Battery tab detection method, device and storage medium

Abstract

The present application discloses a method for detecting battery tabs, including: obtaining a cross-sectional view of multiple layers of tabs of a battery to be detected; identifying and analyzing the cross-sectional view to obtain a plurality of connected regions, each of the connected regions including one tab or multiple adhesively connected tabs; determining the tab layer number corresponding to each connected region according to the position and number of the intersection points of the adhesively connected tabs in each connected region; calculating the total tab layer number of the multiple layers of tabs in the cross-sectional view according to the tab layer number corresponding to each connected region; and determining whether there is a fold in the multiple layers of tabs according to the total tab layer number and a preset true tab layer number. The battery tab detection method, device, and storage medium provided by the present application can automatically identify the tab folding situation, not only improving the detection efficiency but also effectively reducing the missed detection rate.

Description

Technical Field

[0001] The present application relates to the technical field of battery assembly, and in particular to a battery tab detection method, device and storage medium. Background Art

[0002] With the increasing number of electric vehicles, the application of power batteries is also increasing. At present, the manufacturing methods of bare power battery cells mainly include winding and lamination. Among them, the most widely used method is winding. In order to facilitate production and manufacturing, the cell pole pieces used for winding usually need to be die-cut, and only the part of the metal foil that needs to pass the current is retained. This part of the metal foil is the pole ear. Since the metal foil used in the lithium battery pole piece is extremely thin and has low strength, the pole ear is easy to fold during the winding process and is rolled into the cell coating area. There are two types of folding: one is folding into the pole piece where it is located; the other is folding onto the isolation film. The existing pole ear folding is generally detected by visual inspection and Hi-pot test for monitoring the resistance of the battery cell by applying voltage. However, manual visual inspection is inefficient and prone to missed detection. The Hi-pot test only has a high detection rate for the pole ear folding on the isolation film, but it is difficult to identify the pole ear folded into its own layer. The situation where the tab is folded into its own pole piece will cause the battery cell to have low capacitance, short circuit and other phenomena. Even worse, it may cause thermal runaway and fire. Summary of the invention

[0003] In view of the above problems, the present application provides a battery tab detection method, device and storage medium, which can automatically identify the folding of the tab, which not only improves the detection efficiency, but also effectively reduces the missed detection rate.

[0004] In a first aspect, the present application provides a battery tab detection method, comprising: obtaining a cross-sectional view of a multi-layer tab of a battery to be detected; identifying and analyzing the cross-sectional view to obtain multiple connected domains, each of the connected domains including one tab or multiple tabs adhered to each other; determining the number of tab layers corresponding to each connected domain based on the position and number of intersections of the tab adhesions in each connected domain; calculating the total number of tab layers of the multi-layer tabs in the cross-sectional view based on the number of tab layers corresponding to each connected domain; and determining whether the multi-layer tabs are folded based on the total number of tab layers and a preset number of actual tab layers.

[0005] In the battery tab detection method in the technical solution of the embodiment of the present application, after obtaining the cross-sectional view of the multi-layer tabs of the battery to be detected, the cross-sectional view is identified and analyzed to obtain a plurality of connected regions, and each connected region includes one tab or a plurality of mutually adhered tabs; according to the position and number of the intersection points of the adhered tabs in each connected region, each connected region is separately analyzed to obtain the number of tab layers corresponding to the connected region, so that the number of tab layers in each obtained connected region is more accurate; and according to the number of tab layers corresponding to each obtained connected region, the total number of tab layers of the multi-layer tabs in the cross-sectional view is determined. Compared with directly identifying the total number of tab layers in the cross-sectional view, the technical solution provided by the present application first proposes a technical solution for detecting and determining the intersection points of adhered tabs by using connected regions. It utilizes the possible intersection points of adhered tabs, divides the obtained cross-sectional view of the multi-layer tabs into a plurality of connected regions, then separately calculates the tabs in each connected region, and finally sums up the calculation results, so that the result of the total number of tab layers in the obtained cross-sectional view is more accurate. Therefore, when judging whether there is a fold in the multi-layer tabs according to the total number of tab layers and the preset true number of tab layers of the tabs, the judgment accuracy rate is relatively high, and the missed detection rate can be effectively reduced. In addition, the battery tab detection method in this embodiment can automatically identify the tab folding situation by introducing connected regions and performing related image recognition, which not only improves the detection efficiency but also can effectively reduce the missed detection rate.

[0006] In some embodiments, determining the number of tab layers corresponding to each connected region according to the position and number of the intersection points of the adhered tabs in each connected region includes: identifying the position and number of the intersection points of the adhered tabs in each connected region; if the number of intersection points in the connected region is 0, determining that the number of tab layers in the connected region is 1; if the number of intersection points in the connected region is 1 or more, dividing the connected region into a plurality of regions according to the position of the intersection points, and each region does not include the intersection point, and the connected region is a plurality of mutually adhered tabs; determining the number of tab layers in the connected region according to the number of sub-connected regions in each of the plurality of regions, and each sub-connected region includes non-adhered parts or completely adhered parts of the plurality of mutually adhered tabs. In this embodiment, when there is an intersection point in the connected region, it indicates that there are a plurality of mutually adhered tabs in the connected region. At this time, the connected region needs to be divided into a plurality of regions along the length extension direction of the tabs according to the position of the intersection point. Since each region no longer includes the intersection point, therefore, in the obtained plurality of regions, the situation where two adhered parts are regarded as one sub-connected region due to the existence of partially adhered tabs in a certain region will not occur, which is beneficial to accurately determining the number of tab layers in each region.

[0007] In some embodiments, dividing the connected domain into a plurality of regions according to the position of the intersection point, and each of the regions does not include the intersection point, includes: taking a preset offset along the extending direction of the connected domain on both sides of the position of each intersection point as the region boundary; dividing the connected domain into the plurality of regions according to the region boundary, and each of the regions does not include the intersection point. In this embodiment, taking a preset offset along the extending direction of the connected domain on both sides of the position of each intersection point as the region boundary avoids dividing the tab part near the intersection point into the region, so as to avoid double counting of the tabs at the boundary due to each region being divided too narrow, thereby further improving the detection accuracy of the number of sub-connected domains in the region.

