WO2024032000A1 - 裸电芯外观检测方法、装置、计算机设备和存储介质 - Google Patents

裸电芯外观检测方法、装置、计算机设备和存储介质 Download PDF

Info

Publication number
WO2024032000A1
WO2024032000A1 PCT/CN2023/084032 CN2023084032W WO2024032000A1 WO 2024032000 A1 WO2024032000 A1 WO 2024032000A1 CN 2023084032 W CN2023084032 W CN 2023084032W WO 2024032000 A1 WO2024032000 A1 WO 2024032000A1
Authority
WO
WIPO (PCT)
Prior art keywords
detection
edge
bare
battery core
picture
Prior art date
Application number
PCT/CN2023/084032
Other languages
English (en)
French (fr)
Inventor
屠银行
刘晓锋
朱金平
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 EP23797624.6A priority Critical patent/EP4350621A1/en
Priority to US18/503,170 priority patent/US20240070852A1/en
Publication of WO2024032000A1 publication Critical patent/WO2024032000A1/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G06T7/001—Industrial image inspection using an image reference approach
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10004—Still image; Photographic image
    • G06T2207/10008—Still image; Photographic image from scanner, fax or copier
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30164—Workpiece; Machine component
    • 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
    • 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
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P70/00—Climate change mitigation technologies in the production process for final industrial or consumer products
    • Y02P70/50—Manufacturing or production processes characterised by the final manufactured product

