Battery cell detection method and system
Through image acquisition system and color conversion technology, the battery cell is positioned, which solves the problems of high manual positioning cost and inaccurate positioning in the existing technology, and achieves high accuracy positioning of the battery cell area and improves production efficiency.
Patent Information
- Application Number
- CN202410628689.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-21
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2044-05-21
AI Technical Summary
The existing battery cell detection methods have problems such as high manual positioning cost and inaccurate positioning, especially when the tray position is different, it is difficult to achieve accurate positioning through a fixed detection frame.
The image acquisition system is used to collect images of multiple areas of the battery cell, and the converted images are obtained through color conversion, and the different areas of the battery cell are positioned based on multiple color threshold intervals. The difference in color space is used to distinguish the foreground and background to improve the accuracy of positioning. sex.
It improves the positioning accuracy of each area of the battery cell, reduces the calculation amount of the industrial control machine, avoids production fluency problems, and improves the production efficiency of the production line.
Smart Images

Figure CN118229675B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of battery testing, and in particular to a battery cell testing method and system. Background Art
[0002] In a power battery system, after the bare cell is wound and before it is placed in a shell, it is necessary to inspect the appearance and size of the bare cell and position the bare cell so that it can be accurately placed in the shell.
[0003] The bare cell detection method in the related art is usually to manually locate the tabs and other areas on the front bare cell image captured by using a preset tab position frame. This has the problem of high manual detection costs or inaccurate positioning due to the different positions of different bare cells on the tray using a fixed detection frame. Summary of the invention
[0004] The main purpose of this application is to provide a battery cell detection method and system that can improve the accuracy of positioning each area of the battery cell.
[0005] The technical solution of the embodiment of the present application is implemented as follows:
[0006] In a first aspect, an embodiment of the present application provides a battery cell detection method, which is applied to an industrial computer of a battery cell positioning system; the battery cell detection method includes:
[0007] In response to the battery cell arriving at the inspection station, acquiring an image including multiple regions of the battery cell acquired by an image acquisition system;
[0008] Performing color conversion on the image to obtain a converted image of the battery cell;
[0009] Based on multiple color threshold intervals, multiple areas of the battery cell in the conversion image are located respectively to obtain the location detection results of the battery cell; wherein the color threshold interval corresponding to each area is determined based on the material of each area.
[0010] According to the above-mentioned technical means, by performing color conversion on the image of the battery cell, based on the differences in the converted color space between different areas of the battery cell, the foreground and background of the image can be effectively distinguished, the different areas of the battery cell can be segmented, and the different areas of the battery cell can be accurately divided. Positioning based on the divided areas can improve the accuracy of positioning. At the same time, the embodiments of the present application do not need to process and locate the image through neural networks or the like. Positioning through color conversion reduces the amount of calculation of the industrial computer, and reduces the problem that the industrial computer cannot promptly feedback the positioning results of the battery cell to the next workstation due to the large amount of calculation, so that the production of the next workstation needs to wait, which makes the production not smooth, and leads to reduced production efficiency of the production line.
[0011] In the above scheme, the multiple regions include at least the tab region of the battery cell, and the positioning detection result includes at least the tab positioning result; the positioning of the multiple regions of the battery cell in the conversion image based on multiple color threshold intervals to obtain the positioning detection result of the battery cell includes: based on multiple color threshold intervals, the different tab regions of the battery cell corresponding to each color threshold interval in the conversion image are segmented to obtain the foreground images corresponding to each tab region; each foreground image is binarized to obtain a binary image corresponding to each region; each binary image is denoised to obtain a denoised binary image corresponding to each region; the corresponding region in each denoised binary image is contour extracted to obtain the positioning coordinates of each region in the detection station coordinate system; the positioning coordinates of each region are determined as the tab positioning result of the battery cell.
[0012] According to the above technical means, the tab area of the battery cell in the conversion image is segmented by different color threshold intervals, and the segmented foreground image is binarized and denoised, thereby improving the positioning accuracy of the tab area of the battery cell.
[0013] In the above scheme, based on multiple color threshold intervals, different tab areas of the battery cells corresponding to each color threshold interval in the conversion image are segmented respectively to obtain foreground images corresponding to each tab area, including: based on each color threshold interval, different tab areas of the battery cells corresponding to each color threshold interval in the conversion image are segmented respectively to obtain mask areas corresponding to each color threshold interval; areas corresponding to each mask area on the image are extracted to obtain foreground images of areas corresponding to each mask area.
[0014] In the above scheme, the multiple areas include at least two pole lug areas of the battery cell; the battery cell is fixed on the inspection station by a tray; the contour extraction of the corresponding areas in each denoised binary image is performed respectively to obtain the positioning coordinates of each area in the inspection station coordinate system, including: in response to the color value of the tray in the conversion image not being in the color threshold interval corresponding to the two pole lug areas, the pole lug contour extraction of the denoised binary images corresponding to the two pole lug areas is performed respectively to obtain two pole lug contours; based on the two pole lug contours, the pole lug positioning coordinates of the two pole lug areas are determined respectively.
[0015] According to the above technical means, the influence of the aging pallet on image recognition is taken into consideration, and when the color of the pallet is different from the color of the tab area, the positioning coordinates of the tab area can be quickly obtained.
[0016] In the above scheme, the multiple areas include at least two pole lug areas of the battery cell, and the two pole lug areas include a first pole lug and a second pole lug; the battery cell is fixed on the inspection station by a tray; the contour extraction of the corresponding areas in each denoised binary image is performed to obtain the positioning coordinates of each area in the inspection station coordinate system, including: in response to the color value of the tray in the conversion image being in the color threshold interval corresponding to the first pole lug, the pole lug contour extraction of the denoised binary image corresponding to the second pole lug is performed to obtain the second pole lug contour; based on the second pole lug contour, the second pole lug positioning coordinates of the second pole lug in the inspection station coordinate system are determined; based on the second pole lug positioning coordinates and the denoised binary image corresponding to the first pole lug, the first pole lug positioning coordinates of the first pole lug in the inspection station coordinate system are determined.
[0017] According to the above technical means, the influence of aging pallets on image recognition is taken into consideration. When the color of the pallet is the same as the color of the tab area, the mislabeled pallet is removed, thereby improving the accuracy of tab positioning.
[0018] In the above scheme, the first pole lug positioning coordinates of the first pole lug on the detection station coordinate system are determined based on the second pole lug positioning coordinates and the denoised binary image corresponding to the first pole lug, including: based on the second pole lug positioning coordinates, roughly positioning the first pole lug in the first direction of the denoised binary image corresponding to the first pole lug to obtain a rough positioning area corresponding to the first pole lug; in the rough positioning area, determining the contour position of the first pole lug in the second direction; wherein the first direction is perpendicular to the second direction, and the first pole lug is in contact with the tray in the first direction; based on the rough positioning area and the contour position, determining the first pole lug positioning coordinates of the first pole lug on the detection station coordinate system.
[0019] In the above scheme, based on the second pole lug positioning coordinates, the first pole lug is roughly positioned in the first direction of the denoised binary image corresponding to the first pole lug to obtain the coarse positioning area corresponding to the first pole lug, including: based on the second pole lug positioning coordinates, determining the two position coordinates of the pole lug area of the battery cell in the first direction; in the first direction of the denoised binary image corresponding to the first pole lug, determining the area between the two position coordinates as the coarse positioning area corresponding to the first pole lug.
[0020] According to the above technical means, when the color of the tray is the same as the color of a tab area, the tab area with similar color is first roughly positioned and then finely positioned based on the positioning result of another tab area, thereby improving the accuracy of tab positioning.
[0021] In the above scheme, the multiple areas include at least the large surface area of the battery cell, and the positioning detection result includes at least the large surface positioning result; based on multiple color threshold intervals, the multiple areas of the battery cell in the conversion image are positioned respectively to obtain the positioning detection result of the battery cell, including: based on the large surface color threshold interval corresponding to the large surface area, the area corresponding to the large surface color threshold interval in the conversion image is segmented to obtain the foreground image corresponding to the large surface area; the foreground image corresponding to the large surface area is binarized to obtain the large surface binary image corresponding to the large surface area; the large surface contour is extracted from the large surface binary image to obtain a large surface rough positioning contour; the large surface rough positioning contour is a closed contour obtained by connecting multiple rough positioning contour edges in sequence; the multiple rough positioning contour edges are precisely positioned to obtain the precise positioning contour edges corresponding to each rough positioning contour edge; based on the multiple precise positioning contour edges, the large surface positioning coordinates of the large surface area in the detection station coordinate system are determined to obtain the large surface positioning result of the battery cell.
[0022] According to the above technical means, when positioning the large surface, the large surface can be identified and roughly positioned through the large surface color threshold interval corresponding to the large surface area. After the large surface is roughly positioned, each contour edge is precisely positioned, thereby improving the positioning accuracy of the large surface of the battery cell.
[0023] In the above scheme, the battery cell detection method further includes: performing binarization processing on the image to obtain a battery cell binary image corresponding to the battery cell; and performing large surface contour extraction on the battery cell binary image to obtain the large surface rough positioning contour.
[0024] According to the above technical means, when locating a large surface, the image can also be binarized, and a rough positioning outline of the large surface can be obtained by the binarized image. There is no need to determine the six values of the color threshold range. Only one channel of the image needs to be binarized to locate the large surface, and the rough positioning outline of the large surface can be obtained, which can improve the efficiency of large surface positioning.
