can be detected.

[0112] As an example, after obtaining the minimum circumscribed figure corresponding to the first target pole piece contour, the minimum circumscribed figure corresponding to the first target pole piece contour is expanded in the first direction and the second direction respectively. For example, in the X direction, the minimum circumscribed figure corresponding to the first target pole piece contour is expanded by A pixels; in the Y direction, the minimum circumscribed figure corresponding to the first target pole piece contour is expanded by B pixels to expand the area of ​​the minimum circumscribed figure corresponding to the first target pole piece contour.

[0113] In one embodiment, the first preset condition includes at least one of the following:

[0114] The size of the circumscribed figure of the pole piece contour in the first direction is smaller than a first value, wherein the first value is determined by the physical properties of the battery cell and the magnification of the image acquisition device in the first direction, for example, the length of the circumscribed rectangle of the pole piece contour in the X direction is smaller than 3 pixels;

[0115] The size of the circumscribed figure of the pole piece contour in the second direction is smaller than the second value, wherein the first direction and the second direction are perpendicular to each other, the first direction is the extension direction of the pole piece, and the second value is determined by the physical properties of the battery cell and the magnification of the image acquisition device in the second direction; for example, the length of the circumscribed rectangle of the pole piece contour in the Y direction is smaller than 3 pixels;

[0116] The difference between the size of the circumscribed figure of the pole piece contour in the first direction and the size of the cross-sectional image of the battery cell in the first direction is less than a third value, wherein the third value is determined by the physical properties of the battery cell and the magnification of the image acquisition device in the first direction. For example, the length of the circumscribed rectangle of the pole piece contour in the X direction is less than 3 pixels from the length of the cross-sectional image of the battery cell in the X direction;

[0117] The ratio of the size of the circumscribed figure of the pole piece contour in the first direction to the size of the cell cross-sectional image in the first direction is smaller than the first target ratio. For example, the length of the circumscribed rectangle of the pole piece contour in the Y direction is smaller than 1 / 4 of the length of the cell cross-sectional image in the Y direction.

[0118] When the size of the circumscribed figure of the pole piece contour in the second direction is smaller than the fourth value, the size ratio of the circumscribed figure of the pole piece contour is smaller than the second target ratio, wherein the size ratio of the circumscribed figure of the pole piece contour is the ratio of the size of the circumscribed figure of the pole piece contour in the first direction to the size in the second direction, the first target ratio is smaller than the second target ratio, and the fourth value is determined by the physical properties of the battery cell and the magnification of the image acquisition device in the second direction; for example, the length of the circumscribed rectangle of the pole piece contour in the Y direction is less than 300 pixels, and the ratio of the length of the circumscribed rectangle in the X direction to the length in the Y direction is less than 2.

[0119] It should be noted that the first value, the second value, the third value, the fourth value, the first target ratio, and the second target ratio mentioned above can be determined according to actual experience.

[0120] The above-mentioned first preset condition is used to screen the external graphics of the contour in the third area image, so as to retain the first target external graphics that can accommodate all battery cell pole pieces, ensuring that all battery cell pole pieces can be detected for pole piece spacing, thereby improving the integrity of the battery cell pole piece spacing detection and reducing the risk of missed detection.

[0121] After the first region image is identified from the cell cross-sectional image through the above process, the host computer needs to filter the first region image using a first filtering threshold to obtain a second region image containing only the pole piece contour.

[0122] In one embodiment, when the battery cell is a wound battery cell, the host computer rotates the first area image with the pole piece center point of the first area image as the rotation center to obtain a rotated first area image; then, the rotated first area image is filtered by a first filtering threshold to obtain a filtered first area image; the filtered first area image is captured within a preset angle range determined by the pole piece center point to obtain a fourth area image; finally, the fourth area image is filtered by an circumscribed graphic of the contour contained in the fourth area image to obtain a second area image.

[0123] In the above embodiment, the pole piece center point of the first region image is the center point of the pole piece contour with the smallest circumscribed graphic area in the first region image. For example, for a wound battery cell, the pole piece center point is the center point of the innermost circle pole piece.

[0124] In one example, the host computer can use the warpAffine function in the opencv image library to rotate the first region image with the center point of the pole piece as the rotation center and a preset measurement angle (for example, 20° to 70°, -20° to -70°) as the rotation angle. Then, the rotated first region image is filtered using the first filtering threshold, for example, Figure 3 The first region image shown is rotated, and then the rotated first region image is filtered to obtain Fig. 9 The filtered image of the first region is shown.

[0125] It should be noted that the method for determining the above-mentioned first filter threshold is the same as the method for determining the second filter threshold, and the only difference is that the filter parameters are different. In an embodiment of the present application, the size of the convolution kernel used by the first filter threshold is smaller than the size of the first convolution kernel. For example, the size of the first convolution kernel is 51*1, and the size of the convolution kernel corresponding to the first filter threshold is 11*1, so as to retain more details of the battery cell pole piece and ensure the integrity of the battery cell pole piece contour, so as to improve the accuracy of the battery cell pole piece interval detection. In addition, the standard deviation coefficient and the minimum standard deviation threshold corresponding to the first filter threshold are also different from those of the second filter threshold, wherein the standard deviation coefficient StdDevScale corresponding to the first filter threshold is 0.15, and the minimum standard deviation threshold AbsThreshold is 1.0.

