Method, apparatus, and computer device for detecting defects in the insulating coating layer of a battery electrode sheet

Abstract

A method, apparatus, computer device, computer-readable storage medium, computer program product, and battery electrode sheet defect detection system for detecting defects in an insulating coating layer of a battery electrode sheet, wherein the method comprises the steps of: obtaining an electrode sheet image obtained by photographing an electrode sheet, wherein the electrode sheet image includes at least one complete electrode sheet; determining an insulating coating layer region and a tab region within the electrode sheet image; determining a defect detection region of the insulating coating layer region within the electrode sheet image according to the insulating coating layer region and the tab region; and performing defect detection on the defect detection region to obtain a defect detection result. The method realizes detection of the insulating coating of a composite electrode sheet and detects whether there is a defect in the insulating coating layer region, thereby enabling the timely removal of the defective electrode sheet, and has high detection accuracy and improves the execution efficiency of the stacking device.

Description

Technology Field

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

[0002] With the continuous advancement of science and technology, lithium-ion batteries have already been applied to electric vehicles and have become one of the primary power sources. The rapid development of the new energy vehicle industry has placed very high demands on lithium-ion batteries regarding safety, environmental protection, and performance during high-current charging and discharging. In large-scale production, the coating process in lithium-ion battery manufacturing is particularly important to enhance battery performance.

[0003] Conventional battery electrode sheet defect detection methods use two sets of contrasting image sensors to collect images, acquire the distance between the electrode sheet active material coating film and the electrode sheet edge, calculate the positional error amount of the coating film, and perform closed-loop control with a control system to adjust the coating film area until the positional error amount becomes smaller than the specification value. Conventional battery electrode sheet defect detection methods have the disadvantage of low detection accuracy.

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

[0005] In a first aspect, the present application provides a method for detecting defects in the insulating coating layer of a battery electrode sheet, and said method,

[0006] A step of obtaining an electrode sheet image obtained by photographing an electrode sheet, wherein the electrode sheet image includes at least one complete electrode sheet;

[0007] Step of determining the insulating coating layer region and the tab region within the electrode sheet image;

[0008] A step of determining a defect detection area in the insulating coating layer region within an electrode sheet image according to the insulating coating layer region and the tab region;

[0009] It includes the step of performing defect detection on a defect detection area to obtain a defect detection result.

[0010] In the above method for detecting defects in the insulating coating layer of a battery electrode sheet, an electrode sheet is photographed to obtain an electrode sheet image including at least one complete electrode sheet, and an insulating coating layer region and a tab region are determined within the electrode sheet image. Based on the insulating coating layer region and the tab region, a defect detection region within the insulating coating layer region of the electrode sheet image is determined. Finally, defect detection is performed on the defect detection region to obtain a defect detection result. The above method realizes detection of the insulating coating of a composite electrode sheet and detects whether there is a defect in the insulating coating layer region, thereby enabling the timely removal of the defective electrode sheet, high detection accuracy, and improved execution efficiency of the stacking device.

[0011] In one embodiment thereof, the step of determining an insulating coating layer region and a tab region within an electrode sheet image comprises: a step of obtaining an initial positioning electrode sheet edge by performing a full image edge search on the electrode sheet image; a step of determining an insulating coating layer region within the electrode sheet image by performing position recreation based on the initial positioning electrode sheet edge; and a step of determining a tab region within the electrode sheet image by searching through the insulating coating layer region. By performing a full image edge search and position recreation on the electrode sheet image to find an insulating coating layer region within the electrode sheet image, and finding a tab region within the electrode sheet image based on the determined insulating coating layer region, different regions of the electrode sheet image are found stepwise, and accurate and reliable detection is realized.

[0012] In one embodiment thereof, the step of obtaining an initial positioning electrode sheet edge by performing a full image edge search on an electrode sheet image includes the step of obtaining an initial positioning electrode sheet edge by performing a full image edge search on the electrode sheet image from one side far from the tab in a direction approaching the tab. By performing a full image edge search on the electrode sheet image from one side far from the tab in a direction approaching the tab, the initial positioning electrode sheet edge can be accurately found.

[0013] In one embodiment thereof, the step of obtaining an initial positioning electrode sheet edge by performing an overall image edge search on an electrode sheet image from one side far from the tab in a direction approaching the tab comprises: a step of performing an overall image edge search on an electrode sheet image from one side far from the tab in a direction approaching the tab; and a step of determining that the edge search was successful when a predetermined mutation edge is found, and determining the found predetermined mutation edge as the initial positioning electrode sheet edge. When performing an overall image edge search on an electrode sheet image from one side far from the tab in a direction approaching the tab, whether a predetermined mutation edge can be found is analyzed, and if a predetermined mutation edge is found, it is determined as the initial positioning electrode sheet edge, thereby further improving the accuracy of the edge search.

[0014] In one embodiment thereof, the step of determining an insulating coating layer region within an electrode sheet image by performing position recrystallization according to an initial positioning electrode sheet edge includes determining a target insulating coating layer region according to an initial positioning electrode sheet edge and extracting an insulating coating layer region within the electrode sheet image from the target insulating coating layer region. After determining the target insulating coating layer region according to the initial positioning electrode sheet edge, by extracting an insulating coating layer region within the electrode sheet image based on the target insulating coating layer region, the insulating coating layer region can be found simply and quickly.

[0015] In one embodiment thereof, the step of determining a tab region within an electrode sheet image by searching through an insulating coating layer region includes: a step of determining a target tab detection region by performing region location recrystallization according to the insulating coating layer region; and a step of searching for a tab extraction region in the target tab detection region. By combining the insulating coating layer region to perform region location recrystallization and determining the target tab detection region, and then searching for a tab region based on the target tab detection region, the tab region can likewise be found simply and quickly.

[0016] In one embodiment thereof, the step of determining a target tap detection area by performing area position recrystallization according to an insulating coating layer area includes: a step of extracting an initial positioning insulating edge of the insulating coating layer area; and a step of determining a target tap detection area according to the initial positioning insulating edge. By extracting an initial positioning insulating edge of the insulating coating layer area and selecting a target tap detection area by combining the initial positioning insulating edges, the target tap detection area can be determined quickly and accurately.

[0017] In one embodiment thereof, the step of searching for a tap extraction area in a target tap detection area comprises: a step of obtaining a preliminary tap area by extracting an area corresponding to a tap grayscale feature among the target tap detection areas; and a step of determining whether the preliminary tap area is a tap based on the area shape and area size of the preliminary tap area, and if it is a tap, determining that a tap area has been obtained. By determining a preliminary tap area by performing preliminary screening on the target tap detection area by combining tap grayscale features, and analyzing whether a tap area has been found by combining the area shape and area size of the preliminary tap area, the accuracy of the tap area search can be secured.

[0018] In one embodiment thereof, the step of determining a defect detection area of ​​an insulating coating layer region within an electrode sheet image according to an insulating coating layer region and a tab region comprises: a step of performing edge search on the tab region to obtain a tab edge; a step of obtaining an electrode sheet edge according to the tab edge and preset distance data, wherein the preset distance data is distance data between the tab edge and the electrode sheet edge; and a step of determining a defect detection area of ​​an insulating coating layer region within an electrode sheet image according to an initial positioned electrode sheet edge, an initial positioned insulating edge, and an electrode sheet edge. After the tab region is searched, the electrode sheet edge is determined by combining the tab edge and the preset distance data, and furthermore, according to the initial positioned electrode sheet edge, the initial positioned insulating edge, and the electrode sheet edge, a defect detection area of ​​an insulating coating layer region can be accurately found for subsequent defect detection.

[0019] In one embodiment thereof, the step of performing defect detection on a defect detection area to obtain a defect detection result comprises: a step of extracting a connection domain within the defect detection area; and a step of determining that a defect exists if a connection domain similar to a predetermined defect area exists; wherein the defect detection result includes information that a defect exists. Since the connection domain within the defect detection area is extracted and compared with a predetermined defect area, and the presence or absence of a defect in the defect detection area is analyzed, the detection is accurate and efficient.

[0020] In one embodiment thereof, the step of performing defect detection on a defect detection area to obtain a defect detection result further includes the step of calculating a positional error amount of the coating film area of ​​the electrode sheet if no connection domain similar to a predetermined defect area exists, wherein the defect detection result includes information that no defect exists and a positional error amount of the coating film area. If no defect exists in the defect detection area of ​​the insulating coating layer area, the positional error amount of the coating film area of ​​the electrode sheet is also calculated and used to analyze whether the size and width of the insulating coating layer areas on both sides of the electrode sheet match, thereby removing an electrode sheet of abnormal size and further improving the defect detection accuracy of the battery electrode sheet.