[0025] In the above scheme, the multiple coarse positioning contour edges are finely positioned to obtain fine positioning contour edges corresponding to each coarse positioning contour edge, including: setting multiple positioning rectangles at multiple non-overlapping positions on each coarse positioning contour edge; wherein the coarse positioning contour edge is located inside each positioning rectangle; based on the multiple positioning rectangles, multiple fine positioning coordinates at multiple positions are determined respectively; and the multiple fine positioning coordinates corresponding to each coarse positioning contour edge are fitted respectively to obtain the fine positioning contour edges corresponding to each coarse positioning contour edge.
[0026] According to the above technical means, the accuracy of large surface positioning can be improved by finely positioning the rough positioning contour of the large surface through multiple positioning rectangles.
[0027] In the above scheme, the large-surface positioning coordinates of the large-surface area on the detection station coordinate system are determined based on multiple fine positioning contour edges, including: in response to any fine positioning contour edge among the multiple fine positioning contour edges not satisfying the slope condition, based on the coarse positioning contour edge and other fine positioning contours corresponding to any fine positioning contour edge, the large-surface positioning coordinates of the large-surface area on the detection station coordinate system are determined; in response to the multiple fine positioning contour edges all satisfying the slope condition, based on the multiple fine positioning contour edges, the large-surface positioning coordinates of the large-surface area on the detection station coordinate system are determined.
[0028] According to the above technical means, when positioning the large surface, after rough positioning through the image, each contour edge is precisely positioned, thereby improving the positioning accuracy of the large surface of the battery cell.
[0029] In the above scheme, the battery cell detection method also includes: obtaining information about the battery cell; based on the information about the battery cell, determining material information corresponding to the multiple regions of the battery cell respectively; based on the material information corresponding to each region among the multiple regions, determining the color threshold interval corresponding to each region.
[0030] According to the above technical means, based on the differences in the hue, saturation and value (HSV) color space of the material, the color threshold intervals corresponding to different areas of the battery cell are determined, which can effectively segment the various areas of the battery cell and improve the positioning effect and accuracy of each area of the battery cell.
[0031] In the above scheme, the multiple areas include at least two pole lug areas of the battery cell; the battery cell detection method also includes: determining the polarity information of the two pole lug areas based on the material information corresponding to the two pole lug areas respectively; based on the pole lug positioning coordinates of the two pole lug areas, displaying the polarity information of the two pole lug areas respectively on the corresponding pole lug areas on the conversion image.
[0032] According to the above technical means, after the tab is positioned, the polarity of the tab can be determined and displayed on the human-computer interaction interface to show the positioning result and the polarity of the tab to engineers on the production line.
[0033] In a second aspect, an embodiment of the present application provides a battery cell positioning system, the battery cell positioning system comprising: an industrial computer, which sends an image acquisition signal to an image acquisition system in response to the battery cell arriving at a detection station; the image acquisition system is used to perform image acquisition on the battery cell in response to the image acquisition signal, obtain an image including at least multiple areas of the battery cell, and send the image to the industrial computer; the industrial computer is further used to acquire the image, perform color conversion on the image, and obtain a converted image of the battery cell; based on multiple color threshold intervals, multiple areas of the battery cell in the converted image are respectively located to obtain the positioning result of the battery cell; wherein the color threshold interval corresponding to each area is determined based on the material of each area.
[0034] According to the above-mentioned technical means, by performing color conversion on the image of the battery cell, based on the differences in the converted color space between different areas of the battery cell, the foreground and background of the image can be effectively distinguished, the different areas of the battery cell can be segmented, and the different areas of the battery cell can be accurately divided. Positioning based on the divided areas can improve the accuracy of positioning. At the same time, the embodiments of the present application do not need to process and locate the image through neural networks or the like. Positioning through color conversion reduces the amount of calculation of the industrial computer, and reduces the problem that the industrial computer cannot promptly feedback the positioning results of the battery cell to the next workstation due to the large amount of calculation, so that the production of the next workstation needs to wait, which makes the production not smooth, and leads to reduced production efficiency of the production line.
[0035] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present application and are used together with the specification to illustrate the technical solution of the present application. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0037] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.
[0038] Figure 1 This is a schematic diagram of an optional battery cell detection method provided in an embodiment of the present application. Figure 1 ;
[0039] Figure 2 This is a schematic diagram of an optional battery cell detection method provided in an embodiment of the present application. Figure 2 ;
[0040] Figure 3 is a schematic diagram of the process of image positioning provided by an embodiment of the present application;
[0041] Figure 4 This is a schematic diagram of an optional battery cell detection method provided in an embodiment of the present application. Figure 3 ;
[0042] Figure 5 It is a schematic diagram of large-surface precision positioning provided by an embodiment of the present application;
[0043] Figure 6 is a structural schematic diagram of a battery cell positioning system provided in an embodiment of the present application;
[0044] Figure 7 It is a schematic diagram of the process of positioning the battery cell tab provided in an embodiment of the present application;
[0045] Figure 8 It is a schematic diagram of an image flow of positioning a cell tab provided in an embodiment of the present application;
[0046] Fig. 9 It is a schematic diagram of the process of large-surface positioning of a battery cell provided in an embodiment of the present application;
[0047] Fig.10 This is a schematic diagram of the structure of the upper edge positioning of the large surface of the battery cell provided in an embodiment of the present application;
[0048] Fig.11 This is a schematic diagram of the structure of positioning the left edge of the large surface of the battery cell provided in an embodiment of the present application;
[0049] Fig.12 It is a structural schematic diagram of the positioning of the right edge of the large surface of the battery cell provided in an embodiment of the present application. DETAILED DESCRIPTION
[0050] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the specific technical solution of the present application will be further described in detail below in conjunction with the drawings in the embodiments of the present application. The following embodiments are used to illustrate the present application, but are not used to limit the scope of the present application.
[0051] Unless otherwise defined, all technical and scientific terms used in this application have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used in this application are only for the purpose of describing this embodiment and are not intended to limit this application.
[0052] In the following description, references to “some embodiments,” “this embodiment,” “this embodiment,” and examples, etc., describe a subset of all possible embodiments, but it can be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict.
[0053] If similar descriptions of "first / second" appear in the application documents, the following instructions are added. In the following description, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged in a specific order or sequence where permitted, so that the present embodiment described here can be implemented in an order other than that illustrated or described here.
[0054] In the embodiments of the present application, the term "and / or" is merely a description of the association relationship between associated objects, indicating that three relationships may exist. For example, object A and / or object B may represent three situations: object A exists alone, object A and object B exist at the same time, and object B exists alone.
[0055] At present, new energy batteries are more and more widely used in life and industry. New energy batteries are not only used in energy storage power systems such as hydropower, thermal power, wind power and solar power stations, but also widely used in electric vehicles such as electric bicycles, electric motorcycles, electric vehicles, and aerospace and other fields. With the continuous expansion of the application field of power batteries, the market demand is also constantly expanding. In the embodiment of the present application, the battery involved may be a battery cell, also known as a battery cell. A battery cell refers to a basic unit that can realize the mutual conversion of chemical energy and electrical energy, which can be used to make a battery module or a battery pack, so as to supply power to an electrical device. A battery cell may be a secondary battery, which refers to a battery cell that can be used to activate the active material by charging after the battery cell is discharged. The battery cell may be a lithium ion battery, a sodium ion battery, a sodium lithium ion battery, a lithium metal battery, a sodium metal battery, a lithium sulfur battery, a magnesium ion battery, a nickel hydrogen battery, a nickel cadmium battery, a lead-acid battery, etc., and the embodiment of the present application is not limited to this.
[0056] In the embodiments of the present application, the battery cell may refer to a battery cell of any shape, such as a square battery cell, a round battery cell, etc. And the battery cell usually refers to a battery cell, which is one of the basic units that constitute the battery. The battery cell is the core component of the battery, responsible for storing and releasing electrical energy. The battery cell may be: a lithium-ion battery cell (Li-ion Cell), a lithium polymer battery cell (Li-polymer Cell), a nickel-metal hydride battery cell (NiMH Cell), etc. The embodiments of the present application do not impose any restrictions on the type of battery cell, and the specific type can be selected according to the actual application scenario.
[0057] In the embodiments of the present application, the battery cell is the core component of the battery pack, also known as the battery cell. A battery pack usually contains multiple battery cells, which are combined together to provide the required power capacity and voltage. The components of the battery pack include at least: battery cells, battery management system (Battery Management System, BMS), casing, connecting harness, connector and interface, etc. These components work together to combine the battery cells into a fully functional battery pack for various application scenarios. For example, the battery pack can be applied to electric vehicles, energy storage systems, portable electronic devices, solar energy systems, wind energy systems, emergency backup power supplies, power tools or electric bicycles, etc. The embodiments of the present application do not make any restrictions on this, and can be selected according to the actual application scenario.
[0058] It should be noted that the battery pack can use different types of battery cells, such as lithium-ion batteries, nickel-metal hydride batteries, lithium polymer batteries, etc., depending on the needs and performance requirements of the actual application.
[0059] In the embodiment of the present application, the battery may also be a single physical module including one or more battery cells to provide higher voltage and capacity. When there are multiple battery cells, the multiple battery cells are connected in series, in parallel or in hybrid connection through a busbar component.
[0060] In the battery production process, the shelling process of loading the battery cell into the shell is an important process in battery assembly. Before the battery is shelled, the positive and negative adapter plates of the battery cell need to be welded. In order to ensure the quality of welding, it is necessary to determine the accurate positioning of the positive and negative pole ears of the battery cell, and to detect the appearance defects and size of the battery cell, so as to realize the shelling of the battery cell. The accurate positioning of the battery cell before shelling directly affects the execution of the shelling process. Inaccurate positioning of the battery cell can easily cause risks such as battery cell bulging and battery cell scrapping, and may even cause explosion accidents. Here, the battery cell may refer to a battery cell that has not been packaged and assembled, usually consisting of a positive electrode, a negative electrode and a diaphragm.