Definitions

  • the present application relates to the technical field of battery detection, and in particular to a bare battery core appearance detection method, device, computer equipment, computer readable storage medium, computer program product and bare battery core appearance detection system.
  • lithium-ion batteries have been widely used in electric vehicles and have become one of the main power sources for electric vehicles.
  • Lithium iron phosphate batteries have the characteristics of high capacity, high output voltage, and good charge and discharge cycle performance. Bare cell appearance inspection is an extremely important process in the battery cell production process. How to improve the accuracy of bare cell appearance inspection is an urgent problem that needs to be solved.
  • this application provides a bare battery core appearance inspection method, device, computer equipment, computer readable storage medium, computer program product and bare battery core appearance inspection system.
  • this application provides a bare cell appearance detection method, which method is applied to control equipment.
  • the control equipment can be specifically implemented through a logic controller.
  • the method includes:
  • the cell picture taken from the bare cell is taken from the position of the tab on the edge of the bare cell;
  • the above-mentioned method of detecting the appearance of a bare battery cell obtains a picture of the battery core by aligning the edge of the bare battery core with the position of the tab, so that the edge of the battery core is imaged as a parallel light reflection image, which reduces the impact of the battery core tab during imaging due to the thickness of the battery core.
  • the influence of edge authenticity ensures the accuracy of image collection, thereby improving the accuracy of bare cell appearance detection.
  • the battery cell image includes a first battery cell image, the exposure of the first battery cell image is higher than a preset exposure threshold, and the detection object includes the edge of the battery cell isolation film; determine the detection object in the battery cell image It includes: determining the reference position in the first battery cell picture according to the preset battery core model, and grabbing the edge of the battery core isolation film according to the reference position.
  • a high-exposure picture is obtained by taking a high-exposure photo of the bare battery cell, which improves the edge contrast and color difference of the bare battery core, which facilitates grasping the edge of the battery cell, and determines the high-exposure picture in combination with the preset battery cell model. Reference location, convenient Accurately and quickly obtain the edge of the cell isolation film.
  • the detection result information includes size data; performing appearance detection based on the detection object, obtaining the detection result information includes:
  • the dimensional data of the bare cell can be obtained quickly and accurately.
  • edge distance data includes length data and width data; obtaining size data according to multiple edge distance data includes:
  • the size data is obtained.
  • the size data of the bare cell is obtained, which can ensure size detection. accuracy.
  • the detection result information includes the pin withdrawal detection result; performing appearance detection according to the detection area, and obtaining the detection result information includes: determining the pin withdrawal detection area according to the edge of the cell isolation film; detecting the pin withdrawal detection area, and obtaining Needle removal test results.
  • the pin withdrawal detection area is determined based on the edge of the cell isolation film, and combined with the pin withdrawal detection area, the pin withdrawal detection can be performed quickly and conveniently.
  • detecting the needle withdrawal detection area and obtaining the needle withdrawal detection result includes: searching and obtaining spot information in the needle withdrawal detection area, and obtaining the needle withdrawal detection result according to the spot information analysis.
  • the spot information is searched and obtained in the pin withdrawal detection area, and the pin withdrawal detection of the bare battery core can be quickly realized based on the obtained spot information.
  • the spot information includes at least one of a single spot area, a spot size, and a sum of spot areas.
  • detecting the needle withdrawal detection area and obtaining the needle withdrawal detection result includes:
  • the needle removal detection result is obtained through analysis.
  • the pin withdrawal detection is performed by analyzing the distance value from the edge point of the cell isolation film in the pin withdrawal detection area to the edge where it is located, which is beneficial to grasping the collective leakage of pin withdrawal phenomenon at the entire edge.
  • obtaining the needle withdrawal detection result based on multiple distance value analysis includes:
  • the needle withdrawal detection result is obtained through analysis.
  • the method further includes: the host computer binds and stores the inspection result information and the identification information of the bare battery core.
  • the battery core picture is taken by dual cameras aiming at the edge tab position of the bare battery core.
  • dual cameras are used to collect battery cell pictures, which can realize global detection of detection elements, improve the accuracy of detection results, and reduce the probability of false detection and missed detection.
  • this application provides a bare cell appearance detection device, including:
  • the picture acquisition module is used to obtain battery cell pictures taken from bare battery cells; the battery cell pictures are taken at the position of the tabs on the edge of the bare battery core;
  • Image processing module used to determine detection objects in battery cell pictures
  • the image detection module is used to perform appearance detection based on the detection object and obtain detection result information.
  • the application provides a computer device, including a memory and one or more processors.
  • Computer-readable instructions are stored in the memory.
  • processors executes the above steps of the bare cell appearance inspection method.
  • the present application provides one or more computer storage media storing computer-readable instructions.
  • the computer-readable instructions are executed by one or more processors, the one or more processors execute the above-mentioned bare cell. Steps of Appearance Inspection Method.
  • the present application provides a computer program product.
  • the computer program When the computer program is executed by one or more processors, it causes the one or more processors to execute the steps of the above-mentioned bare cell appearance inspection method.
  • the present application provides a bare battery core appearance inspection system, including an image acquisition device and a host computer.
  • the image acquisition device is used to align the position of the edge tabs of the bare battery core to photograph the battery core image, and obtain the battery core image. Send it to the host computer, which is used to conduct bare cell appearance inspection according to the above-mentioned bare cell appearance inspection method.
  • the image acquisition device includes dual cameras.
  • dual cameras are used to collect battery cell pictures, which can realize global detection of detection elements, improve the accuracy of detection results, and reduce the probability of false detection and missed detection.
  • Figure 1 is a schematic diagram of a scene of a bare cell appearance inspection method in some embodiments
  • Figure 2 is a schematic flow chart of a bare cell appearance inspection method in some embodiments
  • Figure 3 is a schematic diagram of battery cells in some embodiments.
  • Figure 4 is a schematic diagram of tab misalignment detection errors in some embodiments.
  • Figure 5 is a schematic diagram of cell size detection in some embodiments.
  • Figure 6 is a flow chart for performing appearance detection according to the detection object and obtaining detection result information in some embodiments
  • Figure 7 is a flow chart for performing appearance detection according to the detection object and obtaining detection result information in other embodiments
  • Figure 8 is a schematic diagram of battery core pin removal detection in some embodiments.
  • Figure 9 is a schematic flow chart of a bare cell appearance inspection method in other embodiments.
  • Figure 10 is a structural block diagram of a bare cell appearance detection device in some embodiments.
  • Figure 11 is an internal structure diagram of a computer device in some embodiments.
  • an embodiment means that a particular feature, structure or characteristic described in connection with the embodiment can be included in at least some embodiments 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. Explicitly and implicitly by those skilled in the art It is understood 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. Bare cell appearance inspection is an extremely important process in the battery cell production process. It plays the role of detecting whether the bare cell meets the specifications of good products. It can screen out unqualified products and reduce the flow of unqualified products into the bare cell pairing process. adverse effects.
  • this application provides a bare battery core appearance detection method, which obtains a battery core picture taken at the position of the edge tab of the bare battery core, determines the detection object in the battery core picture, performs appearance detection based on the detection object, and obtains the detection Result information.
  • the edge imaging of the battery core is parallel light reflection imaging, which reduces the impact of the thickness of the battery core on the authenticity of the edge of the battery core tabs during imaging, ensuring that the image Accuracy of collection.
  • the bare cell appearance inspection method provided by the embodiment of the present application can be applied in the application environment as shown in Figure 1.
  • the control equipment (not shown in the figure) controls the logistics line to transport the bare battery core 1 to the appearance inspection station
  • the camera 2 of the appearance inspection station is aimed at the edge tab position of the bare battery core 1 to take a picture of the battery core, and Upload the battery cell image to the control device
  • the control device determines the detection object in the battery core image, and performs appearance inspection based on the detection object to obtain the detection result information.
  • the bare battery core 1 (or at least the edge tab position of the bare battery core 1) is located within the camera shooting range of the camera 2.
  • the camera 2 is located above the bare battery core 1, so that the camera 2 can aim at the bare battery core 1.
  • the cell picture is taken from the position of the tab on the edge of core 1.
  • the number of cameras 2 is two, that is, dual cameras are used for image acquisition, which can achieve full field of view coverage of the bare battery cells.
  • camera 2 can be a CCD (Charge Coupled Device) camera or other camera.
  • the control device may include a control module and a host computer.
  • the control module controls the logistics line to transport the bare battery core 1.
  • the host computer controls the camera 2 to photograph the bare battery core 1 to obtain a picture of the battery core. Subsequently, the host computer processes the battery core picture. Image analysis obtains detection result information.
  • the control module can be a PLC (Programmable Logic Controller, programmable logic controller), MCU (Microcontroller Unit, microcontroller unit), etc.
  • the host computer can be a notebook, desktop computer or logic controller, etc.
  • the appearance inspection station is also provided with a light source 3, in which the bare battery core 1 is located within the light range emitted by the light source 3.
  • the light source 3 can be located above the bare battery core 1 to facilitate image collection by the camera 2.
  • the light source 3 may specifically include two pairs of light sources. Among them, a pair of light sources is located above the long sides of both sides of the bare battery core 1, and the other pair of light sources is located above the bare battery core 1. Above the short sides on both sides of Core 1.
  • the host computer After completing the appearance inspection of the bare battery core, the host computer also outputs instructions to the control module, and the control module controls the logistics line to transport the bare battery core 1 to the next work station, such as to the sorting station, and conducts the inspection according to the test result information. Bare battery cells 1 are sorted and so on.
  • the control module controls the logistics line to transport the bare battery core 1 to the next work station, such as to the sorting station, and conducts the inspection according to the test result information. Bare battery cells 1 are sorted and so on.
  • the following is an example of using a PLC as the control module and a logic controller as the host computer.
  • a bare cell appearance detection method is provided.
  • the method is applied to a control device.
  • the control device can be implemented through a logic controller.
  • the method includes the following steps:
  • Step S110 Obtain the cell picture taken of the bare cell.
  • the battery cell picture is taken by aligning the edge of the bare battery core with the tab position.
  • the sensor can detect that after the bare battery core is transported to the detection station, the PLC triggers the camera to take a picture.
  • the PLC confirms that the camera is ready, it sends a signal to the logic controller.
  • the logic controller After the logic controller receives the signal, the control is set at the edge pole of the bare battery core.
  • the dual cameras above the ears take pictures and get pictures of the battery cells.
  • the cell picture includes a cell isolation film 11, pole tabs 12 and a marking layer 13.
  • the pole pieces of the cell are wrapped in the cell isolation film 11, and the marking layer 13 is used to mark the bare cell.
  • Information (such as QR code, etc.).
  • the identification layer 13 can be made of blue glue.
  • the QR code of the bare battery core is set in the center of the blue glue.
  • the position of the blue glue needs to be ensured during the appearance inspection to prevent the code scanner at the back of the production line from failing to read the code, resulting in Equipment is down.
  • the logic controller can control the camera to take pictures twice to obtain high-exposure pictures and low-exposure pictures, respectively, for related appearance detection of bare battery cells.
  • the logic controller not only responds to the PLC with a picture-taking completion signal, but also simultaneously performs image detection, parallelizing the picture-taking and detection calculations, reducing the total detection time and improving detection efficiency.
  • the PLC controls the logistics line to transport the bare batteries to the sorting station.
  • Step S120 Determine the detection object in the battery cell picture.
  • the detection object refers to the characteristics related to the appearance detection in the battery cell picture. It can be understood that depending on the detection content of the bare battery core, the battery cell picture used in the detection and the detection objects in the battery cell picture will also be different. different. For example, bare cell appearance inspection can include tab folding detection, tab misalignment detection, pin removal detection, drain piece detection, tab discharge detection, surface dirt detection, bare cell size detection and large surface pressure Injury detection, etc.
  • high-exposure pictures are used for size detection and pin removal detection, in order to improve the contrast and color difference at the edge of the battery core. It is beneficial to grasp the edge of the battery core and improve the stability of edge grasping.
  • Low-exposure pictures are used for product appearance inspection (such as product surface dirt, large surface bruises, drain plates, etc.). Since low-exposure pictures need to be used to obtain surface feature information, the cell surface should not be overexposed when taking pictures. , to prevent product surface appearance defects from being missed due to overexposure.
  • the logic controller performs appearance inspection of bare cells, it extracts relevant features from the corresponding cell pictures as detection objects. For example, when inspecting the size of bare cells, the edge of the cell isolation film is found from a high-exposure picture as the detection object for size inspection.
  • Step S130 Perform appearance detection according to the detection object to obtain detection result information.
  • the logic controller can determine the relevant detection area in combination with the detection object, perform corresponding appearance detection in the detection area, and obtain detection result information.
  • the battery cell picture may include an isolation film detection area 21, a tab folding detection area 22, a pin removal detection area 23, a marking layer detection area 24 and a tab positive and negative detection area 25. Combining the image data in different detection areas, relevant content can be detected in the detection area.
  • the camera calibration plane is the base projection plane for camera measurement.
  • the measured data is the most accurate. It can be seen from Figure 4 that the projection points of the measured objects a, b, and c reflected by the parallel light are the same, so the measured values of a and c are the same as b.
  • the projection points a' and c' are respectively located on both sides of the reference point b'. Since the position of the outermost side of the tab is not fixed in the tab stacking area, a fixed compensation value cannot be added, so the measured tab misalignment detection There will be errors in the results or needle removal test results.
