WO2023193213A1 - 电池极片绝缘涂层缺陷的检测方法、装置和计算机设备 - Google Patents

电池极片绝缘涂层缺陷的检测方法、装置和计算机设备 Download PDF

Info

Publication number
WO2023193213A1
WO2023193213A1 PCT/CN2022/085690 CN2022085690W WO2023193213A1 WO 2023193213 A1 WO2023193213 A1 WO 2023193213A1 CN 2022085690 W CN2022085690 W CN 2022085690W WO 2023193213 A1 WO2023193213 A1 WO 2023193213A1
Authority
WO
WIPO (PCT)
Prior art keywords
pole piece
area
edge
insulating coating
image
Prior art date
Application number
PCT/CN2022/085690
Other languages
English (en)
French (fr)
Inventor
赵柏全
倪大军
胡军
谢险峰
常文
Original Assignee
宁德时代新能源科技股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 宁德时代新能源科技股份有限公司 filed Critical 宁德时代新能源科技股份有限公司
Priority to PCT/CN2022/085690 priority Critical patent/WO2023193213A1/zh
Priority to EP22936156.3A priority patent/EP4383398A1/en
Priority to KR1020247011254A priority patent/KR20240050461A/ko
Priority to CN202280032976.XA priority patent/CN117280513A/zh
Publication of WO2023193213A1 publication Critical patent/WO2023193213A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H01—ELECTRIC ELEMENTS
    • H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
    • H01M10/00—Secondary cells; Manufacture thereof
    • H01M10/04—Construction or manufacture in general
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
    • G01B11/028—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness by measuring lateral position of a boundary of the object
    • H—ELECTRICITY
    • H01—ELECTRIC ELEMENTS
    • H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
    • H01M10/00—Secondary cells; Manufacture thereof
    • H01M10/05—Accumulators with non-aqueous electrolyte
    • H01M10/058—Construction or manufacture
    • H—ELECTRICITY
    • H01—ELECTRIC ELEMENTS
    • H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
    • H01M4/00—Electrodes
    • H01M4/02—Electrodes composed of, or comprising, active material
    • H01M4/04—Processes of manufacture in general
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8854—Grading and classifying of flaws
    • G01N2021/8858—Flaw counting
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8854—Grading and classifying of flaws
    • G01N2021/8861—Determining coordinates of flaws
    • G01N2021/8864—Mapping zones of defects
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
    • Y02E60/10—Energy storage using batteries

