Battery cell alignment detection method, controller, detection system, and storage medium

Abstract

Embodiments of the present application provide a kind of cell alignment detection method, controller, detection system and storage medium, wherein the cell alignment detection method includes: obtaining first battery image;First battery image is input into first training model and is detected to obtain region of interest;Second battery image and second pole piece end position information are obtained according to region of interest and first battery image;Second battery image is input into second training model and is separated to obtain third battery image and first pole piece end position information;Image extraction analysis processing is carried out to third battery image to obtain misplacement amount;According to second pole piece, first pole piece end position information and misplacement amount, the cell alignment degree is obtained.In the technical scheme of the present embodiment, first battery image is processed by first training model and second training model, and the position information and misplacement amount can be accurately obtained, and the accuracy of cell alignment detection can be effectively improved.

Description

Technical Field

[0001] This invention relates to, but is not limited to, the field of automation, and particularly to a method, controller, detection system, and storage medium for detecting cell alignment. Background Technology

[0002] Currently, on the battery cell production line, it is necessary to test the alignment of the electrode plates. Existing technology generally uses X-ray inspection equipment to perform non-destructive testing on the battery cells. Although it can achieve non-destructive testing, this testing method cannot accurately locate the positions of the positive and negative electrode plates, thus causing inaccurate battery cell alignment testing. Summary of the Invention

[0003] The following is an overview of the subject matter described in detail herein. This overview is not intended to limit the scope of the claims.

[0004] The main objective of this invention is to provide a cell alignment detection method, controller, detection system, and storage medium that can effectively improve the accuracy of cell alignment detection.

[0005] In a first aspect, embodiments of the present invention provide a method for detecting cell alignment, comprising:

[0006] Acquire a first cell image, wherein the first cell image is a cell image in which the first electrode and the second electrode are alternately stacked;

[0007] The image of the first cell is input into the first training model for detection processing to obtain the region of interest, which is the region composed of the difference between the first electrode and the second electrode;

[0008] The second cell image and the position information of the second electrode end are obtained based on the region of interest and the first cell image.

[0009] The second cell image is input into the second training model for separation processing to obtain the third cell image, and the end position information of the first electrode is obtained based on the third cell image and the first cell image.

[0010] Image extraction and analysis are performed on the image of the third cell to obtain the misalignment between the first electrode and the adjacent second electrode.

[0011] The cell alignment is obtained based on the end position information of the second electrode, the end position information of the first electrode, and the misalignment amount.

[0012] In one embodiment, the step of performing image extraction and analysis on the image of the third cell to obtain the misalignment between the first electrode and the adjacent second electrode includes:

[0013] Image extraction processing is performed on the third cell image to obtain the outer rectangle of each first electrode in the third cell image;

[0014] The misalignment between the first electrode and the adjacent second electrode is obtained based on the circumscribed rectangle.

[0015] In one embodiment, the step of performing image extraction processing on the third cell image to obtain the circumscribed rectangle of each first electrode in the third cell image includes:

[0016] The third cell image is subjected to image contour extraction processing to obtain the contour of each first electrode in the third cell image;

[0017] Generate the circumscribed rectangle corresponding to the contour of the first electrode based on the contour of the first electrode.

[0018] In one embodiment, obtaining the misalignment between the first electrode and the adjacent second electrode based on the circumscribed rectangle includes:

[0019] The target point is determined based on the circumscribed rectangle;

[0020] The misalignment between the first electrode and the adjacent second electrode corresponding to the circumscribed rectangle is calculated based on the position information corresponding to the target point.

[0021] In one embodiment, determining the target point location based on the circumscribed rectangle includes:

[0022] The vertex position information of the circumscribed rectangle is determined based on the circumscribed rectangle;

[0023] The midpoint position information of the two target sides of the circumscribed rectangle is determined based on the vertex position information, and the direction of the target sides is the same as the stacking direction of the first electrode and the second electrode.

[0024] The midpoint location information is determined as the target point.

[0025] In one embodiment, after performing image contour extraction processing on the third cell image to obtain the contour of each first electrode in the third cell image, the method further includes:

[0026] The outline of each first electrode is labeled to obtain the number of first electrodes;

[0027] The number of the second electrode is determined based on the number of the first electrode.

