Battery diaphragm detection method and device, computing equipment and readable storage medium

Abstract

The invention provides a battery diaphragm detection method and device, computing equipment and a readable storage medium, and belongs to the technical field of batteries. The detection method of the battery diaphragm comprises the steps that a first short circuit trace area is extracted from a first detection image, the first detection image is obtained by imaging the battery diaphragm through a microscopic imaging device, and the first short circuit trace area indicates ablation traces caused by battery short circuit caused by metal foreign matter in the battery diaphragm on the battery diaphragm; preset image features are extracted from a second detection image, the second detection image is obtained by imaging a cross section, crossing the first short circuit trace area, of the battery diaphragm through a microscopic imaging device, and metal foreign matter exists in the cross section of the first short circuit trace area; and determining the type of the metal foreign matter according to the extraction result of the predetermined image features.

Description

Technical Field

[0001] The present application relates to the field of battery technology, and in particular to a method, device, computing equipment, computer-readable storage medium and computer program product for detecting a battery separator. Background Art

[0002] During the production process of lithium-ion batteries, metal foreign matter is often easily introduced into the battery due to problems such as raw material purity and processing technology. During battery formation or use, due to electrochemical reactions and other reasons, it is deposited on the surface of the positive and negative electrodes, causing damage to the battery separator and causing short circuits or micro-short circuits.

[0003] In order for batteries to meet customer needs, it is necessary to detect and attribute the micro-short circuits in battery separators. However, testing battery separators often leads to a series of problems. Summary of the invention

[0004] In view of the above problems, the present application provides a battery diaphragm detection method, apparatus, computing device, computer-readable storage medium and computer program product, aiming to alleviate, mitigate or eliminate the problem of being unable to determine the type of metal foreign matter when inspecting battery diaphragms.

[0005] In a first aspect, the present application provides a method for detecting a battery diaphragm, comprising: extracting a first short-circuit trace area from a first detection image, wherein the first detection image is obtained by imaging the battery diaphragm through a microscopic imaging device, and the first short-circuit trace area indicates ablation marks on the battery diaphragm caused by a battery short circuit caused by metal foreign matter in the battery diaphragm; extracting predetermined image features from a second detection image, wherein the second detection image is obtained by imaging a cross-section of the battery diaphragm across the first short-circuit trace area through a microscopic imaging device, and there is metal foreign matter in the cross-section of the first short-circuit trace area; and determining the type of the metal foreign matter based on the extraction result of the predetermined image features.

[0006] In the technical solution of the embodiment of the present application, the type of metal foreign matter is determined based on the extraction result of predetermined image features extracted from a second detection image obtained by imaging the cross-section of the battery separator across the first short-circuit mark area through a microscopic imaging device. This allows first finding the ablation marks on the battery separator caused by the battery short circuit, and then analyzing the cross-sectional morphology of the cross-sectional processing through the ablation marks, thereby alleviating the problem of being unable to determine the type of metal foreign matter when inspecting the battery separator.

[0007] In some embodiments, extracting the predetermined image feature from the second detection image includes: identifying a first target image region from the second detection image, the first target image region corresponding to the internal region of the diaphragm in the cross section; and extracting the predetermined image feature from the first target image region. By identifying the first target image region corresponding to the internal region of the diaphragm in the cross section from the second detection image, the recognition interference of the image region other than the internal region of the diaphragm in the cross section (for example, the surface region of the diaphragm in the cross section) in the second detection image can be reduced, thereby improving the extraction accuracy of the predetermined image feature.

[0008] In some embodiments, identifying the first target image area from the second detection image includes: detecting a first edge and a second edge of a cross section from the second detection image by performing edge detection on the second detection image, the first edge and the second edge respectively corresponding to edges of two surfaces of a diaphragm body of a battery diaphragm that are opposite to each other on the cross section; and identifying an image area between the first edge and the second edge in the second detection image as the first target image area. By performing edge detection on the second detection image, the first target image area corresponding to the internal area of ​​the diaphragm in the cross section can be quickly identified, thereby improving detection efficiency.

[0009] In some embodiments, the first edge corresponds to the negative side of the battery separator, the second edge corresponds to the positive side of the battery separator, and the predetermined image feature includes: at least one image sub-region extending from the first edge to the second edge, wherein each image sub-region includes a first portion closer to the first edge and a second portion closer to the second edge, and the size of the first portion along the first edge is greater than the size of the second portion along the second edge. By setting the predetermined image feature to include at least one image sub-region that includes a first portion that is larger in size and closer to the first edge along the first edge and a second portion that is smaller in size and closer to the second edge along the second edge, the judgment criteria for the type of metal foreign matter can be preset, thereby increasing the possibility of judging the type of metal foreign matter.

[0010] In some embodiments, extracting predetermined image features from the first target image region includes: detecting a third edge from the first target image region by performing edge detection on the first target image region, the third edge being located between the first edge and the second edge and corresponding to a partial contour of the metal foreign body on the cross section, the average grayscale value of the image region between the first edge and the third edge being greater than the average grayscale value of the image region between the third edge and the second edge; detecting peak points and valley points on the line of the third edge relative to the line of the second edge; and based on the peak points and valley points, dividing the image region between the first edge and the third edge in the first target image region into at least one image sub-region arranged along the first edge, wherein every two adjacent peak points and a valley point located between the two adjacent peak points jointly define an image sub-region. In such a design, the first target image region can be conveniently segmented and divided into at least one image sub-region.

[0011] In some embodiments, according to the extraction result of the predetermined image feature, determining the type of the metal foreign matter includes: in response to extracting the predetermined image feature from the second detection image, determining that the metal foreign matter is a first type, the first type indicates that the metal foreign matter is introduced in the process of preparing the slurry of the electrode sheet and precipitated during the battery cycle; in response to failing to extract the predetermined image feature from the second detection image, determining that the metal foreign matter is a second type, the second type indicates that the metal foreign matter is introduced in the process of producing the battery after the process of preparing the slurry of the electrode sheet. By determining whether the predetermined image feature is extracted, the type of the metal foreign matter can be determined, thereby identifying its specific source and providing a basis for improvement measures.

[0012] In some embodiments, extracting the first short circuit trace area from the first detection image includes: extracting the second short circuit trace area from the third detection image, wherein the third detection image is obtained by imaging the battery negative electrode sheet stacked with the battery separator through a microscopic imaging device, and the second short circuit trace area indicates the ablation trace on the battery negative electrode sheet caused by the battery short circuit caused by the metal foreign matter in the battery separator; and locating the first short circuit trace area corresponding to the second short circuit trace area in the first detection image. By finding the second short circuit trace area on the negative electrode sheet to trace the first short circuit trace area on the battery separator, the first short circuit trace area on the battery separator can be more conveniently found, thereby improving the detection efficiency.

[0013] In some embodiments, extracting the second short-circuit trace area from the third detection image includes: identifying a candidate short-circuit trace area from the third detection image; and in response to the candidate short-circuit trace area satisfying a preset condition, determining the candidate short-circuit trace area as the second short-circuit trace area. By identifying the candidate short-circuit trace area and determining whether it satisfies the preset condition, the second short-circuit trace area on the negative electrode plate can be more conveniently found, thereby improving detection efficiency.

[0014] In some embodiments, the preset condition includes: the similarity between the candidate short circuit trace area and the circle is greater than a similarity threshold, and the area of ​​the candidate short circuit trace area is between a first threshold and a second threshold. By setting the preset condition, it is more convenient to identify which candidate short circuit trace areas on the third detection image can be used as the second short circuit trace area.

