A method and system for detecting defects of wound lithium battery pole piece, tab and adhesive

Abstract

The application discloses a kind of winding lithium battery pole piece, lug and the defect detection method and system of glue, method includes: the detection image of the winding battery cell to be detected is collected, and then the detection image is adaptively threshold segmented, and the pole piece detection area and lug detection area are obtained;Size measurement and light and dark spot detection are carried out on the lug detection area, and the lug defect detection result is obtained;Color extraction is carried out on the detection image, and the glue detection area is obtained, and then the glue detection area is defect detected, and the glue defect detection result is obtained;Region extraction is carried out on the pole piece detection area, and the pole piece near area and pole piece far area are obtained, and then the pole piece near area and pole piece far area are defect detected, and the pole piece defect detection result is obtained.The different defects of the pole piece, lug and glue can be accurately detected, the overkill rate is significantly reduced while not missing detection, the loss caused by scrapped overkill battery is reduced, and the application can be widely used in battery detection technical field.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of battery detection, and particularly relates to a defect detection method and system for a wound lithium battery pole piece, a pole lug and glue. BACKGROUND

[0002] The existing detection methods and devices for pole pieces, pole lugs and glue often only focus on a part for detection, such as focusing on a pole lug, focusing on a pole piece, and the like, and have poor adaptability to complex scenes. For example, it is difficult to optimize and improve the overkill caused by line scanning slip and pole piece creases, it is easy to miss the subtle defects caused by uneven brightness and darkness of pole piece imaging, it is difficult to avoid the overkill caused by the bright spot interference of the pole piece close to the copper foil, it is difficult for the algorithm to self-adapt to different colors of glue such as green glue and yellow glue, and it is easy to miss the slight defects of the edge of the pole piece. SUMMARY

[0003] To solve the above technical problems, the purpose of the present application is to provide a defect detection method and system for a wound lithium battery pole piece, a pole lug and glue with high defect detection precision.

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

[0005] An image of a wound battery cell to be detected is collected, and then adaptive threshold segmentation is performed on the image to obtain a pole piece detection region and a pole lug detection region;

[0006] The pole lug detection region is subjected to size measurement and bright-dark spot detection to obtain a pole lug defect detection result;

[0007] Color extraction is performed on the image to obtain a glue detection region, and then defect detection is performed on the glue detection region to obtain a glue defect detection result;

[0008] The pole piece detection region is subjected to region extraction to obtain a pole piece near region and a pole piece far region, and then defect detection is performed 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 image to obtain the pole piece detection region and the pole lug detection region specifically comprises:

[0010] The background gray mean and the background gray variance of the image are calculated;

[0011] The image is preliminarily segmented according to the background gray mean and the background gray 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 segmentation region;

[0013] performing a caliper pair drop on the first segmentation region to obtain a plurality of width values, and performing an opening operation on the first segmentation region, and then obtaining the pole piece detection region and the tab detection region according to an opening operation result and the plurality of 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, and the size measurement and bright-dark spot detection on the tab detection region to obtain a tab defect detection result specifically includes:

[0015] performing a connected operation on the tab detection region to obtain a plurality of tab segmentation regions;

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

[0017] performing size measurement on the tab detection region according to the first tab defect detection result, and then obtaining the second tab defect detection result according to a size measurement result and a preset tab size threshold;

[0018] performing bright-dark spot detection on the tab detection region to obtain a bright spot defect area and a dark spot defect area, and then obtaining the third tab defect detection result according to the bright spot defect area, the dark spot defect area, and a preset tab spot area threshold.

[0019] In some embodiments, the color extraction on the detection image to obtain a glue detection region 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 gray scale range to obtain a plurality of corresponding glue segmentation images;

[0022] performing intersection solving on each of the glue segmentation images to obtain the glue detection region.

[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, and the defect detection on the glue detection region to obtain a glue defect detection result specifically includes:

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

[0025] performing a straight line search on the glue detection region according to the first glue defect detection result to obtain a glue edge, a copper foil edge, a tab edge and a pole piece edge;

[0026] performing size measurement on the glue detection region to obtain a size measurement result, and calculating relative position sizes of the glue edge to the copper foil edge, the tab edge and the pole piece edge;

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

[0028] performing adaptive threshold segmentation on the glue detection region to obtain a plurality of candidate defect regions, and further calculating features of each of the candidate defect regions, and obtaining the third glue defect detection result according to the features and a preset feature defect specification.