[0028] The total number of electrodes in the first cell image is obtained based on the number of the first electrode and the number of the second electrode.

[0029] In one embodiment, obtaining a second cell image based on the region of interest and the first cell image includes:

[0030] The region of interest is filtered to obtain the filtered region of interest.

[0031] The maximum contour of the filtered region of interest is obtained, and the region of interest is inverted to obtain the inverted region of interest.

[0032] The region of interest after the image is inverted is then bitwise ORed with the first cell image to obtain the second cell image.

[0033] In one embodiment, before acquiring the first cell image, the method includes:

[0034] Acquire target detection images;

[0035] The target detection image is cropped to obtain the detection processing area;

[0036] The detection and processing area is rotated to obtain the first battery cell image.

[0037] In one embodiment, prior to acquiring the target detection image, the method includes:

[0038] Acquire the initial image set obtained by the image acquisition module from the battery cell;

[0039] The initial images of the initial image set are subjected to average grayscale judgment processing to obtain the target detection image.

[0040] In a second aspect, embodiments of the present invention provide a controller, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the cell alignment detection method as described in the first aspect.

[0041] Thirdly, embodiments of the present invention provide a detection system, wherein the helium detection system includes the controller described in the second aspect.

[0042] Fourthly, a computer-readable storage medium storing computer-executable instructions for performing the cell alignment detection method described in the first aspect.

[0043] The beneficial effects of this invention include: acquiring a first cell image, wherein the first cell image is a cell image in which first and second electrodes are alternately stacked; inputting the first cell image into a first training model for detection processing to obtain a region of interest, wherein the region of interest is the region composed of the difference between the first electrode and the second electrode; obtaining a second cell image and the end position information of the second electrode based on the region of interest and the first cell image; inputting the second cell image into a second training model for separation processing to obtain a third cell image, and obtaining the end position information of the first electrode based on the third cell image and the first cell image; performing image extraction and analysis processing on the third cell image to obtain the misalignment amount between the first electrode and the adjacent second electrode; and obtaining the cell alignment degree based on the end position information of the second electrode, the end position information of the first electrode, and the misalignment amount. In the technical solution of this embodiment, by processing the first cell image through the first training model and the second training model, the positions of the positive electrode and the negative electrode can be accurately located. That is, accurate information on the end position of the second electrode, the end position of the first electrode, and the misalignment between the first electrode and the second electrode can be obtained from the first cell image, thereby effectively improving the accuracy of cell alignment detection.

[0044] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the description, claims, and drawings. Attached Figure Description

[0045] Figure 1 This is a system architecture platform for performing a cell alignment detection method provided in one embodiment of the present invention;

[0046] Figure 2 This is a flowchart of a cell alignment detection method provided in one embodiment of the present invention;

[0047] Figure 3 This is a flowchart of a cell alignment detection method provided in another embodiment of the present invention;

[0048] Figure 4 This is a flowchart of a cell alignment detection method provided in another embodiment of the present invention;

[0049] Figure 5 This is a schematic diagram of a battery cell provided in one embodiment of the present invention;

[0050] Figure 6 This is a schematic diagram of a first battery cell image provided in one embodiment of the present invention;

[0051] Figure 7This is a schematic diagram of a region of interest provided in one embodiment of the present invention;

[0052] Figure 8 This is a schematic diagram of the maximum contour of the region of interest provided in one embodiment of the present invention;

[0053] Figure 9 This is a schematic diagram of the region of interest after image inversion according to an embodiment of the present invention;

[0054] Figure 10 This is a schematic diagram of a second battery cell image provided in one embodiment of the present invention;

[0055] Figure 11 This is a schematic diagram of a third battery cell image provided in one embodiment of the present invention. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0057] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, or the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0058] Currently, on the battery cell production line, it is necessary to test the alignment of the electrode plates. Existing technology generally uses X-ray inspection equipment to perform non-destructive testing on the battery cells. Although it can achieve non-destructive testing, this testing method cannot accurately locate the positions of the positive and negative electrode plates, thus causing inaccurate battery cell alignment testing.

