A battery glue folding plate glue wrapping method, equipment and system

Abstract

The present invention relates to a method, device and system for glue-taping, folding and wrapping a battery film. The method uses a camera to monitor the folding process of the battery film in real time, and adopts a feature point detection algorithm to detect the folding angle and position of the film. A visual sensor is used to monitor the glue coating during the wrapping process, and image segmentation and deep learning technology are used to judge the uniformity and thickness of the glue layer. Thermal imaging technology is used to monitor the temperature distribution during the glue curing process, and a high-resolution camera is used to check the surface of the cured glue to identify bubbles and cracks. The method, device and system for glue-taping, folding and wrapping a battery film solves key technical problems such as inaccurate folding, uneven wrapping and curing defects, and can effectively improve the automation level, production efficiency and product quality of the battery production process.

Description

Technical Field

[0001] The present invention specifically relates to a battery glue laminating, folding and wrapping method, equipment and system. Background Art

[0002] With the continuous advancement of battery technology, especially in the production of lithium batteries, soft-pack batteries, and other high-performance batteries, the requirements for process precision of various internal battery components are becoming increasingly stringent. The battery's gluing, folding, winding, and curing processes, as core manufacturing steps, directly impact the battery's performance, reliability, and service life. During the gluing and curing processes, factors such as glue uniformity, thickness control, and curing effectiveness determine key battery properties such as sealing, battery capacity, and cycle stability. Therefore, high-precision control of these processes is crucial during battery production.

[0003] Currently, traditional mechanical equipment and manual labor are often used to ensure accurate plate folding and glue winding in battery production. However, as battery performance requirements increase, traditional production processes and quality control methods are gradually exposing some problems, mainly in the following aspects:

[0004] Folding the battery membrane is a critical step in battery production. The accuracy of the membrane folding directly affects the contact quality between the membrane and other components within the battery. Due to the precision limitations of traditional mechanical folding equipment and operational errors during the folding process, the folding angle, position, and alignment of the battery membrane are difficult to precisely control. This can lead to poor contact of the membrane in subsequent processes, compromising battery performance and quality.

[0005] During the battery wrapping process, the uniformity and thickness of the glue coating are key factors affecting battery quality. Traditional wrapping equipment often cannot monitor the uniformity and thickness of the glue coating in real time, resulting in the glue layer being too thick or too thin, which in turn affects the overall performance of the battery. Uneven glue coating can lead to incomplete curing and even defects such as bubbles and cracks during use, affecting the stability and safety of the battery.

[0006] During battery production, the curing process of the glue is also crucial. Incomplete curing or the presence of curing defects (such as bubbles and cracks) will directly affect the sealing performance and mechanical strength of the battery, thereby affecting the battery's service life and safety. Traditional curing processes usually rely on manual operation or simple temperature control equipment, making it difficult to achieve accurate real-time monitoring and feedback. The occurrence of curing defects often leads to rework and quality fluctuations, increasing production costs and reducing production efficiency. Summary of the Invention

[0007] In order to overcome the shortcomings and disadvantages of the existing technology, the primary purpose of the present invention is to provide a battery glue laminating, folding and wrapping method, equipment and system. This battery glue laminating, folding and wrapping method, equipment and system solves key technical problems such as inaccurate folding, uneven wrapping, and curing defects by integrating advanced image processing technology, visual monitoring and deep learning algorithms, as well as automated feedback control mechanisms, and can effectively improve the automation level, production efficiency and product quality of the battery production process.

[0008] The primary purpose of the present invention is achieved through the following technical solutions:

[0009] A battery adhesive folding and wrapping method includes the following steps:

[0010] The folding process of the battery film is monitored in real time by a camera, and the folding angle and position of the film are detected using a feature point detection algorithm. If the folded plate fails, the folding accuracy of the mechanical equipment is adjusted based on the image processing results. If the folded plate passes, the film enters the glue winding process.

[0011] Use visual sensors to monitor the glue coating during the glue winding process, and use image segmentation and deep learning technology to determine the uniformity and thickness of the glue layer. If the glue winding fails, the glue winding speed and glue coating equipment are adjusted in real time based on the test results. If the glue winding passes, the curing process begins.

[0012] Thermal imaging technology is used to monitor the temperature distribution during the glue curing process, and a high-resolution camera is used to check the surface of the cured glue to identify bubbles and cracks. If the curing is unqualified, the curing equipment is automatically adjusted and rework is performed. If the curing is qualified, the material enters the discharge process.

[0013] Preferably, the method for detecting the folding angle and position of the film using a feature point detection algorithm is:

[0014] Use industrial cameras to monitor the battery membrane folding process in real time, ensuring that the camera can obtain full-view images of the membrane;

[0015] Preprocess the captured original image, including noise removal, contrast enhancement, and edge enhancement;

[0016] The reference images of the membrane before and after folding are used as templates and compared with the real-time captured images;

[0017] Compare the similarity between the template and the real-time image through a sliding window to find the location of the folded part and determine the folded area of ​​the membrane;

[0018] The degree of match between the template and the real-time image is calculated. If the degree of match exceeds a preset threshold, the folding angle and position are considered to meet the requirements.