[0029] In some embodiments, the 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 region to obtain a pole piece slip region;

[0031] performing adaptive threshold segmentation on the pole piece detection region to obtain a crease interference region;

[0032] performing region operation on the pole piece detection region, the pole piece slip region and the crease interference region to obtain the pole piece near region and the pole piece far region.

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

[0034] dividing the pole piece near region 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 and the far region defect candidate region to obtain a pole piece defect candidate region;

[0037] Calculate the region features of the pole piece defect candidate region, and classify the pole piece defect candidate region to obtain a category label;

[0038] According to the region features and the category label, defect screening is performed to obtain the pole piece defect detection result.

[0039] To achieve the above-mentioned purpose, another aspect of the embodiment of the present application proposes a defect detection system for winding lithium battery pole piece, tab and glue, comprising:

[0040] An image acquisition module is configured to acquire a detection image of a winding battery cell to be detected, and then perform adaptive threshold segmentation on the detection image to obtain a pole piece detection region and a tab detection region.

[0041] A tab detection module is configured to perform size measurement and light and dark spot detection on the tab detection region to obtain a tab defect detection result.

[0042] A glue detection module is configured to perform color extraction on the detection image to obtain a glue detection region, and then perform defect detection on the glue detection region to obtain a glue defect detection result.

[0043] A pole piece detection module is configured to perform region extraction on the pole piece detection region to obtain a pole piece near region and a pole piece far region, and then perform defect detection on the pole piece far region and the pole piece near region to obtain a pole piece defect detection result.

[0044] To achieve the above-mentioned purpose, another aspect of the embodiment of the present application proposes an electronic device, which comprises a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection communication between the processor and the memory. The program is executed by the processor to realize the defect detection method for winding lithium battery pole piece, tab and glue as described above.

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

[0046] The beneficial effects of the present invention are as follows: the defect detection method and system for wound lithium battery pole pieces, pole tabs 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 tab detection area, and then performs size measurement and light and dark spot detection on the pole tab detection area to obtain the pole tab 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 region extraction on the pole piece detection area to obtain the pole piece near area and the pole piece far area, and then performs defect detection on the pole piece near area and the pole piece far area to obtain the pole piece defect detection result. The present invention can accurately detect different defects of pole pieces, pole tabs 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 solutions 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 solutions of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative work.

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

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

[0050] Figure 3 A schematic diagram of the effect of segmenting the electrode area 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 the tab detection area and characteristic calculation results 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 flow chart of adhesive defect detection provided by an embodiment of the present invention;

[0055] Figure 8An image schematic diagram of the slip area of the pole piece provided by the embodiment of the present application;

[0056] Figure 9 Another image schematic diagram of the slip area of the pole piece provided by the embodiment of the present application;

[0057] Figure 10 An image schematic diagram of the crease interference area provided by the embodiment of the present application;

[0058] Figure 11 A schematic diagram of the near area and the far area of the pole piece provided by the embodiment of the present application;

[0059] Figure 12 A structural schematic diagram of a defect detection system for winding a lithium battery pole piece, a pole lug and glue provided by the embodiment of the present application;

[0060] Figure 13 A hardware structural schematic diagram of an electronic device provided by the embodiment of the present application. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical scheme and advantages of the present application clearer, the present application is further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementation described in the following exemplary embodiments does not represent all the implementations 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 appended claims.

[0062] It can be understood that the terms "first", "second" and the like used in the present application can be used herein to describe various concepts, but unless specifically stated, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of the present application, the first information can also be referred to as the second information, and similarly, the second information can also be referred to as the first information. Depending on the context, the word "if" as used herein can be interpreted as "when" or "when" or "in response to determining".

[0063] The terms "at least one", "multiple", "each", "any" and the like used in the present application include one, two or more than two, multiple includes two or more than two, 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 the pole piece, tab and glue, such as perforation, scratch, foil exposure, edge material falling and the like, cannot be accurately detected, the performance of the product will be seriously affected. Therefore, accurate detection of the pole piece, tab and glue during winding is an important link.

[0065] The existing detection methods and devices of the pole piece, tab and glue have the following main shortcomings:

[0066] 1. The existing methods and devices generally focus on tab detection or pole piece detection alone, and there are few complete detection devices and methods covering tabs, pole pieces and glue.