[0126] Further, after filtering the first region image, the host computer intercepts the image of ±10° (i.e., the preset angle range) in the X direction of the pole piece center point in the filtered first region image, and obtains the following Fig.10 The fourth region image is shown. Then the findContours function in the opencv image library is used to calculate the image contour of the fourth region image, and the redundant noise contours are excluded according to the following rules:

[0127] The length of the circumscribed figure of the outline in the first direction is less than the fourth value, for example, the length of the circumscribed figure of the outline in the Y direction is less than 100 pixels;

[0128] The length of the circumscribed figure of the outline in the second direction is less than the fifth value. For example, the length of the circumscribed rectangle of the outline in the X direction is less than 100 pixels.

[0129] By filtering out the outlines of the external figures that meet the above rules, we can get Figure 4 The second region image shown contains only the cell pole piece.

[0130] By rotating the first area image, each area to be processed in the first area image is parallel to the first direction and within the preset angle range determined by the center point of the pole piece, so that all areas to be processed in the first area image have the same filtering parameters, ensuring the same filtering effect on the anode and cathode poles at different angles in the first area image, thereby improving the accuracy of the detection of the contours of the anode and cathode poles, and further improving the detection accuracy of the interval between the pole pieces of the battery cell.

[0131] It should be noted that, by processing the regional images corresponding to multiple rotation angles, multiple images such as Fig.10 After the fourth region image shown, the host computer splices multiple fourth region images according to the rotation angle corresponding to each fourth region image, so as to obtain a complete region image containing only the contours of the anode and cathode electrodes. If it is subsequently detected that the spacing between the anode and cathode electrodes does not meet the requirements, it can be marked in the complete region image containing only the contours of the anode and cathode electrodes to determine the location of the abnormal spacing between the electrodes, which is convenient for the assessment of the safety risk of the battery cell, or the correction of the battery cell design data.

[0132] It should be noted that for wound cells, the corresponding pole piece center point can be Fig.11 The method shown is determined by Fig.11 As shown, the method comprises the following steps:

[0133] Step S1101, performing image convolution on the cross-section image of the battery cell using a second convolution kernel to obtain second contour data;

[0134] Step S1102, filtering the cell cross-section image by a third filtering threshold to obtain a fifth region image, wherein the third filtering threshold is determined by the second contour data;

[0135] Step S1103, cropping an image corresponding to a target cropping area from the fifth region image to obtain a cropped fifth region image, wherein the target cropping area is a cropping range determined by a center line of the fifth region image;

[0136] Step S1104, identifying the pole piece contour with the smallest circumscribed pattern area from the cropped fifth region image to obtain a second target pole piece contour;

[0137] Step S1105: determine the intersection of the center line of the fifth region image and the second target pole piece contour as the pole piece center point.

[0138] In the above steps S1101 to S1105, the second convolution kernel is a convolution kernel in the second direction, the corresponding size is 1*7, the standard deviation coefficient StdDevScale is 0.1, and the other parameters remain unchanged. The cell cross-sectional image is convolved by the second convolution kernel, and then the third filter threshold is determined by the method for determining the second filter threshold. The method for determining the third filter threshold is similar to the method for determining the second filter threshold, and no further examples are given here.

[0139] After obtaining the third filtering threshold, the host computer performs grayscale threshold processing on the cross-section image of the battery cell to eliminate the influence of the outer ring anode and cathode on the detection result. Figure 3 To perform grayscale threshold filtering:

[0140] (3)

[0141] In formula (3), is the gray value corresponding to the current pixel in the cell cross-section image.

[0142] After filtering is completed, the fifth region image is cropped with the area determined by 50 pixels above and below the center line of the fifth region image, so as to obtain Fig.12 The cropped fifth region image is shown. In the cropped fifth region image, the rightmost point of the smallest pole piece outline of the circumscribed figure is used to determine the center point of the inner circle of the current wound battery cell, that is, the pole piece center point.

[0143] By confirming the center point of the pole piece and then rotating the first area image with the pole piece center point, each area in the first area image has the same filtering parameters and filtering effect, thereby improving the accuracy of positive and negative pole piece contour detection, and thus improving the detection accuracy of the battery cell pole piece interval.

[0144] After filtering the first area image where the battery cell pole pieces are located in the above manner to obtain a second area image containing only the anode and cathode pole pieces, the host computer can identify the contours of the anode and cathode pole pieces from the second area image to facilitate subsequent detection of the interval between the anode and cathode pole pieces.

[0145] In one embodiment, the host computer first identifies the cathode pole piece contour from the second region image, and then extracts the anode pole piece contour from the second region image based on the cathode pole piece contour. Specifically, the host computer identifies the pole piece contour of the external graphic that meets the second preset condition from the second region image to obtain the cathode pole piece contour; then, the second region image is filtered based on the target grayscale threshold to obtain the processed second region image; and the cathode pole piece contour is used as a mask to extract the anode pole piece contour from the processed second region image.

[0146] In the above embodiment, the target grayscale threshold is determined by the grayscale value of the pixels in the second region image, wherein the target grayscale threshold may be the average grayscale value of the pixels in the second region image. It should be noted that, since the wound battery cell occupies a relatively low proportion in the second region image, the average grayscale value of the entire image is used as the threshold value to process the original image, retaining pixels greater than the target grayscale threshold value, filtering out pixels less than or equal to the target grayscale threshold value, and using the separated cathode electrode piece contour as a mask, the anode electrode piece contour can be extracted from the processed second region image.

