Method, device and equipment for detecting encapsulation condition of end face of cylindrical battery cell and medium

Abstract

The invention discloses a method, a device, equipment and a medium for detecting the encapsulation condition of the end surface of a cylindrical battery cell, and relates to the technical field of industrial visual inspection. The method comprises the following steps: acquiring a to-be-detected target end surface rubber coating image of the cylindrical battery cell; performing insulation sheet detection processing on the target end surface rubber coating image to obtain an insulation sheet detection condition; when the insulation sheet detection condition is that the insulation sheet exists, shielding area detection processing is carried out on the target end surface rubber coating image to obtain a target fan-shaped shielding area; carrying out encapsulation area detection processing on the target end surface encapsulation image to obtain an initial encapsulation area; subtracting the target fan-shaped shielding area from the initial encapsulation area to obtain an encapsulation effective detection area; performing radial scanning detection judgment processing on the rubber coating effective detection area to obtain a plurality of target rubber coating detection areas; and carrying out continuous defect detection processing on the plurality of target encapsulation detection areas to obtain an encapsulation defect detection result. The effective coverage rate and reliability of rubber coating condition detection of the end face of the cylindrical battery cell can be improved.

Description

Technical Field

[0001] The present application relates to the field of industrial visual inspection technology, and in particular to a method, device, equipment and medium for detecting the encapsulation condition of the end face of a cylindrical battery cell. Background Art

[0002] New energy batteries are increasingly being used in daily life and industry. For example, battery-powered new energy vehicles are already widely used. Furthermore, batteries are increasingly being used in energy storage applications. In the production process of cylindrical cells, after winding and before inserting the cylindrical cells into the shell, the positive tabs of the cylindrical cells need to be encapsulated with glue to prevent short circuits between the positive and negative electrodes and to ensure smooth insertion of the cylindrical cells into the shell in subsequent processes. After encapsulation, the cylindrical cells are typically inspected to identify defects such as missing tabs, wrinkles, warping, and damage.

[0003] However, the related art's encapsulation detection scheme for cylindrical battery cells has defects such as insufficient suppression capability for interference areas and reliance on a single width threshold comparison for defect determination, resulting in low detection reliability and affecting the quality of the final product. Summary of the Invention

[0004] The present application aims to solve at least one of the technical problems existing in the prior art. To this end, the present application proposes a method, device, equipment, and medium for detecting the coating condition of cylindrical battery cell end faces, which can improve the effective coverage and reliability of detecting the coating condition of cylindrical battery cell end faces.

[0005] In a first aspect, an embodiment of the present application provides a method for detecting the encapsulation condition of an end face of a cylindrical battery cell, comprising: Acquire an image of the adhesive coating on the target end of the cylindrical battery cell to be inspected; Performing insulation sheet detection processing on the target end adhesive coating image to obtain insulation sheet detection status; When the insulating sheet detection condition is: the insulating sheet exists, performing shielding area detection processing on the target end adhesive image to obtain a target sector-shaped shielding area; the target sector-shaped shielding area includes the extension handle of the end surface of the cylindrical battery cell; Performing a glue coating area detection process on the target end glue coating image to obtain an initial glue coating area; Subtract the target sector-shaped shielding area from the initial encapsulation area to obtain the encapsulation effective detection area; Performing radial scanning detection and determination processing on the effective detection area of ​​the rubber lagging to obtain multiple target rubber lagging detection areas; Continuous defect detection processing is performed on the plurality of target lagging detection areas to obtain lagging defect detection results.

[0006] In a second aspect, the embodiments of the present application provide a device for detecting a gluing condition of an end face of a cylindrical battery cell, comprising at least one processor and a memory connected to the at least one processor in communication; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method for detecting the gluing condition of the end face of the cylindrical battery cell according to any one of the embodiments of the first aspect.

[0007] In a third aspect, the embodiments of the present application provide an electronic device comprising the device for detecting the gluing condition of the end face of the cylindrical battery cell according to the embodiments of the second aspect.

[0008] In a fourth aspect, the embodiments of the present application provide a computer-readable storage medium storing computer executable instructions for causing a computer to perform the method for detecting the gluing condition of the end face of the cylindrical battery cell according to any one of the embodiments of the first aspect.

[0009] The embodiments of the present application include: in the process of detecting the gluing condition of the end face of the cylindrical battery cell, first, a target end face gluing image of the cylindrical battery cell to be detected is acquired; second, insulation sheet detection processing is performed on the target end face gluing image to obtain an insulation sheet detection result; third, when the insulation sheet detection result is that there is an insulation sheet, shielding area detection processing is performed on the target end face gluing image to obtain a target fan-shaped shielding area; the target fan-shaped shielding area includes an extension handle of the end face of the cylindrical battery cell; the target fan-shaped shielding area is an area that will interfere with the gluing condition detection, and the target fan-shaped shielding area lays a foundation for subsequent determination of a target gluing detection area, so as to improve the effective coverage rate of the gluing detection; fourth, gluing area detection processing is performed on the target end face gluing image to obtain an initial gluing area; fifth, the initial gluing area is subtracted by the target fan-shaped shielding area to obtain a gluing effective detection area; the target fan-shaped shielding area that will interfere with the gluing condition detection is removed from the initial gluing area to obtain the gluing effective detection area, so as to improve the effective coverage rate of the gluing detection; sixth, radial scanning detection judgment processing is performed on the gluing effective detection area to obtain a plurality of target gluing detection areas; and finally, continuity defect detection processing is performed on the plurality of target gluing detection areas to obtain a gluing defect detection result; the target gluing detection area can be used to quickly and reliably detect the gluing condition of the end face of the cylindrical battery cell. After the invalid target fan-shaped shielding area is removed, the gluing condition of the end face of the cylindrical battery cell is quickly and reliably detected based on the determined gluing effective detection area, so as to improve the effective coverage rate and reliability of the gluing condition detection. That is, the embodiments of the present application can improve the effective coverage rate and reliability of the gluing condition detection of the end face of the cylindrical battery cell.

