WO2024055569A1 - 检测电芯缺陷的方法、装置和计算机可读存储介质 - Google Patents

检测电芯缺陷的方法、装置和计算机可读存储介质 Download PDF

Info

Publication number
WO2024055569A1
WO2024055569A1 PCT/CN2023/085201 CN2023085201W WO2024055569A1 WO 2024055569 A1 WO2024055569 A1 WO 2024055569A1 CN 2023085201 W CN2023085201 W CN 2023085201W WO 2024055569 A1 WO2024055569 A1 WO 2024055569A1
Authority
WO
WIPO (PCT)
Prior art keywords
battery core
tab
edge line
inflection point
section
Prior art date
Application number
PCT/CN2023/085201
Other languages
English (en)
French (fr)
Inventor
王智玉
王晞
江冠南
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 EP23740926.3A priority Critical patent/EP4361950A1/en
Priority to US18/225,222 priority patent/US20240094137A1/en
Publication of WO2024055569A1 publication Critical patent/WO2024055569A1/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • 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 application relates to the field of battery core detection, and more specifically, to a method, device and computer-readable storage medium for detecting battery core defects.
  • the defects of the battery core can be determined based on the battery core image.
  • Embodiments of the present application provide a method, device and computer-readable storage medium for detecting battery core defects, which can completely obtain image information of the battery core, thereby accurately detecting battery core defects.
  • a method for detecting battery core defects including: determining a first segmentation diagram of the battery core body in the battery core image according to a first preset threshold; determining the tabs in the battery core image according to a second preset threshold.
  • the second segmentation map wherein the second preset threshold is smaller than the first preset threshold; determine the defective state of the battery core according to the first segmentation map and the second segmentation map.
  • the first segmented image determined according to the first preset threshold includes the image of the brighter area (battery cell body) in the battery cell image.
  • the second segmented image determined according to the second preset threshold contains image information of the darker area (lub) in the battery cell image, and the first segmented image and the second segmented image respectively contain images of different parts of the battery core. Therefore, the defective state of the battery core can be effectively detected based on the image information of the first segmentation diagram and the second segmentation diagram.
  • the defects of the battery core are determined based on the first segmentation diagram and the second segmentation diagram.
  • Defects include: determining the overall picture of the battery core based on the first segmented diagram and the second segmented diagram, where the overall diagram includes the battery core body and tabs; determining the defective situation of the battery core based on the overall diagram.
  • the overall diagram contains information about the battery core body and the tabs, the defects of the battery core can be more effectively determined based on the information about the battery core body and tabs in the overall diagram.
  • determining the defective situation of the battery core based on the overall diagram includes: determining information about the inflection point of the tab based on the overall diagram, where the inflection point of the tab is the end point of the connection line between the tab and the battery core body. ; Based on the information about the inflection point of the tab, determine the defective condition of the battery core.
  • the positional relationship between the inflection point of the tab and the battery core body in the overall diagram is more stable and intuitive, and the position of the inflection point of the tab in the overall diagram has a high correlation with the location where the defect occurs in the battery core, then The defects of the battery core can be effectively and accurately determined based on the information of the inflection point of the tab.
  • determining the information about the inflection point of the tab according to the overall diagram includes: determining the statistical diagram of the pixel sum in the first direction according to the overall diagram, wherein the first direction is perpendicular to the battery core body. direction of the first edge line of Inflection point information.
  • the statistical graph of the pixel sum of the overall image in the first direction can intuitively and conveniently reflect the height information of the battery core, and there is an obvious height difference on both sides of the inflection point of the tab, then through the third The statistical graph of the sum of pixels in one direction determines the information about the inflection point of the pole, which can simply and effectively obtain the information about the inflection point of the pole.
  • determining the information about the inflection point of the pole lug based on the statistical map of the sum of pixels in the first direction includes: determining based on the first statistical map of the sum of pixels in the first direction of the first target area.
  • the first target area includes the height information of the tabs and the first edge line and does not cover the width information of the battery core body
  • the first statistical graph can more intuitively reflect the height of the tabs. information, thereby more effectively determining the inflection point information of the polar ear.
  • determining the information about the inflection point of the pole lug based on the first statistical map of the sum of pixels in the first direction of the first target area in the overall image includes: based on the bulge in the first statistical map , determine the information of the inflection point of the pole.
  • the bulges in the first statistical graph can intuitively reflect the inflection point information of the pole, the information of determining the inflection point of the pole according to the bulges in the first statistical graph can be obtained more intuitively and conveniently.
  • the inflection point of the tab includes a first inflection point and a second inflection point of the first tab along the first edge line, and a first inflection point and a second inflection point of the second tab; according to the The inflection point information determines the defect status of the battery core, including: determining whether the battery core has an isolation film based on the values corresponding to the first section, the second section, and the third section of the first edge line in the first statistical chart.
  • the first section is the section from the first corner point of the cell body to the first inflection point of the first tab
  • the second section is the section from the second inflection point of the first tab to the second tab
  • the section between the first inflection point, the third section is the section between the second inflection point of the second tab and the second corner point of the cell body
  • the first corner point is the first edge line of the cell body
  • the corner point close to the first pole, the second corner point is A corner point on the first edge line of the cell body close to the second tab.
  • the corresponding values of the first section, the second section and the third section of the first edge line intuitively reflect the pixel conditions where the isolation film may protrude in the battery core, then according to The values corresponding to the first section, the second section and the third section of the first edge line can not only intuitively and conveniently determine whether the battery core has an isolation film protruding defect, but also determine the location of the isolation film protruding defect of the battery core.
  • determining whether the battery core has an isolation film protruding defect is determined based on the values corresponding to the first section, the second section, and the third section of the first edge line in the first statistical graph, including: When the value corresponding to the first section, the second section or the third section is greater than or equal to the preset threshold, it is determined that the battery core has an isolation film protruding defect; or, in the first section, the second section and the When the values corresponding to the third section are all less than the preset threshold, it is determined that the battery core has no isolation film protruding defect.
  • the second section and the third section can directly reflect the distance of the isolation film relative to the first edge line of the battery core body, through the first section and
  • the relationship between the value corresponding to the third section and the preset threshold can not only determine whether the battery core has a protruding defect of the isolation film, but also directly and conveniently obtain the height information of the protrusion of the isolation film.
  • determining the defective situation of the battery core based on the overall picture includes: determining the defective situation of the battery core based on the second statistical map of the sum of pixels in the second direction of the second target area, wherein: The two directions are perpendicular to the direction of the second edge line of the battery core body.
  • the second target area is the area between the second edge line of the battery core body in the overall diagram and the second boundary line of the overall diagram.
  • the second edge line is the edge line of the end of the battery core body away from the tab
  • the second boundary line is the boundary line of the end of the overall figure away from the tab.
  • the second statistical diagram of the sum of pixels in the second direction of the second target area in the overall picture reflects the protrusion of the isolation film on the side of the cell body away from the tab, according to the overall picture
  • the second statistical map of the sum of pixels in the second direction of the second target area determines the defective state of the battery core, and can more comprehensively detect protruding defects of the isolation film of the battery core.
  • determining the defective state of the battery core according to the second statistical map of the sum of pixels in the second direction of the second target area in the overall image includes: according to the second statistical map, the second edge The value corresponding to the line determines whether the battery core has a protruding defect of the isolation film.
  • the value corresponding to the second edge line is proportional to the protruding height of the cell isolation film, and the coordinates of the value corresponding to the second edge line correspond to the coordinates of the protruding position of the cell isolation film, then According to the value corresponding to the second edge line in the second statistical graph, it can not only be determined whether the battery core has an isolation film protrusion defect, but also the location of the isolation film protrusion.
  • determining whether the battery core has an isolation film protruding defect according to the value corresponding to the second edge line in the second statistical graph includes: the value corresponding to the second edge line is greater than or equal to a preset threshold. In this case, it is determined that the battery core has an isolation film protruding defect; or, in the case where the value corresponding to the second edge line is less than the preset threshold, it is determined that the battery core does not have an isolation film protruding defect.
  • the method for detecting cell defects further includes: determining The width of the battery core body in the first direction, where the first direction is perpendicular to the direction of the first edge line of the battery core body, where the first edge line of the battery core body is close to the tab in the overall view The edge line at one end; determine whether the cell has an isolation film misalignment defect based on the width.
  • the isolating film misalignment defect is determined by the width of the cell body in the first direction in the cell image, and it can be conveniently determined whether the isolating film misalignment defect occurs in the cell, so that more cells can be determined. Defect type.
  • determining whether the battery core has an isolation film misalignment defect based on the width includes: determining that the battery core has an isolation film misalignment defect when the width exceeds a preset range; or, determining whether the battery core has an isolation film misalignment defect when the width does not exceed the preset range. If it is within the case, it is determined that the battery core has no isolating film misalignment defect.
  • the misalignment of the cell isolation film is determined by determining whether the width exceeds the preset range. Not only can it be determined whether there is misalignment of the cell isolation film, but also the width of the misalignment of the cell isolation film can be determined.
  • determining the width of the battery core body in the first direction in the battery core image includes: determining the corner point of the battery core body; and determining the width based on the corner point of the battery core body.
  • a device for detecting cell defects including a processor and a memory.
  • the memory is used to store a program.
  • the processor is used to call and run the program from the memory to execute the first aspect or any one of the first aspects.
  • a computer-readable storage medium including a computer program.
  • the computer program When the computer program is run on a computer, it causes the computer to execute the detection of cells in the above-mentioned first aspect or any possible implementation of the first aspect. defective method.
  • Figure 1 is a schematic structural diagram of the system architecture provided by this application.
  • Figure 2 is a schematic flow chart of a method for detecting cell defects disclosed in an embodiment of the present application
  • Figure 3 is an image of a battery core disclosed in an embodiment of the present application.
  • Figure 4 is an overall view disclosed in an embodiment of the present application.
  • Figure 5 is a first statistical diagram of the sum of pixels in the first direction of the first target area in an overall image disclosed in an embodiment of the present application;
  • FIG6 is an image of a battery cell disclosed in another embodiment of the present application.
  • Figure 7 is a first statistical diagram of the sum of pixels in the first direction of the first target area in an overall image disclosed in another embodiment of the present application.
  • Figure 8 is an example of determining the first direction of the battery core body based on the corner points of the battery core body disclosed in an embodiment of the present application. Schematic flow chart of width on;
  • Figure 9 is a template image disclosed in an embodiment of the present application.
  • Figure 10 is a schematic diagram of the hardware structure of a device for detecting battery core defects according to an embodiment of the present application.
  • Embodiments of the present application may be applied to image processing systems, including but not limited to products based on infrared imaging.
  • the system for detecting battery core defects can be applied to various electronic devices with devices for detecting battery core defects.
  • the electronic devices can be personal computers, computer workstations, smartphones, tablet computers, smart cameras, media consumption equipment, wearable devices, Set-top boxes, game consoles, augmented reality (AR) AR/virtual reality (VR) equipment, vehicle-mounted terminals, etc.
  • AR augmented reality
  • VR virtual reality
  • the size of the sequence numbers of each process does not mean the order of execution.
  • the execution order of each process should be determined by its functions and internal logic, and should not be used in the embodiments of the present application.
  • the implementation process constitutes any limitation.
  • Power batteries are not only used in primary power systems such as water conservancy, wind power, thermal power and solar power stations, but are also widely used in electric bicycles, electric motorcycles, electric vehicles and other electric vehicles, as well as in many fields such as military equipment and aerospace.
  • power batteries usually include casing, protection circuit and battery core.
  • different defects may occur in multiple processes, such as winding, which requires the application of visual technology for automatic detection.
  • the winding needle is moved (the battery core is pulled out) to achieve the separation of the battery core and the winding needle.
  • defects such as protrusion of the isolation film in the battery core and dislocation of the isolation film in the battery core may occur, resulting in a decrease in the yield of power batteries. Therefore, it is necessary to effectively detect defects such as the protrusion of the isolation film in the battery core and the misalignment of the isolation film in the battery core to ensure the safety of the power battery leaving the factory.
  • the material of the tabs of the battery core is thin and soft, the tabs of the battery core are easily deformed during the production process, and the deformed areas of the tabs have poor reflectivity. Or, when the stacked tabs are misaligned, the tabs The misaligned areas are also less reflective. Therefore, the brightness of the deformed area and misaligned area of the tab in the battery core image is low, making it difficult to completely obtain the image information of the battery core and determine the defects of the battery core based on the image information of the battery core.
  • a defective method that determines the first segmentation map of the battery cell body in the battery cell image and the second segmentation map of the pole tab in the battery core image based on different preset thresholds, and based on the first segmentation map and the second segmentation map, Determine battery core defects.
  • the first segmented image determined according to the first preset threshold contains image information of the brighter area (battery cell body) in the battery cell image.
  • the second segmented image determined by the second preset threshold contains the image information of the darker area (lub) in the battery cell image.
  • the first segmented image and the second segmented image respectively contain image information of different parts of the battery core. Therefore, defects in the battery core can be effectively detected based on the image information of the first segmented image and the second segmented image.
  • this embodiment of the present application provides a system architecture 100.
  • the data acquisition device 160 is used to collect images of cells that are locally too dark.
  • the cell image that is too dark in parts may include a cell image that is too dark in one or more places.
  • the data acquisition device 160 After collecting the partially too dark battery cell image, the data acquisition device 160 stores the partially too dark battery cell image into the database 130, and the data processing device 120 obtains the preset based on the partially too dark battery cell image maintained in the database 130.
  • Threshold 101 (including the first preset threshold and the second preset threshold).
