Battery cell detection method, electronic equipment and detection system

Abstract

The invention relates to the technical field of battery detection, and particularly provides a battery cell detection method, electronic equipment and a detection system.The method can comprise the steps that a target battery cell image is recognized, and a region of interest is determined; wherein the region of interest comprises a hot pressing mark of the target battery cell and an edge of the target battery cell; performing edge detection on the region of interest to determine a hot press mark and a cell edge in the region of interest; and calculating the hot-pressing mark and the edge of the battery cell so as to determine hot-pressing state data.

Description

Technical Field

[0001] The present application relates to the technical field of battery detection, and in particular to a battery cell detection method, electronic equipment and a detection system. Background Art

[0002] Hot pressing is one of the processes in the battery cell production process. After hot pressing, two indentations will be left on the bare battery cell. The distance between the two indentations and the nearest corner edge on one side is defined as the bare battery cell avoidance distance. The bare battery cell avoidance distance directly affects whether the battery cell is qualified. However, at present, the bare battery cell avoidance distance is usually not identified, or it is simply checked manually. Summary of the invention

[0003] The purpose of the present application is to provide a battery cell detection method, electronic equipment and detection system, which can improve the efficiency of detecting whether the battery cells are qualified or not.

[0004] In a first aspect, the present invention provides a battery cell detection method, comprising: identifying a target battery cell image to determine a region of interest; wherein the region of interest includes a thermal indentation of the target battery cell and an edge of the target battery cell; performing edge detection on the region of interest to determine the thermal indentation and the battery cell edge in the region of interest; and calculating the thermal indentation and the battery cell edge to determine thermal pressure status data.

[0005] In the above-mentioned embodiment, the battery cells after the hot pressing process are inspected by image recognition. Compared with the manual inspection method, the inspection efficiency and accuracy of the method provided by the present application can be higher, and the inspection standards can be more unified.

[0006] In an optional embodiment, the thermal indentation and the edge are calculated to determine the thermal pressing state data, including: drawing edge lines of the thermal indentation and the edge of the battery cell in the area of ​​interest to obtain thermal indentation lines and edge lines; and determining the thermal pressing state data based on the thermal indentation lines and the edge lines.

[0007] In the above implementation, the region of interest is first extracted, and the hot pressing state is identified based on the region of interest, so that the traces of hot pressing can be located more quickly, and the detection efficiency and accuracy of the hot pressing state can be further improved.

[0008] In an optional embodiment, the hot pressing state data includes a clearance distance formed between the hot indentation and the edge of the battery cell; determining the hot pressing state data based on the hot indentation line and the edge line includes: traversing the pixel points on one of the hot indentation line and the edge line, and calculating the distance from each pixel point to the other line; and determining the clearance distance formed between the hot indentation and the edge of the battery cell in the area of ​​interest from the distance from each pixel point to the other line.

[0009] In an optional embodiment, the hot pressing state data includes an offset angle formed by the hot indentation and the edge of the battery cell; determining the hot pressing state data based on the hot indentation line and the edge line includes: calculating the angle formed by the hot indentation line and the edge line; wherein the angle is used as the offset angle formed by the hot indentation in the area of ​​interest and the edge of the battery cell.

[0010] In an optional embodiment, the identifying the target battery cell image and determining the region of interest includes: matching the target battery cell image with a preset template image to determine the battery cell region image in the target battery cell image; and extracting the region of interest from the battery cell region image.

[0011] In an optional embodiment, the target cell image is matched with a preset template image to determine the cell region image in the target cell image, including: calculating the similarity between the preset template image and each region image in the target cell image; and screening out the cell region images in the target cell image based on the similarity between each region image and the preset template image.

[0012] In an optional embodiment, the calculating the similarity between the preset template image and the regional image in the target battery cell image includes: selecting a first regional image that matches the size of the preset template image from the target battery cell image frame; calculating the similarity between the first regional image and the preset template image; wherein the first regional image is any one of the regional images included in the target battery cell image.

[0013] In an optional embodiment, the step of selecting a first area image that matches the size of the preset template image from the target battery cell image frame includes: selecting a first area image that matches the size of the preset template image from the target battery cell image frame according to a set rule; wherein the set rule includes: from an initial position of the target battery cell image, sequentially selecting area images along a first direction and a second direction of the target battery cell image; wherein the distance between two adjacent movements of the selected area images is a set distance.

[0014] In an optional embodiment, extracting the region of interest from the battery cell area image includes: constructing a coordinate system in the battery cell area image; and selecting the region of interest in the battery cell area image at specified coordinates of the coordinate system using an interest box.

[0015] In an optional embodiment, the method further includes: comparing the hot pressing state data with a hot pressing standard to determine whether the target battery cell is qualified for hot pressing; if the target battery cell is not qualified for hot pressing, controlling the target battery cell to be moved to a recycling location.