Definitions

  • the present invention relates to the technical field of battery maintenance, and in particular to a method, device, computer equipment, computer readable storage medium, computer program product and battery pole defect detection system for detecting defects in the insulation coating of battery pole pieces.
  • lithium-ion batteries have been used in electric vehicles and have become one of the main power sources for electric vehicles.
  • the rapid development of the new energy automobile industry has put forward high requirements for the safety, environmental protection and high-current charging and discharging performance of lithium-ion batteries.
  • the coating process in lithium-ion battery manufacturing is particularly important.
  • Traditional battery pole piece defect detection uses two sets of front and back image sensors to collect pictures, respectively obtain the distance from the pole piece active material coating to the pole piece edge, obtain the misalignment of the coating film through calculation, and conduct closed-loop control with the control system. Adjust the coating area until the misalignment is less than the specified value.
  • the traditional battery pole piece defect detection scheme has the disadvantage of low detection accuracy.
  • a method, device, computer equipment, computer readable storage medium, computer program product and battery pole piece defect detection system for detecting defects in the insulating coating of battery pole pieces are provided.
  • this application provides a method for detecting defects in the insulating coating of battery pole pieces, including:
  • the pole piece image captured by the opposing pole piece and the pole piece image includes at least one complete pole piece
  • the above-mentioned method for detecting insulating coating defects of battery pole pieces involves photographing the pole piece to obtain an image of the pole piece including at least one complete pole piece, determining the insulating coating area and tab area in the pole piece image, and then based on the insulating coating area and the pole tab area.
  • the pole lug area determines the defect detection area of the insulating coating area in the pole piece image.
  • defect detection is performed on the defect detection area to obtain the defect detection results.
  • This method realizes the detection of the insulation coating of the composite front pole piece, and can detect whether there are defects in the insulation coating area, so that the defective pole pieces can be rejected in time.
  • the detection accuracy is high, and it also improves the efficiency of the lamination equipment. operating efficiency.
  • determining the insulating coating area and the tab area in the pole piece image includes: performing full edge search on the pole piece image to obtain the initial positioning of the pole piece edge; and repositioning based on the initial positioning of the pole piece edge. , determine the insulating coating area in the pole piece image; search through the insulating coating area to determine the pole tab area in the pole piece image. Perform full-image edge search and relocation through the pole piece image to find the insulating coating area in the pole piece image, and then find the pole ear area in the pole piece image based on the determined insulating coating area, achieving a step-by-step search into the pole piece image. Different areas, the detection is accurate and reliable.
  • performing full-image edge search on the pole piece image to obtain the initial positioning of the pole piece edge includes: performing full-image edge search on the pole piece image from the side away from the pole to the direction close to the pole, and obtains Initial positioning of pole piece edges. From the pole piece image, the edge of the entire image can be found gradually from the side away from the pole to the direction close to the pole, and the initial positioning of the pole piece edge can be accurately found.
  • the entire image edge search is performed on the pole piece image from the side away from the pole tab to the direction close to the pole tab, and the initial positioning of the pole piece edge is obtained, including: the pole piece image is moved from the side away from the pole tab.
  • searching the entire image of the pole piece image from the side away from the pole to the direction close to the pole analyze whether the predetermined mutation edge can be found. If the predetermined mutation edge is found, it will be used as the initial positioning of the pole piece edge, further improving the Edge finding accuracy.
  • repositioning based on the edge of the initially positioned pole piece and determining the insulating coating area in the pole piece image includes: determining the target insulating coating area based on the edge of the initially positioned pole piece, and extracting the target insulating coating area in the target insulating coating area. Determine the insulating coating area in the pole piece image. After determining the target insulating coating area based on the initial positioning of the pole piece edge, the insulating coating area in the pole piece image is then extracted based on the target insulating coating area, so as to quickly find the insulating coating area.
  • searching through the insulating coating area to determine the tab area in the pole piece image includes: performing area relocation according to the insulating coating area to determine the target tab detection area; in the target tab detection area Find and extract the tab area. Combined with the insulating coating area for regional relocation, after determining the target tab detection area, and then searching for the tab area based on the target tab detection area, the tab area can also be found quickly and easily.
  • performing area relocation based on the insulating coating area to determine the target tab detection area includes: extracting the initially positioned insulating edge of the insulating coating area; and determining the target tab detection area based on the initially positioned insulating edge.
  • searching and extracting the tab area in the target tab detection area includes: extracting the area in the target tab detection area that conforms to the grayscale characteristics of the tab, and obtaining the preliminary tab area; based on the preliminary tab area The region shape and region size determine whether the initial pole region is a pole, and if so, determine the pole region. Combined with the grayscale features of the pole ear, the target pole detection area is initially screened to determine the preliminary pole area, and then combined with the regional shape and area size of the preliminary pole area to analyze whether the pole area is found, which can ensure the accuracy of the pole area search. .
  • determining the defect detection area of the insulating coating area in the pole piece image based on the insulating coating area and the tab area includes: edge-finding the tab area to obtain the tab edge; The edge and the preset distance data are used to obtain the pole piece edge.
  • the preset distance data is the distance data between the pole edge and the pole piece edge; based on the initial positioning of the pole piece edge, the initial positioning of the insulating edge and the pole piece edge, determine the pole piece image.
  • Defect detection area for insulating coating areas After finding the pole tab area, the pole piece edge is determined by combining the pole tab edge and the preset distance data. Then, based on the initial positioning of the pole piece edge, the initial positioning of the insulation edge and the pole piece edge, defects in the insulating coating area can be accurately found. Inspection area for subsequent defect detection.
  • performing defect detection on the defect detection area to obtain defect detection results includes: extracting connected domains in the defect detection area; if there is a connected domain similar to the predetermined defect area, determining that a defect exists; the defect detection results include: Flawed information. By extracting the connected domain in the defect detection area and comparing it with the predetermined defect area, it analyzes whether there are defects in the defect detection area, and the detection is accurate and efficient.
  • performing defect detection on the defect detection area to obtain the defect detection result also includes: if there is no connected domain similar to the predetermined defect area, calculating the misalignment amount of the coating film area of the pole piece; the defect detection result includes: Information about the existence of defects and the amount of misalignment in the coating film area.
  • the misalignment of the coating area of the pole piece is also calculated to analyze whether the size and width of the insulating coating area on both sides of the pole piece are consistent, so as to detect poles with abnormal dimensions. The chips are discarded, which further improves the accuracy of defect detection of battery pole pieces.
  • the pole piece image includes a first pole piece image and a second pole piece image taken from both sides of the pole piece; if there is no connected domain similar to the predetermined defect area, the coating area of the pole piece is calculated
  • the misalignment amount includes: if there is no connected domain similar to the predetermined defect area in the defect detection area corresponding to the first pole piece image and the second pole piece image, calculate the misalignment amount of the coating film area of the pole piece. Combining the pole piece images taken from both sides of the opposite pole piece, detect whether there are defects in the corresponding defect detection areas respectively. When it is determined that there are no defects in the defect detection areas of the two pole piece images, then calculate the misalignment of the coating area of the pole piece. The amount improves the accuracy of defect detection in the insulation coating area of the pole piece.
  • the virtual edge of the pole piece and the second insulating edge calculate the width of the first insulating coating area based on the virtual edge of the first pole piece and the first insulating edge, and calculate the width of the second insulating coating area based on the virtual edge of the second pole piece and the second insulating edge.
  • the width of the insulating coating area calculates the misalignment of the coating film area of the pole piece. Combine the defect detection area of the insulating coating area in the two pole piece images to perform edge search to find the corresponding virtual edge and insulating edge of the pole piece, and then calculate the insulating coating in the two pole piece images based on the virtual edge and insulating edge of the pole piece. layer area width, and finally based on the width of the insulating coating area in the two pole piece images, the misalignment of the coating film area of the pole piece can be accurately calculated.
  • performing edge search on the defect detection area of the insulating coating area in the first pole piece image to obtain the first pole piece virtual edge and the first insulating edge includes: finding the first pole piece image in the defect detection area. The edge points of the defect detection area in the insulating coating area; fitting is performed based on the found edge points to obtain the first pole piece virtual edge and the first insulating edge. By finding the edge points of the defect detection area in the insulation coating area, and then fitting the found edge points to determine the virtual edge and insulating edge of the pole piece, the success rate of finding the virtual edge and insulating edge of the pole piece is improved.
  • the method further includes: binding the defect detection results with the pole piece identification information. Bind the defect detection results with the pole piece identification information to bind the defect detection results to specific pole pieces, providing data support for subsequent operations such as rejecting pole pieces.
  • this application provides a device for detecting defects in the insulating coating of battery pole pieces, including:
  • the image acquisition module is used to acquire the pole piece image captured by the counter pole piece, and the pole piece image includes at least one complete pole piece;
  • Image analysis module used to determine the insulating coating area and tab area in the pole piece image
  • the area extraction module is used to determine the defect detection area of the insulating coating area in the pole piece image based on the insulating coating area and the tab area;
  • the defect analysis module is used to perform defect detection on the defect detection area and obtain defect detection results.
  • the present application provides a computer device, including a memory and a processor.
  • the memory stores a computer program.
  • the processor executes the computer program, the steps of the above method are implemented.
  • the present application provides a computer-readable storage medium on which a computer program is stored.
  • the computer program is executed by a processor, the steps of the above method are implemented.
  • the present application provides a computer program product, which includes a computer program that executes the steps of the above method when the computer program is executed by a processor.
  • this application provides a battery pole piece defect detection system, including an image acquisition device and a host computer.
  • the image acquisition device is used to photograph the pole piece to obtain an image of the pole piece, and send the pole piece image to the host computer.
  • the host computer The machine is used to detect defects in the insulation coating of battery pole pieces according to the above method.
  • Figure 1 is a flow chart of a method for detecting defects in the insulating coating of battery pole pieces in one embodiment
  • Figure 2 is a flow chart for determining the insulating coating area and the tab area in the pole piece image in one embodiment
  • Figure 3 is an embodiment of a flow chart for performing full image edge search on the pole piece image from the side away from the pole tab to the direction close to the pole tab to obtain the initial positioning of the pole piece edge;
  • Figure 4 is a flow chart for determining the tab area in the pole piece image by searching for the insulating coating area in one embodiment
  • Figure 5 is a flow chart for determining the defect detection area of the insulating coating area in the pole piece image based on the insulating coating area and the tab area in one embodiment
  • Figure 6 is a flow chart for performing defect detection on the defect detection area and obtaining defect detection results in one embodiment
  • Figure 7 is a flow chart for calculating the misalignment amount of the coating film area of the pole piece in one embodiment
  • Figure 8 is a schematic diagram of the hardware layout for detecting defects in the insulation coating of battery pole pieces in one embodiment
  • Figure 9 is a schematic diagram of imaging of a camera in an embodiment
  • Figure 10 is a schematic diagram of the calculation method of the misalignment amount in one embodiment
  • Figure 11 is a structural block diagram of a device for detecting defects in the insulating coating of battery pole pieces in one embodiment
  • Figure 12 is an internal structure diagram of a computer device in one embodiment.
  • an embodiment means that a particular feature, structure or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application.
  • the appearances of this phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those skilled in the art understand, both explicitly and implicitly, that the embodiments described herein may be combined with other embodiments.
  • multiple refers to more than two (including two).
  • multiple groups refers to two or more groups (including two groups), and “multiple pieces” refers to It is more than two pieces (including two pieces).
  • Power batteries are the power sources that provide power for tools. They mostly use valve-sealed lead-acid batteries, open tubular lead-acid batteries, and lithium iron phosphate batteries, which have the characteristics of high energy, high power, and high energy density.
  • Traditional battery pole piece defect detection uses two sets of front and back image sensors to collect pictures, respectively obtain the distance from the pole piece active material coating to the pole piece edge, obtain the misalignment of the coating film through calculation, and conduct closed-loop control with the control system.
  • the existing defect detection method is in the coating section/die-cutting section of the pre-process, which only involves the detection of the coating section and the detection of misalignment in the coating film area. It lacks the detection of pole pieces before the production of laminated cells, and cannot effectively control the transfer process. damage and the inability to accurately bind data to specific pole pieces and cells.
  • this application proposes a method for detecting defects in the insulating coating of battery pole pieces. The pole piece is photographed to obtain a pole piece image including at least one complete pole piece, and the insulating coating area and tab area in the pole piece image are determined.
  • the defect detection area of the insulating coating area in the pole piece image is determined. Finally, defect detection is performed on the defect detection area to obtain the defect detection results.
  • This method realizes the detection of the insulation coating of the composite front pole piece, and can accurately detect whether there are defects in the insulation coating area, whether there are defects in the tabs, and whether the size and width of the insulation coating areas on both sides of the pole piece are consistent. The inspection can be linked with the equipment to promptly reject pole pieces with defects and abnormal sizes, thereby improving the operating efficiency of the equipment.
  • the method for detecting defects in the battery pole insulating coating provided in the embodiments of the present application can be applied during the operation of battery production line equipment, such as detecting defects in the battery pole insulating coating during lamination, winding or coating processes.
  • the insulating coating of the battery pole piece may be a ceramic coating, an alumina coating, etc.
  • the ceramic coating may be silicon carbide ceramic or silicon nitride ceramic.
  • defect detection includes detection of misalignment, defects, and tab defects in the insulating coating area and data binding storage, enabling detection of tab defects and insulating coatings on one side of the insulating coating of the cathode sheet before the cathode compounding of the stacked equipment. Detection of regional defects and dimensions.
  • the batteries involved in the embodiments of the present application can be, but are not limited to, used in electrical devices such as vehicles, ships, or aircrafts.
  • a method for detecting insulating coating defects of a battery pole piece which is suitable for detecting insulating coating defects of a composite front cathode piece. As shown in Figure 1, the method includes:
  • Step S100 Obtain the pole piece image captured by the opposite pole piece.
  • the pole piece image contains at least one complete pole piece.
  • a complete pole piece contains a complete pole lug, and extends a certain range to both sides based on the pole lug.
  • the specific range value of the expansion can be set according to the actual product size of the pole piece.
  • the pole pieces on the lamination equipment that are in the process of material roll transfer can be photographed by the image acquisition device to obtain an image of the pole piece that includes at least one complete pole piece.
  • the pole piece image is sent to the host computer for subsequent image processing by the host computer.
  • the image acquisition device can include a camera group, a sensor and a controller. Take the upper cathode camera station as an example.
  • the two cameras in the camera group can be set on both sides of the pole piece strip at the upper cathode camera station.
  • the controller The camera is triggered to take pictures after sensing the pole lug according to the sensor judgment, or the camera is controlled to take periodic photos based on the transmission speed of the pole piece material belt, and the pole piece image captured by the camera is uploaded to the host computer.
  • the light source can be set for each camera to ensure that the ambient brightness is convenient for the camera to capture better images.
  • the controller can be a PLC (Programmable Logic Controller, programmable logic controller), MCU (Micro Control Unit, micro control unit), etc.
  • the camera can be a CCD (Charge Coupled Device, charge coupled device) camera
  • the sensor can be
  • the host computer can be, but is not limited to, various personal computers, laptops, smartphones, tablets and portable wearable devices.
  • Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc.
  • the cameras on both sides can also be jointly calibrated to generate a calibration model, and the coordinates of the two cameras can be aligned to facilitate the subsequent size calculation of the front and back pole piece images to ensure the coating of the pole pieces.
  • the amount of misalignment in the membrane area is calculated accurately.
  • the controller can also upload the pole piece identification information of the current pole piece to the host computer, so that the host computer can bind and store the defect detection results and the pole piece identification information.