  • the above-mentioned preset threshold 101 can be used to determine the segmentation map (including the first segmentation map and the second segmentation map) in the method for detecting cell defects in the embodiment of the present application. It should be noted that in actual applications, the locally too dark cell images maintained in the database 130 are not necessarily collected by the data acquisition device 160, and may also be received from other devices. In addition, it should be noted that the data processing device 120 does not necessarily determine the preset threshold 101 based entirely on the locally too dark battery cell images maintained by the database 130. It may also obtain the partially too dark battery cell images from the cloud or other places. It is determined that the above description should not be used as a limitation on the embodiments of the present application.
  • the preset threshold 101 determined according to the data processing device 120 can be applied to different systems or devices, such as to the execution device 110 shown in Figure 1.
  • the execution device 110 can be a terminal, such as a mobile phone terminal, a tablet computer, a notebook Computers, etc., or servers or clouds, etc.
  • the execution device 110 is configured with an input/output (I/O) interface 112 for data interaction with external devices.
  • the user can input data to the I/O interface 112 through the client device 140.
  • the input data may include: the image to be detected (cell image) input by the client device 140 .
  • the client device 140 may be the same device as the execution device 110 and the data processing device 120.
  • the client device 140 may be a terminal device as the execution device 110 and the data processing device 120.
  • the client device 140 may be a different device from the above-mentioned execution device 110.
  • the client device 140 is a terminal device
  • the execution device 110 is a cloud, server, or other device.
  • the client device 140 may be a terminal device.
  • the device 140 can interact with the execution device 310 through a communication network of any communication mechanism/communication standard.
  • the communication network can be a wide area network, a local area network, a point-to-point connection, etc., or any combination thereof.
  • the computing module 111 of the execution device 110 is used to perform processing according to the input data (such as battery cell image) received by the I/O interface 112 .
  • the execution device 110 can call the data, codes, etc. in the data storage system 150 for corresponding processing, or can also use the data, instructions, etc. obtained by the corresponding processing. stored in the data storage system 150.
  • the I/O interface 112 returns the processing result, such as the defect status of the battery core obtained above, to the client device 140, thereby providing it to the user.
  • the user can manually enter the input data, and the manual input can be operated through the interface provided by the I/O interface 112 .
  • the client device 140 can automatically send input data to the I/O interface 112. If requiring the client device 140 to automatically send input data requires the user's authorization, the user can set corresponding permissions in the client device 140.
  • the user can view the results output by the execution device 110 on the client device 140, and the specific presentation form may be display, sound, action, etc.
  • the client device 140 can also be used as a data collection end to collect the input data of the input I/O interface 112 and the output results of the output I/O interface 112 as new sample data, and store them in the database 130 .
  • the I/O interface 112 directly uses the input data input to the I/O interface 112 and the output result of the output I/O interface 112 as a new sample as shown in the figure.
  • the data is stored in database 130.
  • Figure 1 is only a schematic diagram of a system architecture provided by an embodiment of the present application.
  • the positional relationship between the devices, devices, modules, etc. shown in the figure does not constitute any limitation.
  • the data The storage system 150 is an external memory relative to the execution device 110. In other cases, the data storage system 150 can also be placed in the execution device 110.
  • Figure 2 shows a schematic flow chart of a method for detecting cell defects disclosed in the embodiment of the present application.
  • the battery core includes a battery core body 310 and tabs 320 .
  • the cell body 310 includes pole pieces (not shown in the figure) and isolation films (not shown in the figure).
  • the battery cell image can be a picture taken by a charge coupled device (CCD) camera, or it can be a picture taken by other cameras, which is not limited in this application.
  • CCD charge coupled device
  • a CCD camera can be used to photograph the battery core to form a battery core image.
  • the position of the battery cell body 310 in the battery cell image is determined based on the larger first preset threshold.
  • the first segmentation map determines the second segmentation map of the tab 320 in the cell image according to the smaller second preset threshold.
  • first segmentation map of the battery cell body 310 in the battery cell image based on a larger first preset threshold value and to determine the second segmentation map of the tab 320 in the battery cell image based on a smaller second preset threshold value.
  • direct threshold segmentation method iterative threshold segmentation method, triangular threshold segmentation method, etc. can be used. The following is explained based on the direct threshold segmentation method.
  • the battery cell image may be segmented based on a threshold segmentation method to obtain a first segmentation image of the battery cell body 310 in the battery cell image, where the threshold of the threshold segmentation method is a first preset threshold. For example, if the pixel value in the battery cell image is greater than or equal to the first preset threshold, then the pixel value at this position is set to 1, otherwise the pixel value at this position is set to 0, so as to obtain a bipartite image, which can be The bipartite graph serves as the first segmentation graph. The same method can be used to obtain the second segmentation map.
  • the second Setting the preset threshold to a value smaller than the first preset threshold can effectively segment the image information of the above-mentioned parts.
  • the first segmented view includes the stronger reflectivity of the cell body 310 and the tab 320.
  • the second segmentation image includes image information of the less reflective part of the tab 320 .
  • the defects of the battery core are determined based on the image information of various parts of the battery core contained in the first segmented image and the second segmented image. For example, based on the information of the partial area of the tab 320 (the highly reflective area) in the first segmented diagram and the information of the partial area of the tab 320 (the weakly reflective area) in the second segmented diagram, the first The information of the tabs 320 in the diagram (for example, the position information of the tabs 320) is segmented to obtain the height information of the battery core, and the defects of the battery core are determined based on whether the height information of the battery core meets the preset conditions.
  • the preset condition may be whether the height of the position or area adjacent to the tab 320 exceeds the first standard height.
  • the preset condition may also be whether the height of the tab exceeds the second standard height. If it exceeds, the battery core is defective (for example, the tab is defective). Wherein, the first standard height is greater than the second standard height.
  • the detection situation only needs to be determined based on the height information of the position or area adjacent to the tab 320 .
  • the specific judgment standard used to detect defects in battery cells can be set according to the actual situation.
  • determining the defective situation of the battery core based on the first segmentation diagram and the second segmentation diagram includes: determining an overall diagram of the battery core based on the first segmentation diagram and the second segmentation diagram, wherein the overall The picture includes the battery core body and tabs; determine the defects of the battery core based on the overall picture.
  • the overall image of the battery core can be obtained by splicing the first segmentation image and the second segmentation image, or it can be obtained by denoising and contour extraction of the spliced image.
  • the specific acquisition method is not limited here. That is to say, the specific acquisition method is not limited so that the overall image includes image information of the cell body and tabs. Obtain the information of the tabs of the overall figure (for example, the information of the corner points of the tabs), and determine the defects of the battery core based on the information of the tabs. For example: whether the pole ears are missing. Or, obtain the information of the battery cell body in the overall picture, and determine whether there is a defect in the battery cell body based on the information of the battery cell body in the overall picture.
  • the first segmentation map and the second segmentation map can be spliced to obtain a spliced battery cell image, and then the spliced battery cell image can be denoised (for example, based on an open operation algorithm) to obtain a cleaner image.
  • the spliced cell image is obtained, and multiple contours of the image are obtained (for example, the findContours function in OpenCv can be used) to determine the connected area.
  • the connected area includes the connected area formed by the cell body and the tabs and the connected area where clean noise has not been removed. Since the connected area formed by the cell body and the tabs is larger than the connected area of the noise, the image of the largest connected area is taken as the overall image.
  • the template matching method can be used to determine the information of the corner points of the pole lug. According to the information of the corner points of the pole lug (for example, the coordinates of the corner points of the pole lug (at least two)), the position adjacent to the pole lug position is determined or area, and determine whether the height of the above-mentioned position or area exceeds the first standard height. If it exceeds the first standard height, the battery core is defective.
  • the information of the corner points of the pole lug for example, the coordinates of the corner points of the pole lug (at least two)
  • the position adjacent to the pole lug position is determined or area, and determine whether the height of the above-mentioned position or area exceeds the first standard height. If it exceeds the first standard height, the battery core is defective.
  • the overall diagram contains information about the battery core body and the tabs, the defects of the battery core can be determined more effectively based on the information about the battery core body and tabs in the overall diagram.
  • determining the defective situation of the battery core based on the overall diagram includes: determining information on the inflection point of the tab based on the overall diagram, where the inflection point of the tab is the connection line between the tab and the battery core body. Endpoint; determine the defective condition of the battery core based on the information about the inflection point of the tab.
  • a template matching algorithm can be used to determine the information about the inflection point of the pole in the overall picture. Based on the information about the inflection point of the pole, the position or area adjacent to the pole position is determined, and it is judged whether the height of the above position or area exceeds If the first standard height is exceeded, the battery core is defective.
  • the positional relationship between the inflection point of the tab and the battery core body in the overall diagram is more stable and intuitive, and the position of the inflection point of the tab in the overall diagram has a high correlation with the location where the defect occurs in the battery core, then The defects of the battery core can be effectively and accurately determined based on the information of the inflection point of the tab.
  • determining the information of the inflection point of the tab according to the overall diagram includes: determining the statistical diagram of the pixel sum in the first direction according to the overall diagram, wherein the first direction is perpendicular to the battery core. The direction of the first edge line of the main body; based on the statistical map of the pixel sum in the first direction, the information of the inflection point of the pole ear is determined.
  • the pixel sum is obtained by column to obtain a statistical map of the pixel sum in the first direction.
  • the pixel values of the connected areas of the battery cells are the same, and the pixel values of the background areas other than the connected areas of the battery cells are the same.
  • the statistical graph of the pixel sum of the overall image in the first direction can intuitively and conveniently reflect the height information of the battery core, and there is an obvious height difference on both sides of the inflection point of the tab, then through the third The statistical graph of the sum of pixels in one direction determines the information about the inflection point of the pole, which can simply and effectively obtain the information about the inflection point of the pole.
  • determining the information of the inflection point of the pole lug based on the statistical map of the sum of pixels in the first direction includes: based on the statistical map of the sum of pixels in the first direction of the first target area in the overall image.
  • a statistical chart to determine information about the inflection point of the tab where the first target area is the area between the first edge line of the battery core body in the overall diagram and the first boundary line of the overall diagram, and the first edge line is the battery core The edge line of the main body close to the pole end, and the first boundary line is the boundary line of the overall figure close to the pole end.
  • the method of determining the first statistical map of the sum of pixels in the first direction of the first target region R1 is similar to the method of determining the statistical map of the sum of pixels in the first direction of the overall image, and will not be described again here.
  • There are many ways to identify the first edge line in the overall diagram For example, a straight line detection algorithm, or determining the first edge line based on the corner points of the cell body.
  • the first edge line L1 of the battery cell body in the overall diagram can be obtained based on the straight line detection algorithm, and the first edge line L1 of the battery cell body and the first boundary line L2 of the overall diagram are determined.
  • FIG. 5 is a first statistical diagram of the sum of pixels in the first direction of the first target area R1 in this embodiment.
  • the value of the gentle straight line in the first statistical chart corresponds to the pixel sum of the area (all background) in the first edge line L1 in the first target area R1 that is not connected to the tab
  • the value of the convex part can correspond to The pixel sum of the area of the tab (including the tab and the background) in the first target area R1.
  • the connection points M1, M2, M3 and M4 between the gentle straight line and the convex part correspond to the inflection points of the tabs.
  • the convex part may be a part whose sum of pixels is greater than zero and has a certain width (for example, the difference between the abscissas is between 400 and 800).
  • a certain width for example, the difference between the abscissas is between 400 and 800.
  • the inflection point of the first statistical chart There are many ways to determine the inflection point of the first statistical chart. For example, you can determine the inflection point information of the pole according to the difference between the sum of adjacent pixels in the first statistical chart; you can also determine the inflection point information of the pole according to the change of the sum of pixels in the first statistical chart. Determine the inflection point information of the pole ear.
  • a preset pixel and range (for example, 0-100) is determined based on the height information of the tab, and a search range for the inflection point of the tab is determined in the first statistical chart based on the preset pixels and range (not shown in the figure). (out), the information of the inflection point of the pole is determined within the search range of the inflection point of the pole according to the preset distance information (dx, dy).
  • the first target area includes the height information of the tabs and the first edge line and does not cover the width information of the battery core body
  • the first statistical graph can more intuitively reflect the height of the tabs. information, thereby more effectively determining the inflection point information of the polar ear.
  • determining the information of the inflection point of the pole according to the first statistical map of the sum of pixels in the first direction of the first target area in the overall image includes: based on the convexity in the first statistical map to determine the inflection point information of the polar ear.
  • the position of the bumps in the first statistical graph can be calculated, and the distance between each bump can be calculated. Since there are certain defects in the battery cells produced in the actual production line, multiple bumps will appear in the first statistical graph. Therefore, multiple bumps need to be screened to determine the bump corresponding to the inflection point. Therefore, the protrusion corresponding to the largest distance among the distances between the respective protrusions is regarded as the inflection point of the tab.
  • three bumps appear in the first statistical graph, namely the bump between B1C1, the bump between I2I3 and the bump between D1E1.
  • the distance between the three bumps needs to be calculated.
  • the distance between the starting points of the three bumps can be calculated (for example, the distance of B1I2, the distance of I2D1, and the distance of B1D1), and the largest distance ( The bulge corresponding to the distance B1D1) is the inflection point of the pole.
  • the bulges in the first statistical graph can intuitively reflect the inflection point information of the pole, the information of determining the inflection point of the pole according to the bulges in the first statistical graph can be obtained more intuitively and conveniently.
  • the inflection point of the pole includes a first inflection point and a second inflection point of the first pole along the first edge line, and a first inflection point and a second inflection point of the second pole; according to the pole Information about the inflection point to determine the defect status of the battery core, including: determining whether the battery core has isolation based on the values corresponding to the first section, the second section, and the third section of the first edge line in the first statistical chart Film protrusion defect; wherein, the first section is the section from the first corner point of the cell body to the first inflection point of the first tab, and the second section is the section from the second inflection point of the first tab to the second pole The section between the first inflection point of the lug, the third section is the section between the second inflection point of the second tab and the second corner point of the cell body, the first corner point is the first edge line of the cell body The second corner point is the corner point on the first edge line of the battery core body