[0067] 2. When using a line scan camera scheme for imaging, there are inevitably situations such as slipping during device operation, resulting in abnormal local imaging. The existing methods often detect normal areas with slipping as defects, resulting in overkill of some parts;

[0068] 3. In the production process, the pole piece occasionally has a non-serious crease, but the imaging is clear, which is a normal condition. The existing methods often detect this type of acceptable crease as a defect, resulting in overkill of some parts;

[0069] 4. The pole piece area close to the copper foil often has a slight wrinkle, resulting in a local image that is obviously brighter or has a slight bright spot, which is very similar to the defects on the pole piece far away. The existing methods often detect this type of acceptable bright spot as a defect, resulting in overkill of some parts;

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

[0071] 6. The glue has different colors, and the imaging of the glue at different positions in the field of view is quite different. The existing methods are difficult to accurately detect and are prone to missed detection;

[0072] 7. For AI algorithms, a large number of samples are needed for training, and it is difficult to adapt to contour-type defects. Moreover, new defects may occur in the field, and AI algorithms are difficult to quickly respond to the detection needs of new defects of customers.

[0073] To this end, the embodiment of the present application provides a defect detection method for winding lithium battery pole pieces, tabs and glue. First, a detection image of a winding battery cell to be detected is collected, adaptive threshold segmentation is performed on the detection image to obtain a pole piece detection area and a tab detection area, then size measurement and light and dark spot detection are performed on the tab detection area to obtain a tab defect detection result, then color extraction is performed on the detection image to obtain a glue detection area, then defect detection is performed on the glue detection area to obtain a glue defect detection result, finally, region extraction is performed on the pole piece detection area to obtain a pole piece near region and a pole piece far region, then defect detection is performed on the pole piece near region and the pole piece far region to obtain a pole piece defect detection result. The present application can accurately detect different defects of the pole piece, the tab and the glue, can better detect fine defects, can significantly reduce the overkill rate while not missing detection, can improve the equipment yield, and can reduce the loss caused by scrapped overkill battery cells.

[0074] Reference Figure 1 , Figure 1 A step flow chart of a defect detection method for winding lithium battery pole pieces, tabs and glue provided by the embodiment of the present application is provided. The embodiment of the present application provides a defect detection method for winding lithium battery pole pieces, tabs and glue. The method comprises steps S101 to S104.

[0075] S101, a detection image of a winding battery cell to be detected is collected, and then adaptive threshold segmentation is performed on the detection image to obtain a pole piece detection area and a tab detection area;

[0076] In some optional embodiments, the detection of the pole piece, the tab and the glue comprises four detection stations, which are a positive electrode upper station, a positive electrode lower station, a negative electrode upper station and a negative electrode lower station. The positive electrode upper station and the positive electrode lower station detect defects related to the front and back of the positive electrode respectively, and the negative electrode upper station and the negative electrode lower station detect defects related to the front and back of the negative electrode respectively. The defect types to be detected include dark spots, bright spots, pole piece residual glue, connecting belts (red, white, yellow, etc.), foreign matters, scratches, edge material falling, foil exposure, missing tabs, missing glue (green, yellow, etc.), unqualified tab size, unqualified glue size, unqualified glue position, perforation and damage, etc.

[0077] The embodiment of the present application is based on a visual hardware system to collect the detection image of the winding battery cell, and the visual hardware system comprises a camera, a lens, a light source, a light source controller, an industrial computer, a background plate, a PLC and related cables, etc. The hardware scheme of the four detection stations is unified, only the target in the imaging and field of view is different, and the detection method can be compatible through parameter configuration. First, the positive plate / tab / adhesive reaches the positive upper detection station, triggers the camera to take a picture to obtain the detection image of the current station. Then, the positive plate / tab / adhesive reaches the positive lower detection station, triggers the camera to take a picture to obtain the detection image of the current station. Then, it is judged whether the detection image is a color image, if not, the detection result is unqualified, and the winding battery cell is rejected; if yes, the next step of the defect detection process is performed.

[0078] Further, the line scanning imaging or area array imaging method can be used to collect the detection image of the winding battery cell. For large size winding products, the line scanning imaging method is used, and for smaller size products, the area array imaging method is selected. The advantages of the line scanning imaging method are uniform imaging, high precision, large picture resolution, and it is also suitable for imaging scenes of winding materials or long strip products; the disadvantage is that the imaging is sensitive to the relative position and angle of the camera and the light source, and it is very sensitive to jitter, slip and reverse playback. The advantages of the area array imaging method are that it is not sensitive to the relative position of the camera and the light source, and it is not sensitive to jitter, slip and reverse playback, and more lighting schemes can be selected, and the price is cheaper; the disadvantage is that the precision is lower than that of the line scanning scheme, and the imaging is not uniform.