[0015] In some embodiments, locating the first short-circuit trace area corresponding to the second short-circuit trace area in the first detection image includes: determining the first coordinate of the center of the second short-circuit trace area in the image coordinate system of the third detection image from the third detection image; based on the relative position relationship between the battery negative electrode plate and the battery separator, converting the first coordinate into a second coordinate in the image coordinate system of the first detection image, the second coordinate indicating the center of the first short-circuit trace area; and locating the first short-circuit trace area in the first detection image with the second coordinate as the center. Through the coordinate conversion between the first coordinate and the second coordinate, the first short-circuit trace area can be more conveniently located in the first detection image, thereby improving the detection efficiency.

[0016] In some embodiments, the cross section of the battery diaphragm across the first short-circuit trace region is obtained by cross-section processing the battery diaphragm by a cross-section processing device, the cross-section processing device includes at least one of an ion beam profile grinding device and a focused ion beam device, and the cross-section processing of the battery diaphragm by the cross-section processing device includes: measuring the maximum plane size of the portion of the metal foreign matter in the first short-circuit trace region exposed to the surface of the battery diaphragm; in response to the maximum plane size being greater than or equal to a third threshold, using the ion beam profile grinding device to cross-section process the battery diaphragm; and in response to the maximum plane size being less than the third threshold, using the focused ion beam device to cross-section process the battery diaphragm. By measuring the maximum plane size of the portion of the metal foreign matter in the first short-circuit trace region exposed to the surface of the battery diaphragm and selecting different cross-section processing methods according to the maximum plane size, the possibility of losing the short-circuit point due to the accuracy of the processing device can be reduced while ensuring the processing efficiency.

[0017] In some embodiments, the method further includes: determining a main element in the metal foreign matter, wherein the main element indicates an element of the metal foreign matter penetrating the battery separator. By determining the main element in the metal foreign matter, when there are multiple metal elements on the separator surface near the short-circuit point, the main element and the secondary element causing the micro-short circuit can be better distinguished, so that the source can be more accurately and efficiently checked and improvement measures can be introduced.

[0018] In some embodiments, determining the main element of the metal foreign body includes: identifying a second target image area from a fourth detection image, the second target image area corresponding to an internal area of ​​the diaphragm in the cross section, wherein the fourth detection image is obtained by imaging the cross section by an energy spectrum analysis device, and the fourth detection image indicates the distribution of each element present in the cross section; for each of the elements, determining whether the element exists in the second target image area and whether the ratio of the number of pixels of the element in the second target image area to the total number of pixels of the second target image area is greater than or equal to a fourth threshold; and in response to determining that the element exists in the second target image area and the ratio of the number of pixels of the element in the second target image area to the total number of pixels of the second target image area is greater than or equal to the fourth threshold, determining that the element is the main element. By analyzing the fourth detection image obtained by imaging the cross section by the energy spectrum analysis device, it is possible to more conveniently determine the main element that pierces the diaphragm, thereby being able to more accurately analyze the cause of the self-discharge anomaly.

[0019] In some embodiments, identifying the second target image area from the fourth detection image includes: extracting the first image area and the second image area from the fourth detection image by performing edge detection on the fourth detection image, the first image area and the second image area respectively corresponding to the first coating and the second coating on two surfaces opposite to each other of the battery separator; and identifying the image area between the first area and the second area in the fourth detection image as the second target image area. By performing edge detection to identify the upper and lower coatings, the second target image area corresponding to the internal area of ​​the separator in the cross section can be more conveniently identified, thereby improving detection efficiency.

[0020] In a second aspect, the present application provides a battery diaphragm detection device, comprising: a first module, used to extract a first short-circuit trace area from a first detection image, wherein the first detection image is obtained by imaging the battery diaphragm through a microscopic imaging device, and the first short-circuit trace area indicates the ablation mark on the battery diaphragm caused by a battery short circuit caused by metal foreign matter in the battery diaphragm; a second module, used to extract predetermined image features from a second detection image, wherein the second detection image is obtained by imaging a cross-section of the battery diaphragm across the first short-circuit trace area through a microscopic imaging device, and there is metal foreign matter in the cross-section of the first short-circuit trace area; and a third module, used to determine the type of metal foreign matter based on the extraction result of the predetermined image feature.

[0021] In some embodiments, the apparatus further comprises: a fourth module for determining a main element of the metallic foreign matter, wherein the main element indicates an element of the metallic foreign matter penetrating the battery separator.

[0022] Such a device can provide the advantages described above with respect to the detection method of the battery separator, which will not be described in detail for the sake of brevity.

[0023] In a third aspect, the present application provides a computing device comprising: at least one processor; and at least one memory communicatively connected to the at least one processor, the at least one memory storing instructions, which, when executed individually or collectively by the at least one processor, enable the computing device to execute the method in the above-mentioned embodiment.

[0024] Such a computing device can provide the advantages described above with respect to the battery separator detection method, which will not be described in detail for the sake of brevity.

[0025] In a fourth aspect, the present application provides a computer-readable storage medium storing instructions, which, when executed individually or collectively by one or more processors of a computing device, cause the computing device to execute the method in the above-mentioned embodiment.

[0026] Such a computer-readable storage medium can provide the advantages described above with respect to the detection method of the battery separator, which will not be described in detail for the sake of brevity.

[0027] In a fifth aspect, the present application provides a computer program product, comprising instructions, which, when executed individually or collectively by one or more processors of a computing device, cause the computing device to execute the method in the above embodiment.

[0028] Such a computer program product can provide the advantages described above with respect to the detection method of the battery separator, which will not be described in detail for the sake of brevity.

[0029] 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

[0030] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Moreover, the same reference numerals are used throughout the drawings to represent the same components. In the drawings:

[0031] Figure 1 A flow chart illustrating a method for detecting a battery separator according to an exemplary embodiment;

[0032] Figure 2 is a microscopic image illustrating a first inspection image of a battery separator according to an exemplary embodiment;

[0033] Figure 3 is a microscopic image illustrating a second inspection image of a battery separator according to an exemplary embodiment;

[0034] Figure 4 To illustrate a method according to an exemplary embodiment Figure 1 A flowchart of some example processes in the method;

[0035] Figure 5 To illustrate a method according to an exemplary embodiment Figure 4 A flowchart of some example processes in the method;

[0036] Figure 6 is a schematic diagram illustrating a first target image area in a second detection image according to an exemplary embodiment;

[0037] Figure 7 To illustrate a method according to an exemplary embodiment Figure 4 A flowchart of some example processes in the method;

[0038] Figure 8 To illustrate a method according to an exemplary embodiment Figure 1 A flowchart of some example processes in the method;

[0039] Fig. 9 To illustrate a method according to an exemplary embodiment Figure 1 A flowchart of some example processes in the method;

[0040] Fig.10 A microscopic image illustrating a third detection image of a negative electrode sheet of a battery according to an exemplary embodiment;

[0041] Fig.11 To illustrate a method according to an exemplary embodiment Fig. 9 A flowchart of some example processes in the method;

[0042] Fig.12 To illustrate a method according to an exemplary embodiment Fig. 9 A flowchart of some example processes in the method;

[0043] Fig.13 To illustrate a method according to an exemplary embodiment Figure 1 A flowchart of some example processes in the method;

[0044] Fig.14 is an energy spectrum analysis image illustrating a fourth detection image of a chromium element according to an exemplary embodiment;

[0045] Fig.15 is an energy spectrum analysis image illustrating a fourth detection image of an iron element according to an exemplary embodiment;

[0046] Fig.16 To illustrate a method according to an exemplary embodiment Fig.13 A flowchart of some example processes in the method;

[0047] Fig.17 is an energy spectrum analysis image illustrating a fourth detection image of a chromium element according to another exemplary embodiment;

[0048] Fig.18 is a schematic block diagram illustrating a detection device for a battery separator according to an exemplary embodiment;

[0049] Fig.19 An example configuration of a computing device that may be used to implement the methods described herein is shown. DETAILED DESCRIPTION

[0050] The following embodiments of the technical solution of the present application are described in detail in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application, and are therefore only used as examples, and cannot be used to limit the scope of protection of the present application.

