Method, device and computer equipment for detecting defects in insulating coating of battery electrode sheet

Abstract

A battery pole piece insulating coating defect detection method, device, computer equipment, computer readable storage medium, computer program product and battery pole piece defect detection system, the method comprises: obtaining the pole piece image obtained by shooting the pole piece, the pole piece image at least includes a complete pole piece;Determine the insulating coating area and the lug area in the pole piece image;According to the insulating coating area and the lug area, determine the defect detection area of the insulating coating area in the pole piece image;Defect detection is carried out on the defect detection area to obtain the defect detection result. The method realizes the detection of the insulating coating of the pole piece before compounding, can detect whether the insulating coating area has defects, so as to timely reject the pole piece with defects, has high detection accuracy, and improves the operation efficiency of the lamination equipment.

Description

Technical Field

[0001] This invention relates to the field of battery maintenance technology, and in particular to a method, apparatus, computer equipment, computer-readable storage medium, computer program product, and battery electrode defect detection system for detecting defects in the insulating coating of battery electrodes. Background Technology

[0002] With continuous technological advancements, lithium-ion batteries have been applied in electric vehicles, becoming one of their primary power sources. The rapid development of the new energy vehicle industry has placed high demands on the safety, environmental friendliness, and high-current charge / discharge performance of lithium-ion batteries. In large-scale production, the coating process in lithium-ion battery manufacturing is particularly crucial for improving battery performance.

[0003] Traditional battery electrode defect detection uses two sets of image sensors (one for each side) to acquire images, measuring the distance from the active material coating to the electrode edge. The misalignment is then calculated and integrated into a closed-loop control system to adjust the coating area until the misalignment is less than the specified value. However, this traditional battery electrode defect detection method suffers from low accuracy. Summary of the Invention

[0004] According to various embodiments of this application, a method, apparatus, computer device, computer-readable storage medium, computer program product, and battery electrode defect detection system are provided for detecting defects in the insulating coating of battery electrodes.

[0005] In a first aspect, this application provides a method for detecting defects in the insulating coating of battery electrodes, comprising:

[0006] Acquire an image of the electrode obtained by photographing the electrode; the image must include at least one complete electrode.

[0007] Identify the insulating coating area and the tab area in the electrode image;

[0008] Based on the insulating coating area and the tab area, determine the defect detection area of ​​the insulating coating area in the electrode image;

[0009] Defect detection is performed on the defect detection area to obtain the defect detection results.

[0010] The aforementioned method for detecting defects in the insulating coating of battery electrodes involves capturing an image of the electrode containing at least one complete electrode, identifying the insulating coating region and the tab region within the image, and then determining the defect detection area within the insulating coating region based on these regions. Finally, defect detection is performed on the defect detection area to obtain the defect detection result. This method enables the detection of the insulating coating of pre-composite electrodes, identifying the presence of defects in the insulating coating region, allowing for the timely rejection of defective electrodes. It offers high detection accuracy and improves the operating efficiency of the stacking equipment.

[0011] In one embodiment, determining the insulating coating region and the tab region in the electrode image includes: performing full-image edge finding on the electrode image to obtain initially located electrode edges; relocating based on the initially located electrode edges to determine the insulating coating region in the electrode image; and searching through the insulating coating region to determine the tab region in the electrode image. By performing full-image edge finding and relocation on the electrode image to find the insulating coating region, and then finding the tab region in the electrode image based on the determined insulating coating region, different regions in the electrode image can be found step by step, achieving accurate and reliable detection.

[0012] In one embodiment, performing a full-image edge search on the electrode image to obtain the initially located electrode edge includes: performing a full-image edge search on the electrode image from the side away from the electrode tab towards the side closer to the electrode tab to obtain the initially located electrode edge. By performing a full-image edge search on the electrode image from the side away from the electrode tab towards the side closer to the electrode tab, the initially located electrode edge can be accurately found.

[0013] In one embodiment, edge finding is performed on the entire image of the electrode from the side furthest from the tab towards the tab to obtain the initially located electrode edge. This includes: performing edge finding on the entire image of the electrode from the side furthest from the tab towards the tab; if a predetermined abrupt change edge is found, the edge finding is considered successful, and the found predetermined abrupt change edge is determined as the initially located electrode edge. During the entire image edge finding process, the analysis of whether a predetermined abrupt change edge can be found, and the subsequent use of this edge as the initially located electrode edge, further improves the accuracy of edge finding.

[0014] In one embodiment, repositioning is performed based on the initially located electrode edge to determine the insulating coating region in the electrode image. This includes: determining the target insulating coating region based on the initially located electrode edge, and extracting the insulating coating region from the determined electrode image within the target insulating coating region. After determining the target insulating coating region based on the initially located electrode edge, the insulating coating region in the electrode image is then extracted based on the target insulating coating region, facilitating rapid location of the insulating coating region.

[0015] In one embodiment, the electrode tab region in the electrode image is determined by searching through the insulating coating area, including: performing region relocation based on the insulating coating area to determine the target electrode tab detection area; and searching for and extracting the electrode tab region within the target electrode tab detection area. Combining region relocation with the insulating coating area to determine the target electrode tab detection area, and then searching for the electrode tab region based on the target electrode tab detection area, also allows for convenient and rapid locating of the electrode tab region.

[0016] In one embodiment, the target tab detection area is determined by repositioning the region based on the insulating coating area, including: extracting the initial positioning insulation edge of the insulating coating area; and determining the target tab detection area based on the initial positioning insulation edge. By extracting the initial positioning insulation edge of the insulating coating area and selecting the target tab detection area based on the initial positioning insulation edge, the target tab detection area can be determined quickly and accurately.

[0017] In one embodiment, searching for and extracting a tab region within the target tab detection region includes: extracting regions within the target tab detection region that conform to the grayscale characteristics of a tab, obtaining a preliminary tab region; determining whether the preliminary tab region is a tab based on its shape and size, and if so, confirming that the tab region has been obtained. Preliminary screening of the target tab detection region based on the grayscale characteristics of the tab to determine the preliminary tab region, and then analyzing whether the tab region has been found based on its shape and size, ensures the accuracy of the tab region search.

[0018] In one embodiment, determining the defect detection area of ​​the insulating coating area in the electrode image based on the insulating coating area and the tab area includes: finding the edge of the tab area to obtain the tab edge; obtaining the electrode edge based on the tab edge and preset distance data, where the preset distance data is the distance between the tab edge and the electrode edge; and determining the defect detection area of ​​the insulating coating area in the electrode image based on the initially located electrode edge, the initially located insulating edge, and the electrode edge. After locating the tab area, the electrode edge is determined by combining the tab edge and the preset distance data. Then, based on the initially located electrode edge, the initially located insulating edge, and the electrode edge, the defect detection area in the insulating coating area can be accurately located for subsequent defect detection.

[0019] In one embodiment, defect detection is performed on a defect detection region to obtain a defect detection result, including: extracting connected components in the defect detection region; if a connected component similar to a predetermined defect region exists, a defect is determined to exist; the defect detection result includes information about the existence of a defect. By comparing the extracted connected components in the defect detection region with the predetermined defect region, the presence of a defect in the defect detection region is analyzed, resulting in accurate and efficient detection.