[0079] Further, as an optional implementation, the detection image is subjected to adaptive threshold segmentation to obtain the positive plate detection region and the tab detection region, which can be specifically divided into the following steps S1011 to S1014:

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

[0081] Specifically, first, the color detection image is converted into a gray image, then the background gray mean value and variance are extracted in the left local region of the gray image, and the calculation of the background mean value and variance in the left region is as shown in Figure 2 The background mean value and variance are automatically calculated for each image as the basis for adaptive parameters of the subsequent algorithm.

[0082] S1012, preliminarily segmenting the detection image according to the background gray mean value and the background gray variance to obtain a binary image;

[0083] Exemplarily, the detection image can be preliminarily segmented according to the [bg_value+10, 255] gray scale range, wherein bg_value is the background gray mean value of the detection image, and the binary image of the positive plate and tab region is segmented.

[0084] S1013, perform a close operation on the binary image, and then perform an open operation on the binary image after the close operation to obtain a first segmentation region;

[0085] Exemplarily, a close operation is performed on the binary image using a rectangular structure element with a width x height of 10 x 10, and then an open operation is performed using a rectangular structure element with a width x height of 100 x 2, and then the segmentation region of the pole piece and the lug (i.e., the first segmentation region) is obtained. The open-close operation can well connect the weak edge region and remove the interference region on the background. The effect diagram of the segmentation region of the pole piece is shown in FIG. 8, and the effect diagram of the segmentation region of the lug is shown in FIG. 9. Figure 3 Figure 4

[0086] S1014, perform a caliper pair projection on the first segmentation region to obtain a plurality of width values, and perform an open operation on the first segmentation region, and then obtain a pole piece detection region and a lug detection region according to the open operation result and the width values.

[0087] In some optional embodiments, N caliper pairs are projected along the image height direction, N is generally set to 30, N width values are obtained on the segmentation region of the pole piece and the lug (i.e., the first segmentation region), and then the width values are sorted from small to large, and the width value with a 0.2*N serial number is taken as the width of the pole piece polar_w, so as to avoid the interference of the belt on the accurate extraction of the lug width. Then, the open operation is performed on the segmentation region of the pole piece and the lug (i.e., the first segmentation region), and the rectangular structure element of the open operation can be set to width x height=(polar_w*1.25) x 1, and then the binary image is eroded using the rectangular structure element, and then the binary image after the erosion is expanded using the same rectangular structure element, to obtain a pole piece detection region and a lug detection region.

[0088] It should be noted that the rectangular structure element selected in the above open operation and close operation process can be set according to actual needs, which is not limited herein.

[0089] S102, perform size measurement and light and dark spot detection on the lug detection region to obtain a lug defect detection result;

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

[0091] S1021, perform a connected operation on the lug detection region to obtain a plurality of lug segmentation regions;

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

[0093] Specifically, a connected operation is performed on the tab detection region after the opening operation, to obtain a plurality of separated tab segmentation regions, and the width, height, width-height ratio and rectangularity of all tab segmentation regions are calculated. Figure 5 As shown in the figure, the tab detection region and the feature calculation result of the tab detection region are shown. Because the tab may have deformation problems, but the width, height, width-height ratio and rectangularity can be comprehensively judged and screened out according to the feature calculation result. If the tab screening is successful, the next step of tab defect detection is entered; if the tab screening fails, it is a tab defect.

[0094] It should be noted that the sizes of tabs of different batteries are different, and the specific screening parameter threshold can be adjusted according to the on-site use. For example, the screening parameter threshold can be set as: width > 400 pixels, height > 50 pixels, width-height ratio > 5, rectangularity > 0.85, and area > 25000 pixels 2 .

[0095] S1023, according to the first tab defect detection result, the size of the tab detection region is measured, and then according to the size measurement result and the preset tab size threshold, the second tab defect detection result is obtained.

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

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

[0098] S1024, bright and dark spot detection is performed on the tab detection region, to obtain the bright spot defect area and the dark spot defect area, and then according to the bright spot defect area, the dark spot defect area and the preset tab spot area threshold, the third tab defect detection result is obtained.

[0099] Specifically, in the tab detection area, the obvious bright spot or dark spot defect on the tab is extracted, compared with a preset tab spot area threshold, and then it is judged whether the tab has a defect. It should be noted that the tab spot area threshold can be set according to the customer SOP specification and the on-site detection condition. Exemplarily, the tab spot area threshold can be set as: tab bright spot defect area > 100 pixels 2 , or dark spot defect area > 300 pixels, which is a tab defect unqualified.

[0100] In summary, as Figure 6 shows a flowchart example of tab defect detection. As long as there is a defect tab or the tab size is unqualified or the tab defect is unqualified, the wound battery is determined to be unqualified, and the wound battery is rejected.

