Method and system for detecting defects of pole piece, pole lug and glue of winding lithium battery

Abstract

The invention discloses a defect detection method and system for a pole piece, a pole lug and glue of a winding lithium battery, and the method comprises the steps: collecting a detection image of a to-be-detected winding battery cell, and carrying out the self-adaptive threshold segmentation of the detection image, and obtaining a pole piece detection region and a pole lug detection region; performing size measurement and bright and dark spot detection on the tab detection area to obtain a tab defect detection result; performing color extraction on the detection image to obtain a glue detection area, and further performing defect detection on the glue detection area to obtain a glue defect detection result; and performing region extraction on the pole piece detection region to obtain a pole piece near region and a pole piece far region, and further performing defect detection on the pole piece near region and the pole piece far region to obtain a pole piece defect detection result. According to the invention, different defects of the pole piece, the pole lug and the glue can be accurately detected, the over-killing rate is obviously reduced without missing detection, the loss caused by scrapping of over-killed cells is reduced, and the method can be widely applied to the technical field of battery detection.

Description

Technical Field

[0001] The present application relates to the field of battery detection technology, and in particular to a method and system for detecting defects in wound lithium battery pole pieces, pole ears and glue. Background Art

[0002] The existing detection methods and devices for pole pieces, pole ears and glue often only focus on a certain part for detection, such as focusing on the pole ears, focusing on the pole pieces, etc., and have poor adaptability to complex scenes. For example, it is difficult to optimize and improve the overkill caused by line scanning slippage and pole piece creases, and it is easy to miss subtle defects due to uneven brightness of the pole piece imaging. It is difficult to avoid overkill caused by interference from bright spots on the pole piece close to the copper foil. It is difficult for algorithms to adapt to different colors of glue such as green glue and yellow glue, and it is easy to miss slight defects on the edge of the pole piece. Summary of the invention

[0003] In order to solve the above technical problems, the purpose of the present invention is to provide a method and system for defect detection of wound lithium battery pole pieces, pole ears and glue with high defect detection accuracy.

[0004] To achieve the above-mentioned purpose, one aspect of an embodiment of the present application provides a defect detection method for a wound lithium battery pole piece, pole ear and glue, comprising the following steps:

[0005] Collecting a detection image of the wound battery cell to be detected, and then performing adaptive threshold segmentation on the detection image to obtain a pole piece detection area and a pole ear detection area;

[0006] Performing size measurement and light and dark spot detection on the tab detection area to obtain a tab defect detection result;

[0007] Performing color extraction on the detection image to obtain a glue detection area, and then performing defect detection on the glue detection area to obtain a glue defect detection result;

[0008] Performing region extraction on the pole piece detection region to obtain a pole piece near region and a pole piece far region, and then performing defect detection on the pole piece near region and the pole piece far region to obtain a pole piece defect detection result.

[0009] In some embodiments, the adaptive threshold segmentation of the detection image to obtain the pole piece detection area and the pole lug detection area specifically includes:

[0010] Calculating the background grayscale mean and background grayscale variance of the detection image;

[0011] Performing preliminary segmentation on the detection image according to the background grayscale mean and the background grayscale variance to obtain a binary image;

[0012] Performing a closing operation on the binary image, and then performing an opening operation on the binary image after the closing operation to obtain a first segmented area;

[0013] Caliper pairs are placed in the first segmented area to obtain multiple width values, and an opening operation is performed on the first segmented area, and then the pole piece detection area and the pole lug detection area are obtained according to the opening operation result and each of the width values.

[0014] In some embodiments, the tab defect detection result includes a first tab defect detection result, a second tab defect detection result, and a third tab defect detection result. The size measurement and light and dark spot detection of the tab detection area are performed to obtain the tab defect detection result, which specifically includes:

[0015] Performing interconnection operation on the tab detection area to obtain a plurality of tab segmentation areas;

[0016] Performing feature calculation on each of the tab segmented regions, and then performing tab screening according to the feature calculation results and a preset screening parameter threshold, to obtain the first tab defect detection result;

[0017] Measuring the size of the tab detection area according to the first tab defect detection result, and then obtaining the second tab defect detection result according to the size measurement result and a preset tab size threshold;

[0018] The tab detection area is subjected to light and dark spot detection to obtain a light spot defect area and a dark spot defect area, and then the third tab defect detection result is obtained according to the light spot defect area, the dark spot defect area and a preset tab plaque area threshold.

[0019] In some embodiments, the color extraction of the detection image to obtain the glue detection area specifically includes:

[0020] Performing channel decomposition on the detection image to obtain a first channel image, a second channel image, and a third channel image;

[0021] Performing adaptive threshold segmentation on the first channel image, the second channel image and the third channel image according to a preset grayscale range to obtain a corresponding plurality of segmented images;

[0022] The glue detection area is obtained by performing intersection calculation on each of the glue segmentation images.

[0023] In some embodiments, the glue defect detection result includes a first glue defect detection result, a second glue defect detection result, and a third glue defect detection result. The performing defect detection on the glue detection area to obtain the glue defect detection result specifically includes:

[0024] Performing an opening operation on the glue detection area to obtain the glue area area, and then obtaining the first glue defect detection result according to the glue area area and a preset glue area threshold;

[0025] According to the first adhesive defect detection result, a straight line search is performed on the adhesive detection area to obtain an adhesive edge, a copper foil edge, a pole ear edge and a pole piece edge;

[0026] Measure the size of the glue detection area to obtain the size measurement result, and calculate the relative position size from the glue edge to the copper foil edge, the pole ear edge and the pole piece edge;

[0027] Obtaining the second glue defect detection result according to the size measurement result, the relative position size, a preset glue size threshold, and a preset glue relative position size threshold;

[0028] The glue detection area is segmented by adaptive threshold to obtain a plurality of candidate defect areas, and then the features of each of the candidate defect areas are calculated, and the third glue defect detection result is obtained according to the features and preset feature defect specifications.