[0147] By identifying the cathode electrode contour from the second area image by means of an external graphic, and then extracting the anode electrode contour from the second area image based on the cathode electrode contour and the pixel grayscale value, the accuracy of the extraction of the positive and negative electrodes can be improved, thereby improving the accuracy of the detection of the positive and negative electrode intervals.

[0148] The following is a further introduction to the separation process of the anode and cathode plates.

[0149] For the extraction of the cathode pole piece contour, the host computer first obtains the target coordinates and the graphic width of the target point of the circumscribed graphic of each pole piece contour contained in the second area image in the first direction, and calculates the sum of the target coordinates and the graphic width to obtain the target width corresponding to each pole piece contour; then, based on the target width corresponding to each pole piece contour, all the pole piece contours in the first area image are sorted to obtain a contour sequence; then, based on the contour sequence and the contour area corresponding to each pole piece contour in the first area image, the cathode pole piece contour that meets the second preset condition is extracted from the first area image.

[0150] In the above embodiment, the target point of the circumscribed figure of the pole piece contour may be the center point of the circumscribed rectangle of the pole piece contour; the target coordinate of the target point in the first direction may be the coordinate value of the center point of the circumscribed rectangle in the X direction. The width of the figure corresponding to the pole piece contour is the size of the circumscribed figure of the pole piece contour in the second direction, and the first direction is perpendicular to the second direction. For example, the width of the figure is the length of the circumscribed rectangle of the pole piece contour in the Y direction.

[0151] After obtaining the target coordinates and the width of the external graphics of the pole piece contour in the X direction, the sum of the target coordinates and the width of the graphics of each pole piece contour is calculated to obtain the target width. Then, the pole piece contours contained in the second area image are sorted in order from small to large according to the target width to obtain a contour sequence. Next, according to the contour order in the contour sequence, the contours in the contour sequence are screened, and the non-cathode pole piece contours are filtered out to obtain the anode pole piece contour.

[0152] By screening the pole piece contour through the external graphics corresponding to the pole piece contour, the accuracy of cathode pole piece identification can be improved, and then the accuracy of anode and cathode pole piece contour identification can be improved, providing a basis for the subsequent accurate detection of the anode and cathode pole piece interval.

[0153] In the process of extracting the cathode electrode contour from the first region image, the host computer first removes the first electrode contour and the last two electrode contours in the contour sequence to obtain an updated contour sequence; then, the electrode contour whose contour area meets the second preset condition is removed from the updated contour sequence to obtain the following: Fig.13 The cathode pole piece outline is shown.

[0154] In the above embodiment, the host computer may use the contourArea function in the opencv image library to calculate the contour area of ​​each pole piece contour.

[0155] In one example, for a wound cell, the innermost anode electrode sheet and the outermost anode electrode sheet are not wrapped by the cathode electrode sheet. Therefore, in the order from the inner layer to the outer layer, the first electrode sheet contour and the last two electrode sheet contours of the wound cell must be the anode electrode sheet contour. In extracting the cathode electrode sheet contour, the first electrode sheet contour and the last two electrode sheet contours need to be removed from the contour sequence. For the remaining electrode sheet contours in the contour sequence, they are filtered by the second preset condition to obtain the cathode electrode sheet contour. Among them, the electrode sheet contour that meets the second preset condition includes any of the following:

[0156] (1) The contour area difference corresponding to the contour group is greater than the first area and is located at the front of the pole piece contour in the contour group, wherein the contour group includes two adjacent pole piece contours in the updated contour sequence. For example, the current pole piece contour is pole piece contour 1, and the pole piece contour adjacent to pole piece contour 1 is pole piece contour 2. The area difference between pole piece contour 1 and pole piece contour 2 is greater than 1000 (i.e., the first area), then pole piece contour 1 is filtered out from the first region image.

[0157] (2) The difference in contour area between two adjacent contour groups is greater than the second area, and the pole piece contour shared by the two adjacent contour groups has a first area greater than the second area. For example, if the current pole piece contour is pole piece contour 1, the pole piece contours adjacent to pole piece contour 1 are pole piece contour 2 and pole piece contour 3, and the area difference between pole piece contour 1 and pole piece contour 2 is greater than 300 (i.e., the second area), and the area difference between pole piece contour 1 and pole piece contour 3 is also greater than 300 (i.e., the second area), then pole piece contour 1 is filtered out from the first region image.

[0158] The pole piece contour in the first region image is filtered by the contour area corresponding to the pole piece contour, so as to obtain the cathode pole piece contour, which can improve the extraction accuracy of the cathode pole piece contour.

[0159] Further, after the cathode electrode contour is extracted, the host computer uses the cathode electrode contour as a mask to identify the first region image as follows: Fig.14 The anode piece outline is shown.

[0160] Furthermore, after the separation of the cathode and anode pole pieces is achieved, the host computer can detect the pole piece spacing between adjacent cathode pole piece contours and anode pole piece contours, wherein the host computer can calculate the spacing between the cathode and anode pole piece contours in the form of a ray diagram.

[0161] Specifically, the host computer obtains the ray diagram, and determines the cathode pole piece coordinate set of the cathode pole piece contour according to the intersection of the same ray of the ray diagram and the cathode pole piece contour; then, determines the anode pole piece coordinate set of the anode pole piece contour according to the intersection of the same ray of the ray diagram and the anode pole piece contour; and then determines the pole piece interval between adjacent cathode pole piece contours and anode pole piece contours according to the cathode pole piece coordinate set and the anode pole piece coordinate set.