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

[0102] Specifically, the glue is generally green and yellow, and its defects mainly include inaccurate position, missing, scratches, and damage.

[0103] Further as an optional implementation, the step of 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, the detection image is channel-decomposed to obtain a first channel image, a second channel image, and a third channel image;

[0105] S1032, the first channel image, the second channel image, and the third channel image are adaptively threshold segmented according to a preset gray scale range to obtain a plurality of corresponding glue segmentation images;

[0106] S1033, the intersection of each glue segmentation image is solved to obtain the glue detection area.

[0107] Specifically, the collected color detection image is decomposed into R, G, and B three channel images (i.e. the first channel image, the second channel image, and the third channel image), the R, G, and B three channel images are threshold segmented according to the gray scale range of the glue imaging on different channels, and then the intersection of the segmentation regions of the three channels is solved to obtain the color-extracted glue detection area.

[0108] Further 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 OR operation on the glue detection region to obtain a glue region area, and then obtaining a first glue defect detection result according to the glue region area and a preset glue area threshold value;

[0110] Specifically, the OR operation is performed on the glue detection region to obtain the glue region area, and if the glue region area is greater than the preset glue area threshold value, there is glue, otherwise there is no glue. The glue area threshold value can be set according to actual needs, which is not limited here.

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

[0112] S1036, performing size measurement on the glue detection region to obtain a size measurement result, and calculating a relative position size of the glue edge to the copper foil edge, the tab 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, a preset glue size threshold value and a preset glue relative position size threshold value;

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

[0115] S1038, performing adaptive threshold segmentation on the glue detection region to obtain a plurality of candidate defect regions, and then calculating the features of each candidate defect region, and obtaining a third glue defect detection result according to the features and a preset feature defect specification.

[0116] Specifically, in the glue detection region, the candidate defects on the surface of the glue are extracted by the automatic threshold segmentation algorithm, a plurality of features (such as defect area, defect gray scale, etc.) of each candidate defect are calculated, and then the defect category is judged. According to whether the set feature defect specification exists glue defect, the third glue defect detection result is obtained. Exemplarily, the feature defect specification can be: the glue defect area > 200 pixels 2 , and the glue defect gray scale > 60, then there is glue defect.

[0117] In summary, as Figure 7The flowchart shown is an example of glue defect detection. If there is glue defect or the glue size is unqualified or the glue position size is unqualified, the wound battery is determined to be unqualified, and the wound battery is rejected.

[0118] S104, region extraction is performed on the tab detection region to obtain a tab near region and a tab far region, and then defect detection is performed on the tab near region and the tab far region to obtain a tab defect detection result.

[0119] Specifically, there are many defects on the tab and the defects have complex shapes. The defects on the tab include dark spots, bright spots, tab residual glue, connecting belts (red, white, yellow, etc.), foreign matter, scratches, edge material loss, foil exposure, perforation, damage, etc.

[0120] Further as an optional implementation, the step of region extraction on the tab detection region to obtain a tab near region and a tab far region can be specifically divided into the following steps S1041-S1043:

[0121] S1041, texture analysis is performed on the tab detection region to obtain a tab slip region;

[0122] Specifically, before extracting the tab slip region, a machine connecting belt region of a preset color is extracted in a colored detection image through color extraction, a manual connecting belt region is extracted using morphology based on the tab lug region and the tab width, and the manual connecting belt region and the machine connecting belt region are merged to obtain a connecting belt region. For example, Figure 8 and Figure 9 As shown in the image schematic diagram of the tab slip region, the normal region of the tab is uniformly imaged, and the tab slip region has slight and dense vertical textures. The tab slip region on the tab is extracted by a texture analysis algorithm in the embodiments of the present application.

[0123] In some optional embodiments, the texture on the tab is first extracted by a canny algorithm. Then, the texture is broken according to the combination of straight lines and circular rings to obtain linear textures and circular arc textures. Next, the linear textures are obtained by screening according to the height, width and direction of the textures. Then, the texture conversion region is subjected to a closed operation of a rectangular structure element with a width of 100 and a height of 60, and then area screening is performed to retain the area > 7000 pixels 2 Then, the axis-parallel circumscribed rectangle of the region is obtained, that is, the tab slip region is obtained.

