Tab-defect detection method and system

Abstract

The present application provides a tab-defect detection method and system. The detection method comprises: during the manufacturing of a battery cell, collecting an original image of a tab-related region; on the basis of an edge position of an electrode sheet main body of the cell, setting a reference line in the original image, which has been subjected to data processing, and setting the region at one side of the reference line which is close to the electrode sheet main body in the cell to be a first detection region, and setting the region at the other side of the reference line which is away from the electrode sheet main body to be a second detection region; and according to a preset sequence, using a regional consistency algorithm to detect a target tab image in the first detection region and the second detection region, and determining whether the cell currently subjected to detection is a defective cell.

Description

Tab defect detection method and system Technical Field

[0001] The present application mainly relates to the field of battery cell tab detection, and in particular to a method and system for detecting tab defects. Background Art

[0002] The battery cell tabs serve as the terminal interface for connecting the battery to the outside world, and their quality directly impacts the safety and ultimate lifespan of the finished battery. During the battery cell manufacturing process, such as lamination or winding, the positive and negative electrode sheets, along with the separator, are assembled into a battery cell. During this process, it is necessary to determine whether the tabs on the positive and negative electrode sheets are missing or folded.

[0003] Whether in the lamination or winding process, the overlap, flatness, and absence of folds or missing tabs in the positive and negative tabs are crucial aspects of quality standards. Currently, battery cell tab quality inspection primarily relies on industrial vision combined with deviation correctors and fiber optic sensor positioning, but this detection is ineffective. In actual production, quality issues such as full or partial tab folding, or missing tabs, still frequently occur. In real-world applications, tab folding, in particular, creates the risk of short circuits between the positive and negative terminals, posing a safety hazard to battery use.

[0004] Summary of the Invention

[0005] The technical problem to be solved by the present application is to provide a method and system for detecting tab defects, which can quickly and accurately detect defective tabs during the battery cell preparation process and improve battery quality.

[0006] In order to solve the above technical problems, the present application provides a method for detecting tab defects, including: in the preparation process of battery cells, collecting original images of tab-related areas, wherein the battery cell includes a pole piece, and the pole piece includes a pole piece body and a tab; setting a baseline in the digitized original image according to the edge position of the pole piece body of the battery cell, and setting the side closer to the pole piece body in the battery cell from the baseline as the first detection area, and the other side farther away from the pole piece body as the second detection area; and detecting the target tab image in the first detection area and the second detection area in a preset order, and judging whether the currently detected battery cell is a defective battery cell.

[0007] In one embodiment of the present application, the step of collecting original images of the tab-related area during the preparation process of the battery cell further includes: during the continuous preparation of multiple battery cells, continuously collecting original images of the tab-related area corresponding to each battery cell before the pole sheets corresponding to each battery cell are wound or stacked.

[0008] In one embodiment of the present application, the method for detecting tab defects also includes using two groups of machine vision detection devices to respectively perform the steps of acquiring the original image, setting the baseline, and judging whether the currently detected battery cell is a defective battery cell, and the two groups of machine vision detection devices are respectively arranged at the first detection position and the second detection position in the preparation process of the battery cell. The detection method further includes: when the two groups of machine vision detection devices both judge that the currently detected battery cell is a defective battery cell, marking the currently detected battery cell as a defective battery cell; and when only one group of machine vision detection devices judges that the currently detected battery cell is a defective battery cell, marking the currently detected battery cell as a suspected defective battery cell for re-inspection.

[0009] In one embodiment of the present application, the preset sequence includes sequentially detecting the first detection area and the second detection area, wherein if part or all of the target tab image is detected in the first detection area, the currently detected cell is judged to be a defective cell, otherwise whether the currently detected cell is a defective cell is judged based on a combination of one or more of the outline, length and width or area of ​​the target tab image in the second detection area.

[0010] In one embodiment of the present application, if part or all of the target tab image is not detected in the first detection area, the detection method further includes obtaining a plurality of regional points in the second detection area through a regional consistency algorithm, and connecting the plurality of regional points to enclose a closed area, thereby obtaining the target tab image, wherein the regional consistency algorithm includes: constructing a square matrix [n] of order n with all values ​​1, and obtaining the same regional pixel a in the second detection area. [n] , wherein the same area pixel a [n] The final grayscale image obtained by denoising and grayscale processing of the second detection area is then binarized and segmented; the pixels a in the same area are obtained. [n] Compare with the matrix [n], if the result is consistent, the pixel a in the same area [n] The position where the target tab is located is assigned a value of 255 and set as a region point; and all the region points in the second detection area are connected to enclose the closed area A, and the target tab image a′ is obtained according to the closed area A. [n] The outline, length and width or area of ​​the battery cell are determined to determine whether the current battery cell is a defective battery cell.

[0011] In one embodiment of the present application, the method for detecting tab defects further includes comparing the similarity SIM(i, j) between the region A and a preset tab image in the following manner, thereby determining whether the currently inspected cell is a defective cell based on the contour of the target tab image in the second inspection region:

[0012] Wherein, A(i, j) is the outer edge of the area A, Y(i, j) is the outer edge of the preset tab image, and u is an adjustable proportional coefficient.

[0013] In one embodiment of the present application, the method further includes calculating the tab lateral width L and the tab longitudinal width H in the target tab image in the following manner, thereby determining whether the currently inspected cell is a defective cell based on the length and width of the target tab image in the second inspection area:

[0014] in, a′ [n] The horizontal position value of pixel w column i, a′ [n] The horizontal position value of pixel v in column i, a′ [n] The vertical position value of pixel p row and column j, a′ [n]pj a′ [n] The vertical position value of the pixel in the qth row and the jth column, and the w, v, p and q are obtained according to the area A, N represents a' [n] The number of rows, M represents a′ [n] The number of columns.