[0010] Other features and advantages of the present application will be set forth in the description that follows, and in part will be apparent from the description, or can be learned by practice of the application. The purposes and other advantages of the present application will be realized and attained by the structure particularly pointed out in the description and appended claims. BRIEF DESCRIPTION OF DRAWINGS

[0011] Figure 1 is a flowchart of a method for detecting the encapsulation condition of the end face of a cylindrical battery cell provided by an embodiment of the present application; Figure 2 is a schematic diagram of the end face of a cylindrical battery cell provided by an embodiment of the present application; Figure 3 is a schematic diagram of the algorithm flow for generating a target sector shielding area provided by an embodiment of the present application; Figure 4 is a schematic diagram of the principle of radial scanning provided by an embodiment of the present application; Figure 5 is a schematic diagram of the overall flow of the method for detecting the encapsulation condition of the end face of a cylindrical battery cell provided by an embodiment of the present application; Figure 6 is a schematic diagram of the hardware structure of the device for detecting the encapsulation condition of the end face of a cylindrical battery cell provided by an embodiment of the present application. DETAILED DESCRIPTION

[0012] In order to make the purpose, technical solutions and advantages of the present application more clear, the present application is further described in detail below in combination with the drawings and embodiments.

[0013] It should be noted that although a logical sequence is shown in the flowchart in the description of the present application, in some cases, the steps shown or described in the flowchart can be performed in an order different from that in the flowchart. In the description of the present application, the meaning of "one or more" is one or more, and the meaning of "multiple" is two or more. The description of "first", "second" is only for the purpose of distinguishing technical features, and cannot be understood as indicating or implying relative importance or implying the number of indicated technical features or the sequence of indicated technical features.

[0014] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application and are not intended to limit the present application.

[0015] First, some terms involved in the present application are explained: Template matching: Template matching is a target detection method based on image similarity measurement, which finds the best matching position by sliding the predefined template image on the detection image pixel by pixel.

[0016] Binarization: Binarization is an image processing technique that converts grayscale or color images into images containing only two pixel values, typically 0 and 255, representing black and white.

[0017] Connected Component: A region in an image where pixels have the same value and are adjacent to each other.

[0018] Area Filtering: Area filtering is a region screening technique in morphological image processing, based on the area characteristics of connected domains to remove noise or invalid regions.

[0019] Threshold Segmentation: A technique that divides an image into foreground and background by comparing pixel grayscale values with a threshold value.

[0020] Color Image Channel Separation: The input RGB three-channel color image is decomposed into a red component image, a green component image, and a blue component image.

[0021] Color Space Conversion: Convert the RGB color space to the HSV color space to obtain the hue component, saturation component, and brightness component images.

[0022] Image / Channel Difference: Image / channel difference refers to generating a new difference image by calculating the difference between two images pixel by pixel.

[0023] ROI: Full name Region of Interest, refers to the "box on the feature map", in machine vision, image processing, from the processed image with a box, circle, ellipse, irregular polygon, etc. The area to be processed is called the region of interest.

[0024] Structural Element: Create a circular structural element S(r) for morphological operation.

[0025] Gray Open Operation: Erosion followed by dilation operation.

[0026] Gray Dilation: Maximum filtering of the image with the structural element S.

[0027] Minimum Circumscribed Circle: The smallest circle containing the target region.

[0028] Polar Coordinate Transformation: Conversion of rectangular coordinates to polar coordinates.

[0029] The application discloses a method for detecting the encapsulation condition of the end face of a cylindrical battery cell, a device for detecting the encapsulation condition of the end face of a cylindrical battery cell, an electronic device and a computer readable storage medium, and relates to the technical field of industrial vision detection. The method comprises the following steps: obtaining a target end face encapsulation image of a cylindrical battery cell to be detected; performing insulation sheet detection processing on the target end face encapsulation image to obtain an insulation sheet detection result; when the insulation sheet detection result is that there is an insulation sheet, performing shielding area detection processing on the target end face encapsulation image to obtain a target fan-shaped shielding area; performing encapsulation area detection processing on the target end face encapsulation image to obtain an initial encapsulation area; subtracting the target fan-shaped shielding area from the initial encapsulation area to obtain an encapsulation effective detection area; performing radial scanning detection judgment processing on the encapsulation effective detection area to obtain a plurality of target encapsulation detection areas; and performing continuity defect detection processing on the plurality of target encapsulation detection areas to obtain an encapsulation defect detection result. The effective coverage rate and reliability of the detection of the encapsulation condition of the end face of the cylindrical battery cell can be improved.