[0051] 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.

[0052] 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.

[0053] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0054] 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.

[0055] 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 (including two groups), and "multiple pieces" refers to more than two (including two pieces). The term "based on" should be interpreted as "based at least in part on". As used herein, in addition, the term "at least one of..." covers any one of the listed items and all possible combinations.

[0056] 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.

[0057] 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.

[0058] At present, a high-density laser beam is generally used to irradiate the surface of the battery separator after the battery is disassembled, so that the surface components form plasma and then evaporate.

[0059] However, when the battery separator and the electrode are separated during the battery disassembly process, a portion of the electrode material, such as carbon powder or active material, is usually attached to the battery separator, and it is usually impossible to directly detect metal foreign matter covered by other substances, so it is impossible to accurately analyze the type of metal foreign matter.

[0060] In order to alleviate, mitigate or eliminate the problem of being unable to determine the type of metal foreign matter when inspecting the battery separator, the ablation marks on the battery separator caused by the battery short circuit can be found first, and then the cross-sectional morphology of the cross-section processed through the ablation marks can be analyzed to determine the type of metal foreign matter.

[0061] Based on the above considerations, a battery separator detection method is designed to alleviate, mitigate or eliminate the problem of being unable to determine the type of metal foreign matter when detecting the battery separator by analyzing the cross-sectional morphology of the ablation marks caused by battery short circuit on the battery separator during cross-sectional processing.

[0062] The battery separator detection method disclosed in the embodiment of the present application can be used to detect separators used in electrical devices such as vehicles, ships or aircraft, such as battery separators, but not limited to them.

[0063] Reference Figure 1 , and please refer to Figures 2 to 3 . Figure 1 1 is a flow chart illustrating a method 100 for inspecting a battery separator 125 according to an exemplary embodiment. Figure 2 FIG. 1 is a microscopic image illustrating a first inspection image 115 of a battery separator 125 according to an exemplary embodiment. Figure 3 FIG. 1 is a microscopic image showing a second inspection image 135 of a battery separator 125 according to an exemplary embodiment. The method 100 includes steps S110 to S130.

[0064] In step S110, a first short circuit mark area 120 is extracted from the first detection image 115. The first detection image 115 is obtained by imaging the battery separator 125 through a microscopic imaging device, and the first short circuit mark area 120 indicates the ablation mark on the battery separator 125 caused by the battery short circuit caused by the metal foreign matter 130 in the battery separator 125.

[0065] In step S120, a predetermined image feature 140 is extracted from the second detection image 135. The second detection image 135 is obtained by imaging the cross section of the battery separator 125 across the first short circuit mark area 120 by a microscopic imaging device, and the metal foreign matter 130 exists in the cross section of the first short circuit mark area 120.

[0066] In step S130 , the type of the metallic foreign matter 130 is determined according to the extraction result of the predetermined image feature 140 .

[0067] According to some embodiments of the present application, the microscopic imaging device may include but is not limited to a scanning electron microscope (SEM). According to some embodiments of the present application, the first detection image 115 may be obtained by imaging the surface of the battery separator 125 stacked with the battery negative electrode plate through the microscopic imaging device. It is understood that the first detection image 115 may also be obtained by imaging the surface of the battery separator 125 stacked with the battery positive electrode plate through the microscopic imaging device.

[0068] exist Figure 2 In the example shown, the first short-circuit trace area 120 presents an irregular enclosed shape on the first detection image 115, which indicates the ablation trace caused by the battery short circuit on the battery separator 125. The ablation trace is usually a yellow-brown halo. In some embodiments, the contrast resolution and recognition function of the microscopic imaging device can be used to quickly locate the ablation trace.

[0069] According to some embodiments of the present application, the section of the battery separator 125 that crosses the first short-circuit trace region 120 may be any section of the battery separator 125 as long as the section cuts through the first short-circuit trace region 120 on the surface of the battery separator 125. Figure 3 In the example shown, the white dotted areas in the cross section indicate the presence of metallic foreign matter 130 .

[0070] Method 100 determines the type of metal foreign matter by analyzing the cross section, which allows first finding the ablation marks on the battery separator caused by the battery short circuit, and then analyzing the cross-sectional morphology of the cross section processed through the ablation marks, thereby alleviating the problem of being unable to determine the type of metal foreign matter when inspecting the battery separator.

[0071] Reference Figure 4 , and please refer to Figure 3 . Figure 4 To illustrate a method according to an exemplary embodiment Figure 1 A flowchart of a portion of an exemplary process in method 100. Figure 4 As shown, according to some embodiments, step S120, extracting predetermined image features from the second detection image may include:

[0072] In step S410, a first target image region 145 is identified from the second detection image 135, and the first target image region 145 corresponds to an inner region of the diaphragm in the cross section;

[0073] In step S420 , a predetermined image feature 140 is extracted from the first target image region 145 .

[0074] In order to perform image recognition on the internal area of ​​the diaphragm in the cross section, it is necessary to identify the first target image area 145 corresponding to the internal area of ​​the diaphragm from the second detection image 135. In addition, it is necessary to extract the predetermined image feature 140 from the first target image area 145 in order to further analyze the type of the metal foreign matter 130 present in the cross section.

[0075] By identifying the first target image area 145 corresponding to the internal area of ​​the diaphragm in the cross-section from the second detection image 135, the recognition interference of the image area other than the internal area of ​​the diaphragm in the cross-section (for example, the diaphragm surface area 150 in the cross-section, the redundant blank area 155 in the second detection image 135) in the second detection image 135 can be reduced, thereby improving the extraction accuracy of the predetermined image feature 140.

[0076] Reference Figure 5 , and please refer to Figure 3 . Figure 5 To illustrate a method according to an exemplary embodiment Figure 4 A flowchart of some example processes in the method. Figure 5 As shown, according to some embodiments, step S410, identifying the first target image area 145 from the second detection image 135 may include:

[0077] In step S510, edge detection is performed on the second detection image 135 to detect a first edge 160 and a second edge 165 of the cross section from the second detection image 135, wherein the first edge 160 and the second edge 165 respectively correspond to edges of two surfaces of the separator body of the battery separator 125 that are opposite to each other on the cross section;

[0078] In step S520 , an image region between the first edge 160 and the second edge 165 in the second detection image 135 is identified as a first target image region 145 .

[0079] In this article, the term "edge detection" refers to identifying points in a digital image where brightness changes significantly. In the context of image processing and computer vision, significant changes in image properties usually reflect important events and changes in the properties, including but not limited to discontinuities in depth, surface orientation discontinuities, changes in material properties, and changes in scene lighting.