[0008] In some embodiments, identifying and analyzing the cross-sectional view to obtain a plurality of connected domains, and each of the connected domains includes one tab or a plurality of mutually adhered tabs, includes: eliminating the tab adhesion holes with an area smaller than a preset threshold in the cross-sectional view to obtain a first image; performing connected domain analysis on the first image to obtain the plurality of connected domains, and each of the connected domains includes one tab or a plurality of mutually adhered tabs. In this embodiment, eliminating the tab adhesion holes with an area smaller than a preset threshold in the cross-sectional view can improve the efficiency.

[0009] In some embodiments, eliminating the tab adhesion holes with an area smaller than a preset threshold in the cross-sectional view to obtain a first image includes: performing binarization processing on the cross-sectional view to obtain a binarized image; setting the pixels at the positions of the connected domains with an area smaller than the preset threshold in the binarized image to white to obtain the first image.

[0010] In some embodiments, setting the pixels at the positions of the connected domains with an area smaller than the preset threshold in the binarized image to white to obtain the first image includes: swapping the pixel values of the pixels with a pixel value of 0 and the pixels with a pixel value of 255 in the binarized image to obtain a swapped image; determining the positions of the connected domains with a pixel value of 255 and an area smaller than the preset threshold in the swapped image; adjusting the pixel values of the pixels corresponding to the positions of the connected domains with an area smaller than the preset threshold in the swapped image in the binarized image to 255 to obtain the first image.

[0011] In some embodiments, determining the number of tab layers of the connected domain according to the number of sub-connected domains in each of the plurality of regions includes: determining the number of sub-connected domains in each of the plurality of regions; taking the maximum value of the number of sub-connected domains in the plurality of regions in the connected domain as the number of tab layers of the connected domain. In this embodiment, taking the maximum value of the number of sub-connected domains in the plurality of regions in the connected domain as the number of tab layers of the connected domain is beneficial to accurately calculate the number of tab layers in the region, thereby accurately detecting whether the tabs are folded.

[0012] In some embodiments, determining the number of sub-connected regions in each of the multiple regions includes: obtaining the lengths of all sub-connected regions in each of the multiple regions; determining the number of sub-connected regions in the region according to the number of sub-connected regions whose length in each region is greater than 1 / N times the length of the sub-connected region with the longest length in the region, where N is greater than 0. In this embodiment, a method for determining the number of sub-connected regions in a region by the number of sub-connected regions whose length in each region is greater than 1 / N times the length of the sub-connected region with the longest length in the region is proposed, which realizes avoiding misjudging burrs as adhered tabs, thus eliminating burr interference and further improving the detection accuracy of the tab layers.

[0013] In a second aspect, the present application provides a battery tab detection device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the battery tab detection method in the above embodiments.

[0014] In a third aspect, the present application provides a computer-readable storage medium storing a computer program, characterized in that the computer program realizes the battery tab detection method in the above embodiments when executed by a processor.

[0015] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the following specifically illustrates the specific implementation manners of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present application. And in all the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0017] Figure 1 Schematic diagrams of several adhesion states of tabs discovered by the inventor;

[0018] Figure 2 Schematic diagram of the structure of a battery tab detection system in some embodiments of the present application;

[0019] Figure 3 Schematic diagram of the process of a battery tab detection method in some embodiments of the present application;

[0020] Figure 4It is a cross-sectional view of a battery tab in some embodiments of the present application;

[0021] Figure 5 For Figure 4 It is a schematic diagram after dividing the connected regions of the cross-sectional view shown;

[0022] Figure 6 For Figure 4 It is a schematic diagram after dividing the region of the cross-sectional view shown;

[0023] Figure 7 It is a schematic flowchart of the method for detecting battery tabs in some embodiments of the present application to eliminate tab adhesion holes;

[0024] Figure 8 For the present application Figure 7 The cross-sectional view in the flowchart shown;

[0025] Figure 9 For the present application Figure 7 The binary image obtained after thresholding the cross-section in the flowchart shown Figure 2 ;

[0026] Figure 10 It is a schematic diagram of burrs on battery tabs in some embodiments of the present application;

[0027] Figure 11 It is a schematic example flowchart of the method for detecting battery tabs in some embodiments of the present application;

[0028] Figure 12 It is a schematic structural diagram of a battery tab detection device in some embodiments of the present application. Detailed implementation manners

[0029] Next, embodiments of the technical solutions of the present application will be described in detail with reference to the accompanying drawings. The following embodiments are only used to illustrate the technical solutions of the present application more clearly, and thus are only examples and should not be used to limit the protection scope of the present application.

[0030] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above accompanying drawings are intended to cover non-exclusive inclusion.

[0031] In the description of the embodiments of the present application, technical terms such as "first" and "second" are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity, specific order, or primary-secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "a plurality of" is more than two, unless otherwise clearly and specifically defined.

[0032] Reference to "embodiment" herein means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0033] In the description of the embodiments of the present application, the term "and / or" is merely a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this article generally represents an "or" relationship between the associated objects before and after.

[0034] In the description of the embodiments of the present application, the term "a plurality of" refers to more than two (including two). Similarly, "a plurality of groups" refers to more than two groups (including two groups), and "a plurality of pieces" refers to more than two pieces (including two pieces).

[0035] In the description of the embodiments of the present application, the orientation or positional relationship indicated by technical terms such as "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the embodiments of the present application and simplifying the description, rather than indicating or implying that the indicated device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the embodiments of the present application.

[0036] In the description of the embodiments of the present application, unless otherwise clearly specified and limited, technical terms such as "installation", "connection", "connection", "fixation", etc. should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or integrated; it can also be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and can be the communication inside 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 specific circumstances.

[0037] Since the situation where the battery tab is folded into its own electrode tab can cause phenomena such as low capacity and short circuit in the battery cell, and even more seriously, it can cause thermal runaway and fire. Therefore, during the production process, it is necessary to detect whether the battery tab is folded. In the current detection methods, manual visual inspection has low efficiency and is prone to missed detection. The Hi-pot test has a high detection rate only for the tabs folded onto the separator, but it is difficult to identify the tabs folded into their own layers. Currently, there is no detection method that can automatically identify the folding situation of the tabs, which can not only improve the detection efficiency but also effectively reduce the missed detection rate.