[0015] In one embodiment of the present application, the area of ​​the region A is calculated in the following manner, thereby determining whether the currently inspected cell is a defective cell according to the area of ​​the target tab image in the second inspection region:

[0016] Among them, L w The left starting point of the tab's lateral width L. v The right end point of the tab's transverse width L, H p It is the lower starting point of the longitudinal width H of the tab. q is the upper end point of the longitudinal width H of the tab, f((a′ [n] )) is the function value of the lateral synthesis of the tab, g(a′ [n] ) is the function value of the longitudinal synthesis of the tab.

[0017] In one embodiment of the present application, the original image that has been digitized is the final grayscale image Gray (i, j) obtained by performing denoising and grayscale processing on the original image in sequence, so that the baseline is set in the final grayscale image Gray (i, j) according to the edge position of the electrode body of the battery cell.

[0018] In one embodiment of the present application, if part or all of the target tab image is not detected in the first detection area, the detection method further includes performing binary segmentation of pixels on the final grayscale image Gray(i, j) using the following formula:

[0019] The value of h can be adjusted within the range of 125 to 255 according to the detection situation.

[0020] In one embodiment of the present application, the denoising process includes implementing three primary color stacking in the following manner to obtain a denoised image corresponding to the original image:

[0021] Where (i, j) is the two-dimensional matrix position of any pixel in the original image, R(i, j), G(i, j) and (i(i, j) are the values ​​corresponding to the three primary colors RGB respectively, and K R (m, n), K G (m, n) and K B (m, n) is the filter algorithm corresponding to each of the three primary colors RGB, wherein m and n are the corrected coordinate point offset values ​​of any pixel on the plane.

[0022] In one embodiment of the present application, the grayscale processing includes processing the denoised image in the following manner to obtain the final grayscale image Gray(i, j): Gray(i, j) = k1R(i, j) + k2G(i, j) + k3B(i, j)

[0023] Among them, the values ​​of k1, k2 and k3 are the weighted values ​​corresponding to the three primary colors RGB respectively.

[0024] In order to solve the above technical problems, another aspect of the present application further proposes a detection system for tab defects, comprising: at least one group of machine vision detection devices, the visual detection device comprising a camera and a processor, wherein the camera is suitable for collecting original images of tab-related areas during the preparation process of battery cells, wherein the battery cell comprises a pole piece, and the pole piece comprises a pole piece body and a tab; the processor is suitable for digitizing the original image and setting a baseline according to the edge position of the pole piece body of the battery cell, wherein the side closer to the pole piece body in the battery cell from the baseline is the first detection area, and the other side farther away from the pole piece body is the second detection area; and the processor is also suitable for detecting the target tab image in the first detection area and the second detection area in a preset order according to the detection method described in any embodiment, and judging whether the currently detected battery cell is a defective battery cell.

[0025] In one embodiment of the present application, the number of the machine vision inspection devices is two groups, a first group of machine vision inspection devices located at a first inspection position and a second group of machine vision inspection devices located at a second inspection position, the first inspection position and the second inspection position are respectively located at the process positions before the electrode sheets are wound or stacked during the preparation of the battery cell, and the first inspection position is located at a earlier position in the production sequence than the second inspection position, wherein, when both the first group of machine vision inspection devices and the second group of machine vision inspection devices determine that the currently inspected cell is a defective cell, the first group of machine vision inspection devices and / or the second group of machine vision inspection devices are configured to mark the currently inspected cell as a defective cell; and when only the first group of machine vision inspection devices or the second group of machine vision inspection devices determine that the currently inspected cell is a defective cell, the first group of machine vision inspection devices or the second group of machine vision inspection devices are configured to mark the currently inspected cell as a suspected defective cell for re-inspection.

[0026] Compared with the existing technology, the present application has the following advantages: through the detection method and system of tab defects, the invisible tab quality problem existing in the battery cell stacking process or winding process can be solved more quickly and accurately, and the hidden danger of short circuit of single battery cells can be eliminated; the present application uses industrial vision in conjunction with the battery cell displacement to realize real-time and rapid detection of the tab quality status of the area, and through the arrangement of dual vision, it adds redundant functions, completely realizes the elimination of defective tab batteries, and significantly improves the battery quality.

[0027] Summary of the Figures

[0028] The accompanying drawings are included to provide a further understanding of the present application. They are incorporated into and constitute a part of this application. The accompanying drawings illustrate embodiments of the present application and, together with this specification, serve to explain the principles of the present application. In the accompanying drawings:

[0029] FIG1a is a schematic flow chart of a method for detecting tab defects according to an embodiment of the present application;

[0030] FIG1b is a schematic flow chart of a method for detecting tab defects according to another embodiment of the present application;

[0031] FIG2 is a schematic diagram of tabs of different shapes detected by a tab defect detection method according to an embodiment of the present application;

[0032] FIG3 is a schematic structural diagram of a tab defect detection system according to an embodiment of the present application;

[0033] FIG4 is a schematic diagram of a detection area in a method for detecting tab defects according to an embodiment of the present application;

[0034] FIG5 is a schematic flow chart of a method for detecting tab defects according to another embodiment of the present application;

[0035] FIG6 is a schematic diagram showing the principle of a regional consistency algorithm in a method for detecting tab defects according to an embodiment of the present application; and

[0036] FIG7 is a flow chart of a method for detecting tab defects according to another embodiment of the present application.

[0037] Preferred embodiments of the present invention

[0038] To more clearly illustrate the technical solutions of the embodiments of this application, the following is a brief introduction to the drawings required for describing the embodiments. Obviously, the drawings described below are merely examples or embodiments of this application. Those skilled in the art can apply this application to other similar scenarios based on these drawings without inventive effort. Unless otherwise apparent from the context or otherwise noted, the same reference numerals in the figures represent the same structure or operation.

[0039] As used in this application and the claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" are not intended to refer to the singular but may include the plural. Generally speaking, the terms "comprises" and "include" only indicate the inclusion of the steps and elements specifically identified, and these steps and elements do not constitute an exclusive list. A method or apparatus may also include other steps or elements.