[0029] In some embodiments, the performing of region extraction on the pole piece detection region to obtain a pole piece near region and a pole piece far region specifically includes:

[0030] Performing texture analysis on the pole piece detection area to obtain a pole piece slip area;

[0031] Performing adaptive threshold segmentation on the pole piece detection area to obtain a fold interference area;

[0032] Performing regional operations on the pole piece detection area, the pole piece slip area, and the crease interference area to obtain the pole piece near area and the pole piece far area.

[0033] In some embodiments, the performing defect detection on the near region of the pole piece and the far region of the pole piece to obtain the pole piece defect detection result specifically includes:

[0034] Dividing the near region of the pole piece into a first edge region and a first internal region, performing adaptive threshold segmentation and merging on the first edge region and the first internal region to obtain a near region defect candidate region;

[0035] Dividing the pole piece far region into a second edge region and a second internal region, performing adaptive threshold segmentation and merging on the second edge region and the second internal region to obtain a far region defect candidate region;

[0036] Merging the near-region defect candidate region with the far-region defect candidate region to obtain a pole piece defect candidate region;

[0037] Calculating the regional features of the pole piece defect candidate region, and classifying the pole piece defect candidate region to obtain a category label;

[0038] Defect screening is performed according to the regional features and the category labels to obtain the pole piece defect detection result.

[0039] To achieve the above-mentioned purpose, another aspect of the embodiment of the present application provides a defect detection system for wound lithium battery pole pieces, pole ears and glue, comprising:

[0040] An image acquisition module is used to acquire a detection image of the wound battery cell to be detected, and then perform adaptive threshold segmentation on the detection image to obtain a pole piece detection area and a pole ear detection area;

[0041] A tab detection module is used to perform size measurement and light and dark spot detection on the tab detection area to obtain a tab defect detection result;

[0042] A glue detection module, used to perform color extraction on the detection image to obtain a glue detection area, and then perform defect detection on the glue detection area to obtain a glue defect detection result;

[0043] The pole piece detection module is used to extract the pole piece detection area to obtain the pole piece near area and the pole piece far area, and then perform defect detection on the pole piece far area and the pole piece near area to obtain the pole piece defect detection result.

[0044] To achieve the above-mentioned purpose, another aspect of an embodiment of the present application proposes an electronic device, which includes a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory. When the program is executed by the processor, the defect detection method for wound lithium battery pole sheets, pole ears and glue as described above is realized.

[0045] To achieve the above-mentioned purpose, another aspect of an embodiment of the present application proposes a storage medium, which is a computer-readable storage medium used for computer-readable storage, and the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the defect detection method for wound lithium battery pole sheets, pole ears and glue as described above.

[0046] The beneficial effects of the present invention are as follows: the defect detection method and system of the wound lithium battery pole piece, pole ear and glue of the present invention first collects the detection image of the wound battery cell to be detected, performs adaptive threshold segmentation on the detection image, obtains the pole piece detection area and the pole ear detection area, and then performs size measurement and light and dark spot detection on the pole ear detection area to obtain the pole ear defect detection result, then performs color extraction on the detection image to obtain the glue detection area, and then performs defect detection on the glue detection area to obtain the glue defect detection result, and finally, performs regional extraction on the pole piece detection area to obtain the near area of ​​the pole piece and the far area of ​​the pole piece, and then performs defect detection on the near area of ​​the pole piece and the far area of ​​the pole piece to obtain the pole piece defect detection result. The present invention can accurately detect different defects of pole pieces, pole ears and glue, can better detect subtle defects, significantly reduce the overkill rate without missing detection, can improve the equipment output yield, and reduce the loss caused by scrapping overkill batteries. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solution in the embodiments of the present invention, the following introduction is made to the drawings required for use in the embodiments of the present invention. It should be understood that the drawings introduced below are only for the convenience of clearly describing some embodiments of the technical solution of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0048] Figure 1 A flowchart of a defect detection method for a wound lithium battery pole piece, pole ear and glue provided by an embodiment of the present invention;

[0049] Figure 2 A schematic diagram of the left area for calculating the background mean and variance provided in an embodiment of the present invention;

[0050] Figure 3 A schematic diagram of the effect of segmenting regions of a pole piece provided by an embodiment of the present invention;

[0051] Figure 4 A schematic diagram of the effect of segmenting the tab area provided by an embodiment of the present invention;

[0052] Figure 5 An example diagram of a tab detection area and a characteristic calculation result of the tab detection area provided in an embodiment of the present invention;

[0053] Figure 6 An example diagram of a process for detecting tab defects provided by an embodiment of the present invention;

[0054] Figure 7 An example diagram of a process for adhesive defect detection provided by an embodiment of the present invention;

[0055] Figure 8A schematic diagram of an image of a pole piece slipping area provided by an embodiment of the present invention;

[0056] Fig. 9 Another image schematic diagram of a pole piece slipping area provided by an embodiment of the present invention;

[0057] Fig.10 An image schematic diagram of a fold interference area provided by an embodiment of the present invention;

[0058] Fig.11 A schematic diagram of a pole piece near region and a pole piece far region provided in an embodiment of the present invention;

[0059] Fig.12 A schematic diagram of the structure of a defect detection system for wound lithium battery pole pieces, pole ears and glue provided by an embodiment of the present invention;

[0060] Fig.13 A schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application. They are only examples of devices and methods consistent with some aspects of the embodiments of the present application as detailed in the attached claims.

[0062] It is understood that the terms "first", "second", etc. used in this application can be used to describe various concepts in this article, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another concept. For example, without departing from the scope of the embodiment of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determination".

[0063] The terms "at least one", "multiple", "each", "any", etc. used in this application, at least one includes one, two or more, multiple includes two or more, each refers to each of the corresponding multiple, and any refers to any one of the multiple.