  • the camera layout is such that the center of the camera field of view is aligned with the position of the tab on the edge of the battery core to ensure that the image of the edge of the battery core is parallel light reflected to the camera Imaging, reducing the error caused by the fact that the outermost edge of the tab is not fixed in the tab stacking area and unable to add a fixed compensation value, thereby reducing the true image of the edge of the battery tab due to the thickness of the cell during imaging sexual influence.
  • the above-mentioned method of detecting the appearance of a bare battery cell obtains a picture of the battery core by aligning the edge of the bare battery core with the position of the tab, so that the edge of the battery core is imaged as a parallel light reflection image, which reduces the impact of the battery core tab during imaging due to the thickness of the battery core.
  • the influence of edge authenticity ensures the accuracy of image collection, thereby improving the accuracy of bare cell appearance detection.
  • the battery cell image includes a first battery cell image, the exposure of the first battery cell image is higher than a preset exposure threshold, and the detection object includes the edge of the battery cell isolation film; step S120 includes: according to the preset voltage
  • the core model determines the reference position in the first battery cell picture, and grabs the edge of the battery cell isolation film based on the reference position.
  • the reference position is used as a reference starting point for edge grabbing.
  • the specific setting method of the reference position is not unique.
  • the center position of the cell isolation film or other positions can be selected as the reference position.
  • the logic controller establishes a coordinate system based on the center position of the cell isolation film, and combines the coordinate system and the set edge grabbing area to adjust the cell isolation film.
  • the edge points of edge a, edge b, edge c and edge d are captured, and the edge of the cell isolation film is determined based on the captured edge points.
  • the edge c with the pole lug 12 it can also be passed Set multiple different edge grabbing areas to avoid the pole ear area for edge grabbing processing. By fitting all the real-time grabbing points on the three-segment line, the edge c is obtained to avoid the pole ear area interfering with the real-time grabbing position.
  • the cell model can be established through the CogPMAligTool tool, the cell model can be matched from high-exposure pictures, the position center coordinates (X, Y, R) of the cell isolation film can be obtained, and the spatial coordinate system can be established using the CogFixtureTool tool.
  • the corresponding edge can be obtained by setting the corresponding edge-grabbing tool properties (for example, the polarity setting is from black to white / From white to black; edge calculation method priority, such as area center, search direction, etc.) to obtain the corresponding edge position.
  • a high-exposure picture is obtained by taking a high-exposure photograph of the bare battery core, which improves the edge contrast and color difference of the bare battery core, which facilitates grasping the edge of the battery core, and determines the high-exposure picture in combination with the preset battery cell model.
  • the reference position facilitates accurate and quick acquisition of the edge of the cell isolation film.
  • the detection result information includes size data.
  • step S130 includes step S132 and step S134.
  • Step S132 Calculate the distances from all points on the edge of the cell isolation film to the opposite edge, and obtain multiple edge distance data.
  • the edge distance data includes length data and width data.
  • the length data can be calculated based on edge a and edge b, and the width data can be calculated based on edge c and edge d.
  • the width data can be calculated based on edge c and edge d.
  • Step S132 Obtain size data based on multiple edge distance values.
  • multiple length data can be averaged to obtain the average length
  • multiple width data can be averaged to obtain the average width
  • the average length and average width can be used as the bare electrode
  • the length and width dimensions of the core after calculating the average length and average width, each length data is compared with the average length, and the length data whose difference from the average length meets the preset difference threshold is eliminated.
  • get the target length data compare each width data with the average width, eliminate the width data whose difference from the average width meets the preset difference threshold, obtain the target width data, and then use the average value of the target length data as For the final length, the average value of the target width data is used as the final width, and then the size data of the bare cell is obtained.
  • weighted average processing can also be performed on the length data to obtain the length average, and weighted average processing can be performed on the width data to obtain the width average, and then the length average and the width average are used as the length of the bare cell. wide size data.
  • the four edges a, b, c, and d captured in real time can be used to calculate the distance from all points on line a to line b through the distance from point to line, obtain multiple length data, and then calculate multiple length data.
  • the average value, and the distance from all points on line c to line b are calculated to obtain multiple width data, and then the average value of multiple width data is calculated to obtain the length and width dimensions.
  • the distance from all points on the edge of the cell isolation film to the opposite edge is calculated, and the size data of the bare cell is determined by averaging the obtained edge distance data to ensure the accuracy of size detection.
  • the detection result information includes needle withdrawal detection results.
  • step S130 includes step S136 and step S138.
  • Step S136 Determine the pin withdrawal detection area according to the edge of the cell isolation film.
  • a corresponding pin withdrawal detection area is established according to the edge of the battery core isolation film, so that different pin withdrawal detection areas can be used to position and perform pin withdrawal detection. Different positioning spaces are established in different areas to ensure the stability of the needle removal detection area.
  • edge a and edge c or edge b and edge c
  • edge d is used as the origin of the coordinate system to re-establish the spatial coordinate system, which is used to detect the space following of the needle removal search box.
  • Step S138 Detect the needle withdrawal detection area and obtain the needle withdrawal detection result.
  • the Blob operator tool can be used to obtain information in the pin withdrawal detection area to perform pin withdrawal detection to determine whether there is poor pin withdrawal.
  • poor pin extraction can be understood as the protrusion phenomenon in certain areas on the edge.
  • the visual blob spot tool can be used to obtain spots with contrast differences in the blob area (information such as the length, width/area of the spot), and by detecting the edge area of the cell Set the Blob area, and offset the Blob area to a fixed position according to the pin withdrawal detection specifications (for example, if the pin withdrawal specification is 0.1 millimeter (mm), place the Blob area 0.1mm outside the edge of the cell isolation film).
  • the pin withdrawal detection area is determined based on the edge of the cell isolation film, and combined with the pin withdrawal detection area, the pin withdrawal detection can be performed quickly and conveniently.
  • step S138 includes: searching and acquiring spot information in the needle withdrawal detection area, and obtaining the needle withdrawal detection result according to the spot information analysis.
  • the spot information is obtained by searching in the pin withdrawal detection area, and the pin withdrawal detection of the bare battery core is realized based on the obtained spot information.
  • the specific type of spot information is not unique.
  • the spot information includes at least one of a single spot area, a spot size, and a sum of spot areas. According to the actual situation, one or more of the single spot area, spot size and total spot area can be used to detect the bare battery core to improve the convenience of detection. Benefits.
  • the CogBlobTool1 operator is used to capture the needle removal detection area in real time.
  • the space used in the needle removal detection area follows the corresponding spatial coordinate system established in step S136 to ensure the stability of the detection area.
  • step S138 includes: obtaining the distance value from the edge point of the cell isolation film in the pin withdrawal detection area to the edge, and analyzing and obtaining the pin withdrawal detection result based on multiple distance values.
  • multiple distance values may be sorted to obtain sorted distance values, and then the maximum value among the sorted distance values may be screened out, and whether there is a problem of poor needle extraction based on the maximum value may be detected.
  • edge a the maximum value is obtained by calculating the distance from the point on edge a to edge a itself.
  • the maximum value can be understood as the largest bump on edge a. Based on the maximum distance, it is detected whether there is poor pin extraction, which is beneficial to grasping. Take the entire edge to collectively leak out and pull out the needle.
  • the pin withdrawal detection is performed by analyzing the distance value from the edge point of the cell isolation film in the pin withdrawal detection area to its own edge, which is beneficial to grasping the collective leakage of pin withdrawal phenomenon at the entire edge.
  • the method may also include step S140: the logic controller binds and stores the detection result information and the identification information of the bare cell.
  • the logic controller can also obtain the QR code on the identification layer through image recognition of high-exposure pictures.
  • the logic controller binds the test result information with the identification information of the bare cell and stores it in the database. It can also upload the test result information to MES (Manufacturing Execution System, Manufacturing Execution System) at the same time.
  • MES Manufacturing Execution System, Manufacturing Execution System
  • the PLC triggers the code scanner to scan the QR code on the bare battery core to identify the test result information corresponding to the bare battery core in the database.
  • the test result information can indicate whether the bare battery core is a good product or a bad product. Then, it is determined whether the bare battery core is a good product based on the identified detection result information. If the battery core is a good product, the PLC controls the material handling robot to transport the battery core to the good product buffer area; if the battery core is a non-defective product, the PLC controls the material handling robot to transport the battery core to the non-defective product buffer area.
  • embodiments of the present application also provide a bare cell appearance inspection device for implementing the above-mentioned bare cell appearance inspection method.
  • the solution to the problem provided by this device is similar to the solution recorded in the above method. Therefore, for the specific limitations in the embodiment of one or more bare cell appearance detection devices provided below, please refer to the above article for bare cell. The limitations of appearance inspection methods will not be repeated here.
  • a bare cell appearance detection device including: a picture acquisition module 110, a picture processing module 120 and a picture detection module 130, wherein:
  • the picture acquisition module 110 is used to obtain battery cell pictures that are photographed of bare battery cells; the battery core pictures are photographed by aligning the pole positions of the edge of the bare battery core.
  • the image processing module 120 is used to determine the detection object in the battery cell image.
  • the picture detection module 130 is used to perform appearance detection according to the detection object and obtain detection result information.
  • the battery cell image includes a first battery cell image
  • the exposure of the first battery cell image is higher than a preset exposure threshold
  • the detection object includes the edge of the battery cell isolation film.
  • the image processing module 120 determines the reference position in the first battery cell image according to the preset battery cell model, and grabs the edge of the battery cell isolation film according to the reference position.
  • the detection result information includes dimensional data.
  • the image detection module 130 calculates the distances from all points on the edge of the cell isolation film to the opposite edge to obtain edge distance data; averages the edge distance data to calculate the size data.
  • the detection result information includes needle withdrawal detection results.
  • the picture detection module 130 determines the pin withdrawal detection area according to the edge of the cell isolation film; detects the pin withdrawal detection area to obtain the pin withdrawal detection result.
  • the picture detection module 130 searches and obtains spot information in the needle withdrawal detection area, and obtains the needle withdrawal detection result based on analysis of the spot information.
  • the picture detection module 130 obtains the distance value from the edge point of the cell isolation film in the pin withdrawal detection area to the edge, and obtains the pin withdrawal detection result based on the maximum value analysis among the distance values.
  • the picture detection module 130 binds and stores the detection result information and the identification information of the bare cell.
  • Each module in the above-mentioned bare cell appearance inspection device can be fully or partially implemented by software, hardware and combinations thereof.
  • Each of the above modules may be embedded in or independent of the processor of the computer device in the form of hardware, or may be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.
  • 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 11.
  • 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 computer device's database is used to store 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 bare cell appearance inspection method.
  • Figure 11 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 one or more processors.
  • Computer-readable instructions are stored in the memory. When executed by one or more processors, the computer-readable instructions cause one or more A processor executes the steps in each of the above method embodiments.
  • one or more computer storage media storing computer-readable instructions are provided.
  • the computer-readable instructions When executed by one or more processors, they cause the one or more processors to execute each of the above methods. The steps in the example.
  • a computer program product is provided.
  • the computer program When the computer program is executed by one or more processors, it causes the one or more processors to perform the steps in the above method embodiments.
  • a bare battery core appearance inspection system including an image acquisition device and a host computer.
  • the image acquisition device is used to align the position of the edge tab of the bare battery core to photograph the battery core, and obtain the battery core picture.
  • the pictures are sent to the host computer, and the host computer is used to conduct bare battery core appearance inspection according to the above-mentioned bare battery core appearance inspection method.
  • the image acquisition device uses dual cameras, specifically dual CCD cameras.
  • the dual camera can be located above the bare battery core, and the distance between the dual camera and the bare battery core is set to 423 ⁇ 25mm according to the camera model.
  • the machine can be a notebook, desktop computer or logic controller.
  • the dual camera can use a 12MP color area scan camera.
  • the camera's field of view in the X direction can be 260mm, and the pixel accuracy is 0.06mm/pixel, so that the dual camera field of view can be Full view to battery cells Wild coverage.
  • the camera takes two pictures respectively.
  • the bare battery core appearance inspection system also includes a light source.
  • the distance between the light source and the bare battery core can be set to 100 ⁇ 20mm.
  • the light source may specifically include a pair of light sources disposed above the long sides of both sides of the bare battery core, and the distance between the two light sources may be 370 ⁇ 30 mm.
  • the light source also includes a pair of light sources arranged above the short sides of both sides of the bare cell. The distance between the two light sources can be 370 ⁇ 30mm.
  • two cameras are used to capture the corresponding areas of the bare battery core while ensuring accuracy. It can be compatible with a variety of products.
  • the camera's field of view range is compatible with a maximum of 305° and a minimum of 120°.
  • the distance between the two cameras can be adjusted according to different models of bare batteries.
  • the distance from the light source to the bare battery is designed to be 100 ⁇ 20mm.
  • the angle can be adjusted from 0 to 90°.
  • the distance between the light sources is designed to be 370. ⁇ 30mm, compatible with the largest and smallest sizes of bare cells.
  • 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)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Image Analysis (AREA)
  • Sealing Battery Cases Or Jackets (AREA)
  • Secondary Cells (AREA)