[0059] To address the aforementioned problems, embodiments of the present invention provide a cell alignment detection method, controller, detection system, and storage medium. The cell alignment detection method includes at least the following steps: acquiring a first cell image, wherein the first cell image is a cell image in which first and second electrodes are alternately stacked; inputting the first cell image into a first training model for detection processing to obtain a region of interest, wherein the region of interest is the region composed of the difference between the first electrode and the second electrode; obtaining a second cell image and the end position information of the second electrode based on the region of interest and the first cell image; inputting the second cell image into a second training model for separation processing to obtain a third cell image, and obtaining the end position information of the first electrode based on the third cell image and the first cell image; performing image extraction and analysis processing on the third cell image to obtain the misalignment amount between the first electrode and the adjacent second electrode; and obtaining the cell alignment degree based on the end position information of the second electrode, the end position information of the first electrode, and the misalignment amount.

[0060] In the technical solution of this embodiment, by processing the first cell image through the first training model and the second training model, the positions of the positive electrode and the negative electrode can be accurately located. That is, accurate information on the end position of the second electrode, the end position of the first electrode, and the misalignment between the first electrode and the second electrode can be obtained from the first cell image, thereby effectively improving the accuracy of cell alignment detection.

[0061] The embodiments of the present invention will be further described below with reference to the accompanying drawings.

[0062] like Figure 1 As shown, Figure 1 This is a schematic diagram of a system architecture platform 100 for performing a cell alignment detection method according to an embodiment of this application.

[0063] exist Figure 1 In this example, the system architecture platform 100 includes a processor 110 and a memory 120, which can be connected via a bus or other means. Figure 1 Taking the example of a connection between China and Israel via a bus.

[0064] Memory 120, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory 120 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory 120 may optionally include memory remotely located relative to processor 110, and these remote memories can be connected to the system architecture platform 100 via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0065] The system architecture platform can be a programmable controller or other controllers; this embodiment does not specifically limit it.

[0066] It will be understood by those skilled in the art that Figure 1 The system architecture platform shown does not constitute a limitation on the embodiments of this application. It may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0067] Based on the above system architecture platform, various embodiments of the cell alignment detection method of the present invention are proposed below.

[0068] Reference Figure 2 , Figure 2 This is a flowchart of a cell alignment detection method provided in an embodiment of the present invention. The cell alignment detection method of the present invention may include, but is not limited to, steps S100, S200, S300, S400, S500 and S600.

[0069] Step S100: Obtain a first cell image. The first cell image is a cell image in which the first electrode and the second electrode are alternately stacked.

[0070] Specifically, when it is necessary to detect the alignment of the battery cells, the first image of the battery cell to be detected can be obtained. The battery cell to be detected includes multiple first electrode plates and multiple second electrode plates. The first electrode plates and second electrode plates are stacked alternately. Generally, the lengths of the first electrode plates and the second electrode plates are different. Therefore, when the length of the first electrode plate is longer than the length of the second electrode plate, the first electrode plate will protrude from the second electrode plate.

[0071] It should be noted that the first cell image can be a pre-processed cell image or an unprocessed cell image; this embodiment does not impose any specific limitations on it.

[0072] It should be noted that the polarity of the first electrode is different from that of the second electrode. The first electrode can be positive and the second electrode can be negative, or the first electrode can be negative and the second electrode can be positive. This embodiment does not make specific limitations on it.

[0073] In one embodiment, in the first cell image, the first electrode is a positive electrode, the second electrode is a negative electrode, the length of the negative electrode is longer than the length of the positive electrode, and the positive and negative electrodes are presented in an alternating layered manner in the first cell image, with one less positive electrode than negative electrode.

[0074] Step S200: Input the image of the first cell into the first training model for detection processing to obtain the region of interest, which is the region composed of the difference between the first electrode and the second electrode.

[0075] Specifically, after acquiring a detectable first cell image, the first cell image is input into a first training model for detection processing. The first training model outputs a region of interest (ROI) corresponding to the data of the first cell image. Since the lengths of electrodes of different polarities are different, after the cell is manufactured, there will be a difference between the first electrode and the second electrode. When the length of the first electrode is greater than the length of the second electrode, the difference is the part of the first electrode that protrudes relative to the second electrode. It can be seen that the main purpose of this step is to detect the region formed by the difference between the first electrode and the second electrode, i.e., the ROI. Data for calculating the cell alignment can be obtained from the ROI.