[0030] The embodiments of the application are further described below with reference to the drawings.

[0031] In a first aspect, as shown in the method for detecting the encapsulation condition of the end face of a cylindrical battery cell can include but is not limited to steps S110 to S170. Figure 1

[0032] Step S110: obtaining a target end face encapsulation image of a cylindrical battery cell to be detected.

[0033] Step S120: performing insulation sheet detection processing on the target end face encapsulation image to obtain an insulation sheet detection result.

[0034] Step S130: when the insulation sheet detection result is that there is an insulation sheet, performing shielding area detection processing on the target end face encapsulation image to obtain a target fan-shaped shielding area; the target fan-shaped shielding area includes an extension handle of the end face of the cylindrical battery cell.

[0035] Step S140: performing encapsulation area detection processing on the target end face encapsulation image to obtain an initial encapsulation area.

[0036] Step S150: subtracting the target fan-shaped shielding area from the initial encapsulation area to obtain an encapsulation effective detection area.

[0037] Step S160: performing radial scanning detection judgment processing on the encapsulation effective detection area to obtain a plurality of target encapsulation detection areas.

[0038] Step S170: performing continuity defect detection processing on the plurality of target encapsulation detection areas to obtain an encapsulation defect detection result.

[0039] Specifically, in step S110, the end face of the cylindrical battery cell is shown in the schematic diagram Figure 2 ​The end face of the cylindrical battery cell includes: battery cell, insulation sheet, extension handle and rubber coating.

[0040] Through step S110 to step S170, in the process of detecting the coating condition of the end face of the cylindrical battery cell, first, the target end coating image of the cylindrical battery cell to be detected is obtained; secondly, the target end coating image is subjected to insulation sheet detection processing to obtain the insulation sheet detection condition; then, when the insulation sheet detection condition is: the presence of an insulation sheet, the target end coating image is subjected to shielding area detection processing to obtain a target sector-shaped shielding area; the target sector-shaped shielding area includes the extension handle of the end face of the cylindrical battery cell; the target sector-shaped shielding area is an area that will interfere with the detection of the coating condition, and the detection of the target sector-shaped shielding area lays the foundation for the subsequent determination of the target coating detection area, so as to improve the effective coverage of the coating detection. rate; then, the target end glue image is subjected to glue area detection processing to obtain the initial glue area; then, the initial glue area is subtracted from the target sector shielding area to obtain the effective glue detection area; the target sector shielding area in the initial glue area that will interfere with the glue condition detection is removed to obtain the effective glue detection area to improve the effective coverage of the glue detection; then, the effective glue detection area is subjected to radial scanning detection and judgment processing to obtain multiple target glue detection areas; finally, the multiple target glue detection areas are subjected to continuous defect detection processing to obtain the glue defect detection results; based on the target glue detection area, the glue condition of the end face of the cylindrical battery cell can be quickly and reliably detected. After removing the invalid target sector shielding area, the glue condition of the end face of the cylindrical battery cell can be quickly and reliably detected based on the determined effective glue detection area, thereby improving the effective coverage and reliability of the glue condition detection. That is to say, the embodiment of the present application can improve the effective coverage and reliability of the detection of the glue condition of the end face of the cylindrical battery cell.

[0041] According to some embodiments of the present application, step S110 is further described. Step S110: obtaining an image of the adhesive coating on the target end of the cylindrical battery cell to be inspected, including but not limited to steps S111 to S112.

[0042] Step S111: Acquire an initial end-coating glue image of the cylindrical battery cell.

[0043] Step S112: performing image preprocessing on the initial end adhesive coating image to obtain a target end adhesive coating image; wherein the image preprocessing includes: color channel separation processing; the target end adhesive coating image includes: a red channel component image, a green channel component image, and a blue channel component image.

[0044] Specifically, step S110 further includes: determining the reference position of the cylindrical battery cell by template matching.

[0045] Specifically, the initial end face wrapping image is a color image to be processed. The side surface of the cylindrical battery cell can be captured by the camera to obtain the initial end face wrapping image.

[0046] Specifically, the step S112 includes color channel separation processing on the input color initial end face wrapping image to obtain a red channel component image, a green channel component image and a blue channel component image.

[0047] In some embodiments, the image preprocessing further includes color space conversion processing. Specifically, the obtained red channel component image, green channel component image and blue channel component image can be further subjected to color space conversion according to actual needs.

[0048] Through the steps S111 to S112, the color channel separation processing is performed on the collected initial end face wrapping image to obtain the red channel component image, the green channel component image and the blue channel component image, which lays a data foundation for subsequent insulating sheet detection processing and shielding area detection processing.

[0049] According to some embodiments of the present application, the step S120 is further illustrated, and the step S120 includes but is not limited to steps S121 to S125.

[0050] The step S121 acquires the red channel component image from the target end face wrapping image.