Abstract

一种裸电芯外观检测方法、装置、计算机设备、计算机可读存储介质、计算机程序产品和裸电芯外观检测系统。方法包括：获取对裸电芯拍摄得到的电芯图片（S110）；电芯图片为对准裸电芯边缘极耳位置拍摄得到；确定电芯图片中的检测对象（S120）；根据检测对象进行外观检测，得到检测结果信息（S130）。

Description

裸电芯外观检测方法、装置、计算机设备和存储介质
交叉引用
本申请引用于2022年8月10日递交的名称为“裸电芯外观检测方法、装置、计算机设备和存储介质”的第2022109575776号中国专利申请，其通过引用被全部并入本申请。
技术领域
本申请涉及电池检测技术领域，特别是涉及一种裸电芯外观检测方法、装置、计算机设备、计算机可读存储介质、计算机程序产品和裸电芯外观检测系统。
背景技术
随着新能源汽车的不断普及，锂离子电池已在电动汽车中得到广泛应用，成为电动汽车的主要动力能源之一。
目前电动汽车上使用的锂电池主要以磷酸铁锂电池为主，磷酸铁锂电池具有高容量、输出电压高、较好的充放电循环性能等特点。裸电芯外观检测是电池电芯生产流程中极为重要的一道工序，如何提高裸电芯外观检测的准确性，是一个亟待解决的问题。
发明内容
鉴于上述问题，本申请提供一种裸电芯外观检测方法、装置、计算机设备、计算机可读存储介质、计算机程序产品和裸电芯外观检测系统。
第一方面，本申请提供了一种裸电芯外观检测方法，该方法应用于控制设备，控制设备可具体通过逻辑控制器实现，方法包括：
获取对裸电芯拍摄得到的电芯图片；电芯图片为对准裸电芯边缘极耳位置拍摄得到；
确定电芯图片中的检测对象；及
根据检测对象进行外观检测，得到检测结果信息。
上述裸电芯外观检测方法，通过对准裸电芯边缘极耳位置拍摄得到电芯图片，使得电芯边缘成像为平行光反射成像，减小因电芯厚度关系在成像时对电芯极耳边缘真实性的影响，确保图像采集的准确性，从而提高裸电芯外观检测的准确性。
在一些实施例中，电芯图片包括第一电芯图片，第一电芯图片的曝光度高于预设曝光度阈值，检测对象包括电芯隔离膜的边缘；确定电芯图片中的检测对象包括：根据预设电芯模型确定第一电芯图片中的参考位置，根据参考位置抓取电芯隔离膜的边缘。
上述实施例中，对裸电芯进行高曝光度拍摄得到高曝光度图片，提高裸电芯的边缘对比度色差，利于抓取电芯边缘，并结合预设电芯模型确定高曝光度图片中的参考位置，方便 准确快速获取电芯隔离膜的边缘。
在一些实施例中，检测结果信息包括尺寸数据；根据检测对象进行外观检测，得到检测结果信息包括：
计算电芯隔离膜边缘的所有点到相对边缘的距离，得到多个边缘距离数据；及
根据多个边缘距离数据，得到尺寸数据。
上述实施例中，通过计算电芯隔离膜的边缘所有点到相对边缘的距离，可快速且准确地得到裸电芯的尺寸数据。
在一些实施例中，边缘距离数据包括长度数据和宽度数据；根据多个边缘距离数据，得到尺寸数据包括：
对多个长度数据进行求平均处理，得到长度平均值；
对多个宽度数据进行求平均处理，得到宽度平均值；及
根据长度平均值和宽度平均值，得到尺寸数据。
上述实施例中，通过计算电芯隔离膜的边缘所有点到相对边缘的距离，再对边缘距离数据中的长度数据和宽度数据分别进行求平均，得到裸电芯的尺寸数据，能够确保尺寸检测的准确性。
在一些实施例中，检测结果信息包括拔针检测结果；根据检测区域进行外观检测，得到检测结果信息包括：根据电芯隔离膜的边缘确定拔针检测区域；对拔针检测区域进行检测，得到拔针检测结果。
上述实施例中，以电芯隔离膜的边缘为依据确定拔针检测区域，结合拔针检测区域可快速、便捷进行拔针检测。
在一些实施例中，对拔针检测区域进行检测，得到拔针检测结果包括：在拔针检测区域查找获取斑点信息，根据斑点信息分析得到拔针检测结果。
上述实施例中，在拔针检测区域查找获取斑点信息，根据获取的斑点信息能够快速实现对裸电芯的拔针检测。
在一些实施例中，斑点信息包括单个斑点面积、斑点尺寸和斑点面积总和中的至少一种。
上述实施例中，可根据实际情况设置通过单个斑点面积、斑点尺寸和斑点面积总和中的一种或多种对裸电芯进行拔针检测，提高检测便利性。
在一些实施例中，对拔针检测区域进行检测，得到拔针检测结果包括：
获取拔针检测区域中电芯隔离膜的边缘点到所在边缘的距离值；及
根据多个所述距离值，分析得到拔针检测结果。
上述实施例中，通过分析拔针检测区域中电芯隔离膜的边缘点，到自身所在边缘的距离值来进行拔针检测，有利于抓取整个边缘集体漏出拔针现象。
在一些实施例中，根据多个距离值分析得到拔针检测结果包括：
对多个所述距离值进行排序处理，得到排序后的距离值；
筛选出所述排序后的距离值中的最大值；及
根据筛选出的所述最大值，分析得到拔针检测结果。
上述实施例中，通过根据距离值中的最大值来进行拔针检测，能够合理且快速地抓取出整个边缘集体漏出拔针现象。
在一些实施例中，根据检测对象进行外观检测，得到检测结果信息之后，该方法还包括：上位机将检测结果信息与裸电芯的标识信息进行绑定存储。
上述实施例中，通过将检测结果信息与裸电芯的标识信息进行绑定存储，方便后续工位结合检测结果信息对裸电芯进行分拣。
在一些实施例中，电芯图片由双相机对准裸电芯边缘极耳位置拍摄得到。
上述实施例中，通过双相机采集电芯图片，能够实现检测要素的全局检测，提升检测结果的精确度，降低误检和漏检的概率。
第二方面，本申请提供了一种裸电芯外观检测装置，包括：
图片获取模块，用于获取对裸电芯拍摄得到的电芯图片；电芯图片为对准裸电芯边缘极耳位置拍摄得到；
图片处理模块，用于确定电芯图片中的检测对象；
图片检测模块，用于根据检测对象进行外观检测，得到检测结果信息。
第三方面，本申请提供了一种计算机设备，包括存储器及一个或多个处理器，存储器中储存有计算机可读指令，计算机可读指令被一个或多个处理器执行时，使得一个或多个处理器执行上述的裸电芯外观检测方法的步骤。
第四方面，本申请提供了一个或多个存储有计算机可读指令的计算机存储介质，计算机可读指令被一个或多个处理器执行时，使得一个或多个处理器执行上述的裸电芯外观检测方法的步骤。
第五方面，本申请提供了一种计算机程序产品，该计算机程序被一个或多个处理器执行时，使得一个或多个处理器执行上述的裸电芯外观检测方法的步骤。
第六方面，本申请提供了一种裸电芯外观检测系统，包括图像获取装置和上位机，图像获取装置用于对准裸电芯边缘极耳位置拍摄得到电芯图片，并将电芯图片发送至上位机，上位机用于根据上述的裸电芯外观检测方法进行裸电芯外观检测。
在一些实施例中，图像获取装置包括双相机。
上述实施例中，通过双相机采集电芯图片，能够实现检测要素的全局检测，提升检测结果的精确度，降低误检和漏检的概率。
上述说明仅是本申请技术方案的概述，为了能够更清楚了解本申请的技术手段，而可 依照说明书的内容予以实施，并且为了让本申请的上述和其它目的、特征和优点能够更明显易懂，以下特举本申请的具体实施方式。
附图说明
通过阅读对下文优选实施方式的详细描述，各种其他的优点和益处对于本领域普通技术人员将变得清楚明了。附图仅用于示出优选实施方式的目的，而并不认为是对本申请的限制。而且在全部附图中，用相同的附图标号表示相同的部件。在附图中：
图1为一些实施例中裸电芯外观检测方法的场景示意图；
图2为一些实施例中裸电芯外观检测方法的流程示意图；
图3为一些实施例中电芯图片的示意图；
图4为一些实施例中极耳错位检测误差示意图；
图5为一些实施例中电芯尺寸检测示意图；
图6为一些实施例中根据检测对象进行外观检测，得到检测结果信息的流程图；
图7为另一些实施例中根据检测对象进行外观检测，得到检测结果信息的流程图；
图8为一些实施例中电芯拔针检测示意图；
图9为另一些实施例中裸电芯外观检测方法的流程示意图；
图10为一些实施例中裸电芯外观检测装置的结构框图；
图11为一些实施例中计算机设备的内部结构图。
具体实施方式
为了使本申请的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本申请进行进一步详细说明。应当理解，此处描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。
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些实施例中。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、高功率和高能量密度等特点。裸电芯外观检测是电池电芯生产流程中极为重要的一道工序，起到检测裸电芯是否满足良品规格的作用，能够筛选出不合格产品，减少不合格产品流入裸电芯配对环节带来的不良影响。基于此，本申请提供一种裸电芯外观检测方法，获取对准裸电芯边缘极耳位置拍摄得到的电芯图片，确定电芯图片中的检测对象，根据检测对象进行外观检测，得到检测结果信息。通过对准裸电芯边缘极耳位置拍摄得到电芯图片，使得电芯边缘成像为平行光反射成像，减小因电芯厚度关系在成像时对电芯极耳边缘真实性的影响，确保图像采集的准确性。
本申请实施例提供的裸电芯外观检测方法，可以应用于如图1所示的应用环境中。通过控制设备(图中未示出)控制物流线运输裸电芯1到外观检测工位后，由外观检测工位的相机2对准裸电芯1边缘极耳位置拍摄得到电芯图片，并将电芯图片上传至控制设备，控制设备确定电芯图片中的检测对象，并根据检测对象进行外观检测，得到检测结果信息。其中，裸电芯1(或至少是裸电芯1的边缘极耳位置)位于相机2的相机拍摄范围内，例如，相机2位于裸电芯1的上方，从而使得相机2能够对准裸电芯1边缘极耳位置拍摄得到电芯图片， 相机2的数量为两个，即采用双相机进行图像采集，可做到对裸电芯的全视野覆盖，相机2具体可采用CCD(Charge Coupled Device，电荷耦合器件)相机或其他相机。具体地，控制设备可包括控制模块和上位机，由控制模块控制物流线运输裸电芯1，上位机控制相机2对裸电芯1拍摄得到电芯图片，随后，上位机对电芯图片进行图像分析得到检测结果信息。控制模块可以是PLC(Programmable Logic Controller，可编程逻辑控制器)、MCU(Microcontroller Unit，微控制单元)等，上位机可以是笔记本、台式电脑或逻辑控制器等。