  • Step S200 Determine the insulating coating area and the tab area in the pole piece image.
  • the insulating coating area refers to the area where the insulating material coating is located in the pole piece image
  • the pole tab area refers to the area where the pole tabs are located in the pole piece image.
  • the host computer analyzes the image data of the pole piece image, performs image processing based on the image data, and finds the insulating coating area and pole tab area in the pole piece image.
  • the image data can specifically be grayscale values. By combining the grayscale values of each pixel in the polepiece image, the polepiece image is processed and detected through grayscale difference, edge search, etc., to find the insulation in the polepiece image. coating area and tab area. There is no unique way for the host computer to process and detect the pole piece image.
  • the direction of image detection can be saved in the host computer in advance according to the placement of the pole piece on the pole piece material. For example, as shown in Figure 9, if the captured pole piece image includes, from right to left, the active material coating area 103 of the current pole piece, the insulating material coating area, and the pole piece tabs, then the host computer will The image is subjected to grayscale difference and edge detection from right to left, and the insulating coating area 107 and the tab area 104 in the pole piece image are found in sequence.
  • Step S300 Determine the defect detection area of the insulating coating area in the pole piece image based on the insulating coating area and the tab area.
  • the defect detection area is the target area for defect detection of the insulating coating of the current pole piece. Specifically, after the host computer finds the insulating coating area and the tab area in the pole piece image, it finds the image boundaries between different pole pieces based on the tab area, and then determines the image boundaries of the insulating coating area and pole pieces. The defect detection area of the insulation coating area of the current pole piece in the pole piece image is used as a target area for subsequent defect detection of the insulation coating of the current pole piece.
  • Step S400 Perform defect detection on the defect detection area to obtain defect detection results.
  • the host computer can perform a defect search on the defect detection area in combination with the preset defect area information, and determine whether there are defects in the defect detection area that match the defect area information. , and then obtain the defect detection results of whether there are defects in the insulating coating area of the current pole piece.
  • the method further includes: binding the defect detection result with the pole piece identification information.
  • the pole piece identification information refers to the information that can uniquely determine the pole piece.
  • the type of pole piece identification information is not unique. Specifically, it can be the pole piece number, identification code, etc.
  • the host computer binds the defect detection results with the pole piece identification information, it can be stored in a local database or sent to the controller in the image acquisition device. By binding the defect detection results to the pole piece identification information, the defect detection results can be bound to specific pole pieces, providing data support for subsequent operations such as rejecting pole pieces.
  • the above-mentioned method for detecting insulating coating defects of battery pole pieces involves photographing the pole piece to obtain an image of the pole piece including at least one complete pole piece, determining the insulating coating area and tab area in the pole piece image, and then based on the insulating coating area and the pole tab area.
  • the pole lug area determines the defect detection area of the insulating coating area in the pole piece image.
  • defect detection is performed on the defect detection area to obtain the defect detection results.
  • This method realizes the detection of the insulation coating of the composite front pole piece, and can detect whether there are defects in the insulation coating area, so that the defective pole pieces can be rejected in time.
  • the detection accuracy is high, and it also improves the efficiency of the lamination equipment. operating efficiency.
  • step S200 includes steps S210 to step S230.
  • Step S210 Perform full-image edge search on the pole piece image to obtain the initially positioned pole piece edge.
  • step S210 includes: performing full image edge search on the pole piece image from the side away from the pole tab to the direction close to the pole tab to obtain the initial positioning pole piece edge.
  • the host computer searches for edges through the entire image.
  • the pole piece image is searched from right to left for the initial positioning pole piece edge 106.
  • Step S220 Reposition according to the initially positioned pole piece edge to determine the insulating coating area in the pole piece image.
  • the host computer determines the initially positioned pole piece edge 106 in the pole piece image, it continues to perform area relocation in the direction closer to the pole tab based on the initial positioned pole piece edge 106 to find the insulating coating area 107 in the pole piece image. .
  • Step S230 Search through the insulating coating area to determine the tab area in the pole piece image. After finding the insulating coating area 107 in the pole piece image, the host computer continues to search in a direction closer to the tab based on the insulating coating area 107 to find the tab area 104 in the pole piece image.
  • the entire image edge search and relocation are performed through the pole piece image to find the insulating coating area in the pole piece image, and then the pole ear area in the pole piece image is found based on the determined insulating coating area to achieve stepwise search. to different areas in the pole image, and the detection is accurate and reliable.
  • step S210 the entire image edge search is performed on the pole piece image from the side away from the pole tab to the direction close to the pole tab to obtain the initial positioning of the pole piece edge, including the steps S212 and step S214.
  • Step S212 Perform full-image edge search on the pole piece image from the side away from the pole to the direction close to the pole.
  • the host computer combines the gray values of different pixels in the pole piece image to find the first predetermined mutation from black to white from right to left. edge.
  • N the specific value can be set
  • search boxes extending from the left side to the right side of the image can be set at equal intervals in the pole piece image, and each search box is responsible for detecting an edge point.
  • Step S214 If the predetermined mutation edge is found, it is determined that the edge search is successful, and the found predetermined mutation edge is determined as the initial positioning pole piece edge. If the predetermined mutation edge can be found, the host computer determines that the edge search is successful, and determines the found predetermined mutation edge as the initial positioning pole piece edge.
  • the pole piece image when the pole piece image is edge-searched from the side away from the pole to the direction close to the pole, it is analyzed whether the predetermined mutation edge can be found. If the predetermined mutation edge is found, it is used as the initial positioning of the pole piece. edge, further improving the accuracy of edge finding.
  • the method further includes: if the predetermined mutation edge is not found, determining that the edge search is unsuccessful, and binding the pole piece edge search unsuccessful information with the pole piece identification information. If the pole piece edge search is unsuccessful, there is no need to perform subsequent area search operations. The battery pole piece insulating coating defect detection is completed. The pole piece edge search failed information is bound to the pole piece identification information and is saved in the local database or sent to controller.
  • step S220 includes: determining the target insulating coating area based on the initial positioning of the pole piece edge, and extracting and determining the insulating coating area in the pole piece image from the target insulating coating area.
  • the host computer can pre-store the size of the insulating coating area of the pole piece. As shown in Figure 9, after finding the initial positioning pole piece edge 106 in the pole piece image from right to left, start from the initial positioning pole piece edge 106. Reposition the insulating coating area to the left, and determine a detection area of interest that is larger than or equal to the size of the insulating coating area on the left side of the edge of the initially positioned pole piece as the target insulating coating area. Further, the host computer performs area extraction based on the target insulating coating area, for example, extracting the insulating coating area 107 in the pole piece image through the Blob algorithm.
  • Blob in computer vision refers to a connected area in the image
  • the Blob algorithm extracts and labels connected domains on the binary image after the foreground/background separation of the image.
  • the insulating coating area in the pole piece image is extracted by analyzing the connected areas in the binary image.
  • the insulating coating area in the pole piece image is then extracted based on the target insulating coating area, so as to quickly find the insulating coating area.
  • step S230 includes step S232 and step S234.
  • Step S232 Perform area relocation according to the insulating coating area to determine the target tab detection area. Among them, after the host computer determines the insulating coating area in the pole piece image, it continues to reposition the area in the direction closer to the tab based on the insulating coating area to determine the target tab detection area.
  • step S232 includes: extracting the initially positioned insulating edge of the insulating coating area; and determining the target tab detection area based on the initially positioned insulating edge. Specifically, as shown in Figure 9, after the host computer finds the insulating coating area 107 in the pole piece image, it moves the insulating coating area 107 close to the edge in the tab direction, specifically to the leftmost side of the insulating coating area 107. The edge serves as the initially positioned insulating edge 105 of the insulating coating area 107 .
  • the host computer can also save the tab size of the pole piece in advance, reposition it through the obtained position of the initially positioned insulating edge 105, and determine a tab that is greater than or equal to the tab size on the left side of the initially positioned insulating edge 105.
  • the frame is used as the target ear detection area.
  • the method may also include: if the initial positioning of the insulation edge extraction in the insulation coating area is unsuccessful, binding the insulation edge edge search failure information with the pole piece identification information. If the initial positioning of the insulation edge is unsuccessful, there is no need to perform subsequent operations. The battery pole piece insulation coating defect detection is completed, and the insulation edge edge search failed information is bound to the pole piece identification information and saved in the local database or sent to controller.
  • Step S234 Search and extract the tab area in the target tab detection area. After the host computer determines the target tab detection area, it analyzes the image within the target tab detection area and extracts the tab area.
  • step S234 includes: extracting a region in the target lug detection area that matches the grayscale characteristics of the lug to obtain a preliminary lug area; and determining whether the preliminary lug area is based on the regional shape and size of the preliminary lug area. is the polar ear, if so, determine the polar ear area.
  • the host computer performs binarization processing on the image within the target lug detection area, performs grayscale value analysis on the binarized image, and extracts the area that conforms to the grayscale characteristics of the lug as the preliminary lug area. Further, the host computer analyzes the regional shape and size of the preliminary lug area in combination with the preset lug characteristic parameters to determine whether the preliminary lug area is a lug.
  • the tab characteristic parameters may include parameters such as tab shape and size. If the regional shape and area size of the preliminary tab area are the same as the preset tab shape and size, or the difference is within the preset allowable range, then the It is considered that the regional shape and area size of the preliminary pole region are consistent with the pole characteristic parameters, and the preliminary pole region is determined to be the pole. Preliminary screening of the target ear detection area is performed by combining the grayscale features of the ear to determine the preliminary ear area, and then combined with the regional shape and size of the preliminary ear area to analyze whether the ear area is found, which can ensure the accuracy of the search for the ear area. sex.
  • the area relocation is performed in combination with the insulating coating area. After the target tab detection area is determined, the tab area is searched based on the target tab detection area. This can also facilitate and quickly find the tab area.
  • the method may further include: if it is determined that the preliminary tab area is not a tab, binding the tab absence information with the pole piece identification information. If the tab does not exist, there is no need to perform subsequent operations. The battery pole piece insulation coating defect detection is completed. The tab absence information is bound to the pole piece identification information and then stored in the local database or sent to the controller.
  • step S300 includes steps S310 to step S330.
  • Step S310 Perform edge search on the tab area to obtain the tab edge.
  • the host computer can search for the edge of the tab in the direction parallel to the initially positioned insulating edge. As shown in Figure 9, taking the image of the anti-pole piece to gradually find the initial positioning pole piece edge 106 and the initial positioning insulating edge 105 from right to left as an example, then the host computer will detect the pole lug area 104 along the up and down direction through the edge-finding algorithm. Perform edge search on the edge of the pole to find the upper edge 110 and the lower edge 111 of the pole.
  • the edge search frames of the two tab edges can be determined at the upper and lower edge positions of the tab area 104, and then the pixel points can be traversed in the up and down directions in each frame to find the gray value changes.
  • the search for the edge of the tab in the bounding box is successful.
  • Step S320 Obtain the edge of the pole piece based on the edge of the pole tab and the preset distance data.
  • the preset distance data is the distance data between the edge of the pole piece and the edge of the pole piece.
  • the specific value of the preset distance data can be set according to the distance between the edge of the pole piece and the edge of the pole piece in the actual product.
  • the edge of the pole piece includes the upper edge 112 of the pole piece and the lower edge 113 of the pole piece.
  • the pole can be found by adding the preset distance data to the position of the upper edge 110 of the pole tab.
  • the lower edge 113 of the pole piece can be found by adding the preset distance data to the position of the lower edge 111 of the pole tab.
  • Step S330 Determine the defect detection area of the insulating coating area in the pole piece image based on the initial positioning of the pole piece edge, the initial positioning of the insulating edge and the pole piece edge.
  • the host computer determines the initial positioning pole piece edge 106, the initial positioning insulating edge 105, the pole piece upper edge 112 and the pole piece lower edge 113, it combines the four edge fittings to generate the defect detection of the insulating coating area 107 of the current pole piece. area.
  • the edge of the pole piece is determined based on the edge of the tab and the preset distance data. Then, based on the initial positioning of the edge of the pole piece, the initial positioning of the insulating edge and the edge of the pole piece, the insulating coating can be accurately found. Defect detection area in the layer area for subsequent defect detection.
  • the method further includes: if the edge search of the pole lug area is unsuccessful, binding the unsuccessful edge search information of the pole lug with the pole piece identification information and outputting the result. If the edge search in the tab area is unsuccessful, there is no need to perform subsequent operations. The battery pole piece insulation coating defect detection is completed. The failed tab edge search information is bound to the pole piece identification information and is saved in the local database or sent to controller.
  • step S400 includes step S410 and step S420.
  • Step S410 Extract connected domains in the defect detection area.
  • the connected domain refers to the set of adjacent pixels in the defect detection area whose grayscale values are within the same set range.
  • the host computer can also perform Blob algorithm processing on the defect detection area to obtain the connected domain in the processed binary image.
  • Step S420 If there is a connected domain similar to the predetermined defect area, it is determined that a defect exists.
  • Defect detection results include information about the existence of defects.
  • Corresponding predetermined defect area information can be generated in advance based on the actual defects that may occur in the insulating coating area of the pole piece and stored in the host computer.
  • the predetermined defect area information can include information such as the location, shape, and size of the predetermined defect area.
  • the host computer Combined with the predetermined defect area information, analyze whether the connected domain of the defect detection area is similar to the predetermined defect area.
  • the similarity in position, shape, and size between the connected domain of the defect detection area and the predetermined defect area is higher than the corresponding set threshold, Then it can be considered that the connected domain is similar to the predetermined defect area, and then it is determined that there is a defect in the defect detection area.
  • the front pole piece when detecting whether there are defects in the insulating coating area of the front pole piece, it can be based on two pole piece images taken by two cameras on the composite surface and the non-composite surface of the pole piece respectively, and the two pole piece images are simultaneously photographed. Analyze the pole piece images to determine the defect detection area of the insulating coating area in the two pole piece images, and then detect whether the defect detection area in the two pole piece images has a connected domain similar to the predetermined defect area.
  • the two pole pieces If there is no connected domain similar to the predetermined defect area in the defect detection area in the image, it is considered that there is no defect in the insulation coating area of the current pole piece; if a predetermined defect is detected in the defect detection area of one or two pole pieces images If there are connected domains with similar areas, it is considered that there is a defect in the insulating coating area of the current pole piece.
  • the above method may also first perform image analysis on one of the pole piece images through steps S100 to S400, find the defect detection area in the pole piece image, and analyze whether there is a connection similar to the predetermined defect area. domain, if it exists, it is considered that there is a defect in the insulating coating area of the current pole piece, and there is no need to analyze the image of the other pole piece; if it does not exist, then go through steps S100 to S400 to find the defect in the image of the other pole piece. Detect the region and analyze whether there are connected domains similar to the predetermined defective region.
  • the defect detection area in another pole piece image does not have a connected domain similar to the predetermined defect area, it is considered that there is no defect in the insulating coating area of the current pole piece. On the contrary, it is also considered that the insulating coating area of the current pole piece is not defective. Flawed. In addition, if it is determined that there is a defect in the predetermined defect area, the host computer will bind the defect information with the pole piece identification information and store it in the local database or send it to the controller.
  • step S400 also includes step S430: if there is no connected domain similar to the predetermined defective area, calculate the misalignment amount of the coating film area of the pole piece.
  • the defect detection results include information on the absence of defects and the amount of misalignment in the coating film area. Specifically, if there is no connected domain similar to the predetermined defect area in the defect detection area in the two pole piece images taken by the current pole piece, it is considered that there is no defect in the insulation coating of the current pole piece, and the two pole pieces are combined The image calculates the misalignment of the coating area of the current pole piece.