[0016] In an optional embodiment, the method further includes: after the target battery cell is hot-pressed, controlling a moving component to move the target battery cell to a target position; controlling a target light source to start, and capturing an image of the target battery cell under the illumination of the target light source.

[0017] In an optional implementation, controlling the target light source to start includes: upon detecting that a photoelectric switch at the target position is blocked, controlling the target light source to start.

[0018] In an optional embodiment, the target battery cell image includes a first battery cell image and a second battery cell image; the target position includes a first target position and a second target position; the target light source includes a first light source and a second light source; the controlling the moving component to move the target battery cell to the target position, and the controlling the target light source to start, and collecting the target battery cell image under the illumination of the target light source, include: controlling the moving component to move the target battery cell to the first target position, controlling the first light source to start, and collecting the first battery cell image under the illumination of the target light source; controlling the moving component to move the target battery cell to the second target position, controlling the second light source to start, and collecting the second battery cell image under the illumination of the target light source.

[0019] In the above embodiment, when obtaining the battery cell image, lighting can be performed from two different positions. By collecting the battery cell image based on lighting, the obtained battery cell image can better present the information of different parts of the battery cell, and the recognition result based on the image can also be more reliable.

[0020] In a second aspect, the present invention provides an electronic device, comprising: a processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the machine-readable instructions are executed by the processor to perform the steps of the method described in any one of the aforementioned implementations.

[0021] In a third aspect, the present invention provides a detection system, comprising: an electronic device and an acquisition device; the acquisition device is used to acquire images of target battery cells, and the electronic device is used to process the images acquired by the acquisition device so as to execute the steps of the method described in any one of the aforementioned embodiments.

[0022] In an optional embodiment, it also includes: a light source for illuminating a target position of the acquisition device; a photoelectric switch for controlling the on and off of the light source; and the electronic device is also used to acquire a target battery cell image at the target position when the light source is started.

[0023] In an optional embodiment, the light source includes a first light source and a second light source, and the first light source and the second light source are arranged at different positions.

[0024] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method described in any one of the aforementioned embodiments are executed.

[0025] In a fifth aspect, the present invention provides a computer program product, wherein the computer program product comprises a computer program, and when the computer program is executed by a processor, the method described in any one of the aforementioned embodiments is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0027] Figure 1 A schematic diagram of the interaction of various devices in the detection system provided in an embodiment of the present application; Figure 2 A schematic diagram of an application scenario of the battery cell detection method provided in an embodiment of the present application; Figure 3 A block diagram of an electronic device provided in an embodiment of the present application; Figure 4 A flow chart of a battery cell detection method provided in an embodiment of the present application; Figure 5 A schematic diagram of a region of interest of a target cell image in an example provided in an embodiment of the present application; Figure 6 A schematic diagram of another state of a target cell image provided by an embodiment of the present application; Figure 7A schematic diagram of a cell area image provided in an embodiment of the present application; Figure 8 A schematic diagram of marking hot indentation lines and edge lines on an area of ​​interest provided in an embodiment of the present application.

[0028] Icons: 110 - electronic device; 111 - memory; 113 - processor; 120 - acquisition device; 131 - first light source; 132 - second light source; 140 - transmission mechanism; 150 - moving component; P1 - first target position; P2 - second target position. DETAILED DESCRIPTION

[0029] The technical solutions in the embodiments of the present application will be described below in conjunction with the accompanying drawings in the embodiments of the present application.

[0030] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0031] Hot pressing is one of the processes in the production of battery cells. To prevent the hot pressing process from damaging the corners of bare battery cells and causing failures such as pole piece fracturing, it is necessary to pad the lower pressing plate of the hot press with clear paper (for example, Teflon). After hot pressing, two indentations will be left at the position where the bare battery cells are in contact with the clear paper. The distance between the indentation and the edge of the battery cell close to it is defined as the bare battery cell avoidance distance, and the bare battery cell avoidance distance affects the quality of the battery cell.

[0032] There may be a certain amount of offset in the position of the battery cell when it is being loaded. If the offset of the loading position is not corrected, the air avoidance distance of the bare battery cell may also change. In addition, the cover paper is a consumable item. After a period of use, the cover paper needs to be replaced. Due to the influence of the replacement of the cover paper, the air avoidance distance of the bare battery cell may also change. In the above two situations, the pole pieces at the corners of the bare battery cell may be fractured after hot pressing, and ultimately the product will be unqualified. Therefore, in order to improve the qualified rate of battery cell products, it is necessary to detect the air avoidance distance of the bare battery cell after hot pressing.

[0033] Based on the above research, the embodiments of the present application can provide a battery cell detection method, electronic device and detection system, which can detect the air avoidance distance of bare battery cells through image recognition, thereby improving the qualified rate of battery cells obtained by the battery cell manufacturing process. The battery cell detection method, electronic device and detection system provided by the embodiments of the present application are introduced below through some embodiments.

[0034] To facilitate understanding of this embodiment, the operating environment of a detection system disclosed in an embodiment of the present application is first introduced.