  • the first inflection point B of the first tab 321 and the second inflection point B of the first tab 321 in the battery core image can be determined according to the method of determining the inflection point information of the tab described in the above embodiment.
  • the inflection point C, the first inflection point D of the second tab 322 and the second inflection point E of the second tab 322 can be determined by using a template matching algorithm.
  • the values of the first section A1B1 in the first statistical chart, the second section C1D1 of the first statistical chart, and the third section E1F1 of the first statistical chart correspond to the first area in Figure 6 610, the pixel distribution of the second area 620 and the third area 630, and the first area 610, the second area 620 and the third area 630 are areas where defects in the battery core may occur. Therefore, it can be determined whether there is a defect of the isolation film protruding in the battery core based on the relationship between the values of the first section A1B1, the second section C1D1, and the third section E1F1 and the largest pixel sum in the first statistical graph.
  • the battery core has a defect of the isolation film protruding. If the first section A1B1, the second section E1F1 If the values of segment C1D1 and the third segment E1F1 are greater than the second preset difference value, it is determined that there is no isolation film protrusion in the battery core.
  • the corresponding values of the first section, the second section and the third section of the first edge line intuitively reflect the pixel conditions where the isolation film may protrude in the battery core, then according to The values corresponding to the first section, the second section and the third section of the first edge line can not only intuitively and conveniently determine whether the battery core has an isolation film protruding defect, but also determine the location of the isolation film protruding defect of the battery core.
  • the isolation film protruding defect appears in the second region 620 for illustration.
  • the isolation film isolation film protruding area 621
  • the value corresponding to the second section C1D1 of the first edge line in the first statistical chart will become larger. That is to say, when no isolation film appears in the second area 620 (all are backgrounds), the sum of pixels in the second area 620 in the first direction is zero, and when an isolation film appears in the second area 620 (there is background and isolation film), the sum of pixels in the second region 620 in the first direction increases as the area of the isolation film increases.
  • the value corresponding to the second section C1D1 of the first edge line in the first statistical chart also reflects the protruding height of the isolation film.
  • the highest point I of the needle pullout represents the highest protruding height of the isolation film
  • the value of the corresponding point I1 in Figure 7 is the largest in the second section C1D1. Therefore, the greater the value corresponding to the second section C1D1 of the first edge line in the first statistical chart, the higher the protruding height of the isolation film.
  • the second section corresponds to the value corresponding to C1D1
  • it is greater than or equal to the preset threshold it is determined that the battery core has an isolation film protrusion defect at this position; when the value corresponding to C1D1 in the second section is less than the preset threshold, it is determined that the battery core does not have an isolation film protrusion defect at this position.
  • the method of determining whether there is an isolation film defect in the battery core according to whether the values corresponding to the first section and the third section are greater than or equal to the preset threshold is similar to that in the second section, and will not be described again here.
  • the second section and the third section can directly reflect the distance of the isolation film relative to the first edge line of the battery core body, through the first section and
  • the relationship between the value corresponding to the third section and the preset threshold can not only determine whether the battery core has a protruding defect of the isolation film, but also directly and conveniently obtain the height information of the protrusion of the isolation film.
  • the protruding part of the isolation film of the battery core may not only occur on the side of the battery body close to the tab, but may also occur on the side of the battery body away from the tab.
  • this application also proposes the following embodiments.
  • determining the defect situation of the battery core based on the overall image includes: determining the defects of the battery core based on the second statistical map of the sum of pixels in the second direction of the second target area in the overall image.
  • the second direction is perpendicular to the direction of the second edge line of the battery core body
  • the second target area is the area between the second edge line of the battery core body in the overall view and the second boundary line of the overall view.
  • the second edge line is the edge line of the end of the battery core body away from the tab
  • the second boundary line is the boundary line of the end of the overall figure away from the tab.
  • a method of obtaining a second statistical map of the sum of pixels in the second direction of the second target area in the overall image and a first statistical map of the sum of pixels in the first direction of the first target area in the overall image are obtained.
  • the method is similar and will not be described again here.
  • the protruding defect of the isolation film can be determined based on the changing trend of the second statistical graph. For example, when the second statistical graph is a straight line, it is determined that the battery core does not have an isolation film protruding defect; when the second statistical graph is not a straight line, it is determined that the battery core has an isolation film defect.
  • first direction and the second direction may be parallel.
  • the second statistical diagram of the sum of pixels in the second direction of the second target area in the overall picture reflects the protrusion of the isolation film on the side of the cell body away from the tab, according to the overall picture
  • the second statistical map of the pixel sum in the second direction of the second target area determines the defective state of the battery core, and can more comprehensively detect protruding defects of the isolation film of the battery core.
  • determining the defective state of the battery core according to the second statistical map of the sum of pixels in the second direction of the second target area in the overall image includes: according to the second statistical map, the second The value corresponding to the edge line determines whether the cell has an isolation film protruding defect.
  • the value corresponding to the second edge line in the second statistical graph reflects the protrusion of the isolation film of the battery core away from the tab side.
  • the protruding position of the isolation film on the side of the battery core away from the tab can also be determined based on the coordinates of the value corresponding to the first edge line.
  • the value corresponding to the second edge line is proportional to the protruding height of the cell isolation film, and the coordinates of the value corresponding to the second edge line correspond to the coordinates of the protruding position of the cell isolation film, then According to the value corresponding to the second edge line in the second statistical graph, it can not only be determined whether the battery core has an isolation film protrusion defect, but also the location of the isolation film protrusion.
  • Determining whether the battery core has an isolation film protrusion defect includes: determining that the battery core has an isolation film protrusion defect when the value corresponding to the second edge line is greater than or equal to a preset threshold; or, determining whether the battery core has an isolation film protrusion defect when the value corresponding to the second edge line is less than Under the preset threshold, it is determined that there is no protruding defect of the isolation film in the battery core.
  • the second target area is the background, and the values of the second statistical graph are all zero; when the isolation film protrudes in the second target, the second target area If there is a background and an isolation film, and there are non-zero values in the second statistical graph, determine the relationship between these non-zero values and the preset threshold, and determine whether all battery cells have isolation films protruding.
  • the non-zero value in the second statistical graph is greater than or equal to the preset threshold, it is determined that the battery core has an isolation film protrusion; when the non-zero value in the second statistical graph is less than the preset threshold, it is determined that the battery core has no protrusion. Isolation film protruding defect.
  • the method for detecting battery core defects further includes: determining the width of the battery core body in the first direction of the battery core image, wherein the first direction is perpendicular to the first edge line of the battery core body. direction; determine whether the cell has an isolation film misalignment defect based on the width.
  • the width of the battery core body in the first direction can be determined based on the distance from a point on the first edge line of the battery core body (for example, the inflection point of the tab) in the battery core image to the second edge line of the battery core body. And based on the relationship between the width of the battery core body in the first direction and the preset range, it is determined whether the battery core has an isolation film dislocation defect.
  • the isolating film misalignment defect is determined by the width of the cell body in the first direction in the cell image, and it can be conveniently determined whether the isolating film misalignment defect occurs in the cell, so that more cells can be determined. Defect type.
  • determining whether the battery core has an isolation film misalignment defect based on the width includes: determining that the battery core has an isolation film misalignment defect when the width exceeds a preset range; or, determining whether the battery core has an isolation film misalignment defect when the width does not exceed the preset range. If it is within the case, it is determined that the battery core has no isolating film misalignment defect.
  • the width of the cell body in the first direction will become larger.
  • the width exceeds the preset range, it is determined that the cell has an isolation film misalignment defect; when the width does not exceed the preset range, When inside, make sure there is no isolating film misalignment defect in the cell.
  • the misalignment of the cell isolation film is determined by determining whether the width exceeds the preset range. Not only can it be determined whether there is misalignment of the cell isolation film, but also the width of the misalignment of the cell isolation film can be determined.
  • determining the width of the battery core body in the first direction in the battery core image includes: determining the corner point of the battery core body; and determining the width based on the corner point of the battery core body.
  • the corner points of the battery core and the corner point of the battery core body can be determined to determine the height. For example, as shown in FIG. 8 , the width of the battery core body in the first direction can be determined according to the corner points of the battery core body.
  • a rectangular area 710 including the first corner point of the battery cell body in the template image, a rectangular area 720 including the second corner point of the battery cell body, and a rectangular area 720 including the third corner point of the battery cell body in the template image can be respectively defined.
  • the rectangular area 730 and the rectangular area 740 including the fourth corner point of the cell body serve as four different template images.
  • Search battery cell images based on the above 4 different template images Determine the four target corner areas with the highest similarity to these template images in the battery cell image, and determine the corresponding corner point of the battery cell body ( As shown in Figure 6, the first corner point A, the second corner point F, the third corner point G and the fourth corner point H).
  • FIG. 10 is a schematic diagram of the hardware structure of a device for detecting cell defects according to an embodiment of the present application.
  • the device 800 for detecting cell defects shown in FIG. 10 includes a memory 801, a processor 802, a communication interface 803 and a bus 804.
  • the memory 801, the processor 802, and the communication interface 803 implement communication connections between each other through the bus 804.
  • the memory 801 may be a read-only memory (ROM), a static storage device, and a random access memory (RAM).
  • the memory 801 can store programs. When the program stored in the memory 801 is executed by the processor 802, the processor 802 and the communication interface 803 are used to execute various steps of the method for detecting cell defects in the embodiment of the present application.
  • the processor 802 may be a general central processing unit (CPU), a microprocessor, an application specific integrated circuit (ASIC), a graphics processing unit (GPU), or one or more
  • the integrated circuit is used to execute relevant programs to execute the method for detecting cell defects according to the embodiment of the present application.
  • the processor 802 may also be an integrated circuit chip with signal processing capabilities. During the implementation process, each step of the method for detecting cell defects in the embodiment of the present application can be completed by instructions in the form of hardware integrated logic circuits or software in the processor 802 .
  • the above-mentioned processor 802 can also be a general-purpose processor, a digital signal processor (digital signal processing, DSP), an ASIC, an off-the-shelf programmable gate array (field programmable gate array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.
  • DSP digital signal processing
  • ASIC application specific integrated circuit
  • FPGA field programmable gate array
  • Each method, step and logical block diagram disclosed in the embodiment of this application can be implemented or executed.
  • a general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.
  • the steps of the methods disclosed in conjunction with the embodiments of the present application can be directly implemented by a hardware processor for execution, or can be executed by a combination of hardware and software modules in the processor.
  • the software module can be located in random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers and other mature storage media in this field.
  • the storage medium is located in the memory 801.
  • the processor 802 reads the information in the memory 801 and executes the method for detecting cell defects in the embodiment of the present application in conjunction with its hardware.
  • the communication interface 803 uses a transceiver device such as but not limited to a transceiver to implement communication between the device 800 and other devices or communication networks. For example, the traffic data of the unknown device can be obtained through the communication interface 803.
  • a transceiver device such as but not limited to a transceiver to implement communication between the device 800 and other devices or communication networks.
  • the traffic data of the unknown device can be obtained through the communication interface 803.
  • Bus 804 may include a path that carries information between various components of device 800 (eg, memory 801, processor 802, communication interface 803).
  • the device 800 may also include other devices necessary for normal operation. At the same time, based on specific needs, those skilled in the art should understand that the device 800 may also include hardware devices that implement other additional functions. In addition, those skilled in the art should understand that the device 800 may only include components necessary to implement the embodiments of the present application, and does not necessarily include all components shown in FIG. 10 .
  • Embodiments of the present application also provide a computer-readable storage medium that stores program code for device execution.
  • the program code includes instructions for executing the steps in the method for detecting cell defects.
  • Embodiments of the present application also provide a computer program product.
  • the computer program product includes a computer program stored on a computer-readable storage medium.
  • the computer program includes program instructions. When the program instructions are executed by a computer, The computer executes the above method for detecting cell defects.
  • the above-mentioned computer-readable storage medium may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.
  • the disclosed devices and methods can be implemented in other ways.
  • the device embodiments described above are only illustrative.
  • the division of the units is only a logical function division. In actual implementation, there may be other division methods.
  • multiple units or components may be combined or can be integrated into another system, or some features can be ignored, or not implemented.
  • the coupling or direct coupling or communication connection between each other shown or discussed may be through some interfaces, and the indirect coupling or communication connection of the devices or units may be in electrical, mechanical or other forms.
  • the described embodiments may be implemented by software, hardware, or a combination of software and hardware.
  • the described embodiments may also be embodied by computer-readable media having computer-readable code stored thereon, the computer-readable code including instructions executable by at least one computing device.
  • the computer-readable medium can be associated with any data storage device capable of storing data readable by a computer system. Examples of computer-readable media may include read-only memory, random access memory, compact disc read-only memory (Compact Disc Read-Only Memory, CD-ROM), hard disk drive (Hard Disk Drive, HDD), digital Video disc (Digital Video Disc, DVD), magnetic tape, optical data storage device, etc.
  • the computer readable medium also Can be distributed among computer systems connected through a network, so that computer-readable code can be stored and executed in a distributed manner.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Image Analysis (AREA)