[0040] Unless otherwise specifically stated, the relative arrangement of the parts and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present application. At the same time, it should be understood that, for ease of description, the sizes of the various parts shown in the drawings are not drawn according to actual proportional relationships. The techniques, methods and equipment known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, the techniques, methods and equipment should be considered as part of the authorization specification. In all examples shown and discussed here, any specific values ​​should be interpreted as being merely exemplary and not as limitations. Therefore, other examples of the exemplary embodiments may have different values. It should be noted that similar numbers and letters represent similar items in the following figures, and therefore, once an item is defined in one figure, it does not need to be further discussed in subsequent figures.

[0041] In the description of this application, it should be understood that the directions or positional relationships indicated by directional words such as "front, back, up, down, left, right", "horizontal, vertical, vertical, horizontal" and "top, bottom" are usually based on the directions or positional relationships shown in the accompanying drawings. They are only for the convenience of describing this application and simplifying the description. Unless otherwise specified, these directional words do not indicate or imply that the device or element referred to must have a specific direction or be constructed and operated in a specific direction. Therefore, they cannot be understood as limiting the scope of protection of this application; the directional words "inside and outside" refer to the inside and outside relative to the outline of each component itself.

[0042] For ease of description, spatially relative terms such as "above", "above", "on the upper surface", "above", etc. may be used herein to describe the spatial positional relationship of a device or feature to other devices or features as shown in the figures. It should be understood that spatially relative terms are intended to include different orientations of the device in use or operation in addition to the orientation described in the figures. For example, if the device in the drawings is inverted, the device described as "above other devices or structures" or "above other devices or structures" will be positioned as "below other devices or structures" or "below other devices or structures". Thus, the exemplary term "above" can include both "above" and "below". The device can also be positioned in other different ways (rotated 90 degrees or in other orientations), and the spatially relative descriptions used here are interpreted accordingly.

[0043] Furthermore, it should be noted that the use of terms such as "first" and "second" to define components is solely for the purpose of distinguishing the corresponding components. Unless otherwise stated, these terms have no special meaning and therefore should not be construed as limiting the scope of protection of this application. Furthermore, while the terms used in this application are selected from commonly known and commonly used terms, some terms mentioned in this specification may have been selected by the applicant at his or her discretion, and their detailed meanings are explained in the relevant sections of this description. Furthermore, this application should be understood not only by the actual terms used, but also by the meaning implied by each term.

[0044] Existing battery cell tab quality inspection methods primarily focus on: 1. Using industrial vision combined with a deviation corrector to correct tab alignment, ensuring that the positive and negative tabs of the battery cell overlap within the specified nominal value; 2. Using optical fiber and other sensors to detect the presence and wrinkles of the tabs at specific points; and 3. Using industrial vision to measure the distance between tab edges to determine tab quality. However, these methods still have significant shortcomings in actual production applications, such as low accuracy, slow speed, and the tendency to misjudge defective tabs.

[0045] In order to solve the above technical problems, the present application proposes a method for detecting tab defects with reference to FIG. 1a (hereinafter referred to as “detection method 10”), which can quickly and accurately detect defective tabs during the preparation of battery cells and improve battery quality. This application, including FIG. 1a and other figures, uses some flow charts to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the previous or following operations are not necessarily performed in exact sequence. On the contrary, various steps can be processed in reverse order or simultaneously. At the same time, other operations may be added to these processes, or one or more steps may be removed from these processes.

[0046] According to Figure 1a, the detection method 10 includes steps 11 to 13. Step 11 is to collect the original image of the tab-related area during the preparation process of the battery cell, wherein the battery cell includes a pole piece, and the pole piece includes a pole piece body and a pole piece tab. Step 12 is to set a baseline according to the edge position of the pole piece of the battery cell in the digitized original image, and set the side closer to the pole piece body from the baseline as the first detection area, and the other side farther away from the pole piece body as the second detection area. Step 13 is to detect the target pole piece image in the first detection area and the second detection area in a preset order, and determine whether the current detection cell is a defective battery cell. It should be noted that in different embodiments of the present application, the pole piece includes a pole piece body and a pole piece tab. This is a theoretical definition division for the convenience of describing the technical features of the present application; in actual application, the pole piece body and the pole piece tab defined in the present application can be integrated, and the present application does not impose any restrictions on this.

[0047] Exemplarily, during the inspection process, the first inspection area and the second inspection area can be inspected simultaneously, or the first inspection area and the second inspection area can be inspected sequentially. The inspection order can be selected based on the actual situation. Preferably, the preset order includes inspecting the first inspection area and the second inspection area in sequence, wherein if part or all of the target tab image is detected in the first inspection area, the current inspection cell is judged as a defective cell; otherwise, the target tab image a′ in the second inspection area is detected. [n] The outline, length, width or area of ​​the battery cell are used to determine whether the current battery cell is a defective battery cell.

[0048] Figure 1b shows a method 100 for detecting tab defects of the present application implemented according to the above-mentioned preferred method (hereinafter referred to as "detection method 100"). According to detection method 100, steps 11 and 12 are the same as those of detection method 10, which are steps of collecting original images and setting baselines and first detection areas and second detection areas. The difference is that the detection method 100 shown in Figure 1b additionally has steps 131-133. Specifically, step 131 is to determine whether part or all of the target tab image is detected in the first detection area. If the detection result is yes, step 131 is executed, and the current detection cell is judged as a defective cell. If the detection result of step 131 is otherwise, step 133 is executed, and the target tab image a′ in the second detection area is determined. [n] The outline, length, width or area of ​​the battery cell are used to determine whether the current battery cell is a defective battery cell.

