Battery cell wrinkling detection method and related equipment

Abstract

The embodiment of the invention provides a battery cell wrinkling detection method and related equipment, and belongs to the technical field of lithium battery intelligent equipment. The method comprises the following steps: acquiring position preparation information of positive and negative pole pieces and positive and negative diaphragms reaching preset positions; starting winding according to the position preparation information, and shooting to obtain an image of each circle of winding battery cell; carrying out algorithm processing on the image of the wound battery cell, and extracting to obtain a wrinkled pattern; and analyzing the wrinkles, and judging to obtain a wrinkling detection result. According to the embodiment of the invention, accurate detection of wrinkles can be realized.

Description

Technical Field

[0001] This application relates to the field of lithium battery intelligent equipment technology, and in particular to a method and related equipment for detecting cell wrinkles. Background Technology

[0002] During the lithium battery winding process, higher speeds increase the likelihood of wrinkles forming on the separator or electrode sheets, leading to cell quality issues. At high speeds, existing wrinkle detection technologies cannot achieve the necessary precision.

[0003] In summary, the technical problems existing in the relevant technologies need to be improved. Summary of the Invention

[0004] The main objective of this application is to propose a method and related equipment for detecting cell wrinkles, which can achieve accurate detection of wrinkles.

[0005] To achieve the above objectives, one aspect of this application proposes a method for detecting cell wrinkles, the method comprising: Obtain position preparation information for the positive and negative electrode plates and positive and negative separators to reach the preset positions; Based on the position preparation information, begin winding and capture an image of each turn of the wound cell; The image of the wound battery cell is processed by an algorithm to extract the wrinkled texture; The wrinkled texture is analyzed to determine the wrinkle detection result.

[0006] In some embodiments, starting winding based on the position preparation information and capturing an image of each turn of the wound cell includes: Based on the position preparation information, the transmission mechanism and electrical equipment enter the preparation state and receive the winding preparation prompt information; Based on the winding preparation prompts, begin winding the battery cell and use a camera to capture images of each turn of the wound battery cell.

[0007] In some embodiments, the step of performing algorithmic processing on the image of the wound battery cell to extract the wrinkled texture includes: Obtain image cropping parameters; The image of the wound battery cell is cropped according to the image cropping parameters to obtain a cropped image; the cropped image contains the area of ​​the wound battery cell. The captured image is segmented into the cell region to obtain a cell region image; The image of the battery cell area is segmented to obtain an image of the reflective area and an image of the normal area; The images of the reflective areas and the normal areas are labeled respectively, and a segmentation AI algorithm model is trained. The segmentation AI algorithm model is used to extract the wrinkle texture from the reflective area image and the normal area image to obtain the wrinkled texture.

[0008] In some embodiments, analyzing the wrinkled texture and determining the wrinkle detection result includes: The wrinkled texture is calculated and analyzed to obtain texture features; the texture features include confidence score, area, length, width and aspect ratio; Obtain information on wrinkle inspection requirements; Based on the texture features and the wrinkle detection requirements, the current texture is filtered to determine whether it is a wrinkled texture, thus obtaining the filtered textures; The texture feature values ​​of the entire image containing the selected texture are statistically analyzed; the texture feature values ​​include the total area, total length, average single-line area, and average single-line length of the wrinkled texture; Based on preset parameters and texture feature values ​​on the entire image, it is determined whether the current image is wrinkled, and wrinkle determination information of the image is obtained. Based on the wrinkle judgment information of the image and the image of the wound cell, the analysis of whether the cell is wrinkled is performed to obtain cell analysis data; the cell analysis data includes the number of wrinkled images of the cell, the total wrinkled area of ​​all images, the total number of wrinkles in all images, the total wrinkled length of all images, the average total wrinkled area per image, the average total number of wrinkles per image, and the average total wrinkled length per image. Obtain the battery cell wrinkling detection standard; The wrinkling detection result is obtained by judging based on the cell analysis data and the cell wrinkling detection standard.

[0009] To achieve the above objectives, another aspect of this application proposes a cell wrinkling detection system for implementing the method described above, the system comprising: The first module acquires position preparation information for the positive and negative electrode plates and positive and negative separators to reach the preset positions; The second module starts winding according to the position preparation information and takes images of each turn of the wound cell. The third module performs algorithmic processing on the image of the wound battery cell to extract the wrinkled texture; The fourth module analyzes the wrinkled texture and determines the wrinkle detection result.