[0038] In order to alleviate the above problems, the applicant has studied and found that for a battery with a fixed model, the number of layers of its battery tabs is fixed. When the battery tab is folded, the number of layers of the battery tab will increase. For example, when a tab is folded, its number of layers changes from the original 1 layer to 2 layers. Therefore, it is possible to determine whether the tab in the battery is folded by detecting the number of layers of the battery tab and judging whether the number of layers of the battery tab is the same as the actual true number of tab layers.

[0039] Based on this, the applicant has found that by taking a cross-sectional image of the multi-layer tabs of the battery to be detected and analyzing the pixel brightness and distribution of the cross-sectional image, several line diagrams corresponding to the multi-layer tabs of the battery to be detected can be obtained. Multiple sampling points can be randomly set, the line information at each sampling point can be obtained, and the maximum value among them can be taken as the statistical result of the multi-layer tabs. However, the applicant has found through practice that during the actual production process, since the tab foils will adhere, when the sampling point falls on the adhesion position, it will affect the statistics of the number of tab layers after cross-section segmentation, resulting in inaccurate statistics of the number of tab layers.

[0040] Based on the above considerations, in order to solve the problem, the inventor has found through in-depth research that the tabs have the following several adhesion states, such as Figure 1 shown in Figure 1A solid line represents a tab or multiple completely adhered tabs. In the first case, a single tab 111 is not adhered to other tabs at all, and there are no intersection points on the tab 111. In the second case, two tabs 112 and 113 and more than two tabs (not shown) are adhered at a certain intersection point 110 and do not separate again, and there is 1 intersection point 110 on the two tabs 112 and 113. In the third case, two tabs 114 and 115 and more than two tabs (not shown) are adhered at a certain intersection point and then separate again at the intersection point position, and there is 1 intersection point 120 on the two tabs 114 and 115. In the fourth case, two tabs 116 and 117 and more than two tabs (not shown) are adhered at the first intersection point 130 and are temporarily not separated, and then separate at the second intersection point 140. If they are adhered again at the middle position 40 of the tab (as shown in the figure), then there will be a total of 3 intersection points 130, 140, and 150 on the two tabs 116 and 117. If they separate at the root (near the tab side) or the tail of the tab (not shown), then there will be a total of 2 intersection points on the line graph. In the fifth case, the combination mode, there are adhesions at different positions between the tabs in the previous modes, and the number of adhesion intersection points depends on the position where the adhesion occurs. Figure 1 There are a total of 3 intersection points 160, 170, and 180 on the 4 tabs 118, 119, 120, and 121.

[0041] Based on this, the applicant provides the following several embodiments, so that on the basis of realizing the automatic recognition of the tab folding situation and improving the detection efficiency, it is also possible to fully consider the above-mentioned several tab adhesion situations when determining the tab layer number, accurately detect the tab layer number of the battery tabs, and reduce the missed detection rate.

[0042] First, the devices and systems for implementing the detection methods of all embodiments of the present application will be described.

[0043] See Figure 2 , a detection system optional for implementing the detection method of the embodiment provided by the present application will be described. The detection system includes: a processing device 1, a camera device 2, and a conveying device. Among them, the conveying device includes: a conveyor belt 3 and one or more trays 4 located on the conveyor belt 3, and the trays 4 are used to place the battery 5 to be detected. The camera of the camera device 3 is aligned with the battery 5 to be detected on the tray 4 to take a cross-sectional view of the multi-layer tabs on the battery 5 to be detected. The processing device 1 is connected to the camera device 2 and is used to obtain the cross-sectional view of the multi-layer tabs of the battery 5 to be detected taken by the camera device 2, and implement the battery tab detection method in the embodiment of the present application to automatically recognize the tab folding situation. The battery tab detection method disclosed in the embodiment of the present application can be but is not limited to being used in the above battery tab detection device or system, and the above is only for illustrative purposes.

[0044] Next, embodiments of the battery tab detection method of the present application will be described.

[0045] According to the battery tab detection method of some embodiments of the present application, as Figure 3 shown, it includes:

[0046] Step S11: Obtain a cross-sectional view of multiple layers of tabs of the battery to be detected.

[0047] Step S12: Identify and analyze the cross-sectional view to obtain multiple connected components, and each connected component includes one tab or multiple mutually adhered tabs.

[0048] Step S13: Determine the tab layer number corresponding to each connected component according to the position and number of the intersection points where the tabs in each connected component are adhered.

[0049] Step S14: Calculate the total tab layer number of the multiple layers of tabs in the cross-sectional view according to the tab layer number corresponding to each connected component.

[0050] Step S15: Determine whether there is a fold in the multiple layers of tabs according to the total tab layer number and the preset true tab layer number.

[0051] Assume that the cross-sectional view of the multiple layers of tabs of the battery to be detected obtained is as Figure 4 shown, where a solid line represents one tab or multiple completely adhered tabs. Identify and analyze the cross-sectional view to obtain multiple connected components. A connected component refers to an image area composed of foreground pixel points with the same pixel value and adjacent positions in the image. Since there is no connected area between non-adhered tabs in the cross-sectional view, only a single tab or multiple mutually adhered tabs have a connected area. Therefore, by performing connected component analysis on the cross-sectional view Figure 4 multiple non-adhered connected components in the multiple layers of tabs can be found. One connected component represents one tab, or multiple mutually adhered tabs.

[0052] Figure 5 To be Figure 4 a schematic diagram after the connected component division of the shown cross-sectional view, each dashed box represents a connected component, identify Figure 4Six connected components (1, 2, 3, 4, 5, and 6) can be obtained. The number of layers of the tab corresponding to each connected component is determined according to the position and number of the intersection points of the tab adhesions in each connected component, so that the number of tab layers in each obtained connected component is more accurate. And according to the number of tab layers corresponding to each obtained connected component, the total number of tab layers of the multi-layer tabs in the cross-sectional view is determined. Compared with directly identifying the total number of tab layers in the cross-sectional view, the technical solution provided by the present application first proposes a technical solution for detecting and determining the intersection points of tab adhesions by using connected components. It uses the possible intersection points of tab adhesions to divide the cross-sectional view of the obtained multi-layer tabs into multiple connected components, and then separately calculates the tabs in each connected component and sums the calculation results, so that the result of the total number of tab layers in the obtained cross-sectional view is more accurate. Therefore, when judging whether there is a fold in the multi-layer tabs according to the total number of tab layers and the preset true number of tab layers of the tabs, the judgment accuracy is relatively high, and the missed detection rate can be effectively reduced. In addition, the battery tab detection method in this embodiment can automatically identify the tab folding situation by introducing connected components and performing related image recognition, which not only improves the detection efficiency but also can effectively reduce the missed detection rate.