[0061] Therefore, the battery cell needs to be positioned before it is placed in the shell. In the related art, the battery cell detection method is usually manual positioning or positioning the tabs and other areas on the front battery cell image captured by a preset tab position frame. In this way, there are problems such as high manual detection costs or inaccurate positioning due to the different positions of different battery cells on the tray through a fixed detection frame.
[0062] Based on the above technical problems, the applicant believes that the positioning accuracy of the battery cells can be improved by positioning the battery cells and different areas of the battery cells based on the differences in the materials of different areas of the battery cells in the color space and according to the color value thresholds of different areas or the different grayscale values of the RGB (red, green, blue) color space.
[0063] Here, color space is a spatial combination of specified colors, involving the definition of three colors: red, green, and blue combined with a color model, using one-dimensional, two-dimensional, three-dimensional, or even four-dimensional spatial coordinates to represent a certain color. The color range that can be defined by this coordinate system is the color space. Different color space models have evolved from the RGB color model, such as hue, saturation, and brightness (HSL (Hue, Saturation, Lightness)) and hue, saturation, and value (HSV (Hue, Saturation, Value)). Color space is a space that describes and standardizes color systems, usually defined in mathematical ways (such as numerical values). Color values are used to define the colors of the color space. For example, in the HSV color space, hue (Hue) represents the type of color, and the value range is 0-360. Within this range, 0 represents red, 60 represents yellow, and 120 represents green.
[0064] Based on the above-mentioned inventive concept, an embodiment of the present application provides a battery cell detection method, which is applied to a battery cell positioning system of a battery cell detection station on a battery production line. The battery cell positioning system at least includes an industrial computer and an image acquisition system at the detection station, wherein the image acquisition system can be a charge coupled device (CCD) camera fixed on the detection station, or a two-dimensional camera or a three-dimensional camera capable of image acquisition. The industrial computer can be a host computer, which is used to calculate the image acquired by the image acquisition system to realize battery cell positioning. Here, the host computer refers to a computer or system that communicates and controls the lower computer or the production equipment on the production line. The host computer can issue control commands for monitoring and controlling remote devices or systems. The host computer can be a desktop computer, a server or other advanced computing device.
[0065] The battery cell detection method provided in the embodiment of the present application is that in response to the battery cell arriving at the detection station, the industrial computer obtains an image including multiple areas of the battery cell acquired by the image acquisition system, performs color conversion on the image, converts the acquired image into a color space (which can be an HSV color space), obtains a converted image of the battery cell, and based on multiple color threshold intervals, respectively locates multiple areas of the battery cell in the converted image to obtain a positioning result of the battery cell.
[0066] In this way, the embodiment of the present application performs color conversion on the image of the battery cell, and based on the differences in the converted color space between different areas of the battery cell, effectively distinguishes the foreground and background of the image, segments the different areas of the battery cell, and accurately divides the different areas of the battery cell. Positioning based on the divided areas can improve the accuracy of positioning. At the same time, the embodiment of the present application does not need to process and locate the image through neural networks or other methods. Positioning through color conversion reduces the calculation amount of the industrial computer, and reduces the problem that the industrial computer cannot promptly feedback the positioning results of the battery cell to the next workstation due to the large amount of calculation, so that the production of the next workstation needs to wait, which makes the production not smooth and leads to reduced production efficiency of the production line.
[0067] The battery cells located by the battery cell detection method disclosed in the embodiment of the present application can be used in, but not limited to, electrical devices such as vehicles, ships or aircraft. A power supply system comprising the battery cells disclosed in the present application can be used to form the electrical device, which is conducive to alleviating and automatically adjusting the deterioration of the battery cell expansion force, replenishing the electrolyte consumption, and improving the stability of battery performance and battery life.
[0068] The battery located by the battery cell detection method disclosed in the embodiment of the present application can be used as an electrical device for power supply, and the electrical device can be, but is not limited to, a mobile phone, a tablet, a laptop computer, an electric toy, an electric tool, a battery car, an electric car, a ship, a spacecraft, etc. Among them, the electric toy can include a fixed or mobile electric toy, for example, a game console, an electric car toy, an electric ship toy, an electric airplane toy, etc., and the spacecraft can include an airplane, a rocket, a space shuttle, a spacecraft, etc.
[0069] The embodiment of the present application provides a battery cell detection method to improve the accuracy and efficiency of battery cell positioning. The technical solution of the present application will be described in detail below in conjunction with the accompanying drawings.
[0070] See also Figure 1 , Figure 1 This is a schematic diagram of an optional battery cell detection method provided in an embodiment of the present application. Figure 1 The method is applied to an industrial computer of a cell positioning system. The cell positioning system includes an image acquisition system and an industrial computer. The cell detection method is implemented through steps S101 to S103:
[0071] Step S101: in response to a battery cell arriving at a detection station, acquiring an image including multiple regions of the battery cell acquired by an image acquisition system.
[0072] In some embodiments, the inspection station is a station after the battery cell is wound and before the battery cell is injected and shelled. The wound battery cell reaches the inspection station via a conveyor belt. The inspection station is used to perform appearance inspection on the battery cell. Through positioning, it can be determined whether the spacing between the two tabs meets the requirements, whether the size of the tabs meets the requirements, whether the relative position relationship between the tabs and the large surface meets the requirements, whether the tabs and the large surface have defects, etc.
[0073] In an embodiment of the present application, the image acquisition system may refer to a camera system at a detection station, including components such as a camera, a light source, and a display interface. The display interface may be used to display images captured by the camera, or it may be a system that receives the positioning results of the industrial computer and displays them on the display interface after the industrial computer is positioned. In some embodiments, the display interface may be a human-machine interface (HMI) for on-site engineers to adjust parameters of the image acquisition system, such as exposure and other parameters, to adjust the image quality. Here, the camera may be a charge coupled device (CCD) camera, or a two-dimensional camera or a three-dimensional camera capable of image acquisition.
[0074] In an embodiment of the present application, a mechanical gripper is provided at the inspection station, and the battery cells wound at the winding station are conveyed to the inspection station via a conveyor belt. The industrial computer controls the mechanical gripper to grab the battery cells on the conveyor belt and place them on a tray at the inspection station. The tray is located at a fixed position at the inspection station, and a fixing device is provided on the tray for fixing the battery cells. The positions of the tray and the image acquisition system are relatively fixed, so that the position of each battery cell at the inspection station is kept as consistent as possible, so that the image captured by the image acquisition system can include the appearance of the battery cell.
[0075] Here, after the battery cell is fixed on the tray, the industrial computer can send an image acquisition signal to the image acquisition system to perform image acquisition to obtain an image containing multiple areas of the battery cell. The multiple areas may refer to the tab area and large surface area of the battery cell.
[0076] Here, the pallet may be provided with sensors or other detection devices for detecting the position, signal or other specific characteristics of the battery cells to determine whether the battery cells are in place on the pallet. Once the industrial computer collects the arrival signal from the sensor, it sends an image acquisition signal to the image acquisition system.
[0077] In the embodiment of the present application, the multiple regions of the image include at least the tab region of the battery cell, and the tab region includes the cathode tab region and the anode tab region.
[0078] Step S102: performing color conversion on the image to obtain a converted image of the battery cell.
[0079] In some embodiments, the image captured by the image acquisition system may be an image mode such as a three-primary color (RGB, Red, Green, Blue) image, but the three components of the RGB image are all used to represent the color tone. When positioning by color, the three variables R, G, and B must be considered simultaneously. As a result, when locating each area on the battery cell by using the RGB image, there are too many factors to consider, the calculation is relatively complicated, and it is difficult to distinguish the foreground and background of the battery cell image, resulting in low accuracy of the segmentation result.
[0080] Therefore, the embodiments of the present application can perform color conversion on the image, converting it into a color space in which each area of the battery cell can be more clearly distinguished and the foreground and background of the battery cell can be effectively separated. For example, the HSV color space, in which the channel vector consists of three parts, including hue (Hue), saturation (Saturation) and value (Value), can realize the extraction and recognition of specific color areas, thereby realizing the distinction between different objects in the image.
[0081] In the embodiment of the present application, in order to enable the conversion image to effectively segment the various regions of the battery cell, the image may be converted into the HSV color space to obtain a conversion image.
[0082] Step S103 , based on multiple color threshold intervals, respectively locate multiple areas of the battery cell in the converted image to obtain positioning detection results of the battery cell; wherein the color threshold interval corresponding to each area is determined based on the material of each area.
[0083] In an embodiment of the present application, the materials of different areas of the battery cell are known, and the target color range of each area in the HSV space, that is, the color threshold range, can be determined based on the different color expressions of the material in the HSV space. The converted image is segmented according to the corresponding target color range to obtain the target color area corresponding to each area, and each color area is located to obtain the positioning result of each area.
[0084] In some embodiments, the multiple areas on the conversion image include at least the tab area of the battery cell. The battery cell can use copper and aluminum as the tabs of the two electrodes of the two battery cells respectively. According to the different colors of copper and aluminum in the HSV space, the color threshold intervals corresponding to copper and aluminum can be determined. For example, the color threshold interval of copper can be h between 0-113, s between 53-255, and v between 137-255; the color threshold interval of aluminum can be h between 0-66, s between 36-107, and v between 29-73. Based on these two color threshold intervals, the area corresponding to the copper tab and the aluminum tab in the conversion image can be located, and the contour of the area can be extracted to output the positioning coordinates of the copper tab and the aluminum tab, that is, the tab positioning result of the battery cell.