[0010] In some embodiments, the system further includes a camera, a lens, a light source, a light source controller, an industrial computer, a rejection mechanism, and a gigabit network cable; The camera and lens are used for target imaging and to capture images during the winding process; The light source is used to illuminate the environment during the winding process so that the wrinkled texture achieves a preset clarity and the background grayscale achieves a preset uniformity. The light source controller is used to control the brightness of the light source or to trigger the light source to turn on or off; The industrial control computer is used to run vision software to perform image data processing, and transmits the processing results to the PLC through network communication or IO control card to control the rejection action of the rejection mechanism. The rejection mechanism is used to reject battery cells that do not meet the preset testing requirements; The gigabit network cable is used to connect the camera and the industrial control computer, so that the industrial control computer can control the camera through vision software.

[0011] In some embodiments, the selection of the light source includes short strips of light, long strips of light, or point light sources.

[0012] In some embodiments, the system further includes a mounting bracket; The mounting bracket is used to mount the camera and light source, and also to adjust the angle and distance of the camera and light source.

[0013] To achieve the above objectives, another aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method described above.

[0014] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the methods described above.

[0015] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer program product, including a computer program that, when executed by a processor, implements the aforementioned method.

[0016] The embodiments of this application include at least the following beneficial effects: This application provides a method, system, electronic device, storage medium, and program product for detecting cell wrinkles. The solution includes: acquiring position preparation information of the positive and negative electrode sheets and positive and negative separators reaching preset positions; starting winding according to the position preparation information and capturing images of each turn of the wound cell; performing algorithmic processing on the images of the wound cell to extract wrinkle textures; and analyzing the wrinkle textures to determine the wrinkle detection result. This invention can achieve accurate detection of wrinkles. Attached Figure Description

[0017] Figure 1 This is a flowchart of the cell wrinkling detection method provided in the embodiments of this application; Figure 2 This is a schematic diagram of the visual inspection process provided in an embodiment of this application; Figure 3 This is a schematic diagram of the process for detecting whether an image is wrinkled, as provided in the embodiments of this application; Figure 4 This is a schematic diagram of the winding process image provided in the embodiments of this application; Figure 5 This is a schematic diagram of the segmented image provided in an embodiment of this application; Figure 6 This is a schematic diagram of the wrinkled texture of a single image provided in the embodiments of this application; Figure 7 This is a schematic diagram of the cell wrinkling detection process provided in an embodiment of this application; Figure 8 This is a schematic diagram of the wrinkled image effect provided in the embodiments of this application; Figure 9 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0020] Before providing a detailed description of the embodiments of this application, some of the nouns and terms involved in the embodiments of this application will be explained first. The nouns and terms involved in the embodiments of this application are subject to the following interpretations.

[0021] 1) Segmentation AI algorithm models, used to identify and delineate the specific contours of wrinkled textures in images, including Mask R-CNN, DeepLab series, etc.; 2) Input / Output Control Card: A hardware expansion card that is plugged into the motherboard of the industrial control computer and acts as a physical bridge between the industrial control computer and external devices; 3) PLC, Programmable Logic Controller; 4) NG (Not Good), unqualified, refers to unqualified battery cells that are found to be unqualified and do not meet the preset conditions; 5) AI models, machine learning models used to complete visual tasks, including YOLO, Faster R-CNN, etc. 6) Traditional algorithms, which are based on digital image processing technology and hand-designed features, including threshold segmentation and edge detection (Canny, Sobel operators), etc.

[0022] During the lithium battery winding process, higher speeds increase the likelihood of wrinkles forming on the separator or electrode sheets, leading to cell quality issues. High-speed winding processes are fast, and existing conventional methods for wrinkle inspection cannot perform real-time checks on each roll or provide more detailed assessments of defects, thus failing to achieve precise wrinkle detection.

[0023] In view of this, this application provides a method and related equipment for detecting cell wrinkles. This solution uses machine vision technology to collect and process images of each turn during the winding process in real time. It combines traditional algorithms with AI algorithms to achieve accurate detection of wrinkles, promptly remove wrinkled cells, and ensure the quality of qualified cells.

[0024] Figure 1 This is an optional flowchart of the cell wrinkling detection method provided in the embodiments of this application. Figure 1 The method may include, but is not limited to, steps S101 to S104.