[0049] Exemplarily, the original image of the tab-related area can be understood as an original image of the tab and its surrounding area having a uniform shape (how to delineate the relevant area will be further explained below with reference to FIG4 ). In a preferred embodiment of the present application, the above-mentioned detection method 10 is applied during the continuous preparation of battery cells. That is, during the continuous preparation of multiple battery cells, the original image of the tab-related area corresponding to each battery is continuously collected before the positive electrode sheet, negative electrode sheet, and separator corresponding to each battery are wound or stacked.

[0050] Continuing with Figure 2, Figure 2 shows schematic diagrams of tabs in different configurations. A tab in a normal state is indicated by reference numeral 21; a defective tab is indicated by reference numeral 22; a missing tab is indicated by reference numeral 23; a folded tab is indicated by reference numeral 24; and reference numeral 25 represents the main body of the tab. This embodiment only illustrates tabs in four of these configurations, but the tab configurations detected in this application are not limited to these configurations. The purpose of this application is to implement a tab defect detection method, including the one shown in Figures 1a and 1b, using one or more machine vision devices, thereby improving battery quality.

[0051] In order to better illustrate the detection method 10 and its preferred variants, a detection system 30 for tab defects (hereinafter referred to as "detection system 30") is now introduced with reference to Figure 3. Referring to Figure 3, the detection system 30 includes two groups of machine vision detection devices, namely a first group of machine vision detection devices 31 and a second group of machine vision detection devices 31', wherein the first group of machine vision detection devices 31 and the second group of machine vision detection devices 31' respectively include a first camera 36 and a second camera 36' and respective processors (not shown). It should be noted that the detection system 30 can apply the detection method 10 or the detection method 100. Therefore, in the following description of this application, some detailed features of the detection system 30 can refer to the description of the detection method 10 and the detection method 100, and the repeated content will not be repeated.

[0052] Specifically, the first camera 36 and the second camera 36' are adapted to capture raw images of the tab-related areas during the battery cell preparation process. Referring to Figure 3 , in a specific implementation of this embodiment, the first and second sets of machine vision inspection devices 31 and 31' further include first and second brightness adjusters 37 and 37', respectively. The first and second brightness adjusters 37 and 37' are illustrated as semicircular rings in Figure 3 , while the first and second cameras 36 and 36' are illustrated as rectangular portions in Figure 3 . The first and second cameras 36 and 36' are mounted on the first and second brightness adjusters 37 and 37', respectively. The first and second cameras 36 and 36' are interconnected with their respective processors for data transmission. The first and second sets of machine vision inspection devices 31 and 31' are respectively positioned at the first and second inspection positions during the battery cell preparation process. The drive mechanism 35 drives the electrode sheet at high speed, and the first and second tabs 33 and 34 disposed consecutively on the electrode sheet pass through the two sets of machine vision inspection devices in sequence. The first set of machine vision inspection devices 31 and the second set of machine vision inspection devices 31' will respectively and sequentially collect original images of each tab-related area that passes through. The processors in the two sets of machine vision inspection devices are suitable for using the same algorithm to process the collected original images to obtain corresponding digitized original images. It is understandable that in actual applications, some parameters of the algorithm can be adjusted according to the production site conditions to achieve better coordination and cooperation between the two sets of machine vision inspection devices. When making adjustments, the operating speed of the tab, the spacing between the two sets of machine vision inspection devices, and the current battery cell model can be considered, etc. This application does not impose any restrictions on this.

[0053] In the present application, the processor of the machine vision inspection device is generally configured to detect the target tab image in the first inspection area and the second inspection area in a preset order, and determine whether the current inspection cell is a defective cell. In some preferred embodiments, the processor can also detect the detection target tab image in the first inspection area and the second inspection area in a preset order, wherein if part or all of the target tab image is detected in the first inspection area, the current inspection cell is determined to be a defective cell; otherwise, the target tab image a′ in the second inspection area is determined to be a defective cell. [n] It is determined whether the currently inspected battery cell is a defective battery cell by using any one or more arbitrary combinations of the outline, length, width, and area of ​​the battery cell.

[0054] Preferably, this embodiment uses two groups of machine vision detection devices to detect tab defects. The purpose of using two groups of visual detection devices is to ensure the reliability of the detection. Only when both groups are diagnosed as normal will they be considered qualified. When both groups are diagnosed as abnormal, they are directly discarded as defective cells. In other cases, cells that are judged as suspected defective cells need to be transferred to the manual visual inspection area for manual judgment. Of course, based on the embodiment shown in Figure 3, more groups of visual detection devices can be used to detect tab defects according to actual conditions, and this application is not limited to this. In addition, the two groups of machine vision detection devices detect the target tab image in the first detection area and the second detection area in a preset order, and when judging whether the current detected cell is a defective cell, the same detection order or a different detection order can be adopted, and the two groups of machine vision detection devices are based on the target tab image a′ in the second detection area. [n] When judging whether the currently inspected cell is a defective cell based on a combination of one or more of the outline, length, width or area of ​​the target tab image in the second inspection area, the judgment methods adopted may be the same or different. For example, the first group of machine vision inspection devices 31 judges whether the currently inspected cell is a defective cell based on the outline and length and width of the target tab image in the second inspection area, and the second group of machine vision inspection devices 31' judges whether the currently inspected cell is a defective cell based on the outline and length and width of the target tab image in the second inspection area. [n] The outline, length, width and area of ​​the battery cell are used to determine whether the battery cell being inspected is a defective battery cell.

[0055] In this embodiment, the cameras in the first group of machine vision inspection devices 31 and the second group of machine vision inspection devices 31' shown in Figure 3 can collect the original image with reference to step 11 in the inspection method 10 shown in Figure 1a, and the processor therein is suitable for performing image processing with reference to steps 12 and 13 in the inspection method 10 shown in Figure 1a. For example, a baseline is set based on the data information contained in the original image and the edge position of the electrode body 25 of the battery cell, wherein the side of the baseline closer to the electrode body 25 is the first inspection area, and the other side farther away from the electrode body 25 is the second inspection area. The processor is also configured to detect the target tab image in the first inspection area and / or the second inspection area according to a built-in algorithm, and determine whether the battery cell currently being inspected is a defective battery cell. The algorithm will be further explained below.