[0080] In this document, the term "membrane body" refers to the body portion of the battery separator 125 that does not include the upper and lower coating layers (e.g., aluminum oxide). According to some embodiments of the present application, the edges of the two surfaces of the membrane body of the battery separator 125 that are opposite to each other on the cross section can be marked according to the placement position of the battery separator 125 in the second detection image 135, so that the first edge 160 corresponds to the edge of the upper surface of the membrane body on the cross section, and the second edge 165 corresponds to the edge of the lower surface of the membrane body on the cross section.

[0081] By performing edge detection on the second detection image 135 , the first target image region 145 corresponding to the internal region of the diaphragm in the cross section can be quickly and accurately identified, thereby improving detection efficiency.

[0082] Reference Figure 6 , and please refer to Figure 3 . Figure 6 Schematic diagram illustrating a first target image area 145 in a second detection image 135 according to an exemplary embodiment. Figure 6 As shown, the first edge 160 corresponds to the negative side of the battery separator 125, and the second edge 165 corresponds to the positive side of the battery separator 125. The predetermined image feature 140 includes: at least one image sub-region 170 extending from the first edge 160 to the second edge 165. Each image sub-region 170 includes a first portion 175 closer to the first edge 160 and a second portion 180 closer to the second edge 165. The size of the first portion 175 along the first edge 160 is greater than the size of the second portion 180 along the second edge 165.

[0083] According to some embodiments of the present application, the negative electrode side of the battery separator 125 refers to the side of the battery separator 125 adjacent to the negative electrode plate, and the positive electrode side of the battery separator 125 refers to the side of the battery separator 125 adjacent to the positive electrode plate. According to some embodiments of the present application, before the microscopic imaging device images the cross section of the battery separator 125 across the first short-circuit trace region 120, the negative electrode side and the positive electrode side of the battery separator 125 can be marked so that the negative electrode side and the positive electrode side of the battery separator 125 can be found in the second detection image 135.

[0084] exist Figure 6In the example shown, the predetermined image feature 140 includes three image sub-regions 170 extending from the first edge 160 to the second edge 165. As an example, two adjacent image sub-regions 170 are separated by a dotted line. Each image sub-region 170 includes a first portion 175 and a second portion 180. As an example, the first portion 175 is separated from the second portion 180 by a dotted line. Figure 6 As can be seen in FIG. 1 , the dimension of the first portion 175 along the first edge 160 is greater than the dimension of the second portion 180 along the second edge 165 .

[0085] By setting the predetermined image feature 140 to include at least one image sub-region 170 including a first portion 175 having a larger size along the first edge 160 and closer to the first edge 160 and a second portion 180 having a smaller size along the second edge 165 and closer to the second edge 165, a judgment criterion for the type of the metal foreign matter 130 can be preset, that is, the size of the first portion 175 along the first edge 160 is larger than the size of the second portion 180 along the second edge 165, thereby increasing the possibility of judging the type of the metal foreign matter 130.

[0086] Reference Figure 7 , and please refer to Figure 6 . Figure 7 To illustrate a method according to an exemplary embodiment Figure 4 A flowchart of some example processes in the method. Figure 7 As shown, according to some embodiments, step S420, extracting the predetermined image feature 140 from the first target image area 145 may include:

[0087] In step S710, edge detection is performed on the first target image area 145 to detect a third edge 185 from the first target image area 145, the third edge 185 is located between the first edge 160 and the second edge 165, and corresponds to a partial contour of the metal foreign matter 130 on the cross section, and the average grayscale value of the image area between the first edge 160 and the third edge 185 is greater than the average grayscale value of the image area between the third edge 185 and the second edge 165;

[0088] In step S720, the peak point 190 and the valley point 195 on the line of the third edge 185 relative to the line of the second edge 165 are detected;

[0089] In step S730, based on the peak points 190 and the valley points 195, the image area between the first edge 160 and the third edge 185 in the first target image area 145 is divided into at least one image sub-area 170 arranged along the first edge 160, wherein every two adjacent peak points 190 and a valley point 195 located between the two adjacent peak points 190 jointly define an image sub-area 170.

[0090] exist Figure 3 In the example shown, the metal foreign matter 130 on the cross section is displayed as the whitened pixel areas in the first target image area 145, and is presented as an inverted triangle or inverted cone ridge. Figure 3 and Figure 6 As shown, the third edge 185 corresponds to the peak line or waist line of those inverted triangles or inverted cones.

[0091] In this article, the term "grayscale value" refers to a value that logarithmically divides white and black into several levels based on the different degrees of gray presented at each point on the image. Generally, the larger the grayscale value, the whiter the pixel, for example, white is 255 and black is 0.

[0092] exist Figure 6 In the example shown, four peak points 190 (represented by black solid dots as an example in the figure) and three valley points 195 (represented by black hollow dots as an example in the figure) are detected on the line of the third edge 185 relative to the line of the second edge 165.

[0093] like Figure 6 As shown, every two adjacent peak points 190 and a valley point 195 located between the two adjacent peak points 190 together define an image sub-region 170. As an example, two adjacent image sub-regions 170 are separated by a dotted line.

[0094] By detecting the peak point 190 and the valley point 195 on the line of the third edge 185 , the first target image region 145 can be conveniently segmented into at least one image sub-region 170 .

[0095] Reference Figure 8 , and please refer to Figure 6 . Figure 8 To illustrate a method according to an exemplary embodiment Figure 1 A flowchart of some example processes in the method. Figure 8 As shown, according to some embodiments, step S130, determining the type of the metal foreign body 130 according to the extraction result of the predetermined image feature 140 may include:

[0096] In step S810, in response to extracting the predetermined image feature 140 from the second detection image 135, it is determined that the metal foreign matter 130 is of the first type, and the first type indicates that the metal foreign matter 130 is introduced during the process of preparing the slurry of the electrode sheet and precipitated during the battery cycle;

[0097] In step S820, in response to failure to extract the predetermined image feature 140 from the second detection image 135, the metal foreign matter 130 is determined to be a second type, which indicates that the metal foreign matter 130 is introduced in the process of producing the battery after the process of preparing the slurry of the electrode sheet.

[0098] According to some embodiments of the present application, the first type includes a precipitation type, which is characterized in that the morphology of the precipitation type is dendritic and wide on the negative electrode side and narrow on the positive electrode side under imaging by a microscopic imaging device. According to some embodiments of the present application, the second type includes a hard type, and if there is no regularity shown by the precipitation type, it is a hard type.

[0099] The precipitation type of metal foreign matter 130 mainly comes from the slurry used to prepare the electrode sheet. Therefore, if it is determined that the type of metal foreign matter 130 is precipitation type, the source can be checked from the supplier of the slurry and measures can be taken. The hard type of metal foreign matter 130 mainly comes from the processing technology, such as the winding of the electrode sheet, equipment wear, etc. Therefore, if it is determined that the type of metal foreign matter 130 is hard, the source can be checked from the processing technology and measures can be taken.

[0100] By determining whether the predetermined image feature 140 is extracted, the type of the metal foreign matter 130 can be determined, thereby finding out its specific source and providing a basis for improvement measures.