[0021] In one embodiment thereof, the electrode sheet image includes a first electrode sheet image and a second electrode sheet image obtained by photographing both sides of the electrode sheet; and the step of calculating the position error amount of the coating film region of the electrode sheet when no connection domain similar to a predetermined defect region exists is to calculate the position error amount of the coating film region of the electrode sheet when no connection domain similar to a predetermined defect region exists in the defect detection regions corresponding to the first electrode sheet image and the second electrode sheet image. By combining the electrode sheet images obtained by photographing both sides of the electrode sheet to detect whether a defect exists in the corresponding defect detection region, and calculating the position error amount of the coating film region of the electrode sheet when a defect exists in both defect detection regions of the two electrode sheet images, the defect detection accuracy of the electrode sheet insulating coating layer region is improved.

[0022] In one embodiment thereof, the electrode sheet image includes a first electrode sheet image and a second electrode sheet image obtained by photographing both sides of the electrode sheet; the step of calculating the position error amount of the coating film area of ​​the electrode sheet comprises: a step of performing an edge search on a defect detection area of ​​the insulating coating layer area within the first electrode sheet image to obtain a first electrode sheet virtual edge and a first insulating edge; a step of performing an edge search on a defect detection area of ​​the insulating coating layer area within the second electrode sheet image to obtain a second electrode sheet virtual edge and a second insulating edge; a step of calculating the width of the first insulating coating layer area according to the first electrode sheet virtual edge and the first insulating edge, and calculating the width of the second insulating coating layer area according to the second electrode sheet virtual edge and the second insulating edge; and a step of calculating the position error amount of the coating film area of ​​the electrode sheet according to the width of the first insulating coating layer area and the width of the second insulating coating layer area. Edge search is performed on the defect detection area of ​​the insulating coating layer region among two electrode sheet images to find the corresponding electrode sheet virtual edge and insulating edge, and furthermore, the width of the insulating coating layer region within the two electrode sheet images is calculated according to the electrode sheet virtual edge and insulating edge, and finally, the position error amount of the coating film region of the electrode sheet can be accurately calculated according to the width of the insulating coating layer region within the two electrode sheet images.

[0023] In one embodiment thereof, the method comprises the steps of: performing an edge search on a defect detection area of ​​an insulating coating layer region within a first electrode sheet image to obtain a first electrode sheet virtual edge and a first insulating edge; searching for an edge point of the defect detection area of ​​the insulating coating layer region within the first electrode sheet image; and performing fitting according to the searched edge point to obtain a first electrode sheet virtual edge and a first insulating edge. By searching for an edge point of the defect detection area of ​​the insulating coating layer region and combining the searched edge points to perform fitting to determine the electrode sheet virtual edge and the insulating edge, the success rate of searching for the electrode sheet virtual edge and the insulating edge is improved.

[0024] In one embodiment thereof, after the step of performing defect detection on a defect detection area and obtaining a defect detection result, the method further includes the step of binding the defect detection result with electrode sheet identifier information. By binding the defect detection result with the electrode sheet identifier information, the defect detection result is bound to a specific electrode sheet, thereby providing data support for operations such as the subsequent removal of the electrode sheet.

[0025] In a second aspect, the present application provides a device for detecting defects in the insulating coating layer of a battery electrode sheet, and said detection device,

[0026] An image acquisition module that acquires an electrode sheet image obtained by photographing an electrode sheet, wherein the electrode sheet image includes at least one complete electrode sheet;

[0027] Image analysis module for determining the insulating coating layer region and tab region within an electrode sheet image;

[0028] Region extraction module that determines a defect detection region of the insulating coating layer region within an electrode sheet image according to the insulating coating layer region and the tab region;

[0029] It includes a defect analysis module that performs defect detection on a defect detection area and obtains a defect detection result.

[0030] In a third aspect, the present application provides a computer device, said computer device includes memory and a processor, said computer program is stored in the memory, and when the processor executes the computer program, the steps of said method are implemented.

[0031] In a fourth aspect, the present application provides a computer-readable storage medium in which a computer program is stored, and a step of the method is implemented when the computer program is executed by a processor.

[0032] In a fifth aspect, the present application provides a computer program product comprising a computer program, and when the computer program is executed by a processor, the steps of the method are implemented.

[0033] In a sixth aspect, the present application provides a battery electrode sheet defect detection system, wherein the battery electrode sheet defect detection system comprises an image acquisition device and an upper device, the image acquisition device photographs an electrode sheet to acquire an electrode sheet image and transmits the electrode sheet image to an upper device, and the upper device performs detection of a defect in the insulating coating layer of the battery electrode sheet according to the above method.

[0034] Details of one or more embodiments of the present application are set forth in the drawings and description below. Other features, objects, and advantages of the present invention will become apparent from the specification, drawings, and claims. Brief explanation of the drawing

[0035] In order to more clearly explain the embodiments of the present application or the technical methods of the prior art, the drawings necessary for describing the embodiments or prior art are briefly introduced below. The drawings described below are merely some embodiments of the present application, and it is obvious that those skilled in the art can obtain other drawings based on these attached drawings without any creative labor. FIG. 1 is a flowchart of a method for detecting defects in a battery electrode sheet insulating coating layer according to one embodiment. FIG. 2 is a flowchart of the step of determining an insulating coating layer region and a tab region within an electrode sheet image according to one embodiment. FIG. 3 is a flowchart of the step of obtaining an initial positioning electrode sheet edge by performing a full image edge search on an electrode sheet image according to one embodiment, from one side far from the tab in a direction approaching the tab. FIG. 4 is a flowchart of the step of determining a tab region within an electrode sheet image by searching through an insulating coating layer region according to one embodiment. FIG. 5 is a flowchart of the step of determining a defect detection area of ​​an insulating coating layer region within an electrode sheet image according to an insulating coating layer region and a tab region according to one embodiment. FIG. 6 is a flowchart of the step of performing defect detection on a defect detection area according to one embodiment and obtaining a defect detection result. FIG. 7 is a flowchart of the step of calculating the position error amount of the coating film region of an electrode sheet according to one embodiment. FIG. 8 is a schematic diagram of the arrangement of a battery electrode sheet insulation coating layer defect detection hardware according to one embodiment. FIG. 9 is a schematic diagram of imaging of a camera according to one embodiment. FIG. 10 is a schematic diagram of a method for calculating a position error amount according to one embodiment. FIG. 11 is a structural block diagram of a battery electrode sheet insulation coating layer defect detection device according to one embodiment. FIG. 12 is an internal structure diagram of a computer device according to one embodiment. Specific details for implementing the invention

[0036] Hereinafter, embodiments of the technical solution of the present application will be described in detail with reference to the drawings. The following embodiments are intended only to more clearly explain the technical solution of the present application and shall not limit the scope of protection of the present application.

[0037] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by a person skilled in the art of this application; terms used herein are for the purpose of describing specific embodiments only and are not intended to limit this application; and terms “include” and “comprising” and any variations thereof in the specification, claims, and description of the drawings above are intended to include non-exclusive inclusions.

[0038] In the description of the embodiments of this application, technical terms such as “first,” “second,” etc. are intended only to distinguish different objects and should not be understood as indicating or implying relative importance, or implicitly indicating the quantity, specific order, or primary-second relationship of the indicated technical features. In the description of the embodiments of this application, unless otherwise explicitly and specifically limited, the meaning of “plural” is two or more.

[0039] The term "Examples" as used in this specification means that specific features, structures, or characteristics described in connection with an Example may be included in at least one Example of this Application. Where the word appears in each place in the specification, it does not necessarily mean the same Example, nor does it mean an independent or alternative Example excluded from other Examples. Those skilled in the art will understand, both explicitly and implicitly, that the Examples described in this specification may be combined with other Examples.

[0040] In the description of the embodiments of the present application, the term "and / or" is merely for describing the relationship between related objects and indicates that three relationships may exist; for example, A and / or B may represent three cases: A existing alone, B existing alone, and A and B coexisting. Additionally, in this specification, the letter " / " generally indicates that the objects related before and after are in an "or" relationship.

[0041] In the description of the embodiments of the present application, the term “multiple” refers to two or more (including two), likewise “multiple groups” refers to two or more groups (including two groups), and “multiple sheets” refers to two or more sheets (including two sheets).

[0042] In the description of the embodiments of the present application, the orientations or positional relationships indicated by technical terms such as "center," "longitudinal," "transverse," "length," "width," "thickness," "top," "bottom," "front," "back," "left," "right," "vertical," "horizontal," "top," "bottom," "inside," "outside," "clockwise," "counterclockwise," "axial," "longitudinal," "circular," etc., are based on the orientations or positional relationships illustrated in the accompanying drawings. This is merely for convenience to explain and simplify the embodiments of the present application, and does not imply or suggest that the device or element indicated necessarily has a specific orientation or is structured and operated in a specific orientation; therefore, this should not be understood as a limitation on the embodiments of the present application.

[0043] In the description of the embodiments of this application, unless otherwise explicitly defined and limited, technical terms such as “mounting,” “connecting,” “connecting,” “fixing,” etc., should be understood in a broad sense and, for example, may be a fixed connection, a detachable connection, or an integral connection; a mechanical connection, or an electrical connection; a direct connection, or an indirect connection through an intermediate medium; an internal connection between two elements, or an interactive relationship between two elements. A person skilled in the art can understand the specific meaning of the above terms in the embodiments of this application based on the specific circumstances.