  • the host computer can also bind the defect-free information and misalignment of the coating film area with the pole piece identification information and store it in a local database or send it to the controller.
  • the misalignment of the coating film area of the pole piece is also calculated to analyze whether the size and width of the insulating coating area on both sides of the pole piece are consistent, so as to determine The pole pieces with abnormal sizes are discarded, which further improves the accuracy of defect detection of battery pole pieces.
  • the pole piece image includes a first pole piece image and a second pole piece image obtained by photographing both sides of the pole piece; step S430 includes: if the defect detection corresponding to the first pole piece image and the second pole piece image In the area, there is no connected domain similar to the predetermined defect area, and the misalignment of the coating film area of the pole piece is calculated.
  • the first pole piece image and the second pole piece image are the pole piece images obtained by taking the composite surface and the non-composite surface of the current pole piece respectively. There are no predetermined defects in the defect detection areas in the two pole piece images.
  • the host computer determines that there is no defect in the insulation coating of the current pole piece, and calculates the misalignment of the coating area of the pole piece.
  • the pole piece images taken from both sides of the opposite pole piece detect whether there are defects in the corresponding defect detection areas respectively.
  • it is determined that there are no defects in the defect detection areas of the two pole piece images then calculate the misalignment of the coating area of the pole piece. The amount improves the accuracy of defect detection in the insulation coating area of the pole piece.
  • the pole piece image includes a first pole piece image and a second pole piece image taken from both sides of the pole piece; as shown in Figure 7, in step S430, the misalignment of the coating film area of the pole piece is calculated Amount, including step S432 to step S438.
  • Step S432 Perform edge search on the defect detection area of the insulating coating area in the first pole piece image to obtain the first pole piece virtual edge and the first insulating edge. Specifically, when the defect detection area of the insulating coating area in the first pole piece image is determined and it is judged that there is no connected domain similar to the predetermined defect area in the defect detection area, an edge search is performed on the defect detection area to find the first pole. The first virtual edge of the pole piece and the first insulating edge in the chip image.
  • step S432 includes: finding edge points of the defect detection area of the insulating coating area in the first pole piece image; performing fitting according to the found edge points to obtain the virtual edge of the first pole piece and the first Insulated sides. Specifically, based on the defect detection area of the insulation coating area of the current pole piece in the first pole piece image, the insulation of a current pole piece is determined based on the initial positioning pole piece edge, the initial positioning insulation edge, the pole piece upper edge and the pole piece lower edge.
  • the edge search frame and the pole piece virtual edge search frame are searched respectively, and then the edge search algorithm is used to find the edge in the insulating edge search frame and the pole piece virtual edge search frame respectively, and the edge points in the two border search frames are found, and then the edge points in each search border frame are found.
  • the edge points are fitted, and the virtual edge of the first pole piece and the first insulating edge are obtained correspondingly.
  • the method may also include the step of filtering the edge points to filter out abnormal edge points, and then combine the filtering The remaining edge points after the division are fitted, and the first virtual edge of the pole piece and the first insulating edge are obtained correspondingly.
  • the way to filter edge points is not unique.
  • edge points can be filtered through fitting algorithms. For example, the weighted least squares method can be used to filter out abnormal edge points based on the position of each edge point.
  • Step S434 Perform edge search on the defect detection area of the insulating coating area in the second pole piece image to obtain the second pole piece virtual edge and the second insulating edge. It can be understood that the method of edge-finding the defect detection area of the insulating coating area in the second pole piece image and obtaining the second pole piece virtual edge and the second insulating edge is similar to step S432, and will not be described again here.
  • Step S436 Calculate the width of the first insulating coating area based on the imaginary edge of the first pole piece and the first insulating edge, and calculate the width of the second insulating coating area based on the imaginary edge of the second pole piece and the second insulating edge.
  • the host computer After finding the first pole piece virtual edge and the first insulating edge in the first pole piece image, and the second pole piece virtual edge and the second insulating edge in the second pole piece image, the host computer calculates the first pole piece virtual edge.
  • the distance between the edge and the first insulating edge is the width of the insulating coating area in the first pole piece image, that is, the width of the first insulating coating area.
  • the host computer calculates the distance between the virtual edge of the second pole piece and the second insulating edge to obtain the width of the insulating coating area in the image of the second pole piece, that is, the width of the second insulating coating area.
  • Step S438 Calculate the misalignment amount of the coating film area of the pole piece based on the width of the first insulating coating area and the width of the second insulating coating area.
  • the host computer subtracts the width of the first insulating coating area and the width of the second insulating coating area, and the resulting difference is the misalignment of the coating film area of the current pole piece.
  • the defect detection area of the insulating coating area in the two pole piece images is combined to perform edge search to find the corresponding virtual edge and insulating edge of the pole piece, and then the two pole pieces are calculated based on the virtual edge and insulating edge of the pole piece.
  • the width of the insulating coating area in the image, and finally based on the width of the insulating coating area in the images of the two pole pieces, the misalignment of the coating area of the pole piece can be accurately calculated.
  • the method may also include: if the edge point is not found, binding the edge point search failure information with the pole piece identification information and outputting. If the search for the edge point of the defect detection area in the first pole piece image or the second pole piece image is unsuccessful, there is no need to perform subsequent operations. The battery pole piece insulation coating defect detection is completed, and the unsuccessful edge point search information is added to the pole piece. The slice identification information is bound and saved in the local database or sent to the controller.
  • this application proposes a An online detection method for dimensional defects in the insulating coating of the composite front cathode sheet of an anode continuous stack, using a high-efficiency and high-precision visual algorithm to detect the insulating coating of the composite front cathode sheet, which can accurately detect whether there are defects in the insulating coating area and tabs Whether there are defects and whether the size and width of the insulating coating areas on both sides of the cathode sheet are consistent, testing before lamination can be linked with the equipment to promptly reject the electrode sheets with defects and abnormal sizes, improve equipment operation efficiency, and reduce the risk of missed kills.
  • Figure 8 is a schematic diagram of the hardware layout for insulating coating defect detection.
  • a high frame rate area scan camera is set up on both sides of the cathode strip, and a white strip light source is set up to detect the insulating coating area from the side.
  • Light is the cathode strip
  • A102 is the detection camera 1
  • A103 is the light source corresponding to the detection camera 1
  • A104 is the detection camera 2
  • A105 is the light source corresponding to the detection camera 2.
  • a camera on each side of the pole piece material belt takes pictures of the insulating coating area.
  • the cameras on both sides are jointly calibrated to generate a calibration model.
  • the PLC triggers the camera to take pictures through the induction pole tab and gives the unique identification code of the current pole piece.
  • the vision software processes and detects images through grayscale difference, edge detection and other means to realize the detection and data binding storage of misalignment, defects and tab defects in the insulating coating area.
  • Figure 9 is a schematic diagram of the imaging of the camera in the embodiment.
  • the names of each area are as follows: 101: previous cathode sheet; 102: next cathode sheet; 103: current cathode sheet active material coating area; 104: current cathode sheet electrode Ear, that is, the pole ear area; 105: initial positioning insulating edge, that is, the outer edge of the insulating material coating area; 106: cathode virtual edge/initial positioning pole piece edge, that is, the cathode pole piece active material coating area and insulating material coating area Junction edge; 107: Insulating material coating area, that is, insulating coating area; 108: Offset amount between the upper edge of the pole tab and the upper edge of the current pole piece; 109: Offset amount between the lower edge of the pole tab and the lower edge of the current pole piece; 110: The upper edge of the pole lug; 111: the lower edge of the pole lug; 112: the upper edge of the pole piece; 113: the
  • Figure 10 is a schematic diagram of the calculation method of the misalignment.
  • Surface A is photographed from the non-composite surface of the counterpole piece, and side B is photographed from the composite surface of the counterpole piece.
  • the defect detection items of this defect detection method include: 106 area leakage metal damage defect detection, 106 area width detection, 106 area width AB surface misalignment amount, and 104 area tab missing detection.
  • This defect detection method will accurately reposition the detection area by locating the edge of the pole piece and the insulation coating area, accurately position the detection frame to the corresponding area that needs to be detected, and then conduct detection through edge finding, size measurement and defect detection algorithms respectively.
  • detecting the insulating coating on the lamination equipment can control the damage of the insulating coating during the roll transfer process, provide pole piece data for the equipment, and provide data support for subsequent scrap removal and other operations; provide each pole piece with data support.
  • the unique number of each pole piece can be stored by binding it to make the insulation coating data of each pole piece traceable.
  • This detection method has high detection accuracy, with a pixel accuracy of up to 0.02mm, fast detection efficiency, and a single detection time of less than 20ms.
  • embodiments of the present application also provide a device for detecting defects in the insulating coating of the battery pole piece that is used to implement the above-mentioned method for detecting defects in the insulating coating of the battery pole piece.
  • the solution to the problem provided by this device is similar to the solution described in the above method. Therefore, for the specific limitations in one or more battery exchange processing device embodiments provided below, please refer to the above article on battery pole piece insulation coating. The limitations of the layer defect detection method will not be described again here.
  • a device for detecting insulating coating defects of battery electrode sheets which is suitable for detecting insulating coating defects of composite front cathode sheets.
  • the device includes: image acquisition module 100, image analysis module 200, area extraction module 300 and defect analysis module 400, wherein:
  • the image acquisition module 100 is used to acquire the pole piece image captured by the opposite pole piece, and the pole piece image includes at least one complete pole piece.
  • the image analysis module 200 is used to determine the insulating coating area and the tab area in the pole piece image.
  • the area extraction module 300 is used to determine the defect detection area of the insulating coating area in the pole piece image based on the insulating coating area and the tab area.
  • the defect analysis module 400 is used to perform defect detection on the defect detection area and obtain defect detection results.
  • the image analysis module 200 performs full-image edge search on the pole piece image to obtain the initial positioning of the pole piece edge; repositions the pole piece edge according to the initial positioning to determine the insulating coating area in the pole piece image; through the insulation Search the coating area to determine the tab area in the pole piece image.
  • the image analysis module 200 performs edge search on the pole piece image from the side away from the pole tab to the direction close to the pole tab to obtain the initial positioning of the pole piece edge.
  • the image analysis module 200 performs edge search on the pole piece image from the side away from the pole to the direction close to the pole: if a predetermined mutation edge is found, it is determined that the edge search is successful, and the predetermined edge found is The mutation edge is determined as the edge of the initial positioning pole piece.
  • the image analysis module 200 determines the target insulating coating area based on the initial positioning of the pole piece edge, and extracts and determines the insulating coating area in the pole piece image from the target insulating coating area.
  • the image analysis module 200 performs area relocation based on the insulating coating area to determine the target tab detection area; and searches and extracts the tab area in the target tab detection area.
  • the image analysis module 200 extracts the initially positioned insulating edge of the insulating coating area; and determines the target tab detection area based on the initially positioned insulating edge.
  • the image analysis module 200 extracts a region in the target lug detection area that matches the grayscale characteristics of the lug to obtain a preliminary lug area; and determines whether the preliminary lug area is based on the regional shape and size of the preliminary lug area. is the polar ear, if so, determine the polar ear area.
  • the area extraction module 300 performs edge search on the pole area to obtain the pole edge; and obtains the pole piece edge according to the pole edge and the preset distance data.
  • the preset distance data is the pole edge and the pole piece edge. distance data; determine the defect detection area of the insulating coating area in the pole piece image based on the initial positioning of the pole piece edge, the initial positioning of the insulating edge and the pole piece edge.
  • the defect analysis module 400 extracts the connected domain in the defect detection area; if there is a connected domain similar to the predetermined defect area, it is determined that a defect exists; the defect detection result includes information about the existence of defects.
  • the defect analysis module 400 also calculates the misalignment amount of the coating film area of the pole piece when there is no connected domain similar to the predetermined defect area; the defect detection result includes information about the absence of defects and the misalignment amount of the coating film area.
  • the pole piece image includes a first pole piece image and a second pole piece image taken from both sides of the pole piece; the defect analysis module 400 detects defects corresponding to the first pole piece image and the second pole piece image. When there is no connected domain similar to the predetermined defective area in the area, the misalignment amount of the coating film area of the pole piece is calculated.
  • the pole piece image includes a first pole piece image and a second pole piece image taken from both sides of the pole piece; the defect analysis module 400 detects defects in the insulating coating area in the first pole piece image. Perform edge search to obtain the virtual edge of the first pole piece and the first insulating edge; perform edge search on the defect detection area of the insulating coating area in the image of the second pole piece to obtain the virtual edge of the second pole piece and the second insulating edge; The width of the first insulating coating area is calculated based on the imaginary edge of the first pole piece and the first insulating edge, and the width of the second insulating coating area is calculated based on the imaginary edge of the second pole piece and the second insulating edge; The width of the insulating coating area and the width of the second insulating coating area are used to calculate the misalignment of the coating film area of the pole piece.
  • the defect analysis module 400 searches for edge points of the defect detection area of the insulating coating area in the first pole piece image; and performs fitting according to the found edge points to obtain the virtual edge of the first pole piece and the first Insulated sides.
  • the defect analysis module 400 also binds the defect detection results with the pole piece identification information.
  • a computer device is provided.
  • the computer device can be a server or a terminal. Taking the server as an example, its internal structure diagram can be shown in Figure 12.
  • the computer device includes a processor, memory, and network interfaces connected through a system bus. Wherein, the processor of the computer device is used to provide computing and control capabilities.
  • the memory of the computer device includes non-volatile storage media and internal memory.
  • the non-volatile storage medium stores operating systems, computer programs and databases. This internal memory provides an environment for the execution of operating systems and computer programs in non-volatile storage media.
  • the database of the computer device is used to store defect detection result data.
  • the network interface of the computer device is used to communicate with external terminals through a network connection.
  • the computer program is executed by a processor to implement a method for detecting defects in the insulating coating of battery pole pieces.
  • Figure 12 is only a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer equipment to which the solution of the present application is applied.
  • Specific computer equipment can May include more or fewer parts than shown, or combine certain parts, or have a different arrangement of parts.
  • a computer device including a memory and a processor.
  • the memory stores a computer program.
  • the processor executes the computer program, the steps in the above method embodiments are implemented.
  • a computer-readable storage medium on which a computer program is stored.
  • the computer program is executed by a processor, the steps in the above method embodiments are implemented.
  • a computer program product including a computer program that implements the steps in each of the above method embodiments when executed by a processor.
  • a battery pole piece defect detection system including an image acquisition device and a host computer.
  • the image acquisition device is used to photograph the pole piece to obtain an image of the pole piece, and send the pole piece image to the host computer.
  • the host computer is used to detect defects in the insulation coating of battery pole pieces according to the above method.
  • the image acquisition device specifically includes a camera group, a sensor and a controller, and the controller is connected to the camera group, the sensor and the host computer.
  • the controller can be a PLC, MCU, etc.
  • the camera group can be a CCD camera group
  • the sensor can be a photoelectric induction sensor
  • the host computer can be, but is not limited to, various personal computers, laptops, smart phones, tablets and portable wearables.
  • Equipment, portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc.
  • the computer program can be stored in a computer-readable storage medium.
  • the program can be stored in a computer-readable storage medium.
  • the process may include the processes of the above method embodiments.
  • the aforementioned storage media can be non-volatile storage media such as magnetic disks, optical disks, read-only memory (Read-Only Memory, ROM), or random access memory (Random Access Memory, RAM), etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Manufacturing & Machinery (AREA)
  • Chemical Kinetics & Catalysis (AREA)
  • Electrochemistry (AREA)
  • General Chemical & Material Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Signal Processing (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
  • Battery Electrode And Active Subsutance (AREA)