[0020] In one embodiment, defect detection is performed on the defect detection area to obtain a defect detection result. The method further includes: if no connected region similar to the predetermined defect area exists, calculating the coating area misalignment of the electrode sheet; the defect detection result includes information about the absence of defects and the coating area misalignment. When no defects are found in the defect detection area of ​​the insulating coating region, the coating area misalignment of the electrode sheet is also calculated to analyze whether the width of the insulating coating area on both sides of the electrode sheet is consistent, so as to reject electrodes with dimensional abnormalities, further improving the accuracy of defect detection for battery electrodes.

[0021] In one embodiment, the electrode image includes a first electrode image and a second electrode image obtained by capturing images of both sides of the electrode. If no connected region similar to the predetermined defect area exists, the coating area misalignment of the electrode is calculated, including: if no connected region similar to the predetermined defect area exists in the defect detection areas corresponding to the first and second electrode images, the coating area misalignment of the electrode is calculated. By combining the electrode images obtained by capturing images of both sides of the electrode, the presence of defects in the corresponding defect detection areas is detected separately. When it is determined that no defects exist in the defect detection areas of both electrode images, the coating area misalignment of the electrode is calculated, thereby improving the accuracy of defect detection in the insulating coating area of ​​the electrode.

[0022] In one embodiment, the electrode image includes a first electrode image and a second electrode image obtained by capturing images of both sides of the electrode. Calculating the coating area misalignment of the electrode includes: finding the edges of the defect detection area of ​​the insulating coating region in the first electrode image to obtain a first electrode virtual edge and a first insulating edge; finding the edges of the defect detection area of ​​the insulating coating region in the second electrode image to obtain a second electrode virtual edge and a second insulating edge; calculating the width of the first insulating coating region based on the first electrode virtual edge and the first insulating edge, and calculating the width of the second insulating coating region based on the second electrode virtual edge and the second insulating edge; and calculating the coating area misalignment of the electrode based on the widths of the first and second insulating coating regions. By combining the edge finding of the defect detection areas of the insulating coating regions in the two electrode images to find the corresponding electrode virtual edge and insulating edge, and then calculating the width of the insulating coating region in the two electrode images based on the electrode virtual edge and the insulating edge, the coating area misalignment of the electrode can be accurately calculated based on the widths of the insulating coating regions in the two electrode images.

[0023] In one embodiment, edge finding is performed on the defect detection area of ​​the insulating coating region in the first electrode image to obtain the first electrode virtual edge and the first insulating edge. This includes: finding the edge points of the defect detection area of ​​the insulating coating region in the first electrode image; and fitting the found edge points to obtain the first electrode virtual edge and the first insulating edge. By finding the edge points of the defect detection area of ​​the insulating coating region and then fitting the found edge points to determine the electrode virtual edge and the insulating edge, the success rate of finding the electrode virtual edge and the insulating edge is improved.

[0024] In one embodiment, after performing defect detection on the defect detection area and obtaining the defect detection result, the method further includes: binding the defect detection result with electrode identification information. Binding the defect detection result to the electrode identification information allows the defect detection result to be associated with a specific electrode, providing data support for subsequent operations such as rejecting electrodes.

[0025] Secondly, this application provides a device for detecting defects in the insulating coating of battery electrodes, comprising:

[0026] The image acquisition module is used to acquire images of the electrode obtained by photographing the electrode. The electrode image includes at least one complete electrode.

[0027] The image analysis module is used to determine the insulating coating area and the tab area in the electrode image;

[0028] The region extraction module is used to determine the defect detection area of ​​the insulating coating area in the electrode image based on the insulating coating area and the tab area;

[0029] The defect analysis module is used to perform defect detection on the defect detection area and obtain the defect detection results.

[0030] Thirdly, this application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described method.

[0031] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method.

[0032] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, performs the steps of the above-described method.

[0033] Sixthly, this application provides a battery electrode defect detection system, including an image acquisition device and a host computer. The image acquisition device is used to capture an image of the electrode and send the image to the host computer. The host computer is used to detect defects in the insulating coating of the battery electrode according to the above method.

[0034] Details of one or more embodiments of this application are set forth in the following drawings and description. Other features, objects, and advantages of the invention will become apparent from the specification, drawings, and claims. Attached Figure Description

[0035] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0036] Figure 1 This is a flowchart of a method for detecting defects in the insulating coating of battery electrodes in one embodiment;

[0037] Figure 2 This is a flowchart illustrating the determination of the insulating coating region and the tab region in an electrode image in one embodiment;

[0038] Figure 3 This is a flowchart of a process for initially locating the edge of an electrode by performing a full-image edge search on the electrode image from the side furthest from the electrode tab towards the side closest to the electrode tab in one embodiment.

[0039] Figure 4 This is a flowchart illustrating how to locate the tab region in an electrode image by searching through the insulating coating region in one embodiment.

[0040] Figure 5 This is a flowchart illustrating, in one embodiment, the determination of a defect detection area in the insulating coating region of an electrode image based on the insulating coating region and the tab region;

[0041] Figure 6 This is a flowchart illustrating the defect detection process in one embodiment, showing the defect detection results for a defect detection area.

[0042] Figure 7 This is a flowchart for calculating the misalignment of the coating area of ​​the electrode in one embodiment;

[0043] Figure 8 This is a schematic diagram of the hardware layout for detecting defects in the insulating coating of battery electrodes in one embodiment.

[0044] Figure 9 This is a schematic diagram of camera imaging in one embodiment;

[0045] Figure 10 This is a schematic diagram illustrating the calculation method of misalignment in one embodiment;

[0046] Figure 11This is a structural block diagram of a device for detecting defects in the insulating coating of battery electrodes in one embodiment;

[0047] Figure 12 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0048] The embodiments of the technical solution of this application will now be described in detail with reference to the accompanying drawings. These embodiments are only used to more clearly illustrate the technical solution of this application and are therefore merely examples, and should not be used to limit the scope of protection of this application.

[0049] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0050] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0051] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0052] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0053] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0054] In the description of the embodiments of this application, the technical terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing the embodiments of this application and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the embodiments of this application.

[0055] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0056] With the development of science and technology and the continuous progress of society, the application fields of power batteries are constantly expanding. They are not only used in electric vehicles such as electric bicycles, electric motorcycles, and electric cars, but also in military equipment and aerospace. Power batteries provide power to these vehicles, and are commonly used in valve-sealed lead-acid batteries, open-type tubular lead-acid batteries, and lithium iron phosphate batteries, characterized by high energy, high power, and high energy density. Traditional battery electrode defect detection uses two sets of image sensors to acquire images, obtaining the distance from the active material coating to the electrode edge. The coating misalignment is calculated and used in a closed-loop control system to adjust the coating area until the misalignment is less than the specified value. Existing defect detection methods are based on the pre-process coating / die-cutting stage, only involving coating stage inspection and coating area misalignment detection. They lack inspection of the electrodes before stacking them into cells, failing to effectively control damage during transport and accurately bind data to specific electrodes and cells. Based on this, this application proposes a method for detecting defects in the insulating coating of battery electrodes. The method involves capturing an image of the electrode containing at least one complete electrode, identifying the insulating coating region and the tab region within the image, and then determining the defect detection area within the insulating coating region based on these regions. Finally, defect detection is performed on the defect detection area to obtain the defect detection result. This method enables the detection of the insulating coating of the electrode before lamination, accurately detecting the presence of defects in the insulating coating region, the tab region, and whether the dimensions and widths of the insulating coating regions on both sides of the electrode are consistent. Pre-lamination detection allows for timely rejection of electrodes with defects or dimensional abnormalities, improving equipment operating efficiency.

