WO2024093644A1 - Battery cell detection system and battery cell detection method - Google Patents

Abstract

The present application relates to a battery cell detection system and a battery cell detection method. The system comprises an image acquisition module and a processor. The image acquisition module is used for acquiring a first battery cell image and a second battery cell image of a laminated battery cell undergoing hot pressing. The first battery cell image is used for positioning electrode sheets, and the second battery cell image is used for reconstructing the electrode sheets. The processor is used for recognizing the position of an anode sheet and the position of a cathode sheet according to the first battery cell image, obtaining a flatness parameter of the laminated battery cell according to the position of the anode sheet, the position of the cathode sheet and the second battery cell image, and according to the flatness parameter, confirming whether the laminated battery cell has a defect. By means of the system, Overhang value measurement between an anode sheet and a cathode sheet of a laminated battery cell and surface inclination degree measurement of the laminated battery cell can be implemented at the same time, thereby effectively improving the accuracy of defect detection of the laminated battery cell, and avoiding the phenomena of missing detection and overkill.

Description

Battery cell detection system and battery cell detection method

This application claims the priority of the Chinese patent application filed with the China Patent Office on November 3, 2022, with application number 202211372088.0 and invention name “Battery Cell Detection System and Battery Cell Detection Method”, the entire contents of which are incorporated by reference in this application.

Technical Field

The present application relates to the technical field of battery production, and in particular to a battery cell detection system and a battery cell detection method.

Background technique

The quality of battery electrodes is one of the important factors affecting battery performance. Therefore, in the battery production process, it is necessary to carry out quality inspection of the electrodes during the stacking process.

However, in the traditional technology, the method for detecting the quality of the pole piece during the lamination process is to obtain the coordinates of the pole piece by an indirect method and solve the Overhang value. This results in a low error tolerance rate and low accuracy of the detection results in the traditional technology.

Application Contents

In view of the above problems, the present application provides a battery cell detection system and a battery cell detection method, which can solve the problem of low accuracy in detecting the overhang value of stacked battery cells using an indirect method in traditional technology, and prone to missed detection and false positives.

Technical Solutions

The technical solution adopted in the embodiment of the present application is:

In the first aspect, the present application provides a battery cell detection system, which includes: an image acquisition module and a processor. The image acquisition module is used to obtain a first battery cell image and a second battery cell image of a stacked battery cell; the first battery cell image is used to locate the electrode sheet, and the second battery cell image is used to reconstruct the electrode sheet; the processor is used to identify the anode sheet position and the cathode sheet position according to the first battery cell image, and obtain the flatness parameters of the stacked battery cell according to the anode sheet position, the cathode sheet position and the second battery cell image, and confirm whether the stacked battery cell has defects according to the flatness parameters.

In some embodiments, the image acquisition module acquires a first cell image and a second cell image of each surface of the laminated cell along a direction toward each surface of the laminated cell.

In some embodiments, the image acquisition modules include two, and the two image acquisition modules are respectively located on both sides of the stacked battery cell; the processor is also used to synchronously identify the anode sheet position and the cathode sheet position of each surface of the stacked battery cell based on the first battery cell image of each surface of the stacked battery cell respectively acquired by the two image acquisition modules.

In some embodiments, the system also includes a detection module, which is used to generate a cell position signal and send it to a processor when it detects that the stacked battery cell is located at a preset detection position; the processor is used to generate an image acquisition instruction based on the identification code of the stacked battery cell when receiving the cell position signal and send it to the image acquisition module; the image acquisition module is used to capture a first cell image and a second cell image of the stacked battery cell after hot pressing when receiving the image acquisition instruction.

In some embodiments, each surface of the battery cell includes a plurality of anode sheets and cathode sheets alternately arranged side by side, and the flatness parameter includes the height difference between adjacent anode sheets and cathode sheets; the processor is used to obtain each anode sheet position and each cathode sheet position of the stacked battery cell according to the first battery cell image, and obtain each anode sheet contour image and each cathode sheet contour image of the stacked battery cell according to each anode sheet position, each cathode sheet position and the second battery cell image, obtain the height difference between adjacent anode sheets and cathode sheets according to each anode sheet position, each cathode sheet position, each anode sheet contour image and each cathode sheet contour image, and confirm whether the stacked battery cell has defects based on the height difference.

In some embodiments, the processor is further configured to segment the first cell image into anode slices and/or cathode slices. Get the anode piece position and the cathode piece position.

In some embodiments, the flatness parameters also include the inclination of each surface of the laminated battery cell; the processor is also used to obtain the inclination based on the position of each anode sheet in each surface of the laminated battery cell and the contour image of each anode sheet, and confirm whether the laminated battery cell has defects based on the inclination; and/or, the processor is also used to obtain the inclination based on the position of each cathode sheet in each surface of the laminated battery cell and the contour image of each cathode sheet, and confirm whether the laminated battery cell has defects based on the inclination.

In some embodiments, the system further includes a waste discharge module, and the processor is used to generate a waste discharge instruction and send it to the waste discharge module when there are defects in the laminated battery cells; the waste discharge module is used to remove the laminated battery cells based on the waste discharge instruction.

In some embodiments, the system further includes a gluing module, and the processor is used to generate a gluing instruction and send it to the gluing module when there are no defects in the laminated battery cells; the gluing module is used to glue the laminated battery cells based on the gluing instruction.

In the second aspect, the present application also provides a battery cell detection method, which includes: obtaining a first battery cell image and a second battery cell image of a stacked battery cell, wherein the first battery cell image and the second battery cell image are collected from the same surface of the stacked battery cell; identifying the first battery cell image to obtain the anode sheet position and the cathode sheet position of the stacked battery cell; obtaining the flatness parameters of the stacked battery cell based on the anode sheet position, the cathode sheet position and the second battery cell image; and confirming whether the stacked battery cell has defects based on the flatness parameters.

In some embodiments, the above-mentioned identification of the first battery cell image to obtain the anode sheet position and the cathode sheet position of the stacked battery cell includes: obtaining the anode sheet position and the cathode sheet position according to the grayscale value difference between the anode sheet and the cathode sheet in the first battery cell image.

In some embodiments, the above-mentioned identifying the first battery cell image to obtain the anode sheet position and the cathode sheet position of the stacked battery cell includes: segmenting the first battery cell image to obtain the anode sheet position and the cathode sheet position.

In some embodiments, each surface of the battery cell includes a plurality of anode sheets and cathode sheets alternately arranged side by side, and the above-mentioned segmentation processing of the first battery cell image to obtain the anode sheet position and the cathode sheet position includes: segmenting the anode sheet in the first battery cell image to obtain the anode sheet position; obtaining the cathode sheet position based on the two spaced anode sheet positions; or segmenting the cathode sheet in the first battery cell image to obtain the cathode sheet position; obtaining the anode sheet position based on the two spaced cathode sheet positions; or segmenting the anode sheet and the cathode sheet in the first battery cell image to obtain the anode sheet position and the cathode sheet position.