[0076] It should be noted that the first training model is a model obtained through deep learning. This model is used to detect and process the image of the first cell to obtain the region composed of the difference between the first electrode and the second electrode in the cell, which is the region of interest.

[0077] Step S300: Obtain the second cell image and the position information of the second electrode end based on the region of interest and the first cell image.

[0078] Specifically, by combining the region of interest output by the first training model with the first cell image, a second cell image corresponding to the region of interest in the first cell image can be obtained. Furthermore, the position information of the end of the second electrode can be determined based on the region of interest combined with the first cell image.

[0079] In one embodiment, the region of interest (ROI) output by the first training model is first filtered to effectively remove glitch elements from the original ROI, resulting in a filtered ROI. Then, the maximum contour of the filtered ROI is obtained, and the ROI with the maximum contour is inverted to obtain an inverted ROI, where the ROI within the ROI is set to 0, and the ROI outside the ROI is set to 255. Next, a bitwise OR operation is performed between the inverted ROI and the first cell image to obtain a second cell image. The resulting second cell image is then the image corresponding to the ROI in the first cell image. After a series of processes including filtering, maximizing the contour, and inverting the ROI, a more precise ROI can be obtained, leading to a more accurate extraction of the second cell image from the first cell image, and more precise determination of the second electrode end position information from the first cell image.

[0080] Step S400: Input the second cell image into the second training model for separation processing to obtain the third cell image, and obtain the end position information of the first electrode based on the third cell image and the first cell image.

[0081] Specifically, the second cell image is input into the second training model, which is a model obtained through deep learning. This model is used to separate the second cell image to obtain each independent first electrode in the region of interest. Then, the second training model will output a third cell image, which is a binary image with the same size as the electrode in the region of interest of the first cell image. Thus, the specific coordinate position in the first cell image, i.e. the end position information of the first electrode, can be determined based on the position of the points in the third cell image.

[0082] Step S500: Image extraction and analysis processing is performed on the image of the third cell to obtain the misalignment between the first electrode and the adjacent second electrode.

[0083] In one embodiment, image extraction processing is performed on a third cell image comprising multiple first electrode portion images (i.e., the difference between the first electrode and the second electrode). This yields the circumscribed rectangle of each first electrode in the third cell image, typically the minimum circumscribed rectangle. The size of the circumscribed rectangle can be finely adjusted according to actual conditions. The misalignment between the first electrode and the adjacent second electrode can then be determined from the circumscribed rectangle. It is understood that since the electrodes in the first cell image are alternating layers of first and second electrodes, the circumscribed rectangle of the first electrode in the third cell image obtained from the first cell image is elongated. Therefore, the length of the longer side of the circumscribed rectangle can be used as the misalignment between the first electrode and the adjacent second electrode.

[0084] In one embodiment, the third cell image is first processed by image contour extraction to obtain the contour of each first electrode in the third cell image. Then, an outer rectangle corresponding to the contour of the first electrode is generated based on the contour of the first electrode. The misalignment between the first electrode and the adjacent second electrode can be obtained based on the length of the long side of the outer rectangle. It is understood that the size of the outer rectangle corresponding to each contour may be the same or different.

[0085] In one embodiment, the third cell image is first processed by image contour extraction to obtain the contour of each first electrode in the third cell image. Then, an outer rectangle corresponding to the contour of the first electrode is generated based on the contour of the first electrode. Next, a target point is determined based on the outer rectangle. The misalignment between the first electrode corresponding to the outer rectangle and the adjacent second electrode is calculated based on the position information corresponding to the target point. It should be noted that the target point can be the midpoint of the midpoint of the two short sides of the outer rectangle, or other points near the midpoint of the two short sides of the outer rectangle, which can be set according to the actual situation.