[0057] The method for detecting defects in the insulating coating of battery electrodes provided in this application embodiment can be applied during the operation of battery production line equipment, such as during the stacking, winding, or coating processes. Specifically, the insulating coating of the battery electrode can be a ceramic coating, an alumina coating, etc., and the ceramic coating can be made of silicon carbide ceramic or silicon nitride ceramic. Taking the detection of insulating coating defects in electrodes during the material roll transfer process on the stacking equipment as an example, cameras can be set on both sides of the electrode strip at both the lower cathode camera station and the upper cathode camera station. Images of the electrode strip are obtained by taking pictures of the cathode sheet on the electrode strip using both cameras. By processing the electrode images, the insulating coating area and the tab area are determined. Based on the insulating coating area and the tab area, the defect detection area in the insulating coating area of ​​the electrode image is determined. Finally, defect detection is performed on the defect detection area to obtain the defect detection result. Furthermore, defect detection includes the detection of misalignment, defects, and tab defects in the insulating coating area, as well as data binding and storage, enabling the detection of tab defects, insulating coating area defects, and dimensions on one side of the cathode sheet's insulating coating before cathode lamination in the stacking equipment. It should be noted that the batteries involved in the embodiments of this application can be, but are not limited to, applied in electrical devices such as vehicles, ships, or aircraft.

[0058] In one embodiment, a method for detecting defects in the insulating coating of battery electrodes is provided, applicable to the detection of insulating coating defects in composite front cathode sheets. For example... Figure 1 As shown, the method includes:

[0059] Step S100: Obtain the polar image obtained by photographing the polar image.

[0060] An electrode image includes at least one complete electrode. A complete electrode includes a complete tab, extending outwards from the tab by a certain range. The specific range of extension can be set according to the actual product size of the electrode. Specifically, taking the defect detection of electrodes on a stacking machine as an example, an image acquisition device can capture images of electrodes during the material roll transfer process on the stacking machine, obtaining an image of at least one complete electrode. This image is then sent to a host computer for subsequent image processing. The image acquisition device may include a camera group, sensors, and a controller. Taking the upper cathode camera station as an example, two cameras in the camera group can be positioned on either side of the electrode strip at the upper cathode camera station. The controller triggers the cameras to take pictures after the sensors detect the tab, or it can control the cameras to take pictures periodically based on the electrode strip's transport speed. The captured electrode images are then uploaded to the host computer. Furthermore, light sources can be provided for each camera to ensure ambient brightness for better image acquisition. The controller can be a PLC (Programmable Logic Controller), MCU (Micro Control Unit), etc., the camera can be a CCD (Charge Coupled Device) camera, the sensor can be a photoelectric sensor, and the host computer can be, but is not limited to, various personal computers, laptops, smartphones, tablets, and portable wearable devices. Portable wearable devices can be smartwatches, smart bracelets, head-mounted devices, etc.

[0061] Furthermore, before photographing the electrode, a joint calibration model can be generated from both cameras to align their coordinates. This facilitates subsequent size calculations of the front and back electrode images, ensuring accurate calculation of the coating misalignment. Additionally, after the cameras capture the electrode image, the controller can upload the electrode identification information to the host computer, allowing the host computer to bind and store the defect detection results with the electrode identification information.

[0062] Step S200: Determine the insulating coating area and the tab area in the electrode image.

[0063] The insulating coating area refers to the region where the insulating material coating is located in the electrode image, and the tab area refers to the region where the tab is located in the electrode image. Specifically, after acquiring the electrode image, the host computer analyzes the image data and performs image processing to locate the insulating coating area and tab area in the electrode image. The image data can specifically be grayscale values. By combining the grayscale values ​​of each pixel in the electrode image, the image is processed and detected using methods such as grayscale difference and edge finding to locate the insulating coating area and tab area. The host computer's method of processing and detecting the electrode image is not unique; it can be based on the placement of the electrodes on the electrode strip, and the image detection direction can be pre-saved in the host computer. For example, as... Figure 9 As shown, if the electrode image obtained by the computer consists of the active material coating area 103, the insulating material coating area, and the electrode tab from right to left, the host computer performs grayscale difference and edge detection on the electrode image from right to left, and finds the insulating coating area 107 and the electrode tab area 104 in the electrode image in sequence.

[0064] Step S300: Determine the defect detection area of ​​the insulating coating area in the electrode image based on the insulating coating area and the tab area.

[0065] The defect detection area is the target area for defect detection of the insulating coating of the current electrode. Specifically, after locating the insulating coating area and the tab area in the electrode image, the host computer finds the image boundary between different electrodes based on the tab area, and then combines the image boundary of the insulating coating area and the electrode to determine the defect detection area of ​​the insulating coating area of ​​the current electrode in the electrode image, which serves as the target area for subsequent defect detection of the insulating coating of the current electrode.

[0066] Step S400: Perform defect detection on the defect detection area to obtain the defect detection result.

[0067] Correspondingly, after determining the defect detection area of ​​the insulating coating region of the current electrode, the host computer can perform defect search in the defect detection area in combination with the preset defect area information, determine whether there is a defect in the defect detection area that matches the defect area information, and then obtain the defect detection result of whether there is a defect in the insulating coating region of the current electrode.

[0068] Furthermore, in one embodiment, after step S400, the method further includes binding the defect detection result with electrode identification information. Specifically, electrode identification information refers to information that can uniquely identify an electrode. The type of electrode identification information is not unique; it can be an electrode number, identification code, etc. After the host computer binds the defect detection result with the electrode identification information, it can store it in a local database or send it to the controller in the image acquisition device. By binding the defect detection result with the electrode identification information, the defect detection result is linked to a specific electrode, providing data support for subsequent operations such as electrode rejection.

[0069] The aforementioned method for detecting defects in the insulating coating of battery electrodes involves capturing an image of the electrode containing at least one complete electrode, identifying the insulating coating region and the tab region within the image, and then determining the defect detection area within the insulating coating region based on these regions. Finally, defect detection is performed on the defect detection area to obtain the defect detection result. This method enables the detection of the insulating coating of pre-composite electrodes, identifying the presence of defects in the insulating coating region, allowing for the timely rejection of defective electrodes. It offers high detection accuracy and improves the operating efficiency of the stacking equipment.

[0070] In one embodiment, such as Figure 2 As shown, step S200 includes steps S210 to S230.

[0071] Step S210: Perform full-image edge tracing on the electrode image to obtain the initial location of the electrode edges.