[0064] In the production process of lithium battery cells, if the defects of pole pieces, pole ears and glue cannot be accurately detected, such as perforation, scratches, exposed foil, edge loss and other defects, it will seriously affect the performance of the product. Therefore, in the winding process, accurate detection of pole pieces, pole ears and glue is an important part.

[0065] The existing detection methods and devices for pole pieces, pole ears and glue have the following shortcomings:

[0066] 1. Existing methods and devices generally focus on the detection of tabs or pole pieces, and there are few complete detection devices and methods covering tabs, pole pieces and glue;

[0067] 2. When imaging is performed using a line scan camera solution, it is inevitable that the equipment will slip during operation, resulting in local imaging abnormalities. Existing methods often detect normal areas of slippage as defects, resulting in partial over-detection;

[0068] 3. During the production process, the pole piece may occasionally have minor creases, but the image is relatively clear, which is normal. Existing methods often detect such acceptable creases as defects, resulting in some over-killing;

[0069] 4. There are often slight wrinkles in the electrode area close to the copper foil, which causes the local image to be obviously bright or have slight bright spots, which is very similar to the defects on the electrode farther away. Existing methods often detect such acceptable bright spots as defects, resulting in some over-killing;

[0070] 5. There are slight defects in the edge area of ​​the pole piece, especially in the edge transition zone, such as scratches, a small amount of material loss, etc., and the defect contrast is low. This type of defect needs to be detected, and the existing methods often fail to detect it successfully, resulting in missed detection;

[0071] 6. Glues come in different colors, and the images of glues at different positions in the field of view are quite different. The existing methods are difficult to detect accurately and are prone to miss detection;

[0072] 7. AI algorithms require a large number of samples for training and are difficult to adapt to contour defects. In addition, new defects are prone to appear on site, and it is difficult for AI algorithms to quickly respond to customers' needs for detecting new defects.

[0073] To this end, an embodiment of the present invention proposes a defect detection method for wound lithium battery pole pieces, pole ears and glue, firstly, a detection image of the wound battery cell to be detected is collected, and the detection image is adaptively thresholded to obtain the pole piece detection area and the pole ear detection area, and then the pole ear detection area is dimensioned and the light and dark spots are detected to obtain the pole ear defect detection result, then the detection image is color extracted to obtain the glue detection area, and then the glue detection area is defect detected to obtain the glue defect detection result, and finally, the pole piece detection area is region extracted to obtain the near area of ​​the pole piece and the far area of ​​the pole piece, and then the near area of ​​the pole piece and the far area of ​​the pole piece are defect detected to obtain the pole piece defect detection result. The present invention can accurately detect different defects of pole pieces, pole ears and glue, can better detect subtle defects, significantly reduce the overkill rate without missing detection, can improve the equipment output yield, and reduce the loss caused by scrapped overkill batteries.

[0074] Reference Figure 1 , Figure 1 A flowchart of a defect detection method for a wound lithium battery pole piece, a pole ear and a glue provided in an embodiment of the present invention. The embodiment of the present invention provides a defect detection method for a wound lithium battery pole piece, a pole ear and a glue, and the method includes steps S101 to S104:

[0075] S101, collecting a detection image of the wound battery cell to be detected, and then performing adaptive threshold segmentation on the detection image to obtain a pole piece detection area and a pole ear detection area;

[0076] In some optional embodiments, the detection of the pole piece, the pole ear and the glue includes 4 detection stations, namely the upper station of the positive electrode, the lower station of the positive electrode, the upper station of the negative electrode and the lower station of the negative electrode. The upper and lower stations of the positive electrode respectively detect the defects related to the front and back of the positive electrode, and the upper and lower stations of the negative electrode respectively detect the defects related to the front and back of the negative electrode. The types of defects to be detected include dark spots, bright spots, residual glue on the pole piece, joints (red / white / yellow, etc.), foreign matter, scratches, edge fall, exposed foil, missing pole ear, missing glue (green / yellow, etc.), unqualified pole ear size, unqualified glue size, unqualified glue position, perforation and damage, etc.

[0077] The embodiment of the present invention collects the inspection image of the wound battery cell based on the visual hardware system, and the visual hardware system includes a camera, a lens, a light source, a light source controller, an industrial computer, a background board, a PLC and related cables. The hardware solutions of the four inspection stations are unified, except for the imaging and the targets in the field of view. The inspection methods can be compatible through parameter configuration. First, the positive electrode sheet / ear / glue arrives at the upper positive electrode inspection station, triggering the camera to take a picture to obtain the inspection image of the current station. Then, the positive electrode sheet / ear / glue arrives at the lower positive electrode inspection station, triggering the camera to take a picture to obtain the inspection image of the current station. Then, it is determined whether the inspection image is a color image. If not, the inspection result is unqualified and the wound battery cell is discarded; if so, the next step of the defect detection process is carried out.

[0078] Furthermore, line scan imaging or area array imaging methods can be used to collect inspection images of wound battery cells. Line scan imaging methods are used for large-sized wound products, and area array imaging methods are selected for smaller-sized products. The advantages of the line scan imaging method are uniform imaging, high precision, and high image resolution. It is also suitable for imaging scenarios of coiled or long products; the disadvantage is that the imaging is sensitive to the relative position and angle of the camera and the light source, and is very sensitive to jitter, slippage, and rewinding. The advantage of the area array imaging method is that it is not very sensitive to the relative position of the camera and the light source, and is not sensitive to jitter, slippage, and rewinding. More lighting solutions can be selected and the price is cheaper; the disadvantage is that compared with the line scan solution, the precision is lower and the imaging is uneven.