[0035] like Figure 1 , which is a schematic diagram of the interaction of various devices in the detection system provided in an embodiment of the present application. The electronic device 110 can be connected to one or more acquisition devices 120 to obtain image data collected by the acquisition device 120. The electronic device 110 can perform recognition based on the obtained image data to determine the hot pressing state data.

[0036] The electronic device 110 may be a programmable logic controller (PLC). It may use a programmable memory to store instructions for executing logic operations and other operations of the battery cell detection method, and control various types of mechanical devices involved in the battery cell detection method, such as the acquisition device 120, through digital or analog input and output.

[0037] In order to make the collected image more prominent in the features to be detected, the detection system may further include a light source and a photoelectric switch.

[0038] The light source may be used to illuminate a target position, which may be an area where the target cell is located when the target cell image is collected.

[0039] The photoelectric switch is used to control the on and off of the light source. The electronic device 110 can also be used to collect the target cell image at the target position when the light source is started.

[0040] Exemplarily, the target position may be an area where the target battery cell is placed. Exemplarily, the target position may also be an area specially set up for photographing the placement of the target battery cell.

[0041] Considering that the cell is moved at a high speed in the conventional cell manufacturing process, if the image is taken directly while the cell is being transported by the transport mechanism 140, the image may not be clear. If the transport mechanism 140 is paused for shooting, the efficiency of the cell manufacturing process may be affected. Based on this, the embodiment of the present application provides another shooting method, which is to grab the cell and move it to the target position, and then shoot it.

[0042] Exemplarily, the photoelectric switch of the light source may be disposed at a position between the conveying mechanism 140 and the target position, and the photoelectric switch may be triggered during the process of grabbing the target battery cell from the target position and moving it to the target position to start the light source.

[0043] Optionally, a moving component 150 for grabbing a target cell to be photographed may be provided, and the moving component 150 may be a clamp. The target cell is moved from the conveying mechanism 140 to a target position by the clamp, and after the acquisition device 120 photographs, the clamp moves the target cell from the target position to the conveying mechanism 140.

[0044] In one example, after the gripper moves the target battery cell from the conveying mechanism 140 to the target position, it may stay for a specified time, and then move the target battery cell from the target position to the conveying mechanism 140. The specified time may be a preset time, for example, the specified time may be 0.5s, 1s, 2s, etc.

[0045] Exemplarily, the acquisition device 120 may be arranged below the target position, and the acquisition device 120 may acquire the image of the target cell after the target cell moves to the target position and the light source is started.

[0046] Optionally, the light source may be a bar-shaped light source, which may better illuminate the hot pressing marks on the target battery cell.

[0047] Considering that heat pressing usually produces more than one indentation, in order to better present the indentations in the image, two shots can be taken at different angles to better capture the indentations in different positions.

[0048] In order to better capture the indentation on the target cell, such as Figure 2 As shown, the light source includes a first light source 131 and a second light source 132 , and the first light source 131 and the second light source 132 are arranged at different positions.

[0049] Through the illumination of the first light source 131 , one of the indentations on the target battery cell can be more clearly presented. Through the illumination of the second light source 132 , another indentation on the target battery cell can be more clearly presented.

[0050] The target position may include a first target position P1 and a second target position P2 , wherein the first light source 131 is used to illuminate the first target position P1 , and the second light source 132 may be used to illuminate the second target position P2 .

[0051] In one example, after the gripper moves the target cell from the conveying mechanism 140 to the first target position P1, it may stay for a specified time to capture an image of the target cell, and then move the target cell from the first target position P1 to the conveying mechanism 140. After the gripper moves the target cell from the conveying mechanism 140 to the second target position P2, it may stay for a specified time to capture an image of the target cell, and then move the target cell from the second target position P2 to the conveying mechanism 140.

[0052] In one instance, after the clamp moves the target battery cell from the conveying mechanism 140 to the first target position P1, it can stay for a specified time to capture an image of the target battery cell, and then after moving the target battery cell from the first target position to the second target position P2, it can stay for a specified time to capture an image of the target battery cell, and then move the target battery cell from the second target position P2 to the conveying mechanism 140.

[0053] like Figure 3 , which is a block diagram of an electronic device. The electronic device 110 may include a memory 111 and a processor 113. A person skilled in the art may understand that Figure 3 The structure shown is only for illustration and does not limit the structure of the electronic device 110. For example, the electronic device 110 may also include Figure 3 More or fewer components as shown, or with Figure 3 Different configurations are shown.

[0054] The memory 111 and the processor 113 are electrically connected to each other directly or indirectly to achieve data transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses or signal lines. The processor 113 is used to execute the executable module stored in the memory.

[0055] The memory 111 may be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), etc. The memory 111 is used to store programs, and the processor 113 executes the program after receiving an execution instruction. The method executed by the electronic device 110 defined by the process disclosed in any embodiment of the present application can be applied to the processor 113, or implemented by the processor 113.