[0101] Reference Fig. 9 and Fig.10 . Fig. 9 To illustrate a method according to an exemplary embodiment Figure 1 A flowchart of some example processes in the method. Fig.10 FIG. 2 is a microscopic image showing a third detection image 200 of a negative electrode sheet 210 of a battery according to an exemplary embodiment. Fig. 9 As shown, according to some embodiments, step S110, extracting the first short circuit trace area 120 from the first detection image 115 may include:

[0102] In step S910, a second short-circuit trace area 205 is extracted from the third test image 200, wherein the third test image 200 is obtained by imaging the battery negative electrode sheet 210 stacked with the battery separator 125 through a microscopic imaging device, and the second short-circuit trace area 205 indicates the ablation trace on the battery negative electrode sheet 210 caused by the battery short circuit caused by the metal foreign matter 130 in the battery separator 125;

[0103] In step S920 , the first short trace region 120 corresponding to the second short trace region 205 is located in the first detection image 115 .

[0104] According to some embodiments of the present application, the battery negative electrode plate 210 can be manually placed on a microscopic imaging device, such as a microscope, for defect observation, or a conveyor belt can be used to transport the battery negative electrode plate 210 to a microscopic imaging device, such as a microscope, for automatic identification.

[0105] Generally, the coating of the battery separator 125 will be heated due to the short circuit, and the coating of the battery separator 125 near the center of the second short circuit mark area 205 will fall off and adhere to the battery negative electrode plate 210, and the diameter of the falling object is generally 10-100um.

[0106] According to some embodiments of the present application, since the battery negative electrode sheet 210 and the battery separator 125 are adjacent, when a short circuit occurs in the battery, ablation marks will be generated on the battery negative electrode sheet 210 and the battery separator 125, respectively. When the location of the battery short circuit is different, the location of the ablation marks generated on the battery negative electrode sheet 210 is different, and corresponding ablation marks will also be generated at different locations on the battery separator 125. It should be noted that the ablation marks generated on the battery negative electrode sheet 210 due to the battery short circuit correspond to the ablation marks generated on the battery separator 125 due to the battery short circuit. Therefore, the corresponding ablation marks can be found on the battery separator 125 according to the ablation marks on the battery negative electrode sheet 210 caused by the battery short circuit.

[0107] By tracing back the first short circuit trace area 120 on the battery separator 125 by finding the second short circuit trace area 205 on the battery negative electrode plate 210, the first short circuit trace area 120 on the battery separator 125 can be found more conveniently, thereby improving detection efficiency.

[0108] Reference Fig.11 . Fig.11 To illustrate a method according to an exemplary embodiment Fig. 9 A flowchart of some example processes in the method. Fig.11 As shown, according to some embodiments, step S910, extracting the second short circuit trace area 205 from the third detection image 200 may include:

[0109] In step S1110, a candidate short-circuit trace area is identified from the third detection image 200;

[0110] In step S1120 , in response to the candidate short trace region satisfying a preset condition, the candidate short trace region is determined as the second short trace region 205 .

[0111] Since regions similar to the second short-circuit trace region 205 may be identified in the third detection image 200, some regions are not ablation traces caused by battery short circuit, but substances such as carbon powder. Therefore, in order to reduce the possibility of misidentification, a preset condition may be set, and only candidate short-circuit trace regions that meet the preset condition can be determined as the second short-circuit trace region 205.

[0112] By identifying the candidate short-circuit trace area and determining whether it meets the preset conditions, the second short-circuit trace area 205 on the battery negative electrode plate 210 can be more conveniently found, thereby improving the detection efficiency.

[0113] According to some embodiments of the present application, the preset conditions include: the similarity between the candidate short circuit trace area and the circle is greater than a similarity threshold, and the area of ​​the candidate short circuit trace area is between a first threshold and a second threshold.

[0114] In this article, the term "similarity" refers to a measure of the degree of similarity between two objects. The closer two objects are, the greater their similarity measure is, and the farther two objects are, the smaller their similarity measure is. Therefore, the similarity with a circle can be understood as the degree of similarity with a circle, which can be expressed as a percentage.

[0115] In some embodiments, the similarity threshold may be at least 70%. In some embodiments, the first threshold may be 0.282 mm 2 , the second threshold can be 0.785mm 2 .

[0116] By setting the preset conditions, it is possible to more conveniently identify which candidate short circuit trace regions on the third detection image 200 can be used as the second short circuit trace regions 205 .

[0117] Reference Fig.12 . Fig.12 To illustrate a method according to an exemplary embodiment Fig. 9 A flowchart of some example processes in the method. Fig.12 As shown, according to some embodiments, step S920, locating the first short circuit mark area 120 corresponding to the second short circuit mark area 205 in the first detection image 115 may include:

[0118] In step S1210, a first coordinate of the center of the second short-circuit trace area 205 in the image coordinate system of the third detection image 200 is determined from the third detection image 200;

[0119] In step S1220, based on the relative position relationship between the battery negative electrode plate 210 and the battery separator 125, the first coordinate is converted into a second coordinate in the image coordinate system of the first detection image 115, and the second coordinate indicates the center of the first short-circuit trace area 120;

[0120] In step S1230 , the first short-circuit trace area 120 is located in the first detection image 115 with the second coordinate as the center.

[0121] In this document, the term "image coordinate system" refers to a coordinate system whose origin is at the center of the image plane of the third detection image 200 or the first detection image 115, and whose x-axis and y-axis are respectively parallel to two adjacent vertical sides of the image plane. Of course, other definitions of "image coordinate system" are also possible.

[0122] Therefore, even if the metal foreign matter 130 is small enough, the coordinates of the center of the second short-circuit mark area 205 and the center of the first short-circuit mark area 120 can be matched through a microscopic imaging device, such as a microscope two-dimensional recognition. The matching of the coordinates of the two can accurately locate the short-circuit point on the battery separator 125.

[0123] By means of coordinate conversion between the first coordinate and the second coordinate, the first short circuit trace area 120 can be more conveniently located in the first detection image 115, thereby improving detection efficiency.

[0124] According to some embodiments of the present application, the cross section of the battery separator 125 across the first short-circuit trace region 120 is obtained by cross-section processing the battery separator 125 by a cross-section processing device. The cross-section processing device includes at least one of an ion beam profile grinding device and a focused ion beam device. According to some embodiments, cross-section processing the battery separator 125 by the cross-section processing device includes:

[0125] Measuring the maximum plane size of the portion of the metal foreign matter in the first short-circuit trace area 120 exposed to the surface of the battery separator 125;

[0126] In response to the maximum plane size being greater than or equal to a third threshold, using an ion beam profile milling device to perform cross-section processing on the battery separator 125; and

[0127] In response to the maximum planar dimension being smaller than the third threshold, the battery separator 125 is cross-sectioned using a focused ion beam device.

[0128] According to some embodiments of the present application, the maximum planar size of the portion of the metal foreign body exposed to the surface of the battery separator can be measured using a caliper under a microscopic imaging device, such as a microscope imaging. If the portion of the metal foreign body exposed to the surface of the battery separator is circular, the maximum planar size is the diameter of the portion of the metal foreign body exposed to the surface of the battery separator. In some embodiments, the third threshold value can be 200 μm.

[0129] According to some embodiments of the present application, different cross-section processing methods are selected according to the maximum planar size of the portion of the metal foreign matter exposed on the surface of the battery separator observed by the microscopic imaging device. Specifically, the maximum planar size is determined in the following manner, that is, if there is shedding of active material from the battery negative electrode sheet, such as carbon powder, then it is the maximum planar size of the active material that has fallen off from the battery negative electrode sheet; if there is no shedding of active material from the battery negative electrode sheet, then it is the maximum planar size of the portion of the metal foreign matter corresponding to the center of the ablation mark of the battery negative electrode sheet exposed on the surface of the battery separator. The former is that the active material from the battery negative electrode sheet falls off and adheres to the battery separator, completely covering the metal foreign matter, and the latter is that the metal foreign matter is observed directly on the battery separator.