[0044] With the advancement of science and technology and the continuous development of society, the application fields of power batteries are continuously expanding. They are applied not only to electric transportation means such as electric bicycles, electric motorcycles, and electric vehicles, but also to various fields such as military equipment and aerospace. Power batteries serve as a power source to supply power to tools; valve-sealed lead-acid batteries, open-tube lead-acid batteries, and lithium iron phosphate batteries are mainly used, possessing characteristics such as high energy, high output, and high energy density. Conventional battery electrode sheet defect detection involves collecting images using two opposing sets of image sensors, acquiring the distance between the electrode sheet active material coating film and the electrode sheet edge, calculating the positional error amount of the coating film, and adjusting the coating film area until the positional error amount becomes smaller than the specification value by performing closed-loop control with a control system. Conventional defect detection methods focus on detecting coating sections / die-cut sections throughout the entire process and include only coating section detection and detection of positional errors in coating film areas. Since detection is insufficient before the electrode sheet undergoes stacked cell manufacturing, damage during transport cannot be effectively controlled, and data cannot be accurately bound to specific electrode sheets and cells. Based on this, the present application provides a method for detecting defects in the insulating coating layer of a battery electrode sheet. This method involves photographing an electrode sheet to obtain an electrode sheet image containing at least one complete electrode sheet, determining an insulating coating layer area and a tab area within the electrode sheet image, and determining a defect detection area within the insulating coating layer area of ​​the electrode sheet image based on the insulating coating layer area and the tab area. Finally, defect detection is performed on the defect detection area to obtain a defect detection result.The above method enables detection of the insulation coating on the composite electrode sheet and can accurately detect whether there is a defect in the insulation coating layer area, whether there is a defect in the tab, and whether the size and width of the insulation coating layer area on both sides of the electrode sheet match. Therefore, the composite electrode detection can improve the operational efficiency of the device by integrating with the device to remove defective or abnormally sized electrode sheets in a timely manner.

[0045] The method for detecting defects in the insulating coating layer of a battery electrode sheet provided in this embodiment can be applied to the operation process of a battery production line device, such as a lamination, winding, or coating process, to detect defects in the insulating coating layer of the battery electrode sheet. Here, the insulating coating layer of the battery electrode sheet may specifically be a ceramic coating layer, an alumina coating layer, etc., and the ceramic coating layer may utilize silicon carbide ceramic or silicon nitride ceramic. Taking as an example the case where defect detection in the insulating coating layer of the battery electrode sheet is performed on the electrode sheet during the roll transfer process of a lamination device, cameras are installed on both sides of the electrode sheet supply belt at both the lower negative electrode camera station and the upper negative electrode camera station. The negative electrode sheet on the electrode sheet supply belt is photographed through the cameras on both sides to obtain an electrode sheet image. The electrode sheet image is processed to determine the insulating coating layer area and the tab area within the electrode sheet image, and based on the insulating coating layer area and the tab area, the defect detection area of ​​the insulating coating layer within the electrode sheet image can be determined. Finally, defect detection is performed on the defect detection area to obtain a defect detection result. Furthermore, defect detection includes the detection of positional error in the insulating coating layer area, defects, and tab defects, as well as data binding storage. It is possible to detect defects in one side tab of the cathode sheet insulating coating layer, defects in the insulating coating layer area, and their size prior to the cathode composite of the stacking device. To elaborate, the battery related to the embodiments of the present application may be used in electrical devices such as vehicles, ships, or aircraft, but is not limited thereto.

[0046] In one embodiment, a method for detecting defects in the insulating coating layer of a battery electrode sheet suitable for detecting defects in the insulating coating layer of a composite negative electrode sheet is provided. As illustrated in FIG. 1, the method comprises the following steps.

[0047] Step S100: An image of the electrode sheet obtained by photographing the electrode sheet is acquired.

[0048] The electrode sheet image includes at least one complete electrode sheet. Here, the complete electrode sheet includes one complete tab, extends to both sides by a certain range based on the tab, and the specific extended range value can be set according to the actual product size of the electrode sheet. Specifically, taking the example of defect detection on an electrode sheet on a stacking device, the electrode sheet being roll-transported in the stacking device is photographed through an image acquisition device to acquire an electrode sheet image including at least one complete electrode sheet, and then the electrode sheet image is transmitted to an upper device so that the upper device can subsequently perform image processing. Here, the image acquisition device may include a camera group, a sensor, and a controller. Taking an upper cathode camera station as an example, two cameras from the camera group are installed on both sides of the electrode sheet supply belt of the upper cathode camera station, and the controller determines that a tab has been detected based on the sensor judgment and triggers the camera to take a picture, or controls the camera to take pictures periodically based on the transport speed of the electrode sheet supply belt, and uploads the electrode sheet image captured by the camera to the upper device. In addition, a light source is installed for each camera to ensure ambient brightness, thereby enabling the camera to collect images more easily. Here, the controller may be a PLC (Programmable Logic Controller), an MCU (Micro Control Unit), etc., the camera may be a CCD (Charge Coupled Device) camera, and the sensor may be a photoelectric induction sensor. The upper device may be various personal computers, laptops, smartphones, tablet PCs, and portable wearable devices, but is not limited thereto, and the portable wearable device may be a smart watch, smart band, headset, etc.

[0049] Furthermore, prior to capturing the electrode sheet, both cameras can be jointly calibrated to generate a calibration model and the coordinates of the two cameras can be aligned to subsequently calculate the size of the front and back electrode sheet images, thereby ensuring that the positional error amount of the coating film area of ​​the electrode sheet can be accurately calculated. Additionally, after the camera captures the electrode sheet image, the controller can also upload the electrode sheet identifier information of the current electrode sheet to the upper device, allowing the upper device to bind and store the defect detection result with the electrode sheet identifier information.

[0050] Step S200: Determine the insulating coating layer area and the tab area within the electrode sheet image.

[0051] Here, the insulating coating layer region refers to the region where the insulating material coating layer is located in the electrode sheet image, and the tab region refers to the region where the tab is located in the electrode sheet image. Specifically, after acquiring the electrode sheet image, the upper device analyzes the image data of the electrode sheet image and performs image processing by combining the image data to search for the insulating coating layer region and the tab region within the acquired electrode sheet image. Here, the image data may specifically be grayscale values, and by combining the grayscale values ​​of each pixel point of the electrode sheet image, processing detection is performed on the electrode sheet image using methods such as grayscale difference values ​​and edge search to find the insulating coating layer region and the tab region within the electrode sheet image. The method by which the upper device performs processing detection on the electrode sheet image is not unique, and specifically, the image detection direction may be stored in advance in the upper device according to the arrangement method of the electrode sheet on the electrode sheet supply belt. For example, as illustrated in FIG. 9, when the active material coating layer area (103), insulating material coating layer area, and electrode sheet tab of the current electrode sheet are sequentially from right to left in the captured electrode sheet image, the upper device performs grayscale difference value and edge search detection on the electrode sheet image from right to left to sequentially find the insulating coating layer area (107) and tab area (104) within the electrode sheet image.

[0052] Step S300: Based on the insulating coating layer area and the tab area, determine the defect detection area of ​​the insulating coating layer area within the electrode sheet image.

[0053] Here, the defect detection area is the target area for performing defect detection on the insulating coating layer of the current electrode sheet. Specifically, the upper device searches for the insulating coating layer area and the tab area within the electrode sheet image, finds the image boundary between different electrode sheets based on the tab area, combines the insulating coating layer area and the electrode sheet image boundary to determine the defect detection area of ​​the insulating coating layer of the current electrode sheet within the electrode sheet image, and uses this as the target area for performing subsequent defect detection on the insulating coating layer of the current electrode sheet.

[0054] Step S400: A step of performing defect detection on a defect detection area to obtain a defect detection result; is included.

[0055] In response to this, after determining the defect detection area of ​​the insulating coating layer region of the current electrode sheet, the upper device combines pre-set defect area information to perform a defect search on the defect detection area, determines whether there is a defect matching the defect area information in the defect detection area, and further obtains a defect detection result regarding whether there is a defect in the insulating coating layer region of the current electrode sheet.

[0056] Additionally, in one embodiment, after step (S400), the method further includes the step of binding a defect detection result with electrode sheet identifier information. Specifically, the electrode sheet identifier information refers to information that can uniquely determine an electrode sheet, and the type of electrode sheet identifier information is not unique and may specifically be an electrode sheet number, an identifier code, etc. After the upper device binds the defect detection result with the electrode sheet identifier information, it may store it in a local database or transmit it to the controller of the image acquisition device. By binding the defect detection result with the electrode sheet identifier information, the defect detection result is bound to a specific electrode sheet, thereby providing data support for operations such as the subsequent removal of the electrode sheet.