In some embodiments, each surface of the battery cell includes a plurality of anode sheets and cathode sheets alternately arranged side by side, and the flatness parameter includes the height difference between adjacent anode sheets and cathode sheets; the above-mentioned flatness parameters of the stacked battery cell are obtained according to the anode sheet position, the cathode sheet position and the second battery cell image, including: obtaining the anode sheet reconstructed image and the cathode sheet reconstructed image of the stacked battery cell according to the second battery cell image; obtaining the anode sheet contour image and the cathode sheet contour image according to the anode sheet position, the cathode sheet position, the anode sheet reconstructed image and the cathode sheet reconstructed image; obtaining the height difference between adjacent anode sheets and cathode sheets according to the anode sheet position, the cathode sheet position, the anode sheet contour image and the cathode sheet contour image.

In some embodiments, the height difference between adjacent anode sheets and cathode sheets is obtained according to the anode sheet position, the cathode sheet position, the anode sheet contour map and the cathode sheet contour image, including: obtaining a pole sheet waveform diagram of the stacked battery cell according to the anode sheet position, the cathode sheet position, the anode sheet contour map and the cathode sheet contour image; wherein each peak in the pole sheet waveform diagram is used to characterize the height of the anode sheet or the height of the cathode sheet; and obtaining the height difference according to the absolute value of the height difference between adjacent anode sheet peaks and cathode sheet peaks in the pole sheet peak diagram.

In some embodiments, whether the laminated battery cell has defects is confirmed based on the flatness parameter, including: when the height difference is less than or equal to a preset threshold, confirming that the laminated battery cell has no defects; or, when the height difference is greater than a preset threshold, confirming that the laminated battery cell has defects.

In some embodiments, the flatness parameter also includes the inclination of each surface of the laminated core, the horizontal axis of the electrode waveform diagram Characterize the surface of the stacked battery cell; the above-mentioned flatness parameters of the stacked battery cell are obtained according to the anode sheet position, the cathode sheet position and the second battery cell image, and also include: obtaining the anode sheet peak line according to the line connecting the peaks corresponding to each anode sheet in the pole sheet waveform diagram; obtaining the inclination according to the anode sheet peak line and the horizontal axis of the pole sheet waveform diagram; and/or, obtaining the cathode sheet peak line according to the line connecting the peaks corresponding to each cathode sheet in the pole sheet waveform diagram; obtaining the inclination according to the cathode sheet peak line and the horizontal axis of the pole sheet waveform diagram.

In some embodiments, the above-mentioned confirming whether the laminated battery cell has defects based on the flatness parameter also includes: confirming that the laminated battery cell does not have defects when the inclination is less than or equal to a preset threshold value; or confirming that the laminated battery cell has defects when the inclination is greater than a preset threshold value.

In some embodiments, the above method also includes: obtaining an identification code of the stacked battery cell; confirming the posture parameters of the image acquisition module used to acquire the first battery cell image and the second battery cell image of the stacked battery cell according to the identification code of the stacked battery cell, and confirming the defect detection algorithm corresponding to the stacked battery cell in a preset defect detection algorithm library; wherein the defect detection algorithm is used to detect whether the stacked battery cell has defects.

Beneficial Effects

The first aspect of the beneficial effect provided by the embodiment of the present application is that the battery cell detection system uses a direct method to detect the Overhang value of the anode sheet and the cathode sheet, which effectively improves the accuracy of defect detection of stacked battery cells and avoids missed detection and false positives.

It can be understood that the beneficial effects of the second aspect of the present application can be found in the relevant description of the first aspect of the present application and will not be repeated here.

BRIEF DESCRIPTION OF THE DRAWINGS

Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Moreover, the same reference numerals are used throughout the drawings to represent the same components. In the drawings:

FIG1 is a schematic diagram of the structure of a battery cell detection system in one embodiment of the present application;

FIG2 is a schematic diagram of the structure of a laminated battery cell in one embodiment of the present application;

FIG3a is a schematic diagram of a detection result of a laminated battery cell in one embodiment of the present application;

FIG3 b is a schematic diagram of the detection results of a laminated battery cell in one embodiment of the present application;

FIG4 is a schematic diagram of a flow chart of a battery cell detection method in one embodiment of the present application;

FIG5a is a schematic diagram of a process for identifying the position of an anode sheet and a cathode sheet in one embodiment of the present application;

FIG5 b is a schematic diagram of a process for identifying the position of an anode sheet and a cathode sheet in one embodiment of the present application;

FIG5c is a schematic diagram of a process for identifying the position of an anode sheet and a cathode sheet in one embodiment of the present application;

FIG6 is a schematic diagram of a process for calculating the height difference between adjacent anode sheets and cathode sheets in one embodiment of the present application;

FIG7 is a schematic diagram of a process for calculating the height difference between adjacent anode sheets and cathode sheets in one embodiment of the present application;

FIG8a is a schematic diagram of a process for calculating the inclination of each surface of a laminated battery cell in one embodiment of the present application;

FIG8b is a schematic diagram of a process for calculating the inclination of each surface of a laminated battery cell in one embodiment of the present application;

FIG. 9 is a schematic diagram of a flow chart of a defect detection algorithm confirmed in one embodiment of the present application.

Detailed ways

The following embodiments of the technical solution of the present application will be described in detail in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application, and are therefore only used as examples, and cannot be used to limit the scope of protection of the present application.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to be construed as meaning the same as those commonly understood by those skilled in the art to which this application belongs. It is intended to limit the present application; the term "comprises" and any variation thereof in the specification and claims of the present application and the above-mentioned figure descriptions are intended to cover non-exclusive inclusions.

In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

Lithium-ion batteries (or simply lithium batteries) have been widely used in a variety of electrical products due to their advantages such as high energy density, long cycle life, and no memory effect. For example, electrical products may be, but are not limited to, mobile phones, tablets, laptops, electric toys, electric tools, battery cars, electric cars, ships, spacecraft, etc.

The production process of lithium-ion batteries includes winding process and stacking process. Among them, the stacked battery manufactured by the stacking process has the characteristics of high discharge rate, low internal resistance, high capacity density and high energy density compared with the wound battery manufactured by the winding process, making the stacked battery gradually become the mainstream power battery.

In the lamination process, it is necessary to detect the Overhang value of the laminated battery cells manufactured by the lamination process. Overhang refers to the part of the negative electrode sheet that is beyond the positive and negative electrode sheets in the length and width direction. During the lamination process of the laminated battery cells, if the electrode sheet is not folded along the crease of the anode sheet, the Overhang value of the non-composite surface will usually exceed the preset threshold value; in addition, during the lamination process of the laminated battery cells, the laminated battery cells will swing, which usually causes the position of the laminate to be easily displaced, and usually causes the Overhang value of the non-composite surface to exceed the preset threshold value.