[0130] In some embodiments, the processing accuracy of the ion beam profile milling device can be ±100 μm. The ion beam profile milling device uses an ion beam, such as an argon ion beam, to cut a sample, such as a cross section of a battery separator. During the cutting process, in order to reduce the possibility that the area of ​​the sample that is not desired to be cut is cut by the ion beam, a light shield is used to shield it.

[0131] In some embodiments, the processing accuracy of the focused ion beam device can be ±1 μm. In particular, when the maximum plane size is about 10 μm, the use of the focused ion beam device can reduce the possibility of failures not being discovered due to the loss of part of the metal foreign matter exposed to the surface of the battery separator caused by the device accuracy.

[0132] By measuring the maximum planar dimension of the portion of the metal foreign matter in the first short-circuit trace area 120 exposed to the surface of the battery separator and selecting different cross-section processing methods according to the maximum planar dimension, the possibility of losing the short-circuit point due to the accuracy of the processing equipment can be reduced while ensuring processing efficiency.

[0133] Reference again Figure 1 Additionally or alternatively, the method 100 may further include step S140. It is understandable that the method 100 may also omit step S140.

[0134] In step S140 , a main element in the metallic foreign matter 130 is determined, wherein the main element indicates an element of the metallic foreign matter 130 penetrating the battery separator 125 .

[0135] When there are multiple metal elements on the surface of the battery separator 125 near the short-circuit point, it is necessary to determine the main element that pierces the separator and causes the micro-short circuit. The main element is the cause of the self-discharge anomaly. In addition to the main element, the remaining elements are secondary elements that are precipitated but do not pierce the separator.

[0136] By determining the main elements in the metal foreign matter, when there are multiple metal elements on the diaphragm surface near the short-circuit point, the main and secondary elements causing the micro-short circuit can be better distinguished, thereby enabling more accurate and efficient source investigation and introduction of improvement measures.

[0137] Reference Fig.13 , Fig.14 and Fig.15 . Fig.13 To illustrate a method according to an exemplary embodiment Figure 1 A flowchart of some example processes in the method. Fig.14 The energy spectrum analysis image is an illustration of a fourth detection image 215 of the chromium element according to an exemplary embodiment. Fig.15 FIG. 2 is an energy spectrum analysis image showing a fourth detection image 215 of the iron element according to an exemplary embodiment. Fig.13 As shown, according to some embodiments, step S140, determining the main element in the metal foreign matter 130 may include:

[0138] In step S1310, a second target image region 220 is identified from the fourth detection image 215, and the second target image region 220 corresponds to the inner region of the diaphragm in the cross section, wherein the fourth detection image 215 is obtained by imaging the cross section through an energy spectrum analysis device, and the fourth detection image 215 indicates the distribution of each element existing in the cross section;

[0139] In step S1320, for each of the elements, it is determined whether the element exists in the second target image area 220 and whether the ratio of the number of pixels of the element in the second target image area 220 to the total number of pixels in the second target image area is greater than or equal to a fourth threshold;

[0140] In step S1330, in response to determining that the element exists in the second target image area 220 and the ratio of the number of pixels of the element in the second target image area to the total number of pixels in the second target image area is greater than or equal to a fourth threshold, the element is determined to be a main element.

[0141] According to some embodiments of the present application, the fourth threshold may be 40%. Fig.14 and Fig.15In the example shown, chromium and iron are respectively present in the second target image region 220, and the ratio of the number of pixels of chromium and iron in the second target image region 220 to the total number of pixels in the second target image region is respectively greater than or equal to the fourth threshold value. Thus, it can be determined that chromium and iron are the main elements.

[0142] By analyzing the fourth detection image 215 obtained by imaging the cross section using the energy spectrum analyzer, the main element that pierces the diaphragm can be more conveniently determined, thereby more accurately analyzing the cause of the self-discharge anomaly.

[0143] Reference Fig.16 and Fig.17 . Fig.16 To illustrate a method according to an exemplary embodiment Fig.13 A flowchart of some example processes in the method. Fig.17 FIG. 2 is an energy spectrum analysis image of a fourth detection image 215 of the chromium element according to another exemplary embodiment. Fig.13 As shown, according to some embodiments, step S1310, identifying the second target image area 220 from the fourth detection image 215 may include:

[0144] In step S1610, by performing edge detection on the fourth detection image 215, a first image region 225 and a second image region 230 are extracted from the fourth detection image 215, wherein the first image region 225 and the second image region 230 correspond to the first coating and the second coating on two surfaces opposite to each other of the battery separator, respectively;

[0145] In step S1620 , an image region between the first image region 225 and the second image region 230 in the fourth detection image is identified as a second target image region 220 .

[0146] exist Fig.17 In the example shown, edge detection can be used to identify the upper and lower edges of the first coating and the second coating, thereby determining the specific positions of the first image area 225 and the second image area 230. According to some embodiments of the present application, at least one of the first coating and the second coating may include an aluminum oxide coating.

[0147] By performing edge detection to identify the upper and lower coatings, the second target image region 220 corresponding to the inner region of the diaphragm in the cross section can be more conveniently identified, thereby improving detection efficiency.

[0148] According to some embodiments of the present application, see Figure 1The present application provides a detection method 100 for a battery separator 125, the detection method 100 comprising extracting a first short circuit trace area 120 from a first detection image 115 in step S110. The first detection image 115 is obtained by imaging the battery separator 125 through a microscopic imaging device, and the first short circuit trace area 120 indicates ablation marks on the battery separator 125 caused by a battery short circuit caused by a metal foreign body 130 in the battery separator 125; in step S120, extracting a predetermined image feature 140 from a second detection image 135. The second detection image 135 is obtained by imaging the cross-section of the battery separator 125 across the first short-circuit mark area 120 through a microscopic imaging device, and there is a metal foreign matter 130 in the cross-section of the first short-circuit mark area 120; in step S130, the type of the metal foreign matter 130 is determined according to the extraction result of the predetermined image feature 140; and in step S140, the main element in the metal foreign matter 130 is determined, wherein the main element indicates the element of the metal foreign matter 130 penetrating the battery separator 125.

[0149] Fig.18 1 is a schematic block diagram illustrating a detection device 1800 for a battery separator 125 according to an exemplary embodiment.

[0150] like Fig.18 As shown, the detection device 1800 of the battery separator 125 includes: a first module 1810 , a second module 1820 and a third module 1830 .

[0151] The first module 1810 is configured to extract a first short circuit mark area 120 from the first detection image 115. The first detection image 115 is obtained by imaging the battery separator 125 through a microscopic imaging device, and the first short circuit mark area 120 indicates a burn mark on the battery separator 125 caused by a battery short circuit caused by a metal foreign body 130 in the battery separator 125.

[0152] The second module 1820 is configured to extract a predetermined image feature 140 from the second detection image 135. The second detection image 135 is obtained by imaging the cross section of the battery separator 125 across the first short circuit mark area 120 through a microscopic imaging device, and the metal foreign matter 130 exists in the cross section of the first short circuit mark area 120.

[0153] The third module 1830 is configured to determine the type of the metal foreign matter 130 according to the extraction result of the predetermined image feature 140 .

[0154] It should be understood that Fig.18 Modules 1810, 1820, and 1830 of the apparatus 1800 shown in FIG. 1 may be used in conjunction with reference to Figure 1The steps S110-S130 in the method 100 described above correspond to each other. Therefore, the operations, features and advantages described above for the method 100 are also applicable to the apparatus 1800 and the modules included therein.