[0057] In the above method for detecting defects in the insulating coating layer of a battery electrode sheet, an electrode sheet is photographed to obtain an electrode sheet image including at least one complete electrode sheet, and an insulating coating layer region and a tab region are determined within the electrode sheet image. Based on the insulating coating layer region and the tab region, a defect detection region of the insulating coating layer region within the electrode sheet image is determined. Finally, defect detection is performed on the defect detection region to obtain a defect detection result. The above method realizes detection of the insulating coating of a composite electrode sheet and detects whether there is a defect in the insulating coating layer region, thereby enabling timely removal of the defective electrode sheet, high detection accuracy, and improved execution efficiency of the stacking device.

[0058] In one embodiment, as shown in FIG. 2, step S200 includes steps S210 to S230.

[0059] Step S210: Perform a full image edge search on the electrode sheet image to obtain the initial positioning electrode sheet edge.

[0060] Specifically, the upper device combines the arrangement positions of different regions of the electrode sheet and performs a full image edge search on the electrode sheet image along the corresponding direction to find the initial positioning electrode sheet edge within the electrode sheet image. In one embodiment, step S210 includes the step of obtaining the initial positioning electrode sheet edge by performing a full image edge search on the electrode sheet image from one side far from the tab in a direction approaching the tab. As illustrated in FIG. 9, similarly, taking the example of the active material coating layer region (103), insulating material coating layer region, and electrode sheet tab of the current electrode sheet sequentially from right to left in the electrode sheet image, the upper device searches for the initial positioning electrode sheet edge (106) from right to left in the electrode sheet image through a full image edge search. By performing a full image edge search from one side far from the tab in the electrode sheet image in a direction approaching the tab, the initial positioning electrode sheet edge can be accurately searched.

[0061] Step S220: Position recreation is performed according to the initial positioning electrode sheet edge to determine the insulating coating layer area within the electrode sheet image. Accordingly, the upper device determines the initial positioning electrode sheet edge (106) within the electrode sheet image, and then, based on the initial positioning electrode sheet edge (106), continues to perform area position recreation in a direction approaching the tab to find the insulating coating layer area (107) within the electrode sheet image.

[0062] Step S230: A step of determining a tab region within an electrode sheet image by searching through an insulating coating layer region; the upper device finds an insulating coating layer region (107) within the electrode sheet image, and then searches continuously in a direction approaching the tab based on the insulating coating layer region (107) to find a tab region (104) within the electrode sheet image.

[0063] In the above embodiment, by performing a full image edge search and position recombination on the electrode sheet image to locate the insulating coating layer region within the electrode sheet image and locating the tab region within the electrode sheet image based on the determined insulating coating layer region, different regions of the electrode sheet image are located stepwise, and accurate and reliable detection is realized.

[0064] Furthermore, in one embodiment, as shown in FIG. 3, step S210, which involves searching for an entire image edge from one side far from the tab to a direction approaching the tab to obtain an initial positioning electrode sheet edge, includes steps S212 and S214.

[0065] Step S212: A full image edge search is performed on the electrode sheet image from one side far from the tab toward the tab. Correspondingly, for example, when a full image edge search is performed on the electrode sheet image from right to left, the upper device combines the grayscale values ​​of different pixel points of the electrode sheet image to search for the first predetermined mutated edge that has mutated from black to white from right to left. Here, N (the specific number can be set) search frames are placed at regular intervals on the electrode sheet image, the search frames extend from left to right of the image, and each search frame serves to detect one edge point. For each search frame, pixel points are traversed from right to left to search for a first edge point where the grayscale value changes to a set degree, and then a straight line fitting algorithm is used to determine whether the edge points searched by all search frames can be fitted into a single straight line, and whether the incline between the fitted straight line and the upper edge of the electrode sheet image is within a set range (e.g., between 85° and 95°). If a straight line is found in which the incline with the upper edge of the electrode sheet image is within the set range, it is considered that a predetermined mutant edge has been found.

[0066] Step S214: Includes the step of determining that the edge search was successful when a predetermined mutation edge is detected, and determining the detected predetermined mutation edge as the initial positioning electrode sheet edge. When a predetermined mutation edge is detected, the upper device determines that the edge search was successful and determines the detected predetermined mutation edge as the initial positioning electrode sheet edge.

[0067] In the above embodiment, when performing a full image edge search on an electrode sheet image from one side far from the tab toward the tab, it is analyzed whether a predetermined mutation edge can be searched, and if a predetermined mutation edge is found, it is identified as the initial positioning electrode sheet edge, thereby further improving the accuracy of the edge search.

[0068] In addition, in one embodiment, the method further includes the step of determining that the edge search was unsuccessful if a predetermined mutation edge is not found, and binding the electrode sheet edge search failure information with the electrode sheet identifier information. If the electrode sheet edge search is unsuccessful, there is no need to proceed with a subsequent region search operation, the detection of defects in the battery electrode sheet insulating coating layer is terminated, and the electrode sheet edge search failure information and the electrode sheet identifier information are bound and stored in a local database or transmitted to a controller.

[0069] In one embodiment, step S220 includes determining a target insulating coating layer region based on an initial positioning electrode sheet edge and extracting an insulating coating layer region within an electrode sheet image from the target insulating coating layer region.

[0070] Specifically, the upper device can store the size of the insulating coating layer area of ​​the electrode sheet in advance, and as shown in FIG. 9, after finding the initial positioning electrode sheet edge (106) within the electrode sheet image from right to left, the insulating coating layer area is repositioned to the left of the initial positioning electrode sheet edge (106), and a detection interest area larger than or equal to the size of the insulating coating layer area is determined to the left of the initial positioning electrode sheet edge and used as the target insulating coating layer area. Furthermore, the upper device performs area extraction based on the target insulating coating layer area, for example, by obtaining the insulating coating layer area (107) within the electrode sheet image through a Blob algorithm. Here, a Blob in computer vision refers to a connection domain of one of the images, and the Blob algorithm performs the extraction and notation of the connection domain for a binary image after separating the foreground and background of the image. The insulating coating layer area within the electrode sheet image can be extracted by analyzing the connection domain within the binary image.

[0071] In the above embodiment, after determining the target insulating coating layer region based on the initial positioning electrode sheet edge, the insulating coating layer region within the electrode sheet image is extracted based on the target insulating coating layer region, thereby allowing the insulating coating layer region to be found simply and quickly.

[0072] In one embodiment, as shown in FIG. 4, step S230 includes step S232 and step S234.

[0073] Step S232: Region position recombination is performed according to the insulating coating layer region to determine the target tab detection region. Here, the upper device determines the insulating coating layer region within the electrode sheet image, and then, based on the insulating coating layer region, continues to perform region position recombination in a direction approaching the tab to determine the target tab detection region.

[0074] In one embodiment, step S232 includes the step of extracting an initial positioning insulating edge of an insulating coating layer region; and the step of determining a target tap detection region based on the initial positioning insulating edge. Specifically, as illustrated in FIG. 9, the upper device searches for an insulating coating layer region (107) within an electrode sheet image and then positions the insulating coating layer region (107) close to an edge in the tap direction; specifically, the edge located at the far left of the insulating coating layer region (107) is used as the initial positioning insulating edge (105) of the insulating coating layer region (107). Furthermore, the upper device may store the tap size of the electrode sheet in advance, and reposition the location of the acquired initial positioning insulating edge (105) to determine a single tap detection frame that is larger than or equal to the tap size from the left of the initial positioning insulating edge (105) and use it as the target tap detection region. By extracting the initial positioning insulation edge of the ceramic coating layer region and combining the initial positioning insulation edge to select the target tap detection region, the target tap detection region can be determined quickly and accurately.

[0075] In addition, in one embodiment, if the method fails to extract an initial positioning insulation edge of the insulation coating layer region, it binds the edge search failure information for the insulation edge with the electrode sheet identifier information. If the edge search for the initial positioning insulation edge fails, likewise no subsequent operation is required, the battery electrode sheet insulation coating layer defect detection is terminated, and the edge search failure information for the insulation edge and the electrode sheet identifier information are bound and stored in a local database or transmitted to a controller.

[0076] Step S234: A step of searching for a tap extraction area within a target tap detection area; is included. After determining the target tap detection area, the upper device performs an analysis on the image within the target tap detection area to extract the tap area.

[0077] In one embodiment, step S234 includes: a step of obtaining a preliminary tap area by extracting an area that corresponds to a tap grayscale feature among the target tap detection areas; and a step of determining whether the preliminary tap area is a tap based on the area shape and area size of the preliminary tap area, and if it is a tap, determining that a tap area has been obtained. Specifically, the upper device performs binarization processing on an image within the target tap detection area and performs grayscale value analysis on the binarized image to extract an area that corresponds to a tap grayscale feature and use it as a preliminary tap area. Furthermore, the upper device analyzes the area shape and area size of the preliminary tap area by combining pre-set tap feature parameters to determine whether the preliminary tap area is a tap. If the preliminary tap area is a tap, the tap area (104) is searched. Here, the tap feature parameters may include parameters such as tap shape and size, and if the area shape and area size of the preliminary tap area are identical to the pre-set tap shape and size, or if the difference value is within a pre-set allowable range, the area shape and area size of the preliminary tap area are considered to match the tap feature parameters, and the preliminary tap area is determined to be a tap. By combining tap grayscale features to perform preliminary screening on the target tap detection area to determine a preliminary tap area, and by combining the area shape and area size of the preliminary tap area to analyze whether a tap area has been found, the accuracy of the tap area search can be secured.