Abstract

一种电池极片绝缘涂层缺陷的检测方法、装置、计算机设备、计算机可读存储介质、计算机程序产品和电池极片缺陷检测***，该方法包括：获取对极片拍摄得到的极片图像，极片图像至少包括一个完整的极片；确定极片图像中的绝缘涂层区域和极耳区域；根据绝缘涂层区域和极耳区域，确定极片图像中的绝缘涂层区域的缺陷检测区域；对缺陷检测区域进行缺陷检测，得到缺陷检测结果。该方法实现了对复合前极片绝缘涂层进行检测，可以检测出绝缘涂层区域是否存在缺陷，以便及时对存在缺陷的极片进行剔废，检测准确性高，还提高了叠片设备的运行效率。

Description

电池极片绝缘涂层缺陷的检测方法、装置和计算机设备 技术领域
本发明涉及电池维护技术领域，特别是涉及一种电池极片绝缘涂层缺陷的检测方法、装置、计算机设备、计算机可读存储介质、计算机程序产品和电池极片缺陷检测***。
背景技术
随着科技的不断进步，锂离子电池已在电动汽车中得到应用，成为电动汽车的主要动力能源之一。新能源汽车产业的迅速发展，对锂离子电池的安全、环保及大电流充放电的使用性能等提出了很高的要求。在大规模化生产中，要想提高电池的性能，在锂离子电池制造的涂布工序显得尤为重要。
传统的电池极片缺陷检测是使用正反两组图像传感器采集图片，分别获取极片活性物质涂膜到极片边缘的距离，通过计算获得涂膜错位量，并与控制***进行闭环控制，调整涂膜区域至错位量小于规格值。传统的电池极片缺陷检测方案，存在检测准确性低的缺点。
发明内容
根据本申请的各种实施例，提供一种电池极片绝缘涂层缺陷的检测方法、装置、计算机设备、计算机可读存储介质、计算机程序产品和电池极片缺陷检测***。
第一方面，本申请提供了一种电池极片绝缘涂层缺陷的检测方法，包括：
获取对极片拍摄得到的极片图像，极片图像至少包括一个完整的极片；
确定极片图像中的绝缘涂层区域和极耳区域；
根据绝缘涂层区域和极耳区域，确定极片图像中的绝缘涂层区域的缺陷检测区域；
对缺陷检测区域进行缺陷检测，得到缺陷检测结果。
上述电池极片绝缘涂层缺陷的检测方法，对极片拍摄得到至少包括一个完整极片的极片图像，确定极片图像中的绝缘涂层区域和极耳区域，进而根据绝缘涂层区域和极耳区域，确定极片图像中的绝缘涂层区域的缺陷检测区域。最后，对缺陷检测区域进行缺陷检测，得到缺陷检测结果。该方法实现了对复合前极片绝缘涂层进行检测，可以检测出绝缘涂层区域是否存在缺陷，以便及时对存在缺陷的极片进行剔废，检测准确性高，还提高了叠片设备的运行效率。
在其中一个实施例中，确定极片图像中的绝缘涂层区域和极耳区域，包括：对极片图 像进行全图寻边，得到初定位极片边缘；根据初定位极片边缘进行重定位，确定极片图像中的绝缘涂层区域；通过绝缘涂层区域进行寻找，确定极片图像中的极耳区域。通过极片图像进行全图寻边和重定位，找到极片图像中的绝缘涂层区域，进而基于确定的绝缘涂层区域找到极片图像中的极耳区域，实现逐步查找到极片图像中的不同区域，检测准确可靠。
在其中一个实施例中，对极片图像进行全图寻边，得到初定位极片边缘，包括：对极片图像从远离极耳的一侧向靠近极耳的方向进行全图寻边，得到初定位极片边缘。从极片图像从远离极耳的一侧逐渐向靠近极耳的方向进行全图寻边，可准确查找得到初定位极片边缘。
在其中一个实施例中，对极片图像从远离极耳的一侧向靠近极耳的方向进行全图寻边，得到初定位极片边缘，包括：对极片图像从远离极耳的一侧向靠近极耳的方向进行全图寻边：若寻找到预定突变边缘，确定寻边成功，将寻找到的预定突变边缘确定为初定位极片边缘。在对极片图像从远离极耳的一侧向靠近极耳的方向进行全图寻边时，分析是否能寻找到预定突变边缘，若找到预定突变边缘则作为初定位极片边缘，进一步提高了边缘寻找的准确性。
在其中一个实施例中，根据初定位极片边缘进行重定位，确定极片图像中的绝缘涂层区域，包括：根据初定位极片边缘确定目标绝缘涂层区域，在目标绝缘涂层区域提取确定极片图像中的绝缘涂层区域。在根据初定位极片边缘确定目标绝缘涂层区域后，进而基于目标绝缘涂层区域提取极片图像中的绝缘涂层区域，方便快速寻找到绝缘涂层区域。
在其中一个实施例中，通过绝缘涂层区域进行寻找，确定极片图像中的极耳区域，包括：根据绝缘涂层区域进行区域重定位，确定目标极耳检测区域；在目标极耳检测区域中查找提取极耳区域。结合绝缘涂层区域进行区域重定位，确定目标极耳检测区域后，再基于目标极耳检测区域查找极耳区域，同样可方便快速寻找到极耳区域。
在其中一个实施例中，根据绝缘涂层区域进行区域重定位，确定目标极耳检测区域，包括：提取绝缘涂层区域的初定位绝缘边；根据初定位绝缘边，确定目标极耳检测区域。通过提取绝缘涂层区域的初定位绝缘边，结合初定位绝缘边选定目标极耳检测区域，可快速准确的确定目标极耳检测区域。
在其中一个实施例中，在目标极耳检测区域中查找提取极耳区域，包括：提取目标极耳检测区域中符合极耳灰度特征的区域，获得初步极耳区域；根据初步极耳区域的区域形状和区域大小，确定初步极耳区域是否为极耳，若是，确定得到极耳区域。结合极耳灰度特征对目标极耳检测区域进行初步筛选确定初步极耳区域，进而结合初步极耳区域的区域形状和区域大小分析是否查找到极耳区域，可确保极耳区域的查找准确性。
在其中一个实施例中，根据绝缘涂层区域和极耳区域，确定极片图像中的绝缘涂层区 域的缺陷检测区域，包括：对极耳区域进行寻边，得到极耳边缘；根据极耳边缘和预设距离数据，得到极片边缘，预设距离数据为极耳边缘与极片边缘的距离数据；根据初定位极片边缘、初定位绝缘边和极片边缘，确定极片图像中的绝缘涂层区域的缺陷检测区域。在查找到极耳区域之后，结合极耳边缘和预设距离数据确定极片边缘，进而根据初定位极片边缘、初定位绝缘边和极片边缘，可准确查找到绝缘涂层区域中的缺陷检测区域，以便后续进行缺陷检测。
在其中一个实施例中，对缺陷检测区域进行缺陷检测，得到缺陷检测结果，包括：提取缺陷检测区域中的连通域；若存在与预定缺陷区域相似的连通域，确定存在缺陷；缺陷检测结果包括存在缺陷的信息。通过提取缺陷检测区域中的连通域与预定缺陷区域进行对比，分析缺陷检测区域是否存在缺陷，检测准确高效。
在其中一个实施例中，对缺陷检测区域进行缺陷检测，得到缺陷检测结果，还包括：若不存在与预定缺陷区域相似的连通域，计算极片的涂膜区域错位量；缺陷检测结果包括不存在缺陷的信息和涂膜区域错位量。在绝缘涂层区域的缺陷检测区域中不存在缺陷时，还计算极片的涂膜区域错位量，以用作分析极片两面的绝缘涂层区域尺寸宽度是否一致，以便对存在尺寸异常的极片进行剔废，进一步提高了电池极片的缺陷检测准确性。
在其中一个实施例中，极片图像包括对极片的两面拍摄得到的第一极片图像和第二极片图像；若不存在与预定缺陷区域相似的连通域，计算极片的涂膜区域错位量，包括：若第一极片图像和第二极片图像对应的缺陷检测区域中，均不存在与预定缺陷区域相似的连通域，计算极片的涂膜区域错位量。结合对极片的两面拍摄得到的极片图像，分别检测相应的缺陷检测区域是否存在缺陷，在确定两个极片图像的缺陷检测区域都不存在缺陷时，再计算极片的涂膜区域错位量，提高了对极片绝缘涂层区域的缺陷检测准确性。
在其中一个实施例中，极片图像包括对极片的两面拍摄得到的第一极片图像和第二极片图像；计算极片的涂膜区域错位量，包括：对第一极片图像中的绝缘涂层区域的缺陷检测区域进行寻边，得到第一极片虚边和第一绝缘边；对第二极片图像中的绝缘涂层区域的缺陷检测区域进行寻边，得到第二极片虚边和第二绝缘边；根据第一极片虚边和第一绝缘边，计算得到第一绝缘涂层区域宽度，并根据第二极片虚边和第二绝缘边，计算得到第二绝缘涂层区域宽度；根据第一绝缘涂层区域宽度和第二绝缘涂层区域宽度，计算得到极片的涂膜区域错位量。结合两个极片图像中绝缘涂层区域的缺陷检测区域进行寻边，找到对应的极片虚边和绝缘边，进而根据极片虚边和绝缘边计算得到两个极片图像中的绝缘涂层区域宽度，最后根据两个极片图像中的绝缘涂层区域宽度，可准确计算得到极片的涂膜区域错位量。
在其中一个实施例中，对第一极片图像中的绝缘涂层区域的缺陷检测区域进行寻边， 得到第一极片虚边和第一绝缘边，包括：寻找第一极片图像中的绝缘涂层区域的缺陷检测区域的边缘点；根据寻找到的边缘点进行拟合，得到第一极片虚边和第一绝缘边。通过寻找绝缘涂层区域的缺陷检测区域的边缘点，再结合寻找到的边缘点进行拟合来确定极片虚边和绝缘边，提高极片虚边和绝缘边的查找成功率。
在其中一个实施例中，对缺陷检测区域进行缺陷检测，得到缺陷检测结果之后，该方法还包括：将缺陷检测结果与极片标识信息绑定。将缺陷检测结果与极片标识信息绑定，实现将缺陷检测结果绑定到具体的极片，为后续对极片的剔废等操作提供数据支持。
第二方面，本申请提供了一种电池极片绝缘涂层缺陷的检测装置，包括：
图像获取模块，用于获取对极片拍摄得到的极片图像，极片图像至少包括一个完整的极片；
图像分析模块，用于确定极片图像中的绝缘涂层区域和极耳区域；
区域提取模块，用于根据绝缘涂层区域和极耳区域，确定极片图像中的绝缘涂层区域的缺陷检测区域；
缺陷分析模块，用于对缺陷检测区域进行缺陷检测，得到缺陷检测结果。
第三方面，本申请提供了一种计算机设备，包括存储器和处理器，存储器存储有计算机程序，处理器执行计算机程序时实现上述方法的步骤。
第四方面，本申请提供了一种计算机可读存储介质，其上存储有计算机程序，计算机程序被处理器执行时实现上述方法的步骤。
第五方面，本申请提供了一种计算机程序产品，包括计算机程序，该计算机程序被处理器执行时上述方法的步骤。
第六方面，本申请提供了一种电池极片缺陷检测***，包括图像获取装置和上位机，图像获取装置用于对极片拍摄得到极片图像，并将极片图像发送至上位机，上位机用于根据上述方法进行电池极片绝缘涂层缺陷的检测。
本申请的一个或多个实施例的细节在下面的附图和描述中提出。本发明的其它特征、目的和优点将从说明书、附图以及权利要求书变得明显。
附图说明
为了更清楚地说明本申请实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其它的附图。
图1为一个实施例中电池极片绝缘涂层缺陷的检测方法的流程图；
图2为一个实施例中确定极片图像中的绝缘涂层区域和极耳区域的流程图；
图3为一个实施例中对极片图像从远离极耳的一侧向靠近极耳的方向进行全图寻边，得到初定位极片边缘的流程图；
图4为一个实施例中通过绝缘涂层区域进行寻找，确定极片图像中的极耳区域的流程图；
图5为一个实施例中根据绝缘涂层区域和极耳区域，确定极片图像中的绝缘涂层区域的缺陷检测区域的流程图；
图6为一个实施例中对缺陷检测区域进行缺陷检测，得到缺陷检测结果的流程图；
图7为一个实施例中计算极片的涂膜区域错位量的流程图；
图8为一个实施例中电池极片绝缘涂层缺陷检测硬件布局示意图；
图9为一个实施例中相机的成像示意图；
图10为一个实施例中错位量的计算方式示意图；
图11为一个实施例中电池极片绝缘涂层缺陷的检测装置的结构框图；
图12为一个实施例中计算机设备的内部结构图。
具体实施方式
下面将结合附图对本申请技术方案的实施例进行详细的描述。以下实施例仅用于更加清楚地说明本申请的技术方案，因此只作为示例，而不能以此来限制本申请的保护范围。
除非另有定义，本文所使用的所有的技术和科学术语与属于本申请的技术领域的技术人员通常理解的含义相同；本文中所使用的术语只是为了描述具体的实施例的目的，不是旨在于限制本申请；本申请的说明书和权利要求书及上述附图说明中的术语“包括”和“具有”以及它们的任何变形，意图在于覆盖不排他的包含。
在本申请实施例的描述中，技术术语“第一”“第二”等仅用于区别不同对象，而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量、特定顺序或主次关系。在本申请实施例的描述中，“多个”的含义是两个以上，除非另有明确具体的限定。
在本文中提及“实施例”意味着，结合实施例描述的特定特征、结构或特性可以包含在本申请的至少一个实施例中。在说明书中的各个位置出现该短语并不一定均是指相同的实施例，也不是与其它实施例互斥的独立的或备选的实施例。本领域技术人员显式地和隐式地理解的是，本文所描述的实施例可以与其它实施例相结合。
在本申请实施例的描述中，术语“和/或”仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。另外，本文中字符“/”，一般表示前后关联对象是一种“或”的关系。
在本申请实施例的描述中，术语“多个”指的是两个以上(包括两个)，同理，“多组”指的是两组以上(包括两组)，“多片”指的是两片以上(包括两片)。
在本申请实施例的描述中，技术术语“中心”“纵向”“横向”“长度”“宽度”“厚度”“上”“下”“前”“后”“左”“右”“竖直”“水平”“顶”“底”“内”“外”“顺时针”“逆时针”“轴向”“径向”“周向”等指示的方位或位置关系为基于附图所示的方位或位置关系，仅是为了便于描述本申请实施例和简化描述，而不是指示或暗示所指的装置或元件必须具有特定的方位、以特定的方位构造和操作，因此不能理解为对本申请实施例的限制。
在本申请实施例的描述中，除非另有明确的规定和限定，技术术语“安装”“相连”“连接”“固定”等术语应做广义理解，例如，可以是固定连接，也可以是可拆卸连接，或成一体；也可以是机械连接，也可以是电连接；可以是直接相连，也可以通过中间媒介间接相连，可以是两个元件内部的连通或两个元件的相互作用关系。对于本领域的普通技术人员而言，可以根据具体情况理解上述术语在本申请实施例中的具体含义。
随着科技的发展和社会的不断进步，动力电池的应用领域不断扩展，不仅被应用于电动自行车、电动摩托车、电动汽车等电动交通工具，还被应用于军事装备和航空航天等多个领域。动力电池即为工具提供动力来源的电源，多采用阀口密封式铅酸蓄电池、敞口式管式铅酸蓄电池以及磷酸铁锂蓄电池，具有高能量和高功率、高能量密度等特点。传统的电池极片缺陷检测是使用正反两组图像传感器采集图片，分别获取极片活性物质涂膜到极片边缘的距离，通过计算获得涂膜错位量，并与控制***进行闭环控制，调整涂膜区域至错位量小于规格值。现有的缺陷检测方法处于前工序涂布段/模切段检测，仅涉及涂布段检测以及涂膜区域错位量检测，缺少极片进行叠片电芯制作前的检测，无法有效管控转运过程中的损伤以及无法准确将数据绑定到具体极片及电芯上。基于此，本申请提出一种电池极片绝缘涂层缺陷的检测方法，对极片拍摄得到至少包括一个完整极片的极片图像，确定极片图像中的绝缘涂层区域和极耳区域，进而根据绝缘涂层区域和极耳区域，确定极片图像中的绝缘涂层区域的缺陷检测区域。最后，对缺陷检测区域进行缺陷检测，得到缺陷检测结果。该方法实现了对复合前极片绝缘涂层进行检测，可以精准检测出绝缘涂层区域是否存在缺陷、极耳是否存在缺陷以及极片两面的绝缘涂层区域尺寸宽度是否一致，在复合前进行检测可以与设备联动及时对存在缺陷和尺寸异常的极片进行剔废，提高设备的运行效率。
本申请实施例提供的电池极片绝缘涂层缺陷的检测方法，可以应用于电池生产线设备运行过程中，例如在叠片、卷绕或涂布工艺环节对电池极片绝缘涂层进行缺陷检测。其中，电池极片的绝缘涂层具体可以是陶瓷涂层、氧化铝涂层等，陶瓷涂层可以是采用碳化硅陶瓷或氮化硅陶瓷。以对在叠片设备上处于料卷转运过程中的极片进行电池极片绝缘涂 层缺陷为例，可以是在***极相机工位以及上阴极相机工位处，均在极片料带两侧设置相机，通过两侧相机对极片料带上的阴极片进行拍摄得到极片图像，通过对极片图像进行处理，确定极片图像中的绝缘涂层区域和极耳区域，根据绝缘涂层区域和极耳区域，确定极片图像中的绝缘涂层区域的缺陷检测区域。最后，对缺陷检测区域进行缺陷检测，得到缺陷检测结果。进一步地，缺陷检测包括对绝缘涂层区域的错位量、缺陷、极耳缺陷检测以及数据绑定存储，实现在叠片设备阴极复合前对阴极片绝缘涂层一侧极耳缺陷、绝缘涂层区域缺陷及尺寸的检测。需要说明的是，本申请实施例中涉及的电池，可以但不限应用于车辆、船舶或飞行器等用电装置中。