[0051] The step S122 performs binarization processing on the red channel component image to obtain a first binarization image.

[0052] The step S123 performs region feature analysis processing on the first binarization image to extract connected regions in the first binarization image.

[0053] The step S124 performs gray scale feature statistics on each connected region to obtain gray scale information.

[0054] The step S125 performs comparison processing on the gray scale information and gray scale determination threshold information, and determines the insulating sheet detection situation according to the obtained comparison result.

[0055] Specifically, in the step S121, based on the features of each channel separation image, the red channel component image Ir(x, y) is selected for insulating sheet detection processing to determine whether there is an insulating sheet.

[0056] Specifically, step S122 includes setting grayscale threshold information, which includes an upper threshold and a lower threshold; and performing binarization processing on the selected red channel component image Ir(x, y) based on the grayscale threshold information to obtain a first binarized image. This provides the data foundation for subsequent regional feature analysis.

[0057] Specifically, in step S124, the grayscale information includes: average grayscale intensity and grayscale standard deviation.

[0058] Specifically, in step S125, the grayscale judgment threshold information includes: a grayscale intensity threshold and a standard deviation threshold; wherein, the insulating sheet detection situation is determined based on the comparison result obtained, including: when the average grayscale intensity is less than the grayscale intensity threshold, and the standard deviation threshold is less than the standard deviation threshold, it is judged that there is no insulating sheet; otherwise, it is judged that there is an insulating sheet; and the determination of the existence of the insulating sheet is completed.

[0059] It should be noted that, when it is determined that no insulating sheet exists, the detection of the encapsulation condition of the cylindrical cell end face is terminated; when it is determined that an insulating sheet exists, the subsequent steps S130 to S170 are continued.

[0060] Through steps S121 to S125, the insulation sheet detection is completed, the potential insulation sheet area is extracted, and the insulation sheet's presence is determined, providing a reliable reference for whether to continue the shielded area detection process. Furthermore, during the insulation sheet detection phase, the system uses an adaptive threshold segmentation algorithm to effectively overcome the problem of false detection caused by envelope reflections. Compared with traditional fixed threshold methods, detection accuracy is significantly improved.

[0061] According to some embodiments of the present application, step S130 is further described. Step S130: performing shielding area detection processing on the target end bread glue image to obtain a target fan-shaped shielding area, including but not limited to steps S131 to S134.

[0062] Step S131: performing image difference processing on the red channel component image and the green channel component image obtained from the target end adhesive coating image to obtain a first difference image.

[0063] Step S132: performing image coarse positioning enhancement processing on the differential image to obtain an enhanced circular coarse positioning area.

[0064] Step S133: performing polar coordinate establishment processing and polar coordinate analysis processing based on the enhanced circular coarse positioning area to obtain the maximum angle interval.

[0065] Step S134: performing shielding area generation processing and hole filling processing according to the maximum angle interval to obtain a target sector-shaped shielding area.

[0066] Specifically, step S131 includes: performing a weighted difference operation on the red channel component image Ir(x, y) and the green channel component image Ig(x, y) to obtain a first difference image.

[0067] Specifically, in step S132, the image coarse positioning enhancement process includes: binarization, coarse positioning region extraction, ROI-based differential image cropping, and image enhancement. Specifically, step S132 includes but is not limited to steps S1321 to S1324.

[0068] Step S1321 : setting a threshold range, performing threshold segmentation and binarization based on the threshold range, and obtaining a second binarized image.

[0069] Step S1322, perform rough positioning region extraction processing: perform circular region extraction operation on the second binary image to extract the largest connected region in the binary image; in the largest connected region, use the minimum circumscribed circle algorithm to calculate the region center coordinates and radius R, we get the coordinates of the center of the region is the rough positioning area of ​​a circle with center O and radius R. is the row pixel coordinate, indicating the vertical position of the point in the image (from top to bottom); Represents column pixel coordinates, indicating the horizontal position of the point in the image (from left to right).

[0070] Step S1323: perform ROI-based differential image cropping to obtain a circular rough positioning area. It is understood that the ROI here refers to the extracted circular area.

[0071] Step S1324 , performing image enhancement processing: after defining the circular structure element S, performing a grayscale dilation operation on the cropped circular rough positioning area based on the circular structure element S to obtain an enhanced circular rough positioning area.

[0072] Specifically, step S133: performing polar coordinate establishment processing and polar coordinate analysis processing based on the enhanced circular coarse positioning area to obtain the maximum angle interval, including steps S1331 to S1333.

[0073] Step S1331: Binarize the enhanced circular rough positioning area again to obtain a third binary image, and further determine the candidate area from the third binary image; calculate the minimum circumscribed circle of the candidate area, and record the center coordinate set of each minimum circumscribed circle. ; Where i represents the i-th minimum circumscribed circle; is the pixel-level center coordinate of the i-th minimum circumscribed circle.

[0074] Step S1332: The center of the circular rough positioning area is O (That is, the coordinates of the center of the region mentioned above ) is used as the polar coordinate origin to establish a polar coordinate system; in the established polar coordinate system, polar coordinate transformation is implemented according to mathematical calculation knowledge, and the center coordinates of each pixel in the minimum circumscribed circle center coordinate set are converted into polar coordinates ; Among them, an angle set is generated based on the polar angle in each polar coordinate.