[0078] In the above embodiment, by combining the insulating coating layer regions to perform region location recrystallization and determining the target tap detection region, and then searching for the tap region based on the target tap detection region, the tap region can likewise be found easily and quickly.

[0079] Additionally, in one embodiment, the method binds the tab member information and the electrode sheet identifier information when it is determined that the reserve tab area is not a tab. If no tab exists, likewise no subsequent action is required, the detection of defects in the battery electrode sheet insulating coating layer is terminated, and after binding the tab member information and the electrode sheet identifier information, the data is stored in a local database or transmitted to a controller.

[0080] In one embodiment, as illustrated in FIG. 5, step S300 includes steps S310 to S330.

[0081] Step S310: Edge search is performed on the tab area to obtain the tab edge. After the tab area is searched, the upper device performs edge search in a direction parallel to the initial positioning insulation edge in the tab area to search for the tab edge. For example, as illustrated in FIG. 9, the initial positioning electrode sheet edge (106) and the initial positioning insulation edge (105) are searched gradually from right to left on the electrode sheet image. In this case, the upper device performs edge search for the tab edge in the vertical direction from the tab area (104) using an edge search algorithm to find the upper edge (110) and lower edge (111) of the tab. Specifically, first, depending on the position of the tab area (104), two tab edge search frames are determined at the upper and lower edge positions of the tab area (104), and then pixel points are traversed in the vertical direction within each edge search frame to search for edge points where the change in grayscale value reaches a preset level, and when a single straight line is obtained by fitting multiple edge points found within the same edge search frame, the tab edge search within the edge search frame is successful.

[0082] Step S320: An electrode sheet edge is obtained according to the tab edge and preset distance data. Here, the preset distance data is distance data between the tab edge and the electrode sheet edge, and the specific value of the preset distance data can be set according to the distance between the electrode sheet edge and the tab edge in the actual product. Specifically, as shown in FIG. 9, the electrode sheet edge includes an electrode sheet upper edge (112) and an electrode sheet lower edge (113), and after the tab edge is found, the electrode sheet upper edge (112) can be found by applying the preset distance data to the position of the tab upper edge (110), and the electrode sheet lower edge (113) can be found by applying the preset distance data to the position of the tab lower edge (111).

[0083] Step S330: A step of determining a defect detection area of ​​an insulating coating layer region within an electrode sheet image according to an initial positioning electrode sheet edge, an initial positioning insulation edge, and an electrode sheet edge; is included. Accordingly, the upper device determines an initial positioning electrode sheet edge (106), an initial positioning insulation edge (105), an electrode sheet upper edge (112), and an electrode sheet lower edge (113), and then combines and fits the four edges to create a defect detection area of ​​an insulating coating layer region (107) of the current electrode sheet.

[0084] In the above embodiment, after the tab area is searched, the electrode sheet edge is determined by combining the tab edge and preset distance data, and furthermore, according to the initial positioning electrode sheet edge, the initial positioning insulation edge and the electrode sheet edge, the defect detection area of ​​the insulation coating layer area can be accurately found for subsequent defect detection.

[0085] In addition, in one embodiment, if the edge search of the tab area is not successful, the method binds the tab edge search failure information and the electrode sheet identifier information and outputs them. If the edge search of the tab area is not successful, likewise no subsequent operation is required, the detection of defects in the battery electrode sheet insulating coating layer is terminated, and the tab edge search failure information and the electrode sheet identifier information are bound and stored in a local database or transmitted to a controller.

[0086] In one embodiment, as shown in FIG. 6, step S400 includes step S410 and step S420.

[0087] Step S410: Extracts a connection domain within the defect detection area. Here, the connection domain refers to a set of adjacent pixel points within the defect detection area where all grayscale values ​​are within the same set range. After determining the defect detection area of ​​the insulating coating layer region of the current electrode sheet, the upper device similarly performs Blob algorithm processing on the defect detection area to obtain the connection domain within the binary image after processing.

[0088] Step S420: If a connection domain similar to a predetermined defect region exists, it is determined that a defect exists. The defect detection result includes information that a defect exists. In advance, corresponding predetermined defect region information is generated and stored in an upper device according to defects that may actually occur in the insulating coating layer region of the electrode sheet, wherein the predetermined defect region information may include information such as the location, shape, and size of the predetermined defect region, and the upper device combines the predetermined defect region information to analyze whether the connection domain of the defect detection region is similar to the predetermined defect region. For example, if the similarity between the connection domain of the defect detection region and the location, shape, and size of the predetermined defect region is all higher than a corresponding set threshold, it is considered that the connection domain and the predetermined defect region are similar, and furthermore, it is determined that a defect exists in the defect detection region.

[0089] In the above embodiment, the connection domain within the defect detection area is extracted and compared with a predetermined defect area, and the presence or absence of a defect in the defect detection area is analyzed, so the detection is accurate and efficient.

[0090] To elaborate, when detecting whether there is a defect in the insulating coating layer region of the current electrode sheet, two images of the electrode sheet are obtained by photographing the composite surface and the non-composite surface of the electrode sheet, respectively, through two cameras, and the two electrode sheet images are analyzed synchronously to determine the defect detection region of the insulating coating layer region within the two electrode sheet images. Furthermore, it is detected whether a connection domain similar to the predetermined defect region exists in the defect detection region within the two electrode sheet images. If no connection domain similar to the predetermined defect region exists in either of the defect detection regions within the two electrode sheet images, it is considered that there is no defect in the insulating coating layer region of the current electrode sheet. If a connection domain similar to the predetermined defect region is detected in the defect detection region of one or both electrode sheet images, it is considered that there is a defect in the insulating coating layer region of the current electrode sheet.

[0091] In other embodiments, the method first performs image analysis on one of the electrode sheet images through steps S100 to S400 to locate a defect detection area within the electrode sheet image and analyzes whether a connection domain similar to a predetermined defect area exists; if it does, it is considered that a defect exists in the insulating coating layer area of ​​the current electrode sheet, and there is no need to analyze other electrode sheet images; if it does not exist, it again performs steps S100 to S400 to locate a defect detection area within another electrode sheet image and analyzes whether a connection domain similar to a predetermined defect area exists. If a connection domain similar to a predetermined defect area does not exist in the defect detection area within the other electrode sheet image, it is considered that no defect exists in the insulating coating layer area of ​​the current electrode sheet; conversely, if it does, it is likewise considered that a defect exists in the insulating coating layer area of ​​the current electrode sheet. Additionally, if it is determined that a defect exists in the predetermined defect area, the upper device binds the information indicating the existence of the defect with the electrode sheet identifier information and stores it in a local database or transmits it to a controller.

[0092] Furthermore, in one embodiment, step S400 further includes step S430, which calculates the position error amount of the coating film area of ​​the electrode sheet if no connection domain similar to a predetermined defect area exists. The defect detection result includes information that no defect exists and the position error amount of the coating film area. Specifically, if no connection domain similar to a predetermined defect area exists in the defect detection area within two electrode sheet images of the current electrode sheet, it is considered that no defect exists in the insulating coating layer of the current electrode sheet, and the position error amount of the coating film area of ​​the current electrode sheet is calculated by combining the two electrode sheet images. Additionally, the upper device binds the information that no defect exists and the position error amount of the coating film area to the electrode sheet identifier information and stores it in a local database or transmits it to a controller.

[0093] In the above embodiment, if no defect exists in the defect detection area of ​​the insulating coating layer region, the positional error amount of the coating film region of the electrode sheet is also calculated and used to analyze whether the size and width of the insulating coating layer region on both sides of the electrode sheet match, thereby removing the electrode sheet of abnormal size and further improving the defect detection accuracy of the battery electrode sheet.

[0094] In one embodiment, the electrode sheet image includes a first electrode sheet image and a second electrode sheet image obtained by photographing both sides of the electrode sheet; step S430 calculates the position error amount of the coating film area of ​​the electrode sheet if no connection domain similar to a predetermined defect area exists in the defect detection areas corresponding to the first electrode sheet image and the second electrode sheet image. Here, the first electrode sheet image and the second electrode sheet image are electrode sheet images obtained by photographing the composite surface and non-composite surface of the current electrode sheet, respectively, and if no connection domain similar to a predetermined defect area exists in either of the defect detection areas within the two electrode sheet images, the upper device determines that no defect exists in the insulating coating layer of the current electrode sheet and calculates the position error amount of the coating film area of ​​the electrode sheet. By combining the electrode sheet images obtained by photographing both sides of the electrode sheet to detect whether a defect exists in the corresponding defect detection area, and if a defect exists in both defect detection areas of the two electrode sheet images, the position error amount of the coating film area of ​​the electrode sheet is calculated, thereby improving the defect detection accuracy of the insulating coating layer area of ​​the electrode sheet.