Normally, each cathode sheet of a laminated battery cell is disconnected, which makes it difficult to control and detect the Overhang value of the laminated battery cell. In addition, it is even more difficult to detect the Overhang value between the cathode sheet and the anode sheet on top of it after lamination. During the lamination process, if the anode sheet is not laminated along the crease or the electrode sheet is wrinkled during the lamination process, the defect of the Overhang value of the non-composite surface of the laminated battery cell exceeding the specification will be caused.

In traditional technology, the detection method for stacked cells is: during the stacking process, four cameras are used to take images of the four vertex corners of the pole piece, and two cameras on one side of the pole piece (i.e., located on the same long side) are triggered simultaneously to obtain the cathode coordinates (X11, Y11) and (X12, Y12) of each pole corner corresponding to the two cameras, and the coordinates (X13, Y13) and (X14, Y14) of the two vertex corners on the other side of the cathode piece are calculated in combination with the pole piece width, and then the coordinates (X21, Y21), (X22, Y22), (X23, Y23) and (X24, Y24) of the four vertex corners of the anode piece are calculated in combination with the Overhang value of the non-composite surface of the stacked cell. The vertex coordinates of the anode piece and the cathode piece are calculated by difference calculation, and the absolute value of the difference is the desired Overhang value.

It can be seen that the vertex coordinates of the anode sheet are not directly measured, but are calculated based on the cathode sheet coordinates and the overhang value of the non-composite surface. Therefore, the above measurement method is an indirect measurement method. This leads to a low error tolerance rate of the detection result, which is prone to missed detection and false positives.

Based on the above considerations, the applicant proposed a battery cell detection system and a battery cell detection method, which ensures the accuracy of the stacked battery cell detection results by directly measuring the height of the anode and cathode sheets of the stacked battery cells and measuring the inclination of each surface of the stacked battery cells, thereby avoiding missed detections and false positives.

To facilitate understanding, some words are introduced in the embodiments of the present application.

The batteries involved in the embodiments of the present application can be divided into, but not limited to, button batteries, laminated batteries, soft-pack batteries, hard-shell batteries, cylindrical batteries, etc. according to the battery shape.

The batteries involved in the embodiments of the present application can be classified according to battery materials, including but not limited to: ternary batteries, lithium iron phosphate batteries, silicon system batteries, carbon silicon system batteries, lithium sulfur batteries, etc.

The cathode (or positive electrode) of the battery involved in the embodiment of the present application will be oxidized during the charging process, and lithium ions can escape from the layered intercalation material of the cathode, pass through the electrolyte, and be intercalated into the anode. Correspondingly, the anode (or negative electrode) of the battery involved in the embodiment of the present application will undergo an oxidation reaction during the discharge process, and lithium ions can escape from the anode, pass through the electrolyte, and be re-intercalated into the cathode.

In one embodiment, FIG1 is a schematic diagram of the structure of a battery cell detection system in one embodiment of the present application. As shown in FIG1 , it includes an image acquisition module 20 and a processor 40 .

Specifically, the image acquisition module 20 is in communication connection with the processor 40. The image acquisition module 20 is used to obtain the first cell image and the second cell image of the laminated cell 10 after hot pressing; the processor 40 is used to identify the anode sheet position and the cathode sheet position according to the first cell image, and obtain the flatness parameter of the laminated cell according to the anode sheet position, the cathode sheet position and the second cell image, and confirm whether the laminated cell 10 has defects according to the flatness parameter.

The image acquisition module 20 can be set according to the requirements of the first battery cell image and the second battery cell image, wherein the first battery cell image is used to locate the electrode sheet, and the second battery cell image is used to reconstruct the electrode sheet. For example, the image acquisition module 20 can be a binocular camera, in which one monocular lens is used to acquire RGB images or grayscale images (i.e., the first battery cell image), and the other monocular lens is used to acquire infrared images, depth of field images, or point cloud images (i.e., the second battery cell image); for another example, the image acquisition module 20 can be a line laser 3D camera, which simultaneously acquires grayscale images and point cloud images; for another example, the image acquisition module 20 can be a combination of a monocular camera and a laser radar, wherein the monocular camera acquires RGB images or grayscale images, and the laser radar acquires point cloud images. The image acquisition module 20 can be selected according to actual conditions, and the present application does not limit the specific type and model of the image acquisition module 20.

The processor 40 can be a host computer, an industrial computer or a workstation, etc., as long as it can realize the control of the image acquisition module 20 and the defect detection of the laminated battery core 10.

The battery cell detection system uses a direct method to detect the overhang value of the anode and cathode sheets, effectively improving the accuracy of defect detection of stacked battery cells and avoiding missed detection and false positives.

In one embodiment, as shown in FIG1 , the image acquisition module acquires a first cell image and a second cell image of each surface of the laminated cell 10 along a direction toward each surface of the laminated cell 10. Here, the direction toward the laminated cell 10 can be set according to the actual needs of the production line, for example, perpendicular to the direction of each surface of the laminated cell 10, or at a certain angle to each surface of the laminated cell 10.

Through the first cell image and the second cell image of each surface of the positively facing laminated cell, the subsequent positioning and reconstruction of the anode and cathode sheets are guaranteed to be accurate, ensuring the accuracy of the detection of the flatness parameters of the laminated cell.

In one embodiment, as shown in Fig. 1, the laminated battery core 10 includes a first surface 11 and a second surface 12. The image acquisition module 20 includes two, namely a first image acquisition module 21 and a second image acquisition module 22.

Specifically, the first image acquisition module 21 and the second image acquisition module 22 are respectively located on both sides of the laminated battery cell 10, wherein the first image acquisition module 21 is used to acquire the first battery cell image and the second battery cell image of the first surface 11 of the laminated battery cell 10; the second image acquisition module 22 is used to acquire the first battery cell image and the second battery cell image of the second surface 12 of the laminated battery cell 10.

In one embodiment, as shown in Figures 1 and 2, the processor 40 is also used to synchronously identify the position of the anode sheet 13 and the cathode sheet 14 on each surface of the stacked battery cell 10 based on the first battery cell images of each surface of the stacked battery cell 10 respectively captured by the two image acquisition modules 20.

Specifically, the first image acquisition module 21 acquires a first cell image of the first surface 11 of the laminated cell 10 and a second cell image of the first surface 11 of the laminated cell 10. The second image acquisition module 22 acquires the first cell image and the second cell image of the second surface 12 of the laminated cell 10. The processor 40 synchronously receives the above cell images, and recognizes the first cell image of the first surface 11 and the first cell image of the second surface 12, and synchronously recognizes the anode sheet position and the cathode sheet position of each surface of the laminated cell 10.

Similarly, the processor 40 is also used to synchronously analyze the second battery cell image of the first surface 11 and the second battery cell image of the second surface 12, so as to simultaneously detect the flatness parameters of the first surface 11 and the flatness parameters of the second surface 12. In this way, the detection speed of the battery cell detection system can be improved, the production line beat can be ensured, and the production efficiency can be improved.

In one embodiment, please continue to refer to FIG. 1 , the battery cell detection system further includes a detection module 30. The detection module 30 is in communication connection with the processor 40, the first image acquisition module 21 and the second image acquisition module 22 are respectively located on both sides of the detection module 30, and the laminated battery cell 10 is located in the detection module 30.