[0162] In the above embodiment, the ray diagram includes multiple rays, and the rays are perpendicular to the tangent direction of the pole piece contour, or perpendicular to the extension direction of the pole piece contour. Wherein, in the case of a wound cell, the pole piece spacing can be calculated using a ray diagram including rays perpendicular to the tangent direction of the pole piece contour; in the case of a laminated cell, the pole piece spacing can be calculated using a ray diagram including rays perpendicular to the extension direction of the pole piece contour.

[0163] For wound cells, the host computer can use the center point of the electrode of the wound cell as the starting point of the ray, draw rays of various angles with a gray value of 1 on a blank image, and thus obtain a ray diagram. Then, the product of the ray diagram and the images corresponding to the contours of the cathode and anode electrodes is calculated to obtain the coordinates of the intersection of each cathode and anode electrode contour and the ray at each angle, thereby obtaining the cathode electrode coordinate set and the anode electrode coordinate set.

[0164] For laminated cells, Fig.15 As shown, the host computer can use multiple points on the boundary pole piece contour of the battery cell pole piece as the starting point of the ray, and the multiple points can be set at equal intervals. Similar to the wound battery cell, the product of the ray diagram and the image corresponding to the cathode and anode pole contours is calculated to obtain the coordinates of the intersection of each cathode and anode pole piece contour and the ray at each angle, thereby obtaining the cathode pole piece coordinate set and the anode pole piece coordinate set.

[0165] Furthermore, after obtaining the cathode electrode piece coordinate set and the anode electrode piece coordinate set, the host computer can calculate the electrode piece interval between the contours of adjacent cathode and anode electrode pieces.

[0166] By setting the ray diagram, the intersection coordinates of the positive and negative electrodes on the same ray can be obtained, which is convenient for the subsequent calculation of the electrode spacing between adjacent positive and negative electrodes and can improve the detection accuracy of the electrode spacing.

[0167] In the process of determining the pole piece interval between adjacent cathode pole piece contours and anode pole piece contours based on the cathode pole piece coordinate set and the anode pole piece coordinate set, the host computer sorts the coordinates in the cathode pole piece coordinate set and the anode pole piece coordinate set according to the positional relationship of the intersection in the second area image to obtain a target coordinate sequence; then, the pole piece interval is determined based on the interval between two adjacent coordinates in the target coordinate sequence.

[0168] In one example, taking a wound battery cell as an example, a ray at a certain angle intersects with the cathode pole piece contour and the anode pole piece contour to obtain multiple intersection points. For example, the intersection points where the ray intersects with multiple cathode pole piece contours are A1, A2, A3, and A4 respectively; the intersection points where the ray intersects with multiple anode pole piece contours are B1, B2, B3, and B4 respectively. The above eight intersection points are sorted in order from the inner layer to the outer layer of the battery cell, and the sorting result (i.e., the target coordinate sequence) is A1, B1, A2, B2, A3, B3, A4, and B4. Then, the interval between two adjacent coordinates in the target coordinate sequence is calculated to obtain the pole piece interval.

[0169] By sorting the coordinates in the cathode and anode electrode coordinate sets, the electrode spacing between adjacent cathode and anode electrodes can be calculated based on the sorting results, thereby reducing the risk of false detection and missed detection of the electrode spacing, thereby improving the detection accuracy of the electrode spacing.

[0170] The above describes the detection of the electrode spacing of the wound battery cell. For the laminated battery cell, it can be Fig.16 The first region image acquisition process shown is used to determine the first region image containing only the cell pole piece:

[0171] Step S1601, filtering the contours of the external figures that meet the first preset condition from the third region image to obtain a plurality of pole piece contours;

[0172] Step S1602, merging the circumscribed graphics of the multiple contours according to the sizes and / or positions of the circumscribed graphics corresponding to the multiple contours to obtain second target circumscribed graphics corresponding to the multiple contours;

[0173] Step S1603 , cutting out the area where the second target circumscribed pattern is located from the cell cross-sectional image to obtain a first area image.

[0174] In the above steps S1601 to S1603, the host computer can filter out external graphics whose sizes meet certain conditions, for example, external graphics whose sizes are too large or too small, to filter out interference from the battery shell or other noises. The host computer can also filter out external graphics whose positions meet certain conditions, for example, filter out external graphics that are far away from most external graphics.

[0175] After filtering the external graphics by size and / or position, the remaining external graphics are merged, and the obtained second target external graphics are the external graphics corresponding to the cell pole piece. The area where the second target external graphics is located is cut out from the cell cross-sectional image to obtain the first area image, and the first area image containing only the cell pole piece can be obtained.

[0176] The first area image containing only the cell pole pieces is extracted by using a method for extracting the cell pole piece area corresponding to the laminated cell, which provides a basis for the subsequent accurate detection of the pole piece interval of the laminated cell.

[0177] It should be noted that, for stacked cells, the filtering method for the first area image, the extraction method for the contours of the anode and cathode plates, and the calculation method for the plate spacing are similar to those for wound cells, which have been explained above and will not be repeated here.

[0178] This completes the explanation of the method provided in the embodiments of the present application.