[0072] Specifically, the host computer, considering the arrangement positions of different regions of the electrode, performs a full-image edge search on the electrode image according to the corresponding directions to find the initially located electrode edges in the electrode image. In one embodiment, step S210 includes: performing a full-image edge search on the electrode image from the side away from the electrode tab towards the side closer to the electrode tab to obtain the initially located electrode edges. Figure 9 As shown, taking the electrode image as an example where the active material coating area 103, the insulating material coating area, and the electrode tab are arranged from right to left, the host computer searches for the initial electrode edge 106 from right to left in the electrode image through full-image edge search. By performing full-image edge search from the side away from the electrode tab towards the side closer to the electrode tab, the initial electrode edge can be accurately located.

[0073] Step S220: Reposition the electrode based on the initially positioned electrode edge to determine the insulating coating area in the electrode image. Correspondingly, after determining the initially positioned electrode edge 106 in the electrode image, the host computer continues to reposition the region towards the electrode tab based on the initially positioned electrode edge 106 to find the insulating coating area 107 in the electrode image.

[0074] Step S230: Locate the tab region in the electrode image by searching through the insulating coating area. After finding the insulating coating area 107 in the electrode image, the host computer continues to search towards the tab based on the insulating coating area 107, and finds the tab region 104 in the electrode image.

[0075] In the above embodiments, edge finding and relocation are performed on the entire electrode image to find the insulating coating area in the electrode image, and then the tab area in the electrode image is found based on the determined insulating coating area, so as to gradually find different areas in the electrode image and the detection is accurate and reliable.

[0076] Furthermore, in one embodiment, such as Figure 3 As shown, in step S210, the electrode image is searched for edges from the side away from the electrode tab towards the side closer to the electrode tab to obtain the initial location of the electrode edge, including steps S212 and S214.

[0077] Step S212: Perform full-image edge search on the electrode image from the side furthest from the tab towards the tab. Correspondingly, taking the full-image edge search from right to left as an example, the host computer combines the grayscale values ​​of different pixels in the electrode image to search for the first predetermined abrupt change edge from black to white from right to left. This can be achieved by setting N (specific values ​​can be set) search boxes at equal intervals from the left to the right side of the electrode image, with each search box responsible for detecting one edge point. For each search box, traverse the pixels from right to left, finding the first edge point where the grayscale value changes to the set degree. Then, use a straight-line fitting algorithm to determine whether all the edge points found by the search boxes can be fitted into a straight line, and whether the angle between the fitted line and the upper edge of the electrode image is within a set range (e.g., between 85° and 95°). If a straight line with an angle within the set range with the upper edge of the electrode image is found, the predetermined abrupt change edge is considered to have been found.

[0078] Step S214: If a predetermined mutation edge is found, the edge finding is confirmed as successful, and the found predetermined mutation edge is determined as the initial positioning electrode edge. If a predetermined mutation edge can be found, the host computer determines that the edge finding is successful and determines the found predetermined mutation edge as the initial positioning electrode edge.

[0079] In the above embodiments, when performing full-image edge finding on the electrode image from the side away from the electrode tab towards the side closer to the electrode tab, it is analyzed whether a predetermined abrupt change edge can be found. If a predetermined abrupt change edge is found, it is used as the initial location of the electrode edge, which further improves the accuracy of edge finding.

[0080] Furthermore, in one embodiment, the method further includes: if a predetermined abrupt change edge is not found, determining that the edge finding was unsuccessful, and binding the electrode edge finding failure information with the electrode identification information. If the electrode edge finding is unsuccessful, no further region search operation is required, the battery electrode insulation coating defect detection ends, and the electrode edge finding failure information is bound to the electrode identification information and stored in a local database or sent to the controller.

[0081] In one embodiment, step S220 includes: determining the target insulating coating area based on the initially located electrode edge, and extracting the insulating coating area in the determined electrode image within the target insulating coating area.

[0082] Specifically, the host computer can pre-save the dimensions of the insulating coating area of ​​the electrode, such as... Figure 9 As shown, after initially locating the electrode edge 106 in the electrode image from right to left, the insulating coating region is relocated to the left of the initially located electrode edge 106. A region of interest larger than or equal to the size of the insulating coating region is determined to the left of the initially located electrode edge as the target insulating coating region. Further, the host computer performs region extraction based on the target insulating coating region, for example, using the Blob algorithm to extract the insulating coating region 107 in the electrode image. Here, in computer vision, a Blob refers to a connected region in an image. The Blob algorithm extracts and labels connected components from the binary image after foreground / background separation. The insulating coating region in the electrode image is obtained by analyzing the connected components in the binary image.

[0083] In the above embodiments, after determining the target insulating coating area based on the initial positioning electrode edge, the insulating coating area in the electrode image is then extracted based on the target insulating coating area, which facilitates the rapid locating of the insulating coating area.

[0084] In one embodiment, such as Figure 4 As shown, step S230 includes steps S232 and S234.

[0085] Step S232: Perform region relocation based on the insulating coating area to determine the target electrode detection area. Specifically, after determining the insulating coating area in the electrode image, the host computer continues to perform region relocation based on the insulating coating area, moving closer to the electrode, to determine the target electrode detection area.

[0086] In one embodiment, step S232 includes: extracting the initial positioning insulation edge of the insulation coating area; and determining the target electrode detection area based on the initial positioning insulation edge. Specifically, as shown... Figure 9As shown, after locating the insulating coating region 107 in the electrode image, the host computer positions the edge of the insulating coating region 107 near the tab direction, specifically the leftmost edge of the insulating coating region 107 as the initial positioning insulating edge 105. Furthermore, the host computer can pre-save the tab dimensions of the electrode and reposition it using the obtained position of the initial positioning insulating edge 105. A tab detection frame larger than or equal to the tab size is then determined to the left of the initial positioning insulating edge 105 as the target tab detection area. By extracting the initial positioning insulating edge of the ceramic coating area and combining it with the initial positioning insulating edge to select the target tab detection area, the target tab detection area can be quickly and accurately determined.

[0087] In addition, in one embodiment, the method may further include: if the initial positioning of the insulating edge in the insulating coating area fails to extract, then binding the information of unsuccessful edge finding with the electrode identification information. If the initial positioning of the insulating edge fails to find, then no further operation is required, the defect detection of the battery electrode insulating coating ends, and the information of unsuccessful edge finding is bound with the electrode identification information and saved in a local database or sent to the controller.

[0088] Step S234: Locate and extract the electrode region within the target electrode detection area. After determining the target electrode detection area, the host computer analyzes the image within the target electrode detection area and extracts the electrode region.

[0089] In one embodiment, step S234 includes: extracting regions within the target electrode detection region that conform to the electrode grayscale characteristics to obtain a preliminary electrode region; determining whether the preliminary electrode region is an electrode based on its region shape and size; if so, determining that the electrode region has been obtained. Specifically, the host computer performs binarization processing on the image within the target electrode detection region, performs grayscale value analysis on the binarized image, and extracts regions that conform to the electrode grayscale characteristics as preliminary electrode regions. Further, the host computer analyzes the region shape and size of the preliminary electrode region in conjunction with preset electrode feature parameters to determine whether the preliminary electrode region is an electrode. If the preliminary electrode region is an electrode, electrode region 104 is found. The electrode feature parameters may include parameters such as electrode shape and size. If the region shape and size of the preliminary electrode region are the same as the preset electrode shape and size, or the difference is within a preset allowable range, then the region shape and size of the preliminary electrode region can be considered consistent with the electrode feature parameters, and the preliminary electrode region is determined to be an electrode. By combining the grayscale features of the electrode ear to preliminarily screen the target electrode ear detection area and determine the preliminary electrode ear region, and then combining the region shape and size of the preliminary electrode ear region to analyze whether the electrode ear region has been found, the accuracy of electrode ear region finding can be ensured.