[0025] Step S101: Obtain position preparation information for the positive and negative electrode plates and positive and negative separators to reach the preset positions; Step S102: Start winding according to the position preparation information and take an image of each turn of the wound cell; Step S103: Perform algorithm processing on the image of the wound battery cell to extract the wrinkled texture; Step S104: Analyze the wrinkled texture and determine the wrinkle detection result.

[0026] Steps S101 to S104 shown in the embodiments of this application, by inspecting each turn of each produced cell, exceed the coverage of manual sampling inspection, and can avoid the fatigue, subjectivity and standard fluctuations of manual inspection.

[0027] In step S101 of some embodiments, the edge positions and conveying status of the positive and negative electrode sheets and the positive and negative separators can be monitored in real time by sensors (such as photoelectric sensors). Alternatively, the signals can be fed back to the PLC, and the PLC can determine through program logic whether all materials have synchronously reached the preset starting position near the winding needle, but this is not limited to this.

[0028] In some embodiments, step S102 may include, but is not limited to, steps S201 to S202: Step S201: Based on the position preparation information, the transmission mechanism and electrical equipment enter the preparation state and obtain the winding preparation prompt information; Step S202: According to the winding preparation prompts, start winding the battery cell and use a camera to take an image of each turn of the wound battery cell.

[0029] In step S201 of some embodiments, it is checked whether all execution units (mechanisms) and control units (electrical) are in the correct initial state, and whether the camera connection is normal. If any abnormality is found, the process will be paused and an alarm will be triggered.

[0030] In step S202 of some embodiments, since there is corresponding image data for each revolution, it is possible not only to determine the overall quality of the battery cell, but also to accurately locate which revolution the defect occurred in, providing data support for engineers to trace the root cause of the problem.

[0031] In some embodiments, step S103 may include, but is not limited to, steps S301 to S306: Step S301: Obtain image cropping parameters; Step S302: The image of the wound battery cell is cropped according to the image cropping parameters to obtain the cropped image; the cropped image contains the area of ​​the wound battery cell. Step S303: Segment the captured image into the cell region to obtain the cell region image; Step S304: The image of the battery cell area is segmented to obtain an image of the reflective area and an image of the normal area; Step S305: Label the reflective area image and the normal area image respectively, and train the segmentation AI algorithm model; Step S306: Use the segmentation AI algorithm model to extract the wrinkle texture from the reflective area image and the normal area image to obtain the wrinkled texture.

[0032] In steps S301 and S302 of some embodiments, because the original image captured by the camera contains a large amount of background (such as equipment brackets, background boards, etc.), these areas are irrelevant to the detection target. By pre-setting the cropping parameters (row1, column1, row2, column2), only the core area containing the core can be retained for subsequent processing.

[0033] In step S303 of some embodiments, the battery cell body (i.e., the winding layer) can be accurately segmented from the image by algorithms (such as threshold segmentation, edge detection).

[0034] In step S304 of some embodiments, by partitioning, the algorithm can use the same or different processing strategies and threshold parameters for the reflective area and the normal area to separate the reflective area, thus avoiding the AI ​​model from misidentifying high-intensity reflection as large-area wrinkles (false alarm).

[0035] In step S305 of some embodiments, the images of the reflective area and the normal area are labeled and trained respectively, so that the final AI model can learn the characteristic representation of wrinkles under different lighting conditions.

[0036] In step S306 of some embodiments, an instance segmentation AI model (such as Mask R-CNN) can be used to extract textures, providing a data foundation for subsequent steps.

[0037] In some embodiments, step S104 may include, but is not limited to, steps S401 to S408: Step S401: Calculate and analyze the wrinkled texture to obtain texture features; texture features include confidence score, area, length, width and aspect ratio; Step S402: Obtain wrinkle detection requirement information; Step S403: Based on the texture features and wrinkle detection requirements, filter whether the current texture is a wrinkled texture to obtain the filtered texture; Step S404: Calculate the texture feature values ​​of the entire image containing the selected texture; the texture feature values ​​include the total area, total length, average single-line area, and average single-line length of the wrinkled texture; Step S405: Determine whether the current image is wrinkled based on preset parameters and texture feature values ​​on the entire image to obtain wrinkle determination information of the image; Step S406: Analyze whether the battery cell is wrinkled based on the wrinkle judgment information of the image and the image of the wound battery cell to obtain battery cell analysis data; the battery cell analysis data includes the number of wrinkled images of the battery cell, the total wrinkled area of ​​all images, the total number of wrinkles in all images, the total wrinkled length of all images, the average total wrinkled area per image, the average total number of wrinkles per image, and the average total wrinkled length per image. Step S407: Obtain the cell wrinkling detection standard; Step S408: Based on the cell analysis data and the cell wrinkling detection standard, a judgment is made to obtain the wrinkling detection result.