Abstract

本申请实施例公开了一种检测电芯缺陷的方法、装置和计算机可读存储介质，其中，方法包括：根据第一预设阈值确定电芯图像中电芯主体的第一分割图；根据第二预设阈值确定电芯图像中极耳的第二分割图，其中，第二预设阈值小于第一预设阈值；根据第一分割图和第二分割图，确定电芯的缺陷情况。由此，能够完整地获取电芯的图像信息，从而准确地检测出电芯的缺陷。

Description

检测电芯缺陷的方法、装置和计算机可读存储介质
相关申请的交叉引用
本申请要求享有于2022年09月16日提交的名称为“检测电芯缺陷的方法、装置和计算机可读存储介质”的中国专利申请202211132007.X的优先权，该申请的全部内容通过引用并入本文中。
技术领域
本申请涉及电芯检测领域，更为具体地，涉及一种检测电芯缺陷的方法、装置和计算机可读存储介质。
背景技术
随着图像处理技术的发展，越来越多的图像处理技术被应用到工业检测中。例如，根据电芯图像确定电芯的缺陷情况。
然而，在检测电芯的过程中，由于受到环境光线的影响，使得电芯图像的部分区域出现过暗的情况，从而难以完整地获取电芯的图像信息，并准确地检测出电芯的缺陷。
发明内容
本申请实施例提供了一种检测电芯缺陷的方法、装置和计算机可读存储介质，能够完整地获取电芯的图像信息，从而准确地检测出电芯的缺陷。
第一方面，提供了一种检测电芯缺陷的方法，包括：根据第一预设阈值确定电芯图像中电芯主体的第一分割图；根据第二预设阈值确定电芯图像中极耳的第二分割图，其中，第二预设阈值小于第一预设阈值；根据第一分割图和第二分割图，确定电芯的缺陷情况。
在本申请实施例中，由于第一预设阈值大于第二预设阈值，则根据第一预设阈值确定的第一分割图像包含了电芯图像中较亮的区域(电芯主体)的图像信息，根据第二预设阈值确定的第二分割图像包含了电芯图像中较暗的区域(极耳)的图像信息，第一分割图像和第二分割图像分别包含了电芯不同部位的图像信息，由此，根据第一分割图和第二分割图的图像信息能够有效地检测出电芯的缺陷情况。
在一些可能的实施方式中，根据第一分割图和第二分割图，确定电芯的缺 陷情况，包括：根据第一分割图和第二分割图，确定电芯的整体图，其中，整体图包括电芯主体和极耳；根据整体图，确定电芯的缺陷情况。
在本申请实施例中，由于整体图中包含了电芯主体和极耳两部分的信息，能够更有效地根据整体图中电芯主体和极耳两部分的信息确定电芯的缺陷情况。
在一些可能的实施方式中，根据整体图，确定电芯的缺陷情况，包括：根据整体图，确定极耳的拐点的信息，其中，极耳的拐点为极耳与电芯主体连接线的端点；根据极耳的拐点的信息，确定电芯的缺陷情况。
在本申请实施例中，由于整体图中极耳拐点与电芯主体的位置关系更加稳定和直观，以及整体图中的极耳的拐点的位置与电芯产生缺陷的位置的关联度高，则根据极耳的拐点的信息能够有效且准确地确定电芯的缺陷。
在一些可能的实施方式中，根据整体图，确定极耳的拐点的信息，包括：根据整体图，确定第一方向上的像素和的统计图，其中，第一方向垂直于所述电芯主体的第一边缘线的方向，其中，电芯主体的第一边缘线为整体图中电芯主体的靠近极耳一端的边缘线；根据第一方向上的像素和的统计图，确定极耳的拐点的信息。
在本申请实施例中，由于整体图在第一方向上的像素和的统计图能够直观便捷地反映出电芯的高度信息，且极耳的拐点的两侧具有明显的高度差，则通过第一方向上的像素和的统计图确定极耳的拐点的信息，能够简单有效地获取极耳的拐点的信息。
在一些可能的实施方式中，根据第一方向上的像素和的统计图，确定极耳的拐点的信息，包括：根据第一目标区域的第一方向上的像素和的第一统计图，确定极耳的拐点的信息，其中，第一目标区域为整体图中电芯主体的第一边缘线到整体图的第一边界线之间的区域，整体图的第一边界线为整体图的靠近极耳一端的边界线。
在本申请的实施例中，由于第一目标区域包含了极耳与第一边缘线的高度信息，不涵盖电芯主体的宽度信息，则第一统计图可以更直观地反映出极耳的高度信息，从而更加有效地确定极耳的拐点的信息。
在一些可能的实施方式中，根据整体图中的第一目标区域的第一方向上的像素和的第一统计图，确定极耳的拐点的信息，包括：根据第一统计图中的凸起，确定极耳的拐点的信息。
在本申请实施例中，由于第一统计图中的凸起能够直观地反映出极耳的拐点信息，则根据第一统计图的凸起确定极耳的拐点的信息，能够更加直观便捷地得到极耳的拐点的信息。
在一些可能的实施方式中，极耳的拐点包括沿第一边缘线的第一极耳的第一拐点和第二拐点，以及第二极耳的第一拐点和第二拐点；根据极耳的拐点的信息，确定电芯的缺陷情况，包括：根据第一统计图中，第一边缘线的第一区段、第二区段和第三区段对应的值，确定电芯是否具有隔离膜突出缺陷；其中，第一区段为电芯主体的第一角点至第一极耳的第一拐点间的区段，第二区段为第一极耳的第二拐点至第二极耳的第一拐点间的区段，第三区段为第二极耳的第二拐点和电芯主体的第二角点间的区段，第一角点为电芯主体的第一边缘线上的靠近第一极耳的角点，第二角点为 电芯主体的第一边缘线上的靠近第二极耳的角点。
在本申请实施例中，由于第一边缘线的第一区段、第二区段和第三区段对应的值直观地反映出了电芯可能发生隔离膜突出的地方的像素情况，则根据第一边缘线的第一区段、第二区段和第三区对应的值不仅能够直观便捷地确定电芯是否具有隔离膜突出缺陷，还可以确定电芯的隔离膜突出缺陷的位置。
在一些可能的实施方式中，根据第一统计图中，第一边缘线的第一区段、第二区段和第三区段对应的值，确定电芯是否具有隔离膜突出缺陷，包括：在第一区段、第二区段或第三区段对应的值大于或等于预设阈值的情况下，确定电芯具有隔离膜突出缺陷；或者，在第一区段、第二区段和第三区段对应的值均小于预设阈值的情况下，确定电芯无隔离膜突出缺陷。
在本申请实施例中，由于第一区段、第二区段和第三区段对应的值可以直接反映出隔离膜相对电芯主体的第一边缘线的距离，则通过第一区段和第三区段对应的值与预设阈值的关系，不仅可以确定电芯是否存在隔离膜突出的缺陷，还可以直接便捷地获取隔离膜突出的高度信息。
在一些可能的实施方式中，根据整体图，确定电芯的缺陷情况，包括：根据第二目标区域的第二方向上的像素和的第二统计图，确定电芯的缺陷情况，其中，第二方向垂直于所述电芯主体的第二边缘线的方向，第二目标区域为整体图中电芯主体的第二边缘线到整体图的第二边界线之间的区域，整体图的第二边缘线为电芯主体的远离极耳一端的边缘线，第二边界线为整体图的远离极耳一端的边界线。
在本申请实施例中，由于整体图中的第二目标区域的第二方向上的像素和的第二统计图反映了电芯主体远离极耳一侧的隔离膜的突出情况，则根据整体图中的第二目标区域的第二方向上的像素和的第二统计图，确定电芯的缺陷情况，能够更全面地检测电芯的隔离膜突出缺陷。
在一些可能的实施方式中，根据整体图中的第二目标区域的第二方向上的像素和的第二统计图，确定电芯的缺陷情况，包括：根据第二统计图中，第二边缘线对应的值，确定电芯是否具有隔离膜突出缺陷。
在本申请实施例中，由于第二边缘线对应的值与电芯隔离膜突出的高度成正比，并且第二边缘线对应的值的坐标与电芯隔离膜突出的位置的坐标相对应，则根据第二统计图中第二边缘线对应的值不仅可以确定电芯是否具有隔离膜突出缺陷，还可以确定隔离膜突出的位置。
在一些可能的实施方式中，根据第二统计图中，第二边缘线对应的值，确定电芯是否具有隔离膜突出缺陷，包括：在第二边缘线对应的值大于或等于预设阈值的情况下，确定电芯具有隔离膜突出缺陷；或者，在第二边缘线对应的值小于预设阈值的情况下，确定电芯无隔离膜突出缺陷。
在本申请实施例中，通过比较第二边缘线大于或等于预设阈值的情况判断电芯的隔离膜的情况，不仅可以确定电芯的隔离膜的缺陷是否存在，还可以确定电芯的隔离膜的突出高度。
在一些可能的实施方式中，检测电芯缺陷的方法还包括：确定电芯图像中 电芯主体的第一方向上的宽度，其中，第一方向垂直于电芯主体的第一边缘线的方向，其中，电芯主体的第一边缘线为整体图中电芯主体的靠近极耳一端的边缘线；根据宽度确定电芯是否具有隔离膜错位缺陷。
在本申请实施例中，通过电芯图像中电芯主体的第一方向上的宽度确定隔离膜错位缺陷，能够便捷地确定电芯是否发生隔离膜错位缺陷，从而可以确定更多的电芯的缺陷类型。
在一些可能的实施方式中，根据宽度确定电芯是否具有隔离膜错位缺陷，包括：在宽度超出预设范围的情况下，确定电芯具有隔离膜错位缺陷；或者，在宽度未超出预设范围内的情况下，确定电芯无隔离膜错位缺陷。
在本申请实施例中，通过判断宽度是否超出预设范围确定电芯隔离膜错位的情况，不仅可以确定电芯隔离膜是否存在错位，还可以确定电芯隔离膜错位的宽度。
在一些可能的实施方式中，确定电芯图像中电芯主体的第一方向上的宽度，包括：确定电芯主体的角点；根据电芯主体的角点，确定宽度。
在本申请实施例中，由于电芯主体的角点的位置相对稳定，则根据角点能够获得准确的宽度，从而更准确地确定电芯的隔离膜错位情况。
第二方面，提供了一种检测电芯缺陷的装置，包括处理器和存储器，存储器用于存储程序，处理器用于从存储器中调用并运行程序以执行上述第一方面或第一方面的任一可能的实施方式中的检测电芯缺陷的方法。
第三方面，提供了一种计算机可读存储介质，包括计算机程序，当计算机程序在计算机上运行时，使得计算机执行上述第一方面或第一方面的任一可能的实施方式中的检测电芯缺陷的方法。
附图说明
为了更清楚地说明本申请实施例的技术方案，下面将对本申请实施例中所需要使用的附图作简单地介绍，显而易见地，下面所描述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，还可以根据附图获得其他的附图。
图1是本申请提供的系统架构的结构示意图；
图2是本申请一实施例公开的一种检测电芯缺陷的方法的示意性流程图；
图3是本申请一实施例公开的一种电芯图像；
图4是本申请一实施例公开的一种整体图；
图5是本申请一实施例公开的一种整体图中的第一目标区域的第一方向上的像素和的第一统计图；
图6是本申请另一实施例公开的一种电芯图像；
图7是本申请另一实施例公开的一种整体图中的第一目标区域的第一方向上的像素和的第一统计图；
图8是本申请一实施例公开的根据电芯主体的角点确定电芯主体的第一方向 上的宽度的示意性流程图；
图9是本申请一实施例公开的一种模板图像；
图10是本申请一实施例的一种检测电芯缺陷装置的硬件结构示意图。
具体实施方式
下面结合附图和实施例对本申请的实施方式作进一步详细描述。以下实施例的详细描述和附图用于示例性地说明本申请的原理，但不能用来限制本申请的范围，即本申请不限于所描述的实施例。
本申请实施例可适用于图像处理系统，包括但不限于基于红外成像的产品。该检测电芯缺陷的系统可以应用于具有检测电芯缺陷装置的各种电子设备，该电子设备可以为个人计算机、计算机工作站、智能手机、平板电脑、智能摄像头、媒体消费设备、可穿戴设备、机顶盒、游戏机、增强现实(augmented reality，AR)AR/虚拟现实(virtual reality，VR)设备，车载终端等，本申请公开的实施例对此不做限定。