[0056] The processor 113 may be an integrated circuit chip with signal processing capability. The processor 113 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps, and logic block diagrams disclosed in the embodiments of the present application may be implemented or executed. The general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0057] The electronic device 110 in this embodiment can be used to execute each step in each method provided in the embodiments of the present application. The implementation process of the battery cell detection method is described in detail below through several embodiments.

[0058] See also Figure 4 , is a flow chart of a battery cell detection method provided in an embodiment of the present application. The battery cell detection method provided in an embodiment of the present application can be applied to an electronic device, and the steps in the battery cell detection method are performed by the electronic device.

[0059] The following will Figure 4 The specific process shown is described in detail.

[0060] Step 220 , identifying the target battery cell image and determining a region of interest.

[0061] The region of interest includes the thermal indentation of the target battery cell and the edge of the target battery cell.

[0062] The thermal indentation is an indentation left at the position where the target battery cell contacts the transparent sheet after the target battery cell undergoes a thermal pressing process. The edge of the target battery cell included in the region of interest may be an edge close to the thermal indentation.

[0063] Optionally, the size of the region of interest may be preset, and a region having the same size as the region of interest may be captured from the target cell image as the region of interest.

[0064] Optionally, the relative position of the region of interest in the image may be preset, and the region of interest may be captured from the target cell image based on the relative position.

[0065] Exemplarily, the size of the region of interest and the relative position of the region of interest in the image may be preset, and based on the relative position, an area having the size of the region of interest may be intercepted from the target cell image as the region of interest.

[0066] In one example, the relative position of the region of interest in the image can be the upper left corner of the image, and the size of the region of interest can be 128*128 pixels. Then, a 128*128 pixel area can be intercepted from the upper left corner of the target battery cell image as the region of interest. Of course, depending on the actual scene arrangement, for example, when the distance between the acquisition device and the target battery cell is far, the image of the target battery cell taken is small, and the size of the pre-set region of interest can also be relatively smaller; when the distance between the acquisition device and the target battery cell is close, the image of the target battery cell taken is large, and the size of the pre-set region of interest can also be relatively larger. Specifically, the relative position of the region of interest in the image and the size of the region of interest can be set based on actual conditions.

[0067] Optionally, an operation interface may be provided, which may display the target cell image, and the region of interest may be selected by operating the target cell image in the operation interface.

[0068] Optionally, edge detection may be performed on the target cell image to select a region of the target cell, and then a region of interest may be selected from the region of the target cell.

[0069] Step 240 , performing edge detection on the region of interest to determine the thermal indentation and the cell edge in the region of interest.

[0070] Optionally, by identifying each pixel point in the region of interest, the value of each pixel point can be identified in sequence along a specified direction. If a pixel jump occurs, it can be used as a candidate point for thermal indentation and battery cell edge.

[0071] After traversing each pixel point in the region of interest, the thermal indentation and the edge of the battery cell can be determined from the candidate points. For example, the edge of the battery cell in the image can be a trace formed by the candidate points close to the edge of the image. For example, the thermal indentation in the image can be a trace formed by the candidate points close to the middle area of ​​the image.

[0072] The designated method may be a direction perpendicular to the thermal indentation. Since the general direction of the thermal indentation is determined when the components of the detection system are arranged, the movement method of the battery cell and the thermal pressing process are determined. Figure 5 Taking the example shown in the figure as an example, the thermal indentation in the target cell image is usually parallel to the D1 direction shown in the figure, or forms a smaller angle with the D1 direction shown in the figure. Figure 5In the example shown, the cell edge in the image may be a trace formed by a candidate point close to the upper edge of the image, and the thermal indentation in the image may be a trace formed by a candidate point far from the upper edge of the image.

[0073] Step 260 , calculating the thermal indentation and the cell edge to determine thermal pressure state data.

[0074] The thermal pressure state data may be used to represent the state of the thermal indentation of the battery cell. Exemplarily, the thermal pressure state data may include the avoidance distance of the target battery cell, whether the thermal indentation of the target battery cell is parallel to the edge of the target battery cell, etc.

[0075] The hot pressing state data can be used as a basis for judging whether the hot pressing result of the target battery cell is qualified.

[0076] Optionally, the hot pressing state data is compared with the hot pressing standard to determine whether the target battery cell is qualified for hot pressing; if the target battery cell is not qualified for hot pressing, the target battery cell can be controlled to be moved to a recycling location.

[0077] The hot pressing standard may include, but is not limited to, a standard range of the depth of the hot indentation, a standard range of the distance between the hot indentation and the edge of the battery cell, an angle range formed by the hot indentation and the edge of the battery cell, etc.

[0078] Optionally, after determining that the target battery cell fails the thermal pressing, an alarm signal may be output to remind relevant personnel that the thermal pressing fails.

[0079] In order to reduce the number of unqualified battery cells in hot pressing, the equipment in the hot pressing section can be controlled to be shut down to facilitate relevant technicians to adjust the equipment in the hot pressing section to improve the hot pressing qualification rate.