[0085] In some embodiments, the multiple areas on the conversion image also include a large surface area of the battery cell, and the large surface is identified by using a color threshold interval corresponding to the large surface area to obtain a large surface positioning result of the battery cell.
[0086] Here, performing contour extraction on a region corresponding to a certain color threshold interval may refer to dividing pixels on the converted image into two categories by the color threshold interval, where the color values of the pixels are in the color threshold interval and the color values of the pixels are not in the color threshold interval. The two categories may be binarized to obtain two regions, and the boundary of the two regions is used as the contour of the region corresponding to the color threshold interval. Here, binarization may be in the form of black and white or in other forms.
[0087] Here, a coarse positioning rectangular frame can be set according to the approximate position of the lug in the image in the historical data to specify the approximate position range of the lug, and then the lug area in the coarse positioning rectangular frame can be iteratively segmented according to the segmentation algorithm until foreground images with only the copper lug and the aluminum lug are obtained respectively. The foreground image can be binarized to obtain a binary image, and the contour coordinates of the copper lug and the aluminum lug can be obtained based on the binary image as the positioning result of the copper lug and the aluminum lug.
[0088] In some embodiments, the materials of the tabs and the large surface of the battery cell are known, and the color threshold intervals of the tabs and the large surface on the conversion image can be determined according to the materials. Therefore, the determination of the color threshold interval can be achieved through steps S1 to S3:
[0089] Step S1, obtaining information of the battery cell.
[0090] In some embodiments, the battery cell may be transferred from a winding station to a current inspection station. Therefore, the industrial computer may directly send an information acquisition request to the industrial computer of the winding station to obtain the battery cell information. The battery cell information includes at least the material of the battery cell tabs.
[0091] In some embodiments, each battery cell has an electronic tag during the production process, which may be a QR code tag, a Radio Frequency Identification (RFID) tag or other identification. After winding is completed, the information of the battery cell is stored and the information is obtained by scanning the electronic tag of the battery cell.
[0092] An information reading device may be provided at the inspection station. The information reading device may be a barcode scanner or a radio frequency identification device. The industrial computer uses the barcode scanner to read the electronic tag of the battery cell on the tray to obtain the information of the battery cell.
[0093] Step S2: Based on the information of the battery cell, determine the material information corresponding to the multiple regions of the battery cell.
[0094] In the embodiment of the present application, by acquiring the battery cell information, the material information of the tabs and large surface of the battery cell can be determined.
[0095] Step S3: determining the color threshold interval corresponding to each area based on the material information corresponding to each area among the multiple areas.
[0096] In the embodiment of the present application, after the materials of each region of the battery cell are determined, the color threshold intervals corresponding to the respective regions can be determined according to the differences of the respective materials in the HSV color space.
[0097] The embodiment of the present application determines the color threshold intervals corresponding to different areas of the battery cell based on the differences in materials in the HSV color space, which can effectively segment the areas of the battery cell and improve the positioning effect and accuracy of each area of the battery cell.
[0098] In some embodiments, after the tab of the battery cell is positioned, the polarity of the tab can be determined according to the material of the tab, and the polarity corresponding to the tab is marked in the positioning area of the tab on the image, and displayed on the display interface of the detection station or the marked image is sent to the next station. Here, determining the polarity of the tab and marking it can be achieved through steps S4 and S5:
[0099] Step S4: determining polarity information of the two tab regions based on the material information corresponding to the two tab regions respectively.
[0100] In some embodiments, the material of the tabs of the battery cell is known. When the material is known, the polarities of the two tabs are also known. Therefore, after positioning the different tabs, the polarities of the corresponding tabs can be determined. For example, the tabs of the battery cell are copper tabs and aluminum tabs. After the positions of the copper tabs and aluminum tabs are determined respectively, it can be determined that the tab at the copper tab is the anode tab of the battery cell, and the tab at the aluminum tab is the cathode tab of the battery cell.
[0101] Step S5: Based on the tab positioning coordinates of the two tab regions, the polarity information of the two tab regions are respectively displayed on the corresponding tab regions on the conversion image.
[0102] In some embodiments, after determining the location coordinates and polarity of each tab region, a location frame of each tab region can be generated on the conversion image based on the location coordinates, and the material and polarity of the tab can be displayed next to the location frame. The conversion image with the tab location frame, tab material, and tab polarity can be displayed on a human-machine interface (HMI) of an industrial computer.
[0103] After positioning the tab, the embodiment of the present application can determine the polarity of the tab and display it on the human-computer interaction interface to show the positioning result and the polarity of the tab to the operator on the production line, so that at the battery cell pairing station, the operator can pair the tabs based on the polarity of the battery cell, and when the ultrasonic welding adapter is subsequently performed, the correctness of the positive and negative pole connection can be guaranteed to avoid reverse connection of the battery.
[0104] In some embodiments, after obtaining the cell positioning result of the battery cell, the industrial computer can detect whether the distance between the two pole ears of the battery cell meets the requirements, the size of the pole ears, and whether the relative positions of the two pole ears meet the requirements based on the positioning result, and determine the battery cells that do not meet the conditions as unqualified (NG, Not Good) products, flow out of the inspection station, and transport the NG products as scrap materials to the area corresponding to scrap materials; the battery cells that meet the requirements are transferred to the next station, such as the battery cell pairing station.
[0105] The embodiment of the present application performs color conversion on the image of the battery cell, and based on the differences in the converted color space between different areas of the battery cell, effectively distinguishes the foreground and background of the image, segments the different areas of the battery cell, and accurately divides the different areas of the battery cell. Positioning based on the divided areas can improve the accuracy of positioning. At the same time, the embodiment of the present application does not need to process and locate the image through neural networks or other methods. Positioning through color conversion reduces the calculation amount of the industrial computer, and reduces the problem that the industrial computer cannot promptly feedback the positioning result of the battery cell to the next workstation due to the large amount of calculation, so that the production of the next workstation needs to wait, which makes the production not smooth and leads to reduced production efficiency of the production line.
[0106] In some embodiments, Figure 2 This is a schematic diagram of an optional battery cell detection method provided in an embodiment of the present application. Figure 2 ,like Figure 2 As shown, the multiple regions of the battery cell include at least the tab region of the battery cell, and the positioning detection result of the battery cell includes at least the tab positioning result. Step S103 can be implemented by steps S201 to S205:
[0107] Step S201 : based on a plurality of color threshold intervals, segmenting the different tab regions of the battery cell corresponding to each color threshold interval in the conversion image respectively, to obtain a foreground image corresponding to each tab region respectively.
[0108] In the embodiment of the present application, image segmentation is a natural step from coarse to fine reasoning, and the goal of segmentation is to label each pixel in the image with a corresponding class of content. That is, image segmentation is to classify each pixel in the image into one of the classes.
[0109] In the embodiment of the present application, the pixels in a color threshold interval can be determined as the area corresponding to the color threshold interval, and the area is segmented on the converted image to obtain the foreground image corresponding to the area. Here, the foreground image refers to the image of only the segmented areas, and the pixel values of other places except the area are 0, that is, black.
[0110] Figure 3 is a schematic diagram of the process of image positioning provided by the embodiment of the present application, such as Figure 3 As shown, based on step S201, each cell region on the conversion image 301 can be segmented. Figure 3 Taking a tab of a battery cell as an example, a foreground image 302 of the tab is extracted through a color threshold interval corresponding to the tab.
[0111] Here, step S201 can be implemented by steps S2011 and S2012:
[0112] Step S2011: based on each color threshold interval, segmenting the different tab regions of the battery cell corresponding to each color threshold interval in the conversion image respectively, to obtain mask regions corresponding to each color threshold interval on the conversion image.
[0113] In an embodiment of the present application, based on the color threshold intervals corresponding to different pole lug areas, the areas corresponding to each color threshold interval in the conversion image are segmented, and mask images corresponding to different pole lug areas are obtained respectively. Each mask image only has the mask area corresponding to the segmented pole lug area, that is, the mask image of the color threshold interval corresponding to the copper pole lug only has the area corresponding to the copper pole lug.
[0114] Step S2012: extracting the area corresponding to each mask area on the image to obtain a foreground image corresponding to the area corresponding to each mask area.
[0115] Here, according to the position of each mask area on the image, the area corresponding to each mask area of the image is extracted to obtain the foreground image corresponding to the area corresponding to each mask area.
[0116] Step S202: Binarize each foreground image to obtain a binary image corresponding to each region.
[0117] Please continue to refer to Figure 3 Each foreground image (such as the foreground image 302 of the tab) only contains the corresponding regions. The foreground image can be binarized, and the pixel value of each region of the battery cell is set to 0, and the background is set to 255, so as to facilitate denoising of the image and obtain a binary image 303.
[0118] In some embodiments, before binarization, the foreground image can be converted into a grayscale image, and then the grayscale image can be binarized to avoid inaccurate binarization results due to some anomalies in the foreground image (for example, some areas of metal are abnormally bright).
[0119] Step S203: perform denoising processing on each binary image to obtain a denoised binary image corresponding to each region.
[0120] In some embodiments, the binary image corresponding to each region can be denoised by bit operation denoising and corrosion and dilation operation denoising to obtain a denoised binary image corresponding to each region, such as Figure 3 The denoised binary image 304 in FIG.
[0121] Here, bitwise denoising is used to process the pixel values of the image. The noise is removed by performing AND, OR, NOT operations on the grayscale of each pixel in the binary image. For example, the neighborhood of a white pixel (for example, the 3*3 area around the pixel) is checked through bitwise operations. If there is no white pixel in the neighborhood, the white pixel is considered as noise and eliminated. Erosion and dilation denoising is a morphological denoising operation. The edges of each area are denoised by shrinking and enlarging the image to obtain the denoised binary image corresponding to each area.