[0056] For example, Figure 4 illustrates a schematic diagram of the principle of demarcating a reference line to obtain a first inspection area S' and a second inspection area S in this embodiment. Referring to Figure 4, a schematic diagram of a set of consecutive inspection areas for tab defects is shown in one embodiment of the present application, for example, during the continuous production of multiple battery cells. The diagram includes four first inspection areas, namely, first inspection area 1 S1', first inspection area 2 S2', first inspection area 3 S3', and first inspection area 4 S4', and four second inspection areas, namely, second inspection area 1 S1, second inspection area 2 S2, second inspection area 3 S3, and second inspection area 4 S4. In this embodiment, when continuously producing battery cells of the same model, the tab-related area mentioned above is a rectangular area 40 of uniform size. After acquiring a raw image of the rectangular area 40 corresponding to each tab, a reference line 41 is marked therein based on the edge position of the electrode body 25 after digital processing. For example, in this embodiment, the reference line 41 itself is the edge position of the electrode body 25. After setting the baseline 41, the side closer to the pole piece body 25 (or in this embodiment, it can be understood as the area above the baseline 41 in the rectangular area 40) can be set as the first detection area S', and the other side farther away from the pole piece body 25 can be set as the second detection area S.

[0057] The basic concepts of a tab defect detection method and detection system proposed in this application have been preliminarily explained above with reference to Figures 1a to 4. The following further details how to perform data processing on the original images of the tab-related areas collected in some preferred embodiments based on the detection method 10 in Figure 1a, the detection method 100 in Figure 1b, and the detection system 30 in Figure 3.

[0058] First, in some embodiments of the present application, the original image that has been digitized is a final grayscale image Gray(i, j) obtained by sequentially performing denoising and grayscale processing on the original image.

[0059] Preferably, the denoising process includes implementing three primary color stacking in the following manner to obtain a denoised image corresponding to the original image:

[0060] Wherein, (i, j) is the two-dimensional matrix position of any pixel in the original image, R(i, j), G(i, j) and B(i, j) are the values ​​corresponding to the three primary colors RGB, respectively, and the value range is [0, 250] or [0, 255], etc., and the upper limit can be selected between 250-255; K R (m, n), K G (m, n) and K B (m, n) are the filter algorithms corresponding to the three primary colors RGB, wherein the filters can be adjusted according to the actual application, and the algorithm can be adjusted by a matched filter, a high-pass filter, a low-pass filter, a band-pass filter, etc.

[0061] Exemplarily, the three primary colors overlap includes calculating the R value of each pixel in the original image, and the R value has a corresponding filter K R (m, n), the main function of the filter is to remove impurities in the original image. The R value R(i, j) of the original image is the sum of the R values ​​of each pixel in the original image after filtering. The method for calculating the G and B values ​​is similar to that of the R value, so we will not go into details here. The three primary colors stacked by the algorithm implemented in this application ultimately presents a denoised image corresponding to the original image.

[0062] Further preferably, the grayscale processing includes processing the denoised image in the following manner to obtain the final grayscale image Gray(i, j): Gray(i, j) = k1R(i, j) + k2G(i, j) + k3B(i, j)

[0063] Among them, the values ​​of k1, k2 and k3 are the weighted values ​​corresponding to the three primary colors RGB respectively, and can be set according to specific usage.

[0064] After the original image is denoised and grayscale processed, the final grayscale image is obtained, so that the baseline 41 can be set in the final grayscale image according to the edge position of the electrode body 25 in the battery cell with reference to Figure 4. The baseline 41 divides the detection area into two areas: the first detection area S' and the second detection area S, wherein the first detection area S' is a tab-free area, also known as a tab-free area; the second detection area S is a complete tab detection area, also known as a tab area. In both the first detection area S' and the second detection area S, the width, shape and area of ​​the graphics included in the edge of the tab can be measured to determine the quality of the tab. Preferably, in some embodiments of the present application including Figures 1a and 1b, only when part or all of the target tab image is not detected in the first detection area S', the target tab image a' will be further calculated in the second detection area S according to the corresponding algorithm. [n] The shape, outline, length, width, and area of ​​the tab are then analyzed to further verify whether a normal tab that meets the requirements and standards is present in the second inspection area S, i.e., the tab area. This approach can reduce the amount of computation required and improve the calculation and response speed of the machine vision inspection device.

[0065] Continuing to refer to FIG5 , FIG5 is further optimized based on the detection method 10 shown in FIG1a and the detection method 100 shown in FIG1b , especially for the refinement of the algorithm arrangement based on the target tab image in the second detection area S. First, after the original image of the tab-related area is acquired at high speed, the first detection area S' is first detected to see whether the target tab image is detected. If the target tab image is detected, the tab is directly marked as a folding defect; if the target tab image is not detected, the second detection area S is detected. Detecting the second detection area S includes sequentially determining whether the tab image contour, length and width dimensions, and area of ​​the second detection area S match the preset tab image. Exemplarily, the preset tab image is a standard tab image for a specific battery cell type.

[0066] The optimization algorithm in each step of Figure 5 will be further described in detail below. First, for example, if part or all of the target tab image (e.g., an image after denoising and grayscale processing) is not detected in the first detection area S', the final grayscale image Gray(i, j) can first be binarized and segmented using the following formula:

[0067] The h value is the judgment threshold value that has been adjusted and tested, and the value range of the h value is 125-255. The h value is adjustable within the range of 125-255 according to the detection situation. For example, the specific h value can be adjusted and tested using the on-site histogram. After the grayscale processing of the image, the value at each Gray(i, j) position is between (0-255). Binarization of the final grayscale image can make the image appear only in black and white.