[0179] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0180] In one embodiment, Fig.17 A schematic diagram of a cell detection device is shown. Fig.17 It can be seen that the device 1700 includes: a region identification module 1701, a filtering module 1702, a pole piece identification module 1703 and an interval detection module 1704.

[0181] A region identification module 1701 is used to identify a first region image where a cell pole piece is located from a cell cross-sectional image, wherein the first region image includes a plurality of contours;

[0182] A filtering module 1702 is used to filter the multiple contours of the first region image according to a first filtering threshold value to obtain a second region image including the pole piece contour, wherein the first filtering threshold value is determined by the pixel grayscale value of the first region image;

[0183] The electrode piece recognition module 1703 is used to respectively recognize the cathode electrode piece contour and the anode electrode piece contour from the second region image according to the electrode piece contour and the pixel grayscale in the second region image;

[0184] The interval detection module 1704 is used to detect the distance between the adjacent cathode pole piece contours and the anode pole piece contours to obtain the pole piece interval.

[0185] In one embodiment, the region identification module includes: a first filtering module, an external graphic determination module and a first processing module. The first filtering module is used to filter the cell cross-sectional image through a second filtering threshold to obtain a third region image containing multiple contours, wherein the second filtering threshold is determined by the pixel grayscale value of the cell cross-sectional image; the external graphic determination module is used to determine the external graphic of the contour contained in the third region image; the first processing module is used to process the cell cross-sectional image according to the first preset condition and the external graphic of the contour contained in the third region image to obtain a first region image containing the cell pole piece, wherein the first preset condition is determined according to the size of the external graphic.

[0186] In one embodiment, the battery cell detection device further includes: a convolution module, a first calculation module, a first threshold determination module, and a second threshold determination module. The convolution module is used to perform image convolution on the battery cell cross-sectional image through the first convolution kernel before filtering the battery cell cross-sectional image through the second filtering threshold to obtain the third area image containing the contour, so as to obtain the first contour data corresponding to the battery cell cross-sectional image; the first calculation module is used to calculate the pixel grayscale standard deviation corresponding to the first contour data; the first threshold determination module is used to determine the first coefficient as the second filtering threshold when the first coefficient is greater than the preset first standard deviation threshold, wherein the first coefficient is the product of the preset first standard deviation coefficient and the pixel grayscale standard deviation; the second threshold determination module is used to determine the first standard deviation threshold as the second filtering threshold when the first coefficient is less than or equal to the first standard deviation threshold.

[0187] In one embodiment, when the battery cell is a wound battery cell, the first processing module is specifically used to filter out the outline of the external figure that meets the first preset condition from the third area image to obtain multiple pole piece outlines; obtain the first target pole piece outline with the largest external figure area from the multiple pole piece outlines; crop the area where the first target external figure is located from the battery cell cross-sectional image to obtain the first area image, wherein the first target external figure is the external figure determined by the first target pole piece outline.

[0188] In one embodiment, the battery cell detection device further includes: an area expansion module for, after acquiring a first target pole piece contour having the largest circumscribed graphic area from a plurality of pole piece contours, performing area expansion on the circumscribed graphic of the first target pole piece contour to obtain a first target circumscribed graphic.

[0189] In one embodiment, the first preset condition includes at least one of the following:

[0190] The size of the circumscribed figure of the pole piece contour in the first direction is smaller than a first value, wherein the first value is determined by the physical properties of the battery cell and the magnification of the image acquisition device in the first direction;

[0191] The size of the circumscribed figure of the pole piece contour in the second direction is smaller than the second value, wherein the first direction and the second direction are perpendicular to each other, the first direction is the extension direction of the pole piece, and the second value is determined by the physical properties of the battery cell and the magnification of the image acquisition device in the second direction;

[0192] The difference between the size of the circumscribed figure of the pole piece contour in the first direction and the size of the cross-sectional image of the battery cell in the first direction is less than a third value, and the second value is determined by the physical properties of the battery cell and the magnification of the image acquisition device in the second direction;

[0193] The ratio of the size of the circumscribed figure of the pole piece contour in the first direction to the size of the cross-sectional image of the battery cell in the first direction is smaller than the first target ratio;

[0194] When the size of the circumscribed figure of the pole piece contour in the second direction is smaller than a fourth value, the size ratio of the circumscribed figure of the pole piece contour is smaller than a second target ratio, wherein the size ratio of the circumscribed figure of the pole piece contour is the ratio of the size of the circumscribed figure of the pole piece contour in the first direction to the size in the second direction, the first target ratio is smaller than the second target ratio, and the fourth value is determined by the physical properties of the battery cell and the magnification of the image acquisition device in the second direction.

[0195] In one embodiment, the filtering module is specifically used to rotate the first area image with the pole piece center point of the first area image as the rotation center to obtain the rotated first area image, wherein the pole piece center point is the center point of the pole piece contour with the smallest circumscribed graphic area in the first area image; filter the rotated first area image through a first filtering threshold to obtain the filtered first area image; capture the filtered first area image within a preset angle range determined by the pole piece center point to obtain a fourth area image; filter the fourth area image through the circumscribed graphic of the contour contained in the fourth area image to obtain the second area image.