应理解，本文中的具体的例子只是为了帮助本领域技术人员更好地理解本申请实施例，而非限制本申请实施例的范围。
还应理解，在本申请的各种实施例中，各过程的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本申请实施例的实施过程构成任何限定。
还应理解，本说明书中描述的各种实施方式，既可以单独实施，也可以组合实施，本申请实施例对此并不限定。
除非另有说明，本申请实施例所使用的所有技术和科学术语与本申请的技术领域的技术人员通常理解的含义相同。本申请中所使用的术语只是为了描述具体的实施例的目的，不是旨在限制本申请的范围。本申请所使用的术语“和/或”包括一个或多个相关的所列项的任意的和所有的组合。
目前，动力电池的应用越加广泛。动力电池不仅被应用于水利，风力、火力和太阳能电站等初等电源系统，还被广泛应用于电动自行车、电动摩托车、电动汽车等电动交通工具，以及军事装备和航空航天等多个领域。随着动力电池应用领域不断扩大，其市场需求也在不断增加。其中，动力电池通常包括外壳、保护电路和电芯。在电芯生产的过程中，多个工序可能会出现不同的缺陷，例如卷绕，需要应用视觉技术来自动检测。
本发明人注意到，在电芯的生产制造过程中，通常需要将电芯卷绕在卷针上，当卷绕完成后移动卷针(电芯拔针)，实现电芯与卷针的分离。在实际生产过程中，受到机器、环境等因素的影响，会造成电芯中的隔离膜突出和电芯中的隔离膜错位等缺陷，从而导致动力电池的良率下降。因此，需要有效地检测出电芯中的隔离膜突出和电芯中隔离膜错位等缺陷，以确保动力电池出厂的安全性。
然而，由于电芯的极耳的材质薄且软，导致在生产过程中电芯的极耳容易发生形变，且极耳的形变区域的反光性较差。或者，当堆叠的极耳发生错位时，极耳 的错位区域的反光性也较差。因此，电芯图像中极耳的形变区域和错位区域的亮度较低，难以完整地获取电芯的图像信息，并根据电芯的图像信息确定电芯的缺陷情况。
基于以上考虑，为了解决因极耳形变或者堆叠的极耳错位导致的电芯图像的信息不清楚而无法有效地检测出电芯缺陷的问题，发明人经过深入研究，设计了一种检测电芯缺陷的方法，该方法根据不同的预设阈值确定电芯图像中电芯主体的第一分割图和电芯图像中极耳的第二分割图，并根据第一分割图和第二分割图，确定电芯的缺陷情况。
上述方法中，由于第一预设阈值大于第二预设阈值，则根据第一预设阈值确定的第一分割图像包含了电芯图像中较亮的区域(电芯主体)的图像信息，根据第二预设阈值确定的第二分割图像包含了电芯图像中较暗的区域(极耳)的图像信息，第一分割图像和第二分割图像分别包含了电芯不同部位的图像信息，由此，根据第一分割图和第二分割图的图像信息能够有效地检测出电芯的缺陷情况。
为了更好地理解本申请实施例的方案，下面先结合图1对本申请实施例可能的应用场景进行简单的介绍。
如图1所示，本申请实施例提供了一种系统架构100。在图1中，数据采集设备160用于采集局部过暗的电芯图像。针对本申请实施例的检测电芯缺陷的方法来说，局部过暗的电芯图像可以是包括具有一处或多处过暗的电芯图像。
在采集到局部过暗的电芯图像之后，数据采集设备160将局部过暗的电芯图像存入数据库130，数据处理设备120基于数据库130中维护的局部过暗的电芯图像处理得到预设阈值101(包括第一预设阈值和第二预设阈值)。
上述预设阈值101能够用于确定本申请实施例的检测电芯缺陷的方法中的分割图(包括第一分割图和第二分割图)。需要说明的是，在实际的应用中，所述数据库130中维护的局部过暗的电芯图像不一定都来自于数据采集设备160的采集，也有可能是从其他设备接收得到的。另外需要说明的是，数据处理设备120也不一定完全基于数据库130维护的局部过暗的电芯图像进行预设阈值101的确定，也有可能从云端或其他地方获取局部过暗的电芯图像进行确定，上述描述不应该作为对本申请实施例的限定。
根据数据处理设备120确定的预设阈值101可以应用于不同的系统或设备中，如应用于图1所示的执行设备110，所述执行设备110可以是终端，如手机终端，平板电脑，笔记本电脑等，还可以是服务器或者云端等。在图1中，执行设备110配置输入/输出(input/output，I/O)接口112，用于与外部设备进行数据交互，用户可以通过客户设备140向I/O接口112输入数据，所述输入数据在本申请实施例中可以包括：客户设备140输入的待检测图像(电芯图像)。
在一些实施方式中，该客户设备140可以与上述执行设备110、数据处理设备120为同一设备，例如，客户设备140可以与上述执行设备110、数据处理设备120均为终端设备。
在另一些实施方式中，该客户设备140可以与上述执行设备110为不同设备，例如，客户设备140为终端设备，而执行设备110为云端、服务器等设备，客户设 备140可以通过任何通信机制/通信标准的通信网络与执行设备310进行交互，通信网络可以是广域网、局域网、点对点连接等方式，或它们的任意组合。
执行设备110的计算模块111用于根据I/O接口112接收到的输入数据(如电芯图像)进行处理。在执行设备110的计算模块111执行计算等相关的处理过程中，执行设备110可以调用数据存储系统150中的数据、代码等以用于相应的处理，也可以将相应处理得到的数据、指令等存入数据存储系统150中。
最后，I/O接口112将处理结果，如上述得到的电芯的缺陷情况返回给客户设备140，从而提供给用户。
在图1中所示情况下，用户可以手动给定输入数据，该手动给定可以通过I/O接口112提供的界面进行操作。另一种情况下，客户设备140可以自动地向I/O接口112发送输入数据，如果要求客户设备140自动发送输入数据需要获得用户的授权，则用户可以在客户设备140中设置相应权限。用户可以在客户设备140查看执行设备110输出的结果，具体的呈现形式可以是显示、声音、动作等具体方式。客户设备140也可以作为数据采集端，采集如图所示输入I/O接口112的输入数据及输出I/O接口112的输出结果作为新的样本数据，并存入数据库130。当然，也可以不经过客户设备140进行采集，而是由I/O接口112直接将如图所示输入I/O接口112的输入数据及输出I/O接口112的输出结果，作为新的样本数据存入数据库130。
值得注意的是，图1仅是本申请实施例提供的一种系统架构的示意图，图中所示设备、器件、模块等之间的位置关系不构成任何限制，例如，在图1中，数据存储系统150相对执行设备110是外部存储器，在其它情况下，也可以将数据存储系统150置于执行设备110中。
下面结合图2对本申请实施例的检测电芯缺陷的方法的主要过程进行介绍。
图2示出了本申请实施例公开的一种检测电芯缺陷的方法的示意性流程图。
210，根据第一预设阈值确定电芯图像中电芯主体的第一分割图；根据第二预设阈值确定电芯图像中极耳的第二分割图，其中，第二预设阈值小于第一预设阈值。
如图3所示，电芯包括电芯主体310和极耳320。其中，电芯主体310包括极片(图中未示出)和隔离膜(图中未示出)。而电芯图像可以是电荷耦合元件(charge coupled device，CCD)相机拍摄的图片，也可以是其他相机拍摄的图片，本申请对此不作限定。
在实际生产的过程中，可以在完成电芯卷绕并将卷针拔出后，利用CCD相机拍摄电芯以形成电芯图像。此时，由于电芯主体310和极耳320对光线的反射强度不同，导致电芯图像存在明暗不一的区域，则根据较大的第一预设阈值确定电芯图像中电芯主体310的第一分割图，根据较小的第二预设阈值确定电芯图像中极耳320的第二分割图。
根据较大的第一预设阈值确定电芯图像中电芯主体310的第一分割图和较小的第二预设阈值确定电芯图像中极耳320的第二分割图的方式有很多。例如，可以采用直接阈值分割法、迭代阈值分割法、三角阈值分割法等。下面基于直接阈值分割法进行说明。
可以基于阈值分割法对电芯图像进行分割，以获得电芯图像中电芯主体310的第一分割图，其中，阈值分割法的阈值为第一预设阈值。例如，若电芯图像中的像素值大于等于第一预设阈值，则将该位置的像素值设置为1，否则将该位置的像素值设置为0，以此获得一个二分图，可以将该二分图作为第一分割图。可以采用同样的方法，获得第二分割图。
需要说明的是，由于极耳320的形变部位和极耳320的错位部位的反光性差，导致电芯图像中相应区域的暗度较低，相应位置的像素值较小，由此，将第二预设阈值设置为小于第一预设阈值的值，能够有效地分割出上述部位的图像信息。并且，由于极耳320未发生形变部位和极耳320未错位部分的反光性和电芯主体310的反光性相似，则第一分割图包含了电芯主体310和极耳320的反光性较强部分的图像信息，第二分割图包含了极耳320的反光性较弱部分的图像信息。
220，根据第一分割图和第二分割图，确定电芯的缺陷情况。
具体地，根据第一分割图和第二分割图包含的电芯的各个部位的图像信息，确定电芯的缺陷情况。例如，根据第一分割图中的极耳320的部分区域(反光性强的区域)的信息和第二分割图中的极耳320的部分区域(反光性弱的区域)的信息，确定第一分割图中的极耳320的信息(例如，极耳320的位置信息)，获取电芯的高度信息，根据电芯的高度信息是否满足预设条件，确定电芯的缺陷情况。其中，预设条件可以为与极耳320相邻的位置或者区域的高度是否超出第一标准高度，若超出，则电芯存在缺陷(例如，电芯主体存在异物突出)。预设条件还可以为极耳的高度是否超出第二标准高度，若超出，则电芯存在缺陷(例如，极耳存在缺陷)。其中，第一标准高度大于第二标准高度。
需要说明的是，在根据第一标准高度确定电芯是否存在缺陷时，由于极耳320的高度超出第一标准高度，则不需要考虑极耳320的位置或者区域的高度信息。因此，仅需要根据与极耳320相邻的位置或者区域的高度信息确定检测情况。具体采用哪种判断标准检测电芯何种存在缺陷，可以根据实际情况设定。
在本申请实施例中，通过设置不同的预设阈值获取电芯不同部位的分割图，能够获取完整地电芯的图像信息，从而有效地检测出电芯的缺陷情况。
在本申请的一些实施例中，根据第一分割图和第二分割图，确定电芯的缺陷情况，包括：根据第一分割图和第二分割图，确定电芯的整体图，其中，整体图包括电芯主体和极耳；根据整体图，确定电芯的缺陷情况。
具体地，电芯的整体图可以是根据第一分割图和第二分割图拼接获取的，也可以是对拼接后的图像进行去噪和轮廓提取后获取的。具体的获取方式在此不做限制。也就是说，不限制具体的获取方式使得整体图包括电芯主体和极耳的图像信息。获取整体图的极耳的信息(例如，极耳的角点的信息)，并根据极耳的信息确定电芯的缺陷情况。例如：极耳是否存在缺失。或者，获取整体图的电芯主体的信息，并根据整体图的电芯主体的信息确定是电芯主体是否存在缺陷。