Specifically, the detection module 30 is used to generate a cell position signal and send it to the processor 40 when it is detected that the laminated battery cell 10 is located at a preset detection position. The processor 40 is used to generate an image acquisition instruction based on the identification code of the laminated battery cell 10 and send it to the image acquisition module 20, that is, to the first image acquisition module 21 and the second image acquisition module 22 when receiving the cell position signal. The identification code of the laminated battery cell 10 can be a product serial number (Serial Number, SN code). The image acquisition module 20 is used to collect the first cell image and the second cell image of the laminated battery cell after hot pressing when receiving the image acquisition instruction, that is, the first image acquisition module 21 and the second image acquisition module 22 synchronously perform image acquisition.

The image acquisition instruction generated by the product serial number of the laminated battery cell 10 can ensure that the image acquisition module 20 is in the best position for the acquisition posture (such as shooting height) of the laminated battery cell 10 of the battery model.

In one embodiment of the present application, the identification code includes the model information of the laminated battery cell 10. The image acquisition instruction includes the position parameters of the image acquisition module, and the image acquisition module 20 is used to obtain the position and posture of the laminated battery cell 10 when performing image acquisition according to the position parameters.

When capturing images of different types of battery cells, the shooting distance between each image capture module 20 and its surface may be different. The battery cell detection system automatically adjusts the shooting distance between the image capture module 20 and the corresponding battery cell surface according to the battery model information. Specifically, the battery detection system is preset with a preset posture library established for each battery model, and the posture data of the image capture module 20 when capturing images of the stacked battery cells 10 is confirmed according to the different battery models of the processor 40. Among them, the posture data includes the height of the battery cell image captured by the image capture module 20, the shooting angle of the battery cell image by the image capture module 20, and the moving speed of the image capture module. By automatically confirming the image capture posture through the identification code of the stacked battery cell 10, the system's adaptability to the detection of different types of batteries can be improved, thereby enhancing the versatility of the battery cell detection system.

In one embodiment of the present application, the processor 40 is also used to confirm the defect detection algorithm corresponding to the laminated battery cell according to the identification code of the laminated battery cell 10. It is understandable that different types of battery cells may use different defect detection algorithms when performing image-based defect detection. The battery cell detection system automatically confirms the corresponding defect detection algorithm based on the battery model information, which can improve the system's adaptability to the detection of different types of battery cells and further enhance the versatility of the battery cell detection system.

As shown in FIG. 2 , FIG. 2 is a schematic diagram of the structure of the surface of the laminated battery cell 10 in one embodiment of the present application. Each surface of the laminated battery cell 10 includes a plurality of anode sheets 13 and cathode sheets 14 arranged alternately side by side. In one embodiment of the present application, please continue to refer to FIG. 1 , the flatness parameter includes the height difference between adjacent anode sheets 13 and cathode sheets 14.

Specifically, the processor 40 is used to obtain each anode sheet position and each cathode sheet position of the laminated battery cell according to the first battery cell image, and obtain each anode sheet position, each cathode sheet position and the second battery cell image according to each anode sheet position, each cathode sheet position and the second battery cell image. The height difference between the adjacent anode sheets 13 and cathode sheets 14 is obtained according to each anode sheet position, each cathode sheet position, each anode sheet contour image and each cathode sheet contour image. As shown in FIG3a, it is confirmed whether the laminated battery cell 10 has defects according to the height difference 16. Wherein, if the height difference is less than or equal to the preset threshold value, it indicates that the surface flatness of the laminated battery cell 10 meets the requirements, and it is confirmed that the laminated battery cell 10 does not have defects; if the height difference is greater than the preset threshold value, it indicates that the surface flatness of the laminated battery cell 10 does not meet the requirements, and it is confirmed that the laminated battery cell 10 has defects.

When the positions of the anode sheet 13 and the cathode sheet 14 in the laminated battery cell 10 are identified, the processor 40 is also used to segment the anode sheet and/or the cathode sheet of the first battery cell image to obtain the anode sheet position and the cathode sheet position. It can be seen that the first scheme is to segment the anode sheet 13 in each surface of the laminated battery cell 10, identify all the anode sheet 13 areas on each surface, and then draw the ROI (i.e., region of interest) area between two adjacent anode sheet 13 areas, that is, the position of the cathode sheet 14 is obtained, thereby realizing the identification of the anode sheet position and the cathode sheet position. The second scheme is to segment the cathode sheet 14 in each surface of the laminated battery cell 10, identify all the cathode sheet 14 areas on each surface, and then draw the ROI (i.e., region of interest) area between two adjacent cathode sheet 14 areas, that is, the position of the anode sheet 13 is obtained, thereby realizing the identification of the anode sheet position and the cathode sheet position. The third scheme is to segment the anode sheet 13 and the cathode sheet 14 in each surface of the laminated battery cell 10 at the same time to identify the anode sheet position and the cathode sheet position.

Through the above three schemes, reasonable anode and cathode positioning methods are adapted for different types of laminated battery cells 10. In addition, the specific use of the above three positioning schemes can be reasonably determined according to the production line's requirements for detection speed and the like.

In one embodiment of the present application, as shown in FIG. 3 b , the flatness parameter also includes an inclination 18 of each surface of the laminated battery core 10 .

Specifically, the schemes for obtaining the inclination include the following: In the first scheme, the processor 40 is used to obtain the inclination of the laminated battery core 10 according to the position of each anode sheet in each surface of the laminated battery core 10 and the contour image of each anode sheet. In the second scheme, the processor 40 is used to obtain the inclination of the laminated battery core 10 according to the position of each cathode sheet in each surface of the laminated battery core 10 and the contour image of each cathode sheet. In the above two schemes, the processor 40 is also used to confirm whether the laminated battery core 10 has defects according to the inclination. In the third scheme, the processor 40 simultaneously obtains the inclination corresponding to the anode sheet 13 and the inclination corresponding to the cathode sheet 14 according to the methods of schemes one and two, respectively, and confirms whether the laminated battery core 10 has defects according to the inclination corresponding to the anode sheet 13 and the inclination corresponding to the cathode sheet 14. Among them, when the inclination is less than or equal to the preset threshold, it means that the surface flatness of the laminated battery core 10 meets the requirements, and it is confirmed that the laminated battery core 10 does not have defects; when the inclination is greater than the preset threshold, it means that the surface flatness of the laminated battery core 10 does not meet the requirements, and it is confirmed that the laminated battery core 10 has defects.

The battery cell detection system can detect the height difference between the anode sheet 13 and the cathode sheet 14 on each surface of the laminated battery cell 10, and can also detect the inclination of each surface of the laminated battery cell 10. The height difference between the adjacent anode sheets 13 and cathode sheets 14 on each surface of the laminated battery cell 10 indicates whether the electrode sheets are stacked along the creases during the folding process or whether the electrode sheets are wrinkled during the lamination process, and the inclination of each surface of the laminated battery cell 10 indicates that the laminated battery cell 10 is tilted and does not meet the requirements for shell insertion; the battery cell detection system can detect multiple defects of the laminated battery cell 10 at the same time to avoid missing defective laminated battery cells 10.