进一步地，外观检测工位还设置有光源3，其中，裸电芯1位于光源3发射出的光线范围内，如光源3可位于裸电芯1的上方，以方便相机2进行图像采集。为了便于相机2采集到更为清晰的电芯图片，光源3可具体包括两对光源，其中，一对光源位于裸电芯1两侧长边上方的一对光源，另一对光源位于裸电芯1两侧短边上方。此外，在完成裸电芯外观检测后，上位机还输出指令给控制模块，控制模块控制物流线将裸电芯1运输到下一工位，例如输送到分拣工位，根据检测结果信息对裸电芯1进行分拣等。为便于理解，以下均以控制模块采用PLC，上位机采用逻辑控制器为例进行解释说明。
在一些实施例中，如图2所示，提供了一种裸电芯外观检测方法，该方法应用于控制设备，控制设备具体可通过逻辑控制器实现，方法包括以下步骤：
步骤S110：获取对裸电芯拍摄得到的电芯图片。
其中，电芯图片为对准裸电芯边缘极耳位置拍摄得到。具体地，可通过传感器检测到裸电芯运输到检测工位后PLC触发相机拍照，PLC确认相机准备完成时发送信号至逻辑控制器，逻辑控制器接收到信号后控制设置于裸电芯边缘极耳上方的双相机进行拍照，得到电芯图片。如图3所示，电芯图片中包括电芯隔离膜11、极耳12和标识层13，电芯的极片包裹在电芯隔离膜11内，标识层13用作设置裸电芯的标识信息(如二维码等)。其中，标识层13具体可采用蓝胶，蓝胶中心设置裸电芯的二维码，在外观检测中需确保蓝胶位置，以防止产线后面工位扫码枪扫码读取失败，导致设备宕机。进一步地，逻辑控制器可以是控制相机拍照两次得到高曝光度图片和低曝光度图片，分别用作裸电芯的相关外观检测。此外，在相机拍照完成后，逻辑控制器在向PLC回复拍照完成信号的同时，还同步进行图像检测，将拍照与检测计算并行，降低检测总耗时，提高检测效率。PLC在接收到拍照完成信号后，控制物流线运输裸电芯到达分拣工位。
步骤S120：确定电芯图片中的检测对象。
检测对象即指电芯图片中与外观检测相关的特征，可以理解，根据裸电芯的检测内容不同，进行检测时所使用的电芯图片，以及电芯图片中的检测对象也会对应有所不同。例如，裸电芯外观检测可包括极耳翻折检测、极耳错位检测、拔针不良检测、漏极片检测、极耳放反检测、表面脏污检测、裸电芯尺寸检测以及大面压伤检测等。对裸电芯拍摄得到的电芯图片中，高曝光度图片用作进行尺寸检测及拔针检测，目的是为了提高电芯边缘对比度色差， 利于抓取电芯边缘，提高抓边稳定性能。低曝光度图片用作进行产品外观检测(如产品表面脏污、大面压伤、漏极片等)，由于需要利用低曝光度图片获取表面特征信息，所以采图时电芯表面不宜过曝，防止产品表面外观缺陷因过曝导致缺陷漏检。逻辑控制器进行裸电芯外观检测时，从相应电芯图片中提取相关特征作为检测对象。例如，在进行裸电芯尺寸检测时，则是从高曝光度图片中找到电芯隔离膜的边缘作为检测对象，以用作尺寸检测。
步骤S130：根据检测对象进行外观检测，得到检测结果信息。
在确定电芯图片中的检测对象之后，逻辑控制器可结合检测对象确定相关检测区域，在检测区域内进行对应的外观检测，得到检测结果信息。继续参照图3，根据检测内容不同，电芯图片中可包括隔离膜检测区域21、极耳翻折检测区域22、拔针检测区域23、标识层检测区域24和极耳正反检测区域25，结合不同检测区域中的图像数据，可在检测区域中进行相关内容的检测。
如图4所示，在通过相机拍摄电芯图片时，由于相机标定平面放置于测量平面，以相机标定平面为参考坐标系基准，故相机标定平面是相机测量的基准投影平面，在此投影面测量出的数据最为准确。由图4可以看出，平行光线反射的被测物a、b、c的投影点相同，所以a、c的测量值和b相同。a’、c’投影点分别位于b’基准点的两侧，由于极耳的最外侧侧量边在极耳堆叠区域内位置不固定，无法加固定补偿值，故测量出的极耳错位检测结果或拔针检测结果就会有误差。在裸电芯外观检测中，因极耳的最外侧侧量边在极耳堆叠区域内位置不固定，无法加固定补偿值，因此存在检测误差，极耳折叠区越大误差越大。因为极耳边缘与电芯表面不在同一平面，因此，本申请在采用双相机拍摄时，将相机布局为相机视野中心对准电芯边缘极耳位置，确保电芯边缘成像为平行光反射到相机成像，减小因极耳的最外侧侧量边在极耳堆叠区域内位置不固定，无法加固定补偿值而存在的误差，从而降低因电芯厚度关系在成像时对电芯极耳边缘真实性的影响。
上述裸电芯外观检测方法，通过对准裸电芯边缘极耳位置拍摄得到电芯图片，使得电芯边缘成像为平行光反射成像，减小因电芯厚度关系在成像时对电芯极耳边缘真实性的影响，确保图像采集的准确性，从而提高裸电芯外观检测的准确性。
在一些实施例中，电芯图片包括第一电芯图片，第一电芯图片的曝光度高于预设曝光度阈值，检测对象包括电芯隔离膜的边缘；步骤S120包括：根据预设电芯模型确定第一电芯图片中的参考位置，根据参考位置抓取电芯隔离膜的边缘。
其中，参考位置为用作进行边缘抓取的参考起始点，参考位置的具体设置方式并不唯一，可以是选择电芯隔离膜的中心位置或其他位置作为参考位置。如图5所示，以电芯隔离膜的中心位置作为参考位置为例，则逻辑控制器以电芯隔离膜的中心位置建立坐标系，结合坐标系和设定抓边区域对电芯隔离膜的边缘a、边缘b、边缘c和边缘d进行边缘点抓取，根据抓取的边缘点拟合确定电芯隔离膜的边缘。其中，对于设置有极耳12的边缘c，还可通过 设定多个不同的抓边区域以避开极耳区域进行抓边处理，通过拟合三段线上所有实时抓取的点，得到边缘c，避免极耳区域干扰实时抓取的位置。
具体地，可通过CogPMAligTool工具建立电芯模型，从高曝光度图片中匹配该电芯模型，获取电芯隔离膜的位置中心坐标(X,Y,R)，使用CogFixtureTool工具建立空间坐标系，通过建立CCD视觉CogFindLineTool抓边工具使用空间跟随模式，设置好抓边区域避开极耳位置区域干扰，可以获取到对应的边缘，通过设置好对应抓边工具属性(例如，极性设置由黑到白/由白到黑；边缘计算方式优先级，如区域中心，搜索方向等)，获取对应边缘位置。
本实施例中，对裸电芯进行高曝光度拍摄得到高曝光度图片，提高裸电芯的边缘对比度色差，利于抓取电芯边缘，并结合预设电芯模型确定高曝光度图片中的参考位置，方便准确快速获取电芯隔离膜的边缘。
对应地，在一些实施例中，检测结果信息包括尺寸数据。如图6所示，步骤S130包括步骤S132和步骤S134。
步骤S132：计算电芯隔离膜边缘的所有点到相对边缘的距离，得到多个边缘距离数据。其中，边缘距离数据包括长度数据和宽度数据。
如图5所示，可根据边缘a和边缘b计算得到长度数据，根据边缘c和边缘d计算得到宽度数据。以计算长度数据为例，可以是计算边缘a上所有点到边缘b的距离得到长度数据；也可以是计算边缘b上所有点到边缘a的距离，得到多个边缘距离值，进而根据多个边缘距离值，得到长度数据；还可以是同时计算边缘a上所有点到边缘b的距离，以及边缘b上所有点到边缘a的距离，得到多个边缘距离值，进而根据多个边缘距离值，得到长度数据。
步骤S132：根据多个边缘距离值，得到尺寸数据。
在计算得到多个边缘距离数据后，可以将多个长度数据进行求平均，得到长度平均值，将多个宽度数据进行求平均得到宽度平均值，再将长度平均值和宽度平均值作为裸电芯的长宽尺寸数据。在另一些实施例中，还可以是计算得到长度平均值和宽度平均值之后，将每一长度数据与长度平均值做比较，剔除与长度平均值的差值满足预设差值阈值的长度数据，得到目标长度数据，将每一宽度数据与宽度平均值做比较，剔除与宽度平均值的差值满足预设差值阈值的宽度数据，得到目标宽度数据，再将目标长度数据的平均值作为最终长度，将目标宽度数据的平均值作为最终宽度，进而得到裸电芯的尺寸数据。在其他实施例中，还可以是对长度数据进行加权平均处理，得到长度平均值，对宽度数据进行加权平均处理，得到宽度平均值，进而将长度平均值和宽度平均值作为裸电芯的长宽尺寸数据。
具体地，可通过实时抓取的a、b、c、d四条边，通过点到线的距离，计算a线上所有点到b线的距离，得到多个长度数据，再计算多个长度数据的平均值，以及计算c线上所有点到b线的距离，得到多个宽度数据，再计算多个宽度数据的平均值，得到长宽尺寸。例:通过CogFindLineTool1实时抓取边缘b，获取CogFindLineTool1.Results.GetLine()实时抓取的 b边缘，通过CogFindLineTool2实时抓取边缘a。在确定边缘a和边缘b之后，采用CogFindLineTool2.Results.Count获取实时抓取到的点位个数Count，采用For(int i＝0；i<Count-1,i++)循环语句循环，获取对应边缘上所有点，使用CogDistancePiontLineTool算子工具，在算子工具中边缘b赋值：
CogDistancePiontLineTool.LineCogFindLineTool2.Results[i].X/CogFindLineTool2.Results[i].Y。
赋值CogDistancePiontLineTool.X/CogDistancePiontLineTool.Y算子运行获得边缘a上所有点到边缘b的距离，得到尺寸距离平均值。在抓取到对应的边缘后，可以通过算子直接获取得到每个点的坐标，即所有边缘上点是已知的，可以反复调用边缘上所有点，根据边缘上点的坐标计算得到尺寸距离平均值。
本实施例中，通过计算电芯隔离膜的边缘所有点到相对边缘的距离，根据得到的边缘距离数据进行求平均确定裸电芯的尺寸数据，确保尺寸检测的准确性。
在一些实施例中，检测结果信息包括拔针检测结果。如图7所示，步骤S130包括步骤S136和步骤S138。
步骤S136：根据电芯隔离膜的边缘确定拔针检测区域。
在确定电芯隔离膜的边缘之后，根据电芯隔离膜的边缘建立相应的拔针检测区域，从而可通过不同拔针检测区域来定位进行拔针检测。通过不同区域建立不同定位空间，确保拔针检测区域的稳定性。如图8所示，以边缘a和边缘c(或边缘b和边缘c)线线交点作为坐标系原点，重新建立空间坐标系，用于检测上拔针搜索框空间跟随。同理，以边缘a、边缘d线线交点作为坐标系原点，重新建立空间坐标系，用于检测下拔针搜索框空间跟随。
步骤S138：对拔针检测区域进行检测，得到拔针检测结果。