举例说明，可以对第一分割图和第二分割图进行拼接，以获得拼接的电芯图像，再对该拼接后的电芯图像进行去噪(例如，基于开运算算法)，获得较为干净 的拼接后的电芯图像，获取该图像的多个轮廓(例如，可以采用OpenCv中的findContours函数)，以确定连通区域。其中，连通区域包括电芯主体和极耳形成的连通区域和未剔除干净的噪声的连通区域。由于电芯主体和极耳形成的连通区域较之噪声的连通区域大，则将最大的连通区域的图像作为整体图。可以采用模板匹配的方法确定极耳的角点的信息，根据极耳的角点的信息(例如，极耳的角点的坐标(至少两个))，确定与极耳位置相邻的位置或者区域，判断上述位置或者区域的高度是否超出第一标准高度，若超出，则该电芯存在缺陷。
需要说明的是，上述实施例示出的电芯缺陷情况仅作为示例，不对本申请进行限制。
在本申请实施例中，由于整体图中包含了电芯主体和极耳两部分的信息，能够更有效地根据整体图中电芯主体和极耳两部分的信息确定电芯的缺陷情况。
在本申请的一些实施例中，根据整体图，确定电芯的缺陷情况，包括：根据整体图，确定极耳的拐点的信息，其中，极耳的拐点为极耳与电芯主体连接线的端点；根据极耳的拐点的信息，确定电芯的缺陷情况。
举例说明，可以采用模板匹配算法确定整体图中的极耳的拐点的信息，根据极耳的拐点的信息，确定与极耳位置相邻的位置或者区域，并判断上述位置或者区域的高度是否超出第一标准高度，若超出，则该电芯存在缺陷。
在本申请实施例中，由于整体图中极耳拐点与电芯主体的位置关系更加稳定和直观，以及整体图中的极耳的拐点的位置与电芯产生缺陷的位置的关联度高，则根据极耳的拐点的信息能够有效且准确地确定电芯的缺陷。
在本申请的一些实施例中，根据整体图，确定极耳的拐点的信息，包括：根据整体图，确定第一方向上的像素和的统计图，其中，第一方向垂直于所述电芯主体的第一边缘线的方向；根据第一方向上的像素和的统计图，确定极耳的拐点的信息。
具体地，在整体图上，沿着整体图的行方向，按列求取像素和，以获得第一方向上的像素和的统计图。在整体图中，电芯的连通区域的像素值相同，除电芯的连通区域以外的背景区域的像素值相同。计算相邻两列的像素和的差值，根据相邻像素和的差值超出第一预设差值时，则相邻两列中像素和较小的列上存在拐点，再根据电芯主体的高度在相邻两列中像素和较小的列上确定极耳的拐点的信息(拐点的位置信息)。
在本申请实施例中，由于整体图在第一方向上的像素和的统计图能够直观便捷地反映出电芯的高度信息，且极耳的拐点的两侧具有明显的高度差，则通过第一方向上的像素和的统计图确定极耳的拐点的信息，能够简单有效地获取极耳的拐点的信息。
在本申请的一些实施例中，根据第一方向上的像素和的统计图，确定极耳的拐点的信息，包括：根据整体图中的第一目标区域的第一方向上的像素和的第一统计图，确定极耳的拐点的信息，其中，第一目标区域为整体图中电芯主体的第一边缘线到整体图的第一边界线之间的区域，第一边缘线为电芯主体的靠近极耳一端的边缘线，第一边界线为整体图的靠近极耳一端的边界线。
具体地，第一目标区域R1的第一方向上的像素和的第一统计图的确定方式与整体图的第一方向上的像素和的统计图的确定方式类似，在此不再赘述。可以采用多种方式识别整体图中的第一边缘线。例如，直线检测算法，或者，根据电芯主体的角点确定第一边缘线。
例如，如图4所示，可以基于直线检测算法获取整体图中电芯主体的第一边缘线L1，根据电芯主体的第一边缘线L1与整体图的第一边界线L2确定整体图中的第一目标区域R1。
图5为本实施例中第一目标区域R1的第一方向上的像素和的第一统计图。其中，第一统计图中平缓的直线的值对应的是第一目标区域R1中第一边缘线L1中未与极耳相连的区域(均是背景)的像素和，凸起部分的值可以对应第一目标区域R1中极耳的区域(包括极耳和背景)的像素和。平缓的直线与凸起的部分的连接点M1、连接点M2、连接点M3和连接点M4对应的是极耳的拐点。其中，凸起部分可以为像素和大于零且具有一定宽度(例如，横坐标的差值在400～800之间)的部分。例如，在图5中，在第一统计图像中，M1M2段为一个凸起，M3M4为另一个凸起。
确定第一统计图的拐点的方式有很多，例如，可以根据第一统计图中相邻像素和的差值，确定极耳的拐点信息；也可以根据第一统计图中像素和的变化情况，确定极耳的拐点信息。
例如，根据极耳的高度信息，确定预设的像素和范围(例如，0-100)，根据预设的像素和范围在第一统计图中确定极耳的拐点的搜索范围(图中未示出)，在根据预先设置的距离信息(dx，dy)在极耳的拐点的搜索范围内确定极耳的拐点的信息。
在本申请的实施例中，由于第一目标区域包含了极耳与第一边缘线的高度信息，不涵盖电芯主体的宽度信息，则第一统计图可以更直观地反映出极耳的高度信息，从而更加有效地确定极耳的拐点的信息。
在本申请的一些实施例中，根据整体图中的第一目标区域的第一方向上的像素和的第一统计图，确定极耳的拐点的信息，包括：根据第一统计图中的凸起，确定极耳的拐点的信息。
具体地，可以计算第一统计图中凸起的位置，计算各个凸起之间的距离。由于因为实际产线中生产出来的电芯存在一定的缺陷，则第一统计图中会出现多个凸起，因此需要对多个凸起进行筛选，以确定与拐点对应的凸起。因此，将各个凸起之间的距离中的最大的距离对应的凸起为极耳的拐点。
举例说明，如图7所示，第一统计图中出现了三个凸起，即B1C1之间的凸起、I2I3之间的凸起和D1E1之间的凸起。此时，需要计算三个凸起之间的距离，例如，可以计算三个凸起的各个起点之间的距离(例如，B1I2的距离、I2D1的距离以及B1D1的距离)，将最大的距离(B1D1的距离)对应的凸起为极耳的拐点。
在本申请实施例中，由于第一统计图中的凸起能够直观地反映出极耳的拐点信息，则根据第一统计图的凸起确定极耳的拐点的信息，能够更加直观便捷地得到极耳的拐点的信息。
在本申请的一些实施例中，极耳的拐点包括沿第一边缘线的第一极耳的第一拐点和第二拐点，以及第二极耳的第一拐点和第二拐点；根据极耳的拐点的信息，确定电芯的缺陷情况，包括：根据第一统计图中，第一边缘线的第一区段、第二区段和第三区段对应的值，确定电芯是否具有隔离膜突出缺陷；其中，第一区段为电芯主体的第一角点至第一极耳的第一拐点间的区段，第二区段为第一极耳的第二拐点至第二极耳的第一拐点间的区段，第三区段为第二极耳的第二拐点和电芯主体的第二角点间的区段，第一角点为电芯主体的第一边缘线上的靠近第一极耳的角点，第二角点为电芯主体的第一边缘线上的靠近第二极耳的角点。
示例性地，如图6所示，可以根据上述实施例描述的确定极耳的拐点的信息的方法确定电芯图像中第一极耳321的第一拐点B、第一极耳321的第二拐点C、第二极耳322的第一拐点D和第二极耳322的第二拐点E，可以通过模板匹配算法确定电芯图像中电芯主体的第一边缘线L1上的第一角点A和第二角点F。
如图7所示，第一统计图中的第一区段A1B1、第一统计图的第二区段C1D1和第一统计图的第三区段E1F1的值对应的是图6中第一区域610、第二区域620和第三区域630的像素分布情况，且第一区域610、第二区域620和第三区域630为电芯可能出现缺陷的区域。由此，可以根据第一区段A1B1、第二区段C1D1和第三区段E1F1的值与第一统计图中最大的像素和的关系，以确定电芯是否存在隔离膜突出的缺陷。若第一区段A1B1、第二区段C1D1和第三区段E1F1的值小于等于第二预设差值，则确定电芯存在隔离膜突出的缺陷，若第一区段A1B1、第二区段C1D1和第三区段E1F1的值大于第二预设差值，则确定电芯未存在隔离膜突出。
在本申请实施例中，由于第一边缘线的第一区段、第二区段和第三区段对应的值直观地反映出了电芯可能发生隔离膜突出的地方的像素情况，则根据第一边缘线的第一区段、第二区段和第三区对应的值不仅能够直观便捷地确定电芯是否具有隔离膜突出缺陷，还可以确定电芯的隔离膜突出缺陷的位置。
在本申请的一些实施例中，根据第一统计图中，第一边缘线的第一区段、第二区段和第三区段对应的值，确定电芯是否具有隔离膜突出缺陷，包括：在第一区段、第二区段或第三区段对应的值大于或等于预设阈值的情况下，确定电芯具有隔离膜突出缺陷；或者，在第一区段、第二区段和第三区段对应的值均小于预设阈值的情况下，确定电芯无隔离膜突出缺陷。
示例性地，以隔离膜突出缺陷出现在第二区域620内进行说明。如图6和图7所示，由于在第二区域620内出现隔离膜(隔离膜突出区域621，)则第一统计图中第一边缘线的第二区段C1D1对应的值将变大。也就是说，在第二区域620内未出现隔离膜(均是背景)时，第二区域620在第一方向上的像素和为零，在第二区域620内出现隔离膜(存在背景和隔离膜)时，第二区域620在第一方向上的像素和随着隔离膜的面积增大而增大。并且，第一统计图中第一边缘线的第二区段C1D1对应的值还反映了隔离膜突出的高度。如图6中的拔针最高点I表示隔离膜突出的最高高度，则图7中的对应点I1的值在第二区段C1D1对应的值最大。由此，第一统计图中第一边缘线的第二区段C1D1对应的值越大，隔离膜突出的高度越高。当第二区段对应C1D1对应的值 大于或等于预设阈值时，则确定电芯在该位置存在隔离膜突出缺陷；当第二区段对应C1D1对应的值小于预设阈值时，则确定电芯在该位置未存在隔离膜突出缺陷。
需要说明的是，根据第一区段和第三区段对应的值是否大于等于预设阈值，以确定电芯是否存在隔离膜缺陷的方法和第二区段类似，在此不再赘述。
在本申请实施例中，由于第一区段、第二区段和第三区段对应的值可以直接反映出隔离膜相对电芯主体的第一边缘线的距离，则通过第一区段和第三区段对应的值与预设阈值的关系，不仅可以确定电芯是否存在隔离膜突出的缺陷，还可以直接便捷地获取隔离膜突出的高度信息。
需要说明的是，在一些应用场景下，电芯的隔离膜突出的部位不仅会发生在电芯主体靠近极耳的一侧，还可能发生在电芯主体远离极耳的一侧。为了进一步解决该问题，本申请还提出了如下实施例。
在本申请的一些实施例中，根据整体图，确定电芯的缺陷情况，包括：根据整体图中的第二目标区域的第二方向上的像素和的第二统计图，确定电芯的缺陷情况，其中，第二方向垂直于所述电芯主体的第二边缘线的方向，第二目标区域为整体图中电芯主体的第二边缘线到整体图的第二边界线之间的区域，第二边缘线为电芯主体的远离极耳一端的边缘线，第二边界线为整体图的远离极耳一端的边界线。
具体地，获取整体图中的第二目标区域的第二方向上的像素和的第二统计图的方式和获取整体图中的第一目标区域的第一方向上的像素和的第一统计图的方式类似，在此不再赘述。可以根据第二统计图的变化趋势确定隔离膜突出缺陷。例如，当第二统计图是一条直线时，则确定电芯不具有隔离膜突出缺陷，当第二统计图不是一条直线时，则确定电芯具有隔离膜缺陷。
需要说明的是，第一方向和第二方向可以平行。
在本申请实施例中，由于整体图中的第二目标区域的第二方向上的像素和的第二统计图反映了电芯主体远离极耳一侧的隔离膜的突出情况，则根据整体图中的第二目标区域的第二方向上的像素和的第二统计图，确定电芯的缺陷情况，能够更全面地检测电芯的隔离膜突出缺陷。
在本申请的一些实施例中，根据整体图中的第二目标区域的第二方向上的像素和的第二统计图，确定电芯的缺陷情况，包括：根据第二统计图中，第二边缘线对应的值，确定电芯是否具有隔离膜突出缺陷。