[0053] According to some embodiments of the present application, determining the number of tab layers corresponding to each connected component according to the position and number of the intersection points of the tab adhesions in each connected component includes: identifying the position and number of the intersection points of the tab adhesions in each connected component; if the number of intersection points in the connected component is 0, determining that the number of tab layers of the connected component is 1; if the number of intersection points in the connected component is 1 or more, dividing the connected component into multiple regions according to the positions of the intersection points, and each region does not include intersection points, and the connected component is multiple mutually adhered tabs; determining the number of tab layers of the connected component according to the number of sub-connected components in each region of the multiple regions, and each sub-connected component includes non-adhered parts or completely adhered parts of the multiple mutually adhered tabs.

[0054] When determining the number of tab layers corresponding to each connected component, the skeleton of the connected component can be extracted. Here, the skeleton can be understood as the lines of the connected component, and the positions and numbers of the intersection points on the skeleton are calculated and determined according to the positions and numbers of the intersection points.

[0055] If the number of intersection points in a connected component is 0, it can be determined that the connected component is a single tab, and the number of tab layers in the connected component can be directly determined to be 0. As Figure 5 shown, the number of intersection points in the first connected component 1 is 0, so the first connected component 1 includes a single tab 11; the number of intersection points in the fourth connected component 4 is 0, so the fourth connected component 4 includes a single tab 16.

[0056] If the number of intersection points in a connected component is 1 or more, the connected component is multiple mutually adhered tabs. As Figure 5As shown, there is an intersection point 101 in the second connected region 2, and the number of intersection points is 1. The second connected region 2 includes two mutually adhered tabs 12 and 13; there is an intersection point 102 in the third connected region 3, and the number of intersection points is 1. The third connected region 3 includes two mutually adhered tabs 14 and 15; there are intersection points 103, 104, and 105 in the fifth connected region 5, and the number of intersection points is 3. The fifth connected region 5 includes two mutually adhered tabs 17 and 18; there are intersection points 106, 107, and 108 in the sixth connected region 6, and the number of intersection points is 3. The sixth connected region 6 includes four mutually adhered tabs 19, 20, 21, and 22.

[0057] If the connected region is multiple mutually adhered tabs, it is necessary to divide the connected region into multiple regions along the extension direction of the tab length according to the position of the intersection point. Since each region does not include the intersection point position, therefore, in the obtained multiple regions, there will be no situation where two adhered parts are regarded as a sub-connected region due to the existence of partially adhered tabs in a certain region. In this embodiment, each sub-connected region in each region includes the non-adhered part or the completely adhered part of multiple mutually adhered tabs, which is beneficial to accurately determining the number of layers of the tabs in each region.

[0058] As Figure 6 shown is the schematic diagram after dividing the cross-sectional view shown in Figure 4 where each thin dashed box represents a connected region, and each thickened dashed box represents a region.

[0059] There is 1 intersection point 101 in the second connected region 2. Along the extension direction of the tab length, it can be divided into 2 regions 21 and 22. One of the regions 21 includes two sub-connected regions 201 and 202, and each sub-connected region is the non-adhered part of the tabs. Among them, the sub-connected region 201 is the part where the tab 12 is not adhered to the tab 13, and the sub-connected region 202 is the part where the tab 13 is not adhered to the tab 12; the other region 22 includes a sub-connected region 203, and this sub-connected region 203 is the part where the tab 12 and the tab 13 are completely adhered.

[0060] There is 1 intersection point 102 in the third connected region 3. Along the extension direction of the tab length, it can be divided into 2 regions 31 and 32. One of the regions 31 includes two sub-connected regions 301 and 302, and each sub-connected region is the non-adhered part of the tabs. Among them, the sub-connected region 301 is the part where the tab 14 is not adhered to the tab 15, and the sub-connected region 302 is the part where the tab 15 is not adhered to the tab 14; the other region 32 also includes two sub-connected regions, and each sub-connected region is the non-adhered part of the tabs. Among them, the sub-connected region 303 is the part where the tab 14 is not adhered to the tab 15, and the sub-connected region 304 is the part where the tab 15 is not adhered to the tab 14.

[0061] There are 3 intersection points in the fifth connected region 5. Along the extending direction of the tab length, it can be divided into 4 regions 51, 52, 53 and 54. Among them, both regions 51 and 53 include two sub-connected regions. Region 51 includes sub-connected regions 501 and 502. Sub-connected region 501 is the part where tab 17 is not adhered to tab 18, and sub-connected region 502 is the part where tab 18 is not adhered to tab 17. Region 53 includes sub-connected regions 504 and 505. Sub-connected region 504 is the part where tab 18 is not adhered to tab 17, and sub-connected region 505 is the part where tab 17 is not adhered to tab 18. The other two regions 52 and 54 both include one sub-connected region. Among them, region 52 includes sub-connected region 503, and region 54 includes sub-connected region 506. Sub-connected regions 503 and 506 are both the parts where tabs 17 and 18 are completely adhered.

[0062] There are 3 intersection points 106, 107 and 108 in the sixth connected region 6. Along the extending direction of the tab length, it can be divided into 4 regions 61, 62, 63 and 64. Both region 61 and region 62 include four sub-connected regions. Among them, region 61 includes sub-connected regions 601, 602, 603 and 604, and region 62 includes sub-connected regions 605, 606, 607 and 608. And each sub-connected region is the part where tabs 19, 20, 21 and 22 are not adhered to each other. Both region 63 and region 64 include three sub-connected regions. Among them, region 63 includes sub-connected regions 609, 610 and 611. Sub-connected region 609 is the part where tab 19 and tab 20 are completely adhered, sub-connected region 610 is tab 21, and sub-connected region 611 is tab 22. Region 64 includes sub-connected regions 612, 613 and 614. Sub-connected region 612 is the part where tab 19 and tab 20 are completely adhered, sub-connected region 613 is tab 21, and sub-connected region 614 is tab 22.