在一个实施例中，提供了一种电池极片绝缘涂层缺陷的检测方法，适用于对复合前阴极片进行绝缘涂层缺陷的检测。如图1所示，该方法包括：
步骤S100：获取对极片拍摄得到的极片图像。
极片图像至少包括一个完整的极片。其中，一个完整的极片包含一个完整的极耳，并以极耳为基础向两边扩展一定范围，扩展的具体范围值可根据极片的实际产品尺寸进行设定。具体地，同样以对叠片设备上的极片进行缺陷为例，可通过图像获取装置对叠片设备上处于料卷转运过程中的极片拍摄得到至少包括一个完整极片的极片图像，然后将极片图像发送给上位机，以供上位机后续进行图像处理。其中，图像获取装置可包括相机组、传感器和控制器，以上阴极相机工位为例，可将相机组中的两个相机设置在上阴极相机工位处极片料带的两侧，控制器在根据传感器判断感应到极耳后触发相机进行拍照，或者是结合极片料带的传输速度控制相机进行周期性拍照，将相机拍摄得到的极片图像上传给上位机。此外，还可针对各相机设置光源，确保环境亮度方便相机更好的进行图像采集。其中，控制器可以是PLC(Programmable Logic Controller，可编程逻辑控制器)、MCU(Micro Control Unit，微控制单元)等，相机可以是CCD(Charge Coupled Device，电荷耦合器件)相机，传感器可以是采用光电式感应传感器，上位机可以但不限于是各种个人计算机、笔记本电脑、智能手机、平板电脑和便携式可穿戴设备，便携式可穿戴设备可为智能手表、智能手环、头戴设备等。
进一步地，在对极片进行拍摄之前，还可以对两侧相机进行联合标定生成标定模型，将两个相机的坐标对齐，以便于后续进行正反面极片图像的尺寸计算，确保极片的涂膜区域错位量计算准确。此外，在相机拍摄得到极片图像后，控制器还可以将当前极片的极片标识信息一并上传给上位机，以便上位机将缺陷检测结果与极片标识信息绑定存储。
步骤S200：确定极片图像中的绝缘涂层区域和极耳区域。
其中，绝缘涂层区域指极片图像中绝缘材料涂层所在的区域，极耳区域即指极片图像中极耳所在的区域。具体地，上位机在获取到极片图像后，分析极片图像的图像数据，结 合图像数据进行图像处理，查找得到极片图像中的绝缘涂层区域和极耳区域。其中，图像数据具体可以是灰度值，通过结合极片图像中各像素点的灰度值，对极片图像通过灰度差值、寻边等方式进行处理检测，找到极片图像中的绝缘涂层区域和极耳区域。上位机对极片图像进行处理检测的方式并不唯一，具体可根据极片料带上极片的放置方式，预先在上位机中保存图像检测的方向。例如，如图9所示，若拍摄得到的极片图像中从右到左依次为当前极片的活性物质涂层区103、绝缘材料涂层区和极片极耳，则上位机对极片图像从右到左进行灰度差值和寻边检测，依次找到极片图像中的绝缘涂层区域107和极耳区域104。
步骤S300：根据绝缘涂层区域和极耳区域，确定极片图像中的绝缘涂层区域的缺陷检测区域。
其中，缺陷检测区域即对当前极片的绝缘涂层进行缺陷检测的目标区域。具体地，上位机在查找到极片图像中的绝缘涂层区域和极耳区域后，基于极耳区域找到不同极片之间的图像边界，进而结合绝缘涂层区域和极片的图像边界确定极片图像中当前极片的绝缘涂层区域的缺陷检测区域，作为后续对当前极片的绝缘涂层进行缺陷检测的目标区域。
步骤S400：对缺陷检测区域进行缺陷检测，得到缺陷检测结果。
对应地，在确定当前极片的绝缘涂层区域的缺陷检测区域后，上位机可结合预设的缺陷区域信息对缺陷检测区域进行缺陷查找，判断缺陷检测区域是否有与缺陷区域信息匹配的缺陷，进而得到当前极片的绝缘涂层区域是否存在缺陷的缺陷检测结果。
此外，在一个实施例中，步骤S400之后，该方法还包括：将缺陷检测结果与极片标识信息绑定。具体地，极片标识信息即指能够唯一确定极片的信息，极片标识信息的类型并不唯一，具体可以是极片的编号、标识码等。上位机将缺陷检测结果与极片标识信息绑定后，可以是存储至本地数据库，也可以是发送至图像获取装置中的控制器。通过将缺陷检测结果与极片标识信息绑定，实现将缺陷检测结果绑定到具体的极片，为后续对极片的剔废等操作提供数据支持。
上述电池极片绝缘涂层缺陷的检测方法，对极片拍摄得到至少包括一个完整极片的极片图像，确定极片图像中的绝缘涂层区域和极耳区域，进而根据绝缘涂层区域和极耳区域，确定极片图像中的绝缘涂层区域的缺陷检测区域。最后，对缺陷检测区域进行缺陷检测，得到缺陷检测结果。该方法实现了对复合前极片绝缘涂层进行检测，可以检测出绝缘涂层区域是否存在缺陷，以便及时对存在缺陷的极片进行剔废，检测准确性高，还提高了叠片设备的运行效率。
在一个实施例中，如图2所示，步骤S200包括步骤S210至步骤S230。
步骤S210：对极片图像进行全图寻边，得到初定位极片边缘。
具体地，上位机结合极片不同区域的排列位置，按照相应方向对极片图像进行全图寻边，找到极片图像中的初定位极片边缘。在一个实施例中，步骤S210包括：对极片图像从远离极耳的一侧向靠近极耳的方向进行全图寻边，得到初定位极片边缘。如图9所示，同样以极片图像中从右到左依次为当前极片的活性物质涂层区103、绝缘材料涂层区和极片极耳为例，则上位机通过全图寻边，对极片图像从右往左寻找初定位极片边缘106。通过从极片图像从远离极耳的一侧逐渐向靠近极耳的方向进行全图寻边，可准确查找得到初定位极片边缘。
步骤S220：根据初定位极片边缘进行重定位，确定极片图像中的绝缘涂层区域。对应地，上位机在确定极片图像中的初定位极片边缘106之后，基于初定位极片边缘106继续向靠近极耳的方向进行区域重定位，找到极片图像中的绝缘涂层区域107。
步骤S230：通过绝缘涂层区域进行寻找，确定极片图像中的极耳区域。上位机在找到极片图像中的绝缘涂层区域107之后，基于绝缘涂层区域107继续向靠近极耳的方向进行寻找，找到极片图像中的极耳区域104。
上述实施例中，通过极片图像进行全图寻边和重定位，找到极片图像中的绝缘涂层区域，进而基于确定的绝缘涂层区域找到极片图像中的极耳区域，实现逐步查找到极片图像中的不同区域，检测准确可靠。
进一步地，在一个实施例中，如图3所示，步骤S210中对极片图像从远离极耳的一侧向靠近极耳的方向进行全图寻边，得到初定位极片边缘，包括步骤S212和步骤S214。
步骤S212：对极片图像从远离极耳的一侧向靠近极耳的方向进行全图寻边。对应地，同样以对极片图像从右往左进行全图寻边为例，上位机结合极片图像不同像素点的灰度值从右往左寻找第一条由黑到白突变的预定突变边缘。其中，可以是在极片图像等间距设置N(具体数值可设定)个从图像左侧延伸至右侧的搜寻框，每个搜寻框负责检测一个边缘点。对每个搜寻框从右往左遍历像素点，寻找第一个灰度值变化到设定程度的边缘点，然后把所有搜寻框寻到的边缘点利用直线拟合算法判断是否能拟合成为一条直线，以及拟合完成的直线与极片图像上边缘的夹角是否在设定范围内(比如85°到95°之间)，若能找到与极片图像上边缘的夹角在设定范围内的直线，则认为找到预定突变边缘。
步骤S214：若寻找到预定突变边缘，确定寻边成功，将寻找到的预定突变边缘确定为初定位极片边缘。若能找到预定突变边缘，则上位机判定寻边成功，将寻找到的预定突变边缘确定为初定位极片边缘。
上述实施例中，在对极片图像从远离极耳的一侧向靠近极耳的方向进行全图寻边时，分析是否能寻找到预定突变边缘，若找到预定突变边缘则作为初定位极片边缘，进一步提高了边缘寻找的准确性。
此外，在一个实施例中，该方法还包括：若未寻找到预定突变边缘，确定寻边不成功，将极片寻边不成功信息与极片标识信息绑定。如果极片寻边不成功，则无需进行后续的区域查找操作，电池极片绝缘涂层缺陷检测结束，将极片寻边不成功信息与极片标识信息绑定后保存在本地数据库或发送至控制器。
在一个实施例中，步骤S220包括：根据初定位极片边缘确定目标绝缘涂层区域，在目标绝缘涂层区域提取确定极片图像中的绝缘涂层区域。
具体地，上位机可预先保存极片的绝缘涂层区域尺寸，如图9所示，在从右至左查找到极片图像中的初定位极片边缘106之后，从初定位极片边缘106往左侧对绝缘涂层区域进行重定位，在初定位极片边缘左侧确定一个大于或等于绝缘涂层区域尺寸的检测感兴趣区域，作为目标绝缘涂层区域。进一步地，上位机基于目标绝缘涂层区域进行区域提取，例如通过Blob算法提取得到极片图像中的绝缘涂层区域107。其中，计算机视觉中的Blob是指图像中的一块连通区域，Blob算法是对图像前景/背景分离后的二值图像，进行连通域提取和标记。通过分析二值图像中的连通区域提取得到极片图像中的绝缘涂层区域。
上述实施例中，在根据初定位极片边缘确定目标绝缘涂层区域后，进而基于目标绝缘涂层区域提取极片图像中的绝缘涂层区域，方便快速寻找到绝缘涂层区域。
在一个实施例中，如图4所示，步骤S230包括步骤S232和步骤S234。
步骤S232：根据绝缘涂层区域进行区域重定位，确定目标极耳检测区域。其中，上位机在确定极片图像中的绝缘涂层区域之后，基于绝缘涂层区域继续向靠近极耳的方向进行区域重定位，确定目标极耳检测区域。
在一个实施例中，步骤S232包括：提取绝缘涂层区域的初定位绝缘边；根据初定位绝缘边，确定目标极耳检测区域。具体地，如图9所示，上位机在查找到极片图像中的绝缘涂层区域107后，将绝缘涂层区域107靠近极耳方向的边缘，具体将位于绝缘涂层区域107最左侧的边缘作为绝缘涂层区域107的初定位绝缘边105。进一步地，上位机还可预先保存极片的极耳尺寸，通过获得的初定位绝缘边105的位置进行重定位，在初定位绝缘边105左侧确定一个大于或等于极耳尺寸的极耳检测框，作为目标极耳检测区域。通过提取陶瓷涂层区的初定位绝缘边，结合初定位绝缘边选定目标极耳检测区域，可快速准确的确定目标极耳检测区域。
此外，在一个实施例中，该方法还可包括：若绝缘涂层区域的初定位绝缘边提取不成功，则将绝缘边寻边不成功信息与极片标识信息绑定。如果初定位绝缘边寻边不成功，则同样无需进行后续操作，电池极片绝缘涂层缺陷检测结束，将绝缘边寻边不成功信息与极片标识信息绑定后保存在本地数据库或发送至控制器。
步骤S234：在目标极耳检测区域中查找提取极耳区域。上位机在确定目标极耳检测 区域之后，对目标极耳检测区域内的图像进行分析，提取得到极耳区域。
在一个实施例中，步骤S234包括：提取目标极耳检测区域中符合极耳灰度特征的区域，获得初步极耳区域；根据初步极耳区域的区域形状和区域大小，确定初步极耳区域是否为极耳，若是，确定得到极耳区域。具体地，上位机对目标极耳检测区域内的图像进行二值化处理，对二值化处理后的图像进行灰度值分析，提取符合极耳灰度特征的区域作为初步极耳区域。进一步地，上位机再结合预设的极耳特征参数对初步极耳区域的区域形状和区域大小进行分析，判断初步极耳区域是否为极耳。若初步极耳区域为极耳，则找到极耳区域104。其中，极耳特征参数可包括极耳形状和尺寸等参数，如果初步极耳区域的区域形状、区域大小与预设的极耳形状、尺寸相同，或者差值在预设允许范围内，则可认为初步极耳区域的区域形状和区域大小与极耳特征参数一致，确定初步极耳区域为极耳。通过结合极耳灰度特征对目标极耳检测区域进行初步筛选确定初步极耳区域，进而结合初步极耳区域的区域形状和区域大小分析是否查找到极耳区域，可确保极耳区域的查找准确性。
上述实施例中，结合绝缘涂层区域进行区域重定位，确定目标极耳检测区域后，再基于目标极耳检测区域查找极耳区域，同样可方便快速寻找到极耳区域。
此外，在一个实施例中，该方法还可包括：若确定初步极耳区域不是极耳，则将极耳不存在信息与极片标识信息绑定。如果极耳不存在，则同样无需进行后续操作，电池极片绝缘涂层缺陷检测结束，将极耳不存在信息与极片标识信息绑定后保存在本地数据库或发送至控制器。
在一个实施例中，如图5所示，步骤S300包括步骤S310至步骤S330。
步骤S310：对极耳区域进行寻边，得到极耳边缘。在查找到极耳区域后，上位机可以是在极耳区域沿与初定位绝缘边平行的方向进行寻边，查找极耳边缘。如图9所示，同样以对极片图像从右往左逐步寻找到初定位极片边缘106和初定位绝缘边105为例，则上位机对极耳区域104沿上下方向，通过寻边算法对极耳边缘进行寻边，找到极耳的上边缘110和下边缘111。具体地，可先根据极耳区域104的位置，在极耳区域104上下边缘位置确定两个极耳边缘的寻边框，然后在各寻边框内沿上下方向遍历像素点，寻找灰度值变化到达到预设程度的边缘点，如果将同一个寻边框内找到的多个边缘点拟合得到一条直线，则该寻边框内寻找极耳边缘成功。
步骤S320：根据极耳边缘和预设距离数据，得到极片边缘。其中，预设距离数据为极耳边缘与极片边缘的距离数据，预设距离数据的具体取值可根据实际产品中极片边缘与极耳边缘的距离来进行设置。具体地，如图9所示，极片边缘包括极片上边缘112和极片下边缘113，在寻找到极耳边缘后，在极耳上边缘110的位置加上预设距离数据便可找到 极片上边缘112，在极耳下边缘111的位置加上预设距离数据便可找到极片下边缘113。
步骤S330：根据初定位极片边缘、初定位绝缘边和极片边缘，确定极片图像中的绝缘涂层区域的缺陷检测区域。对应地，上位机在确定初定位极片边缘106、初定位绝缘边105、极片上边缘112和极片下边缘113之后，结合四条边缘拟合生成当前极片的绝缘涂层区域107的缺陷检测区域。
上述实施例中，在查找到极耳区域之后，结合极耳边缘和预设距离数据确定极片边缘，进而根据初定位极片边缘、初定位绝缘边和极片边缘，可准确查找到绝缘涂层区域中的缺陷检测区域，以便后续进行缺陷检测。
此外，在一个实施例中，该方法还包括：若对极耳区域寻边不成功，则将极耳寻边不成功信息与极片标识信息绑定后输出。如果对极耳区域寻边不成功，则同样无需进行后续操作，电池极片绝缘涂层缺陷检测结束，将极耳寻边不成功信息与极片标识信息绑定后保存在本地数据库或发送至控制器。
在一个实施例中，如图6所示，步骤S400包括步骤S410和步骤S420。
步骤S410：提取缺陷检测区域中的连通域。其中，连通域即指缺陷检测区域中灰度值均在同一个设定范围内且相邻的像素点的集合。在确定当前极片的绝缘涂层区域的缺陷检测区域之后，上位机同样可对缺陷检测区域进行Blob算法处理，获取处理后的二值图像中的连通域。
步骤S420：若存在与预定缺陷区域相似的连通域，确定存在缺陷。缺陷检测结果包括存在缺陷的信息。可预先根据极片的绝缘涂层区域实际可能出现的缺陷，生成相应的预定缺陷区域信息并保存在上位机中，预定缺陷区域信息可包括预定缺陷区域的位置、形状以及尺寸等信息，上位机结合预定缺陷区域信息分析缺陷检测区域的连通域与预定缺陷区域是否相似，例如，如果缺陷检测区域的连通域与预定缺陷区域在位置、形状和尺寸上的相似度均高于相应设定阈值，则可认为该连通域与预定缺陷区域相似，进而确定缺陷检测区域存在缺陷。
上述实施例中，通过提取缺陷检测区域中的连通域与预定缺陷区域进行对比，分析缺陷检测区域是否存在缺陷，检测准确高效。
需要说明的是，在检测当前极片的绝缘涂层区域是否存在缺陷时，可以是根据两个相机分别对极片的复合面和非复合面拍摄得到的两张极片图像，同步对两张极片图像进行分析，确定两个极片图像中绝缘涂层区域的缺陷检测区域，进而检测两个极片图像中的缺陷检测区域是否存在与预定缺陷区域相似的连通域，如果两个极片图像中的缺陷检测区域都不存在与预定缺陷区域相似的连通域，则认为当前极片的绝缘涂层区域不存在缺陷；如果在一个或两个极片图像的缺陷检测区域检测到与预定缺陷区域相似的连通域，则认为当前 极片的绝缘涂层区域存在缺陷。