具体地，可通过Blob算子工具获取拔针检测区域中的信息进行拔针检测，确定是否存在拔针不良。其中，拔针不良可以理解为边缘某些区域存在凸出现象，采用视觉Blob斑点工具可以获取Blob区域内对比度存在差值的斑点(斑点的长宽/面积等信息)，通过在电芯边缘区域设置Blob区域，根据拔针检测规格将Blob区域偏移固定位置(例拔针规格为0.1毫米(mm)，则将Blob区域放置在电芯隔离膜的边缘外0.1mm位置)，当Blob算子工具检测到对比度存在差值的斑点，即为有拔针超限。本实施例中，以电芯隔离膜的边缘为依据确定拔针检测区域，结合拔针检测区域可快速、便捷进行拔针检测。
在一些实施例中，步骤S138包括：在拔针检测区域查找获取斑点信息，根据斑点信息分析得到拔针检测结果。通过在拔针检测区域查找获取斑点信息，根据获取的斑点信息实现对裸电芯的拔针检测。其中，斑点信息的具体类型也并不唯一，在一些实施例中，斑点信息包括单个斑点面积、斑点尺寸和斑点面积总和中的至少一种。可根据实际情况设置通过单个斑点面积、斑点尺寸和斑点面积总和中的一种或多种对裸电芯进行拔针检测，提高检测便 利性。
例如，通过CogBlobTool1算子实时抓取拔针检测区域，拔针检测区域所使用的空间跟随为步骤S136中建立的相对应的空间坐标系，确保检测区域的稳定性。采用CogBlobTool1.Results.GetBlobs().count获取实时抓取到的斑点个数，采用For(int i＝0；i<Count-1,i++)循环语句循环，获取对应区域所有斑点(高/宽/面积)，通过
CogBlobTool1.Results.GetBlobs()[i].GetMeasure(CogBlobMeasureConstants.BoundingBoxExtremaAngleHeiht)
/CogBlobTool1.Results.GetBlobs()[i].GetMeasure(CogBlobMeasureConstants.BoundingBoxExtremaAngleWidth)
/CogBlobTool1.Results.GetBlobs()[i].Area，将获取得到的高宽数据，存入数组(高)和数据(宽)，判断数组中数据是否满足规格，将斑点面积累加，得到斑点面积总和，判断斑点面积总和是否满足规格。具体的，可以在高宽数组中数据不满足规格的情况下，判定结果直接为不合格。在高宽数组中数据合格时，若斑点面积总和满足规格，则判定结果为合格；反之，则判定结果为不合格。
在另一些实施例中，步骤S138包括：获取拔针检测区域中电芯隔离膜的边缘点到所在边缘的距离值，根据多个距离值，分析得到拔针检测结果。
具体的，可以是对多个距离值进行排序处理，得到排序后的距离值，然后，筛选出排序后的距离值中的最大值，根据最大值检测是否存在拔针不良的问题。以边缘a为例，通过计算边缘a上的点到边缘本身a的距离获取最大值，最大值即可理解为边缘a上最大的凸点，根据最大距离检测是否存在拔针不良，有利于抓取整个边缘集体漏出拔针现象。例如：通过CogFindLineTool3实时抓取边缘，采用CogFindLineTool3.Results.Count获取实时抓取到的点位个数Count，采用For(int i＝0；i<Count-1,i++)循环语句循环，获取对应边缘上所有点位通过CogFindLineTool3.Results[i].DistanceToLine()算法，获取每个点到边缘本身的距离，将结果保存在数组中，通过将数组中数据进行大小排序得到最大值，最后判断该值是否在检测规格范围内。可以理解的是，在其他实施例中，还可以是采用其他方式进行拔针检测，如求取距离值中的平均值，判断平均值是否在预设的检测规格范围内，以检测是否存在拔针不良。
本实施例中，通过分析拔针检测区域中电芯隔离膜的边缘点，到自身所在边缘的距离值来进行拔针检测，有利于抓取整个边缘集体漏出拔针现象。
此外，在一些实施例中，如图9所示，步骤S130之后，该方法还可包括步骤S140：逻辑控制器将检测结果信息与裸电芯的标识信息进行绑定存储。以标识信息为二维码为例，逻辑控制器还可通过对高曝光度图片进行图像识别，获取标识层上的二维码。在得到检测结果信息后，逻辑控制器将检测结果信息与裸电芯的标识信息绑定存入数据库，还可将检测结果信息同时上传MES(Manufacturing Execution System，制造执行系统)，待裸电芯运输到 分拣工位，PLC触发扫码枪扫描裸电芯上的二维码，以识别数据库中与该裸电芯相对应的检测结果信息，检测结果信息可表征裸电芯为良品或非良品，进而根据识别到的检测结果信息判定裸电芯是否为良品。如果电芯是良品，则PLC控制搬料机械手将电芯搬运至良品缓存区；如果电芯是非良品，则PLC控制搬料机械手将电芯搬运至非良品缓存区。
本实施例中，通过将检测结果信息与裸电芯的标识信息进行绑定存储，方便后续工位结合检测结果信息对裸电芯进行分拣。
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裸电芯外观检测方法的裸电芯外观检测装置。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裸电芯外观检测装置实施例中的具体限定可以参见上文中对于裸电芯外观检测方法的限定，在此不再赘述。
在一些实施例中，如图10所示，提供了一种裸电芯外观检测装置，包括：图片获取模块110、图片处理模块120和图片检测模块130，其中：
图片获取模块110，用于获取对裸电芯拍摄得到的电芯图片；电芯图片为对准裸电芯边缘极耳位置拍摄得到。
图片处理模块120，用于确定电芯图片中的检测对象。
图片检测模块130，用于根据检测对象进行外观检测，得到检测结果信息。
在一些实施例中，电芯图片包括第一电芯图片，第一电芯图片的曝光度高于预设曝光度阈值，检测对象包括电芯隔离膜的边缘。图片处理模块120根据预设电芯模型确定第一电芯图片中的参考位置，根据参考位置抓取电芯隔离膜的边缘。
在一些实施例中，检测结果信息包括尺寸数据。图片检测模块130计算电芯隔离膜边缘的所有点到相对边缘的距离，得到边缘距离数据；根据边缘距离数据进行求平均，计算得到尺寸数据。
在一些实施例中，检测结果信息包括拔针检测结果。图片检测模块130根据电芯隔离膜的边缘确定拔针检测区域；对拔针检测区域进行检测，得到拔针检测结果。
在一些实施例中，图片检测模块130在拔针检测区域查找获取斑点信息，根据斑点信息分析得到拔针检测结果。
在一些实施例中，图片检测模块130获取拔针检测区域中电芯隔离膜的边缘点到所在边缘的距离值，根据距离值中的最大值分析得到拔针检测结果。
在一些实施例中，图片检测模块130将检测结果信息与裸电芯的标识信息进行绑定存储。
上述裸电芯外观检测装置中的各个模块可全部或部分通过软件、硬件及其组合来实现。上述各模块可以硬件形式内嵌于或独立于计算机设备中的处理器中，也可以以软件形式存储于计算机设备中的存储器中，以便于处理器调用执行以上各个模块对应的操作。
在一些实施例中，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11所示。该计算机设备包括通过系统总线连接的处理器、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系统、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系统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裸电芯外观检测方法。
本领域技术人员可以理解，图11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。
在一些实施例中，提供了一种计算机设备，包括存储器及一个或多个处理器，存储器中储存有计算机可读指令，计算机可读指令被一个或多个处理器执行时，使得一个或多个处理器执行上述各方法实施例中的步骤。
在一些实施例中，提供一个或多个存储有计算机可读指令的计算机存储介质，计算机可读指令被一个或多个处理器执行时，使得所述一个或多个处理器执行上述各方法实施例中的步骤。
在一些实施例中，提供了一种计算机程序产品，该计算机程序被一个或多个处理器执行时，使得一个或多个处理器执行上述各方法实施例中的步骤。
在一些实施例中，还提供了一种裸电芯外观检测系统，包括图像获取装置和上位机，图像获取装置用于对准裸电芯边缘极耳位置拍摄得到电芯图片，并将电芯图片发送至所述上位机，上位机用于根据上述的裸电芯外观检测方法进行裸电芯外观检测。
其中，图像获取装置采用双相机，具体可采用双CCD相机。为便于双相机能够更好地采集裸电芯的图片，确保检测结果的精度，双相机可位于裸电芯上方，并根据相机型号将双相机与裸电芯的间距设置为423±25mm，上位机可采用笔记本、台式电脑或逻辑控制器等。具体地，为了提升检测效果，降低误检和漏检的的概率，双相机可采用12MP彩色面阵相机，相机X方向视野可为260mm，像素精度为0.06mm/pixel，使得双相机视野可做到电芯的全视 野覆盖。相机分别拍照两次，高曝光度图片用于裸电芯尺寸检测，低曝光度图片用于裸电芯瑕疵检测。此外，裸电芯外观检测系统还包括光源，同样的，为了使得相机能够拍摄到更为清晰的电芯图片，可将光源与裸电芯的间距设置为100±20mm。光源具体可包括设置于裸电芯两侧长边上方的一对光源，两个光源的间距可为370±30mm。光源还包括设置于裸电芯两侧短边上方的一对光源，两个光源的间距为可370±30mm。随着裸电芯流入检测工位，在确保精度的情况下采用2只相机分别拍摄裸电芯对应部分区域，可以兼容多种产品，相机视野范围可兼容最大305°，最小120°。检测过程中，两个相机的间距可根据裸电芯的不同型号进行调节，光源到裸电芯的间距设计为100±20mm，角度可调节范围0到90°，光源之间的间距设计为370±30mm，可兼容最大和最小尺寸的裸电芯。
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。
以上所述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。
以上所述实施例仅表达了本申请的几种实施方式，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，在不脱离本申请构思的前提下，还可以做出若干变形和改进，这些都属于本申请的保护范围。因此，本申请专利的保护范围应以所附权利要求为准。