[0155] For the sake of brevity, certain operations, features and advantages are not described in detail herein.

[0156] Reference again Fig.18 The detection device 1800 for the battery separator 125 may further include a fourth module 1840 (indicated by a dotted box).

[0157] The fourth module 1840 is configured to determine a main element in the metallic foreign matter 130 , wherein the main element indicates an element of the metallic foreign matter 130 penetrating the battery separator 125 .

[0158] It should be understood that Fig.18 The module 1840 of the apparatus 1800 shown in FIG. 1 can be used with reference to Figure 1 The described method 100 corresponds to step S140.

[0159] For the sake of brevity, certain operations, features and advantages are not described in detail herein.

[0160] Although specific functions are discussed above with reference to specific modules, it should be noted that the functions of the various modules discussed herein may be divided into multiple modules, and / or at least some functions of multiple modules may be combined into a single module. The specific module discussed herein performing an action includes the specific module itself performing the action, or alternatively the specific module calling or otherwise accessing another component or module that performs the action (or performs the action in conjunction with the specific module). Therefore, the specific module that performs an action may include the specific module itself that performs the action and / or another module that the specific module calls or otherwise accesses to perform the action.

[0161] It should also be understood that various techniques may be described herein in the general context of software hardware elements or program modules. Fig.18The modules described can be implemented in hardware or in hardware in combination with software and / or firmware. For example, these modules can be implemented as computer program codes / instructions, which are configured to be executed in one or more processors and stored in a computer-readable storage medium. Alternatively, these modules can be implemented as hardware logic / circuits. For example, in some embodiments, one or more of the first module 1810, the second module 1820, the third module 1830, and the fourth module 1840 can be implemented together in a system on chip (System on Chip, SoC). SoC may include an integrated circuit chip (which includes a processor (e.g., a central processing unit (CPU), a microcontroller, a microprocessor, a digital signal processor (DSP), etc.), a memory, one or more communication interfaces, and / or one or more components in other circuits), and may optionally execute the received program code and / or include embedded firmware to perform functions.

[0162] In the following, combined Fig.19 Illustrative examples of such computing devices, computer-readable storage media, and computer program products are described.

[0163] Fig.19 An example configuration of a computing device 1900 that can be used to implement the methods described herein is shown. The above-mentioned apparatus 1800 can also be implemented in whole or at least in part by the computing device 1900 or a similar device or system.

[0164] The computing device 1900 may include at least one processor 1902, memory 1904, communication interface(s) 1906, a display device 1908, other input / output (I / O) devices 1910, and one or more mass storage devices 1912, all capable of communicating with one another, such as via a system bus 1914 or other appropriate connections.

[0165] Processor 1902 may be a single processing unit or multiple processing units, all of which may include a single or multiple computing units or multiple cores. Processor 1902 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuits, and / or any device that manipulates signals based on operating instructions. In addition to other capabilities, processor 1902 may be configured to obtain and execute computer-readable instructions stored in memory 1904, mass storage device 1912, or other computer-readable media, such as program code of an operating system 1916, program code of an application program 1918, program code of other programs 1920, and the like.

[0166] The memory 1904 and the mass storage device 1912 are examples of computer-readable storage media for storing instructions that are executed by the processor 1902 to implement the various functions described above. For example, the memory 1904 may generally include both volatile memory and non-volatile memory (e.g., RAM, ROM, etc.). In addition, the mass storage device 1912 may generally include a hard drive, a solid-state drive, a removable medium, including external and removable drives, a memory card, a flash memory, a floppy disk, an optical disk (e.g., a CD, a DVD), a storage array, a network attached storage, a storage area network, etc. The memory 1904 and the mass storage device 1912 may all be collectively referred to herein as memory or computer-readable storage media, and may be a non-transitory medium capable of storing computer-readable, processor-executable program instructions as computer program code, which may be executed by the processor 1902 as a specific machine configured to implement the operations and functions described in the examples herein.

[0167] Although in Fig.19 1900, but modules 1810, 1820, 1830, and 1840, or portions thereof, may be implemented using any form of computer-readable media accessible by the computing device 1900. As used herein, "computer-readable media" includes at least two types of computer-readable media, namely, computer-readable storage media and communication media.

[0168] Computer-readable storage media include volatile and non-volatile, removable and non-removable media implemented by any method or technology for storing information, such as computer-readable instructions, data structures, program modules, or other data. Computer-readable storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD), or other optical storage device, magnetic cassette, magnetic tape, magnetic disk storage device or other magnetic storage device, or any other non-transmission medium that can be used to store information for access by a computing device. In contrast, communication media can embody computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transmission mechanism. Computer-readable storage media as defined herein do not include communication media.

[0169] A number of programs may be stored on the mass storage device 1912. These programs include an operating system 1916, one or more application programs 1918, other programs 1920, and program data 1922, and they may be loaded into the memory 1904 for execution. Examples of such applications or program modules may include, for example, computer program logic (e.g., computer program code or instructions) for implementing the following components / functions: method 100 (including any suitable steps of method 100), and / or additional embodiments described herein.

[0170] One or more communication interfaces 1906 are used to exchange data with other devices, such as through a network, direct connection, etc. Such communication interfaces can be one or more of the following: any type of network interface (e.g., a network interface card (NIC)), a wired or wireless (such as IEEE 802.11 wireless LAN (WLAN)) wireless interface, a Worldwide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth™ interface, a Near Field Communication (NFC) interface, etc. The communication interface 1906 can facilitate communication within a variety of network and protocol types, including wired networks (e.g., LAN, cable, etc.) and wireless networks (e.g., WLAN, cellular, satellite, etc.), the Internet, etc. The communication interface 1906 can also provide communication with external storage devices (not shown) such as storage arrays, network attached storage, storage area networks, etc.

[0171] In some examples, a display device 1908 such as a monitor may be included for displaying information and images to the user. Other I / O devices 1910 may be devices that receive various inputs from the user and provide various outputs to the user, and may include a touch input device, a gesture input device, a camera, a keyboard, a remote control, a mouse, a printer, an audio input / output device, and the like.

[0172] The technology described herein can be supported by these various configurations of the computing device 1900, and is not limited to the specific examples of the technology described herein. For example, the functionality can also be implemented in whole or in part on the "cloud" by using a distributed system. The cloud includes and / or represents a platform for resources. The platform abstracts the underlying functionality of the hardware (e.g., server) and software resources of the cloud. Resources can include applications and / or data that can be used when performing computing processing on a server away from the computing device 1900. Resources can also include services provided over the Internet and / or through a subscriber network such as a cellular or Wi-Fi network. The platform can abstract resources and functions to connect the computing device 1900 to other computing devices. Therefore, the implementation of the functions described herein can be distributed throughout the cloud. For example, the functions can be implemented partially on the computing device 1900 and partially through a platform that abstracts the functions of the cloud.

[0173] 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 method for detecting a battery separator, characterized in that: include: Extracting a first short-circuit trace area from a first detection image, wherein the first detection image is obtained by imaging the battery separator using a microscopic imaging device, and the first short-circuit trace area indicates ablation marks on the battery separator caused by a battery short circuit caused by metal foreign matter in the battery separator; Extracting a predetermined image feature from a second detection image, wherein the second detection image is obtained by imaging a cross section of the battery separator across the first short-circuit trace region by the microscopic imaging device, and the metal foreign matter exists in the cross section of the first short-circuit trace region; and The type of the metal foreign matter is determined according to the extraction result of the predetermined image feature.