[0122] Step S204 , respectively extracting contours of corresponding regions in each denoised binary image to obtain positioning coordinates of each region in the detection station coordinate system.
[0123] Here, the detection station coordinate system may refer to a unified coordinate system constructed for each physical position in the detection station. Through the detection station coordinate system, the visual positions of the two tabs and the large surface of the battery cell to be positioned in the detection station can be unified into the same coordinate system.
[0124] In the embodiment of the present application, there are only 0 and 255 in the denoised binary image, so the contour of each area of the battery cell can be quickly extracted (here, the non-0 area of the denoised binary image is bright, and the 0 area is black, and the contour points of the bright area can be obtained as the contour of each area), so that the positioning of the contour in different directions can be determined, thereby obtaining the positioning coordinates of the contour of each area. Here, the positioning coordinates can refer to the positioning coordinates of the minimum circumscribed rectangle of each area, which is represented by the coordinates of the lower left corner of the rectangle and the length and width of the rectangle.
[0125] Step S205: determining the positioning coordinates of each area as the tab positioning result of the battery cell.
[0126] The embodiment of the present application can display the positioning frame corresponding to the positioning coordinates of each area on the conversion image as the positioning result of the battery cell, and display it on the HMI interface of the inspection station.
[0127] The embodiment of the present application segments each area of the battery cell in the conversion image through different color threshold intervals, binarizes and denoises the segmented foreground image, and improves the positioning accuracy of each area of the battery cell.
[0128] In some embodiments, the multiple regions of the battery cell may include at least two pole ear regions of the battery cell. After the battery cell is wound at the winding station, it arrives at the inspection station. The grasping robot of the inspection station grasps the battery cell and places it on the tray of the inspection station. The tray of the inspection station is provided with a fixing device for fixing the battery cell. After the tray is used for a long time, the fixing device on the tray is in contact and friction with the battery cell for a long time, and some battery cell materials may remain or the tray may be worn, resulting in the color of the fixing device on the conversion image after color conversion being the same as the color of the pole ear, which may cause the pole ear to be inaccurate when it is segmented, resulting in inaccurate positioning. Therefore, the embodiment of the present application can change the positioning method of the pole ear based on whether the color of the fixing device of the tray on the conversion image is similar to the color of the pole ear.
[0129] In some embodiments, if the color of the fixing device of the tray in the conversion image is different from the colors of the two tabs, step S204 may be implemented by steps S2041 and S2042:
[0130] Step S2041 , in response to the color value of the pallet in the conversion image not being within the color threshold interval corresponding to the two tab regions, performing tab contour extraction on the denoised binary images corresponding to the two tab regions to obtain two tab contours.
[0131] In some embodiments, the color value of the pallet in the converted image is not in the color threshold interval corresponding to the two lug areas, indicating that when the lug area is segmented based on the color threshold interval, part of the pallet area will not be marked as a lug. At this time, the denoised binary image only contains the lug area, and there is no pallet marked as a lug. Therefore, the lug contour can be directly extracted from the lug area to obtain two lug contours without the need to first identify the pallet and then remove it.
[0132] Step S2042: based on the two tab contours, determine the tab positioning coordinates of the two tab regions on the detection station coordinate system.
[0133] When the two tab contours are obtained respectively, the tab positioning coordinates of the two tab regions on the detection station coordinate system can be determined.
[0134] The embodiment of the present application takes into account the influence of an aged pallet on image recognition, and when the color of the pallet is different from the color of the tab area, the positioning coordinates of the tab area can be quickly obtained.
[0135] In some embodiments, if the color of the fixture of the tray in the conversion image is within the color threshold interval of any tab, step S204 can also be implemented through steps S2043 to S2045:
[0136] Step S2043: In response to the color value of the tray in the converted image being in the color threshold interval corresponding to the first pole lug, extracting the pole lug contour from the denoised binary image corresponding to the second pole lug to obtain the second pole lug contour.
[0137] In some embodiments, if the color of the pallet is within the color threshold interval corresponding to a pole lug, for example, the color value of the pallet is within the color threshold interval corresponding to the first pole lug, it means that when the first pole lug is segmented by the color threshold interval, part of the pallet area will be considered as the first pole lug, that is, the denoised binary image corresponding to the first pole lug includes not only the first pole lug, but also the pallet. Therefore, it is inaccurate to directly perform contour extraction on the denoised binary image corresponding to the first pole lug. At this time, since the heights of the two pole lugs on the battery cell are consistent, the first pole lug can be located based on the coordinates of the second pole lug.
[0138] At this time, the denoised binary image corresponding to the second pole ear only includes the second pole ear, so the contour extraction can be directly performed to obtain the second pole ear positioning coordinates in the detection station coordinate system.
[0139] Step S2044: determining the second pole lug positioning coordinates of the second pole lug in the detection station coordinate system based on the second pole lug contour.
[0140] Step S2045 : determining the first pole tab positioning coordinates of the first pole tab in the detection station coordinate system based on the second pole tab positioning coordinates and the denoised binary image corresponding to the first pole tab.
[0141] In some embodiments, after determining the positioning coordinates of the second pole ear, the position interval of the pole ear in the first direction of the detection station coordinate system can be determined. Based on the position interval, the values of the pixels in other areas of the denoised binary image corresponding to the first pole ear except for the position interval are inverted and set to 255. At this time, the mislabeled pallet area in the denoised binary image corresponding to the first pole ear can be removed.
[0142] Here, the first direction refers to the direction in which the tab is connected to the large surface.
[0143] In some embodiments, step S2045 may be implemented by steps S11 to S13:
[0144] Step S11 : based on the positioning coordinates of the second pole tab, roughly positioning the first pole tab in a first direction of the denoised binary image corresponding to the first pole tab to obtain a roughly positioned region corresponding to the first pole tab.
[0145] Here, after obtaining the second tab positioning coordinates, the position of the tab of the battery cell in the first direction can be determined, so the first tab can be roughly positioned according to the coordinates in the first direction in the second tab positioning coordinates to obtain the rough positioning area corresponding to the first tab. For example, if the coordinates of the second tab in the first direction are (7, 9), then the rough positioning area is the area with coordinates between 7 and 9 in the first direction.
[0146] In some embodiments, step 11 may be implemented through steps S111 to S112:
[0147] Step S111 : determining two position coordinates of the tab region of the battery cell in the first direction based on the second tab positioning coordinates.
[0148] In some embodiments, under ideal conditions, that is, when there are no errors in the battery cell production process, the heights of the two pole ears of the battery cell in the first direction are the same. Therefore, when the first pole ear is difficult to position in the first direction, the two position coordinates of the pole ear of the battery cell in the first direction can be determined based on the positioning coordinates of the second pole ear in the first direction, and the area between the two position coordinates is the area of the pole ear in the first direction.
[0149] Step S112: In a first direction of the denoised binary image corresponding to the first pole tab, determine the area between the two position coordinates as a coarse positioning area corresponding to the first pole tab.
[0150] Here, the rough positioning area refers to an area between two parallel lines perpendicular to the first direction formed based on two position coordinates. In the first direction, the electrode tab is located in the rough positioning area.
[0151] Step S12: determining the contour position of the first pole tab in the second direction in the rough positioning area; wherein the first direction is perpendicular to the second direction, and the first pole tab is in contact with the tray in the first direction.
[0152] Here, the first pole ear does not contact the tray in the second direction. Therefore, after removing the mislabeled tray area in the first direction, the contour of the first pole ear in the second direction can be directly extracted in the rough positioning area to obtain the contour coordinates of the first pole ear in the second direction, that is, the contour position.
[0153] Step S13: determining the first tab positioning coordinates of the first tab on the detection station coordinate system based on the rough positioning area and the contour position.
[0154] Here, the rough positioning area can obtain the coordinates of the first pole lug in the first direction, and the contour position can obtain the coordinates of the first pole lug in the second direction. Therefore, the first pole lug positioning coordinates of the first pole lug in the detection station coordinate system can be obtained.
[0155] The embodiment of the present application takes into account the impact of aging pallets on image recognition. When the color of the pallet is the same as the color of the tab area, the mislabeled pallet is removed, thereby improving the accuracy of tab positioning.
[0156] In some embodiments, the plurality of regions of the battery cell further comprises a large surface area of the battery cell. Figure 4 This is a schematic diagram of an optional battery cell detection method provided in an embodiment of the present application. Figure 3 ,like Figure 4 As shown, the multiple areas of the battery cell may include at least the large area of the battery cell, and the positioning detection result of the battery cell also includes the large area positioning result. Step S204 may also be implemented through steps S401 to S405:
[0157] Step S401 : based on the large surface color threshold interval corresponding to the large surface area, segment the area in the converted image corresponding to the large surface color threshold interval to obtain a foreground image corresponding to the large surface area.
[0158] In some embodiments, the large surface color threshold interval corresponding to the large surface area can be set by the production line operator based on the performance of the large surface material in the HSV color space. The conversion image is segmented based on the large surface color threshold interval to obtain a foreground image corresponding to the large surface area. The foreground image corresponding to the large surface area only includes the large surface area of the battery cell.
[0159] Step S402: binarize the foreground image corresponding to the large surface area to obtain a large surface binary image corresponding to the large surface area.
[0160] Step S403 , extracting the large surface contour from the large surface binary image to obtain a large surface rough positioning contour; the large surface rough positioning contour is a closed contour obtained by sequentially connecting a plurality of rough positioning contour edges.