[0080] Through the above method, the region of interest is first extracted, and the hot pressing state data is determined based on the processing and identification of the region of interest. Compared with the manual identification method, it can be relatively more accurate and objective.

[0081] In order to more conveniently realize the hot pressing state data, a line may be drawn first for the hot pressing mark and the edge of the battery cell. Based on this, the above step 260 may include step 261 and step 262.

[0082] Step 261 , edge lines are drawn for the thermal indentation and the edge of the battery cell in the region of interest to obtain thermal indentation lines and edge lines.

[0083] Optionally, a heat embossing line can be drawn based on the determined pixel points in the heat embossing. For example, all the determined pixel points in the heat embossing can be selected using a rectangular frame, and then the midline of the long side of the rectangular frame is used as the heat embossing line. The midline of the long side can be understood as a line connecting the midpoints of the two widths of the rectangle.

[0084] Optionally, edge lines may be drawn based on the determined pixel points in the cell edge. Exemplarily, all the determined pixel points in the cell edge may be selected using a rectangular frame, and then the midline of the long side of the rectangular frame is used as the edge line.

[0085] Optionally, a Hough transform line detection algorithm may also be used to determine the heat indentation lines and edge lines in the region of interest.

[0086] Step 262, determining the hot pressing state data according to the hot pressing mark line and the edge line.

[0087] The thermal pressing state data may include a clearance distance between the thermal pressing mark and the edge of the battery cell.

[0088] If the thermal indentation line and the edge line are two parallel lines, the distance from any point on the thermal indentation line to the edge line can be used as the clearance distance between the thermal indentation and the edge of the battery cell.

[0089] If the hot indentation line and the edge line are two non-parallel lines, the point with the smallest distance from the hot indentation line to the edge line can be selected first, and then the point with the smallest distance from the edge line to the hot indentation line can be selected, so as to determine the clearance distance between the hot indentation and the edge of the battery cell based on the two results. For example, the result with the smallest distance can be selected as the clearance distance between the hot indentation and the edge of the battery cell.

[0090] If the thermal indentation line and the edge line are two non-parallel lines, the distance between the midpoint of the thermal indentation line and the midpoint of the edge line can be used as the clearance distance formed between the thermal indentation and the edge of the battery cell.

[0091] Optionally, the above-mentioned step 262 may include: traversing the pixel points on one of the thermal indentation line and the edge line, and calculating the distance from each pixel point to the other line; from the distance from each pixel point to the other line, determining the clearance distance formed by the thermal indentation in the area of ​​interest and the edge of the battery cell.

[0092] Exemplarily, the distances from all pixel points in the thermal indentation line to the edge line may be traversed to determine the minimum distance as the clearance distance between the thermal indentation and the edge of the battery cell.

[0093] Exemplarily, the distances from all pixel points in the edge line to the thermal indentation line may be traversed, and the minimum distance may be determined therefrom as the clearance distance formed between the thermal indentation and the edge of the battery cell.

[0094] Exemplarily, the distances from all pixels in the thermal indentation line to the edge line can be traversed to determine the first minimum distance, and then the distances from all pixels in the edge line to the thermal indentation line can be traversed to determine the second minimum distance, and the smaller value between the first minimum distance and the second minimum distance can be used as the avoidance distance formed between the thermal indentation and the edge of the battery cell.

[0095] The thermal pressing state data may include an offset angle formed by the thermal pressing mark and the edge of the battery cell.

[0096] The above step 262 may include: calculating the angle formed by the thermal indentation line and the edge line, wherein the angle is used as the offset angle formed by the thermal indentation in the region of interest and the edge of the battery cell.

[0097] In the above manner, a straight line between the thermal indentation and the edge of the battery cell can be drawn first, and the avoidance distance and the offset angle can be determined based on the straight line to make the calculation easier.

[0098] Considering that the collected original battery cell image may contain a relatively large non-battery cell area, the battery cell portion image may be selected first, and then subsequent processing may be performed. Based on this, the above step 240 may include step 241 and step 242.

[0099] Step 241 : Match the target cell image with a preset template image to determine a cell region image in the target cell image.

[0100] The preset template image may be a pre-selected template image. For example, the preset template image may be an image acquired based on the same acquisition device as the target cell image, with the same gripper moved to the same target position, and the cell area is captured. In this embodiment, after the preset template image is determined, the preset template image may be used to match the image of the cell area as long as the acquisition device is not changed, the gripper is not changed, and the target position is not changed.

[0101] Exemplarily, the preset template image may be matched with each region image of the target cell image to determine a region with the highest similarity to the preset template image, and use the region as the cell region image.