[0038] In step S401 of some embodiments, the blurred "image region" extracted by the AI ​​model is transformed into a series of precise, measurable digital features. Different features can describe texture from different perspectives. For example, "area" measures the extent of influence, "aspect ratio" distinguishes between linear wrinkles and block wrinkles, and "confidence" represents the degree of understanding of the AI ​​model.

[0039] In step S402 of some embodiments, since different customers and different models of battery cells have different tolerances for wrinkling, this step parameterizes the detection standard, allowing for quick adaptation to new quality requirements by modifying the parameters without modifying the algorithm code.

[0040] In step S403 of some embodiments, the detection results are closely linked to process requirements, and the decision is not based on the assumptions of the algorithm engineer, but on the customer's actual production process and quality standards.

[0041] In step S404 of some embodiments, by calculating the total area, total length, etc., the overall quality of the winding layer represented by the current image is comprehensively evaluated, which makes the judgment more comprehensive and reasonable.

[0042] In step S405 of some embodiments, quality can be controlled and problems can be detected in real time. Each turn can be judged in real time during the winding process. Once an image is judged to be NG, a warning can be issued.

[0043] In step S406 of some embodiments, this is a data aggregation step that summarizes the detection results of hundreds or thousands of images into a quality report about the entire cell, which fully describes the wrinkling situation of the cell from multiple statistical dimensions (total number of lines, total area, average length, etc.).

[0044] In step S407 of some embodiments, the decision basis is clear and predefined, and applies to the entire cell as a standard (e.g., allowing no more than 3 wrinkles in the entire cell, and the total area not exceeding the allowed area).

[0045] In step S408 of some embodiments, the wrinkling detection result can directly drive the rejection mechanism (such as a robotic arm or cylinder) to perform an action to separate the NG battery cells, thereby forming a complete "detection-judgment-execution" automated closed loop without human intervention.

[0046] This application embodiment also provides a cell wrinkling detection system for implementing the method described above. The system includes: The first module acquires position preparation information for the positive and negative electrode plates and positive and negative separators to reach the preset positions; The second module prepares the information based on the location and begins winding, capturing images of each turn of the wound cell. The third module performs algorithmic processing on the image of the wound battery cell to extract the wrinkled texture. The fourth module analyzes the wrinkled texture and determines the wrinkle detection result.

[0047] Optionally, the above four modules work together to transform a subjective quality inspection task that relies on human eyes and experience into an automated intelligent process that is data-driven and capable of in-depth analysis.

[0048] In some embodiments, the system further includes a camera, a lens, a light source, a light source controller, an industrial computer, a rejection mechanism, and a gigabit network cable; The camera and lens are used to image the target and capture images during the winding process; The light source is used to illuminate the environment during the winding process so that the wrinkled texture achieves the preset clarity and the background grayscale achieves the preset uniformity. A light source controller is used to control the brightness of a light source or to trigger the light source to turn on or off. The industrial computer is used to run vision software to process image data and transmit the processing results to the PLC via network communication or IO control card to control the rejection action of the rejection mechanism. The rejection mechanism is used to reject battery cells that do not meet the preset testing requirements; Gigabit Ethernet cables are used to connect cameras and industrial PCs, enabling the industrial PCs to control the cameras via vision software.

[0049] Optionally, the cell wrinkle detection system of the present invention includes a vision device, which comprises a camera, lens, light source, light source controller, industrial computer, rejection mechanism, and gigabit network cable. The combination of a high-resolution camera and a precision lens can clearly capture tiny, subtle wrinkle textures and convert them into high-definition digital images. The light source provides uniform illumination, overcoming the influence of ambient light variations. The light source controller can precisely adjust the brightness of the light source to adapt to the reflective properties of different material surfaces and find the optimal imaging effect. The industrial computer is responsible for running complex image processing algorithms and AI models, completing computational tasks from image preprocessing to feature extraction and logical judgment. The rejection mechanism receives instructions from the industrial computer and accurately separates cells judged as NG from the production line. The gigabit network cable provides high-speed bandwidth, allowing image data to be transmitted from the camera to the industrial computer for processing in real time without frame loss, meeting the production line's cycle time requirements.