[0090] In the above embodiments, by combining the insulating coating area for area relocation and determining the target tab detection area, the tab area can be found based on the target tab detection area, which can also facilitate and quickly find the tab area.

[0091] In addition, in one embodiment, the method may further include: if it is determined that the preliminary tab area is not a tab, then binding the tab absence information with the electrode identification information. If the tab is not present, then no further operation is required; the battery electrode insulation coating defect detection is completed, and the tab absence information is bound with the electrode identification information and stored in a local database or sent to the controller.

[0092] In one embodiment, such as Figure 5 As shown, step S300 includes steps S310 to S330.

[0093] Step S310: Find the edge of the tab region to obtain the tab edge. After finding the tab region, the host computer can perform edge finding along a direction parallel to the initially positioned insulating edge within the tab region to locate the tab edge. For example... Figure 9 As shown, taking the step-by-step tracing of the electrode image from right to left to find the initial electrode edge 106 and the initial insulation edge 105 as an example, the host computer uses an edge-finding algorithm to find the upper edge 110 and the lower edge 111 of the electrode along the vertical direction of the electrode region 104. Specifically, based on the position of the electrode region 104, the search borders for the two electrode edges can be determined at the upper and lower edge positions of the electrode region 104. Then, within each search border, pixels are traversed along the vertical direction to find edge points where the grayscale value changes to a preset level. If multiple edge points found within the same search border are fitted to form a straight line, then the electrode edge has been successfully found within that search border.

[0094] Step S320: Obtain the electrode edge based on the tab edge and the preset distance data. The preset distance data is the distance between the tab edge and the electrode edge; the specific value of the preset distance data can be set according to the actual distance between the electrode edge and the tab edge in the product. Specifically, for example... Figure 9 As shown, the electrode edge includes the upper edge 112 and the lower edge 113. After finding the electrode tab edge, the upper edge 112 can be found by adding the preset distance data to the position of the upper edge 110 of the electrode tab, and the lower edge 113 can be found by adding the preset distance data to the position of the lower edge 111 of the electrode tab.

[0095] Step S330: Based on the initially located electrode edge, the initially located insulation edge, and the electrode edge, determine the defect detection area of ​​the insulation coating region in the electrode image. Correspondingly, after determining the initially located electrode edge 106, the initially located insulation edge 105, the upper edge of the electrode 112, and the lower edge of the electrode 113, the host computer combines the four edges to generate the defect detection area of ​​the insulation coating region 107 of the current electrode.

[0096] In the above embodiments, after locating the tab area, the electrode edge is determined by combining the tab edge and preset distance data. Then, based on the initially located electrode edge, the initially located insulation edge, and the electrode edge, the defect detection area in the insulation coating area can be accurately located for subsequent defect detection.

[0097] Furthermore, in one embodiment, the method further includes: if edge finding in the tab area is unsuccessful, then binding the edge finding failure information with the electrode identification information and outputting it. If edge finding in the tab area is unsuccessful, then no further operation is required; the battery electrode insulation coating defect detection is completed, and the edge finding failure information is bound with the electrode identification information and saved in a local database or sent to the controller.

[0098] In one embodiment, such as Figure 6 As shown, step S400 includes steps S410 and S420.

[0099] Step S410: Extract connected components from the defect detection region. A connected component refers to the set of adjacent pixels in the defect detection region whose grayscale values ​​all fall within the same defined range. After determining the defect detection region of the insulating coating area of ​​the current electrode, the host computer can also perform Blob algorithm processing on the defect detection region to obtain the connected components in the processed binary image.

[0100] Step S420: If a connected component similar to the predetermined defect area exists, a defect is determined to exist. The defect detection result includes information about the presence of a defect. Pre-defined defect area information can be generated in advance based on the actual defects that may occur in the insulating coating area of ​​the electrode and stored in the host computer. The predetermined defect area information may include the location, shape, and size of the predetermined defect area. The host computer analyzes whether the connected component of the defect detection area is similar to the predetermined defect area based on the predetermined defect area information. For example, if the similarity of the connected component of the defect detection area to the predetermined defect area in terms of location, shape, and size is higher than a corresponding set threshold, then the connected component can be considered similar to the predetermined defect area, thus determining that a defect exists in the defect detection area.

[0101] In the above embodiments, by extracting the connected components in the defect detection area and comparing them with the predetermined defect area, the system analyzes whether there is a defect in the defect detection area, thus achieving accurate and efficient detection.

[0102] It should be noted that when detecting whether there is a defect in the insulating coating area of ​​the current electrode, two images of the electrode obtained by two cameras respectively capturing the composite and non-composite surfaces can be analyzed simultaneously to determine the defect detection area of ​​the insulating coating region in the two electrode images. Then, it is detected whether there is a connected component similar to the predetermined defect area in the defect detection area of ​​the two electrode images. If there is no connected component similar to the predetermined defect area in the defect detection area of ​​the two electrode images, it is considered that there is no defect in the insulating coating area of ​​the current electrode. If a connected component similar to the predetermined defect area is detected in the defect detection area of ​​one or two electrode images, it is considered that there is a defect in the insulating coating area of ​​the current electrode.

[0103] In other embodiments, the above method may first perform image analysis on one electrode image through steps S100-S400 to find the defect detection region in the electrode image and analyze whether there is a connected component similar to the predetermined defect region. If there is, the insulating coating region of the current electrode is considered to have a defect, and there is no need to analyze the other electrode image. If not, then through steps S100-S400, the defect detection region in the other electrode image is found and analyzed to see if there is a connected component similar to the predetermined defect region. If the defect detection region in the other electrode image also does not have a connected component similar to the predetermined defect region, the insulating coating region of the current electrode is considered to have no defect; otherwise, the insulating coating region of the current electrode is also considered to have a defect. Furthermore, if it is determined that the predetermined defect region has a defect, the host computer binds the defect information with the electrode identification information and stores it in a local database or sends it to the controller.

[0104] Further, in one embodiment, step S400 further includes step S430: if no connected region similar to the predetermined defect area exists, calculate the coating area misalignment of the electrode sheet. The defect detection result includes information about the absence of defects and the coating area misalignment. Specifically, if neither of the defect detection areas in the two electrode sheet images taken for the current electrode sheet contains a connected region similar to the predetermined defect area, then the insulating coating of the current electrode sheet is considered to be defect-free, and the coating area misalignment of the current electrode sheet is calculated by combining the two electrode sheet images. In addition, the host computer can also bind the information about the absence of defects and the coating area misalignment with the electrode sheet identification information and store it in a local database or send it to the controller.