[0075] Step S1333: sort the polar angles in the angle set in order of size. After sorting, take the polar angle The maximum and minimum values ​​are differentially calculated to obtain the maximum angle interval .

[0076] Specifically, step S134 : performing shielding area generation processing and hole filling processing according to the maximum angle interval to obtain the target sector-shaped shielding area includes: steps S1341 to S1342 .

[0077] Step S1341: the shielding area generation process is specifically as follows: As the center reference, generate the target sector shielding area : ; Where (x, y) is the image pixel coordinate; is the coordinate of the center of the reference circle (the coordinate of the polar coordinate origin); is the shielding center angle of the target sector shielding area (i.e. the maximum angle interval mentioned above ); and ±45° is the shielding area angle; Calculates the polar angle.

[0078] Step S1342: simultaneously shield the target sector area Perform hole filling processing to obtain the final target sector-shaped shielding area.

[0079] like Figure 3 As shown, an example is given to illustrate the algorithm flow for generating a target sector-shaped shielding area in an embodiment of the present application. The algorithm for generating a target sector-shaped shielding area mainly includes: inputting a to-be-processed image, locating the center of a reference circle, extracting an annular feature area, detecting and screening feature points, establishing polar coordinate mapping, statistically analyzing angle distribution, determining the maximum angle interval, calculating the shielding area boundary, and calculating and outputting the target sector-shaped shielding area.

[0080] The target fan-shaped shielding area is an area that will interfere with the encapsulation condition detection. Through steps S131 to S134, the target fan-shaped shielding area is detected to lay a foundation for subsequent determination of the target encapsulation detection area, so as to improve the effective coverage rate of encapsulation detection.

[0081] According to some embodiments of the present application, step S140 is further illustrated, and step S140 is encapsulation region detection processing on the target end face encapsulation image to obtain an initial encapsulation region, including but not limited to steps S141 to S144.

[0082] Step S141: acquiring a green channel component image and a blue channel component image from the target end face encapsulation image.

[0083] Step S142: performing second difference processing on the green channel component image and the blue channel component image to obtain a second difference image.

[0084] Step S143: performing morphological filtering processing on the second difference image to obtain a filtered second difference image.

[0085] Step S144: performing binarization processing, connected region extraction processing, and screening processing based on area characteristics on the filtered second difference image to obtain the initial encapsulation region.

[0086] Specifically, the second difference processing is multi-channel difference processing; through steps S141 to S142, weighted difference operation is performed on the green channel component image Ib(x, y) and the blue channel component image Ig(x, y) to obtain a second difference image; and data foundation is laid for subsequent obtaining of the initial encapsulation region.

[0087] In step S143, the morphological filtering processing on the second difference image specifically refers to: after defining a circular structural element S, performing a gray open operation on the second difference image; and obtaining a filtered second difference image.

[0088] Specifically, step S144 includes but is not limited to steps S1441 to S1443.

[0089] Step S1441: performing binarization processing on the filtered second difference image to obtain a fourth binarization image.

[0090] Step S1442: performing connected region extraction processing on the fourth binarization image to obtain a plurality of connected regions, and acquiring area characteristics of each connected region.

[0091] Step S1443: according to the area characteristics, sorting in descending order of area, and screening a connected region with a relatively large area as the initial encapsulation region.

[0092] After the initial encapsulation area is obtained through steps S141 to S1443, the target sector-shaped shielding area in the initial encapsulation area that may interfere with the encapsulation condition detection is subsequently removed to obtain the encapsulation effective detection area, thereby improving the effective coverage of the encapsulation detection.

[0093] Take an example to further illustrate step S150. In step S150, perform the subtraction operation of the encapsulation area to obtain the effective detection area of ​​the encapsulation : ; in, is the pixel set of the original encapsulation area (i.e. the initial encapsulation area), It is a pre-calculated target sector shielding area; It is the effective detection area of ​​the lagging.

[0094] According to some embodiments of the present application, step S160 is further described. Step S160: radial scanning detection and judgment processing is performed on the effective detection area of ​​the rubber lagging to obtain multiple target rubber lagging detection areas, including but not limited to steps S161 to S164.

[0095] Step S161, radial scanning detection is performed on the effective detection area of ​​the encapsulation obtained in step S150, see Figure 4 The radial scanning principle is: the center of the rubber bag in the effective detection area As the origin, N detection lines are uniformly generated along the radial direction. , two adjacent detection lines Preset angles between After completing the radial scanning test, the coordinates of the end point of each test line (radial scanning coordinate calculation formula) are: ; Where R is the minimum circumscribed circle radius generated by the coarse positioning area, and 150 is the radius expansion amount.

[0096] Step S162, obtain the detection line Effective detection area with lagging The intersection area ; It is understandable that N detection lines The effective detection area of ​​the lagging There are multiple intersection areas , i represents the i-th intersection area.

[0097] Step S163: for each intersection area Calculate the minimum bounding rectangle parameters. Specifically, the minimum bounding rectangle parameters include: center coordinates , direction angle and half side length and .