[0124] S1042, adaptive threshold segmentation is performed on the tab detection region to obtain a crease interference region;

[0125] In some optional embodiments, as shown in Figure 10The following diagram shows an image of the crease interference region. Compared to the pole piece slip region, the crease interference region of the pole piece 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) for segmentation are calculated using 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 whose width × height = 15 × 1. Then, the region is opened using a rectangular structure element whose 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. Perform 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. As Figure 11 The figure shows a schematic diagram of the near and far regions of the pole piece. According to the position of the pole tab and the overall area of ​​the pole piece, the near and far regions 1 and 2 close to the pole tab and the far and far regions 1 and 2 far from the pole tab are generated. Finally, the near and far regions of the pole piece are subtracted from the pole piece slip area and the crease interference area to form the new near and far regions 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] Further as an optional implementation, the step of performing defect detection on the pole piece near region and the pole piece far region to obtain a pole piece defect detection result can be specifically divided into the following steps S1044 to S1048:

[0134] S1044, dividing the pole piece near region 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;

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

[0136] S1045, 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;

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

[0138] Wherein, the edge defect is generally a bright spot formed by dropping material, which is relatively obvious. For the extraction of the second edge defect candidate region, first, the mean gray value mean of the pole piece is obtained. Then, threshold segmentation is performed, and a loose low threshold value = mean + 40 is set. The region obtained by segmentation is the second edge defect candidate region. For the second internal defect candidate region, the following three methods are used for defect extraction, and finally the regions obtained by methods 1, 2 and 3 are merged to obtain the second internal defect candidate region:

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

[0140] Method 2: Extract the region by dynamic threshold. First, mean filtering is performed on the image, and the filter kernel size is selected as 9x9. Then, the defect bright region and the defect dark region are obtained according to the mean filtered image and the original image.

[0141] Method 3: Extract the defect region by texture analysis. First, the texture region on the pole piece is extracted using the canny algorithm. Then, the small textures are filtered out by screening the length of the texture. Then, the texture edge is converted into a closed region. Next, the closed operation is performed on the region with a rectangular structure element widthxheight = 8*8. Finally, the regions with an area greater than 500 pixels are screened out as the defect region.

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

[0143] S1047, calculate the region features of the pole piece defect candidate region, and classify the pole piece defect candidate region to obtain a category label;

[0144] S1048, perform defect screening according to the region features and the category label to obtain a pole piece defect detection result.

[0145] Specifically, the gray scale features and the region features of the pole piece defect candidate region are calculated, such as defect gray mean and variance, background gray, defect contrast, defect area, defect circumscribed rectangle length and aspect ratio, etc. Then, the pole piece defect candidate region is classified using a binary tree method according to the calculated region features to obtain a category label, wherein the category label includes dark spot / dark mark, bright spot, pole piece residual glue (connecting band) / foreign matter, scratch / edge dropping material / missing foil, and missing pole lug, etc. Finally, according to the category label and the defect features of the pole piece defect candidate region, the combined post-processing logic is used to screen out the defects that are killed, and finally the real defects are obtained. If any one of the defects exists, it is determined that the wound battery is unqualified, and the wound battery is rejected.

[0146] Wherein, if the defect gray value is 15 or more less than the background gray value, it is a dark spot / dark mark; if the defect gray value is 15 or more brighter than the background gray value, it is a bright spot; the pole piece residual glue (connecting band) / foreign matter is obtained by color extraction; the bright spot detected in the edge region of the pole piece is the edge dropping material; the long and narrow defect on the pole piece is the scratch; the large area bright defect with uniform gray value on the pole piece is the missing foil; the absence of the pole lug in the image is the missing pole lug.

[0147] The defect detection method for the wound lithium battery pole piece, tab and glue is described above. It can be recognized that, compared with the wound cell defect detection method in the prior art, the embodiment of the present application can accurately detect different defects of the pole piece, tab and glue, and can well solve the difficulties such as line scan picture slip interference, pole piece crease interference, different types of glue detection difficulty, bright spot interference caused by copper foil near the tab and local deformation of the pole piece. The fine defects can be better detected, the detection requirements of the customer can be better met, the overkill rate is significantly reduced without missing detection, the equipment yield is improved, and the loss caused by scrapped overkill cells is reduced.

[0148] Referring Figure 12 The embodiment of the present application also provides a defect detection system for wound lithium battery pole pieces, tabs and glue, comprising:

[0149] An image acquisition module is configured to acquire a detection image of a wound cell to be detected, and then perform adaptive threshold segmentation on the detection image to obtain a pole piece detection region and a tab detection region.

[0150] A tab detection module is configured to perform size measurement and bright-dark spot detection on the tab detection region to obtain a tab defect detection result.

[0151] A glue detection module is configured to perform color extraction on the detection image to obtain a glue detection region, and then perform defect detection on the glue detection region to obtain a glue defect detection result.