[0063] According to some embodiments of the present application, optionally, the connected region is divided into multiple regions according to the positions of the intersection points, and each region does not include intersection points, including: taking a preset offset on both sides of the position of each intersection point along the extending direction of the connected region as the region boundary; dividing the connected region into multiple regions according to the region boundary, and each region does not include intersection points.

[0064] As Figure 6 shown is the schematic diagram after dividing the cross-sectional view shown in Figure 4 taking the region boundary for region division. Figure 6The short solid lines perpendicular to the length extension direction of the connected region represent the region boundaries. When dividing the connected region into multiple regions according to the intersection positions, a certain offset is taken on both sides of each intersection along the extension direction of the tab (i.e., the extension direction of the connected region) as the region boundary, and both ends of the connected region are automatically determined as the region boundaries. The connected region is divided into multiple regions that do not include intersections according to the region boundaries. Among them, the preset offset can be set according to actual needs. For example, the preset offset can be 5 pixel points, 8 pixel points, 10 pixel points, etc.

[0065] Since the tab parts near the intersections may still be adhered, if the region is directly divided based on the positions of the intersections, the number of sub-connected regions within the determined regions may still be inaccurate. In this embodiment, a preset offset is taken on both sides of the position of each intersection along the extension direction of the connected region as the region boundary, avoiding dividing the tab parts near the intersections into the regions, so as to avoid double-counting of the tabs at the boundaries due to each region being divided too narrow, thereby further improving the detection accuracy of the number of sub-connected regions within the regions.

[0066] According to some embodiments of the present application, optionally, identifying and analyzing the cross-sectional view to obtain multiple connected regions, each connected region including one tab or multiple mutually adhered tabs, includes: eliminating the tab adhesion holes with an area smaller than a preset threshold in the cross-sectional view to obtain a first image; performing connected region analysis on the first image to obtain multiple connected regions, each connected region including one tab or multiple mutually adhered tabs.

[0067] As Figure 6 shown in the fifth connected region 5, when there is a tab adhesion hole ( Figure 6 at the position shown in region 53 of the fifth connected region 5 in Figure 6 ), if the area of the tab adhesion hole is small enough, the tab adhesion hole can be eliminated to improve the detection efficiency. And after eliminating the small-area tab adhesion hole, since the tabs will not adhere at the end close to the battery ( Figure 6 the left side in

[0068] ), it will not affect the determination of the tab layer number of the connected region. Among them, the preset threshold can be set according to actual needs. For example, the preset threshold can be 25 pixel points, 20 pixel points, 25 pixel points, etc.

[0068] The specific process of eliminating the tab adhesion holes with an area smaller than the preset threshold in the cross-sectional view to obtain the first image is as Figure 7 shown, including:

[0069] Step S21: Performing binarization processing on the cross-sectional view to obtain a binarized image, where the cross-sectional view is as Figure 4 shown, and the binarized image is as Figure 8 shown.

[0070] Step S22: Swap the pixel values of the pixels with a pixel value of 0 and the pixels with a pixel value of 255 in the binary image to obtain a swapped image, as shown in Figure 9 shown.

[0071] Step S23: Determine the positions of the connected regions in the swapped image with a pixel value of 255 and an area smaller than a preset threshold.

[0072] Step S24: Adjust the pixel values of the pixels at the positions of the connected regions in the binary image corresponding to the positions of the connected regions with an area smaller than the preset threshold in the swapped image to 255 to obtain a first image.

[0073] According to some embodiments of the present application, eliminating the tab adhesion holes with an area smaller than a preset threshold in the cross-sectional view to obtain a first image includes: performing binarization processing on the cross-sectional view to obtain a binary image;

[0074] Setting the pixels at the positions of the connected regions with an area smaller than the preset threshold in the binary image to white to obtain a first image.

[0075] When eliminating the possible tab adhesion holes in the cross-sectional view, the cross-sectional view can be first binarized to obtain a binary image. In this binary image, the pixel values of the pixel points of the tab part are 255 and are displayed as white; the pixel values of the pixel points of the background part are 0 and are displayed as black. The black connected regions with an area smaller than the preset threshold in the binary image can be confirmed as tab adhesion holes. By setting the pixel points at the positions of the black connected regions with an area smaller than the preset threshold to white, that is, the pixel values become 255, the color of the tab adhesion holes is made the same as the color of the tabs, and the tab adhesion holes and the tabs are visually integrated to eliminate the tab adhesion holes.

[0076] According to some embodiments of the present application, setting the pixels at the positions of the connected regions with an area smaller than the preset threshold in the binary image to white to obtain a first image includes: swapping the pixel values of the pixels with a pixel value of 0 and the pixels with a pixel value of 255 in the binary image to obtain a swapped image; determining the positions of the connected regions in the swapped image with a pixel value of 255 and an area smaller than the preset threshold; adjusting the pixel values of the pixels at the positions of the connected regions in the binary image corresponding to the positions of the connected regions with an area smaller than the preset threshold in the swapped image to 255 to obtain a first image.

[0077] When eliminating the ear adhesion holes as described above, the pixel points at the positions of the black connected regions with an area smaller than a preset threshold can be directly set to white to eliminate the ear adhesion holes. In this embodiment, another implementation manner is given. First, the pixel values of the pixels with a pixel value of 0 and the pixels with a pixel value of 255 in the binary image are swapped to obtain a swapped image. In the swapped image, the pixel values of the pixel points of the ear part are 0 and are displayed as black, and the pixel values of the pixel points of the background part are 255 and are displayed as white. By identifying the white connected regions with an area smaller than a preset threshold, and adjusting the pixel values at the positions of the white connected regions in the binary image corresponding to the swapped image with an area smaller than the preset threshold to 255 to obtain a first image.