[0098] Step S164: determine the intersection area where the main semi-axis length L1>0 as the effective detection area, and store the detection data for each effective detection area. and .

[0099] Through steps S161 to S164, after eliminating interference, multiple target lagging detection areas are obtained, laying a data foundation for subsequent continuous defect detection processing.

[0100] According to some embodiments of the present application, step S170 is further described. Step S170: continuous defect detection processing is performed on multiple target lagging detection areas to obtain lagging defect detection results, including but not limited to steps S171 to S174.

[0101] Step S171: traverse the target lagging detection area in sequence, determine the target lagging detection area where the lagging width is less than the preset width threshold as a width abnormal position, and generate an abnormal position index set based on multiple width abnormal positions.

[0102] Step S172: sequentially traverse the width abnormal positions in the abnormal position index set, perform continuous interval detection and recording processing according to the preset minimum number of continuous defect points, and obtain a continuous defect interval; the number of width abnormal positions included in the continuous defect interval is greater than the minimum number of continuous defect points.

[0103] Step S173: When the number of continuous defect intervals is not zero, it is determined that the lagging defect detection result is: there are continuous defect intervals.

[0104] Step S174: When the number of continuous defect intervals is zero, the lagging defect detection result is determined to be: there are no continuous defect intervals.

[0105] The defect area is identified by step S171. An example is given to illustrate step S171: First, set a preset width threshold T = X pixels; specifically, the classic value of X is 100 pixels, which is dynamically adjusted according to process requirements. Then, traverse all detection positions and record the index set of abnormal positions: ; in, It is an abnormal position index set, which can also be understood as an abnormal scan line index set. is the width of the rubber coating in the radial direction on the i-th scanning line, and N is the total number of detection points.

[0106] The continuity defect determination is realized by step S172. Take an example to illustrate step S172: First, initialize the counter, set the minimum number of continuous defect points m, and the current continuous length L to 0. Then, traverse the abnormal position index set : When the adjacent index satisfies : Let L = L + 1. Finally, when L ≥ m, record the continuous defect interval: ; Wherein, is the continuous defect interval, which is also the continuous defect index set. Specifically, if m = 6, when L ≥ 6, i.e. 6 consecutive detection position abnormalities trigger an alarm.

[0107] Through steps S171 to S174, the encapsulation condition of the cylindrical battery end face is quickly and reliably detected based on the determined encapsulation effective detection area, and the effective coverage rate and reliability of the encapsulation condition detection are improved.

[0108] According to some embodiments of the present application, after step S170, i.e. after obtaining the encapsulation defect detection result, the encapsulation condition detection method further includes but is not limited to steps S210 to S220.

[0109] Step S210: When the encapsulation defect detection result is: there is a continuous defect interval, mark and visually display the continuous defect interval.

[0110] Step S220: When the encapsulation defect detection result is: there is no continuous defect interval, perform size calculation processing on the encapsulation of the cylindrical battery end face to obtain the average encapsulation thickness.

[0111] Specifically, in step S210, in an embodiment, when there is a continuous defect interval, the continuous defect interval is merged, the defect is marked, and the entire corresponding defect area is visually displayed.

[0112] Specifically, in step S220, when performing size calculation processing, the calculation formula of the average encapsulation thickness used is: ; end the overall algorithm, and output: qualification determination and average encapsulation thickness .

[0113] Through steps S210 to S220, different subsequent processing is performed according to different encapsulation defect detection results, so that engineering personnel can timely learn about the encapsulation defect detection results and related situations.

[0114] In combination with Figure 5 , the overall flow of the encapsulation condition detection method for the cylindrical battery end face provided by an embodiment of the present application is further illustrated.

[0115] Step S501: input the initial end face encapsulation image of the cylindrical battery.

[0116] Step S502: Color channel separation is performed on the initial end face coating image to obtain a target end face coating image.

[0117] Step S503: Insulation sheet detection is performed based on the target end face coating image to determine whether the insulation sheet detection exists. If not, step S504 is executed; if yes, step S505 is executed.

[0118] Step S504: The detection is ended.

[0119] Step S505: Image difference processing, image coarse positioning enhancement processing, and image coarse positioning enhancement processing are performed based on the target end face coating image to obtain an enhanced circular coarse positioning region.

[0120] Step S506: Polar coordinate establishment processing and polar coordinate analysis processing are performed on the enhanced circular coarse positioning region to obtain a maximum angle interval.

[0121] Step S507: A target sector shielding region is generated based on the maximum angle interval.

[0122] Step S508: Coating region detection processing is performed on the target end face coating image to obtain an initial coating region. The initial coating region is subtracted from the target sector shielding region to obtain a coating effective detection region.

[0123] Step S509: Radial scanning detection judgment and continuity defect detection are performed based on the coating effective detection region.

[0124] Step S510: It is determined whether there is a defect. If yes, step S511 is executed; if not, step S512 is executed.

[0125] Step S511: Size calculation processing is performed on the end face coating of the cylindrical battery cell to obtain an average coating thickness.

[0126] Step S512: The defect region is marked and visualized.