[0079] As an optional implementation, the step of performing adaptive threshold segmentation on the detection image to obtain the pole piece detection area and the pole ear detection area can be specifically divided into the following steps S1011 to S1014:

[0080] S1011, calculating the background grayscale mean and background grayscale variance of the detection image;

[0081] Specifically, the color detection image is first converted into a grayscale image, and then the background grayscale mean and variance are extracted in the local area on the left of the grayscale image. The left area of ​​the background mean and variance is calculated as follows: Figure 2 The background mean and variance are automatically calculated for each image, which serves as the basis for subsequent algorithm parameter adaptation.

[0082] S1012, performing preliminary segmentation on the detection image according to the background grayscale mean and the background grayscale variance to obtain a binary image;

[0083] Exemplarily, the detection image can be preliminarily segmented according to the grayscale range of [bg_value+10,255], where bg_value is the background grayscale mean of the detection image, and the binary images of the pole piece and the pole ear area are obtained by segmentation.

[0084] S1013, performing a closing operation on the binary image, and then performing an opening operation on the binary image after the closing operation to obtain a first segmented region;

[0085] For example, a rectangular structure element with a width × height = 10 × 10 is used to perform a closing operation on the binary image, and then a rectangular structure element with a width × height = 100 × 2 is used to perform an opening operation, thereby obtaining the segmented area of ​​the pole piece and the pole ear (i.e., the first segmented area). The embodiment of the present invention can well connect the weak edge area and eliminate the interference area on the background through the opening and closing operation. The schematic diagram of the segmented area effect of the pole piece is shown in FIG. Figure 3 As shown, the schematic diagram of the segmentation effect of the tab is as follows Figure 4 shown.

[0086] S1014, placing calipers in the first segmented area to obtain multiple width values, and performing an opening operation on the first segmented area, and then obtaining a pole piece detection area and a pole ear detection area according to the opening operation result and each width value.

[0087] In some optional embodiments, N caliper pairs are placed along the image height direction, N is generally set to 30, and N width values ​​are obtained on the segmented area of ​​the pole piece and the pole ear (i.e., the first segmented area), and then the width values ​​are sorted from small to large, and the width value of the sequence number 0.2*N is used as the width polar_w of the pole piece, so as to avoid interference with the accurate extraction of the width of the pole ear due to the connection band. Then, the segmented area of ​​the pole piece and the pole ear (i.e., the first segmented area) is opened, and the rectangular structure element of the opening operation can be set to width × degree = (polar_w*1.25) × 1, and the binary image is first eroded using the rectangular structure element, and then the eroded binary image is expanded using the same rectangular structure element to obtain the pole piece detection area and the pole ear detection area.

[0088] It should be noted that the rectangular structural elements selected in the above-mentioned opening and closing operation processes can be set according to actual needs and are not limited here.

[0089] S102, measuring the size and detecting the bright and dark spots in the tab detection area to obtain a tab defect detection result;

[0090] As an optional implementation, the tab defect detection result includes a first tab defect detection result, a second tab defect detection result, and a third tab defect detection result. The step of performing size measurement and light and dark spot detection on the tab detection area to obtain the tab defect detection result can be specifically divided into the following steps S1021 to S1024:

[0091] S1021, performing interconnection operation on the tab detection area to obtain a plurality of tab segmentation areas;

[0092] S1022, performing feature calculation on each tab segmentation area, and then performing tab screening according to the feature calculation result and a preset screening parameter threshold to obtain a first tab defect detection result;

[0093] Specifically, the tab detection areas after the opening operation are connected to obtain multiple separated tab segmentation areas, and the width, height, aspect ratio, and rectangularity of all tab segmentation areas are calculated, such as Figure 5 The following are examples of the characteristic calculation results of the tab detection area and the tab detection area. Because the tab may be deformed, the tab can be comprehensively judged and screened out based on the characteristic calculation results such as width, height, aspect ratio and rectangularity. If the tab is successfully screened, the next step is tab defect detection; if the tab fails to be screened, it is a missing tab defect.

[0094] It should be noted that the tab sizes of different batteries are different, and the specific screening parameter thresholds can be adjusted according to the on-site usage. For example, the screening parameter thresholds can be set to: width>400pixel, height>50pixel, aspect ratio>5, rectangularity>0.85, area>25000pixel2.

[0095] S1023, measuring the size of the tab detection area according to the first tab defect detection result, and then obtaining a second tab defect detection result according to the size measurement result and a preset tab size threshold;

[0096] Specifically, when the first tab defect detection result is that a tab exists, the length, width and other dimensions of the tab are measured to obtain a dimension measurement result, which is then compared with the set tab dimension threshold and tolerance range to determine whether there are any unqualified tab dimensions.

[0097] It should be noted that the lug sizes of different products are different, and the lug size threshold can be set according to the product specifications. For example, the lug size threshold can be set as follows: the lug length is 7±1 mm, and the lug width is 3±0.5 mm.

[0098] S1024, performing light and dark spot detection on the tab detection area to obtain the light spot defect area and the dark spot defect area, and then obtaining a third tab defect detection result based on the light spot defect area, the dark spot defect area and a preset tab plaque area threshold.

[0099] Specifically, in the lug detection area, the obvious bright or dark spot defects on the lug are extracted and compared with the preset lug plaque area threshold to determine whether there are defects on the lug. It should be noted that the lug plaque area threshold can be set according to customer SOP specifications and on-site inspection conditions. Exemplarily, the lug plaque area threshold can be set to: if the lug bright spot defect area is greater than 100 pixel2, or the dark spot defect area is greater than >300 pixel, the lug defect is unqualified.

[0100] In summary, if Figure 6 The figure shows an example of the process of detecting tab defects. As long as there is a missing tab or the tab size is unqualified or the tab defect is unqualified, the wound battery cell is judged as a defective product and is discarded.

[0101] S103, performing color extraction on the detection image to obtain a glue detection area, and then performing defect detection on the glue detection area to obtain a glue defect detection result;

[0102] Specifically, the glue is usually green or yellow in color, and its defects are mainly inaccurate positioning, missing stickers, scratches, and breakage.