[0095] Furthermore, in one embodiment, the electrode sheet image includes a first electrode sheet image and a second electrode sheet image obtained by photographing both sides of the electrode sheet; and as shown in FIG. 7, the step S430 of calculating the position error amount of the coating film area of ​​the electrode sheet includes steps S432 to S438.

[0096] Step S432: An edge search is performed on a defect detection area of ​​an insulating coating layer region within a first electrode sheet image to obtain a first electrode sheet virtual edge and a first insulating edge. Specifically, a defect detection area of ​​an insulating coating layer region within a first electrode sheet image is determined, and if it is determined that there is no connection domain similar to a predetermined defect region in the defect detection area, an edge search is performed on the defect detection area to find a first electrode sheet virtual edge and a first insulating edge within the first electrode sheet image.

[0097] In one embodiment, step S432 includes: searching for edge points of a defect detection area of ​​an insulating coating layer region within a first electrode sheet image; and performing fitting according to the searched edge points to obtain a first electrode sheet virtual edge and a first insulating edge. Specifically, based on the defect detection area of ​​an insulating coating layer region within a first electrode sheet image of a current electrode sheet, an edge search frame for an insulating edge of a current electrode sheet and an edge search frame for an electrode sheet virtual edge are determined according to an initial positioned electrode sheet edge, an initial positioned insulating edge, an upper electrode sheet edge, and a lower electrode sheet edge. Then, edge search is performed through an edge search algorithm within each edge search frame for an insulating edge and an edge search frame for an electrode sheet virtual edge to find edge points within the two edge search frames, and further, the edge points within each edge search frame are fitted to obtain the corresponding first electrode sheet virtual edge and the first insulating edge. By searching for edge points in the defect detection area of ​​the insulating coating layer area and combining the searched edge points to perform fitting, thereby determining the electrode sheet virtual edge and insulating edge, the success rate of searching for the electrode sheet virtual edge and insulating edge is improved.

[0098] Furthermore, after searching for edge points in the defect detection area of ​​the insulating coating layer region within the first electrode sheet image, the method further includes a step of filtering and removing edge points, filtering and removing abnormal edge points, and then fitting the remaining edge points after filtering and removing to obtain the corresponding first electrode sheet virtual edge and first insulating edge. Here, the method of filtering and removing edge points is not unique, and specifically, it may be filtering and removing edge points through a fitting algorithm, such as filtering and removing abnormal edge points using a weighted least squares method by combining the positions of each edge point.

[0099] Step S434: An edge search is performed on the defect detection area of ​​the insulating coating layer region within the second electrode sheet image to obtain the second electrode sheet virtual edge and the second insulating edge. It can be understood that the method of performing an edge search on the defect detection area of ​​the insulating coating layer region within the second electrode sheet image to obtain the second electrode sheet virtual edge and the second insulating edge is similar to Step S432, so it is not described further here.

[0100] Step S436: Calculate the width of the first insulating coating layer area based on the first electrode sheet virtual edge and the first insulating edge, and calculate the width of the second insulating coating layer area based on the second electrode sheet virtual edge and the second insulating edge. After finding the first electrode sheet virtual edge and the first insulating edge within the first electrode sheet image, and the second electrode sheet virtual edge and the second insulating edge within the second electrode sheet image, the upper device calculates the distance between the first electrode sheet virtual edge and the first insulating edge to obtain the width of the insulating coating layer area within the first electrode sheet image, i.e., the width of the first insulating coating layer area. The upper device also calculates the distance between the second electrode sheet virtual edge and the second insulating edge to obtain the width of the insulating coating layer area within the second electrode sheet image, i.e., the width of the second insulating coating layer area.

[0101] Step S438: A step of calculating the positional error amount of the coating film area of ​​the electrode sheet according to the width of the first insulating coating layer area and the width of the second insulating coating layer area; is included. Accordingly, the upper device subtracts the width of the first insulating coating layer area and the width of the second insulating coating layer area to obtain a difference value, and considers this as the positional error amount of the coating film area of ​​the current electrode sheet.

[0102] In the above embodiment, edge search is performed on the defect detection area of ​​the insulating coating layer area among the two electrode sheet images to find the corresponding electrode sheet virtual edge and insulating edge, and furthermore, the width of the insulating coating layer area within the two electrode sheet images is calculated according to the electrode sheet virtual edge and insulating edge, and finally, the position error amount of the coating film area of ​​the electrode sheet can be accurately calculated according to the width of the insulating coating layer area within the two electrode sheet images.

[0103] In addition, in one embodiment, the method further includes the step of binding edge point search failure information and electrode sheet identifier information and outputting them if no edge point is found. If the edge point search for a defect detection area within the first electrode sheet image or the second electrode sheet image is unsuccessful, likewise no subsequent operation is required, the battery electrode sheet insulating coating layer defect detection is terminated, and the edge point search failure information and electrode sheet identifier information are bound and stored in a local database or transmitted to a controller.

[0104] To better understand the method for detecting defects in the insulating coating layer of the battery electrode sheet described above, specific embodiments are described in detail below.

[0105] Regarding the problem that conventional battery electrode sheet defect detection includes only coating section detection and coating film area position error detection, but does not include insulation coating layer defect detection and cannot bind data to specific electrode sheets during coating process detection, the present application provides an online method for detecting size defects in the insulation coating layer of a composite pre-cathode sheet with a continuous anode stacking. By using a high-efficiency, high-precision vision algorithm to detect the insulation coating layer of the composite pre-cathode sheet, it is possible to accurately detect whether there is a defect in the insulation coating layer area, whether there is a defect in the tab, and whether the size and width of the insulation coating layer area on both sides of the cathode sheet match. The composite pre-detection can be linked with a device to remove electrode sheets with defects or abnormal sizes in a timely manner, thereby improving the operational efficiency of the device and reducing the risk of missing removal. Specifically, FIG. 8 is a schematic diagram of the hardware arrangement for insulation coating layer defect detection. High-frame-rate array cameras are installed on each side of the cathode supply belt, and white bar-shaped light sources are installed on each side to irradiate light onto the insulation coating layer area from the side. Here, A101 is a cathode supply belt, A102 is detection camera 1, A103 is a light source corresponding to detection camera 1, A104 is detection camera 2, and A105 is a light source corresponding to detection camera 2. An insulating coating layer area is photographed by one camera on each side of the electrode sheet supply belt, and both cameras are jointly calibrated to create a calibration model. The PLC detects a tab and triggers the camera to photograph, providing a unique identifier code of the current electrode sheet. Using vision software of an upper device, processing detection is performed on the image using means such as grayscale difference values ​​and edge detection, thereby implementing positional error, defect, and tab defect detection of the insulating coating layer area and data binding storage.

[0106] FIG. 9 shows an imaging schematic diagram of a camera according to an embodiment, and the names of each region are as follows: 101: Previous cathode sheet; 102: Next cathode sheet; 103: Current cathode sheet active material coating layer region; 104: Current cathode sheet tab, i.e., tab region; 105: Initial positioning insulation edge, i.e., outer edge of the insulation material coating layer region; 106: Cathode virtual edge / initial positioning electrode sheet edge, i.e., boundary edge between the cathode sheet active material coating layer region and the insulation material coating layer region; 107: Insulation material coating layer region, i.e., insulation coating layer region; 108: Offset between the tab upper edge and the current electrode sheet upper edge; 109: Offset between the tab lower edge and the current electrode sheet lower edge; in step (110), the tab upper edge; 111: Tab lower edge; 112: Electrode sheet upper edge; 113: Electrode sheet lower edge.

[0107] FIG. 10 is a schematic diagram of a method for calculating a positional error amount, wherein side A is a non-composite surface of the electrode sheet and side B is a composite surface of the electrode sheet. The defect detection items of the defect detection method include detection of a 106-area leakage metal breakage defect, detection of a 106-area width, a positional error amount of a 106-area width AB surface, and detection of a 104-area tab loss.

[0108] The above defect detection method determines the edge and insulating coating layer regions of the electrode sheet to accurately reposition the detection area, accurately positions the detection frame in the corresponding area requiring detection, performs detection through edge search, size measurement, and defect detection algorithms, and outputs the defect detection result. In the stacking device, the detection of the insulating coating layer can control damage to the insulating coating layer during the roll transfer process, and can provide electrode sheet information to the device to provide data support for operations such as subsequent removal; and can bind and store a unique number to each electrode sheet so that the data of the insulating coating layer of each electrode sheet can be traceable. The above detection method has high detection accuracy, pixel accuracy can reach 0.02 mm, detection efficiency is fast, and the single detection time is less than 20 ms.