[0152] A pole piece detection module is configured to perform region extraction on the pole piece detection region to obtain a pole piece near region and a pole piece far region, and then perform defect detection on the pole piece far region and the pole piece near region to obtain a pole piece defect detection result.

[0153] The contents in the defect detection method for the wound lithium battery pole piece, tab and glue embodiment are applicable to the defect detection system for the wound lithium battery pole piece, tab and glue embodiment. The function realized by the defect detection system for the wound lithium battery pole piece, tab and glue embodiment is the same as that of the defect detection method for the wound lithium battery pole piece, tab and glue embodiment, and the beneficial effects achieved by the defect detection system for the wound lithium battery pole piece, tab and glue embodiment are also the same as those achieved by the defect detection method for the wound lithium battery pole piece, tab and glue embodiment.

[0154] The embodiment of the present application also provides an electronic device, which comprises a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection communication between the processor and the memory. The program is executed by the processor to realize the defect detection method for the wound lithium battery pole piece, tab and glue. The electronic device can be any smart terminal, such as a tablet computer or a vehicle-mounted computer.

[0155] AsFigure 13 Fig. 1 shows a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present application. Figure 13 The electronic device provided by the embodiment of the present application comprises:

[0156] The processor 1001 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits, and is configured to execute related programs to implement the technical solutions provided by the embodiment of the present application.

[0157] The memory 1002 can be implemented by a ROM (Read Only Memory), a static storage device, a dynamic storage device, or a RAM (Random Access Memory), and the like. The memory 1002 can store an operating system and other application programs. When the technical solutions provided by the embodiments of the present application are implemented by software or firmware, the related program codes are stored in the memory 1002 and are called and executed by the processor 1001 to implement the defect detection method for the wound lithium battery pole piece, tab and adhesive.

[0158] The input / output interface 1003 is configured to realize information input and output.

[0159] The communication interface 1004 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.).

[0160] The bus 1005 is configured to transmit information between the components (for example, the processor 1001, the memory 1002, the input / output interface 1003 and the communication interface 1004) of the device.

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

[0162] The embodiment of the present application further provides a storage medium. The storage medium is a computer readable storage medium, and is configured to store computer readable information. 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 the wound lithium battery pole piece, tab and adhesive.

[0163] Memory, as used in the specification, includes both volatile and nonvolatile memory, and can include but is not limited to removable memory and non-removable memory such as RAM, ROM, EEPROM, flash memory or other memory technology. Memory can also include remote storage devices that are not physically located on the processor, such as a remote memory device that is in communication with the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0164] The embodiments of the present application further disclose a computer program product or computer program, which comprises computer instructions 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 to enable the computer device to perform the method shown in the embodiments of the present application. Figure 1 The embodiments of the present application further disclose a computer program product or computer program, which comprises computer instructions 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 to enable the computer device to perform the method shown in the embodiments of the present application.

[0165] In some alternative embodiments, the functions / operations mentioned in the block diagrams can not occur in the order mentioned in the operation diagrams. For example, depending on the functions / operations involved, two blocks shown in succession can actually be executed substantially concurrently or the blocks can sometimes be executed in reverse order. Additionally, the embodiments presented and described in the flow diagrams of the present application are only examples. Alternative embodiments are possible where the order of various operations is changed and where sub-operations described as part of a larger operation are executed independently.

[0166] Furthermore, although the present application is described in the context of functional modules, it is to be understood that one or more of the functions and / or features described above can be integrated in a single physical device and / or software module, or one or more functions and / or features can be implemented in separate physical devices or software modules. It is also to be understood that detailed discussion of the actual implementation of each module is unnecessary to an understanding of the present application. Rather, the actual implementation is within the routine of an engineer in the art, given the property, function and internal relationships of the various functional modules disclosed herein. Accordingly, the present application is not limited to the specific embodiments illustrated herein, but is capable of being practiced with other like devices and methods within the scope of the present application as set forth in the claims below. It is also to be understood that the specific concepts disclosed are illustrative in nature only and are not intended to limit the scope of the present application, which is to be determined by the full scope of the claims and equivalents thereof.

[0167] If the above functions are realized in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the parts of the prior art that contribute to the present application or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described above in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

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

[0169] It should be understood that parts of the present application can be realized in hardware, software, firmware or a combination thereof. In the above-described embodiments, a plurality of steps or methods can be realized by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if realized in hardware, and as in another embodiment, it can be realized by any one or a combination of the following technologies known in the art: discrete logic circuit with logic gates for implementing logic functions on data signals, application specific integrated circuit with suitable combination logic gates, programmable gate array (PGA), field programmable gate array (FPGA), etc.