[0196] In one embodiment, the battery cell detection device also includes: a pole piece center point determination module, which is used to perform image convolution on the battery cell cross-sectional image through a second convolution kernel to obtain second contour data; filter the battery cell cross-sectional image through a third filtering threshold to obtain a fifth area image, wherein the third filtering threshold is determined by the second contour data; crop the image corresponding to the target cropping area from the fifth area image to obtain a cropped fifth area image, wherein the target cropping area is a cropping range determined by the center line of the fifth area image; identify the pole piece contour with the smallest circumscribed graphic area from the cropped fifth area image to obtain a second target pole piece contour; determine the intersection of the center line of the fifth area image and the second target pole piece contour as the pole piece center point.

[0197] In one embodiment, the electrode piece recognition module includes: a cathode electrode piece recognition module, a second filtering module, and an anode electrode piece recognition module. The cathode electrode piece recognition module is used to recognize the electrode piece contour of the external graphic that meets the second preset condition from the second region image to obtain the cathode electrode piece contour; the second filtering module is used to filter the second region image based on the target grayscale threshold to obtain the processed second region image, wherein the target grayscale threshold is determined by the pixel grayscale value in the second region image; the anode electrode piece recognition module is used to extract the anode electrode piece contour from the processed second region image using the cathode electrode piece contour as a mask.

[0198] In one embodiment, the cathode electrode identification module includes: a graphic width acquisition module, a second calculation module, a contour sorting module and a target extraction module. The graphic width acquisition module is used to obtain the target coordinates and graphic width of the target point of the circumscribed graphic of each electrode contour contained in the second area image in the first direction, wherein the graphic width is the size of the circumscribed graphic of the electrode contour in the second direction, and the first direction and the second direction are perpendicular to each other; the second calculation module is used to calculate the sum of the target coordinates and the graphic width to obtain the target width corresponding to each electrode contour; the contour sorting module is used to sort all the electrode contours in the first area image based on the target width corresponding to each electrode contour to obtain a contour sequence; the target extraction module is used to extract the cathode electrode contour that meets the second preset condition from the first area image based on the contour sequence and the contour area corresponding to each electrode contour in the first area image.

[0199] In one embodiment, the target extraction module is specifically used to remove the first pole piece contour and the last two pole piece contours in the contour sequence to obtain an updated contour sequence; remove the pole piece contour whose contour area satisfies the second preset condition from the updated contour sequence to obtain the cathode pole piece; wherein the pole piece contour that satisfies the second preset condition includes any one of the following items: a pole piece contour whose contour area difference corresponding to the contour group is greater than the first area and is located at the front of the contour group, wherein the contour group includes two adjacent pole piece contours in the updated contour sequence; a pole piece contour whose contour area difference between two adjacent contour groups is greater than the second area, and a pole piece contour shared by two adjacent contour groups, wherein the first area is greater than the second area.

[0200] In one embodiment, the interval detection module includes: a ray acquisition module, a first coordinate determination module, a second coordinate determination module and an interval determination module. The ray acquisition module is used to acquire a ray diagram, wherein the ray diagram contains multiple rays, and the rays are perpendicular to the tangent direction of the pole piece contour, or perpendicular to the extension direction of the pole piece contour; the first coordinate determination module is used to determine the cathode pole piece coordinate set of the cathode pole piece contour according to the intersection of the same ray of the ray diagram and the cathode pole piece contour; the second coordinate determination module is used to determine the anode pole piece coordinate set of the anode pole piece contour according to the intersection of the same ray of the ray diagram and the anode pole piece contour; the interval determination module is used to determine the pole piece interval between adjacent cathode pole piece contours and anode pole piece contours according to the cathode pole piece coordinate set and the anode pole piece coordinate set.

[0201] In one embodiment, the interval determination module is specifically used to sort the coordinates in the cathode pole piece coordinate set and the anode pole piece coordinate set according to the positional relationship of the intersection in the second area image to obtain a target coordinate sequence; and determine the pole piece interval according to the interval between two adjacent coordinates in the target coordinate sequence.

[0202] In one embodiment, when the battery cell is a stacked battery cell, the area recognition module is specifically used to filter out the contours of the external graphics that meet the first preset condition from the battery cell cross-sectional image to obtain multiple pole piece contours; merge the external graphics of the multiple contours according to the sizes and / or positions of the external graphics corresponding to the multiple contours to obtain second target external graphics corresponding to the multiple contours; and crop the area where the second target external graphics is located from the battery cell cross-sectional image to obtain a first area image.

[0203] In one embodiment, the present application further provides a readable storage medium having computer program instructions stored thereon, and the computer program instructions implement the above-mentioned battery cell detection method when executed by a processor.

[0204] In one embodiment, the present application further provides a computer program product. When instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the above-mentioned battery cell detection method.

[0205] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0206] The functional blocks shown in the above structural block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application-specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link via a data signal carried in a carrier. "Machine-readable medium" may include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROMs, flash memory, erasable ROMs (EROMs), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0207] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0208] The above reference to the flowchart and / or block diagram of the cell detection method, device, storage medium and computer program product according to the embodiment of the present application describes various aspects of the present application. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0209] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application, and they should all be included in the scope of the claims and specification of the present application. In particular, as long as there is no structural conflict, the various technical features mentioned in the various embodiments can be combined in any way. The present application is not limited to the specific embodiments disclosed herein, but includes all technical solutions that fall within the scope of the claims.