[0086] In one embodiment, firstly, image contour extraction processing is performed on the third cell image to obtain the contour of each first electrode in the third cell image. Then, an outer rectangle corresponding to the contour of the first electrode is generated. Next, the vertex position information of the outer rectangle is determined based on the outer rectangle, and the midpoint position information of the two target sides of the outer rectangle is determined based on the vertex position information. The direction of the target sides is the same as the stacking direction of the first and second electrodes. The midpoint position information is determined as the target point. For example, after obtaining the minimum outer rectangle of the contour, the four vertices of the minimum outer rectangle are extracted and sorted. The midpoints of the four sides are obtained through the four vertices. The midpoints of the left and right ends of the first electrode and its adjacent second electrode are compared to obtain the misalignment amount. That is, the length of the outer rectangle can represent the distance between the first and second electrodes.

[0087] Step S600: The cell alignment is obtained based on the end position information of the second electrode, the end position information of the first electrode, and the misalignment amount.

[0088] Specifically, by processing the image of the first cell using the first training model and the second training model, the positions of the positive and negative electrodes can be accurately located. That is, accurate information on the end position of the second electrode, the end position of the first electrode, and the misalignment between the first and second electrodes can be obtained from the image of the first cell, thereby effectively improving the accuracy of cell alignment detection.

[0089] Reference Figure 3 , Figure 3The flowchart of a cell alignment detection method provided in another embodiment of the present invention includes steps S310, S320 and S330 before step S100.

[0090] Step S310: Obtain the target detection image.

[0091] Specifically, the target detection image can be a detection image that meets the basic detection requirements after preliminary screening, or it can be a detection image that meets the basic detection requirements stored in the memory.

[0092] In one embodiment, cell alignment detection is a process of real-time detection of each cell. The target cell to be detected is photographed by an image acquisition module. To reduce the error rate of the photographing step, multiple images are typically captured to obtain an initial image set for the cell. Then, the initial images in the initial image set are processed by average grayscale judgment to obtain the target detection image. This step can filter out erroneous images obtained during the image acquisition module's imaging process. For example, sometimes the initial image read is a completely black image; this step can filter out images incorrectly imaged by the x-ray device.

[0093] In one embodiment, cell alignment detection is a process of detecting a batch of cells. The target detection image is a target detection image obtained by scanning after the initial image of the cell has been processed by average grayscale judgment. Multiple target detection images are stored in memory in a certain order.

[0094] It should be noted that the image acquisition module can be an x-ray device or a photographic device; this embodiment does not specifically limit it.

[0095] Step S320: Perform cropping processing on the target detection image to obtain the detection processing area.

[0096] Specifically, the acquired target detection image is cropped. The cropped points can be manually selected or fixed. For example: [x,y,width,height] [300,300,900,700]; or [x,y,width,height] [250,250,950,600]. These settings can be adjusted according to the actual situation; this implementation does not impose specific limitations on them.

[0097] Step S330: Rotate the detection processing area to obtain the first cell image.

[0098] Specifically, after the detection and processing area is captured, it can be rotated to facilitate subsequent detection, processing and judgment. For example, the detection and processing area can be rotated by 270 degrees; or by 90 degrees. The settings can be made according to the actual situation, and this embodiment does not impose any specific limitations on them.

[0099] Reference Figure 4 , Figure 4 The flowchart shows a cell alignment detection method provided in another embodiment of the present invention. The steps of the embodiment of the present invention include, but are not limited to, steps S410, S420, S430, and S440.

[0100] Step S410: Read the initial image (e.g., image detected from the x-ray device) of the battery cell to be tested. Figure 5 As shown, under normal circumstances, a battery cell includes multiple positive electrode plates 510 and multiple negative electrode plates 520. The positive electrode plates 510 and negative electrode plates 520 are stacked alternately. The lengths of the positive electrode plates 510 and negative electrode plates 520 are different. When assembled into a battery cell, the head of the positive electrode plate 510 is flush with the head of the negative electrode plate 520. When the length of the negative electrode plate 520 is greater than the length of the positive electrode plate 510, a portion of the negative electrode plate 520 will protrude from the positive electrode plate 510. The length of the protruding portion is the alignment that needs to be tested.