[0068] For example, referring to FIG6 , after the final grayscale image is binarized and segmented, a region consistency algorithm can be used to obtain a target tab image in the second detection area S. The region consistency algorithm can process the image using the following formula:

[0069] First, construct a square matrix [n] of all 1s of order n, and obtain the same area pixel a in the second detection area S [n] , wherein the same area pixel a [n] The final grayscale image obtained by denoising and grayscale processing of the second detection area S is then obtained by binary segmentation. [n] Compare with the above [n], if the result is consistent, the pixel a in the same area [n] The position where the target lug is located is assigned a value of 255 and set as a region point; and all the region points in the second detection region are connected to form a closed region A, and the target lug image a′ is obtained according to the closed region A. [n] The outline, length and width or area of ​​the battery cell can be determined to determine whether the current battery cell is a defective battery cell.

[0070] Continuing with FIG5 , the detection method includes a pre-set tab image with a normal tab image. The detection method 10 compares the similarity SIM(i, j) between region A and the pre-set tab image, thereby determining whether the currently inspected cell is a defective cell based on the contour of the target tab image in the second inspection region S. In some preferred embodiments of the present application, the specific formula for determining similarity is as follows:

[0071] Among them, A(i, j) is the outer edge of area A, Y(i, j) is the outer edge of the preset tab image, and u is an adjustable scale factor, which can be manually set in the initial comparison of the visual software of the visual inspection device.

[0072] Furthermore, if the contour of the target tab image matches the preset tab image, the length and width of the target tab image are further calculated; if the contour of the target tab image does not match the preset tab image, the tab is marked as having a shape defect.

[0073] For example, if the outline of the target tab image matches the preset tab image, it is necessary to further calculate the length and width of the target tab image. Calculating the length and width of the target tab image mainly includes calculating the horizontal width L and the vertical width H of the tab in the target tab image. Based on the length and width of the target tab image in the second inspection area S, it is determined whether the current inspection cell is a defective cell. The specific calculation formulas for L and H are as follows:

[0074] in, a′ [n] The horizontal position value of pixel w column i, a′ [n] The horizontal position value of pixel v in column i, a′ [n] The vertical position value of pixel p row and column j, a′ [n] The vertical position value of the pixel in the qth row and the jth column, and w, v, p and q are the positions corresponding to the four vertices of the area A that can be automatically obtained in the image having the area A after the area A is obtained.

[0075] Furthermore, if the length and width of the target tab image match the preset tab image, the area of ​​the target tab image is further calculated; if the length and width of the target tab image do not match the preset tab image, the tab is marked as having a shape defect.

[0076] Continuing with FIG5 , if the outline and length and width of the target tab image match the preset tab image, the area of ​​the target tab image, i.e., the area of ​​region A, is calculated. Thus, whether the currently inspected cell is a defective cell is determined based on the area of ​​the target tab image in the second inspection region S:

[0077] Among them, L w The left starting point of the tab's lateral width L. v The right end point of the tab's transverse width L, H p It is the lower starting point of the longitudinal width H of the tab. q is the upper end point of the longitudinal width H of the tab, f((a′ [n] )) is the function value of the lateral synthesis of the tab, g(a′ [n] ) is the function value of the longitudinal synthesis of the tab.

[0078] Furthermore, if the area of ​​the target tab image matches the preset tab image, the tab is judged to be a normal tab and can run normally and execute the lower-level program. If the outline of the target tab image does not match the preset tab image, it is marked as a tab with large or small defects.

[0079] It will be appreciated that the foregoing description of a preferred embodiment of the detection method 10 shown in FIG. 1a and the detection method 100 shown in FIG. 1b has been described in detail with reference to FIG. 5 and FIG. 6 . However, the present application is not limited to the foregoing description. For example, referring to FIG. 5 , when determining the tab image contour, length and width dimensions, and area in the second detection area S2, one or more of these dimensions may be selected for measurement, such as determining the contour alone, determining the length and width alone, determining the area alone, or a combination of two or three of these dimensions. When using a combination of two or three dimensions, the different dimensions may be determined simultaneously or sequentially. Specifically, the order of determining the contour, determining the length and width, and determining the area may also be adjusted according to the specific circumstances. Of course, in this embodiment, the contour, length and width dimensions, and area are judged in this order. In practical applications, since the algorithms for contour and length and width dimensions are simpler than those for area, it is preferred to judge the contour and length and width dimensions first. On the basis of their qualified judgment, the reliability of the judgment is further improved by judging the area, so that defective tabs can be detected more quickly and accurately, with faster judgment speed and better effect.

[0080] Further, referring to FIG7 , FIG7 further optimizes the detection method 10 shown in FIG1a and the detection method 100 shown in FIG1b . This optimized detection method can also specifically refer to the detection system 30 shown in FIG3 . Specifically, in combination with the detection system 30 shown in FIG3 , the optimized tab defect detection method shown in FIG7 can be obtained. In this embodiment, during the operation of a battery cell, if the first set of visual inspection devices 31 at the first inspection position does not mark the currently inspected cell as a defective cell, the second set of visual inspection devices 31' at the second inspection position will continue to determine whether the currently inspected cell is a defective cell. If the second set of visual inspection devices 31' does not determine the currently inspected cell as a defective cell, the cell is normal and the lower-level procedures can be executed, such as hot pressing of a normal cell. If the second set of visual inspection devices 31' determines that the currently inspected cell is a defective cell, the currently inspected cell is determined to be a suspected defective cell and is moved to the manual visual inspection area for manual verification. In this embodiment, in order to maintain a smooth production process, both normal tabs and defective tabs will be prepared into finished battery cells according to the normal process. However, during the preparation of the battery cells, the inspection cells with defective tabs will be marked by a machine vision inspection device, thereby facilitating the subsequent process of re-inspecting defective cells or suspected defective cells to better ensure the quality of the battery.