Claims

1. A battery cell detection method, characterized in that: include: Identify a first region image where the cell pole piece is located from the cell cross-sectional image, wherein the first region image includes a plurality of contours; Filtering the plurality of contours of the first region image according to a first filtering threshold value to obtain a second region image including the pole piece contour, wherein the first filtering threshold value is determined by the pixel grayscale value of the first region image; According to the pole piece contours and pixel grayscales in the second region image, respectively identifying the cathode pole piece contour and the anode pole piece contour from the second region image; Detecting the distance between the adjacent cathode pole piece contours and anode pole piece contours to obtain the pole piece spacing; Among them, according to the pole piece contour and pixel grayscale in the second area image, the cathode pole piece contour and the anode pole piece contour are respectively identified from the second area image, including: identifying the pole piece contour of the external graphic that meets the second preset condition from the second area image to obtain the cathode pole piece contour; filtering the second area image based on the target grayscale threshold to obtain the processed second area image, wherein the target grayscale threshold is determined by the pixel grayscale value in the second area image; using the cathode pole piece contour as a mask, extracting the anode pole piece contour from the processed second area image.

2. The method according to claim 1, characterized in that Identifying a first region image where a cell pole piece is located from a cell cross-sectional image includes: Filtering the cell cross-sectional image by a second filtering threshold to obtain a third region image including a plurality of contours, wherein the second filtering threshold is determined by a pixel grayscale value of the cell cross-sectional image; Determine a circumscribed figure of a contour included in the third region image; The cell cross-sectional image is processed according to a first preset condition and an external graphic of a contour included in the third region image to obtain a first region image including the cell pole piece, wherein the first preset condition is determined according to a size of the external graphic.

3. The method according to claim 2, characterized in that Before filtering the cell cross-sectional image by using the second filtering threshold to obtain a third region image containing a contour, the method further includes: Performing image convolution on the battery core cross-sectional image through a first convolution kernel to obtain first contour data corresponding to the battery core cross-sectional image; Calculating the pixel grayscale standard deviation corresponding to the first contour data; When the first coefficient is greater than a preset first standard deviation threshold, determining the first coefficient as the second filtering threshold, wherein the first coefficient is the product of the preset first standard deviation coefficient and the pixel grayscale standard deviation; When the first coefficient is less than or equal to the first standard deviation threshold, the first standard deviation threshold is determined as the second filtering threshold.

4. The method according to claim 2 or 3, characterized in that: In the case where the battery cell is a wound battery cell, the battery cell cross-sectional image is processed according to the first preset condition and the circumscribed graph of the contour included in the third region image to obtain a first region image including the battery cell electrode piece, including: Filtering the contours of the external figures that meet the first preset condition from the third region image to obtain a plurality of the pole piece contours; Acquire a first target pole piece contour having the largest circumscribed graphic area from the plurality of pole piece contours; The region where the first target circumscribed figure is located is cut out from the cell cross-sectional image to obtain the first region image, wherein the first target circumscribed figure is a circumscribed figure determined by the first target pole piece contour.

5. The method according to claim 4, characterized in that After obtaining a first target pole piece contour having the largest circumscribed graphic area from the plurality of pole piece contours, the method further comprises: The circumscribed figure of the first target pole piece contour is expanded in region to obtain the first target circumscribed figure.

6. The method according to claim 4, characterized in that The first preset condition includes at least one of the following: The size of the circumscribed figure of the pole piece contour in the first direction is smaller than a first value, wherein the first value is determined by the physical properties of the battery cell and the magnification of the image acquisition device in the first direction; The size of the circumscribed figure of the pole piece contour in the second direction is smaller than a second value, wherein the first direction and the second direction are perpendicular to each other, the first direction is the extension direction of the pole piece, and the second value is determined by the physical properties of the battery cell and the magnification of the image acquisition device in the second direction; The difference between the size of the circumscribed figure of the pole piece contour in the first direction and the size of the cross-sectional image of the battery cell in the first direction is less than a third value, wherein the third value is determined by the physical properties of the battery cell and the magnification of the image acquisition device in the first direction; The ratio of the size of the circumscribed figure of the pole piece contour in the first direction to the size of the cell cross-sectional image in the first direction is smaller than the first target ratio; When the size of the circumscribed figure of the pole piece contour in the second direction is smaller than a fourth value, the size ratio of the circumscribed figure of the pole piece contour is smaller than a second target ratio, wherein the size ratio of the circumscribed figure of the pole piece contour is the ratio of the size of the circumscribed figure of the pole piece contour in the first direction to the size in the second direction, the first target ratio is smaller than the second target ratio, and the fourth value is determined by the physical properties of the battery cell and the magnification of the image acquisition device in the second direction.

7. The method according to claim 4, characterized in that The first region image is filtered according to a first filtering threshold to obtain a second region image containing a pole piece contour, including: Taking the pole piece center point of the first region image as the rotation center, the first region image is rotated to obtain a rotated first region image, wherein the pole piece center point is the center point of the pole piece contour with the smallest circumscribed figure area in the first region image; Performing filtering processing on the rotated first region image by using the first filtering threshold to obtain a filtered first region image; Performing image interception on the filtered first region image within a preset angle range determined by the center point of the pole piece to obtain a fourth region image; The fourth region image is filtered using a circumscribed graph of a contour included in the fourth region image to obtain the second region image.

8. The method according to claim 7, characterized in that The method further comprises: Performing image convolution on the battery core cross-section image using a second convolution kernel to obtain second contour data; Filtering the cell cross-sectional image by a third filtering threshold to obtain a fifth region image, wherein the third filtering threshold is determined by the second contour data; cropping an image corresponding to a target cropping area from the fifth region image to obtain a cropped fifth region image, wherein the target cropping area is a cropping range determined by a center line of the fifth region image; Identify the pole piece contour with the smallest circumscribed pattern area from the cropped fifth region image to obtain a second target pole piece contour; The intersection point of the center line of the fifth region image and the second target pole piece contour is determined as the pole piece center point.