Claims (17)

  1. 一种裸电芯外观检测方法，包括：
    获取对裸电芯拍摄得到的电芯图片；所述电芯图片为对准裸电芯边缘极耳位置拍摄得到；
    确定所述电芯图片中的检测对象；及
    根据所述检测对象进行外观检测，得到检测结果信息。
  2. 根据权利要求1所述的方法，其中，所述电芯图片包括第一电芯图片，所述第一电芯图片的曝光度高于预设曝光度阈值，所述检测对象包括电芯隔离膜的边缘；所述确定所述电芯图片中的检测对象包括：根据预设电芯模型确定所述第一电芯图片中的参考位置，根据所述参考位置抓取电芯隔离膜的边缘。
  3. 根据权利要求2所述的方法，其中，所述检测结果信息包括尺寸数据；所述根据所述检测对象进行外观检测，得到检测结果信息，包括：
    计算所述电芯隔离膜边缘的所有点到相对边缘的距离，得到多个边缘距离数据；及
    根据多个所述边缘距离数据，得到尺寸数据。
  4. 根据权利要求3所述的方法，其中，所述边缘距离数据包括长度数据和宽度数据；所述根据多个所述边缘距离数据，得到尺寸数据包括：
    对多个所述长度数据进行求平均处理，得到长度平均值；
    对多个所述宽度数据进行求平均处理，得到宽度平均值；
    根据所述长度平均值和所述宽度平均值，得到尺寸数据。
  5. 根据权利要求2所述的方法，其中，所述检测结果信息包括拔针检测结果；所述根据所述检测区域进行外观检测，得到检测结果信息包括：
    根据所述电芯隔离膜的边缘确定拔针检测区域；及
    对所述拔针检测区域进行检测，得到拔针检测结果。
  6. 根据权利要求4所述的方法，其中，所述对所述拔针检测区域进行检测，得到拔针检测结果包括：
    在所述拔针检测区域查找获取斑点信息，根据所述斑点信息分析得到拔针检测结果。
  7. 根据权利要求6所述的方法，其中，所述斑点信息包括单个斑点面积、斑点尺寸和斑点面积总和中的至少一种。
  8. 根据权利要求5所述的方法，其中，所述对所述拔针检测区域进行检测，得到拔针检测结果包括：
    获取所述拔针检测区域中所述电芯隔离膜的边缘点到所在边缘的距离值，得到多个距离值；及
    根据多个所述距离值，分析得到拔针检测结果。
  9. 根据权利要求8所述的方法，其中，所述根据多个所述距离值分析得到拔针检测结果包括：
    对多个所述距离值进行排序处理，得到排序后的距离值；
    筛选出所述排序后的距离值中的最大值；
    根据筛选出的所述最大值，分析得到拔针检测结果。
  10. 根据权利要求1-9任意一项所述的方法，其中，所述根据所述检测对象进行外观检测，得到检测结果信息之后，所述方法还包括：将所述检测结果信息与裸电芯的标识信息进行绑定存储。
  11. 根据权利要求1-9任意一项所述的方法，其中，所述电芯图片由双相机对准裸电芯边缘极耳位置拍摄得到。
  12. 一种裸电芯外观检测装置，包括：
    图片获取模块，用于获取对裸电芯拍摄得到的电芯图片；所述电芯图片为对准裸电芯边缘极耳位置拍摄得到；
    图片处理模块，用于确定所述电芯图片中的检测对象；及
    图片检测模块，用于根据所述检测对象进行外观检测，得到检测结果信息。
  13. 一种计算机设备，包括存储器及一个或多个处理器，所述存储器中储存有计算机可读指令，所述计算机可读指令被所述一个或多个处理器执行时，使得所述一个或多个处理器执行权利要求1至11中任一项所述的方法的步骤。
  14. 一个或多个存储有计算机可读指令的计算机存储介质，所述计算机可读指令被一个或多个处理器执行时，使得所述一个或多个处理器执行权利要求1至11中任一项所述的方法的步骤。
  15. 一种计算机程序产品，包括计算机程序，该计算机程序被一个或多个处理器执行时，使得所述一个或多个处理器执行权利要求1至11中任一项所述的方法的步骤。
  16. 一种裸电芯外观检测系统，包括：图像获取装置和上位机，所述图像获取装置用于对准裸电芯边缘极耳位置拍摄得到电芯图片，并将所述电芯图片发送至所述上位机，所述上位机用于根据权利要求1-11任意一项所述的方法进行裸电芯外观检测。
  17. 根据权利要求16所述的系统，其中，所述图像获取装置包括双相机。
PCT/CN2023/084032 2022-08-10 2023-03-27 裸电芯外观检测方法、装置、计算机设备和存储介质 WO2024032000A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP23797624.6A EP4350621A1 (en) 2022-08-10 2023-03-27 Bare cell appearance inspection method and apparatus, computer device, and storage medium
US18/503,170 US20240070852A1 (en) 2022-08-10 2023-11-06 Appearance detection method and apparatus for bare cell, computer device, and storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210957577.6 2022-08-10
CN202210957577.6A CN115829913B (zh) 2022-08-10 2022-08-10 裸电芯外观检测方法、装置、计算机设备和存储介质