具体地，第二统计图中第二边缘线对应的值反映了电芯远离极耳侧的隔离膜的突出情况。第二边缘线对应的值越大，则电芯远离极耳侧的隔离膜突出的越多。并且，还可以根据第一边缘线对应的值的坐标，确定电芯远离极耳侧的隔离膜突出的位置。
在本申请实施例中，由于第二边缘线对应的值与电芯隔离膜突出的高度成正比，并且第二边缘线对应的值的坐标与电芯隔离膜突出的位置的坐标相对应，则根据第二统计图中第二边缘线对应的值不仅可以确定电芯是否具有隔离膜突出缺陷，还可以确定隔离膜突出的位置。
在本申请的一些实施例中，根据第二统计图中，第二边缘线对应的值，确 定电芯是否具有隔离膜突出缺陷，包括：在第二边缘线对应的值大于或等于预设阈值的情况下，确定电芯具有隔离膜突出缺陷；或者，在第二边缘线对应的值小于预设阈值的情况下，确定电芯无隔离膜突出缺陷。
可以理解的是，在第二目标区域未出现隔离膜突出时，第二目标区域均是背景，则第二统计图的值均为零；在第二目标出现隔离膜突出时，第二目标区域存在背景和隔离膜，则第二统计图存在不为零的值，则确定这些不为零的值与预设阈值的关系，确定电芯是否均有隔离膜突出。当第二统计图中的不为零的值大于或等于预设阈值，则确定电芯具有隔离膜突出；当第二统计图中的不为零的值小于预设阈值，则确定电芯无隔离膜突出缺陷。
在本申请实施例中，通过比较第二边缘线大于或等于预设阈值的情况判断电芯的隔离膜的情况，不仅可以确定电芯的隔离膜的缺陷是否存在，还可以确定电芯的隔离膜的突出高度。
在一些可能的实施方式中，检测电芯缺陷的方法还包括：确定电芯图像中电芯主体的第一方向上的宽度，其中，第一方向垂直于所述电芯主体的第一边缘线的方向；根据宽度确定电芯是否具有隔离膜错位缺陷。
具体地，可以根据电芯图像中电芯主体的第一边缘线上的点(例如，极耳的拐点)到电芯主体的第二边缘线的距离确定电芯主体的第一方向上宽度。并根据电芯主体的第一方向上宽度与预设范围的关系，确定电芯是否具有隔离膜错位缺陷。
在本申请实施例中，通过电芯图像中电芯主体的第一方向上的宽度确定隔离膜错位缺陷，能够便捷地确定电芯是否发生隔离膜错位缺陷，从而可以确定更多的电芯的缺陷类型。
在一些可能的实施方式中，根据宽度确定电芯是否具有隔离膜错位缺陷，包括：在宽度超出预设范围的情况下，确定电芯具有隔离膜错位缺陷；或者，在宽度未超出预设范围内的情况下，确定电芯无隔离膜错位缺陷。
可以理解的是，隔离膜发生错位时，电芯主体在第一方向上的宽度将变大，则当宽度超出预设范围时，确定电芯具有隔离膜错位缺陷；在宽度未超出预设范围内时，确定电芯无隔离膜错位缺陷。
在本申请实施例中，通过判断宽度是否超出预设范围确定电芯隔离膜错位的情况，不仅可以确定电芯隔离膜是否存在错位，还可以确定电芯隔离膜错位的宽度。
在一些可能的实施方式中，确定电芯图像中电芯主体的第一方向上的宽度，包括：确定电芯主体的角点；根据电芯主体的角点，确定宽度。
可以采用多种方式确定电芯的角点以及电芯主体的角点，确定高度。举例说明，如图8所示，可以根据电芯主体的角点确定电芯主体的第一方向上的宽度。
910，获取模板图像。
如图9所示，可以分别将包含模板图像中的电芯主体的第一角点的矩形区域710、包含电芯主体的第二角点的矩形区域720、包含电芯主体的第三角点的矩形区域730和包含电芯主体的第四角点的矩形区域740作为四个不同的模板图像。
920，基于模板匹配算法确定电芯图像中的电芯主体的第一角点、电芯主体 的第二角点、电芯主体的第三角点和电芯主体的第四角点。
基于上述4个不同的模板图像搜索电芯图像。在电芯图像中确定与这些模板图像相似度最高的4个目标角点区域，根据提前预设的位置信息(dx1，dy1)在相应的目标角点区域确定电芯主体的相应的角点(如图6所示第一角点A、第二角点F、第三角点G和第四角点H)。
930，根据第一角点或者第二角点的坐标确定电芯主体的第一边缘线，根据第三角点或者第四角点的坐标确定电芯主体的第二边缘线。
940，根据第一角点或者第二角点到第二边缘线的距离，或者，第三角点或者第四角点到第一边缘线的距离确定电芯主体的第一方向上宽度。
在本申请实施例中，由于电芯主体的角点的位置相对稳定，则根据角点能够获得准确的宽度，从而更准确地确定电芯的隔离膜错位情况。
图10是本申请实施例的检测电芯缺陷的装置的硬件结构示意图。图10所示的检测电芯缺陷的装置800包括存储器801、处理器802、通信接口803以及总线804。其中，存储器801、处理器802、通信接口803通过总线804实现彼此之间的通信连接。
存储器801可以是只读存储器(read-only memory，ROM)，静态存储设备和随机存取存储器(random access memory，RAM)。存储器801可以存储程序，当存储器801中存储的程序被处理器802执行时，处理器802和通信接口803用于执行本申请实施例的检测电芯缺陷的方法的各个步骤。
处理器802可以采用通用的中央处理器(central processing unit，CPU)，微处理器，应用专用集成电路(application specific integrated circuit，ASIC)，图形处理器(graphics processing unit，GPU)或者一个或多个集成电路，用于执行相关程序，以执行本申请实施例的检测电芯缺陷的方法。
处理器802还可以是一种集成电路芯片，具有信号的处理能力。在实现过程中，本申请实施例的检测电芯缺陷的方法的各个步骤可以通过处理器802中的硬件的集成逻辑电路或者软件形式的指令完成。
上述处理器802还可以是通用处理器、数字信号处理器(digital signal processing，DSP)、ASIC、现成可编程门阵列(field programmable gate array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。可以实现或者执行本申请实施例中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。结合本申请实施例所公开的方法的步骤可以直接体现为硬件处理器执行完成，或者用处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器801，处理器802读取存储器801中的信息，结合其硬件执行本申请实施例的检测电芯缺陷的方法。
通信接口803使用例如但不限于收发器一类的收发装置，来实现装置800与其他设备或通信网络之间的通信。例如，可以通过通信接口803获取未知设备的流量数据。
总线804可包括在装置800各个部件(例如，存储器801、处理器802、通信接口803)之间传送信息的通路。
应注意，尽管上述装置800仅仅示出了存储器、处理器、通信接口，但是在具体实现过程中，本领域的技术人员应当理解，装置800还可以包括实现正常运行所必须的其他器件。同时，根据具体需要，本领域的技术人员应当理解，装置800还可包括实现其他附加功能的硬件器件。此外，本领域的技术人员应当理解，装置800也可仅仅包括实现本申请实施例所必须的器件，而不必包括图10中所示的全部器件。
本申请实施例还提供了一种计算机可读存储介质，存储用于设备执行的程序代码，程序代码包括用于执行上述检测电芯缺陷的方法中的步骤的指令。
本申请实施例还提供了一种计算机程序产品，所述计算机程序产品包括存储在计算机可读存储介质上的计算机程序，所述计算机程序包括程序指令，当所述程序指令被计算机执行时，使所述计算机执行上述检测电芯缺陷的方法。
上述的计算机可读存储介质可以是暂态计算机可读存储介质，也可以是非暂态计算机可读存储介质。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的装置、计算机可读存储介质和计算机程序产品的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
本申请中使用的用词仅用于描述实施例并且不用于限制权利要求。如在实施例以及权利要求的描述中使用的，除非上下文清楚地表明，否则单数形式的“一个”和“所述”旨在同样包括复数形式。类似地，如在本申请中所使用的术语“和/或”是指包含一个或一个以上相关联的列出的任何以及所有可能的组合。另外，当用于本申请中时，术语“包括”指陈述的特征、整体、步骤、操作、元素，和/或组件的存在，但不排除一个或一个以上其它特征、整体、步骤、操作、元素、组件和/或这些的分组的存在或添加。
所描述的实施例中的各方面、实施方式、实现或特征能够单独使用或以任意组合的方式使用。所描述的实施例中的各方面可由软件、硬件或软硬件的结合实现。所描述的实施例也可以由存储有计算机可读代码的计算机可读介质体现，该计算机可读代码包括可由至少一个计算装置执行的指令。所述计算机可读介质可与任何能够存储数据的数据存储装置相关联，该数据可由计算机系统读取。用于举例的计算机可读介质可以包括只读存储器、随机存取存储器、紧凑型光盘只读储存器(Compact Disc Read-Only Memory，CD-ROM)、硬盘驱动器(Hard Disk Drive，HDD)、数字视频光盘(Digital Video Disc，DVD)、磁带以及光数据存储装置等。所述计算机可读介质还 可以分布于通过网络联接的计算机系统中，这样计算机可读代码就可以分布式存储并执行。
上述技术描述可参照附图，这些附图形成了本申请的一部分，并且通过描述在附图中示出了依照所描述的实施例的实施方式。虽然这些实施例描述的足够详细以使本领域技术人员能够实现这些实施例，但这些实施例是非限制性的；这样就可以使用其它的实施例，并且在不脱离所描述的实施例的范围的情况下还可以做出变化。比如，流程图中所描述的操作顺序是非限制性的，因此在流程图中阐释并且根据流程图描述的两个或两个以上操作的顺序可以根据若干实施例进行改变。作为另一个例子，在若干实施例中，在流程图中阐释并且根据流程图描述的一个或一个以上操作是可选的，或是可删除的。另外，某些步骤或功能可以添加到所公开的实施例中，或两个以上的步骤顺序被置换。所有这些变化被认为包含在所公开的实施例以及权利要求中。
另外，上述技术描述中使用术语以提供所描述的实施例的透彻理解。然而，并不需要过于详细的细节以实现所描述的实施例。因此，实施例的上述描述是为了阐释和描述而呈现的。上述描述中所呈现的实施例以及根据这些实施例所公开的例子是单独提供的，以添加上下文并有助于理解所描述的实施例。上述说明书不用于做到无遗漏或将所描述的实施例限制到本申请的精确形式。根据上述教导，若干修改、选择适用以及变化是可行的。在某些情况下，没有详细描述为人所熟知的处理步骤以避免不必要地影响所描述的实施例。虽然已经参考优选实施例对本申请进行了描述，但在不脱离本申请的范围的情况下，可以对其进行各种改进并且可以用等效物替换其中的部件。尤其是，只要不存在结构冲突，各个实施例中所提到的各项技术特征均可以任意方式组合起来。本申请并不局限于文中公开的特定实施例，而是包括落入权利要求的范围内的所有技术方案。