[0078] According to some embodiments of the present application, optionally, determining the number of ear layers of a connected region according to the number of sub-connected regions in each of a plurality of regions includes: determining the number of sub-connected regions in each of the plurality of regions; taking the maximum value of the number of sub-connected regions in the plurality of regions in the connected region as the number of ear layers of the connected region.

[0079] Combined with the attached Figure 4 、the attached Figure 5 and the attached Figure 6 for illustration, in the attached Figure 5 the second connected region 2 is divided into two regions 21 and 22. Region 21 includes two sub-connected regions 201 and 202, and region 22 includes one sub-connected region 203. The maximum value of the number of sub-connected regions in these two regions 21 and 22 is 2, so the number of ear layers of the second connected region 2 is 2 layers.

[0080] The third connected region 3 is divided into two regions 31 and 32. Region 31 includes two sub-connected regions 301 and 302, and region 32 includes two sub-connected regions 303 and 304. The maximum value of the number of sub-connected regions in these two regions 31 and 32 is 2, so the number of ear layers of the second connected region 2 is 2 layers.

[0081] The fifth connected region 5 is divided into four regions 51, 52, 53 and 54. Region 51 includes two sub-connected regions 501 and 502, region 52 includes one sub-connected region 503, region 53 includes two sub-connected regions 504 and 505, and region 54 includes one sub-connected region 506. The maximum value of the number of sub-connected regions in these four regions 51, 52, 53 and 54 is 2, so the number of ear layers of the fifth connected region 5 is 2 layers.

[0082] The sixth connected region 6 is divided into 4 regions 61, 62, 63, and 64. Region 61 includes 4 sub-connected regions 601, 602, 603, and 604. Region 62 includes 4 sub-connected regions 605, 606, 607, and 608. Region 63 includes 3 sub-connected regions 609, 610, and 611. Region 64 includes 3 sub-connected regions 612, 6130, and 614. The maximum number of sub-connected regions in these 4 regions 61, 62, 63, and 64 is 4. Then, the tab layer number of the sixth connected region 6 is 4 layers.

[0083] When the tab is folded, the tab layer number increases in some regions and decreases in some regions in the cross-sectional view. Therefore, to accurately detect whether the tab is folded, it is necessary to take the maximum value of the number of sub-connected regions in multiple regions of the connected region as the tab layer number of the connected region. In this embodiment, taking the maximum value of the number of sub-connected regions in multiple regions of the connected region as the tab layer number of the connected region is beneficial to accurately calculate the tab layer number in the region, so as to accurately detect whether the tab is folded.

[0084] According to some embodiments of the present application, optionally, determining the number of sub-connected regions in each of the multiple regions includes: obtaining the length of all sub-connected regions in each of the multiple regions; determining the number of sub-connected regions in the region according to the number of sub-connected regions whose length is greater than 1 / N times the length of the longest sub-connected region in the region, where N>0.

[0085] As Figure 10 shown, if burrs 200 appear on the surface of the tab 11 in a certain connected region 1, then in the regions 1001 and 1002 divided according to the intersection point 100, the number of sub-connected regions where burrs 200 are easily determined to exist in region 1001 is greater than the true tab layer number of this region 1001, resulting in an inaccurate final detection result.

[0086] The inventor found that when determining the tab layer number by setting sampling points on the line graph of the multi-layer tabs of the battery to be detected, there will be a problem of how to select the sampling point interval (step size), that is, how many pixels to skip to count the number of tabs in the vertical direction. If the step size is selected too large, the tabs are partially separated and not counted, which easily leads to the count being less than the true value and misjudging the tab as folded; a small step size can reduce the problem of missed statistics to a certain extent, but it is more sensitive to burrs generated by local abnormal segmentation and is prone to overcounting. Secondly, it increases the computational complexity of the program.

[0087] Before counting the number of tab layers in each connected component in this embodiment, it is necessary to eliminate local burrs to prevent miscounting burrs as tabs. The processing method is as follows: After dividing each connected component into regions, determine the length of each sub-connected component in each region, and determine the maximum value of the lengths of all sub-connected regions in the region. When the length of a sub-connected component in the region is less than 1 / N * the maximum value, when counting the number of sub-connected components in the region, do not count this sub-connected component. For example, assume Figure 10 In region 1001 in Figure 10 , there are two sub-connected components 10 and 20. The length of sub-connected component 10 is L2, and the length of sub-connected component 20 is L1. If the length L1 of sub-connected component 20 is less than 1 / N * L2, then do not count this sub-connected component 20; only count the sub-connected component 10 in this region 1001 whose length is greater than or equal to 1 / N * L2. Among them, N > 0, N is an empirical value, and N usually takes a value between 5 and 6.

[0088] According to the number of sub-connected components in each region whose length is greater than 1 / N times the length of the longest sub-connected component in the region, determine the number of sub-connected components in the region, which realizes avoiding misjudging burrs as adhered tabs, thereby eliminating burr interference and further improving the detection accuracy of the number of tab layers.

[0089] The following are some embodiments of the present application. Refer to Figure 11 , specifically including:

[0090] S31: Obtain a cross-sectional view of the multi-layer tabs of the battery to be detected.

[0091] S32: Identify and analyze the cross-sectional view to obtain multiple connected components, and each connected component includes one tab or multiple adhered tabs.

[0092] After obtaining the cross-sectional view, perform binarization processing on the cross-sectional view to obtain a binary image. Binarization processing is to change the gray value of the points on the image to 0 or 255, that is, to make the whole image show an obvious black and white effect. In this embodiment, the pixel values of the pixel points of the tab part in the cross-sectional view are changed to 255 and displayed as white; the pixel values of the pixel points of the background part are changed to 0 and displayed as black.

[0093] Perform connected component analysis on the binary image to obtain multiple connected components, and each connected component includes at least one tab or multiple adhered tabs. Among them, each connected component may be a tab or background interference, and can be screened according to the length characteristics of the tab. For example: The length of the tab is generally a fixed value, and the connected component with a length roughly the same as this fixed value can be determined as the required connected component, and the connected component with a length too short or too long compared with this fixed value can be determined as interference noise.

[0094] S33: Select a connected component and determine the position and number of intersection points in the connected component.

[0095] The position and number of intersection points in the connected domain can be calculated by extracting the skeleton of the connected domain.