[0102] Exemplarily, the similarity between the preset template image and each area image in the target cell image is calculated; based on the similarity between each area image and the preset template image, the cell area image in the target cell image is screened out. The cell area image can be understood as the area image in the target cell image that is most similar to the preset template image. In actual use, when a regional image that meets the set conditions is matched, it can be used as the cell area image. The set condition can indicate that the similarity is greater than a set threshold, and the set threshold can be 80%, 75%, 85%, etc.

[0103] A first region image matching the size of a preset template image may be selected from the target cell image frame; and a similarity between the first region image and the preset template image may be calculated.

[0104] Optionally, each region image in the target cell image may be selected according to a set rule, wherein the first region image is any region image among the region images included in the target cell image.

[0105] The above setting rule may include sequentially selecting the regional image from the initial position of the target cell image along the first direction and the second direction of the target cell image.

[0106] The distance between two adjacent frame selection area image movements is the set distance.

[0107] Exemplarily, the initial position may be the upper left corner of the initial position image. Exemplarily, the first direction may be a direction parallel to one of the sides of the target battery cell image, and the second direction may be a direction perpendicular to the first direction. The set distance may be one or more pixels, which may be specifically determined based on the overall size of the image. For example, when the size of the image to be processed is relatively large, a relatively large value may be selected for the set distance; when the size of the image to be processed is relatively small, a relatively small value may be selected for the set distance. For example, when the processing accuracy requirement is high, a relatively small value may be selected for the set distance; when the processing accuracy requirement is low, a relatively large value may be selected for the set distance.

[0108] Exemplarily, a normalized cross-correlation method may be used to match the preset template image and the target cell image to determine a cell region image in the target cell image that has the highest similarity to the preset template image.

[0109] Step 241 may include: graying the target cell image, converting the color target cell image acquired by the acquisition device into a grayscale image, and then matching the grayscale image with a preset template image to determine the cell region image in the target cell image.

[0110] For example, the target cell image can be grayed using a grayscale processing method of the average value method, that is, the average value of the R, G, and B component values ​​of the target cell image is taken to obtain a grayscale image with a grayscale of each pixel in the range of 0-255. The specific formula is: R=G=B=(R+G+B) / 3.

[0111] In order to improve the accuracy of the hot pressing state data and reduce the interference of the interference information in the image on the calculation, after obtaining the grayscale image, some noise reduction processing can be performed to improve the reliability of the information in the grayscale image, which can further improve the reliability of the subsequently determined region of interest.

[0112] Exemplarily, a Gaussian blur function may be used to perform Gaussian blur processing on a grayscale image to reduce the influence of noise and fine edges.

[0113] Step 242: extracting a region of interest from the cell region image.

[0114] Before extracting the area of ​​interest, you can first establish a coordinate system.

[0115] A coordinate system is constructed in the cell region image; in the cell region image, a region of interest is selected using an interest box at specified coordinates of the coordinate system.

[0116] Exemplarily, the specified coordinates may be pre-set coordinate values. For example, the specified coordinates may be two-thirds or three-quarters of the length of the battery cell on the ordinate, and zero on the abscissa. For another example, the specified coordinates may be two-thirds or three-quarters of the length of the battery cell on the ordinate, and one-half or three-quarters of the length of the battery cell on the abscissa. Of course, the specified coordinates may also be determined based on the size of the actual designed interest box and the size of the target battery cell, as long as the thermal indentation and the edge of the target battery cell are in the selected area of ​​interest.

[0117] Optionally, when selecting the region of interest, the center of the interest box is located at the specified coordinates. Optionally, when selecting the region of interest, one of the vertices of the interest box may also be located at the specified coordinates.

[0118] Exemplarily, the center of the cell region image may be taken as the origin, the direction parallel to one side of the cell region image may be taken as the horizontal coordinate, and the direction perpendicular to the horizontal coordinate may be taken as the vertical coordinate.

[0119] The size and shape of the interest frame are preset, and the interest frame can be in a rectangular, circular, or other shape.

[0120] You can use the origin of the coordinate system as a reference point and use the interest box to select an area of ​​interest at the specified coordinates.

[0121] Selecting the region of interest in the above manner can better present the thermal indentation and the edge of the battery cell, which can provide a reliable basis for subsequent calculations.

[0122] Considering that one of the points of accuracy of image recognition lies in the reliability of the image used for processing, based on this, the method of the present application may also include step 211 and step 212.

[0123] In step 211 , after the target battery cell is hot pressed, the moving assembly is controlled to move the target battery cell to a target position.

[0124] Exemplarily, after the target battery cell is hot-pressed, it can be moved to a designated position under the transport of a transport mechanism, and the moving component moves the target battery cell from the transport mechanism to the target position.

[0125] Step 212, controlling the target light source to start, and capturing the target battery cell image under the illumination of the target light source.

[0126] The target light source can be activated based on a photoelectric switch. For example, when it is detected that the photoelectric switch at the target position is blocked, the target light source is controlled to be activated.

[0127] In this embodiment, the photoelectric switch can be installed between the conveying mechanism for conveying the target battery cell and the target position. During the process of moving the target battery cell from the conveying mechanism to the target position, the target battery cell can block the photoelectric switch, thereby starting the target power supply.