[0103] As an optional implementation, the step of performing color extraction on the detection image to obtain the glue detection area can be specifically divided into the following steps S1031 to S1033:

[0104] S1031, performing channel decomposition on the detection image to obtain a first channel image, a second channel image, and a third channel image;

[0105] S1032, performing adaptive threshold segmentation on the first channel image, the second channel image, and the third channel image according to a preset grayscale range to obtain a corresponding plurality of segmented images;

[0106] S1033, performing intersection calculation on each glue segmentation image to obtain a glue detection area.

[0107] Specifically, the collected color detection image is decomposed into three channel images of R, G, and B (i.e., the first channel image, the second channel image, and the third channel image), and the R, G, and B three channel images are threshold segmented according to the grayscale range of the glue imaging on different channels, and then the intersection of the segmented areas of the three channels is calculated to obtain the glue detection area for color extraction.

[0108] As an optional implementation, the glue defect detection result includes a first glue defect detection result, a second glue defect detection result, and a third glue defect detection result. The step of performing defect detection on the glue detection area to obtain the glue defect detection result can be specifically divided into the following steps S1034 to S1038:

[0109] S1034, performing an opening operation on the glue detection area to obtain the glue area, and then obtaining a first glue defect detection result according to the glue area and a preset glue area threshold;

[0110] Specifically, an opening operation is performed on the glue detection area to obtain the glue area. If the glue area is greater than a preset glue area threshold, glue exists, otherwise glue does not exist. The glue area threshold can be set according to actual needs and is not limited here.

[0111] S1035, performing a straight line search on the glue detection area according to the first glue defect detection result to obtain a glue edge, a copper foil edge, a pole ear edge, and a pole piece edge;

[0112] S1036, measuring the size of the glue detection area, obtaining the size measurement result, and calculating the relative position size from the glue edge to the copper foil edge, the pole ear edge, and the pole piece edge;

[0113] S1037, obtaining a second glue defect detection result according to the size measurement result, the relative position size, the preset glue size threshold, and the preset glue relative position size threshold;

[0114] Specifically, when the first glue defect detection result is that glue exists, the glue edge, copper foil edge, pole ear edge and pole piece edge are found in the local area and nearby area of ​​the glue through a straight line search algorithm, and then the length and width of the glue and the relative position size of the glue relative to the copper foil edge, pole ear edge and pole piece edge are calculated. Then, according to the set glue size threshold and glue relative position size threshold, it is judged whether it meets the requirements to obtain the second glue defect detection result. The glue size threshold and glue relative position size threshold can be set according to actual needs and are not limited here.

[0115] S1038, performing adaptive threshold segmentation on the glue detection area to obtain multiple candidate defect areas, and then calculating the features of each candidate defect area, and obtaining a third glue defect detection result based on the features and preset feature defect specifications.

[0116] Specifically, within the glue detection area, candidate defects on the glue surface are extracted by an automatic threshold segmentation algorithm, and multiple features of each candidate defect (such as defect area, defect grayscale, etc.) are calculated to determine the defect category. A third glue defect detection result is obtained based on whether there is a glue defect according to the set characteristic defect specification. Exemplarily, the characteristic defect specification may be: glue defect area>200pixel2, and glue defect grayscale>60, then there is a glue defect.

[0117] In summary, if Figure 7 The figure shows an example flow chart of glue defect detection. As long as there is glue deficiency or the glue size is unqualified or the glue position size is unqualified, the wound battery cell is judged as a defective product and is discarded.

[0118] S104, performing region extraction on the pole piece detection region to obtain the pole piece near region and the pole piece far region, and then performing defect detection on the pole piece near region and the pole piece far region to obtain the pole piece defect detection result.

[0119] Specifically, there are many defects on the pole piece and the shapes are complex. The defects on the pole piece include: dark spots, bright spots, residual adhesive on the pole piece, joints (red / white / yellow, etc.), foreign matter, scratches, edge drop, exposed foil, perforation, breakage, etc.

[0120] As an optional implementation, the step of performing region extraction on the pole piece detection region to obtain the pole piece near region and the pole piece far region can be specifically divided into the following steps S1041 to S1043:

[0121] S1041, performing texture analysis on the pole piece detection area to obtain the pole piece slipping area;

[0122] Specifically, before extracting the pole piece slipping area, the machine taping area of ​​preset color is extracted from the color detection image by color extraction, and the manual taping area with poor imaging is extracted by morphology through the pole ear and pole piece area and the pole piece width, and the manual taping area is merged with the machine taping area to obtain the taping area. Figure 8 and Fig. 9 The figure shows an image diagram of the pole piece slipping area. The normal area of ​​the pole piece is imaged uniformly, while the pole piece slipping area has slight and dense vertical textures. The embodiment of the present invention extracts the pole piece slipping area on the pole piece through a texture analysis algorithm.

[0123] In some optional embodiments, the texture on the pole piece is first extracted by the Canny algorithm. Then, the texture is interrupted according to the combination of straight lines and circular rings to obtain straight line textures and arc textures. Next, the linear texture is obtained by screening according to the height, width and direction of the texture. Then, the texture is converted to a region, and a closing operation of the rectangular structural element width × height = 100 × 60 is performed, and then the area is screened, and the area > 7000 pixel2 is retained. Then, the axis-parallel circumscribed rectangle of the region is obtained to obtain the pole piece slip area.

[0124] S1042, performing adaptive threshold segmentation on the pole piece detection area to obtain a fold interference area;

[0125] In some optional embodiments, such as Fig.10The figure shows an image diagram of the crease interference area. Compared with the pole piece slipping area, the pole piece crease interference area is generally a horizontal crease with only one relatively obvious texture. First, the mean and variance of the pole piece are calculated. Then, based on the mean and variance, the low threshold low_thre and high threshold high_thre of the segmentation are calculated by the following formula, and the image is segmented to obtain a binary image:

[0126] low_thre=mean-35;

[0127] high_thre=mean-(deviation*3.5)

[0128] Among them, mean is the mean of the pole piece, and deviation is the variance of the pole piece.