[0161] In some embodiments, the pixels in the large surface binary image are divided into two categories, and the boundary between the bright area and the dark area is the large surface rough positioning contour, which may at least include the upper, lower, left, and right edges of the large surface. The large surface rough positioning contour may also be the smallest circumscribed rectangle of the large surface.
[0162] In some embodiments, the large surface can also be roughly positioned by using images of multiple areas of the battery cell acquired by the image acquisition system. That is, when obtaining the rough positioning contour of the large surface, the embodiment of the present application can also be implemented through steps S21 and S22:
[0163] Step S21, binarizing the image to obtain a binary image of the battery cell corresponding to the battery cell.
[0164] In some embodiments, the image is an RGB image acquired by an acquisition system, and the binarization processing may be grayscale processing of the green channel of the RGB image, so that the large surface area in the image is a bright area and the other areas are dark areas, thereby obtaining a binary image of the battery cell corresponding to the battery cell.
[0165] Step S22, extracting the large surface contour of the battery cell binary image to obtain a large surface rough positioning contour; the large surface rough positioning contour is a closed contour obtained by sequentially connecting multiple rough positioning contour edges.
[0166] In some embodiments, the pixels in the battery cell binary image are divided into two categories, and the boundary between the bright area and the dark area is the rough positioning contour of the large surface, and the boundary may at least include the upper, lower, left and right sides of the large surface. The rough positioning contour of the large surface may be the smallest circumscribed rectangle of the large surface.
[0167] In some embodiments, on the premise that the coordinates of the pole lug have been determined, the coordinates of the upper edge of the pole lug in the first direction can be translated downward by the height of the pole lug to obtain the upper contour edge of the large surface; here, since the lower edge of the pole lug is connected to the upper edge of the large surface, the coordinates of the lower edge of the pole lug can also be used as the coordinates of the upper contour of the large surface.
[0168] Step S404: finely position the plurality of coarsely positioned contour edges to obtain finely positioned contour edges corresponding to the coarsely positioned contour edges.
[0169] In some embodiments, step S404 may be implemented by steps S4041 to S4043:
[0170] Step S4041, setting a plurality of positioning rectangles at a plurality of non-overlapping positions on each rough positioning contour edge; wherein the rough positioning contour edge is located inside each positioning rectangle.
[0171] Figure 5 Schematic diagram of large surface precision positioning provided by the embodiment of the present application, such as Figure 5 As shown, a plurality of positioning rectangles 501 are set at a plurality of non-overlapping positioning positions on each rough positioning contour edge. Figure 5 Taking the upper contour edge of the large surface as an example, a plurality of positioning rectangles 501 are set, and the coarse positioning contour edge is located inside each positioning rectangle.
[0172] Step S4042: Based on the multiple positioning rectangles, determine multiple precise positioning coordinates at multiple positions respectively.
[0173] Here, the precise positioning coordinates at each positioning position can be the coordinates of the boundary between the large surface and the background in each positioning rectangle. It can also be the maximum value in each positioning rectangle, such as Figure 5 As shown, it may be the maximum coordinate value of the contour edge in each positioning rectangle 501 in the vertical direction (ie, the first direction).
[0174] Step S4043: Fitting the multiple fine positioning coordinates corresponding to each coarse positioning contour edge respectively to obtain the fine positioning contour edge corresponding to each coarse positioning contour edge.
[0175] Here, after obtaining a plurality of precise positioning coordinates corresponding to each contour edge, the plurality of precise positioning coordinates corresponding to each contour edge can be fitted by the least square method to obtain a precise positioning contour edge corresponding to each coarse positioning contour edge.
[0176] Step S405 , based on a plurality of precisely positioned contour edges, determining the large-surface positioning coordinates of the large-surface region in the detection station coordinate system, and obtaining the large-surface positioning result of the battery cell.
[0177] In some embodiments, since the least squares method will fit a straight line, if one or more of the precise positioning errors occur, the fitted straight line will be significantly different from the actual contour. Therefore, it is necessary to judge the slope of the fitted straight line. If the slope of the fitted straight line meets the conditions, the precise positioning contour edge is used as the positioning coordinate of the large surface. If the conditions are not met, the coarse positioning contour edge is used as the positioning coordinate of the large surface.
[0178] In some embodiments, step S405 may be implemented by steps S4051 and S4052:
[0179] Step S4051, in response to any of the multiple fine positioning contour edges not satisfying the slope condition, determining the large surface positioning coordinates of the large surface area in the detection station coordinate system based on the coarse positioning contour edge and other fine positioning contours corresponding to the any fine positioning contour edge.
[0180] In some embodiments, the slope condition may mean that the slope of the fine positioning contour edge in the first direction should be greater than 200, and the slope of the fine positioning contour edge in the second direction should be less than 0.01. If any of the multiple fine positioning contour edges does not meet the slope condition, the contour edge uses the coordinates of the rough positioning contour edge as the positioning coordinates of the contour edge, thereby determining the large surface positioning coordinates of the large surface area in the detection station coordinate system.
[0181] Step S4052: In response to the multiple precise positioning contour edges all satisfying the slope condition, based on the multiple precise positioning contour edges, determine the large surface positioning coordinates of the large surface area in the detection station coordinate system.
[0182] In some embodiments, if a plurality of precisely positioned contour edges all satisfy the slope condition, the large surface positioning coordinates of the large surface area in the inspection station coordinate system are determined based on the coordinates of the plurality of precisely positioned contour edges.
[0183] In some embodiments, since the large surface of the battery cell occupies a large area on the image and has a clear outline, color conversion may not be performed and the large surface outline can be directly located through the image.
[0184] When positioning the large surface in the embodiment of the present application, each contour edge is precisely positioned after rough positioning through the image, thereby improving the positioning accuracy of the large surface of the battery cell.
[0185] In order to implement the battery cell detection method provided in the embodiment of the present application, the embodiment of the present application also provides a battery cell positioning system. Figure 6 is a schematic diagram of the structure of the battery cell positioning system provided in the embodiment of the present application, such as Figure 6 As shown, the battery cell positioning system includes: an industrial computer 601 and an image acquisition system 602 .
[0186] The industrial computer 601, in response to the battery cell arriving at the detection station, sends an image acquisition signal to the image acquisition system 602; the image acquisition system 602 is used to capture the image of the battery cell in response to the image acquisition signal, obtain an image including at least multiple areas of the battery cell, and send the image to the industrial computer 601; the industrial computer 601 is also used to obtain the image, perform color conversion on the image, and obtain a converted image of the battery cell; based on multiple color threshold intervals, multiple areas of the battery cell in the converted image are respectively located to obtain the positioning detection result of the battery cell. The tab positioning result is uploaded to the Manufacturing Execution System (MES).
[0187] In some embodiments, the image acquisition system 602 is fixed on the detection station and may include a light source and a camera. The camera may be fixed on the detection station through a locking structure to acquire images of the battery cell and obtain an image; the light source is fixed on the detection station, located between the camera and the battery cell, to provide light for the camera.
[0188] In some embodiments, the light source may include an axially arranged dome light source and a coaxial light source to achieve better lighting and make the image clearer.
[0189] In the embodiment of the present application, in order to prevent the light source from causing harm to human eyes and the camera from being contaminated, a protective cover may be added to the outside of the camera.
[0190] Next, an application of a battery cell detection method in a practical scenario is provided.
[0191] Based on the related art, the position of the battery cell on the tray will be offset, so using the preset position of the lug detection frame will cause large errors in the positioning coordinates of the lug, which brings the problem of insufficient robustness. The embodiment of the present application aims at the difference in the HSV color space after the copper lug and the aluminum lug in the bare battery cell are imaged, and the areas of the copper lug and the aluminum lug are respectively extracted through different HSV threshold intervals, and the background area noise is eliminated through filtering and denoising, and then the copper lug and the aluminum lug are located. It is also possible to locate the large surface of the bare battery cell.
[0192] Figure 7 : is a schematic diagram of the process of positioning the bare cell tab provided in an embodiment of the present application, Figure 8 : is a schematic diagram of the image flow of positioning the bare cell tab provided in the embodiment of the present application, such as Figure 7 and Figure 8 As shown, the bare cell tab positioning can be achieved through steps S701 to S713:
[0193] Step S701, obtaining a large-surface image of a bare cell.
[0194] In the embodiment of the present application, the industrial computer obtains the large-surface image 801 (ie, image) of the bare battery cell based on the image acquisition device at the detection station.
[0195] Step S702: extracting a copper tab mask image based on a first HSV threshold value interval.
[0196] Here, the large surface image of the bare cell may refer to an RGB image, and the RGB image may be converted into an HSV color space to obtain an HSV image, and the HSV image may be segmented based on the first HSV threshold interval to obtain a copper tab mask image 802, such as Figure 8 As shown, based on the first HSV threshold interval, the foreground image of the copper tab is extracted. Here, the first HSV threshold interval may refer to h being between 0-113, s being between 53-255, and v being between 137-255.
[0197] Step S703: extracting the copper tab foreground image from the large surface image of the bare cell based on the copper tab mask image.
[0198] In the embodiment of the present application, the copper tab area is matched in the bare cell large surface image 801 based on the copper tab mask image 802, and the copper tab in the bare cell large surface image 801 is segmented to obtain the copper tab foreground image 803.
[0199] Step S704: convert the copper tab foreground image into a grayscale image.
[0200] In some embodiments, the pixels in the copper tab foreground image may be binarized to convert the copper tab foreground image into a grayscale image.
[0201] Step S705: filter and denoise the grayscale image.
[0202] In the embodiment of the present application, the grayscale image can be denoised by corrosion and dilation operations to obtain a first denoised grayscale image 804. Here, the role of corrosion is to eliminate the boundary points of the copper pole ear and eliminate the noise points; the role of dilation is to merge the background points in contact with the copper pole ear into the copper pole ear and fill the void in the copper pole ear.