[0128] Considering that there may usually be two thermal indentations, in order to capture the two thermal indentations more clearly, an image of each of the two thermal indentations may be collected once.

[0129] The target cell image mentioned above may include a first cell image and a second cell image; the target position includes a first target position and a second target position; and the target light source includes a first light source and a second light source.

[0130] Then, the moving component can be controlled to move the target cell to the first target position, the first light source can be controlled to start, and the first cell image can be captured under the illumination of the target light source. Then, the moving component can be controlled to move the target cell to the second target position, the second light source can be controlled to start, and the second cell image can be captured under the illumination of the target light source.

[0131] The first battery cell image and the second battery cell image may be processed in the manner of steps 220 to 260 . If the recognition result of any one of the images is that the hot pressing fails, it may be determined that the target battery cell fails the hot pressing.

[0132] Exemplarily, when the first target position is illuminated by the first light source, the first thermal indentation of the target battery cell can be more clearly presented, and when the second target position is illuminated by the second light source, the second thermal indentation of the target battery cell can be more clearly presented.

[0133] By collecting the image of the target battery cell in the above manner, the thermal indentation of the obtained image can be clearly presented under the illumination of the light source, thereby providing a reliable data basis for subsequent calculations and improving the reliability of the results of the thermal pressure state.

[0134] The whole process of hot pressure testing of the target battery cell is described below in conjunction with the accompanying drawings: First, after the target battery cell is hot-pressed, the target battery cell may be moved to a first target position to capture a first battery cell image at this position, and the target battery cell may be moved to a second target position to capture a second battery cell image at this position.

[0135] Then, the first battery cell image and the second battery cell image can be grayed out to convert the color first battery cell image and the second battery cell image captured by the camera into grayscale images. Figure 6 This is a schematic diagram of another state of the target battery cell image provided by an embodiment of the present application. The other state is a grayscale image after grayscale processing.

[0136] Then, the preset template image can be used to match the grayscale image to select the battery cell area image. Figure 7 Shows the Figure 6 The cell area image is obtained after matching in the example shown.

[0137] In order to conveniently extract the region of interest in the cell region image, a coordinate system may be first established in the cell region image, so as to determine the region of interest in the cell region image based on the coordinate system. Figure 7 The example shown also includes the constructed coordinate system.

[0138] In this coordinate system, the region of interest is extracted from the cell area image, where Figure 5 The example shown can be Figure 7 The schematic diagram of the region of interest extracted by the example shown in the figure. Then, edge detection can be performed on the region of interest to obtain the thermal indentation and the edge of the battery cell. The thermal indentation line and edge line can be obtained by using Hough line detection and drawn on the image of the region of interest. Figure 8 In the example shown, a schematic diagram of marking the hot indentation lines and edge lines on the region of interest is shown.

[0139] Then the avoidance distance and offset angle can be calculated based on the hot indentation line and the edge line.

[0140] For example, the avoidance distance and the offset angle may be directly displayed in the battery cell image, and whether the thermal pressing of the target battery cell is qualified may be output.

[0141] The above process can be used to detect whether the two battery cell images are qualified by hot pressing.

[0142] When the test results of the two battery cell images are determined to be qualified for hot pressing, the target battery cell can be placed in the normal process for subsequent battery cell manufacturing processes. When the test result of any battery cell image is determined to be unqualified for hot pressing, the target battery cell can be placed in a recycling location.

[0143] Optionally, the target cell heat pressing failure may be outputted on the electronic device so that the technician can adjust the equipment of the heat pressing section that fails to meet the requirements. For example, the position of the sheet paper may be adjusted, and the position and angle of the equipment of the heat pressing section may be adjusted.

[0144] In addition, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the battery cell detection method described in the above method embodiment are executed.

[0145] The computer program product of the battery cell detection method provided in the embodiment of the present application includes a computer-readable storage medium storing program code, and the instructions included in the program code can be used to execute the steps of the battery cell detection method described in the above method embodiment. For details, please refer to the above method embodiment, which will not be repeated here.

[0146] In several embodiments provided in the present application, it should be understood that the disclosed method can also be implemented in other ways. The method embodiments described above are merely schematic, for example, the flowcharts and block diagrams in the accompanying drawings show the possible implementation architecture, functions and operations of the methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a part of a program segment or code, and a part of the program segment or code contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0147] If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes. It should be noted that in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprises" or any other variation thereof are intended to cover non-exclusive inclusion, so that a process, method, article or apparatus that includes a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or apparatus. In the absence of more restrictions, the elements defined by the sentence "includes..." do not exclude the presence of other identical elements in the process, method, article or apparatus that includes the elements. The above description is only a preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application. It should be noted that similar numbers and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0148] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A battery cell detection method, characterized in that: include: Identify the target battery cell image and determine the region of interest; wherein the region of interest includes the thermal indentation of the target battery cell and the edge of the target battery cell; Performing edge detection on the region of interest to determine thermal indentations and cell edges in the region of interest; The thermal indentation and the battery cell edge are calculated to determine thermal pressure state data.