[0105] In the above embodiments, when there are no defects in the defect detection area of ​​the insulating coating area, the misalignment of the coating area of ​​the electrode is also calculated to analyze whether the size and width of the insulating coating area on both sides of the electrode are consistent, so as to reject the electrode with size abnormalities, thereby further improving the defect detection accuracy of the battery electrode.

[0106] In one embodiment, the electrode image includes a first electrode image and a second electrode image obtained by capturing images of both sides of the electrode. Step S430 includes: if there are no connected regions similar to a predetermined defect region in the defect detection areas corresponding to the first electrode image and the second electrode image, calculate the coating area misalignment of the electrode. The first electrode image and the second electrode image are respectively captured on the composite surface and the non-composite surface of the current electrode. When there are no connected regions similar to a predetermined defect region in the defect detection areas of both electrode images, the host computer determines that the insulating coating of the current electrode is free of defects and calculates the coating area misalignment of the electrode. By combining the electrode images captured on both sides of the electrode, detecting whether there are defects in the corresponding defect detection areas, and calculating the coating area misalignment of the electrode only after determining that there are no defects in the defect detection areas of both electrode images, the accuracy of defect detection in the insulating coating area of ​​the electrode is improved.

[0107] Furthermore, in one embodiment, the electrode image includes a first electrode image and a second electrode image obtained by capturing images of both sides of the electrode; such as Figure 7 As shown, step S430 calculates the misalignment of the coating area of ​​the electrode, including steps S432 to S438.

[0108] Step S432: Perform edge tracing on the defect detection area of ​​the insulating coating region in the first electrode image to obtain the first electrode virtual edge and the first insulating edge. Specifically, after determining the defect detection area of ​​the insulating coating region in the first electrode image and determining that there is no connected region similar to the predetermined defect area in the defect detection area, perform edge tracing on the defect detection area to find the first electrode virtual edge and the first insulating edge in the first electrode image.

[0109] In one embodiment, step S432 includes: finding edge points of the defect detection area of ​​the insulating coating region in the first electrode image; and fitting the found edge points to obtain the first electrode virtual edge and the first insulating edge. Specifically, based on the defect detection area of ​​the insulating coating region of the current electrode in the first electrode image, an insulating edge search frame and a virtual edge search frame are determined according to the initially located electrode edge, the initially located insulating edge, the upper edge of the electrode, and the lower edge of the electrode. Then, edge searching is performed within the insulating edge search frame and the virtual edge search frame respectively using an edge-finding algorithm to find the edge points within the two search frames. Finally, the first electrode virtual edge and the first insulating edge are obtained by fitting the edge points within each search frame. By finding the edge points of the defect detection area of ​​the insulating coating region and then fitting the found edge points to determine the electrode virtual edge and the insulating edge, the success rate of finding the electrode virtual edge and the insulating edge is improved.

[0110] Furthermore, after finding the edge points of the defect detection area in the insulating coating region of the first electrode image, the method may also include a step of filtering out edge points to remove abnormal edge points. Then, the remaining edge points after filtering are combined for fitting to obtain the virtual edge of the first electrode and the first insulating edge. The method for filtering out edge points is not unique; it can be done through a fitting algorithm, such as using a weighted least squares method based on the position of each edge point to filter out abnormal edge points.

[0111] Step S434: Perform edge tracing on the defect detection area of ​​the insulating coating region in the second electrode image to obtain the virtual edge of the second electrode and the second insulating edge. It can be understood that the method of performing edge tracing on the defect detection area of ​​the insulating coating region in the second electrode image to obtain the virtual edge and the second insulating edge is similar to step S432, and will not be repeated here.

[0112] Step S436: Calculate the width of the first insulating coating region based on the virtual edge of the first electrode and the first insulating edge, and calculate the width of the second insulating coating region based on the virtual edge of the second electrode and the second insulating edge. After locating the virtual edge of the first electrode and the first insulating edge in the first electrode image, and the virtual edge of the second electrode and the second insulating edge in the second electrode image, the host computer calculates the distance between the virtual edge of the first electrode and the first insulating edge to obtain the width of the insulating coating region in the first electrode image, i.e., the width of the first insulating coating region. The host computer then calculates the distance between the virtual edge of the second electrode and the second insulating edge to obtain the width of the insulating coating region in the second electrode image, i.e., the width of the second insulating coating region.

[0113] Step S438: Calculate the coating area misalignment of the electrode based on the widths of the first and second insulating coating areas. Correspondingly, the host computer subtracts the widths of the first and second insulating coating areas, and the difference is the coating area misalignment of the current electrode.

[0114] In the above embodiments, edge finding is performed by combining the defect detection area of ​​the insulating coating region in the two electrode images to find the corresponding electrode virtual edge and insulating edge. Then, the width of the insulating coating region in the two electrode images is calculated based on the electrode virtual edge and insulating edge. Finally, the misalignment amount of the coating region of the electrode can be accurately calculated based on the width of the insulating coating region in the two electrode images.

[0115] In addition, in one embodiment, the method may further include: if no edge point is found, binding the edge point finding failure information with the electrode identification information and outputting it. If the edge point finding of the defect detection area in the first electrode image or the second electrode image is unsuccessful, no further operation is required, the battery electrode insulation coating defect detection ends, and the edge point finding failure information is bound with the electrode identification information and saved in the local database or sent to the controller.

[0116] To facilitate a better understanding of the above-mentioned method for detecting defects in the insulating coating of battery electrodes, a detailed explanation is provided below with reference to specific embodiments.

[0117] To address the issue that existing battery electrode defect detection methods only involve coating section inspection and coating area misalignment detection, neglecting insulation coating defect detection, and that coating process inspection cannot bind data to specific electrodes, this application proposes an online detection method for dimensional defects in the insulating coating of the cathode sheet before continuous anode lamination. This method utilizes a high-efficiency, high-precision visual algorithm to inspect the insulating coating of the cathode sheet before lamination, accurately detecting the presence of defects in the insulating coating area, the presence of defects in the electrode tabs, and the consistency of the size and width of the insulating coating area on both sides of the cathode sheet. Pre-lamination inspection allows for timely rejection of electrodes with defects and dimensional anomalies in conjunction with equipment, improving equipment operating efficiency and reducing the risk of missed defects. Specifically, as... Figure 8 The diagram shows the hardware layout for detecting defects in the insulating coating. A high-frame-rate area array camera is mounted on each side of the cathode strip, and a white strip light source is mounted on each side to illuminate the insulating coating area. A101 is the cathode strip, A102 is camera 1, A103 is the light source corresponding to camera 1, A104 is camera 2, and A105 is the light source corresponding to camera 2. Each camera on each side of the electrode strip captures images of the insulating coating area. The two cameras are jointly calibrated to generate a calibration model. The PLC triggers the cameras to take pictures by sensing the electrode tabs and provides a unique identifier for the current electrode. Vision software on the host computer processes the images using grayscale difference and edge detection methods to detect misalignment, defects, and electrode tab defects in the insulating coating area, and performs data binding and storage.