[0129] Next, the region is closed using a rectangular structure element of width × height = 15 × 1. Then, the region is opened using a rectangular structure element of width × height = (polar_w*0.9) × 1. Finally, the axis-parallel circumscribed rectangle of the region is obtained to obtain the fold interference region.

[0130] S1043, performing regional operations on the pole piece detection area, the pole piece slip area, and the crease interference area to obtain the pole piece near area and the pole piece far area.

[0131] Specifically, for the pole piece slip area and crease interference area, an adaptive threshold segmentation algorithm is used to obtain the more serious bright / dark defect areas in the interference area. First, the grayscale mean and variance deviation of the pole piece are calculated. If the calculated grayscale value is greater than mean+40, then the area is a relatively serious bright defect area; if the calculated grayscale value is less than mean-30, then the area is a relatively serious dark defect area. Then, based on the aforementioned obtained pole ear detection area, pole piece detection area, and pole piece width, a morphological algorithm is used to obtain the pole piece near area and pole piece far area. Fig.10 The figure shows the schematic diagram of the near region and far region of the pole piece. According to the position of the pole lug and the overall area of ​​the pole piece, the near region 1 and the near region 2 of the pole piece close to the pole lug and the far region 1 and the far region 2 of the pole piece far from the pole lug are generated. Finally, the near region and the far region of the pole piece are subtracted from the slip region of the pole piece and the crease interference region to form the new near region and the far region of the pole piece.

[0132] It should be noted that since the pole piece slip area and the crease interference area are normal areas, the embodiment of the present invention subtracts the pole piece slip area and the crease interference area (i.e., performs regional shielding) to form new pole piece near area and pole piece far area, thereby avoiding a large amount of overkill.

[0133] As an optional implementation, the step of performing defect detection on the near region and the far region of the pole piece to obtain the pole piece defect detection result can be specifically divided into the following steps S1044 to S1048:

[0134] S1044, dividing the near region of the pole piece into a first edge region and a first internal region, performing adaptive threshold segmentation and merging on the first edge region and the first internal region, and obtaining a near region defect candidate region;

[0135] Specifically, for the near-pole region, a rectangular structural element with width × height = 30 × 1 is used for corrosion to obtain the first internal region. Then, the near-pole region is subtracted from the eroded region to obtain the first edge region. For the first edge region, an adaptive threshold segmentation algorithm with a loose threshold is used to extract the first edge defect candidate region; for the first internal region, an adaptive threshold segmentation algorithm with a strict threshold is used to extract the first internal defect candidate region. Then, the first edge defect candidate region and the first internal defect candidate region are merged to form a near-region defect candidate region.

[0136] S1045, dividing the far region of the pole piece into a second edge region and a second inner region, performing adaptive threshold segmentation and merging on the second edge region and the second inner region to obtain a far region defect candidate region;

[0137] Specifically, for the far region of the pole piece, a rectangular structural element width × height = 30 × 1 is used for corrosion to obtain the second internal region. Then, the far region of the pole piece is subtracted from the eroded region to obtain the second edge region. For the second edge region, an adaptive threshold segmentation algorithm with a loose threshold is used to extract the second edge defect candidate region; for the second internal region, an adaptive threshold segmentation algorithm with a strict threshold is used to extract the second internal defect candidate region. For the second internal region, an adaptive threshold segmentation algorithm with a strict threshold is used to extract the second internal defect candidate region. Then, the second edge defect candidate region and the second internal defect candidate region are merged to form a far region defect candidate region.

[0138] Among them, edge defects are generally bright spots formed by material dropouts, which are more obvious. For the extraction of the second edge defect candidate area, first obtain the grayscale mean of the pole piece. Then, perform threshold segmentation, set a loose low threshold = mean + 40, and the segmented area is the second edge defect candidate area. For the second internal defect candidate area, the following three methods are used for defect extraction. Finally, the areas obtained by methods 1, 2, and 3 are merged to obtain the second internal defect candidate area:

[0139] Method 1: Extract bright / dark defects through automatic threshold segmentation, which is the same as the second edge defect candidate area extraction method mentioned above.

[0140] Method 2: Extracting regions by dynamic thresholding. First, perform mean filtering on the image, and select a filter kernel size of 9 × 9. Then, obtain the defect bright region and defect dark region based on the mean filtered image and the original image.

[0141] Method 3: Extract defective areas through texture analysis. First, use the Canny algorithm to extract the texture area on the pole piece. Then, filter by the length of the texture to filter out very small textures. Then, the texture edge is converted into a closed area. Next, perform a closed operation on the area with a rectangular structural element width × height = 8*8. Finally, filter the closed area, and the area larger than 500 pixels is a defective area.

[0142] S1046, merging the near-region defect candidate region and the far-region defect candidate region to obtain the pole piece defect candidate region;

[0143] S1047, calculating the regional features of the pole piece defect candidate regions, and classifying the pole piece defect candidate regions to obtain category labels;

[0144] S1048. Defect screening is performed according to regional features and category labels to obtain pole piece defect detection results.

[0145] Specifically, the grayscale features and regional features of the pole piece defect candidate area are calculated, such as the defect grayscale mean and variance, background grayscale, defect contrast, defect area, defect circumscribed rectangle length and aspect ratio, etc., and then the pole piece defect candidate area is classified using the binary tree method according to the calculated regional features to obtain category labels, where the category labels include dark spots / dark marks, bright spots, pole piece residual glue (tape connection) / foreign matter, scratches / edge drop / foil leakage, and missing pole ears, etc. Finally, according to the category labels and defect features of the pole piece defect candidate area, the combined post-processing logic is used to filter out the over-killed defects and finally obtain the real defects. If any of these defects exists, the wound battery cell is judged as a defective product and the wound battery cell is discarded.