[0101] Step S420: Determine the initial image by average grayscale to obtain the target detection image;

[0102] Step S430: Extract the detection processing area from the target detection image;

[0103] Step S440: Rotate the image of the detection processing area by a preset angle to obtain the first cell image, as shown below. Figure 6 As shown;

[0104] Step S450: Convert the first cell image into a grayscale image;

[0105] Step S460: The first cell image, converted to grayscale, is input into the first training model for detection processing to obtain the region of interest, such as... Figure 7 As shown (via Figure 7 (It can obtain the end position information of the positive electrode plate);

[0106] Step S470: Filter the first cell image converted to grayscale to remove burrs from the first cell image;

[0107] Step S480: Obtain the maximum contour of the region of interest, such as... Figure 8 As shown;

[0108] Step S490: Invert the image of the maximum contour of the region of interest to obtain the inverted region of interest, such as... Figure 9 As shown, the value within the region of interest is 0, and the value outside the region of interest is 255;

[0109] Step S500: Perform a bitwise OR operation between the inverted region of interest (ROI) of the image and the first cell image to obtain the second cell image (the second cell image is the image corresponding to the ROI of the first cell image). Figure 10 As shown.

[0110] Step S510: Input the second cell image into the second training model for separation processing to obtain the third cell image, such as... Figure 11 As shown (the third cell image and the first cell image can provide information about the end position of the negative electrode).

[0111] Step S520: Binarize the third cell image to obtain a binary image of the same size as the first cell image (the binary image can be combined with the third cell image to obtain the specific coordinates of the points in the third cell image in the first cell image).

[0112] Step S530: Filter and denoise the binarized image of the third battery cell;

[0113] Step S540: Obtain the outline of each negative electrode in the third cell image, sort them by Y value, and label each first electrode in the third cell image (i.e., label each white horizontal line in the third cell image).

[0114] Step S550: Traverse each contour. The number of contours represents the number of negative electrode sheets. Calculate the number of positive electrode sheets and the total number of electrodes based on the number of negative electrode sheets. (Since there is one less positive electrode sheet than negative electrode sheet, the number of positive electrode sheets and the total number of electrodes can be calculated simultaneously.)

[0115] Step S560: Obtain the outline of the negative electrode and generate the minimum bounding rectangle of the bounding rectangle corresponding to the outline.

[0116] Step S570: Extract the vertices of the smallest bounding rectangle and sort them;

[0117] Step S580: Obtain the midpoints of the four sides using the four vertices of the smallest bounding rectangle;

[0118] Step S590: Compare the midpoints of the left and right ends of adjacent positions to obtain the misalignment amount of adjacent electrodes (adjacent electrodes refer to one positive electrode and one negative electrode; the misalignment amount is the length of the rectangle, i.e., the distance between the positive and negative electrodes).

[0119] In step S600, the cell alignment is obtained by using the end position information of the positive electrode, the end position information of the negative electrode, and the misalignment amount.

[0120] In the technical solution of this embodiment, by processing the first cell image through the first training model and the second training model, the positions of the positive electrode and the negative electrode can be accurately located. That is, accurate information on the end position of the second electrode, the end position of the first electrode, and the misalignment between the first electrode and the second electrode can be obtained from the first cell image, thereby effectively improving the accuracy of cell alignment detection.

[0121] Additionally, one embodiment of this application provides a controller, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor and the memory can be connected via a bus or other means. It should be noted that the controller in this embodiment may correspond to including, for example... Figure 1 The memory and processor in the illustrated embodiment can constitute Figure 1 The system architecture platform shown in the embodiment is part of the same inventive concept, and therefore has the same implementation principle and beneficial effects, which will not be described in detail here.

[0122] The non-transient software program and instructions required to implement the cell alignment detection method on the controller side of the above embodiments are stored in memory. When executed by the processor, the cell alignment detection method of the above embodiments is executed, for example, the method described above is executed. Figure 2 Method steps S100 to S600 in the text Figure 3 Method steps S310 to S330 and Figure 4 Method steps S410 to S600.

[0123] In addition, one embodiment of this application also provides a detection system, including the controller in the above embodiment. The implementation principle and beneficial effects are the same as those of the controller, and will not be described in detail here.

[0124] Furthermore, one embodiment of this application also provides a computer-readable storage medium storing computer-executable instructions. When these computer-executable instructions are used to execute the aforementioned cell alignment detection method, for example, to execute the above-described method... Figure 2 Method steps S100 to S600 in the text Figure 3 Method steps S310 to S330 and Figure 4 Method steps S410 to S600.