[0118] like Figure 9The diagram shown is an imaging schematic of the camera in the embodiment. The names of each region are as follows: 101: Previous cathode sheet; 102: Next cathode sheet; 103: Active material coating area of ​​the current cathode sheet; 104: Tab of the current cathode sheet, i.e., tab area; 105: Initial positioning insulation edge, i.e., outer edge of the insulation material coating area; 106: Cathode virtual edge / initial positioning electrode edge, i.e., the boundary between the active material coating area and the insulation material coating area of ​​the cathode electrode; 107: Insulation material coating area, i.e., insulation coating area; 108: Offset between the upper edge of the tab and the upper edge of the current electrode; 109: Offset between the lower edge of the tab and the lower edge of the current electrode; 110: Upper edge of the tab; 111: Lower edge of the tab; 112: Upper edge of the electrode; 113: Lower edge of the electrode.

[0119] Figure 10 This diagram illustrates the calculation method for misalignment, where side A is the image taken from the non-composite side of the electrode, and side B is the image taken from the composite side of the electrode. The defect detection items of this method include: metal leakage and breakage defect detection in region 106, width detection in region 106, misalignment of the width of region 106 on sides A and B, and electrode tab loss detection in region 104.

[0120] This defect detection method accurately repositions the detection area by locating the electrode edge and the insulating coating region, precisely positioning the detection frame to the corresponding area to be inspected. Then, it performs detection through edge finding, dimensional measurement, and defect detection algorithms, outputting the defect detection results. Detecting the insulating coating on the lamination equipment allows for control over damage to the insulating coating during the roll transfer process, providing electrode data for subsequent rejection operations. Assigning a unique number to each electrode ensures traceability of the insulating coating data for each electrode. This detection method boasts high accuracy (pixel precision down to 0.02mm) and high efficiency (single detection time less than 20ms).

[0121] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0122] Based on the same inventive concept, this application also provides a battery electrode insulation coating defect detection device for implementing the above-mentioned method for detecting defects in battery electrode insulation coatings. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more battery swapping device embodiments provided below can be found in the limitations of the battery electrode insulation coating defect detection method described above, and will not be repeated here.

[0123] In one embodiment, a device for detecting defects in the insulating coating of battery electrodes is provided, suitable for detecting defects in the insulating coating of composite front cathode sheets. Figure 11 As shown, the device includes: an image acquisition module 100, an image analysis module 200, a region extraction module 300, and a defect analysis module 400, wherein:

[0124] The image acquisition module 100 is used to acquire an image of the electrode obtained by shooting the electrode, and the image of the electrode includes at least one complete electrode.

[0125] Image analysis module 200 is used to determine the insulating coating area and the tab area in the electrode image.

[0126] The region extraction module 300 is used to determine the defect detection area of ​​the insulating coating area in the electrode image based on the insulating coating area and the tab area.

[0127] The defect analysis module 400 is used to perform defect detection on the defect detection area and obtain the defect detection results.

[0128] In one embodiment, the image analysis module 200 performs full-image edge tracing on the electrode image to obtain the initial location of the electrode edge; it then performs relocation based on the initially located electrode edge to determine the insulating coating region in the electrode image; and finally, it searches through the insulating coating region to determine the tab region in the electrode image.

[0129] In one embodiment, the image analysis module 200 performs full-image edge tracing on the electrode image from the side furthest from the electrode tab towards the side closest to the electrode tab to obtain the initial location of the electrode edge.

[0130] In one embodiment, the image analysis module 200 performs full-image edge tracing on the electrode image from the side away from the electrode tab towards the side closer to the electrode tab: if a predetermined abrupt change edge is found, the edge tracing is determined to be successful, and the found predetermined abrupt change edge is determined as the initially located electrode edge.

[0131] In one embodiment, the image analysis module 200 determines the target insulating coating area based on the initially located electrode edge, and extracts the insulating coating area in the determined electrode image within the target insulating coating area.

[0132] In one embodiment, the image analysis module 200 performs region relocation based on the insulating coating area to determine the target tab detection area; and locates and extracts the tab area within the target tab detection area.

[0133] In one embodiment, the image analysis module 200 extracts the initial positioning insulation edge of the insulation coating area; based on the initial positioning insulation edge, the target electrode detection area is determined.

[0134] In one embodiment, the image analysis module 200 extracts regions in the target electrode detection region that conform to the electrode grayscale characteristics to obtain a preliminary electrode region; based on the region shape and region size of the preliminary electrode region, it determines whether the preliminary electrode region is an electrode, and if so, it determines that the electrode region has been obtained.

[0135] In one embodiment, the region extraction module 300 performs edge finding on the tab region to obtain the tab edge; based on the tab edge and preset distance data, the electrode edge is obtained, where the preset distance data is the distance between the tab edge and the electrode edge; based on the initially located electrode edge, the initially located insulation edge, and the electrode edge, the defect detection area of ​​the insulation coating region in the electrode image is determined.

[0136] In one embodiment, the defect analysis module 400 extracts connected components in the defect detection area; if a connected component similar to the predetermined defect area exists, it is determined that a defect exists; the defect detection result includes information about the existence of a defect.

[0137] In one embodiment, the defect analysis module 400 also calculates the coating region misalignment of the electrode when there is no connected region similar to the predetermined defect region; the defect detection result includes information on the absence of defects and the coating region misalignment.

[0138] In one embodiment, the electrode image includes a first electrode image and a second electrode image obtained by taking pictures of both sides of the electrode; when there is no connected region similar to the predetermined defect region in the defect detection areas corresponding to the first electrode image and the second electrode image, the defect analysis module 400 calculates the coating area misalignment of the electrode.

[0139] In one embodiment, the electrode image includes a first electrode image and a second electrode image obtained by capturing images of both sides of the electrode; the defect analysis module 400 performs edge tracing on the defect detection area of ​​the insulating coating region in the first electrode image to obtain the first electrode virtual edge and the first insulating edge; it performs edge tracing on the defect detection area of ​​the insulating coating region in the second electrode image to obtain the second electrode virtual edge and the second insulating edge; based on the first electrode virtual edge and the first insulating edge, it calculates the width of the first insulating coating region, and based on the second electrode virtual edge and the second insulating edge, it calculates the width of the second insulating coating region; based on the width of the first insulating coating region and the width of the second insulating coating region, it calculates the coating region misalignment of the electrode.

[0140] In one embodiment, the defect analysis module 400 finds the edge points of the defect detection area in the insulating coating region of the first electrode image; and performs fitting based on the found edge points to obtain the virtual edge of the first electrode and the first insulating edge.

[0141] In one embodiment, the defect analysis module 400 also binds the defect detection results with the electrode identification information.

[0142] In one embodiment, a computer device is provided, which can be a server or a terminal. Taking a server as an example, its internal structure diagram can be as follows: Figure 12 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores defect detection result data. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements a method for detecting defects in the insulating coating of battery electrodes.

[0143] Those skilled in the art will understand that Figure 12 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0144] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0145] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0146] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0147] In one embodiment, a battery electrode defect detection system is also provided, including an image acquisition device and a host computer. The image acquisition device is used to capture images of the electrode and send them to the host computer. The host computer is used to detect defects in the insulating coating of the battery electrode according to the above method. Specifically, the image acquisition device includes a camera group, a sensor, and a controller. The controller connects the camera group, the sensor, and the host computer. The controller can be a PLC, MCU, etc., the camera group can be a CCD camera group, the sensor can be a photoelectric sensor, and the host computer can be, but is not limited to, various personal computers, laptops, smartphones, tablets, and portable wearable devices. Portable wearable devices can be smartwatches, smart bracelets, head-mounted devices, etc.