[0050] In some embodiments, the light source may be selected from short strips of light, long strips of light, or point light sources.

[0051] Optionally, the purpose of providing multiple light source options is not to pile up configurations, but to address different on-site challenges to achieve the best imaging effect. Different installation spaces, cell sizes, and material reflection characteristics require different lighting solutions. Short strip lights and long strip lights are usually used to produce low-angle lighting, which can excellently highlight the shadows generated by concave and convex defects such as wrinkles, thus forming high contrast in the image and making the wrinkle features very obvious. Point light sources (large light spot light sources) can provide bright and uniform forward lighting, which helps to overcome local reflection and obtain an image with uniform overall gray level, and is more suitable for detecting the overall flatness of the surface.

[0052] In some embodiments, the system further includes a mounting bracket; The mounting bracket is used to mount the camera and the light source, and is also used to adjust the angles and distances of the camera and the light source.

[0053] Optionally, the mounting bracket makes it easy to disassemble, replace, and maintain the camera and the light source. If the production line needs to be renovated or the equipment needs to be relocated, the entire vision device can be easily disassembled and reinstalled, and can quickly resume working status through adjustment.

[0054] Next, in combination with specific application examples, the solutions of the embodiments of the present invention will be introduced and described in detail: In the embodiments of the present application, during the winding process of the lithium battery winding machine, winding images are acquired in real time, the wrinkles on the images are detected, and then it is determined whether the battery cell is wrinkled, and the wrinkled battery cells are discharged in time to reduce defects and improve quality.

[0055] To fully describe the methods and related devices involved in the present invention, the following will be described in three parts: visual detection process, vision device, and main algorithms.

[0056] 1. Visual detection process The visual detection process is as Figure 2 shown and is described as follows: First, the positive and negative electrode plates and the positive and negative separators reach near the winding needle through the conveying and transfer mechanism, and the mechanism such as electricity is prepared for winding.

[0057] Then, winding starts, and the wrinkling camera takes pictures of each roll. Each picture is processed through image processing algorithms and AI algorithms to extract the wrinkle texture.

[0058] Then, after winding is completed, the vision device comprehensively judges whether the battery cell is wrinkled according to the wrinkle texture situation of each picture. There are some small local textures that do not affect the quality of the battery cell, and such situations are qualified battery cells.

[0059] Then, the battery cell moves to the rejection station through the conveying mechanism.

[0060] Then, based on the wrinkling detection results, wrinkled cells are rejected and moved to the wrinkled cell material box. Qualified cells are moved to the next processing station.

[0061] 2. Visual devices Vision devices include cameras, lenses, light sources, light source controllers, industrial computers, mounting brackets, rejection mechanisms, gigabit network cables, etc.

[0062] The camera and lens are mainly used for target imaging, acquiring images in real time during the winding process for algorithmic processing and analysis.

[0063] Considering installation space and product size, the light source can be selected from two short light strips, one long light strip, or one point light source with a large light spot. The purpose of the light source is to make the wrinkled texture clear and accurate, and the background grayscale uniform, so that the algorithm can extract the wrinkled texture on each image more accurately and stably.

[0064] A light source controller is used to control the brightness of a light source or to trigger actions such as turning the light source on or off, thereby controlling the light source.

[0065] The industrial control computer is the computing center. The vision software processes the image data and transmits the results to the PLC through network communication or I / O control cards, thereby controlling the rejection action of the rejection mechanism.

[0066] Mounting brackets are used to mount cameras, light sources, etc., and need to be easily adjustable so that angles and distances can be finely adjusted for better image quality.

[0067] The rejection mechanism is used to reject NG (non-quality) battery cells. The size of the battery cells and the rejection requirements are different, so the rejection mechanism used is also different.

[0068] Gigabit Ethernet cables are used to connect cameras to industrial control computers, allowing the industrial control computers to control cameras and other devices via vision software.

[0069] 3. Main Algorithm The process of detecting whether a single image is wrinkled is as follows: Figure 3 As shown, the explanation is as follows: First, the camera acquires images: During the winding process, the PLC triggers the camera in real time to capture images, and the camera obtains multiple images of the winding process.