[0109] It should be understood that although the steps of the flowcharts associated with each of the above embodiments are shown sequentially according to the direction of the arrows, these steps are not necessarily performed in the order indicated by the arrows. The execution of these steps may be performed in a different order unless explicitly specified herein, and there are no strict restrictions on the order. Furthermore, at least some of the steps of the flowcharts associated with each of the above embodiments may include multiple steps or multiple sections, and these steps or sections may not necessarily be executed at the same time but may be executed at different times, and the execution order of these steps or sections may not necessarily be sequential but may be alternated with other steps or at least some of the steps or sections within other steps.

[0110] Based on the same inventive concept, embodiments of the present application also provide a battery electrode sheet insulating coating layer defect detection device for implementing the method for detecting defects in the battery electrode sheet insulating coating layer. Since the means for solving the problem provided by the device are similar to the means described in the method, specific limitations of one or more embodiments of the battery electrode sheet insulating coating layer defect detection device provided below may refer to the limitations on the method for detecting defects in the battery electrode sheet insulating coating layer and are not described redundantly herein.

[0111] In one embodiment, a battery electrode sheet insulation coating layer defect detection device suitable for detecting insulation coating layer defects for a composite negative electrode sheet is provided. As illustrated in FIG. 11, the device comprises an image acquisition module (100), an image analysis module (200), a region extraction module (300), and a defect analysis module (400), wherein,

[0112] The image acquisition module (100) acquires an electrode sheet image obtained by photographing an electrode sheet, wherein the electrode sheet image includes at least one complete electrode sheet.

[0113] The image analysis module (200) determines the insulating coating layer area and the tab area within the electrode sheet image.

[0114] The region extraction module (300) determines the defect detection region of the insulating coating layer region within the electrode sheet image according to the insulating coating layer region and the tab region.

[0115] The defect analysis module (400) performs defect detection on the defect detection area and obtains a defect detection result.

[0116] In one embodiment, the image analysis module (200) performs a full image edge search on an electrode sheet image to obtain an initial positioning electrode sheet edge; performs position recreation according to the initial positioning electrode sheet edge to determine an insulating coating layer region within the electrode sheet image; and determines a tab region within the electrode sheet image by searching through the insulating coating layer region.

[0117] In one embodiment, the image analysis module (200) performs a full image edge search for the electrode sheet image from one side far from the tab toward the tab to obtain an initial positioning electrode sheet edge.

[0118] In one embodiment, the image analysis module (200) performs a full image edge search on the electrode sheet image from one side far from the tab toward the tab; if a predetermined mutation edge is found, it determines that the edge search was successful and includes the step of determining the found predetermined mutation edge as the initial positioning electrode sheet edge.

[0119] In one embodiment, the image analysis module (200) determines a target insulating coating layer region based on the initial positioning electrode sheet edge and extracts an insulating coating layer region within the electrode sheet image from the target insulating coating layer region.

[0120] In one embodiment, the image analysis module (200) performs region location recrystallization according to the insulating coating layer region to determine the target tap detection region; and includes the step of searching for a tap extraction region in the target tap detection region.

[0121] In one embodiment, the image analysis module (200) includes the step of extracting an initial positioning insulation edge of an insulating coating layer region; and determining a target tab detection region according to the initial positioning insulation edge.

[0122] In one embodiment, the image analysis module (200) extracts an area corresponding to a tap grayscale feature among the target tap detection areas to obtain a preliminary tap area; determines whether the preliminary tap area is a tap based on the area shape and area size of the preliminary tap area, and if it is a tap, determines that a tap area has been obtained.

[0123] In one embodiment, the region extraction module (300) performs an edge search on the tab region to obtain a tab edge. Based on the tab edge and preset distance data, an electrode sheet edge is obtained, wherein the preset distance data is distance data between the tab edge and the electrode sheet edge; based on the initial positioning electrode sheet edge, the initial positioning insulation edge, and the electrode sheet edge, a defect detection region of the insulation coating layer region within the electrode sheet image is determined.

[0124] In one embodiment, the defect analysis module (400) includes the step of extracting a connection domain within a defect detection area; and determining that a defect exists if a connection domain similar to a predetermined defect area exists, wherein the defect detection result includes information that a defect exists.

[0125] In one embodiment, the defect analysis module (400) also calculates the position error amount of the coating film region of the electrode sheet if there is no connection domain similar to a predetermined defect region; and the defect detection result includes information that no defect exists and the position error amount of the coating film region.

[0126] In one embodiment, the electrode sheet image includes a first electrode sheet image and a second electrode sheet image obtained by photographing both sides of the electrode sheet; and the defect analysis module (400) calculates the position error amount of the coating film area of ​​the electrode sheet if there are no connection domains similar to a predetermined defect area in the defect detection area corresponding to the first electrode sheet image and the second electrode sheet image.

[0127] In one embodiment, the electrode sheet image includes a first electrode sheet image and a second electrode sheet image obtained by photographing both sides of the electrode sheet; the defect analysis module (400) performs an edge search on a defect detection area of ​​an insulating coating layer area within the first electrode sheet image to obtain a first electrode sheet virtual edge and a first insulating edge; performs an edge search on a defect detection area of ​​an insulating coating layer area within the second electrode sheet image to obtain a second electrode sheet virtual edge and a second insulating edge; calculates the width of the first insulating coating layer area according to the first electrode sheet virtual edge and the first insulating edge, and calculates the width of the second insulating coating layer area according to the second electrode sheet virtual edge and the second insulating edge; and calculates the position error amount of the coating film area of ​​the electrode sheet according to the width of the first insulating coating layer area and the width of the second insulating coating layer area.

[0128] In one embodiment, the defect analysis module (400) searches for edge points of a defect detection area in an insulating coating layer area within a first electrode sheet image. It includes the step of performing fitting according to the searched edge points to obtain a first electrode sheet virtual edge and a first insulating edge.

[0129] In one embodiment, the defect analysis module (400) also binds the defect detection result and the electrode sheet identifier information.

[0130] In one embodiment, a computer device is provided, which may be a server or a terminal; taking the case where it is a server as an example, its internal structure may be as illustrated in FIG. 12. The computer device includes a processor, memory, and a network interface connected via a system bus. Here, the processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. An operating system, a computer program, and a database are stored in the non-volatile storage medium. The internal memory provides an environment for executing the execution system and the computer program within the non-volatile storage medium. The database of the computer device stores defect detection result data. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for detecting defects in the insulating coating layer of a battery electrode sheet is implemented.

[0131] A person skilled in the art will understand that the structure illustrated in FIG. 12 is a block diagram of some structure related to the means of the present application and does not constitute a limitation on the computer device to which the means of the present application apply, and that the specific computer device may include more or fewer components than illustrated in the drawing, combine some components, or have a different arrangement of components.

[0132] In one embodiment, a computer device is provided, which includes memory and a processor, a computer program is stored in the memory, and when the processor executes the computer program, the steps of each method embodiment are implemented.

[0133] In one embodiment, a computer-readable storage medium is provided in which a computer program is stored, and when the computer program is executed by a processor, the steps of each method embodiment are implemented.

[0134] In one embodiment, a computer program product including a computer program is provided, and when the computer program is executed by a processor, the steps of each method embodiment are implemented.

[0135] In one embodiment, a battery electrode sheet defect detection system is provided, comprising an image acquisition device and an upper device, wherein the image acquisition device captures an electrode sheet to acquire an electrode sheet image and transmits the electrode sheet image to the upper device, and the upper device performs the detection of defects in the insulating coating layer of the battery electrode sheet according to the above method. Here, the image acquisition device specifically includes a camera group, a sensor, and a controller, and the controller connects the camera group, the sensor, and the upper device. The controller may be a PLC, an MCU, etc., the camera group may be a CCD camera group, the sensor may use a photoelectric induction sensor, and the upper device may be various personal computers, laptops, smartphones, tablet PCs, and portable wearable devices, but is not limited thereto, and the portable wearable device may be a smart watch, a smart band, a headset, etc.

[0136] A person of ordinary knowledge in the relevant field will understand that the implementation of all or part of the process of the method of the above-mentioned embodiment may be completed by directing the relevant hardware through a computer program, said computer program may be stored on a computer-readable storage medium, and that the execution of said program may include a process such as that of the embodiment of each of the above-mentioned method. Here, said storage medium may be a non-volatile storage medium such as a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0137] Each technical feature of the above embodiments may be combined arbitrarily, and for the sake of simplicity of description, not all possible combinations of each technical feature of the above embodiments have been described; however, as long as such combinations of technical features are not contradictory, they should be considered within the scope described herein.

[0138] The above embodiments represent only some embodiments of the present invention, and while the description is specific and detailed, it should not be understood as a limitation on the scope of the patent. It should be noted that a person skilled in the art can make various modifications and improvements without departing from the spirit of the present invention, and all of these fall within the scope of protection of the present invention. Accordingly, the scope of protection of the present invention should be based on the appended claims.