[0125] It will be understood by those skilled in the art that all or some of the steps and systems in the methods disclosed above can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, as is known to those skilled in the art, communication media typically include computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium. It should be noted that computer-readable storage media may be non-volatile or volatile.

[0126] The above provides a detailed description of the preferred embodiments of this application. However, this application is not limited to the above-described embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of this application. All such equivalent modifications or substitutions are included within the scope defined by the claims of this application.

Claims

1. A method for detecting cell alignment, characterized in that, include: Acquire a first cell image, wherein the first cell image is a cell image in which the first electrode and the second electrode are alternately stacked; The image of the first cell is input into the first training model for detection processing to obtain the region of interest, which is the region composed of the difference between the first electrode and the second electrode; The region of interest is filtered to obtain the filtered region of interest. The maximum contour of the filtered region of interest is obtained, and the region of interest is inverted to obtain the inverted region of interest. The region of interest after the image is inverted is bitwise ORed with the first cell image to obtain the second cell image. The second cell image is input into the second training model for separation processing to obtain the third cell image, and the end position information of the first electrode is obtained based on the third cell image and the first cell image. Image extraction processing is performed on the third cell image to obtain the outer rectangle of each first electrode in the third cell image; The misalignment between the first electrode and the adjacent second electrode is obtained based on the circumscribed rectangle. The cell alignment is obtained based on the end position information of the second electrode, the end position information of the first electrode, and the misalignment amount.

2. The cell alignment detection method according to claim 1, characterized in that, The step of performing image extraction processing on the third cell image to obtain the circumscribed rectangle of each first electrode in the third cell image includes: The third cell image is subjected to image contour extraction processing to obtain the contour of each first electrode in the third cell image; Generate the circumscribed rectangle corresponding to the contour of the first electrode based on the contour of the first electrode.

3. The cell alignment detection method according to claim 2, characterized in that, The step of obtaining the misalignment between the first electrode and the adjacent second electrode based on the circumscribed rectangle includes: The target point is determined based on the circumscribed rectangle; The misalignment between the first electrode and the adjacent second electrode corresponding to the circumscribed rectangle is calculated based on the position information corresponding to the target point.

4. The cell alignment detection method according to claim 3, characterized in that, The step of determining the target point location based on the circumscribed rectangle includes: The vertex position information of the circumscribed rectangle is determined based on the circumscribed rectangle; The midpoint position information of the two target sides of the circumscribed rectangle is determined based on the vertex position information, and the direction of the target sides is the same as the stacking direction of the first electrode and the second electrode. The midpoint location information is determined as the target point.

5. The cell alignment detection method according to claim 1, characterized in that, After performing image contour extraction processing on the third cell image to obtain the contour of each first electrode in the third cell image, the method further includes: The outline of each first electrode is labeled to obtain the number of first electrodes; The number of the second electrode is determined based on the number of the first electrode. The total number of electrodes in the first cell image is obtained based on the number of the first electrode and the number of the second electrode.

6. The cell alignment detection method according to claim 1, characterized in that, The step of obtaining the second cell image based on the region of interest and the first cell image includes: The region of interest is filtered to obtain the filtered region of interest. The maximum contour of the filtered region of interest is obtained, and the region of interest is inverted to obtain the inverted region of interest. The region of interest after the image is inverted is then bitwise ORed with the first cell image to obtain the second cell image.

7. The cell alignment detection method according to claim 1, characterized in that, Before acquiring the first cell image, the method includes: Acquire target detection images; The target detection image is cropped to obtain the detection processing area; The detection and processing area is rotated to obtain the first battery cell image.

8. The cell alignment detection method according to claim 7, characterized in that, Before acquiring the target detection image, the method includes: Acquire the initial image set obtained by the image acquisition module from the battery cell; The initial images of the initial image set are subjected to average grayscale judgment processing to obtain the target detection image.

9. A controller, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, when the processor executes the computer program, it implements the cell alignment detection method according to any one of claims 1 to 8.

10. A detection system, characterized in that, include: The controller as described in claim 9.

11. A computer-readable storage medium storing computer-executable instructions, the computer being configured to perform the cell alignment detection method according to any one of claims 1 to 8.

Images