[0127] It should be emphasized that the shortcomings of existing algorithms are as follows: insufficient ability to suppress reflective interference; fixed detection parameters and poor adaptability; insufficient accuracy in identifying local defects; a static rectangular shielding window is used during the detection process to avoid interference from fixed structures such as the extension handle, and the position and size of the window need to be manually pre-set; defect judgment relies on a single width threshold comparison, and lacks analysis of defect morphology and distribution patterns. This application proposes a feature extraction method based on data quantization. Through data quantification visual analysis technology, it fundamentally reconstructs the logical architecture of traditional detection methods and transforms subjective experience-driven feature judgment into a scientific decision-making system based on objective data quantification. In terms of interference elimination, the algorithm deeply combines the product characteristics of cylindrical cells and constructs a layered suppression mechanism for the interference sources of envelope reflection and extension handle obstruction: first, a reflection suppression mechanism is established based on material properties; second, a dynamic reference coordinate system correction technology is used to track the geometric features of the end face of the cylindrical cell in real time; finally, based on detection data screening, the systematic errors caused by process fluctuations are effectively eliminated.

[0128] In summary, the embodiment of the present application first adopts a multi-channel collaborative analysis strategy, combining red channel grayscale statistics with red-blue differential processing and blue-green channel differential processing, which effectively overcomes the problem of reflective interference in traditional methods in insulating sheet detection; secondly, through the polar coordinate dynamic shielding mechanism, the optimal shielding area is automatically generated based on the characteristic circle distribution analysis, which greatly improves the effective coverage of the rubber coating detection. The three-level progressive detection architecture adopted by the algorithm realizes rapid screening, and the key threshold can be dynamically adjusted with the parameterized design, which can effectively overcome the reflective interference and improve the detection reliability. The radial scanning strategy optimizes the stability while ensuring the detection accuracy, and the continuous defect judgment logic effectively balances the false positive rate and the missed detection rate. This technical solution realizes the determination of the existence of insulating sheets and the detection of rubber coating quality while maintaining a millisecond-level detection speed, which fully matches the high-speed beat requirements of the cylindrical battery production line. It can be seen that the cylindrical battery end face insulating sheet and rubber coating quality detection algorithm proposed in this application has achieved a significant improvement in detection capability and stability through an innovative multi-level detection architecture.

[0129] like Figure 6 As shown, the present invention also provides a device for detecting the encapsulation condition of the end face of a cylindrical battery cell, comprising: The processor 601 may be implemented as a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is configured to execute relevant programs to implement the technical solutions provided in the embodiments of the present application. The memory 602 can be implemented in the form of a read only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM), etc. The memory 602 can store an operating system and other application programs. When the technical solutions provided by the embodiments of the present specification are implemented by software or firmware, the related program codes are stored in the memory 602 and are called and executed by the processor 601 to implement the method for detecting the encapsulation condition of the end face of the cylindrical battery cell provided by the embodiments of the present application; The input / output interface 603 is configured to realize information input and output. The communication interface 604 is configured to realize the communication interaction between the device and other devices. The communication can be realized by a wired manner (for example, a USB, a network cable, etc.) or a wireless manner (for example, a mobile network, WIFI, Bluetooth, etc.). The bus 605 is configured to transmit information between various components (for example, the processor 601, the memory 602, the input / output interface 603, and the communication interface 604) of the device. The processor 601, the memory 602, the input / output interface 603, and the communication interface 604 are connected to each other through the bus 605 to realize the communication connection between the devices.

[0130] The embodiments of the present application also provide an electronic device, which comprises the device for detecting the encapsulation condition of the end face of the cylindrical battery cell.

[0131] The embodiments of the present application also provide a storage medium, which is a computer readable storage medium. The storage medium stores a computer program. The computer program is executed by a processor to implement the method for detecting the encapsulation condition of the end face of the cylindrical battery cell.

[0132] The memory is a non-transitory computer readable storage medium, which can be used to store a non-transitory software program and a non-transitory computer executable program. In addition, the memory can include a high-speed random access memory and can also include a non-transitory memory, for example, at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory can optionally include a memory remotely arranged relative to the processor. These remote memories can be connected to the processor through a network. Examples of the network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The device embodiments described above are only schematic and the units described as separate components can or can not be physically separated, and can be located in one place or can be distributed on multiple network units. According to actual needs, some or all of the modules can be selected to achieve the purpose of the embodiments of the present application.

[0133] As will be appreciated by one of ordinary skill in the art, all or some steps, systems of the above-disclosed methods can be implemented as software, firmware, hardware, or any suitable combination thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or as hardware, or as an integrated circuit, such as an application- specific integrated circuit. Such software can be distributed on computer readable media, which can comprise computer storage media (or non-transitory media) and communication media (or transitory media). As is well known to those of ordinary skill in the art, computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer. Further, as is well known to those of ordinary skill in the art, communication media typically embodies computer readable instructions, data structures, program modules, or other data in a modulated data signal, such as a carrier wave or other transport mechanism, and includes any information delivery media.

[0134] The above description is that of the preferred embodiments of the present application. Various modifications and changes can be made thereto without departing from the spirit of the application, which is defined by the appended claims.