[0146] Among them, if the defect grayscale value is more than 15 less than the background grayscale value, it is a dark spot / dark mark; if the defect grayscale value is more than 15 brighter than the background grayscale value, it is a bright spot; the residual glue (joint) / foreign matter of the pole piece is obtained by color extraction to obtain the joint or foreign matter; the bright spot detected in the edge area of ​​the pole piece is edge material loss; the long and thin defects on the pole piece are scratches; the large area of ​​bright defects on the pole piece with relatively uniform grayscale values ​​is leaking foil; if there is no pole ear in the image, it is a missing pole ear.

[0147] The above describes the defect detection method for wound lithium battery pole pieces, pole ears and glue according to the embodiment of the present invention. It can be recognized that compared with the defect detection method for wound battery cells in the prior art, the embodiment of the present invention can accurately detect different defects of pole pieces, pole ears and glue, and can solve the difficulties such as slippage interference of line scan images, interference from pole piece creases, difficulty in detecting different types of glue, interference from bright spots caused by copper foil near the pole ears and local deformation of the pole pieces. It can better detect subtle defects and better meet the detection needs of customers. It can significantly reduce the overkill rate without missing any detection, improve the output yield of the equipment, and reduce the losses caused by scrapped overkill batteries.

[0148] Reference Fig.12 The embodiment of the present invention also provides a defect detection system for wound lithium battery pole pieces, pole ears and glue, including:

[0149] An image acquisition module is used to acquire the detection image of the wound battery cell to be detected, and then perform adaptive threshold segmentation on the detection image to obtain the pole piece detection area and the pole ear detection area;

[0150] Tab detection module, used to measure the size and detect bright and dark spots in the tab detection area to obtain tab defect detection results;

[0151] The glue detection module is used to perform color extraction on the detection image to obtain the glue detection area, and then perform defect detection on the glue detection area to obtain the glue defect detection result;

[0152] The pole piece detection module is used to extract the pole piece detection area to obtain the pole piece near area and the pole piece far area, and then perform defect detection on the pole piece far area and the pole piece near area to obtain the pole piece defect detection result.

[0153] The contents of the above-mentioned defect detection method embodiments for wound lithium battery pole sheets, pole tabs and glue are all applicable to the present defect detection system embodiments for wound lithium battery pole sheets, pole tabs and glue. The functions specifically implemented by the present defect detection system embodiments for wound lithium battery pole sheets, pole tabs and glue are the same as those in the above-mentioned defect detection method embodiments for wound lithium battery pole sheets, pole tabs and glue, and the beneficial effects achieved are also the same as those achieved by the above-mentioned defect detection method embodiments for wound lithium battery pole sheets, pole tabs and glue.

[0154] The embodiment of the present invention also provides an electronic device, the electronic device comprising: a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory, and the program is executed by the processor to realize the above-mentioned defect detection method for wound lithium battery pole piece, pole ear and glue. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0155] like Fig.13 FIG. 1 is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present invention, referring to FIG. Fig.13 , an embodiment of the present invention provides an electronic device, including:

[0156] The processor 1001 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present invention.

[0157] The memory 1002 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). The memory 1002 can store an operating system and other application programs. When the technical solution provided in the embodiments of this specification is implemented by software or firmware, the relevant program code is stored in the memory 1002, and the processor 1001 calls and executes the defect detection method for wound lithium battery pole pieces, pole ears, and glue of the embodiment of the present invention;

[0158] Input / output interface 1003, used to implement information input and output;

[0159] The communication interface 1004 is used to realize the communication interaction between the device and other devices. The communication can be realized through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WIFI, Bluetooth, etc.);

[0160] A bus 1005 , which transmits information between various components of the device (e.g., the processor 1001 , the memory 1002 , the input / output interface 1003 , and the communication interface 1004 );

[0161] The processor 1001 , the memory 1002 , the input / output interface 1003 and the communication interface 1004 are connected to each other in communication within the device via the bus 1005 .

[0162] An embodiment of the present invention also provides a storage medium, which is a computer-readable storage medium used for computer-readable storage. The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the above-mentioned defect detection method for wound lithium battery pole pieces, pole ears and glue.

[0163] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0164] The embodiment of the present invention also discloses a computer program product or a computer program, wherein the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes Figure 1 The method shown.

[0165] In some selectable embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the above-mentioned boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided by way of example, for the purpose of providing a more comprehensive understanding of technology. The disclosed method is not limited to the operation and logic flow presented herein. Selectable embodiments are expected, wherein the order of various operations is changed and the sub-operation of a part for which is described as a larger operation is performed independently.

[0166] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise specified to the contrary, one or more of the above-mentioned functions and / or features can be integrated into a single physical device and / or software module, or one or more functions and / or features can be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present invention. More specifically, in view of the properties, functions and internal relationships of the various functional modules in the device disclosed herein, the actual implementation of the module will be understood within the conventional skills of the engineer. Therefore, those skilled in the art can implement the present invention set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0167] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the above methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0168] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0169] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0170] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

[0171] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.

Claims

1. A method for detecting defects in wound lithium battery pole pieces, pole ears and glue, characterized in that: The following steps are involved: Collecting a detection image of the wound battery cell to be detected, and then performing adaptive threshold segmentation on the detection image to obtain a pole piece detection area and a pole ear detection area; Performing size measurement and light and dark spot detection on the tab detection area to obtain a tab defect detection result; Performing color extraction on the detection image to obtain a glue detection area, and then performing defect detection on the glue detection area to obtain a glue defect detection result; Performing region extraction on the pole piece detection region to obtain a pole piece near region and a pole piece far region, and then performing defect detection on the pole piece near region and the pole piece far region to obtain a pole piece defect detection result.