9. The method according to claim 1, characterized in that: Identifying the electrode piece contour of the external figure satisfying the second preset condition from the second region image to obtain the cathode electrode piece contour includes: Obtaining the target coordinates of the target point of the circumscribed figure of each pole piece contour contained in the second region image in the first direction and the figure width, wherein the figure width is the size of the circumscribed figure of the pole piece contour in the second direction, and the first direction and the second direction are perpendicular to each other; Calculating the sum of the target coordinates and the graphic width to obtain the target width corresponding to each pole piece contour; Sorting all the pole piece contours in the first region image based on the target width corresponding to each pole piece contour to obtain a contour sequence; Based on the contour sequence and the contour area corresponding to each pole piece contour in the first region image, a cathode pole piece contour satisfying the second preset condition is extracted from the first region image.

10. The method according to claim 9, characterized in that Extracting a cathode pole piece contour satisfying the second preset condition from the first regional image based on the contour sequence and the contour area corresponding to each pole piece contour in the first regional image includes: Removing the first pole piece contour and the last two pole piece contours in the contour sequence to obtain an updated contour sequence; Removing the electrode piece contour whose contour area satisfies the second preset condition from the updated contour sequence to obtain the cathode electrode piece contour; Wherein, the pole piece profile that meets the second preset condition includes any one of the following: a pole piece contour corresponding to a contour group having a contour area difference greater than the first area and located at the front of the contour group, wherein the contour group includes two adjacent pole piece contours in the updated contour sequence; The difference in contour areas between two adjacent contour groups is greater than the second area, and the pole piece contour shared by the two adjacent contour groups has the first area greater than the second area.

11. The method according to claim 1, characterized in that: Detect the distance between the adjacent cathode pole piece contours and anode pole piece contours to obtain the pole piece spacing, including: Acquire a ray diagram, wherein the ray diagram includes a plurality of rays, and the rays are perpendicular to a tangent direction of a pole piece contour, or perpendicular to an extension direction of the pole piece contour; Determining a cathode pole piece coordinate set of the cathode pole piece contour according to an intersection point between a same ray of the ray diagram and the cathode pole piece contour; Determining an anode pole piece coordinate set of the anode pole piece contour according to an intersection point between the same ray of the ray diagram and the anode pole piece contour; The pole piece spacing between adjacent cathode pole piece contours and the anode pole piece contours is determined according to the cathode pole piece coordinate set and the anode pole piece coordinate set.

12. The method according to claim 11, characterized in that Determining the electrode piece spacing between adjacent cathode electrode piece contours and the anode electrode piece contours according to the cathode electrode piece coordinate set and the anode electrode piece coordinate set includes: Sorting the coordinates in the cathode electrode piece coordinate set and the anode electrode piece coordinate set according to the positional relationship of the intersection points in the second region image to obtain a target coordinate sequence; The pole piece interval is determined according to the interval between two adjacent coordinates in the target coordinate sequence.

13. The method according to claim 2 or 3, characterized in that: In the case where the battery cell is a laminated battery cell, the contour of the external graphics in the battery cell cross-sectional image that meets the first preset condition is filtered out to obtain a first region image containing the battery cell electrode sheet, including: Filtering the contours of the external graphics that meet the first preset condition from the battery cell cross-sectional image to obtain a plurality of the pole piece contours; Merging the circumscribed graphics of the plurality of contours according to the sizes and / or positions of the circumscribed graphics corresponding to the plurality of contours to obtain second target circumscribed graphics corresponding to the plurality of contours; The area where the second target circumscribed pattern is located is cut out from the cell cross-sectional image to obtain the first area image.

14. A battery cell detection device, characterized in that: include: A region recognition module, used to recognize a first region image where a cell pole piece is located from a cell cross-sectional image, wherein the first region image includes a plurality of contours; A filtering module, used for filtering the multiple contours of the first region image according to a first filtering threshold value to obtain a second region image including the pole piece contour, wherein the first filtering threshold value is determined by the pixel grayscale value of the first region image; A pole piece recognition module, used to recognize the cathode pole piece contour and the anode pole piece contour from the second region image according to the pole piece contour and the pixel grayscale in the second region image; An interval detection module is used to detect the interval between the adjacent cathode pole piece contours and the anode pole piece contours to obtain the pole piece interval; Among them, the pole piece identification module includes: a cathode pole piece identification module, which is used to identify the pole piece contour of the external graphic that meets the second preset condition from the second area image to obtain the cathode pole piece contour; a second filtering module, which is used to filter the second area image based on the target grayscale threshold to obtain the processed second area image, wherein the target grayscale threshold is determined by the pixel grayscale value in the second area image; an anode pole piece identification module, which is used to extract the anode pole piece contour from the processed second area image using the cathode pole piece contour as a mask.

15. A readable storage medium, characterized in that: Computer program instructions are stored on the readable storage medium, and when the computer program instructions are executed by the processor, the battery cell detection method according to any one of claims 1 to 13 is implemented.

16. A computer program product, characterized in that When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the battery cell detection method as described in any one of claims 1 to 13.

Images