[0070] Then, image cropping is performed based on the input parameters: Observe the area covered by the battery cell during the winding process, set the image cropping parameters row1, column1, row2, column2, and crop the image accordingly. See below. Figure 4 As the winding process continues, the diameter of the core increases, and the green box represents the area captured in the image.

[0071] Then, image segmentation is performed for secondary localization and left / right partitioning: During the winding process, the diameter of the battery cell gradually increases. The battery cell region is segmented in the local image obtained in the previous step to obtain the battery cell region in the current image. Considering the potential for reflection in the installation space and the accuracy of AI algorithm extraction, the image is split left and right to form an image of the reflective area and an image of the normal area. For example... Figure 5 Cell extraction is performed on a local image, then a layer is reduced in the height direction, and finally, the image is divided into left and right regions. The left region of the image has some reflection and is uneven. The right region of the image has good uniformity.

[0072] Then, an AI algorithm is used to extract the wrinkle texture in the left and right regions. The left and right regions are labeled separately, and the model is trained. An instance segmentation AI algorithm is then used to extract the wrinkle texture.

[0073] Then, calculate various features of the texture: mainly the texture confidence score, area, length, width, and aspect ratio.

[0074] Then, the detected wrinkled textures are filtered: based on the texture features, the wrinkle detection requirements of the customer are aligned, and the current texture is filtered to determine whether it is a wrinkled texture, thereby reducing false judgments.

[0075] Then, calculate the wrinkle texture features after filtering: here we count the texture feature values ​​on the whole image, such as the total area, total length, average single area, and average single length of the wrinkle texture.

[0076] Then, based on the input parameters and the texture feature values ​​of the entire image, it is determined whether the current image is wrinkled. The wrinkled texture of a single image is as follows: Figure 6 As shown.

[0077] The process of detecting whether a single battery cell is wrinkled is as follows: Figure 7 As shown, the explanation is as follows: First, acquire images of each revolution of the current battery cell in real time: as mentioned above, acquire images of each revolution of a single battery cell.

[0078] Next, determine if the current image is wrinkled: as mentioned above, determine whether each image is a wrinkled image.

[0079] Then, statistical analysis is performed to determine if the battery cell is wrinkled: This involves counting the number of wrinkled images for a single cell, the total wrinkled area across all images, the total number of wrinkles in all images, the total wrinkled length across all images, and calculating the average total wrinkled area, average total number of wrinkles in a single image, and average total wrinkled length per image. Based on these statistical parameters and the customer's wrinkle detection standards, it is then determined whether the current battery cell is wrinkled. (Reference) Figure 8 The image shows a wrinkled effect.

[0080] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method.

[0081] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0082] Please see Figure 9 , Figure 9 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes: The processor 901 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 902 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 902 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 902 and is called and executed by the processor 901 using the methods described in the embodiments of this application. The 903 input / output interface is used to implement information input and output. The communication interface 904 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 905 transmits information between various components of the device (e.g., processor 901, memory 902, input / output interface 903, and communication interface 904); The processor 901, memory 902, input / output interface 903, and communication interface 904 are connected to each other within the device via bus 905.

[0083] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0084] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0085] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0086] It is understood that the content of the above method embodiments is applicable to the embodiments of this program product. The specific functions implemented by the embodiments of this program product are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0087] Memory, 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 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 may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor 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.

[0088] The present invention takes into account that conventional sensor methods in related technologies cannot detect the entire surface of the battery cell, have low accuracy, and cannot measure the number, area, length and other characteristics of wrinkles, making it difficult to calculate the specific specifications of each wrinkle in detail.

[0089] The battery cell wrinkle detection method, system, electronic device, storage medium, and program product provided in this application employ machine vision technology to acquire and process images of each turn during the winding process in real time. Combining traditional algorithms with AI algorithms, it achieves accurate wrinkle detection, promptly rejects wrinkled battery cells, and ensures the quality of qualified battery cells. The method of this invention extracts each wrinkle texture and can calculate feature information such as the length, area, and contrast of the wrinkle texture, making the wrinkle detection standard more objective and accurate, thereby enabling accurate detection of wrinkled battery cells.