[0170] Although the embodiments of the present application have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, replacements and variations can be made to the embodiments without departing from the principles and spirit of the present application, and the scope of the present application is defined by the claims and their equivalents.

[0171] The above is a specific description of the preferred embodiment of the present application, but the present application is not limited to the embodiment, and those skilled in the art can make various equivalent modifications or replacements without departing from the spirit of the present application, and these equivalent modifications or replacements are all included in the scope defined by the claims of the present application.

Claims

1. A method for detecting defects in wound lithium battery pole pieces, pole tabs and glue, characterized in that: The following steps are involved: Collecting a detection image of the wound battery cell to be inspected, and then performing adaptive threshold segmentation on the detection image to obtain a pole piece detection area and a tab 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 area 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; The adaptive threshold segmentation of the detection image to obtain the electrode detection area and the tab 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 region; Performing caliper placement on the first segmented area to obtain a plurality of width values, and performing an opening operation on the first segmented area, and then obtaining the electrode piece detection area and the tab detection area according to the opening operation result and each of the width values; 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 plurality of corresponding segmented images; performing intersection calculation on each of the glue segmentation images to obtain the glue detection area; The first channel image, the second channel image and the third channel image are R, G and B channel images.

2. The method for detecting defects in wound lithium battery pole pieces, pole tabs and adhesive according to claim 1, characterized in that: The tab defect detection results include a first tab defect detection result, a second tab defect detection result, and a third tab defect detection result. The tab defect detection results are obtained by performing size measurement and light and dark spot detection on the tab detection area, specifically including: Performing a connection 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 based on the feature calculation results and a preset screening parameter threshold to obtain the first tab defect detection result; performing a size measurement on 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; 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 the third tab defect detection result based on the light spot defect area, the dark spot defect area and the preset tab plaque area threshold.

3. The defect detection method for wound lithium battery pole pieces, pole tabs and glue according to claim 1, characterized in that: The adhesive defect detection result includes a first adhesive defect detection result, a second adhesive defect detection result, and a third adhesive defect detection result. The adhesive defect detection result obtained by performing defect detection on the adhesive detection area specifically includes: performing an opening operation on the glue detection area to obtain an area of ​​the glue area, and then obtaining the first glue defect detection result based on the area of ​​the glue area and a preset glue area threshold; 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; Measure the size of the glue detection area to obtain a size measurement result, and calculate the relative position size of the glue edge to the copper foil edge, the pole ear edge and the pole piece edge; Obtaining a 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; Adaptive threshold segmentation is performed on the glue detection area to obtain multiple candidate defect areas, and then the characteristics of each candidate defect area are calculated. According to the characteristics and preset characteristic defect specifications, the third glue defect detection result is obtained.

4. The method for detecting defects in wound lithium battery pole pieces, pole tabs, and adhesive according to claim 1, wherein: The region extraction of the pole piece detection area to obtain the pole piece near region and the pole piece far region 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 crease 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.

5. The method for detecting defects in wound lithium battery pole pieces, pole tabs and adhesive according to claim 1, characterized in that: The defect detection of 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: 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 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; Merging the near-region defect candidate region and the far-region defect candidate region to obtain a pole piece defect candidate region; Calculating the regional features of the pole piece defect candidate area, and classifying the pole piece defect candidate area to obtain a category label; Defect screening is performed according to the regional features and the category labels to obtain the electrode defect detection result.

6. A defect detection system for wound lithium battery pole pieces, pole tabs and glue, characterized in that: include: An image acquisition module is used to acquire a detection image of the wound battery cell to be inspected, and then perform adaptive threshold segmentation on the detection image to obtain a pole piece detection area and a tab 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 tab defect detection results; a glue detection module, configured 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; A pole piece detection module is used to extract the pole piece detection area to obtain a pole piece near area and a pole piece far area, and then perform defect detection on the pole piece far area and the pole piece near area to obtain a pole piece defect detection result; The adaptive threshold segmentation of the detection image to obtain the electrode detection area and the tab 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 region; Performing caliper placement on the first segmented area to obtain a plurality of width values, and performing an opening operation on the first segmented area, and then obtaining the electrode piece detection area and the tab detection area according to the opening operation result and each of the width values; 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 plurality of corresponding segmented images; performing intersection calculation on each of the glue segmentation images to obtain the glue detection area; The first channel image, the second channel image and the third channel image are R, G and B channel images.

7. 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 5 are realized.

8. A storage medium, which is a computer-readable storage medium and is 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 5.

Images