[0081] Furthermore, if the first group of visual inspection devices 31 located at the first inspection position marks the currently inspected cell as a defective cell and transmits the result to the second group of visual inspection devices 31', the second group of visual inspection devices 31' located at the second inspection position will continue to determine whether the currently inspected cell is a defective cell. If the second group of visual inspection devices 31' determines that the currently inspected cell is not a defective cell, the currently inspected cell will be determined as a suspected defective cell and the currently inspected cell will be moved to the manual visual inspection area to wait for manual inspection. If the second group of visual inspection devices 31' determines that the currently inspected cell is a defective cell, the currently inspected cell will be moved to the scrap area. In other embodiments, if the second group of visual inspection devices 31' determines that the currently inspected cell is not a defective cell, the second group of visual inspection devices 31' may also transmit the judgment result to the first group of visual inspection devices 31, and the first group of visual inspection devices 31 may determine that the currently inspected cell is a suspected defective cell and move the currently inspected cell to the manual visual inspection area.

[0082] The basic concepts have been described above. It will be apparent to those skilled in the art that the above disclosures are merely examples and do not limit the present application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and revisions to the present application. Such modifications, improvements, and revisions are suggested in the present application and remain within the spirit and scope of the exemplary embodiments of the present application.

[0083] At the same time, this application uses specific terms to describe the embodiments of this application. For example, "one embodiment," "an embodiment," and / or "some embodiments" refer to a certain feature, structure, or characteristic related to at least one embodiment of this application. Therefore, it should be emphasized and noted that "one embodiment," "an embodiment," or "an alternative embodiment" mentioned twice or multiple times in different locations in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of this application may be appropriately combined.

[0084] Some aspects of the present application can be performed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software can all be referred to as "data blocks", "modules", "engines", "units", "components" or "systems". The processor can be one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DAPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors or combinations thereof. In addition, various aspects of the present application may be expressed as computer products located in one or more computer-readable media, which include computer-readable program code. For example, computer-readable media may include, but are not limited to, magnetic storage devices (e.g., hard disks, floppy disks, tapes...), optical disks (e.g., compact disks CDs, digital versatile disks DVDs...), smart cards, and flash memory devices (e.g., cards, sticks, key drives...).

[0085] A computer-readable medium may include a propagated data signal embodying computer program code, for example, in baseband or as part of a carrier wave. The propagated signal may be in a variety of forms, including electromagnetic, optical, etc., or a suitable combination thereof. A computer-readable medium may be any computer-readable medium other than a computer-readable storage medium that can be connected to an instruction execution system, apparatus, or device to communicate, propagate, or transmit the program for use. The program code on the computer-readable medium may be transmitted via any suitable medium, including radio, cable, fiber optic cable, radio frequency signal, or similar medium, or any combination of the above.

[0086] Similarly, it should be noted that, in order to simplify the description of this application and thus facilitate understanding of one or more embodiments of the application, the foregoing description of the embodiments of this application sometimes combines multiple features into a single embodiment, figure, or description thereof. However, this disclosure method does not mean that the subject matter of this application requires more features than those recited in the claims. In fact, the features of an embodiment may be fewer than all the features of the individual embodiments disclosed above.

[0087] In some embodiments, numbers are used to describe the quantity of components and attributes. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise stated, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the description and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of the present application are approximate values, in specific embodiments, the settings of such numerical values ​​are as accurate as possible within the feasible range.

[0088] Although the present application has been described with reference to the current specific embodiments, ordinary technicians in this technical field should recognize that the above embodiments are only used to illustrate the present application, and various equivalent changes or substitutions can be made without departing from the spirit of the present application. Therefore, as long as the changes and modifications to the above embodiments are within the scope of the essential spirit of the present application, they will fall within the scope of the claims of the present application.

Claims

1. A method for detecting tab defects, characterized in that: include: In the process of preparing the battery cell, collecting the original image of the area related to the pole ear, wherein the battery cell includes a pole piece, and the pole piece includes a pole piece body and a pole ear; In the original image processed by digitization, a reference line is set according to the edge position of the pole piece body, and a side closer to the pole piece body from the reference line is set as a first detection area, and another side farther from the pole piece body is set as a second detection area; and The target tab image is detected in the first detection area and the second detection area in a preset order, and it is determined whether the currently detected battery cell is a defective battery cell.

2. The detection method according to claim 1, characterized in that The step of collecting original images of the tab-related areas during the preparation of the battery cells further includes: in the process of continuous preparation of multiple battery cells, continuously collecting original images of the tab-related areas corresponding to each battery cell before the pole sheets corresponding to each battery cell are wound or stacked.

3. The detection method according to claim 2, characterized in that The method further includes using two sets of machine vision detection devices to respectively perform the steps of collecting the original image, setting the baseline, and judging whether the currently detected battery cell is a defective battery cell, wherein the two sets of machine vision detection devices are respectively arranged at a first detection position and a second detection position in the preparation process of the battery cell, and the detection method further includes: When both of the two groups of machine vision inspection devices determine that the currently inspected battery cell is a defective battery cell, marking the currently inspected battery cell as a defective battery cell; and When only one set of machine vision inspection devices determines that the currently inspected battery cell is a defective battery cell, the currently inspected battery cell is marked as a suspected defective battery cell for re-inspection.

4. The detection method according to claim 1, characterized in that The preset sequence includes sequentially detecting the first detection area and the second detection area, wherein if part or all of the target tab image is detected in the first detection area, the currently detected cell is judged to be a defective cell, otherwise whether the currently detected cell is a defective cell is judged based on a combination of one or more of the contour, length and width or area of ​​the target tab image in the second detection area.