[0148] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This computer program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, optical disk, or read-only memory (ROM), or random access memory (RAM).

[0149] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0150] The above embodiments merely illustrate several implementation methods of the present invention, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this invention patent should be determined by the appended claims.

Claims

1. A method for detecting defects in the insulating coating of battery electrodes, characterized in that, include: Acquire an image of an electrode by taking a photograph of the electrode, wherein the image of the electrode includes at least one complete electrode; Identify the insulating coating area and the tab area in the electrode image; Based on the insulating coating area and the tab area, determine the defect detection area of ​​the insulating coating area in the electrode image; Defect detection is performed on the defect detection area to obtain the defect detection result; The step of determining the defect detection area of ​​the insulating coating area in the electrode image based on the insulating coating area and the tab area includes: performing edge tracing on the tab area to obtain the tab edge; obtaining the electrode edge based on the tab edge and preset distance data, wherein the preset distance data is the distance data between the tab edge and the electrode edge; and determining the defect detection area of ​​the insulating coating area in the electrode image based on the initially located electrode edge, the initially located insulating edge, and the electrode edge. The step of performing defect detection on the defect detection area to obtain a defect detection result includes: extracting connected components in the defect detection area; if there is a connected component similar to a predetermined defect area, it is determined that a defect exists; the defect detection result includes information about the existence of a defect.

2. The method according to claim 1, characterized in that, Determining the insulating coating region and the tab region in the electrode image includes: Perform full-image edge tracing on the electrode image to obtain the initial location of the electrode edges; Repositioning is performed based on the initial positioning of the electrode edge to determine the insulating coating area in the electrode image; The tab region in the electrode image is determined by searching through the insulating coating area.

3. The method according to claim 2, characterized in that, The step of performing full-image edge tracing on the electrode image to obtain the initial location of the electrode edges includes: The electrode image is used to perform a full-image edge search from the side furthest from the electrode tab towards the side closest to the electrode tab to obtain the initially located electrode edge.

4. The method according to claim 3, characterized in that, The step of performing a full-image edge tracing on the electrode image from the side furthest from the electrode tab towards the side closest to the electrode tab to obtain the initially located electrode edge includes: Perform a full-image edge search on the electrode image from the side furthest from the electrode tab towards the side closest to the electrode tab: If a predetermined mutation edge is found, the edge finding is confirmed to be successful, and the found predetermined mutation edge is determined as the edge of the initially positioned electrode.

5. The method according to claim 2, characterized in that, The step of repositioning based on the edge of the initially positioned electrode to determine the insulating coating area in the electrode image includes: The target insulating coating area is determined based on the initially located electrode edge, and the insulating coating area in the electrode image is extracted and determined from the target insulating coating area.

6. The method according to claim 2, characterized in that, The step of locating and determining the tab region in the electrode image through the insulating coating area includes: Based on the insulating coating area, the target electrode detection area is determined by repositioning the region. Locate and extract the electrode area within the target electrode detection area.

7. The method according to claim 6, characterized in that, The step of repositioning the target electrode detection area based on the insulating coating area includes: Extract the initial positioning insulation edge of the insulation coating area; Based on the initial positioning insulation edge, the target electrode detection area is determined.

8. The method according to claim 6, characterized in that, The step of locating and extracting the electrode region in the target electrode detection region includes: Extract the region in the target electrode detection region that matches the electrode grayscale characteristics to obtain the preliminary electrode region; Based on the shape and size of the preliminary electrode region, determine whether the preliminary electrode region is an electrode; if so, determine that the electrode region is obtained.

9. The method according to claim 1, characterized in that, The step of performing defect detection on the defect detection area to obtain defect detection results further includes: If no connected region similar to the predetermined defect area exists, the coating area misalignment of the electrode is calculated; the defect detection result includes information that no defect exists and the coating area misalignment.

10. The method according to claim 9, characterized in that, The electrode image includes a first electrode image and a second electrode image obtained by taking pictures of both sides of the electrode; If no connected region similar to the predetermined defect region exists, the calculation of the coating region misalignment of the electrode includes: If there is no connected region similar to the predetermined defect region in the defect detection areas corresponding to the first electrode image and the second electrode image, calculate the coating area misalignment of the electrode.

11. The method according to claim 9, characterized in that, The electrode image includes a first electrode image and a second electrode image obtained by taking pictures of both sides of the electrode; the calculation of the coating area misalignment of the electrode includes: The defect detection area of ​​the insulating coating region in the first electrode image is searched to obtain the virtual edge of the first electrode and the first insulating edge. Edge-finding is performed on the defect detection area of ​​the insulating coating region in the second electrode image to obtain the virtual edge of the second electrode and the second insulating edge. The width of the first insulating coating area is calculated based on the virtual edge of the first electrode and the first insulating edge, and the width of the second insulating coating area is calculated based on the virtual edge of the second electrode and the second insulating edge. The misalignment of the coating area of ​​the electrode is calculated based on the width of the first insulating coating area and the width of the second insulating coating area.

12. The method according to claim 11, characterized in that, The step of finding the edge of the defect detection area in the insulating coating region of the first electrode image to obtain the virtual edge of the first electrode and the first insulating edge includes: Locate the edge points of the defect detection area in the insulating coating region of the first electrode image; By fitting the found edge points, the virtual edge of the first electrode and the first insulating edge are obtained.

13. The method according to any one of claims 1-12, characterized in that, After performing defect detection on the defect detection area and obtaining the defect detection result, the method further includes binding the defect detection result with the electrode identification information.

14. A device for detecting defects in the insulating coating of battery electrodes, characterized in that, include: An image acquisition module is used to acquire an image of an electrode obtained by photographing an electrode, wherein the image of the electrode includes at least one complete electrode. The image analysis module is used to determine the insulating coating area and the tab area in the electrode image; The region extraction module is used to determine the defect detection area of ​​the insulating coating area in the electrode image based on the insulating coating area and the tab area; The defect analysis module is used to perform defect detection on the defect detection area and obtain the defect detection results; The region extraction module is further configured to: perform edge finding on the electrode region to obtain the electrode edge; and obtain the electrode edge based on the electrode edge and preset distance data, wherein the preset distance data is the distance between the electrode edge and the electrode edge. Based on the initial positioning of the electrode edge, the initial positioning of the insulation edge, and the electrode edge, the defect detection area of ​​the insulation coating region in the electrode image is determined; The defect analysis module is further configured to: extract connected components in the defect detection area; if a connected component similar to a predetermined defect area exists, determine that a defect exists; the defect detection result includes information about the existence of a defect.

15. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 13.

16. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 13.

17. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 13.

18. A battery electrode defect detection system, characterized in that, The device includes an image acquisition device and a host computer. The image acquisition device is used to capture an image of the electrode sheet and send the image to the host computer. The host computer is used to detect defects in the insulating coating of the battery electrode sheet according to any one of claims 1-13.

Images