2. The method according to claim 1, characterized in that The step of calculating the hot pressing mark and the edge to determine hot pressing state data includes: Drawing edge lines of the thermal indentation and the edge of the battery cell in the region of interest to obtain thermal indentation lines and edge lines; The hot pressing state data is determined according to the hot pressing mark line and the edge line.

3. The method according to claim 2, characterized in that The thermal pressing state data includes the clearance distance formed by the thermal pressing mark and the edge of the battery cell; The step of determining the hot pressing state data according to the hot pressing mark line and the edge line comprises: Traversing the pixel points on one of the heat-indentation line and the edge line, and calculating the distance from each pixel point to the other line; The clearance distance between the thermal indentation in the region of interest and the edge of the battery cell is determined from the distance from each pixel point to another line.

4. The method according to claim 2, characterized in that: The thermal pressing state data includes an offset angle formed by the thermal pressing mark and the edge of the battery cell; The step of determining the hot pressing state data according to the hot pressing mark line and the edge line comprises: The angle formed by the thermal indentation line and the edge line is calculated; wherein the angle is used as an offset angle formed by the thermal indentation in the region of interest and the edge of the battery cell.

5. The method according to claim 1, characterized in that The step of identifying the target battery cell image and determining the region of interest includes: Matching the target cell image with a preset template image to determine a cell area image in the target cell image; A region of interest is extracted from the cell region image.

6. The method according to claim 5, characterized in that The step of matching the target cell image with a preset template image to determine a cell region image in the target cell image includes: Calculating the similarity between the preset template image and each area image in the target cell image; Based on the similarity between each area image and the preset template image, the cell area images in the target cell image are screened out.

7. The method according to claim 6, characterized in that The calculating the similarity between the preset template image and the regional image in the target cell image includes: Selecting a first area image matching the size of the preset template image from the target cell image frame; The similarity between the first region image and the preset template image is calculated; wherein the first region image is any region image among the region images included in the target cell image.

8. The method according to claim 7, characterized in that The step of selecting a first area image matching the size of the preset template image from the target cell image frame includes: According to a set rule, a first area image matching the size of the preset template image is framed from the target battery cell image; wherein the set rule includes: from an initial position of the target battery cell image, regional images are framed in sequence along a first direction and a second direction of the target battery cell image; wherein the distance between two adjacent movement of the framed regional images is a set distance.

9. The method according to claim 5, characterized in that The extracting the region of interest from the cell region image comprises: Constructing a coordinate system in the cell region image; In the cell area image, an area of ​​interest is selected using an interest box at designated coordinates in the coordinate system.

10. The method according to any one of claims 1 to 9, characterized in that: Also includes: Comparing the hot pressing state data with the hot pressing standard to determine whether the target battery cell is hot pressed qualified; If the target battery cell fails the hot pressing test, the target battery cell is controlled to be moved to a recycling location.

11. The method according to any one of claims 1 to 9, characterized in that: The method further comprises: After the target battery cell is hot pressed, controlling the moving component to move the target battery cell to a target position; The target light source is controlled to start, and the target cell image is captured under the illumination of the target light source.

12. The method according to claim 11, characterized in that The controlling the target light source to start up includes: When it is detected that the photoelectric switch at the target position is blocked, the target light source is controlled to start.

13. The method according to claim 11, characterized in that The target cell image includes a first cell image and a second cell image; the target position includes a first target position and a second target position; the target light source includes a first light source and a second light source; The controlling movement component to move the target battery cell to a target position, and the controlling the target light source to start, and collecting the target battery cell image under the illumination of the target light source, include: Controlling the moving component to move the target battery cell to a first target position, controlling the first light source to start, and capturing the image of the first battery cell under the illumination of the target light source; The moving component is controlled to move the target battery cell to a second target position, the second light source is controlled to start, and the image of the second battery cell is captured under the illumination of the target light source.

14. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the machine-readable instructions are executed by the processor to perform the steps of the method according to any one of claims 1 to 13.

15. A detection system, characterized in that: include: Electronic equipment and acquisition equipment; The acquisition device is used to acquire the target battery cell image, and the electronic device is used to process the image acquired by the acquisition device to execute the steps of the method according to any one of claims 1 to 13.

16. The detection system according to claim 15, characterized in that: Also includes: A light source, used to illuminate the target position of the acquisition device; A photoelectric switch, used to control the on and off of the light source; The electronic device is further used to collect the target battery cell image in the target position when the light source is started.

17. The detection system according to claim 16, characterized in that: The light source includes a first light source and a second light source, and the first light source and the second light source are arranged at different positions.

18. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, performs the steps of the method according to any one of claims 1 to 13.

19. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 13 is implemented.

Images