2. The method according to claim 1, characterized in that: Extracting a predetermined image feature from the second detection image comprises: identifying a first target image region from the second detection image, the first target image region corresponding to an inner region of the diaphragm in the cross section; and The predetermined image feature is extracted from the first target image region.

3. The method according to claim 2, characterized in that The identifying the first target image area from the second detection image comprises: By performing edge detection on the second detection image, a first edge and a second edge of the cross section are detected from the second detection image, wherein the first edge and the second edge respectively correspond to edges of two surfaces of the separator body of the battery separator on the cross section that are opposite to each other; An image region between the first edge and the second edge in the second detection image is identified as the first target image region.

4. The method according to claim 3, characterized in that The first edge corresponds to the negative electrode side of the battery separator, the second edge corresponds to the positive electrode side of the battery separator, and the predetermined image feature includes: at least one image sub-region extending from the first edge to the second edge, wherein each image sub-region includes a first portion closer to the first edge and a second portion closer to the second edge, and a size of the first portion along the first edge is greater than a size of the second portion along the second edge.

5. The method according to claim 4, characterized in that The extracting the predetermined image feature from the first target image area comprises: By performing edge detection on the first target image area, a third edge is detected from the first target image area, the third edge is located between the first edge and the second edge and corresponds to a partial contour of the metal foreign object on the cross section, and an average grayscale value of the image area between the first edge and the third edge is greater than an average grayscale value of the image area between the third edge and the second edge; Detecting peak points and valley points on the line of the third edge relative to the line of the second edge; and Based on the peak points and the valley points, the image area between the first edge and the third edge in the first target image area is divided into the at least one image sub-area arranged along the first edge, wherein every two adjacent peak points and a valley point between the two adjacent peak points jointly define an image sub-area.

6. The method according to any one of claims 1 to 5, characterized in that Determining the type of the metal foreign matter according to the extraction result of the predetermined image feature includes: In response to extracting the predetermined image feature from the second detection image, determining that the metal foreign matter is a first type, the first type indicating that the metal foreign matter is introduced during the process of preparing the slurry of the electrode sheet and precipitated during the battery cycle; In response to failure to extract the predetermined image feature from the second detection image, the metal foreign matter is determined to be a second type, the second type indicating that the metal foreign matter is introduced in a battery production process after the process of preparing the slurry for the electrode sheet.

7. The method according to any one of claims 1 to 6, characterized in that Extracting the first short circuit trace area from the first detection image comprises: Extracting a second short-circuit trace area from a third detection image, wherein the third detection image is obtained by imaging a battery negative electrode sheet stacked with the battery separator using a microscopic imaging device, and the second short-circuit trace area indicates ablation marks on the battery negative electrode sheet caused by a battery short circuit caused by metal foreign matter in the battery separator; and The first short circuit trace area corresponding to the second short circuit trace area is located in the first detection image.

8. The method according to claim 7, characterized in that Extracting the second short circuit trace area from the third detection image comprises: identifying a candidate short-circuit trace area from the third detection image; and In response to the candidate short trace region satisfying a preset condition, the candidate short trace region is determined as the second short trace region.

9. The method according to claim 8, characterized in that The preset conditions include: the similarity between the candidate short circuit trace area and the circle is greater than a similarity threshold, and the area of ​​the candidate short circuit trace area is between a first threshold and a second threshold.

10. The method according to any one of claims 7 to 9, characterized in that: The locating the first short circuit trace area corresponding to the second short circuit trace area in the first detection image comprises: Determine, from the third detection image, a first coordinate of a center of the second short-circuit trace area in an image coordinate system of the third detection image; Based on the relative positional relationship between the battery negative electrode plate and the battery separator, converting the first coordinate into a second coordinate in an image coordinate system of the first detection image, the second coordinate indicating the center of the first short-circuit trace area; and The first short circuit trace area is located in the first detection image with the second coordinate as the center.

11. The method according to any one of claims 1 to 10, characterized in that The cross section of the battery separator across the first short-circuit trace region is obtained by cross-section processing the battery separator by a cross-section processing device, wherein the cross-section processing device includes at least one of an ion beam profile grinding device and a focused ion beam device, and the cross-section processing of the battery separator by the cross-section processing device includes: measuring the maximum plane size of the portion of the metal foreign matter in the first short-circuit trace region exposed to the surface of the battery separator; In response to the maximum plane size being greater than or equal to a third threshold, using the ion beam profile milling device to perform cross-section processing on the battery separator; and In response to the maximum planar dimension being smaller than the third threshold, the battery separator is cross-sectioned using the focused ion beam device.

12. The method according to any one of claims 1 to 11, characterized in that The method further comprises: A main element in the metallic foreign matter is determined, wherein the main element indicates an element of the metallic foreign matter penetrating the battery separator.

13. The method according to claim 12, characterized in that Determining the main element of the metal foreign matter comprises: identifying a second target image region from a fourth detection image, the second target image region corresponding to an inner region of the diaphragm in the cross section, wherein the fourth detection image is obtained by imaging the cross section by an energy spectrum analysis device, and the fourth detection image indicates distribution conditions of various elements present in the cross section; For each of the elements, determining whether the element exists in the second target image region and whether a ratio of the number of pixels of the element in the second target image region to the total number of pixels in the second target image region is greater than or equal to a fourth threshold; and In response to determining that the element exists in the second target image area and the ratio of the number of pixels of the element in the second target image area to the total number of pixels in the second target image area is greater than or equal to a fourth threshold, the element is determined to be the main element.

14. The method according to claim 13, characterized in that The identifying the second target image area from the fourth detection image comprises: Extracting a first image region and a second image region from the fourth detection image by performing edge detection on the fourth detection image, the first image region and the second image region respectively corresponding to a first coating layer and a second coating layer on two surfaces of the battery separator that are opposite to each other; and An image area in the fourth detection image located between the first image area and the second image area is identified as the second target image area.

15. A battery separator detection device, characterized in that: include: A first module is used to extract a first short-circuit trace area from a first detection image, wherein the first detection image is obtained by imaging the battery separator through a microscopic imaging device, and the first short-circuit trace area indicates an ablation trace on the battery separator caused by a battery short circuit caused by a metal foreign body in the battery separator; A second module is used to extract a predetermined image feature from a second detection image, wherein the second detection image is obtained by imaging the cross section of the battery separator across the first short-circuit trace area by the microscopic imaging device, and the metal foreign matter exists in the cross section of the first short-circuit trace area; and The third module is used to determine the type of the metal foreign matter according to the extraction result of the predetermined image feature.

16. The device according to claim 15, characterized in that The device also includes: The fourth module is used to determine the main element of the metal foreign matter, wherein the main element indicates the element of the metal foreign matter penetrating the battery separator.

17. A computing device, characterized in that include: at least one processor; as well as At least one memory is communicatively connected to the at least one processor, the at least one memory stores instructions, and when the instructions are executed by the at least one processor individually or collectively, the computing device performs the method of any one of claims 1 to 14.

18. A computer-readable storage medium, characterized in that: Instructions are stored, which, when executed individually or collectively by one or more processors of a computing device, cause the computing device to perform the method of any one of claims 1 to 14.

19. A computer program product, characterized in that The method comprises instructions which, when executed individually or collectively by one or more processors of a computing device, cause the computing device to perform the method of any one of claims 1 to 14.

Images