在其他实施例中，上述方法还可以是先通过步骤S100-步骤S400，对其中一个极片图像进行图像分析，找到该极片图像中的缺陷检测区域并分析是否存在与预定缺陷区域相似的连通域，如果存在，则认为当前极片的绝缘涂层区域存在缺陷，无需对另一个极片图像进行分析；如果不存在，则再通过步骤S100-步骤S400，找到另一个极片图像中的缺陷检测区域并分析是否存在与预定缺陷区域相似的连通域。如果另一个极片图像中的缺陷检测区域也不存在与预定缺陷区域相似的连通域，则认为当前极片的绝缘涂层区域不存在缺陷，反之，则同样认为当前极片的绝缘涂层区域存在缺陷。此外，如果确定预定缺陷区域存在缺陷，则上位机将存在缺陷的信息与极片标识信息绑定后存储至本地数据库或发送至控制器。
进一步地，在一个实施例中，步骤S400还包括步骤S430：若不存在与预定缺陷区域相似的连通域，计算极片的涂膜区域错位量。缺陷检测结果包括不存在缺陷的信息和涂膜区域错位量。具体地，若对当前极片拍摄的两张极片图像中的缺陷检测区域都不存在与预定缺陷区域相似的连通域，则认为当前极片的绝缘涂层不存在缺陷，结合两个极片图像对当前极片的涂膜区域错位量进行计算。此外，上位机还可将不存在缺陷的信息和涂膜区域错位量，与极片标识信息绑定后存储至本地数据库或发送至控制器。
上述实施例中，在绝缘涂层区域的缺陷检测区域中不存在缺陷时，还计算极片的涂膜区域错位量，以用作分析极片两面的绝缘涂层区域尺寸宽度是否一致，以便对存在尺寸异常的极片进行剔废，进一步提高了电池极片的缺陷检测准确性。
在一个实施例中，极片图像包括对极片的两面拍摄得到的第一极片图像和第二极片图像；步骤S430包括：若第一极片图像和第二极片图像对应的缺陷检测区域中，均不存在与预定缺陷区域相似的连通域，计算极片的涂膜区域错位量。其中，第一极片图像和第二极片图像即分别对当前极片的复合面和非复合面拍摄得到的极片图像，在两个极片图像中的缺陷检测区域均不存在与预定缺陷区域相似的连通域时，则上位机判定当前极片的绝缘涂层不存在缺陷，计算极片的涂膜区域错位量。结合对极片的两面拍摄得到的极片图像，分别检测相应的缺陷检测区域是否存在缺陷，在确定两个极片图像的缺陷检测区域都不存在缺陷时，再计算极片的涂膜区域错位量，提高了对极片绝缘涂层区域的缺陷检测准确性。
进一步地，在一个实施例中，极片图像包括对极片的两面拍摄得到的第一极片图像和第二极片图像；如图7所示，步骤S430中计算极片的涂膜区域错位量，包括步骤S432至步骤S438。
步骤S432：对第一极片图像中的绝缘涂层区域的缺陷检测区域进行寻边，得到第一极片虚边和第一绝缘边。具体地，在确定第一极片图像中的绝缘涂层区域的缺陷检测区域， 并判断缺陷检测区域不存在与预定缺陷区域相似的连通域时，对缺陷检测区域进行寻边，找到第一极片图像中的第一极片虚边和第一绝缘边。
在一个实施例中，步骤S432包括：寻找第一极片图像中的绝缘涂层区域的缺陷检测区域的边缘点；根据寻找到的边缘点进行拟合，得到第一极片虚边和第一绝缘边。具体地，基于当前极片在第一极片图像中绝缘涂层区域的缺陷检测区域，根据初定位极片边缘、初定位绝缘边、极片上边缘和极片下边缘确定一个当前极片的绝缘边寻边框和极片虚边寻边框，然后分别在绝缘边寻边框和极片虚边寻边框内通过寻边算法进行寻边，找到两个寻边框内的边缘点，进而根据各寻边框内的边缘点进行拟合，对应得到第一极片虚边和第一绝缘边。通过寻找绝缘涂层区域的缺陷检测区域的边缘点，再结合寻找到的边缘点进行拟合来确定极片虚边和绝缘边，提高极片虚边和绝缘边的查找成功率。
进一步地，在寻找第一极片图像中的绝缘涂层区域的缺陷检测区域的边缘点之后，该方法还可包括对边缘点进行滤除的步骤，从而滤除异常的边缘点，然后结合滤除后剩下的边缘点进行拟合，对应得到第一极片虚边和第一绝缘边。其中，对边缘点进行滤除的方式并不唯一，具体可通过拟合算法对边缘点进行滤除，例如结合各边缘点的位置采用加权最小二乘法滤除异常的边缘点。
步骤S434：对第二极片图像中的绝缘涂层区域的缺陷检测区域进行寻边，得到第二极片虚边和第二绝缘边。可以理解，对第二极片图像中的绝缘涂层区域的缺陷检测区域进行寻边，并得到第二极片虚边和第二绝缘边的方式与步骤S432类似，在此不再赘述。
步骤S436：根据第一极片虚边和第一绝缘边，计算得到第一绝缘涂层区域宽度，并根据第二极片虚边和第二绝缘边，计算得到第二绝缘涂层区域宽度。在找到第一极片图像中的第一极片虚边和第一绝缘边，以及第二极片图像中的第二极片虚边和第二绝缘边之后，上位机计算第一极片虚边和第一绝缘边之间的距离，得到第一极片图像中的绝缘涂层区域宽度，即第一绝缘涂层区域宽度。上位机再计算第二极片虚边和第二绝缘边之间的距离，得到第二极片图像中的绝缘涂层区域宽度，即第二绝缘涂层区域宽度。
步骤S438：根据第一绝缘涂层区域宽度和第二绝缘涂层区域宽度，计算得到极片的涂膜区域错位量。对应地，上位机将第一绝缘涂层区域宽度和第二绝缘涂层区域宽度相减，得到的差值则为当前极片的涂膜区域错位量。
上述实施例中，结合两个极片图像中绝缘涂层区域的缺陷检测区域进行寻边，找到对应的极片虚边和绝缘边，进而根据极片虚边和绝缘边计算得到两个极片图像中的绝缘涂层区域宽度，最后根据两个极片图像中的绝缘涂层区域宽度，可准确计算得到极片的涂膜区域错位量。
此外，在一个实施例中，该方法还可包括：若未寻找到边缘点，则将边缘点寻找不成 功信息与极片标识信息绑定后输出。如果对第一极片图像或第二极片图像中缺陷检测区域的边缘点寻找不成功，则同样无需进行后续操作，电池极片绝缘涂层缺陷检测结束，将边缘点寻找不成功信息与极片标识信息绑定后保存在本地数据库或发送至控制器。
为便于更好地理解上述电池极片绝缘涂层缺陷的检测方法，下面结合具体实施例进行详细解释说明。
针对现有电池极片缺陷检测仅涉及涂布段检测以及涂膜区域错位量检测，未涉及绝缘涂层缺陷检测，涂布过程检测无法将数据绑定到具体极片的问题，本申请提出一种阳极连续叠片复合前阴极片绝缘涂层尺寸缺陷在线检测方法，利用高效率高精度视觉算法对复合前阴极片绝缘涂层进行检测，可以精准检测出绝缘涂层区域是否存在缺陷、极耳是否存在缺陷以及阴极片两面的绝缘涂层区域尺寸宽度是否一致，在复合前进行检测可以与设备联动及时对存在缺陷和尺寸异常的极片进行剔废，提高设备运行效率，降低漏杀风险。具体地，如图8所示为绝缘涂层缺陷检测硬件布局示意图，在阴极料带两侧分别架设一个高帧率面阵相机，并分别架设一个白色条形光源由侧面对绝缘涂层区域打光。其中，A101为阴极料带，A102为检测相机1，A103为检测相机1对应光源，A104为检测相机2，A105为检测相机2对应光源。极片料带两侧各一个相机对绝缘涂层区域进行拍摄，两侧相机进行联合标定生成标定模型，PLC通过感应极耳触发相机拍照并给出当前极片的唯一标识码，利用上位机中的视觉软件对图像通过灰度差值、寻边等手段进行处理检测，实现对绝缘涂层区域的错位量、缺陷以及极耳缺陷检测以及数据绑定存储。
如图9所示为实施例中相机的成像示意图，各区域名称如下：101：前一个阴极片；102：下一个阴极片；103：当前阴极片活性物质涂层区；104：当前阴极片极耳，即极耳区域；105：初定位绝缘边，即绝缘材料涂层区外边缘；106：阴极虚边/初定位极片边缘，即阴极极片活性物质涂层区与绝缘材料涂层区交界边；107：绝缘材料涂层区，即绝缘涂层区域；108：极耳上边缘与当前极片上边缘偏移量；109：极耳下边缘与当前极片下边缘偏移量；110：极耳上边缘；111：极耳下边缘；112：极片上边缘；113：极片下边缘。
图10为错位量的计算方式示意图，其中，A面为对极片的非复合面拍摄得到，B面为对极片的复合面拍摄得到。该缺陷检测方法的缺陷检测项目包括：106区域漏金属破损缺陷检测、106区域宽度检测、106区域宽度AB面的错位量以及104区域极耳缺失检测。
该缺陷检测方法通过定位极片边和绝缘涂层区域将准确对检测区域进行重定位，将检测框准确定位到对应需要检测的区域，然后通过寻边、尺寸测量以及缺陷检测算法分别进行检测，输出缺陷检测结果，在叠片设备上检测绝缘涂层可以管控到料卷转运过程的绝缘涂层的损伤，可以为设备提供极片数据，为后续剔废等操作提供数据支持；给每张极片绑定唯一编号进行存储可以使得每个极片的绝缘涂层数据具有可追溯性。该检测方法的检测 精度高，像素精度可达0.02mm，检测效率快，单次检测时间小于20ms。
应该理解的是，虽然如上的各实施例所涉及的流程图中的各个步骤按照箭头的指示依次显示，但是这些步骤并不是必然按照箭头指示的顺序依次执行。除非本文中有明确的说明，这些步骤的执行并没有严格的顺序限制，这些步骤可以以其它的顺序执行。而且，如上的各实施例所涉及的流程图中的至少一部分步骤可以包括多个步骤或者多个阶段，这些步骤或者阶段并不必然是在同一时刻执行完成，而是可以在不同的时刻执行，这些步骤或者阶段的执行顺序也不必然是依次进行，而是可以与其它步骤或者其它步骤中的步骤或者阶段的至少一部分轮流或者交替地执行。
基于同样的发明构思，本申请实施例还提供了一种用于实现上述所涉及的电池极片绝缘涂层缺陷的检测方法的电池极片绝缘涂层缺陷的检测装置。该装置所提供的解决问题的实现方案与上述方法中所记载的实现方案相似，故下面所提供的一个或多个换电处理装置实施例中的具体限定可以参见上文中对于电池极片绝缘涂层缺陷的检测方法的限定，在此不再赘述。
在一个实施例中，提供了一种电池极片绝缘涂层缺陷的检测装置，适用于对复合前阴极片进行绝缘涂层缺陷的检测。如图11所示，该装置包括：图像获取模块100、图像分析模块200、区域提取模块300和缺陷分析模块400，其中：
图像获取模块100，用于获取对极片拍摄得到的极片图像，极片图像至少包括一个完整的极片。
图像分析模块200，用于确定极片图像中的绝缘涂层区域和极耳区域。
区域提取模块300，用于根据绝缘涂层区域和极耳区域，确定极片图像中的绝缘涂层区域的缺陷检测区域。
缺陷分析模块400，用于对缺陷检测区域进行缺陷检测，得到缺陷检测结果。
在一个实施例中，图像分析模块200对极片图像进行全图寻边，得到初定位极片边缘；根据初定位极片边缘进行重定位，确定极片图像中的绝缘涂层区域；通过绝缘涂层区域进行寻找，确定极片图像中的极耳区域。
在一个实施例中，图像分析模块200对极片图像从远离极耳的一侧向靠近极耳的方向进行全图寻边，得到初定位极片边缘。
在一个实施例中，图像分析模块200对极片图像从远离极耳的一侧向靠近极耳的方向进行全图寻边：若寻找到预定突变边缘，确定寻边成功，将寻找到的预定突变边缘确定为初定位极片边缘。
在一个实施例中，图像分析模块200根据初定位极片边缘确定目标绝缘涂层区域，在目标绝缘涂层区域提取确定极片图像中的绝缘涂层区域。
在一个实施例中，图像分析模块200根据绝缘涂层区域进行区域重定位，确定目标极耳检测区域；在目标极耳检测区域中查找提取极耳区域。
在一个实施例中，图像分析模块200提取绝缘涂层区域的初定位绝缘边；根据初定位绝缘边，确定目标极耳检测区域。
在一个实施例中，图像分析模块200提取目标极耳检测区域中符合极耳灰度特征的区域，获得初步极耳区域；根据初步极耳区域的区域形状和区域大小，确定初步极耳区域是否为极耳，若是，确定得到极耳区域。
在一个实施例中，区域提取模块300对极耳区域进行寻边，得到极耳边缘；根据极耳边缘和预设距离数据，得到极片边缘，预设距离数据为极耳边缘与极片边缘的距离数据；根据初定位极片边缘、初定位绝缘边和极片边缘，确定极片图像中的绝缘涂层区域的缺陷检测区域。
在一个实施例中，缺陷分析模块400提取缺陷检测区域中的连通域；若存在与预定缺陷区域相似的连通域，确定存在缺陷；缺陷检测结果包括存在缺陷的信息。
在一个实施例中，缺陷分析模块400还在不存在与预定缺陷区域相似的连通域时，计算极片的涂膜区域错位量；缺陷检测结果包括不存在缺陷的信息和涂膜区域错位量。
在一个实施例中，极片图像包括对极片的两面拍摄得到的第一极片图像和第二极片图像；缺陷分析模块400在第一极片图像和第二极片图像对应的缺陷检测区域中，均不存在与预定缺陷区域相似的连通域时，计算极片的涂膜区域错位量。
在一个实施例中，极片图像包括对极片的两面拍摄得到的第一极片图像和第二极片图像；缺陷分析模块400对第一极片图像中的绝缘涂层区域的缺陷检测区域进行寻边，得到第一极片虚边和第一绝缘边；对第二极片图像中的绝缘涂层区域的缺陷检测区域进行寻边，得到第二极片虚边和第二绝缘边；根据第一极片虚边和第一绝缘边，计算得到第一绝缘涂层区域宽度，并根据第二极片虚边和第二绝缘边，计算得到第二绝缘涂层区域宽度；根据第一绝缘涂层区域宽度和第二绝缘涂层区域宽度，计算得到极片的涂膜区域错位量。
在一个实施例中，缺陷分析模块400寻找第一极片图像中的绝缘涂层区域的缺陷检测区域的边缘点；根据寻找到的边缘点进行拟合，得到第一极片虚边和第一绝缘边。
在一个实施例中，缺陷分析模块400还将缺陷检测结果与极片标识信息绑定。
在一个实施例中，提供了一种计算机设备，该计算机设备可以是服务器，还可以是终端，以服务器为例，其内部结构图可以如图12所示。该计算机设备包括通过***总线连接的处理器、存储器和网络接口。其中，该计算机设备的处理器用于提供计算和控制能力。该计算机设备的存储器包括非易失性存储介质和内存储器。该非易失性存储介质存储有操作***、计算机程序和数据库。该内存储器为非易失性存储介质中的操作***和计算机程 序的运行提供环境。该计算机设备的数据库用于存储缺陷检测结果数据。该计算机设备的网络接口用于与外部的终端通过网络连接通信。该计算机程序被处理器执行时以实现一种电池极片绝缘涂层缺陷的检测方法。
本领域技术人员可以理解，图12中示出的结构，仅仅是与本申请方案相关的部分结构的框图，并不构成对本申请方案所应用于其上的计算机设备的限定，具体的计算机设备可以包括比图中所示更多或更少的部件，或者组合某些部件，或者具有不同的部件布置。
在一个实施例中，提供了一种计算机设备，包括存储器和处理器，存储器存储有计算机程序，处理器执行计算机程序时实现上述各方法实施例中的步骤。
在一个实施例中，提供了一种计算机可读存储介质，其上存储有计算机程序，计算机程序被处理器执行时实现上述各方法实施例中的步骤。
在一个实施例中，提供了一种计算机程序产品，包括计算机程序，该计算机程序被处理器执行时实现上述各方法实施例中的步骤。
在一个实施例中，还提供了一种电池极片缺陷检测***，包括图像获取装置和上位机，图像获取装置用于对极片拍摄得到极片图像，并将极片图像发送至上位机，上位机用于根据上述方法进行电池极片绝缘涂层缺陷的检测。其中，图像获取装置具体包括相机组、传感器和控制器，控制器连接相机组、传感器和上位机。控制器可以是PLC、MCU等，相机组可以是CCD相机组，传感器可以是采用光电式感应传感器，上位机可以但不限于是各种个人计算机、笔记本电脑、智能手机、平板电脑和便携式可穿戴设备，便携式可穿戴设备可为智能手表、智能手环、头戴设备等。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机程序来指令相关的硬件来完成，该计算机程序可存储于一计算机可读取存储介质中，该程序在执行时，可包括如上述各方法的实施例的流程。其中，前述的存储介质可为磁碟、光盘、只读存储记忆体(Read-Only Memory，ROM)等非易失性存储介质，或随机存储记忆体(Random Access Memory，RAM)等。
以上实施例的各技术特征可以进行任意的组合，为使描述简洁，未对上述实施例中的各个技术特征所有可能的组合都进行描述，然而，只要这些技术特征的组合不存在矛盾，都应当认为是本说明书记载的范围。
以上实施例仅表达了本发明的几种实施方式，其描述较为具体和详细，但并不能因此而理解为对发明专利范围的限制。应当指出的是，对于本领域的普通技术人员来说，在不脱离本发明构思的前提下，还可以做出若干变形和改进，这些都属于本发明的保护范围。因此，本发明专利的保护范围应以所附权利要求为准。