5. The detection method according to claim 4, characterized in that: If part or all of the target tab image is not detected in the first detection area, the detection method further includes obtaining a plurality of regional points in the second detection area by a regional consistency algorithm, and connecting the plurality of regional points to enclose a closed area, thereby obtaining the target tab image, wherein the regional consistency algorithm includes: Construct a square matrix [n] of order n with all values ​​being 1, and obtain the same area pixel a in the second detection area [n] , where the same area pixel a [n] The final grayscale image obtained by denoising and grayscale processing of the second detection area is obtained by binary segmentation; The same area pixel a [n] Compare with the square matrix [n], if the result is consistent, the same area pixel a [n] The location is assigned a value of 255 and is set as a region point; and Connect all the area points in the second detection area to enclose the closed area A, and obtain the target tab image a′ according to the closed area A [n] The outline, length, width or area of ​​the battery cell can be determined to determine whether the currently detected battery cell is a defective battery cell.

6. The detection method according to claim 5, characterized in that It also includes comparing the similarity SIM(i, j) between the region A and the preset tab image in the following manner, so as to determine whether the currently inspected battery cell is a defective battery cell according to the contour of the target tab image in the second inspection region: Wherein, A(i, j) is the outer edge of the area A, Y(i, j) is the outer edge of the preset tab image, and u is an adjustable proportional coefficient.

7. The detection method according to claim 5, characterized in that: The method further includes calculating a lateral width L and a longitudinal width H of the tab in the target tab image in the following manner, thereby determining whether the currently inspected battery cell is a defective battery cell according to the length and width of the target tab image in the second inspection area: Among them, a′ [n]iw a′ [n] The horizontal position value of pixel w in row i, a′ [n]iv a′ [n] The horizontal position value of the pixel in the i-th row of column v, a′ [n]pj a′ [n] The vertical position value of the pixel in row p and column j, a′ [n]qj a′ [n] The vertical position value of the pixel in the qth row and the jth column, and the w, v, p and q are obtained according to the area A, and N represents a′ [n] The number of rows, M represents a′ [n] The number of columns.

8. The detection method according to claim 5, characterized in that: The method further includes calculating the lateral width L and longitudinal width H of the target tab in the tab image, and calculating the area S of the region A by: A , thereby judging whether the currently inspected battery cell is a defective battery cell according to the area of ​​the target tab image in the second inspection area: Among them, a′ [n]iw a′ [n] The horizontal position value of pixel w in row i, a′ [n]iv a′ [n] The horizontal position value of the pixel in the i-th row of column v, a′ [n]pj a′ [n] The vertical position value of the pixel in row p and column j, a′ [n]qj a′ [n] The vertical position value of the pixel in the qth row and the jth column, and the w, v, p and q are obtained according to the area A; L w It is the left starting point of the lateral width L of the tab. v It is the right end point of the lateral width L of the tab, H p It is the lower starting point of the longitudinal width H of the tab. q is the upper end point of the longitudinal width H of the tab, f(a′ [n] ) is the function value of the lateral synthesis of the tab, g(a′ [n] ) is the function value of the longitudinal synthesis of the tab, N represents a′ [n] The number of rows, M represents a′ [n] The number of columns.

9. The detection method according to any one of claims 1 to 8, characterized in that: The original image processed by digitization is a final grayscale image Gray (i, j) obtained by sequentially performing the denoising process and the grayscale process on the original image. The method also includes setting the baseline in the final grayscale image Gray (i, j) according to the edge position of the electrode body of the battery cell.

10. The detection method according to claim 9, characterized in that: If part or all of the target tab image is not detected in the first detection area, the detection method further includes performing the binary segmentation of pixels on the final grayscale image Gray(i, j) by the following formula: The value range of h is 125 to 255.

11. The detection method according to claim 9, characterized in that: The denoising process includes implementing three primary color stacking in the following manner to obtain a denoised image corresponding to the original image: Where (i, j) is the two-dimensional matrix position of any pixel in the original image, R(i, j), G(i, j) and B(i, j) They are the values ​​corresponding to the three primary colors RGB, K R (m, n), K G (m, n) and K B (m, n) are the filter algorithms corresponding to the three primary colors RGB respectively.

12. The detection method according to claim 11, characterized in that: The grayscale processing includes processing the denoised image in the following manner to obtain the final grayscale image Gray(i, j): Gray(i, j)=k1R(i, j)+k2G(i, j)+k3B(i, j) Among them, the values ​​of k1, k2 and k3 are the weighted values ​​corresponding to the three primary colors RGB respectively.

13. A detection system for tab defects, comprising: At least one set of machine vision detection devices, the visual detection devices comprising a camera and a processor, wherein: The camera is suitable for collecting original images of the area related to the tab during the preparation process of the battery cell, wherein the battery cell includes a pole piece, and the pole piece includes a pole piece body and a tab; The processor is suitable for digitally processing the original image and setting a reference line according to the edge position of the pole piece body of the battery cell, wherein the side closer to the pole piece body in the battery cell from the reference line is the first detection area, and the other side farther from the pole piece body is the second detection area; and The processor is also suitable for detecting the target tab image in the first detection area and the second detection area in a preset order according to the detection method as described in any one of claims 1 to 2 and 4 to 12, and determining whether the current detected battery cell is a defective battery cell.

14. The detection system according to claim 13, characterized in that: The number of the machine vision inspection devices is two groups, including a first group of machine vision inspection devices located at a first inspection position and a second group of machine vision inspection devices located at a second inspection position, the first inspection position and the second inspection position are respectively located at process positions before the pole pieces are wound or stacked during the preparation of the battery cell, and the first inspection position is located at a front position in the production sequence compared to the second inspection position, wherein, When both the first group of machine vision detection devices and the second group of machine vision detection devices determine that the currently detected battery cell is a defective battery cell, the first group of machine vision detection devices and / or the second group of machine vision detection devices are configured to mark the currently detected battery cell as a defective battery cell; and When only the first group of machine vision inspection devices or only the second group of machine vision inspection devices determines that the currently inspected battery cell is a defective battery cell, the first group of machine vision inspection devices or the second group of machine vision inspection devices is configured to mark the currently inspected battery cell as a suspected defective battery cell for re-inspection.

Images