In one embodiment of the present application, please continue to refer to FIG. 1 , the battery cell detection system further includes a waste discharge module 50 , which matches the detection module 30 and is communicatively connected to the processor 40 .

Specifically, the processor 40 is used to generate a waste discharge instruction and send it to the waste discharge module 50 when there are defects in the laminated battery cell 10; the waste discharge module 50 is used to remove the defective laminated battery cell 10 for waste discharge based on the waste discharge instruction.

By discharging the defective laminated battery core 10, the defective laminated battery core 10 is prevented from entering the The shell causes safety risks in the use of finished batteries.

In one embodiment of the present application, please continue to refer to FIG. 1 , the battery cell detection system further includes a gluing module 60 , which is a downstream production line of the detection module 30 and is communicatively connected to the processor 40 .

Specifically, the processor 40 is used to generate a glue sticking instruction and send it to the glue sticking module 60 when there is no defect in the laminated battery core 10; the glue sticking module 60 is used to glue the laminated battery core 10 based on the glue sticking instruction.

Through the automatic control of the detection module 30 and the gluing module 60 of the production line by the processor 40, the stacked battery cells 10 detected to be free of defects are automatically fed from the detection module 30 to the gluing module 60, thereby realizing a high degree of automation and intelligence in the detection of the stacked battery cells 10 during the hot pressing and gluing processes, and reducing the impact of adding a detection process between the hot pressing process and the gluing process on production efficiency.

In one embodiment, FIG4 is a schematic diagram of a flow chart of a battery cell detection method in one embodiment of the present application, and the battery cell detection method can be applied to the above-mentioned battery cell detection system. As shown in FIG4 , the steps include:

Step 410: Acquire a first cell image and a second cell image of the laminated cell after hot pressing, wherein the first cell image and the second cell image are acquired from the same surface of the laminated cell.

It can be known that, through the two oppositely arranged image acquisition modules 20 of the battery cell detection system, the first battery cell image and the second battery cell image of each surface of the laminated battery cell 10 can be obtained simultaneously.

Step 420: Identify the first battery cell image to obtain the position of the anode sheet and the position of the cathode sheet of the stacked battery cell.

Step 430: Obtain the flatness parameters of the stacked battery cell according to the anode sheet position, the cathode sheet position and the second battery cell image.

Step 440: Determine whether the laminated battery cell has defects based on the flatness parameters.

Through the above implementation, the Overhang values of the anode and cathode sheets on each surface of the laminated battery cell 10 can be detected in real time, and it can be confirmed in time whether the electrode sheets of the laminated battery cell 10 are laminated along the creases during the folding process or whether the electrode sheets are wrinkled during the lamination process. Defective laminated battery cells 10 are discarded based on the detection results to avoid the laminated battery cells 10 whose Overhang values do not meet the design requirements and do not meet the process safety from being put into the shell, resulting in defects in the entire produced battery.

In one embodiment, step 420: identifying the first battery cell image to obtain the anode sheet position and the cathode sheet position includes:

The anode piece position and the cathode piece position are obtained according to the gray value difference between the anode piece and the cathode piece in the first battery cell image.

It can be seen that, due to the different colors of the anode and cathode sheets, when the first cell image is a grayscale image, the anode and cathode sheets present different display effects in the first cell image. Therefore, all anode sheets 13 and cathode sheets 14 on each surface of the laminated cell 10 can be identified by image recognition.

In one embodiment, obtaining the anode sheet position and the cathode sheet position according to the gray value difference between the anode sheet and the cathode sheet in the first battery cell image includes:

The first battery cell image is segmented to obtain the anode sheet position and the cathode sheet position.

It can be seen that the segmentation algorithm used in the segmentation process segments the RGB image or grayscale image of the first battery cell image; and the segmentation algorithm is not limited to a segmentation operator trained using machine learning, nor is it limited to an instance segmentation or semantic segmentation model trained using deep learning. The embodiments of the present application are not intended to limit the specific segmentation method, as long as it can achieve the segmentation of the anode and/or cathode in the first battery cell image to obtain a recognition result.

Figures 5a, 5b and 5c are schematic diagrams of a process for identifying anode sheets and cathode sheets in a first cell image in one embodiment of the present application. As shown in Figure 2, each surface of the cell 10 includes a plurality of anode sheets 13 and cathode sheets 14 arranged alternately side by side. Therefore, the step of segmenting the first cell image to obtain the anode sheet position and the cathode sheet position may include the following three schemes.

As shown in Figure 5a, the first solution is:

Step 510: Segment the anode sheets in the first battery cell image to obtain the anode sheet positions.

Step 520: Obtain the cathode sheet position according to the two spaced anode sheet positions.

As shown in Figure 5b, the second solution is:

Step 530: Segment the cathode slice in the first battery cell image to obtain the cathode slice position.

Step 540: Obtain the anode piece position according to the two spaced cathode piece positions.

Based on the above, after all cathode sheets and anode sheets in each surface are detected according to the first battery cell image, the first scheme of FIG5a draws an ROI area between each two adjacent anode sheets, and the ROI area is the cathode sheet; the second scheme of FIG5b draws an ROI area between each two adjacent cathode sheets, and the ROI area is the anode sheet. This method can effectively reduce the computing consumption and improve the detection speed of the system.

As shown in Figure 5c, the third solution is:

Step 550: Segment the anode piece and the cathode piece in the first battery cell image to obtain the anode piece position and the cathode piece position.

As shown in the third scheme of FIG. 5 c , the anode sheet 13 and the cathode sheet 14 are segmented at the same time. Compared with the first scheme of FIG. 5 a and the second scheme of FIG. 5 b , the computing power requirement for the simultaneous identification of the two types of electrodes is increased, but the post-processing operation of ROI drawing is reduced.

The embodiments of the present application are not intended to limit the specific method of dividing the anode sheet 13 and the cathode sheet 14 , as long as the positioning of the anode sheet 13 and the cathode sheet 14 is achieved through any of the above solutions.

Take the flatness parameter including the height difference between the adjacent anode sheet 13 and cathode sheet 14 on the surface of the laminated battery cell 10 as an example:

FIG6 is a schematic diagram of a process for obtaining the flatness parameters of a laminated battery cell in one embodiment of the present application. As shown in FIG6 , step 430: obtaining the flatness parameters of the laminated battery cell according to the anode sheet position, the cathode sheet position and the second battery cell image, including:

Step 610: Obtain an anode sheet reconstructed image and a cathode sheet reconstructed image of the stacked battery cell according to the second battery cell image.

The anode sheet reconstructed image and the cathode sheet image may be point cloud images, which may be acquired through a 3D laser beam camera or through laser radar scanning.

Step 620: Obtain an anode film contour image and a cathode film contour image according to the anode film position, the cathode film position, the anode film reconstructed image and the cathode film reconstructed image.