[0203] Step S706: Obtain the copper tab positioning result based on the denoised grayscale image.
[0204] In the embodiment of the present application, the minimum circumscribed rectangle of the copper tab can be obtained according to the grayscale image after denoising, and the positioning result of the copper tab on the image can be obtained. The contour coordinates are (x cu ,y cu , w cu ,h cu ), where x cu and cu is the coordinate value of the lower left corner of the minimum bounding rectangle, w cu is the width of the minimum enclosing rectangle, h cu is the height of the minimum enclosing rectangle.
[0205] Step S707: extracting the aluminum tab mask image based on the second HSV threshold range.
[0206] In the embodiment of the present application, the HSV image is segmented based on the second HSV threshold interval to obtain the aluminum tab mask image 805, such as Figure 8 As shown, based on the second HSV threshold interval, the foreground image of the aluminum tab is extracted. Here, the second HSV threshold interval may refer to h being between 0-66, s being between 36-107, and v being between 29-73.
[0207] Step S708: extracting the aluminum tab foreground image from the original image based on the aluminum tab mask image.
[0208] In the embodiment of the present application, the aluminum tab region is matched in the bare cell large surface image 801 based on the aluminum tab mask image 805, and the aluminum tab in the bare cell large surface image 801 is segmented to obtain the aluminum tab foreground image 806.
[0209] Step S709: convert the aluminum tab foreground image into a grayscale image, and invert part of the image.
[0210] In the embodiment of the present application, the pixels in the aluminum tab foreground image may be binarized to convert the aluminum tab foreground image into a grayscale image.
[0211] Here, if Figure 8As shown in the aluminum tab foreground image 806, after the tray is aged or used for a long time, the material of the bare battery cell will remain on the tray, causing the color of part of the tray in the image to be the same as the tab. Therefore, it is necessary to invert the grayscale value of the tray position in the grayscale image to obtain the inverted grayscale image 807.
[0212] Step S710: performing bitwise operation and filtering denoising on the inverted grayscale image.
[0213] In the embodiment of the present application, the inverted grayscale image can be denoised by bitwise denoising and erosion and dilation operations to obtain a denoised second grayscale image 808.
[0214] Step S711: based on the denoised grayscale image, obtain the initial positioning result of the aluminum tab.
[0215] In the embodiment of the present application, based on the denoised grayscale image, the positioning result of the minimum circumscribed rectangular frame of the aluminum tab can be obtained, and the contour coordinates are (x al ,y al , w al ,h al ), where x al and al is the coordinate value of the lower left corner of the minimum enclosing rectangle, w al is the width of the minimum enclosing rectangle, h al is the height of the minimum enclosing rectangle.
[0216] Step S712: based on the initial positioning result of the aluminum tab and the positioning result of the copper tab, obtain the positioning result of the aluminum tab.
[0217] In the embodiment of the present application, as shown in the second denoised grayscale image 808 after denoising, the area on the tray used to fix the aluminum lug is the same color as the aluminum lug, which may cause inaccurate positioning of the aluminum lug in the y direction. However, due to the special color of the copper lug, the tray will not be identified as the lug when the copper lug is identified. Therefore, the y coordinate of the copper lug will not be affected by the tray. In the production process of the bare cell, the size of the cathode lug and the anode lug is the same. Therefore, in order to make the identification of the aluminum lug more accurate, the y coordinate y in the positioning result of the copper lug can be used. cu Position the aluminum tab and obtain the coordinates of the minimum circumscribed rectangular frame of the aluminum tab (point (x al ,y cu ), point(x al +w al ,y cu +h al )).
[0218] Step S713, outputting the polarity and positioning results of the copper and aluminum tabs.
[0219] In an embodiment of the present application, before locating the tabs of the bare battery cell, it is known that the tabs of the bare battery cell are copper and aluminum. Therefore, after identifying copper and aluminum through different threshold intervals, the polarity of the bare battery cell can be determined, that is, copper is the cathode and aluminum is the anode.
[0220] After the positioning results of the copper tab and the aluminum tab are obtained, the positioning frames and polarities of the copper tab and the aluminum tab can be displayed based on the large surface image 801 of the bare battery cell, such as Figure 8 The positioning result is shown in Figure 809.
[0221] The present application embodiment further provides a method for positioning a large surface of a bare cell. Fig. 9 : is a schematic diagram of the process of large-surface positioning of a bare cell provided in an embodiment of the present application, such as Fig. 9 As shown, the large surface positioning of the bare cell can be achieved through steps S901 to S911:
[0222] Step S901, obtaining a large-surface image of a bare cell.
[0223] In some embodiments, the industrial computer obtains a large-surface image (ie, image) of the bare battery cell, where the large-surface image includes not only the large-surface area but also the tab area.
[0224] Step S902: convert the large surface image into a grayscale image, perform threshold segmentation and binarization processing, and obtain a binary image.
[0225] In an embodiment of the present application, the large surface image can be converted into a grayscale image, and the large surface segmentation and binarization processing can be performed to obtain a binary image. In the binary image, the pixel value of the battery cell area is 255, and the pixel value of the background is 0.
[0226] Step S903: based on the binary image, extract the foreground circumscribed rectangle as the rough location of the large surface.
[0227] In some embodiments, the circumscribed rectangle of the cell area is used as the large surface for rough positioning, and the roughly positioned circumscribed rectangle includes the tabs and the large surface.
[0228] Step S904, the rough positioning upper edge is moved down by the height of the tab to obtain a rough positioning upper edge of the large surface edge.
[0229] Here, under the premise that the tab has been positioned, the tab height can be moved down from the rough positioning upper edge to obtain a large surface edge rough positioning upper edge.
[0230] Step S905: Take multiple rectangles near the upper edge of the rough positioning and calculate the maximum vertical gradient point.
[0231] In some embodiments, Fig.10 is a schematic diagram of the structure of the upper edge positioning of the large surface of the battery cell provided in the embodiment of the present application, such as Fig.10 As shown, multiple upper edge positioning rectangles 101 are taken for upper edge rough positioning, and the maximum coordinate of the large surface contour in each upper edge positioning rectangle 101 in the vertical direction is calculated.
[0232] Step S906: Use the least square method to obtain the precise location of the upper edge, and the lower edge is the lower edge of the image.
[0233] Based on the positioning coordinates determined by multiple upper edge positioning rectangles, the upper edge precise positioning is obtained by fitting through the least squares method, such as Fig.10 As shown, the image does not capture the entire area of the battery cell. Fig.10 , the lower edge of the large surface is the lower edge of the image. Here, if the image captures the lower edge of the large surface, the lower edge of the large surface is located by the method of first coarse positioning and then fine positioning in the above-mentioned upper edge and left and right edges.
[0234] Step S907: Roughly locate the left and right edges, take multiple rectangles, and calculate the maximum horizontal gradient point.
[0235] Fig.11 : is a schematic diagram of the structure of the left edge positioning of the large surface of the battery cell provided in the embodiment of the present application, such as Fig.11 As shown, multiple left edge positioning rectangles 102 are taken for left edge rough positioning, and the maximum coordinate of the large surface contour in each left edge positioning rectangle 102 in the horizontal direction is calculated, that is, the maximum horizontal gradient point of each left edge positioning rectangle.
[0236] Fig.12 : is a schematic diagram of the structure of positioning the right edge of the large surface of the battery cell provided in an embodiment of the present application, such as Fig.12 As shown, multiple right edge positioning rectangles 103 are taken for right edge rough positioning, and the maximum coordinate of the large surface contour in each right edge positioning rectangle 103 in the horizontal direction is calculated, that is, the maximum horizontal gradient point of each right edge positioning rectangle.
[0237] Step S908: Least squares method is used to obtain precise positioning of the left and right sides.
[0238] Based on the positioning coordinates of multiple left edge positioning rectangles and right edge positioning rectangles, fitting is performed through the least square method to obtain the left edge precise positioning and the right edge precise positioning.
[0239] S909: Whether the precise positioning slope satisfies the slope condition.
[0240] In some embodiments, the first precise positioning line is required to perform a slope error prevention judgment, the slopes of the vertical left and right precise positioning edges need to be greater than a threshold of 200, and the slopes of the horizontal precise positioning edges need to be less than a threshold of 0.01. If the error prevention is met, precise positioning is used and step S910 is executed, otherwise coarse positioning is used and step S911 is executed.
[0241] Step S910: output precise positioning results.
[0242] Step S911, output the coarse positioning result.
[0243] The embodiment of the present application aims at the difference between the copper pole lug and the aluminum pole lug in the HSV color space after imaging, and uses two sets of HSV threshold intervals to extract the areas of the copper pole lug and the aluminum pole lug respectively, and eliminates the background area noise through filtering and denoising. The present application solves the problem of difficult-to-handle noise when extracting the aluminum pole lug area using the HSV threshold interval by borrowing the positioning information of the copper pole lug, that is, using the regional y coordinate of the copper pole lug as the regional y coordinate of the aluminum pole lug. At the same time, for the bare cell sample, it is possible to accurately extract the lug area, determine the polarity of the lug, and complete the large-surface positioning of the bare cell.
[0244] It should be understood that "one embodiment" or "an embodiment" mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the size of the serial number of each step / process mentioned above does not mean the order of execution, and the execution order of each step / process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application. The serial numbers of the embodiments of the present application mentioned above are for description only and do not represent the advantages and disadvantages of the embodiments.
[0245] The present application uses descriptions such as "upper", "lower", "top", "bottom", "front", "back", "inside" and "outside" to indicate directions or positional relationships. This is only for the convenience of describing the present application, and does not indicate or imply that the device referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, it should not be understood as limiting the scope of protection of the present application.