[0090] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0091] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0092] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0093] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0094] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0095] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0096] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0097] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0098] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0099] If the integrated unit is implemented as a software functional unit 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 this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0100] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for detecting wrinkles in battery cells, characterized in that, The method includes the following steps: Obtain position preparation information for the positive and negative electrode plates and positive and negative separators to reach the preset positions; Based on the position preparation information, begin winding and capture an image of each turn of the wound cell; The image of the wound battery cell is processed by an algorithm to extract the wrinkled texture; The wrinkled texture is analyzed to determine the wrinkle detection result.

2. The method according to claim 1, characterized in that, The step of starting winding based on the position preparation information and capturing images of each turn of the wound cell includes: Based on the position preparation information, the transmission mechanism and electrical equipment enter the preparation state and receive the winding preparation prompt information; Based on the winding preparation prompts, begin winding the battery cell and use a camera to capture images of each turn of the wound battery cell.

3. The method according to claim 1, characterized in that, The step of processing the image of the wound battery cell using an algorithm to extract the wrinkled texture includes: Obtain image cropping parameters; The image of the wound battery cell is cropped according to the image cropping parameters to obtain a cropped image; the cropped image contains the area of ​​the wound battery cell. The captured image is segmented into the cell region to obtain a cell region image; The image of the battery cell area is segmented to obtain an image of the reflective area and an image of the normal area; The images of the reflective areas and the normal areas are labeled respectively, and a segmentation AI algorithm model is trained. The segmentation AI algorithm model is used to extract the wrinkle texture from the reflective area image and the normal area image to obtain the wrinkled texture.

4. The method according to claim 1, characterized in that, The analysis of the wrinkled texture to determine the wrinkle detection result includes: The wrinkled texture is calculated and analyzed to obtain texture features; the texture features include confidence score, area, length, width and aspect ratio; Obtain information on wrinkle inspection requirements; Based on the texture features and the wrinkle detection requirements, the current texture is filtered to determine whether it is a wrinkled texture, thus obtaining the filtered textures; The texture feature values ​​of the entire image containing the selected texture are statistically analyzed; the texture feature values ​​include the total area, total length, average single-line area, and average single-line length of the wrinkled texture; Based on preset parameters and texture feature values ​​on the entire image, it is determined whether the current image is wrinkled, and wrinkle determination information of the image is obtained. Based on the wrinkle judgment information of the image and the image of the wound cell, the analysis of whether the cell is wrinkled is performed to obtain cell analysis data; the cell analysis data includes the number of wrinkled images of the cell, the total wrinkled area of ​​all images, the total number of wrinkles in all images, the total wrinkled length of all images, the average total wrinkled area per image, the average total number of wrinkles per image, and the average total wrinkled length per image. Obtain the battery cell wrinkling detection standard; The wrinkling detection result is obtained by judging based on the cell analysis data and the cell wrinkling detection standard.

5. A cell wrinkling detection system, used to implement the method as described in any one of claims 1 to 4, characterized in that, The system includes: The first module acquires position preparation information for the positive and negative electrode plates and positive and negative separators to reach the preset positions; The second module starts winding according to the position preparation information and takes images of each turn of the wound cell. The third module performs algorithmic processing on the image of the wound battery cell to extract the wrinkled texture; The fourth module analyzes the wrinkled texture and determines the wrinkle detection result.

6. The system according to claim 5, characterized in that, The system also includes a camera, lens, light source, light source controller, industrial computer, rejection mechanism and gigabit network cable; The camera and lens are used for target imaging and to capture images during the winding process; The light source is used to illuminate the environment during the winding process so that the wrinkled texture achieves a preset clarity and the background grayscale achieves a preset uniformity. The light source controller is used to control the brightness of the light source or to trigger the light source to turn on or off; The industrial control computer is used to run vision software to perform image data processing, and transmits the processing results to the PLC through network communication or IO control card to control the rejection action of the rejection mechanism. The rejection mechanism is used to reject battery cells that do not meet the preset testing requirements; The gigabit network cable is used to connect the camera and the industrial control computer, so that the industrial control computer can control the camera through vision software.

7. The system according to claim 6, characterized in that, The choice of light source includes short strips of light, long strips of light, or point light sources.

8. The system according to claim 5, characterized in that, The system also includes a mounting bracket; The mounting bracket is used to mount the camera and light source, and also to adjust the angle and distance of the camera and light source.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method according to any one of claims 1 to 4.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 4.

Images