[0096] S34: Determine whether the number of intersection points in the connected domain is greater than 0. If it is not greater than 0, execute step S5; otherwise, execute step S6.

[0097] S35: Determine that the number of tab layers corresponding to the connected domain is 1.

[0098] See Figure 5 , if the number of intersection points in a connected domain is 0, it can be determined that the connected domain is a single tab, and the number of tab layers in the connected domain can be directly determined to be 0. If the number of intersection points in a connected domain is 1 or more, the connected domain is multiple mutually adhered tabs. At this time, step S6 needs to be continued to further determine the number of layers of the multiple mutually adhered tabs in the connected domain.

[0099] S36: Divide the connected domain into multiple regions according to the positions of the intersection points, and each region does not include intersection points.

[0100] If there is an intersection part where two tabs intersect in a certain region, when judging the number of sub-connected domains in the region later, the two tabs with the intersection part will be regarded as one sub-connected domain, which will lead to inaccurate detection of the number of sub-connected domains in the region. Therefore, it is necessary to divide the connected domain into multiple regions along the extension direction of the tab length according to the positions of the intersection points, and each region does not include the intersection point positions, so as to facilitate accurately determining the number of tab layers in each region.

[0101] Optionally, since the tab parts near the intersection points may still be adhered, if the region is divided directly based on the position of the intersection point, the number of sub-connected domains in the determined region may still be inaccurate. In this embodiment, a preset offset is taken on both sides of the position of each intersection point along the extension direction of the connected domain as the region boundary, avoiding dividing the tab parts near the intersection points into the region, so as to further improve the detection accuracy of the number of sub-connected domains in the region.

[0102] S37: Determine the number of sub-connected domains in the region according to the number of sub-connected domains in each region whose length is greater than 1 / N times the length of the longest sub-connected domain in the region.

[0103] Since if there are burrs on the tab surface in a certain connected domain, in the region divided according to the intersection points, the number of sub-connected domains that can be easily determined in the region with burrs is greater than the actual number of tab layers in the region, resulting in inaccurate final detection results. Therefore, in this embodiment, before counting the number of tab layers of each connected domain, local burrs need to be removed to prevent miscounting burrs as tabs. The specific processing method is as follows:

[0104] Determine the lengths of the sub-connected regions in each region, and determine the maximum value max_length of the lengths of all sub-connected regions within that region. When the length of a sub-connected region within that region is less than

[0105] 1 / N * max_length, when counting the number of sub-connected regions within that region, do not count this sub-connected region; only count the sub-connected regions within that region with lengths greater than or equal to 1 / N * max_length. Among them, N > 0, N is an empirical value, and N usually takes a value between 5 and 6.

[0106] Since when the tab turns over, the number of tab layers increases in some regions and decreases in some regions in the cross-sectional view, in order to accurately detect whether the tab has turned over, it is necessary to take the maximum value of the number of sub-connected regions in multiple regions within the connected region as the number of tab layers of the connected region.

[0107] S38: Determine whether all connected regions have been traversed. If it is determined to be yes, execute step S9; otherwise, return to step S3 for execution;

[0108] After executing steps S5 and S7, execute step S8 to determine whether all connected regions have been traversed. If all connected regions have been traversed, continue to execute step S9 to further determine the total number of tab layers of the multi-layer tabs in the cross-sectional view. If not all connected regions have been traversed, it is necessary to continue to execute step S3 to continue analyzing the connected regions for which the number of tab layers has not been determined.

[0109] S39: Calculate the total number of tab layers of the multi-layer tabs in the cross-sectional view according to the number of tab layers corresponding to each connected region.

[0110] Add up the number of tab layers corresponding to each connected region, and the total number of tab layers of the multi-layer tabs in the cross-sectional view can be obtained. Taking the Figure 5 example shown, the number of tab layers corresponding to the first connected region is 1, the number of tab layers corresponding to the second connected region is 2, the number of tab layers corresponding to the third connected region is 2, the number of tab layers corresponding to the fourth connected region is 1, the number of tab layers corresponding to the fifth connected region is 2, and the number of tab layers corresponding to the sixth connected region is 4. Then Figure 5 the corresponding cross-sectional view Figure 4 the total number of tab layers of the multi-layer tabs is 12.

[0111] S40: Determine whether the multi-layer tabs are folded according to the total number of tab layers and the preset true number of tab layers.

[0112] When the battery tab is folded, the number of layers of the battery tab will increase. By detecting the number of layers of the battery tab and determining whether the number of layers of the battery tab is the same as the actual true tab layer number, it is determined whether the tab in the battery is folded. In the above example, the total number of tab layers of the multi-layer tabs in the cross-sectional view is 12. Assuming the true tab layer number is 12, the total number of tab layers is the same as the preset true tab layer number, and there is no folding of the multi-layer tabs in the cross-sectional view; assuming the true tab layer number is 10, then there is folding of the multi-layer tabs in the cross-sectional view.

[0113] For the battery tab detection method of this embodiment, aiming at the phenomenon that the tabs may stick together, analyzing the pattern of the intersection points generated by the sticking, it is proposed to use the connected domain as a unit, divide the connected domain into multiple regions by the intersection points of the tab sticking, and perform connected domain analysis on each region to count the number of tabs. Compared with directly identifying the total number of tab layers in the cross-sectional view, the result of the total number of tab layers in the obtained cross-sectional view is more accurate; therefore, when judging whether there is folding of the multi-layer tabs according to the total number of tab layers and the preset true tab layer number, the judgment accuracy is higher, and the missed detection rate can be effectively reduced. The battery tab detection method in this embodiment can automatically identify the folding situation of the tabs, which not only improves the detection efficiency but also can effectively reduce the missed detection rate. In addition, for some abnormal burrs appearing in the tab cross-sectional view, a method is proposed to determine the number of sub-connected domains in the region by the number of sub-connected domains whose length in each region is greater than 1 / N times the length of the longest sub-connected domain in the region, so as to eliminate the burr interference, improve the detection accuracy of the tab layer number, and further reduce the missed detection rate.