It can be seen that by locating each anode sheet position and each cathode sheet position of the stacked battery cell 10, assigning each anode sheet position identifier and cathode sheet position identifier, and passing the above identifiers to the anode sheet reconstructed image and the cathode sheet reconstructed image, the height difference detection results of the anode sheet and the cathode sheet at the specific position can be obtained.

Step 630: Obtain the height difference between adjacent anode sheets and cathode sheets according to the anode sheet position, the cathode sheet position, the anode sheet contour map and the cathode sheet contour image.

By calculating the height difference between every two adjacent anode sheets and cathode sheets of the laminated battery core 10, all anode sheets and cathode sheets on the surface of the laminated battery core 10 are detected, thereby realizing the detection of the Overhang value of the laminated battery core.

FIG7 is a schematic diagram of a process for obtaining the height difference between adjacent anode sheets and cathode sheets in one embodiment of the present application. As shown in FIG7 , step 630: obtaining the height difference between adjacent anode sheets and cathode sheets according to the anode sheet position, cathode sheet position, anode sheet contour image and cathode sheet contour image, including:

Step 710: Obtain a pole waveform diagram of the laminated battery cell according to the anode position, cathode position, anode contour diagram and cathode contour image; wherein each peak in the pole waveform diagram is used to characterize the height of the anode or the cathode.

It should be noted that the horizontal axis of the electrode waveform diagram represents the cross-sectional center line (or any parallel line of the center line) of the laminated battery cell 10 along the staggered arrangement direction of the anode and cathode sheets (i.e., the direction from left to right in FIG. 2 ). The vertical axis represents the height of the anode sheet and the cathode sheet of the laminated battery cell 10 .

It can be seen that when the anode sheet contour image and the cathode sheet contour image are mapped to the electrode sheet waveform diagram along the staggered arrangement direction of the anode sheets and cathode sheets of the laminated battery cell 10, each waveform of the electrode sheet waveform diagram inherits the above-mentioned anode sheet identification and cathode sheet identification.

Step 720: Obtain the height difference according to the absolute value of the height difference between the adjacent anode plate peaks and cathode plate peaks in the pole plate peak diagram.

It can be seen that the height of the anode sheet 13 of the laminated battery cell 10 may be higher than that of the cathode sheet 14, or lower than that of the cathode sheet 14. As long as the absolute value of the height difference does not meet the preset threshold, there is a defect.

Wherein, step 440: confirming whether the laminated cell has defects according to the flatness parameter includes the following two results:

The first result is: when the height difference is less than or equal to a preset threshold, it is confirmed that there are no defects in the laminated battery cell.

The second result is: when the height difference is greater than a preset threshold, it is confirmed that the laminated battery cell is defective.

Among them, the preset thresholds of the height difference of different types of laminated battery cells 10 may be different. The height difference threshold of each laminated battery cell 10 is a known parameter according to its quality requirements, that is, the preset threshold of the height difference. When confirming whether the laminated battery cell 10 has defects, it is only necessary to compare the height difference of adjacent anode sheets and cathode sheets obtained by measurement with the preset threshold.

Take the flatness parameter including the inclination of each surface of the laminated battery cell 10 as an example:

Figures 8a and 8b are schematic diagrams of a process for obtaining the inclination of each surface of a laminated battery cell in one embodiment of the present application. As shown in Figures 3a, 8a and 8b, step 430: according to the anode sheet position, the cathode sheet position and the second battery cell image, the step of obtaining the flatness parameter of the laminated battery cell may also include the following three schemes.

As shown in Figure 8a, the first solution is:

Step 810: Obtain the anode plate peak line according to the connecting line of the peak corresponding to each anode plate in the electrode plate waveform diagram.

Step 820: Obtain the inclination according to the anode plate peak line and the horizontal axis of the pole plate waveform diagram.

As shown in FIG3a , the anode sheet crest line 17 is a line connecting the crests corresponding to each anode sheet. By calculating the angle between the anode sheet crest line 17 and the horizontal axis, the inclination of the laminated battery cell 10 along the direction in which the anode sheets 13 and the cathode sheets 14 are staggered can be obtained.

As shown in Figure 8b, the second solution is:

Step 830: Obtain the cathode plate peak line according to the connecting line of each cathode plate corresponding to the peak in the electrode plate waveform diagram.

Step 840: Obtain the inclination according to the cathode plate peak line and the horizontal axis of the pole plate waveform diagram.

It can be seen that the inclination of the laminated battery cell 10 can be characterized by the anode sheet crest line or the cathode sheet crest line (not shown). Similarly, by calculating the angle between the cathode sheet crest line and the horizontal axis, the inclination of the laminated battery cell 10 along the staggered arrangement direction of the anode sheet 13 and the cathode sheet 14 can be obtained.

The third solution is a combination of the two solutions shown in FIG. 8a and FIG. 8b .

It can be seen that by calculating the peak line of the anode sheet and the peak line of the cathode sheet at the same time, an inclination is calculated respectively. After that, the inclination corresponding to the anode sheet and the inclination corresponding to the cathode sheet can be measured multiple times, and the results of multiple inclinations can be fitted; the inclination corresponding to the anode sheet and the inclination corresponding to the cathode sheet can be measured multiple times, and the average value of multiple inclination results can be taken; the inclination corresponding to the anode sheet and the inclination corresponding to the cathode sheet with a larger value can also be selected to characterize the inclination of the laminated battery cell 10, etc. In the third scheme, the specific use of the results of Figures 8a and 8b can be selected according to actual conditions.

Among them, step 440: confirming whether the laminated cell has defects according to the flatness parameter, also includes the following two results:

The first result is: when the inclination is less than or equal to the preset threshold, it is confirmed that there is no defect in the laminated battery cell.

The second result is: when the inclination is greater than a preset threshold, it is confirmed that the laminated battery cell is defective.

The preset inclination thresholds of different types of laminated battery cells 10 may be different. The inclination threshold of each laminated battery cell 10 is a known parameter according to its quality requirements, that is, the preset inclination threshold. When a defect is detected, it is only necessary to compare the inclination obtained by measurement with the preset threshold.

Based on the above, by mapping the stacked battery cell 10 to a waveform diagram, a set of battery cell detection methods can be used to detect the height difference between the anode sheet 13 and the cathode sheet 14 on each surface of the stacked battery cell 10, and also detect the inclination of each surface of the stacked battery cell 10. This detection method has good generalization ability and effectively improves the efficiency of detecting the surface flatness of the stacked battery cell 10.

FIG9 is a schematic diagram of a process flow of confirming a laminated core defect detection algorithm in one embodiment of the present application. As shown in FIG9 , the method further includes:

Step 910: Obtain the identification code of the laminated battery cell, where the identification code may be a product serial number (Serial Number, SN code).