2. A defect detection method for wound lithium battery pole pieces, pole ears and glue according to claim 1, characterized in that: The adaptive threshold segmentation of the detection image to obtain the pole piece detection area and the pole ear detection area specifically includes: Calculating the background grayscale mean and background grayscale variance of the detection image; Performing preliminary segmentation on the detection image according to the background grayscale mean and the background grayscale variance to obtain a binary image; Performing a closing operation on the binary image, and then performing an opening operation on the binary image after the closing operation to obtain a first segmented area; Caliper pairs are placed in the first segmented area to obtain multiple width values, and an opening operation is performed on the first segmented area, and then the pole piece detection area and the pole lug detection area are obtained according to the opening operation result and each of the width values.

3. A defect detection method for wound lithium battery pole pieces, pole ears and glue according to claim 1, characterized in that: The tab defect detection result includes a first tab defect detection result, a second tab defect detection result, and a third tab defect detection result. The tab defect detection result is obtained by performing size measurement and light and dark spot detection on the tab detection area, and specifically includes: Performing interconnection operation on the tab detection area to obtain a plurality of tab segmentation areas; Performing feature calculation on each of the tab segmented regions, and then performing tab screening according to the feature calculation results and a preset screening parameter threshold, to obtain the first tab defect detection result; Measuring the size of the tab detection area according to the first tab defect detection result, and then obtaining the second tab defect detection result according to the size measurement result and a preset tab size threshold; The tab detection area is subjected to light and dark spot detection to obtain a light spot defect area and a dark spot defect area, and then the third tab defect detection result is obtained according to the light spot defect area, the dark spot defect area and a preset tab plaque area threshold.

4. A defect detection method for wound lithium battery pole pieces, pole ears and glue according to claim 1, characterized in that: The color extraction of the detection image to obtain the glue detection area specifically includes: Performing channel decomposition on the detection image to obtain a first channel image, a second channel image, and a third channel image; Performing adaptive threshold segmentation on the first channel image, the second channel image and the third channel image according to a preset grayscale range to obtain a corresponding plurality of segmented images; The glue detection area is obtained by performing intersection calculation on each of the glue segmentation images.

5. The defect detection method for wound lithium battery pole piece, pole ear and glue according to claim 1, characterized in that: The glue defect detection result includes a first glue defect detection result, a second glue defect detection result and a third glue defect detection result. The glue defect detection is performed on the glue detection area to obtain the glue defect detection result, which specifically includes: Performing an opening operation on the glue detection area to obtain the glue area area, and then obtaining the first glue defect detection result according to the glue area area and a preset glue area threshold; According to the first adhesive defect detection result, a straight line search is performed on the adhesive detection area to obtain an adhesive edge, a copper foil edge, a pole ear edge and a pole piece edge; Measure the size of the glue detection area to obtain the size measurement result, and calculate the relative position size from the glue edge to the copper foil edge, the pole ear edge and the pole piece edge; Obtaining the second glue defect detection result according to the size measurement result, the relative position size, a preset glue size threshold, and a preset glue relative position size threshold; The glue detection area is segmented by adaptive threshold to obtain a plurality of candidate defect areas, and then the features of each of the candidate defect areas are calculated, and the third glue defect detection result is obtained according to the features and preset feature defect specifications.

6. A method for detecting defects in wound lithium battery pole pieces, pole tabs and glue according to claim 1, characterized in that: The extracting the region of the pole piece detection area to obtain the near region of the pole piece and the far region of the pole piece specifically includes: Performing texture analysis on the pole piece detection area to obtain a pole piece slip area; Performing adaptive threshold segmentation on the pole piece detection area to obtain a fold interference area; Performing regional operations on the pole piece detection area, the pole piece slip area, and the crease interference area to obtain the pole piece near area and the pole piece far area.

7. A defect detection method for wound lithium battery pole pieces, pole ears and glue according to claim 1, characterized in that: The defect detection of the near area of ​​the pole piece and the far area of ​​the pole piece to obtain the pole piece defect detection result specifically includes: Dividing the near region of the pole piece into a first edge region and a first internal region, performing adaptive threshold segmentation and merging on the first edge region and the first internal region to obtain a near region defect candidate region; Dividing the far region of the pole piece into a second edge region and a second internal region, performing adaptive threshold segmentation and merging on the second edge region and the second internal region to obtain a far region defect candidate region; Merging the near-region defect candidate region with the far-region defect candidate region to obtain a pole piece defect candidate region; Calculating the regional features of the pole piece defect candidate region, and classifying the pole piece defect candidate region to obtain a category label; Defect screening is performed according to the regional features and the category labels to obtain the pole piece defect detection result.

8. A defect detection system for wound lithium battery pole pieces, pole ears and glue, characterized in that: include: An image acquisition module is used to acquire a detection image of the wound battery cell to be detected, and then perform adaptive threshold segmentation on the detection image to obtain a pole piece detection area and a pole ear detection area; A tab detection module is used to perform size measurement and light and dark spot detection on the tab detection area to obtain a tab defect detection result; A glue detection module, used to perform color extraction on the detection image to obtain a glue detection area, and then perform defect detection on the glue detection area to obtain a glue defect detection result; The pole piece detection module is used to extract the pole piece detection area to obtain the pole piece near area and the pole piece far area, and then perform defect detection on the pole piece far area and the pole piece near area to obtain the pole piece defect detection result.

9. An electronic device, characterized in that: The electronic device includes a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory. When the program is executed by the processor, the steps of the defect detection method for wound lithium battery pole sheets, pole ears and glue as described in any one of claims 1 to 7 are realized.

10. A storage medium, the storage medium being a computer-readable storage medium, used for computer-readable storage, characterized in that: The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the defect detection method for wound lithium battery pole sheets, pole ears and glue as described in any one of claims 1 to 7.

Images