[0246] In the description of this application, it should also be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be directly connected or indirectly connected through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to the specific circumstances.
[0247] It should be noted that, in this application, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.
[0248] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.
[0249] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, the functional units in the embodiments of the present application may be all integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.
[0250] The above are only implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed in the present application should be covered within the protection scope of the present application.
Claims
1. A battery cell detection method, characterized in that: An industrial computer used in a battery cell positioning system; the battery cell detection method comprises: In response to the battery cell arriving at the inspection station, acquiring an image including multiple regions of the battery cell acquired by an image acquisition system; the multiple regions at least include a large surface area of the battery cell; Performing color conversion on the image to obtain a converted image of the battery cell; Based on multiple color threshold intervals, multiple areas of the battery cell in the converted image are located respectively to obtain positioning detection results of the battery cell; wherein the color threshold interval corresponding to each area is determined based on the material of each area, and the positioning detection results at least include large-surface positioning results; The method of locating multiple areas of the battery cell in the conversion image based on multiple color threshold intervals to obtain the positioning detection result of the battery cell includes: Based on the large surface color threshold interval corresponding to the large surface area, segmenting the area corresponding to the large surface color threshold interval in the conversion image to obtain a foreground image corresponding to the large surface area; Binarizing the foreground image corresponding to the large surface area to obtain a large surface binary image corresponding to the large surface area; Extracting the large-surface contour from the large-surface binary image to obtain a large-surface rough positioning contour; the large-surface rough positioning contour is a closed contour obtained by sequentially connecting a plurality of rough positioning contour edges; Precisely positioning the plurality of coarsely positioned contour edges to obtain finely positioned contour edges corresponding to the coarsely positioned contour edges; Based on a plurality of precisely positioned contour edges, the large-surface positioning coordinates of the large-surface area in the detection station coordinate system are determined to obtain the large-surface positioning result of the battery cell.
2. The battery cell detection method according to claim 1, characterized in that: The multiple regions at least include a tab region of the battery cell, and the positioning detection result at least includes a tab positioning result; The method of locating multiple areas of the battery cell in the conversion image based on multiple color threshold intervals to obtain the positioning detection result of the battery cell includes: Based on a plurality of color threshold intervals, different tab regions of the battery cell corresponding to each color threshold interval in the conversion image are segmented to obtain foreground images corresponding to each tab region; Binarize each foreground image separately to obtain a binary image corresponding to each area; De-noising each binary image respectively to obtain a denoised binary image corresponding to each region; The contours of the corresponding areas in each denoised binary image are extracted respectively to obtain the positioning coordinates of each area in the detection station coordinate system; The positioning coordinates of each area are determined as the tab positioning results of the battery cell.
3. The battery cell detection method according to claim 2, characterized in that: The method of segmenting different tab regions of the battery cell corresponding to each color threshold interval in the conversion image based on multiple color threshold intervals to obtain foreground images corresponding to each tab region includes: Based on each color threshold interval, different tab regions of the battery cell corresponding to each color threshold interval in the conversion image are segmented respectively to obtain mask regions corresponding to each color threshold interval on the conversion image; The area corresponding to each mask area on the image is extracted to obtain a foreground image of the area corresponding to each mask area.
4. The battery cell detection method according to claim 2, characterized in that: The multiple regions include at least two tab regions of the battery cell; the battery cell is fixed on the inspection station by a tray; The contour extraction of the corresponding areas in each denoised binary image is performed to obtain the positioning coordinates of each area in the detection station coordinate system, including: In response to the color value of the pallet in the conversion image not being within the color threshold interval corresponding to the two tab regions, performing tab contour extraction on the denoised binary images corresponding to the two tab regions to obtain two tab contours; Based on the two tab contours, the tab positioning coordinates of the two tab regions on the detection station coordinate system are determined.
5. The battery cell detection method according to claim 2, characterized in that: The multiple regions include at least two tab regions of the battery cell, and the two tab regions include a first tab and a second tab; the battery cell is fixed on the inspection station by a tray; The contour extraction of the corresponding areas in each denoised binary image is performed to obtain the positioning coordinates of each area in the detection station coordinate system, including: In response to the color value of the tray in the conversion image being in the color threshold interval corresponding to the first pole lug, performing pole lug contour extraction on the denoised binary image corresponding to the second pole lug to obtain a second pole lug contour; Based on the second pole lug profile, determining the second pole lug positioning coordinates of the second pole lug in the detection station coordinate system; Based on the second pole lug positioning coordinates and the denoised binary image corresponding to the first pole lug, the first pole lug positioning coordinates of the first pole lug in the detection station coordinate system are determined.
6. The battery cell detection method according to claim 5, characterized in that: The determining the first pole lug positioning coordinates of the first pole lug in the detection station coordinate system based on the second pole lug positioning coordinates and the denoised binary image corresponding to the first pole lug includes: Based on the positioning coordinates of the second pole tab, roughly positioning the first pole tab in a first direction of the denoised binary image corresponding to the first pole tab to obtain a rough positioning area corresponding to the first pole tab; In the rough positioning area, determining the contour position of the first pole tab in the second direction; wherein the first direction is perpendicular to the second direction, and the first pole tab contacts the tray in the first direction; Based on the coarse positioning area and the contour position, a first pole tab positioning coordinate of the first pole tab on the detection station coordinate system is determined.
7. The battery cell detection method according to claim 6, characterized in that: The method of roughly locating the first pole lug in a first direction of the denoised binary image corresponding to the first pole lug based on the positioning coordinates of the second pole lug to obtain a rough positioning area corresponding to the first pole lug includes: Based on the second tab positioning coordinates, determining two position coordinates of the tab region of the battery cell in the first direction; In a first direction of the denoised binary image corresponding to the first pole tab, an area between the two position coordinates is determined as a coarse positioning area corresponding to the first pole tab.
8. The battery cell detection method according to any one of claims 1 to 7, characterized in that: The battery cell detection method further comprises: Binarizing the image to obtain a binary image of the battery cell corresponding to the battery cell; The large surface contour is extracted from the battery cell binary image to obtain the large surface rough positioning contour.
9. The battery cell detection method according to claim 8, characterized in that: The step of finely positioning the plurality of coarsely positioned contour edges to obtain finely positioned contour edges corresponding to each coarsely positioned contour edge includes: A plurality of positioning rectangles are arranged at a plurality of non-overlapping positions on each rough positioning contour edge; wherein the rough positioning contour edge is located inside each positioning rectangle; Based on the multiple positioning rectangles, respectively determine multiple precise positioning coordinates at multiple positions; The multiple fine positioning coordinates corresponding to each coarse positioning contour edge are fitted respectively to obtain the fine positioning contour edge corresponding to each coarse positioning contour edge.
10. The battery cell detection method according to any one of claims 1 to 7, characterized in that: The determining of the large surface positioning coordinates of the large surface area in the detection station coordinate system based on the multiple precise positioning contour edges includes: In response to any one of the multiple fine positioning contour edges not satisfying a slope condition, determining a large surface positioning coordinate of the large surface area in a detection station coordinate system based on a coarse positioning contour edge and other fine positioning contours corresponding to the any one of the fine positioning contour edges; In response to the plurality of precisely positioned contour edges all satisfying a slope condition, the large surface positioning coordinates of the large surface area in the inspection station coordinate system are determined based on the plurality of precisely positioned contour edges.
11. The battery cell detection method according to any one of claims 1 to 7, characterized in that: The battery cell detection method further comprises: Obtaining information of the battery cell; Based on the information of the battery cell, determining the material information respectively corresponding to the multiple regions of the battery cell; The color threshold interval corresponding to each area is determined based on material information corresponding to each area of the multiple areas.
12. The battery cell detection method according to claim 11, characterized in that: The multiple regions include at least two tab regions of the battery cell; and the battery cell detection method further includes: Determining polarity information of the two tab regions based on material information corresponding to the two tab regions respectively; Based on the tab positioning coordinates of the two tab regions, polarity information of the two tab regions are respectively displayed on the corresponding tab regions on the conversion image.
13. A battery cell detection system, characterized in that: The battery cell detection system comprises: The industrial computer sends an image acquisition signal to the image acquisition system in response to the battery cell arriving at the inspection station; The image acquisition system is used to acquire an image of the battery cell in response to the image acquisition signal, obtain an image including at least multiple regions of the battery cell, and send the image to the industrial computer; the multiple regions include at least a large surface area of the battery cell; The industrial computer is further used to acquire the image, perform color conversion on the image, and obtain a converted image of the battery cell; based on multiple color threshold intervals, respectively locate multiple areas of the battery cell in the converted image to obtain a positioning detection result of the battery cell; wherein the color threshold interval corresponding to each area is determined based on the material of each area, and the positioning detection result includes at least a large-surface positioning result; The industrial computer is also used to segment the area corresponding to the large surface color threshold interval in the conversion image based on the large surface color threshold interval corresponding to the large surface area, so as to obtain a foreground image corresponding to the large surface area; binarize the foreground image corresponding to the large surface area, so as to obtain a large surface binary image corresponding to the large surface area; extract the large surface contour from the large surface binary image, so as to obtain a large surface rough positioning contour; the large surface rough positioning contour is a closed contour obtained by sequentially connecting a plurality of rough positioning contour edges; finely position the plurality of rough positioning contour edges, so as to obtain fine positioning contour edges corresponding to each rough positioning contour edge; based on the plurality of fine positioning contour edges, determine the large surface positioning coordinates of the large surface area on the detection station coordinate system, so as to obtain the large surface positioning result of the battery cell.