Step 920: According to the identification code of the stacked battery cell, confirm the posture parameters of the image acquisition module used to acquire the first battery cell image and the second battery cell image of the stacked battery cell, and confirm the defect detection algorithm corresponding to the stacked battery cell in the preset defect detection algorithm library; wherein the defect detection algorithm is used to detect whether the stacked battery cell has defects.

It is understandable that due to the different models of different laminated battery cells 10, the corresponding defect detection algorithms may be different. For different laminated battery cells 10, the segmentation algorithm corresponding to each laminated battery cell 10 may be based on different segmentation methods or sample training corresponding to each laminated battery cell 10, and each laminated battery cell 10 is associated with the identification code of the laminated battery cell 10, so that the battery cell detection system can establish a defect detection algorithm library for different models of laminated battery cells 10. When in use, the battery cell detection system automatically calls the corresponding defect detection algorithm for defect identification based on the model information included in the identification code of each laminated battery cell 10, which enhances the robustness of the defect detection system and improves the efficiency of defect detection.

It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

Based on the same inventive concept, the embodiment of the present application also provides a battery cell detection device for implementing the battery cell detection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the battery cell detection device embodiment provided below can refer to the limitations of the battery cell detection method above, and will not be repeated here.

In one embodiment, the battery cell detection device comprises:

The acquisition unit 1010 is configured to acquire a first battery cell image and a second battery cell image of the stacked battery cell, wherein the first battery cell image and the second battery cell image are acquired from the same surface of the stacked battery cell.

The identification unit 1020 is configured to identify the first battery cell image and obtain the position of the anode sheet and the cathode sheet of the stacked battery cell.

The calculation unit 1030 is configured to obtain the flatness parameter of the stacked battery cell according to the anode sheet position, the cathode sheet position and the second battery cell image.

The confirmation unit 1040 is configured to confirm whether the laminated battery cell has defects according to the flatness parameter.

Optionally, the acquisition unit 1010 is also configured to acquire an identification code of the stacked battery cell; and confirm a defect detection algorithm corresponding to the stacked battery cell in a preset defect detection algorithm library according to the identification code of the stacked battery cell; wherein the defect detection algorithm is used to detect whether the stacked battery cell has defects.

Optionally, the identification unit 1020 is further configured to obtain the anode piece position and the cathode piece position according to the gray value difference between the anode piece and the cathode piece in the first battery cell image.

Optionally, the identification unit 1020 is further configured to perform segmentation processing on the first battery cell image to obtain the anode sheet position and the cathode sheet position.

Optionally, the identification unit 1020: is also configured to segment the anode sheet in the first battery cell image to obtain the anode sheet position; obtain the cathode sheet position based on the two spaced anode sheet positions; or segment the cathode sheet in the first battery cell image to obtain the cathode sheet position; obtain the anode sheet position based on the two spaced cathode sheet positions; or segment the anode sheet and the cathode sheet in the first battery cell image to obtain the anode sheet position and the cathode sheet position.

Optionally, the computing unit 1030 is also configured to obtain an anode reconstructed image and a cathode reconstructed image of the stacked battery cell based on the second battery cell image; obtain an anode contour image and a cathode contour image based on the anode position, the cathode position, the anode reconstructed image and the cathode reconstructed image; and obtain a height difference between adjacent anodes and cathodes based on the anode position, the cathode position, the anode contour image and the cathode contour image.

Optionally, the calculation unit 1030 is also configured to obtain a pole piece waveform diagram of the stacked battery cell according to the anode piece position, the cathode piece position, the anode piece contour diagram and the cathode piece contour image; wherein each peak in the pole piece waveform diagram is used to characterize the height of the anode piece or the height of the cathode piece; and obtain the height difference according to the absolute value of the height difference between adjacent anode piece peaks and cathode piece peaks in the pole piece peak diagram.

Optionally, the calculation unit 1030 is also configured to obtain the anode plate peak line according to the line connecting the peaks corresponding to each anode plate in the pole plate waveform diagram; obtain the inclination according to the anode plate peak line and the horizontal axis of the pole plate waveform diagram; and/or obtain the cathode plate peak line according to the line connecting the peaks corresponding to each cathode plate in the pole plate waveform diagram; obtain the inclination according to the cathode plate peak line and the horizontal axis of the pole plate waveform diagram.

Optionally, the confirmation unit 1040 is further configured to confirm that the laminated battery cell has no defects when the height difference is less than or equal to a preset threshold; or to confirm that the laminated battery cell has defects when the height difference is greater than a preset threshold.

Optionally, the confirmation unit 1040 is further configured to confirm that the laminated battery cell has no defects when the inclination is less than or equal to a preset threshold; or to confirm that the laminated battery cell has defects when the inclination is greater than a preset threshold.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the technical solution in the above-mentioned battery cell detection method embodiment of the present application is implemented. The implementation principle and technical effect are similar and will not be repeated here.

In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the technical solution in the above-mentioned battery cell detection method embodiment of the present application is implemented. The implementation principle and technical effect are similar and will not be repeated here.

Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, For example, static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, etc., but is not limited thereto.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application, and they should all be included in the scope of the claims and specification of the present application. In particular, as long as there is no structural conflict, the various technical features mentioned in the various embodiments can be combined in any way. The present application is not limited to the specific embodiments disclosed herein, but includes all technical solutions that fall within the scope of the claims.

Claims (19)

1. A battery cell detection system, characterized by comprising:

   An image acquisition module, used to obtain a first cell image and a second cell image of a stacked cell; wherein the first cell image is used to locate the electrode piece, and the second cell image is used to reconstruct the electrode piece;

   A processor is used to identify the anode sheet position and the cathode sheet position according to the first battery cell image, and to obtain the flatness parameter of the stacked battery cell according to the anode sheet position, the cathode sheet position and the second battery cell image, and to confirm whether the stacked battery cell has defects according to the flatness parameter.
2. The battery cell detection system according to claim 1 is characterized in that the image acquisition module acquires a first battery cell image and a second battery cell image of each surface of the laminated battery cell along a direction toward each surface of the laminated battery cell.
3. The battery cell detection system according to claim 1, characterized in that the image acquisition modules include two, and the two image acquisition modules are respectively located on both sides of the laminated battery cell;

   The processor is also used to synchronously identify the anode sheet position and the cathode sheet position of each surface of the stacked battery cell according to the first battery cell image and the second battery cell image of each surface of the stacked battery cell respectively acquired by the two image acquisition modules.
4. The battery cell detection system according to claim 1, characterized in that the system further comprises a detection module, wherein the detection module is used to generate a battery cell position signal and send it to the processor when detecting that the laminated battery cell is located at a preset detection position;

   The processor is used for generating an image acquisition instruction based on the identification code of the laminated battery cell and sending the instruction to the image acquisition module when receiving the battery cell position signal;

   The image acquisition module is used to acquire the first battery cell image and the second battery cell image of the laminated battery cells after hot pressing when receiving the image acquisition instruction.
5. The battery cell detection system according to claim 1, characterized in that each surface of the battery cell comprises a plurality of anode sheets and cathode sheets arranged alternately side by side, and the flatness parameter comprises a height difference between adjacent anode sheets and cathode sheets;