Claims

1. A method for detecting the encapsulation condition of the end face of a cylindrical battery cell, characterized in that: include: Acquire an image of the adhesive coating on the target end of the cylindrical battery cell to be inspected; Performing insulation sheet detection processing on the target end adhesive coating image to obtain insulation sheet detection status; When the insulating sheet detection condition is: the insulating sheet exists, performing shielding area detection processing on the target end adhesive image to obtain a target sector-shaped shielding area; the target sector-shaped shielding area includes the extension handle of the end surface of the cylindrical battery cell; Performing a glue coating area detection process on the target end glue coating image to obtain an initial glue coating area; Subtract the target sector-shaped shielding area from the initial encapsulation area to obtain the encapsulation effective detection area; Performing radial scanning detection and determination processing on the effective detection area of ​​the rubber lagging to obtain multiple target rubber lagging detection areas; Continuous defect detection processing is performed on the plurality of target lagging detection areas to obtain lagging defect detection results.

2. The method for detecting the encapsulation condition of the end face of a cylindrical battery cell according to claim 1, characterized in that: The step of obtaining the adhesive coating image of the target end of the cylindrical battery cell to be inspected includes: Acquire an initial end coating image of the cylindrical battery cell; The initial end adhesive coating image is subjected to image preprocessing to obtain a target end adhesive coating image; wherein the image preprocessing includes: color channel separation processing; the target end adhesive coating image includes: a red channel component image, a green channel component image and a blue channel component image.

3. The method for detecting the encapsulation condition of the end face of a cylindrical battery cell according to claim 2, characterized in that: The performing insulation sheet detection processing on the target end adhesive coating image to obtain insulation sheet detection status includes: Acquire a red channel component image from the target end breading glue image; Binarizing the red channel component image to obtain a first binarized image; performing regional feature analysis on the first binary image to extract connected regions in the first binary image; Performing grayscale feature statistics on each of the connected regions to obtain grayscale information; The grayscale information is compared with the grayscale determination threshold information, and the insulation sheet detection condition is determined according to the obtained comparison result.

4. The method for detecting the encapsulation condition of the end face of a cylindrical battery cell according to claim 2, characterized in that: Performing shielding area detection processing on the target end bread glue image to obtain the target sector shielding area includes: performing image difference processing on a red channel component image and a green channel component image obtained from the target end adhesive coating image to obtain a first difference image; Performing image coarse positioning enhancement processing on the differential image to obtain an enhanced circular coarse positioning area; Polar coordinate establishment and polar coordinate analysis are performed based on the enhanced circular coarse positioning area to obtain the maximum angle interval; A shielding area generation process and a hole filling process are performed according to the maximum angle interval to obtain a target sector-shaped shielding area.

5. The method for detecting the encapsulation condition of the end face of a cylindrical battery cell according to claim 2, characterized in that: The step of performing a glue coating area detection process on the target end glue coating image to obtain an initial glue coating area includes: Acquire a green channel component image and a blue channel component image from the target end breading glue image; performing a second difference processing on the green channel component image and the blue channel component image to obtain a second difference image; performing morphological filtering on the second differential image to obtain a filtered second differential image; The filtered second differential image is subjected to binarization processing, connected region extraction processing, and area feature-based screening processing to obtain an initial encapsulation area.

6. The method for detecting the encapsulation condition of the end face of a cylindrical battery cell according to claim 2, characterized in that: The continuous defect detection process is performed on the plurality of target lagging detection areas to obtain the lagging defect detection results, including: Traversing the target lagging detection area in sequence, determining the target lagging detection area where the lagging width is less than a preset width threshold as a width abnormal position, and generating an abnormal position index set based on the multiple width abnormal positions; Sequentially traverse the width abnormal positions in the abnormal position index set, perform continuous interval detection and recording processing according to a preset minimum number of continuous defect points, and obtain a continuous defect interval; the number of the width abnormal positions included in the continuous defect interval is greater than the minimum number of continuous defect points; When the number of the continuous defect intervals is not zero, determining the lagging defect detection result as: there are continuous defect intervals; When the number of the continuous defect intervals is zero, the lagging defect detection result is determined to be: there are no continuous defect intervals.

7. The method for detecting the encapsulation condition of the end face of a cylindrical battery cell according to claim 6, characterized in that: After obtaining the lagging defect detection result, the lagging condition detection method further includes: When the lagging defect detection result is: there is a continuous defect interval, the continuous defect interval is marked and visually displayed; When the result of the encapsulation defect detection is: there is no continuous defect interval, the size of the end encapsulation of the cylindrical battery cell is calculated to obtain an average encapsulation thickness.

8. A device for detecting the encapsulation condition of the end face of a cylindrical battery cell, characterized in that: It includes at least one processor and a memory for communicating with the at least one processor; the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method for detecting the encapsulation condition of the end face of a cylindrical battery cell as described in any one of claims 1 to 7.

9. An electronic device, characterized in that: It includes the device for detecting the encapsulation condition of the end face of a cylindrical battery cell as described in claim 8.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the method for detecting the encapsulation condition of the end face of a cylindrical battery cell according to any one of claims 1 to 7.

Images