Claims (16)

  1. 一种检测电芯缺陷的方法，其特征在于，所述方法包括：
    根据第一预设阈值确定电芯图像中电芯主体的第一分割图；
    根据第二预设阈值确定所述电芯图像中极耳的第二分割图，其中，所述第二预设阈值小于所述第一预设阈值；
    根据所述第一分割图和所述第二分割图，确定所述电芯的缺陷情况。
  2. 根据权利要求1所述的方法，其特征在于，所述根据所述第一分割图和所述第二分割图，确定所述电芯的缺陷情况，包括：
    根据所述第一分割图和所述第二分割图，确定所述电芯的整体图，其中，所述整体图包括所述电芯主体和所述极耳；
    根据所述整体图，确定所述电芯的缺陷情况。
  3. 根据权利要求2所述的方法，其特征在于，所述根据所述整体图，确定所述电芯的缺陷情况，包括：
    根据所述整体图，确定所述极耳的拐点的信息，其中，所述极耳的拐点为所述极耳与所述电芯主体连接线的端点；
    根据所述极耳的拐点的信息，确定所述电芯的缺陷情况。
  4. 根据权利要求3所述的方法，其特征在于，所述根据所述整体图，确定所述极耳的拐点的信息，包括：
    根据所述整体图，确定第一方向上的像素和的统计图，其中，所述第一方向垂直于所述电芯主体的第一边缘线的方向，其中，所述电芯主体的第一边缘线为所述整体图中所述电芯主体的靠近所述极耳一端的边缘线；
    根据所述第一方向上的像素和的统计图，确定所述极耳的拐点的信息。
  5. 根据权利要求4所述的方法，其特征在于，所述根据所述第一方向上的像素和的统计图，确定所述极耳的拐点的信息，包括：
    根据第一目标区域的所述第一方向上的像素和的第一统计图，确定所述极耳的拐点的信息，其中，所述第一目标区域为所述整体图中所述电芯主体的第一边缘线到所述整体图的第一边界线之间的区域，所述整体图的第一边界线为所述整体图的靠近所述极耳一端的边界线。
  6. 根据权利要求5所述的方法，其特征在于，所述根据第一目标区域的所述第一方向上的像素和的第一统计图，确定所述极耳的拐点的信息，包括：
    根据所述第一统计图中的凸起，确定所述极耳的拐点的信息。
  7. 根据权利要求5或6所述的方法，其特征在于，所述极耳的拐点包括沿所述第一边缘线的第一极耳的第一拐点和第二拐点，以及第二极耳的第一拐点和第二拐点；
    所述根据所述极耳的拐点的信息，确定所述电芯的缺陷情况，包括：
    根据所述第一统计图中，所述第一边缘线的第一区段、第二区段和第三区段对应的值，确定所述电芯是否具有隔离膜突出缺陷；
    其中，所述第一区段为所述电芯主体的第一角点至所述第一极耳的第一拐点间的区段，所述第二区段为所述第一极耳的第二拐点至所述第二极耳的第一拐点间的区段，所述第三区段为所述第二极耳的第二拐点和所述电芯主体的第二角点间的区段，所述第一角点为所述电芯主体的所述第一边缘线上的靠近所述第一极耳的角点，所述第二角点为所述电芯主体的所述第一边缘线上的靠近所述第二极耳的角点。
  8. 根据权利要求7所述的方法，其特征在于，所述根据所述第一统计图中，所述第一边缘线的第一区段、第二区段和第三区段对应的值，确定所述电芯是否具有隔离膜突出缺陷，包括：
    在所述第一区段、所述第二区段或所述第三区段对应的值大于或等于预设阈值的情况下，确定所述电芯具有隔离膜突出缺陷；或者，
    在所述第一区段、所述第二区段和所述第三区段对应的值均小于预设阈值的情况下，确定所述电芯无隔离膜突出缺陷。
  9. 根据权利要求2至8中任一项所述的方法，其特征在于，所述根据所述整体图，确定所述电芯的缺陷情况，包括：
    根据第二目标区域的第二方向上的像素和的第二统计图，确定所述电芯的缺陷情况，其中，所述第二方向垂直于所述电芯主体的第二边缘线的方向，所述第二目标区域为所述整体图中所述电芯主体的第二边缘线到所述整体图的第二边界线之间的区域，所述电芯主体的第二边缘线为所述电芯主体的远离所述极耳一端的边缘线，所述整体图的第二边界线为所述整体图的远离所述极耳一端的边界线。
  10. 根据权利要求9所述的方法，其特征在于，所述根据第二目标区域的第二方向上的像素和的第二统计图，确定所述电芯的缺陷情况，包括：
    根据所述第二统计图中，所述第二边缘线对应的值，确定所述电芯是否具有隔离膜突出缺陷。
  11. 根据权利要求10所述的方法，其特征在于，所述根据所述第二统计图中，所述第二边缘线对应的值，确定所述电芯是否具有隔离膜突出缺陷，包括：
    在所述第二边缘线对应的值大于或等于预设阈值的情况下，确定所述电芯具有隔离膜突出缺陷；或者，
    在所述第二边缘线对应的值小于预设阈值的情况下，确定所述电芯无隔离膜突出缺陷。
  12. 根据权利要求2至11中任一项所述的方法，其特征在于，所述方法还包括：
    确定所述电芯图像中电芯主体的第一方向上的宽度，其中，所述第一方向垂直于所述电芯主体的第一边缘线的方向，其中，所述电芯主体的第一边缘线为所述整体图中所述电芯主体的靠近所述极耳一端的边缘线；
    根据所述宽度确定所述电芯是否具有隔离膜错位缺陷。
  13. 根据权利要求12所述的方法，其特征在于，所述根据所述宽度确定所述电芯是否具有隔离膜错位缺陷，包括：
    在所述宽度超出预设范围的情况下，确定所述电芯具有隔离膜错位缺陷；或者，
    在所述宽度未超出预设范围内的情况下，确定所述电芯无隔离膜错位缺陷。
  14. 根据权利要求12或13所述的方法，其特征在于，所述确定所述电芯图像中电芯主体的第一方向上的宽度，包括：
    确定所述电芯主体的角点；
    根据所述电芯主体的角点，确定所述宽度。
  15. 一种检测电芯缺陷的装置，其特征在于，包括处理器和存储器，所述存储器用于存储程序，所述处理器用于从所述存储器中调用并运行所述程序以执行权利要求1至14中任一项所述的检测电芯缺陷的方法。
  16. 一种计算机可读存储介质，其特征在于，包括计算机程序，当所述计算机程序在计算机上运行时，使得所述计算机执行权利要求1至14中任一项所述的检测电芯缺陷的方法。
PCT/CN2023/085201 2022-09-16 2023-03-30 检测电芯缺陷的方法、装置和计算机可读存储介质 WO2024055569A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP23740926.3A EP4361950A1 (en) 2022-09-16 2023-03-30 Battery cell defect detection method and apparatus, and computer-readable storage medium
US18/225,222 US20240094137A1 (en) 2022-09-16 2023-07-24 Method and device for detecting defect of electrode assembly, and computer-readable storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211132007.XA CN115829921B (zh) 2022-09-16 2022-09-16 检测电芯缺陷的方法、装置和计算机可读存储介质
CN202211132007.X 2022-09-16

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/225,222 Continuation US20240094137A1 (en) 2022-09-16 2023-07-24 Method and device for detecting defect of electrode assembly, and computer-readable storage medium

Publications (1)

Publication Number Publication Date
WO2024055569A1 true WO2024055569A1 (zh) 2024-03-21

Family

ID=85523680

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/085201 WO2024055569A1 (zh) 2022-09-16 2023-03-30 检测电芯缺陷的方法、装置和计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN115829921B (zh)
WO (1) WO2024055569A1 (zh)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP4339887A4 (en) * 2022-07-21 2024-03-20 Contemporary Amperex Technology Co Ltd METHOD AND APPARATUS FOR INSPECTING THE APPEARANCE OF A TAB OF A SET OF BATTERY CELLS, AND ELECTRONIC DEVICE
CN115829921B (zh) * 2022-09-16 2024-01-05 宁德时代新能源科技股份有限公司 检测电芯缺陷的方法、装置和计算机可读存储介质
CN116703890B (zh) * 2023-07-28 2023-12-19 上海瑞浦青创新能源有限公司 极耳缺陷的检测方法和系统
CN117538335B (zh) * 2024-01-09 2024-05-31 宁德时代新能源科技股份有限公司 极耳缺陷检测方法和极耳缺陷检测设备

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110824371A (zh) * 2019-11-08 2020-02-21 广东利元亨智能装备股份有限公司 电池检测方法、装置、电子设备及可读存储介质
CN112557390A (zh) * 2019-09-10 2021-03-26 惠州旭鑫智能技术有限公司 一种动力电池裸电芯极耳错位缺陷单目视觉检测方法
US20210209739A1 (en) * 2018-08-27 2021-07-08 Beijing Baidu Netcom Science And Technology Co., Ltd. Battery detection method and device
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
CN114627092A (zh) * 2022-03-23 2022-06-14 广东利元亨智能装备股份有限公司 缺陷检测方法、装置、电子设备及可读存储介质
CN115829921A (zh) * 2022-09-16 2023-03-21 宁德时代新能源科技股份有限公司 检测电芯缺陷的方法、装置和计算机可读存储介质

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017172611A1 (en) * 2016-03-28 2017-10-05 General Dynamics Mission Systems, Inc. System and methods for automatic solar panel recognition and defect detection using infrared imaging
CN108037130B (zh) * 2017-12-01 2020-10-16 深圳市科陆电子科技股份有限公司 电芯的极耳缺陷自动检测方法及自动检测装置
CN112669295A (zh) * 2020-12-30 2021-04-16 上海电机学院 一种基于二次阈值分割理论的锂电池极片缺陷检测方法
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
CN114764804B (zh) * 2022-06-16 2022-09-20 深圳新视智科技术有限公司 锂电池极片缺陷检测方法、装置、设备及存储介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210209739A1 (en) * 2018-08-27 2021-07-08 Beijing Baidu Netcom Science And Technology Co., Ltd. Battery detection method and device
CN112557390A (zh) * 2019-09-10 2021-03-26 惠州旭鑫智能技术有限公司 一种动力电池裸电芯极耳错位缺陷单目视觉检测方法
CN110824371A (zh) * 2019-11-08 2020-02-21 广东利元亨智能装备股份有限公司 电池检测方法、装置、电子设备及可读存储介质
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
CN114627092A (zh) * 2022-03-23 2022-06-14 广东利元亨智能装备股份有限公司 缺陷检测方法、装置、电子设备及可读存储介质
CN115829921A (zh) * 2022-09-16 2023-03-21 宁德时代新能源科技股份有限公司 检测电芯缺陷的方法、装置和计算机可读存储介质

Also Published As

Publication number Publication date
CN115829921B (zh) 2024-01-05
CN115829921A (zh) 2023-03-21

Similar Documents

Publication Publication Date Title
WO2024055569A1 (zh) 检测电芯缺陷的方法、装置和计算机可读存储介质
US9741125B2 (en) Method and system of background-foreground segmentation for image processing
CN111819601A (zh) 为图像处理进行点云配准的方法和系统
US10915998B2 (en) Image processing method and device
EP3937129A1 (en) Image processing method and related apparatus
CN108564082B (zh) 图像处理方法、装置、服务器和介质
CN110544258A (zh) 图像分割的方法、装置、电子设备和存储介质
US10645364B2 (en) Dynamic calibration of multi-camera systems using multiple multi-view image frames
CN107833843B (zh) 缺陷来源的分析方法及分析系统、缺陷检测装置
CN112991459B (zh) 一种相机标定方法、装置、设备以及存储介质
WO2022082999A1 (zh) 一种物体识别方法、装置、终端设备及存储介质
CN109378279A (zh) 晶圆检测方法及晶圆检测系统
CN113409296B (zh) 一种卷绕电芯的抽芯检测方法、电子设备及存储介质
CN113673584A (zh) 一种图像检测方法及相关装置
WO2024016715A1 (zh) 检测系统的成像一致性的方法、装置和计算机存储介质
CN114549393A (zh) 图像标注方法、装置、设备及计算机存储介质
WO2024000420A1 (zh) 缺陷检测方法和装置
EP4361950A1 (en) Battery cell defect detection method and apparatus, and computer-readable storage medium
CN116668843A (zh) 一种拍摄状态的切换方法、装置、电子设备以及存储介质
CN116993654A (zh) 摄像头模组缺陷检测方法、装置、设备、存储介质及产品
US20220345621A1 (en) Scene lock mode for capturing camera images
US20240070840A1 (en) Defect detection method and apparatus, and computer-readable storage medium
CN116182807B (zh) 一种姿态信息确定方法、装置、电子设备、系统和介质
WO2024113368A1 (zh) 图像处理方法、装置和存储介质
CN116684569A (zh) 一种虚拟立体物体成像方法、装置、相机及存储介质

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2023740926

Country of ref document: EP

Effective date: 20230724