   The processor is used to obtain each anode sheet position and each cathode sheet position of the stacked battery cell based on the first battery cell image, and obtain each anode sheet contour image and each cathode sheet contour image of the stacked battery cell based on each anode sheet position, each cathode sheet position and the second battery cell image, obtain the height difference between adjacent anode sheets and cathode sheets based on each anode sheet position, each cathode sheet position, each anode sheet contour image and each cathode sheet contour image, and confirm whether the stacked battery cell has defects based on the height difference.
6. The battery cell detection system according to claim 5 is characterized in that the processor is also used to segment the anode piece and/or the cathode piece of the first battery cell image to obtain the anode piece position and the cathode piece position.
7. The battery cell detection system according to claim 5, characterized in that the flatness parameter also includes the inclination of each surface of the laminated battery cell;

   The processor is further used to obtain the inclination according to the position of each anode sheet in each surface of the laminated battery core and the contour image of each anode sheet, and confirm whether the laminated battery core has defects according to the inclination; and/or

   The processor is also used to obtain the inclination based on the position of each cathode sheet in each surface of the laminated battery cell and the contour image of each cathode sheet, and confirm whether the laminated battery cell has defects based on the inclination.
8. The battery cell detection system according to any one of claims 1 to 7, characterized in that the system further comprises a waste discharge module,

   The processor is used to generate a waste discharge instruction and send it to the waste discharge module when there is a defect in the laminated battery core;

   The waste discharge module is used to remove the laminated battery core based on the waste discharge instruction.
9. The battery cell detection system according to claim 1, characterized in that the system further comprises a glue sticking module,

   The processor is used for generating a glue sticking instruction and sending it to the glue sticking module when there is no defect in the laminated battery core;

   The gluing module is used to glue the laminated battery cells based on the gluing instruction.
10. A battery cell detection method, characterized by comprising:

    Acquire a first cell image and a second cell image of the laminated cell, wherein the first cell image and the second cell image are acquired from the same surface of the laminated cell;

    Recognize the first battery cell image to obtain the position of the anode sheet and the cathode sheet of the laminated battery cell;

    Obtaining a flatness parameter of the laminated battery cell according to the anode sheet position, the cathode sheet position and the second battery cell image;

    According to the flatness parameter, it is confirmed whether the laminated battery core has defects.
11. The battery cell detection method according to claim 10, characterized in that the identifying the first battery cell image to obtain the anode sheet position and the cathode sheet position of the stacked battery cell comprises:

    The anode piece position and the cathode piece position are obtained according to the gray value difference between the anode piece and the cathode piece in the first battery cell image.
12. The battery cell detection method according to claim 10, characterized in that the identifying the first battery cell image to obtain the anode sheet position and the cathode sheet position of the stacked battery cell comprises:

    The first battery cell image is segmented to obtain the anode sheet position and the cathode sheet position.
13. The battery cell detection method according to claim 12, characterized in that each surface of the battery cell includes a plurality of anode sheets and cathode sheets arranged alternately side by side, and the segmentation processing of the first battery cell image to obtain the anode sheet position and the cathode sheet position includes:

    Segmenting the anode sheet in the first battery cell image to obtain the anode sheet position;

    Obtaining the cathode sheet position according to the two anode sheet positions spaced apart; or

    Segmenting the cathode sheet in the first battery cell image to obtain the cathode sheet position;

    Obtaining the anode sheet position according to the two cathode sheet positions spaced apart; or

    The anode piece and the cathode piece in the first battery cell image are segmented to obtain the anode piece position and the cathode piece position.
14. The battery cell detection method according to claim 10, characterized in that each surface of the battery cell includes a plurality of anode sheets and cathode sheets arranged alternately side by side, and the flatness parameter includes the height difference between adjacent anode sheets and cathode sheets; the flatness parameter of the stacked battery cell is obtained according to the anode sheet position, the cathode sheet position and the second battery cell image, comprising:

    Obtaining a reconstructed image of an anode sheet and a reconstructed image of a cathode sheet of the stacked battery cell according to the second battery cell image;

    Obtaining an anode film contour image and a cathode film contour image according to the anode film position, the cathode film position, the anode film reconstructed image and the cathode film reconstructed image;

    The height difference between adjacent anode pieces and cathode pieces is obtained according to the anode piece position, the cathode piece position, the anode piece outline diagram and the cathode piece outline image.
15. The battery cell detection method according to claim 14, characterized in that the anode sheet position, The cathode sheet position, the anode sheet contour map and the cathode sheet contour image are used to obtain the height difference between adjacent anode sheets and cathode sheets, including:

    According to the anode sheet position, the cathode sheet position, the anode sheet contour diagram and the cathode sheet contour image, a pole sheet waveform diagram of the laminated battery cell is obtained; wherein each peak in the pole sheet waveform diagram is used to characterize the height of the anode sheet or the height of the cathode sheet;

    The height difference is obtained according to the absolute value of the height difference between the adjacent anode plate peak and cathode plate peak in the pole plate peak diagram.
16. The battery cell detection method according to claim 14 or 15 is characterized in that the step of confirming whether the laminated battery cell has defects based on the flatness parameter comprises:

    When the height difference is less than or equal to a preset threshold, confirming that the laminated battery core has no defects; or

    When the height difference is greater than a preset threshold, it is confirmed that the laminated battery cell has a defect.
17. The battery cell detection method according to claim 14, characterized in that the flatness parameter also includes the inclination of each surface of the laminated battery cell, and the horizontal axis of the electrode waveform graph represents the surface of the laminated battery cell; the flatness parameter of the laminated battery cell is obtained according to the anode sheet position, the cathode sheet position and the second battery cell image, and further includes:

    Obtaining an anode plate peak line according to a connecting line of a peak corresponding to each anode plate in the electrode plate waveform diagram;

    The inclination is obtained according to the anode plate peak line and the horizontal axis of the pole plate waveform diagram; and/or

    Obtaining a cathode plate wave crest line according to a connecting line of a wave crest corresponding to each cathode plate in the electrode plate waveform diagram;

    The inclination is obtained according to the cathode plate peak line and the horizontal axis of the pole plate waveform diagram.
18. The battery cell detection method according to claim 17, characterized in that the step of confirming whether the laminated battery cell has defects based on the flatness parameter further comprises:

    When the inclination is less than or equal to a preset threshold, confirming that the laminated battery core has no defects; or

    When the inclination is greater than a preset threshold, it is confirmed that the laminated battery cell has a defect.
19. The battery cell detection method according to any one of claims 10 to 18, characterized in that the method further comprises:

    Obtaining an identification code of the laminated battery cell;

    According to the identification code of the stacked battery cell, the posture parameters of the image acquisition module used to acquire the first battery cell image and the second battery cell image of the stacked battery cell are confirmed, and the defect detection algorithm corresponding to the stacked battery cell is confirmed in a preset defect detection algorithm library; wherein the defect detection algorithm is used to detect whether the stacked battery cell has defects.