Claims (20)

  1. 一种电池极片绝缘涂层缺陷的检测方法，其特征在于，包括：
    获取对极片拍摄得到的极片图像，所述极片图像至少包括一个完整的极片；
    确定所述极片图像中的绝缘涂层区域和极耳区域；
    根据所述绝缘涂层区域和极耳区域，确定所述极片图像中的绝缘涂层区域的缺陷检测区域；
    对所述缺陷检测区域进行缺陷检测，得到缺陷检测结果。
  2. 根据权利要求1所述的方法，其特征在于，所述确定所述极片图像中的绝缘涂层区域和极耳区域，包括：
    对所述极片图像进行全图寻边，得到初定位极片边缘；
    根据所述初定位极片边缘进行重定位，确定所述极片图像中的绝缘涂层区域；
    通过所述绝缘涂层区域进行寻找，确定所述极片图像中的极耳区域。
  3. 根据权利要求2所述的方法，其特征在于，所述对所述极片图像进行全图寻边，得到初定位极片边缘，包括：
    对所述极片图像从远离极耳的一侧向靠近极耳的方向进行全图寻边，得到所述初定位极片边缘。
  4. 根据权利要求3所述的方法，其特征在于，所述对所述极片图像从远离极耳的一侧向靠近极耳的方向进行全图寻边，得到所述初定位极片边缘，包括：
    对所述极片图像从远离极耳的一侧向靠近极耳的方向进行全图寻边：
    若寻找到预定突变边缘，确定寻边成功，将寻找到的预定突变边缘确定为所述初定位极片边缘。
  5. 根据权利要求2所述的方法，其特征在于，所述根据所述初定位极片边缘进行重定位，确定所述极片图像中的绝缘涂层区域，包括：
    根据所述初定位极片边缘确定目标绝缘涂层区域，在所述目标绝缘涂层区域提取确定所述极片图像中的绝缘涂层区域。
  6. 根据权利要求2所述的方法，其特征在于，所述通过所述绝缘涂层区域进行寻找，确定所述极片图像中的极耳区域，包括：
    根据所述绝缘涂层区域进行区域重定位，确定目标极耳检测区域；
    在所述目标极耳检测区域中查找提取极耳区域。
  7. 根据权利要求6所述的方法，其特征在于，所述根据所述绝缘涂层区域进行区域重定位，确定目标极耳检测区域，包括：
    提取所述绝缘涂层区域的初定位绝缘边；
    根据所述初定位绝缘边，确定目标极耳检测区域。
  8. 根据权利要求6所述的方法，其特征在于，所述在所述目标极耳检测区域中查找提取极耳区域，包括：
    提取所述目标极耳检测区域中符合极耳灰度特征的区域，获得初步极耳区域；
    根据所述初步极耳区域的区域形状和区域大小，确定所述初步极耳区域是否为极耳，若是，确定得到极耳区域。
  9. 根据权利要求7所述的方法，其特征在于，所述根据所述绝缘涂层区域和极耳区域，确定所述极片图像中的绝缘涂层区域的缺陷检测区域，包括：
    对所述极耳区域进行寻边，得到极耳边缘；
    根据所述极耳边缘和预设距离数据，得到极片边缘，所述预设距离数据为极耳边缘与极片边缘的距离数据；
    根据所述初定位极片边缘、所述初定位绝缘边和所述极片边缘，确定所述极片图像中的绝缘涂层区域的缺陷检测区域。
  10. 根据权利要求1所述的方法，其特征在于，所述对所述缺陷检测区域进行缺陷检测，得到缺陷检测结果，包括：
    提取所述缺陷检测区域中的连通域；
    若存在与预定缺陷区域相似的所述连通域，确定存在缺陷；所述缺陷检测结果包括存在缺陷的信息。
  11. 根据权利要求10所述的方法，其特征在于，所述对所述缺陷检测区域进行缺陷检测，得到缺陷检测结果，还包括：
    若不存在与所述预定缺陷区域相似的所述连通域，计算所述极片的涂膜区域错位量；所述缺陷检测结果包括不存在缺陷的信息和所述涂膜区域错位量。
  12. 根据权利要求11所述的方法，其特征在于，所述极片图像包括对所述极片的两面拍摄得到的第一极片图像和第二极片图像；
    所述若不存在与所述预定缺陷区域相似的所述连通域，计算所述极片的涂膜区域错位量，包括：
    若所述第一极片图像和所述第二极片图像对应的缺陷检测区域中，均不存在与所述预定缺陷区域相似的所述连通域，计算所述极片的涂膜区域错位量。
  13. 根据权利要求11所述的方法，其特征在于，所述极片图像包括对所述极片的两面拍摄得到的第一极片图像和第二极片图像；所述计算所述极片的涂膜区域错位量，包括：
    对所述第一极片图像中的绝缘涂层区域的缺陷检测区域进行寻边，得到第一极片虚边和第一绝缘边；
    对所述第二极片图像中的绝缘涂层区域的缺陷检测区域进行寻边，得到第二极片虚边和第二绝缘边；
    根据所述第一极片虚边和所述第一绝缘边，计算得到第一绝缘涂层区域宽度，并根据所述第二极片虚边和所述第二绝缘边，计算得到第二绝缘涂层区域宽度；
    根据所述第一绝缘涂层区域宽度和所述第二绝缘涂层区域宽度，计算得到所述极片的涂膜区域错位量。
  14. 根据权利要求13所述的方法，其特征在于，所述对所述第一极片图像中的绝缘涂层区域的缺陷检测区域进行寻边，得到第一极片虚边和第一绝缘边，包括：
    寻找所述第一极片图像中的绝缘涂层区域的缺陷检测区域的边缘点；
    根据寻找到的边缘点进行拟合，得到所述第一极片虚边和所述第一绝缘边。
  15. 根据权利要求1-14任意一项所述的方法，其特征在于，对所述缺陷检测区域进行缺陷检测，得到缺陷检测结果之后，该方法还包括：将所述缺陷检测结果与极片标识信息绑定。
  16. 一种电池极片绝缘涂层缺陷的检测装置，其特征在于，包括：
    图像获取模块，用于获取对极片拍摄得到的极片图像，所述极片图像至少包括一个完整的极片；
    图像分析模块，用于确定所述极片图像中的绝缘涂层区域和极耳区域；
    区域提取模块，用于根据所述绝缘涂层区域和极耳区域，确定所述极片图像中的绝缘涂层区域的缺陷检测区域；
    缺陷分析模块，用于对所述缺陷检测区域进行缺陷检测，得到缺陷检测结果。
  17. 一种计算机设备，包括存储器和处理器，所述存储器存储有计算机程序，其特征在于，所述处理器执行所述计算机程序时实现权利要求1至15中任一项所述的方法的步骤。
  18. 一种计算机可读存储介质，其上存储有计算机程序，其特征在于，所述计算机程序被处理器执行时实现权利要求1至15中任一项所述的方法的步骤。
  19. 一种计算机程序产品，包括计算机程序，其特征在于，该计算机程序被处理器执行时实现权利要求1至15中任一项所述的方法的步骤。
  20. 一种电池极片缺陷检测***，其特征在于，包括图像获取装置和上位机，所述图像获取装置用于对极片拍摄得到极片图像，并将所述极片图像发送至所述上位机，所述上位机用于根据权利要求1-15任意一项所述的方法进行电池极片绝缘涂层缺陷的检测。
PCT/CN2022/085690 2022-04-08 2022-04-08 电池极片绝缘涂层缺陷的检测方法、装置和计算机设备 WO2023193213A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
PCT/CN2022/085690 WO2023193213A1 (zh) 2022-04-08 2022-04-08 电池极片绝缘涂层缺陷的检测方法、装置和计算机设备
EP22936156.3A EP4383398A1 (en) 2022-04-08 2022-04-08 Method and apparatus for detecting defect of insulating coating of battery electrode plate, and computer device
KR1020247011254A KR20240050461A (ko) 2022-04-08 2022-04-08 배터리 전극 시트 절연 코팅층 결함의 검출 방법, 장치 및 컴퓨터 장치
CN202280032976.XA CN117280513A (zh) 2022-04-08 2022-04-08 电池极片绝缘涂层缺陷的检测方法、装置和计算机设备

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2022/085690 WO2023193213A1 (zh) 2022-04-08 2022-04-08 电池极片绝缘涂层缺陷的检测方法、装置和计算机设备

Publications (1)

Publication Number Publication Date
WO2023193213A1 true WO2023193213A1 (zh) 2023-10-12

Family

ID=88243756

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/085690 WO2023193213A1 (zh) 2022-04-08 2022-04-08 电池极片绝缘涂层缺陷的检测方法、装置和计算机设备

Country Status (4)

Country Link
EP (1) EP4383398A1 (zh)
KR (1) KR20240050461A (zh)
CN (1) CN117280513A (zh)
WO (1) WO2023193213A1 (zh)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117109447A (zh) * 2023-10-24 2023-11-24 钛玛科（北京）工业科技有限公司 自适应极耳宽度检测方法、装置及设备
CN117181891A (zh) * 2023-11-06 2023-12-08 宁德时代新能源科技股份有限公司 料带的检测方法和模切机
CN117213372A (zh) * 2023-11-09 2023-12-12 宁德时代新能源科技股份有限公司 极片检测方法及***
CN117781914A (zh) * 2024-02-28 2024-03-29 宁德时代新能源科技股份有限公司 极耳错位检测***及方法
CN118015075A (zh) * 2024-04-10 2024-05-10 江苏时代新能源科技有限公司 边缘定位方法及***

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117782995B (zh) * 2024-02-23 2024-06-25 宁德时代新能源科技股份有限公司 缺陷检测方法、缺陷检测***、装置、设备和存储介质

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2013080667A (ja) * 2011-10-05 2013-05-02 Toyota Motor Corp 絶縁層付電極板の補修装置及び電池の製造方法
CN105244470A (zh) * 2015-09-11 2016-01-13 合肥国轩高科动力能源有限公司 一种高安全锂离子叠片电池正极片及其制备方法
CN109358070A (zh) * 2018-08-31 2019-02-19 广州超音速自动化科技股份有限公司 极片检测方法、电子设备、存储介质及***
CN210730683U (zh) * 2019-08-29 2020-06-12 宁德时代新能源科技股份有限公司 极片制备***
CN211578881U (zh) * 2019-10-30 2020-09-25 天津力神电池股份有限公司 一种降低电池自放电和提升电池安全性的锂离子电池极组
CN112215825A (zh) * 2020-10-19 2021-01-12 杭州百子尖科技股份有限公司 新能源电池制造中基于机器视觉的质量分析方法及***
CN113313711A (zh) * 2021-07-29 2021-08-27 浙江双元科技股份有限公司 一种用于锂电池极片宽度检测的相机、***及检测方法

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2013080667A (ja) * 2011-10-05 2013-05-02 Toyota Motor Corp 絶縁層付電極板の補修装置及び電池の製造方法
CN105244470A (zh) * 2015-09-11 2016-01-13 合肥国轩高科动力能源有限公司 一种高安全锂离子叠片电池正极片及其制备方法
CN109358070A (zh) * 2018-08-31 2019-02-19 广州超音速自动化科技股份有限公司 极片检测方法、电子设备、存储介质及***
CN210730683U (zh) * 2019-08-29 2020-06-12 宁德时代新能源科技股份有限公司 极片制备***
CN211578881U (zh) * 2019-10-30 2020-09-25 天津力神电池股份有限公司 一种降低电池自放电和提升电池安全性的锂离子电池极组
CN112215825A (zh) * 2020-10-19 2021-01-12 杭州百子尖科技股份有限公司 新能源电池制造中基于机器视觉的质量分析方法及***
CN113313711A (zh) * 2021-07-29 2021-08-27 浙江双元科技股份有限公司 一种用于锂电池极片宽度检测的相机、***及检测方法

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117109447A (zh) * 2023-10-24 2023-11-24 钛玛科（北京）工业科技有限公司 自适应极耳宽度检测方法、装置及设备
CN117109447B (zh) * 2023-10-24 2024-01-05 钛玛科（北京）工业科技有限公司 自适应极耳宽度检测方法、装置及设备
CN117181891A (zh) * 2023-11-06 2023-12-08 宁德时代新能源科技股份有限公司 料带的检测方法和模切机
CN117181891B (zh) * 2023-11-06 2024-04-12 宁德时代新能源科技股份有限公司 料带的检测方法和模切机
CN117213372A (zh) * 2023-11-09 2023-12-12 宁德时代新能源科技股份有限公司 极片检测方法及***
CN117213372B (zh) * 2023-11-09 2024-04-09 宁德时代新能源科技股份有限公司 极片检测方法及***
CN117781914A (zh) * 2024-02-28 2024-03-29 宁德时代新能源科技股份有限公司 极耳错位检测***及方法
CN118015075A (zh) * 2024-04-10 2024-05-10 江苏时代新能源科技有限公司 边缘定位方法及***

Also Published As

Publication number Publication date
KR20240050461A (ko) 2024-04-18
CN117280513A (zh) 2023-12-22
EP4383398A1 (en) 2024-06-12

Similar Documents

Publication Publication Date Title
WO2023193213A1 (zh) 电池极片绝缘涂层缺陷的检测方法、装置和计算机设备
WO2024032002A1 (zh) 电芯检测方法、装置、***、计算机设备和存储介质
WO2024032000A1 (zh) 裸电芯外观检测方法、装置、计算机设备和存储介质
WO2024021662A1 (zh) 检测电芯表面缺陷的方法和装置
CN113376177A (zh) 极耳检测方法、装置及电子设备
CN113538430B (zh) 基于差分的极片缺陷检测方法、装置、设备及介质
CN110544231A (zh) 基于背景标准化和集中补偿算法的锂电池电极表面缺陷检测方法
CN115797346B (zh) 极耳状态检测方法、装置、计算机设备和存储介质
CN114740001A (zh) 一种锂电池极片尺寸检测装置及方法
WO2024093644A1 (zh) 电芯检测***及电芯检测方法
WO2023206020A1 (zh) 电池极片的Overhang检测方法、装置、设备、存储介质
WO2023070552A1 (zh) 一种电池卷芯卷绕覆盖检测方法、装置及设备
CN115839959A (zh) 极耳检测***及极耳检测方法
CN116007506A (zh) 电池极片的检测方法、装置、计算机设备及存储介质
WO2023130338A1 (zh) 极片的叠片方法、装置和叠片机
CN112989901A (zh) 基于深度学习的液位仪读数的识别方法
WO2023202209A1 (zh) 对复合料带的阴极极片进行折角检测的方法、装置和***
CN112415013A (zh) 一种铜箔缺陷检测***
CN103134757A (zh) 一种基于双目异质机器视觉的检测***及其检测方法
CN116029987A (zh) 一种焊接质量检测方法、装置及电子设备
TWI343656B (zh)
WO2024016266A1 (zh) 检测电芯组件的极耳外观的方法与装置、电子设备
CN202420442U (zh) 在线检测锂离子电池极片毛刺装置
CN117726574B (zh) 聚合物锂离子电池生产用封装***及其方法
WO2024044947A1 (zh) 缺陷检测的方法、装置和计算机可读存储介质

Legal Events

Date Code Title Description
WWE Wipo information: entry into national phase

Ref document number: 202280032976.X

Country of ref document: CN

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22936156

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2022936156

Country of ref document: EP

Effective date: 20240305

ENP Entry into the national phase

Ref document number: 20247011254

Country of ref document: KR

Kind code of ref document: A