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/503,170 Continuation US20240070852A1 (en) 2022-08-10 2023-11-06 Appearance detection method and apparatus for bare cell, computer device, and storage medium

Publications (1)

Publication Number Publication Date
WO2024032000A1 true WO2024032000A1 (zh) 2024-02-15

Family

ID=85523039

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/084032 WO2024032000A1 (zh) 2022-08-10 2023-03-27 裸电芯外观检测方法、装置、计算机设备和存储介质

Country Status (4)

Country Link
US (1) US20240070852A1 (zh)
EP (1) EP4350621A1 (zh)
CN (1) CN115829913B (zh)
WO (1) WO2024032000A1 (zh)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115829913B (zh) * 2022-08-10 2024-05-17 宁德时代新能源科技股份有限公司 裸电芯外观检测方法、装置、计算机设备和存储介质
CN116037731B (zh) * 2023-03-31 2023-07-28 江苏时代新能源科技有限公司 极耳翻折改善装置及方法、电池生产设备
CN117740792A (zh) * 2024-02-20 2024-03-22 宁德时代新能源科技股份有限公司 裸电芯检测系统及裸电芯检测系统的点检方法
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、缺陷检测系统、装置、设备和存储介质
CN117825395A (zh) * 2024-03-06 2024-04-05 宁德时代新能源科技股份有限公司 裸电芯缺陷检测系统及方法
CN117895092A (zh) * 2024-03-15 2024-04-16 宁德时代新能源科技股份有限公司 一种用于对裸电芯进行配对的方法和系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109443418A (zh) * 2018-08-31 2019-03-08 广州超音速自动化科技股份有限公司 极片制片贴胶和裸电芯检测方法、设备、存储介质及系统
CN112577421A (zh) * 2019-12-11 2021-03-30 广东利元亨智能装备股份有限公司 一种电芯检测方法、装置及设备
WO2021169335A1 (zh) * 2020-02-25 2021-09-02 华南理工大学 一种锂电池极耳激光焊点视觉在线检测方法
CN113409296A (zh) * 2021-06-30 2021-09-17 广东利元亨智能装备股份有限公司 一种卷绕电芯的抽芯检测方法、电子设备及存储介质
CN115829913A (zh) * 2022-08-10 2023-03-21 宁德时代新能源科技股份有限公司 裸电芯外观检测方法、装置、计算机设备和存储介质

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107941805A (zh) * 2017-12-01 2018-04-20 无锡先导智能装备股份有限公司 电芯质量检测方法
CN109239075B (zh) * 2018-08-27 2021-11-30 北京百度网讯科技有限公司 电池检测方法及装置
CN109358064B (zh) * 2018-08-31 2022-07-08 广州超音速自动化科技股份有限公司 极片制片卷绕缺陷全功能检测方法、设备、介质及系统
CN109269419B (zh) * 2018-08-31 2022-01-18 广州超音速自动化科技股份有限公司 裸电芯外观尺寸检测方法、电子设备、存储介质及系统
CN111192246B (zh) * 2019-12-27 2023-06-13 苏州班奈特电子有限公司 一种焊点的自动检测方法
CN214957024U (zh) * 2021-04-23 2021-11-30 欣旺达电动汽车电池有限公司 电芯拔针检测装置和电芯加工设备
CN113989232B (zh) * 2021-10-28 2022-12-16 广东利元亨智能装备股份有限公司 电芯缺陷检测方法、装置、电子设备和存储介质
DE202022101348U1 (de) * 2022-03-14 2022-04-14 Guangzhou Supersonic Automation Technology Co. , Ltd. Vollfunktions-Erfassungssystem für Wickelfehler bei der Polstückherstellung
CN114813745A (zh) * 2022-04-01 2022-07-29 上海先导慧能技术有限公司 极耳翻折检测方法、装置、系统、电子设备及存储介质
CN114740001A (zh) * 2022-04-13 2022-07-12 深圳市凌云视迅科技有限责任公司 一种锂电池极片尺寸检测装置及方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109443418A (zh) * 2018-08-31 2019-03-08 广州超音速自动化科技股份有限公司 极片制片贴胶和裸电芯检测方法、设备、存储介质及系统
CN112577421A (zh) * 2019-12-11 2021-03-30 广东利元亨智能装备股份有限公司 一种电芯检测方法、装置及设备
WO2021169335A1 (zh) * 2020-02-25 2021-09-02 华南理工大学 一种锂电池极耳激光焊点视觉在线检测方法
CN113409296A (zh) * 2021-06-30 2021-09-17 广东利元亨智能装备股份有限公司 一种卷绕电芯的抽芯检测方法、电子设备及存储介质
CN115829913A (zh) * 2022-08-10 2023-03-21 宁德时代新能源科技股份有限公司 裸电芯外观检测方法、装置、计算机设备和存储介质

Also Published As

Publication number Publication date
CN115829913A (zh) 2023-03-21
US20240070852A1 (en) 2024-02-29
CN115829913B (zh) 2024-05-17
EP4350621A1 (en) 2024-04-10

Similar Documents

Publication Publication Date Title
WO2024032000A1 (zh) 裸电芯外观检测方法、装置、计算机设备和存储介质
WO2024032002A1 (zh) 电芯检测方法、装置、系统、计算机设备和存储介质
CN104792788B (zh) 一种涂胶视觉检测方法及其装置
WO2024108847A1 (zh) 辊、点检方法及装置、卷材传送方法及装置、设备、介质
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
CN101832753A (zh) 锂离子电池极片ccd在线检测系统和方法
WO2022143283A1 (zh) 摄像头标定方法、装置、计算机设备和存储介质
WO2023070552A1 (zh) 一种电池卷芯卷绕覆盖检测方法、装置及设备
US20230140944A1 (en) Battery Cell Exterior Inspection System
KR101469158B1 (ko) 카메라 렌즈 모듈 검사장치 및 그에 따른 검사방법
CN115147370A (zh) 一种电池顶盖焊接缺陷检测方法、装置、介质及电子设备
CN114088738A (zh) 一种环状焊缝的高精度缺陷检测方法和装置
KR20230108774A (ko) 레이저 거리 측정기 및 스테레오 카메라를 이용하여 이차전지용 전극의 결함을 검출하기 위한 비젼 검사 시스템
WO2020132961A1 (zh) 外观缺陷检测方法及装置
CN114549393A (zh) 图像标注方法、装置、设备及计算机存储介质
CN113109364A (zh) 一种芯片缺陷的检测方法及装置
CN102856214A (zh) 电路板置件方法
WO2024045427A1 (zh) 电芯检测系统及其控制方法、控制器和存储介质
CN113182205B (zh) 一种基于互联网的手机零件全自动机器人光电检测方法
CN114943715A (zh) 一种基于偏振度分布的机器视觉计数测量方法
CN116324864A (zh) 检测方法、电子设备和计算机可读存储介质
CN114445370A (zh) 一种模组膜层异物检测方法、装置和系统及计算机介质
CN112597832A (zh) 矩形件安装偏位判定方法和装置
WO2024016266A1 (zh) 检测电芯组件的极耳外观的方法与装置、电子设备
US11935260B1 (en) Method and apparatus for measuring dimensions, and computer-readable storage medium

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2023797624

Country of ref document: EP

Effective date: 20231211

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

Ref document number: 23797624

Country of ref document: EP

Kind code of ref document: A1