Claims

Claim 1 A method for detecting defects in the insulating coating layer of a battery electrode sheet comprises: a step of obtaining an electrode sheet image obtained by photographing an electrode sheet, wherein the electrode sheet image includes at least one complete electrode sheet; a step of determining an insulating coating layer region and a tab region within the electrode sheet image; a step of determining a defect detection region of the insulating coating layer region within the electrode sheet image according to the insulating coating layer region and the tab region; a step of performing defect detection on the defect detection region and obtaining a defect detection result, wherein the step of performing defect detection on the defect detection region and obtaining a defect detection result comprises: a step of extracting a connection domain within the defect detection region; a step of determining that a defect exists if the connection domain similar to a predetermined defect region exists, wherein the defect detection result includes information that a defect exists; and a step of calculating a positional error amount of the coating film region of the electrode sheet if the connection domain similar to the predetermined defect region does not exist, wherein the defect detection result includes information that no defect exists and the positional error amount of the coating film region. A method for detecting defects in an insulating coating layer of a battery electrode sheet, comprising: a connection domain which refers to a set of adjacent pixel points in which all grayscale values ​​in the defect detection area are within the same set range; and a predetermined defect area which is corresponding information generated in advance according to a defect that may actually occur in the insulating coating layer area of ​​the electrode sheet. Claim 2 A method for detecting defects in an insulating coating layer of a battery electrode sheet according to claim 1, wherein the step of determining an insulating coating layer region and a tab region within the electrode sheet image comprises: a step of performing a full image edge search on the electrode sheet image to obtain an initial positioning electrode sheet edge; a step of performing position recreation according to the initial positioning electrode sheet edge to determine an insulating coating layer region within the electrode sheet image; and a step of determining a tab region within the electrode sheet image by searching through the insulating coating layer region. Claim 3 A method for detecting defects in a battery electrode sheet insulating coating layer according to claim 2, wherein the step of obtaining an initial positioning electrode sheet edge by performing a full image edge search on the electrode sheet image comprises the step of obtaining the initial positioning electrode sheet edge by performing a full image edge search on the electrode sheet image from one side far from the tab in a direction approaching the tab. Claim 4 A method for detecting defects in a battery electrode sheet insulating coating layer according to claim 3, wherein the step of obtaining the initial positioning electrode sheet edge by performing a full image edge search on the electrode sheet image from one side far from the tab in a direction approaching the tab comprises: a step of performing a full image edge search on the electrode sheet image from one side far from the tab in a direction approaching the tab; and a step of determining that the edge search was successful when a predetermined mutation edge is found, and determining the found predetermined mutation edge as the initial positioning electrode sheet edge. Claim 5 A method for detecting defects in a battery electrode sheet insulating coating layer according to claim 2, wherein the step of determining an insulating coating layer region within the electrode sheet image by performing position recreation according to the initial positioning electrode sheet edge comprises the step of determining a target insulating coating layer region according to the initial positioning electrode sheet edge and extracting an insulating coating layer region within the electrode sheet image from the target insulating coating layer region. Claim 6 A method for detecting defects in a battery electrode sheet insulating coating layer according to claim 2, wherein the step of determining a tab region within the electrode sheet image by searching through the insulating coating layer region comprises: a step of determining a target tab detection region by proceeding with region location recrystallization according to the insulating coating layer region; and a step of searching for a tab extraction region in the target tab detection region. Claim 7 A method for detecting defects in a battery electrode sheet insulating coating layer according to claim 6, wherein the step of determining a target tab detection area by performing area position recreation according to the insulating coating layer area comprises: a step of extracting an initial positioning insulating edge of the insulating coating layer area; and a step of determining a target tab detection area according to the initial positioning insulating edge. Claim 8 A method for detecting defects in an insulating coating layer of a battery electrode sheet according to claim 6, wherein the step of searching for a tap extraction area in the target tap detection area comprises: a step of obtaining a preliminary tap area by extracting an area corresponding to a tap grayscale feature among the target tap detection areas; and a step of determining whether the preliminary tap area is a tap based on the shape and size of the area of ​​the preliminary tap area, and if it is a tap, determining that a tap area has been obtained. Claim 9 A method for detecting defects in an insulating coating layer of a battery electrode sheet according to claim 7, wherein the step of determining a defect detection area of ​​an insulating coating layer region within an electrode sheet image according to the insulating coating layer region and the tab region comprises: a step of performing an edge search on the tab region to obtain a tab edge; a step of obtaining an electrode sheet edge according to the tab edge and preset distance data, wherein the preset distance data is distance data between the tab edge and the electrode sheet edge; and a step of determining a defect detection area of ​​an insulating coating layer region within an electrode sheet image according to the initial positioning electrode sheet edge, the initial positioning insulating edge, and the electrode sheet edge. Claim 10 A method for detecting defects in an insulating coating layer of a battery electrode sheet according to claim 1, wherein the electrode sheet image includes a first electrode sheet image and a second electrode sheet image obtained by photographing both sides of the electrode sheet; and wherein the step of calculating the position error amount of the coating film region of the electrode sheet when the connection domain similar to the predetermined defect region does not exist includes the step of calculating the position error amount of the coating film region of the electrode sheet when the connection domain similar to the predetermined defect region does not exist in the defect detection region corresponding to the first electrode sheet image and the second electrode sheet image. Claim 11 A method for detecting defects in an insulating coating layer of a battery electrode sheet according to claim 1, wherein the electrode sheet image includes a first electrode sheet image and a second electrode sheet image obtained by photographing both sides of the electrode sheet; and the step of calculating the positional error amount of the coating film area of ​​the electrode sheet comprises: a step of performing an edge search on a defect detection area of ​​the insulating coating layer area within the first electrode sheet image to obtain a first electrode sheet virtual edge and a first insulating edge; a step of performing an edge search on a defect detection area of ​​the insulating coating layer area within the second electrode sheet image to obtain a second electrode sheet virtual edge and a second insulating edge; a step of calculating the width of the first insulating coating layer area according to the first electrode sheet virtual edge and the first insulating edge, and calculating the width of the second insulating coating layer area according to the second electrode sheet virtual edge and the second insulating edge; and a step of calculating the positional error amount of the coating film area of ​​the electrode sheet according to the width of the first insulating coating layer area and the width of the second insulating coating layer area. Claim 12 A method for detecting defects in an insulating coating layer of a battery electrode sheet according to claim 11, wherein the step of performing an edge search on a defect detection area of ​​an insulating coating layer region within the first electrode sheet image to obtain a first electrode sheet virtual edge and a first insulating edge comprises: a step of searching for an edge point of a defect detection area of ​​an insulating coating layer region within the first electrode sheet image; and a step of performing fitting according to the searched edge point to obtain the first electrode sheet virtual edge and the first insulating edge. Claim 13 A method for detecting defects in a battery electrode sheet insulating coating layer, characterized in that, in the first aspect, after the step of performing defect detection on the defect detection area and obtaining a defect detection result, the method further comprises the step of binding the defect detection result with electrode sheet identifier information. Claim 14 A device for detecting defects in the insulating coating layer of a battery electrode sheet comprises: an image acquisition module that acquires an electrode sheet image obtained by photographing an electrode sheet, wherein the electrode sheet image includes at least one complete electrode sheet; an image analysis module that determines an insulating coating layer region and a tab region within the electrode sheet image; a region extraction module that determines a defect detection region of the insulating coating layer region within the electrode sheet image according to the insulating coating layer region and the tab region; and a defect analysis module that performs defect detection on the defect detection region and obtains a defect detection result. Performing defect detection on the defect detection region and obtaining a defect detection result comprises: extracting a connection domain within the defect detection region; determining that a defect exists if the connection domain similar to a predetermined defect region exists, wherein the defect detection result includes information that a defect exists; and calculating a positional error amount of the coating film region of the electrode sheet if the connection domain similar to the predetermined defect region does not exist, wherein the defect detection result includes information that no defect exists and the positional error amount of the coating film region. A battery electrode sheet insulating coating layer defect detection device comprising, wherein the connection domain refers to a set of adjacent pixel points in the defect detection area where all grayscale values ​​are within the same set range, and the predetermined defect area is corresponding information generated in advance according to a defect that may actually occur in the insulating coating layer area of ​​the electrode sheet. Claim 15 A computer device comprising a memory and a processor, wherein the memory has a computer program stored therein, and when the processor executes the computer program, a step of the method according to any one of claims 1 to 13 is implemented. Claim 16 A computer-readable storage medium having a computer program stored therein, characterized in that when the computer program is executed by a processor, a step of the method according to any one of claims 1 to 13 is implemented. Claim 17 A computer program stored on a computer-readable storage medium, wherein when the computer program is executed by a processor, a step of the method according to any one of claims 1 to 13 is implemented. Claim 18 A battery electrode sheet defect detection system comprising an image acquisition device and a higher device, wherein the image acquisition device photographs an electrode sheet to acquire an electrode sheet image and transmits the electrode sheet image to the higher device, and the higher device performs the detection of a defect in the insulating coating layer of the battery electrode sheet according to a method according to any one of claims 1 to 13. Claim 19 delete Claim 20 delete

Images