[0114] It is verified that for the production line production cell data, the overkill rate of the tab folding defect determined by using the battery tab detection method of this embodiment is within 3%, and the missed kill rate is controlled within 0.7%; and the probability of generating such burrs in the actual production line data is about 0.1%. Using the battery tab detection method of this embodiment, before entering the logic of counting the tab layer number, the local burr abnormality interference is eliminated, and the situation of missed kill caused by the burrs appearing due to abnormal tab segmentation is reduced.

[0115] See Figure 12 , a battery tab detection device for implementing the detection methods of all embodiments of the present application is described. The detection device includes: at least one processor 701; and a memory 702 communicatively connected to the at least one processor 701; wherein, the memory 702 stores instructions executable by the at least one processor 701, and the instructions are executed by the at least one processor 701 so that the at least one processor 701 can execute the battery tab detection methods of all embodiments of the present application. Figure 3 The device shown does not include a camera device. Therefore, an external camera device can be used for shooting, and the battery tab detection device directly obtains the cross-sectional view of the multi-layer tabs of the battery to be detected that has been photographed from the external camera device.

[0116] Among them, the memory 702 and the processor 701 are connected in a bus manner. The bus may include any number of interconnected buses and bridges, and the bus connects various circuits of one or more processors 701 and the memory 702 together. The bus can also connect various other circuits together, such as peripheral devices, voltage regulators, and power management circuits, etc., which are well known in the art, so they will not be further described herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be a component or multiple components, such as multiple receivers and transmitters, and provides a unit for communicating with various other devices on the transmission medium. The data processed by the processor 701 is transmitted on the wireless medium through the antenna. Further, the antenna also receives data and transmits the data to the processor 701.

[0117] The processor 701 is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interface, voltage regulation, power management, and other control functions. The memory 702 can be used to store the data used by the processor 701 when executing operations.

[0118] A computer-readable storage medium according to some embodiments of the present application stores a computer program, characterized in that when the computer program is executed by a processor, it implements the battery tab detection method in any of the above embodiments.

[0119] That is, those skilled in the art can understand that all or part of the steps in implementing the methods of the above embodiments can be completed by instructing relevant hardware through a program. This program is stored in a storage medium, including several instructions to enable a device (which can be a single-chip microcomputer, a chip, etc.) or a processor to execute all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs.

[0120] 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 foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the various embodiments of the present application, and they should all be covered by the scope of the claims and the description of the present application. In particular, as long as there is no conflict, the technical features mentioned in each embodiment can be combined in any way. The present application is not limited to the specific embodiments disclosed in the text, but includes all technical solutions falling within the scope of the claims.

Claims

1. A method for detecting battery tabs, characterized in that Including: Obtain a cross-sectional view of the multi-layer tabs of the battery to be detected; Identify and analyze the cross-sectional view to obtain multiple connected components, each of the connected components including one tab or multiple adhered tabs; Determine the tab layer number corresponding to each connected component according to the position and number of the intersection points where the tabs in each connected component are adhered; Calculate the total tab layer number of the multi-layer tabs in the cross-sectional view according to the tab layer number corresponding to each connected component; Judge whether there is folding of the multi-layer tabs according to the total tab layer number and the preset true tab layer number.

2. The battery tab detection method according to claim 1, wherein, The determining the tab layer number corresponding to each connected component according to the position and number of the intersection points where the tabs in each connected component are adhered includes: Identify the position and number of the intersection points where the tabs in each connected component are adhered; If the number of the intersection points in the connected component is 0, determine that the tab layer number of the connected component is 1; If the number of the intersection points in the connected component is 1 or more, divide the connected component into multiple regions according to the positions of the intersection points, and each region does not include the intersection points, and the connected component is multiple adhered tabs; Determine the tab layer number of the connected component according to the number of sub-connected components in each of the multiple regions, and each sub-connected component includes non-adhered parts or fully adhered parts of the multiple adhered tabs.

3. The battery tab detection method according to claim 2, wherein The dividing the connected component into multiple regions according to the positions of the intersection points, and each region does not include the intersection points includes: Take a preset offset on both sides of the position of each intersection point along the extending direction of the connected component as the region boundary; Divide the connected component into the multiple regions according to the region boundary, and each region does not include the intersection points.

4. The battery tab detection method according to claim 1, wherein The identifying and analyzing the cross-sectional view to obtain multiple connected components, each of the connected components including one tab or multiple adhered tabs includes: Eliminate the tab adhesion holes with an area smaller than a preset threshold in the cross-sectional view to obtain a first image; Perform connected component analysis on the first image to obtain the multiple connected components, each of the connected components including one tab or multiple adhered tabs.

5. The battery tab detection method according to claim 4, wherein, The eliminating the tab adhesion holes with an area smaller than a preset threshold in the cross-sectional view to obtain a first image includes: Perform binarization processing on the cross-sectional view to obtain a binarized image; Set the pixels at the positions of the connected components with an area smaller than the preset threshold in the binarized image to white to obtain the first image.

6. The battery tab detection method according to claim 5, wherein, The setting the pixels at the positions of the connected components with an area smaller than the preset threshold in the binarized image to white to obtain the first image includes: Interchange the pixel values of the pixels with a pixel value of 0 and the pixels with a pixel value of 255 in the binarized image to obtain an interchanged image; Determine the positions of the connected components with a pixel value of 255 and an area smaller than the preset threshold in the interchanged image; Adjust the pixel values of the pixels corresponding to the positions of the connected components with an area smaller than the preset threshold in the interchanged image in the binarized image to 255 to obtain the first image.

7. The battery tab detection method according to claim 2, wherein, The determining the tab layer number of the connected component according to the number of sub-connected components in each of the multiple regions includes: Determine the number of sub-connected domains in each of the multiple regions; Take the maximum value of the number of sub-connected domains in the multiple regions of the connected domain as the tab number of the connected domain.

8. The battery tab detection method according to claim 7, wherein The determining the number of sub-connected domains in each of the multiple regions includes: Obtain the lengths of all sub-connected domains in each of the multiple regions; Determine the number of sub-connected domains in the region according to the number of sub-connected domains in each region whose length is greater than 1 / N times the length of the sub-connected domain with the longest length in the region, where N>0.

9. A battery tab detection device, characterized in that, including: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the battery tab detection method according to any one of claims 1 to 8.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the battery tab detection method according to any one of claims 1 to 8.

Images