[0019] As a preferred method, the method of using image segmentation and deep learning technology to judge the uniformity and thickness of the glue layer is:

[0020] Use industrial cameras to capture real-time images during the glue winding process;

[0021] Image segmentation technology is used to separate the glue-coated area from the background in the image, and the boundary between the glue-coated area and the background is identified through the threshold segmentation algorithm;

[0022] After image segmentation, the convolutional neural network (CNN) is used to extract the features of the glue coating layer and evaluate the uniformity of the glue layer.

[0023] The network input is the glue area image after image segmentation;

[0024] The network output is a score of the glue layer uniformity, which is a score between 0 and 1. The closer to 1, the more uniform it is, and the closer to 0, the less uniform it is.

[0025] Based on the brightness of the glue layer in the image, the brightness of the coating area is analyzed to estimate the thickness of the glue;

[0026] The uniformity and thickness detection results output by the deep learning model are compared with the preset coating standards to determine whether the coating quality is qualified.

[0027] As a preferred method, the method of inspecting the surface of the cured glue by a high-resolution camera to identify air bubbles and cracks is as follows:

[0028] During the glue curing process, an infrared thermal imager is used to monitor the temperature distribution on the glue surface in real time;

[0029] After curing is completed, an industrial camera is used to capture images of the glue surface;

[0030] The uniformity of glue curing is judged by thermal imaging, and surface defects after curing are confirmed by visual inspection.

[0031] Preferably, the method for confirming surface defects after curing by visual inspection is:

[0032] Use threshold segmentation to process the image and extract possible defect areas on the glue surface;

[0033] By image segmentation, surface protrusions or circular transparent areas are identified from the image and marked as bubble areas;

[0034] The elongated linear defect areas are identified from the image by Canny edge and marked as crack areas.

[0035] Another technical problem to be solved by the present invention is to provide a battery glue folding and wrapping device, comprising:

[0036] The workbench includes a first rotating processing table for driving the batteries to be transported to each processing station, and a plurality of battery processing clamping claws provided on the first rotating processing table, and a second rotating processing table for driving the batteries to be transported to a recycling channel and a finished product channel, and a plurality of battery recycling clamping claws provided on the second rotating processing table;

[0037] A folding device is used to fold the battery on the battery processing clamping claw;

[0038] The glue wrapping device is used to wrap glue around the battery on the battery processing clamping claw;

[0039] A curing device, used for curing the battery on the battery processing clamping claw;

[0040] A folding plate detection device is used to monitor the folding process of the battery film in real time through a camera and detect the folding angle and position of the film using plate matching or feature point detection algorithms;

[0041] The glue winding detection device is used to monitor the glue coating during the glue winding process through visual sensors and use image segmentation and deep learning technology to determine the uniformity and thickness of the glue layer;

[0042] The curing monitoring device is used to monitor the temperature distribution during the glue curing process using thermal imaging technology, and to inspect the surface of the cured glue using a high-resolution camera to identify air bubbles and cracks.

[0043] Another technical problem to be solved by the present invention is to provide a battery glue laminating and folding plate wrapping system, comprising:

[0044] The folding plate detection module is used to monitor the folding process of the battery film in real time through a camera, and uses plate matching or feature point detection algorithms to detect the folding angle and position of the film. If the folding plate fails, the folding accuracy of the mechanical equipment is adjusted according to the detection results;

[0045] The glue winding detection module is used to monitor the glue coating during the glue winding process through visual sensors and use image segmentation and deep learning technology to determine the uniformity and thickness of the glue layer. If the glue winding fails, the glue winding speed and glue coating equipment are adjusted in real time based on the detection results;

[0046] The curing monitoring module uses thermal imaging technology to monitor the temperature distribution during the curing process of the glue. It also uses a high-resolution camera to inspect the surface of the cured glue to identify defects such as bubbles and cracks. If the curing fails, the curing equipment is automatically adjusted and rework is performed.

[0047] The automatic feedback control system is used to adjust the parameters of the corresponding process equipment in real time according to the detection results of each module, including the glue coating amount, glue coating speed, folding accuracy, glue winding speed, glue coating amount, and the temperature and time of the curing equipment.

[0048] Another technical problem to be solved by the present invention is to provide an electronic device, including a memory, a processor and a computer program stored in the memory and runnable on the processor. When the processor executes the program, a battery glue folding and wrapping method as described above is implemented.

[0049] Another technical problem to be solved by the present invention is to provide a computer-readable storage medium on which a computer program is stored, which, when executed by a processor, implements a battery glue-taping, folding and wrapping method as described above.

[0050] Compared with the prior art, the present invention has the following advantages:

[0051] This method uses a camera to monitor the folding process in real time, adopts plate matching or feature point detection algorithm to detect the angle and position of the folded plate, and adjusts the folding accuracy of the mechanical equipment in real time when the folded plate is unqualified, thereby effectively improving the folding accuracy and avoiding production defects caused by folding problems; this method uses a visual sensor to monitor the glue winding process, combines image segmentation and deep learning technology to judge the uniformity and thickness of the glue layer, and if unqualified, it can automatically adjust the glue winding speed to ensure the quality of the glue winding process.

[0052] This method uses thermal imaging technology to monitor the temperature distribution during the glue curing process, and uses a high-resolution camera to inspect the surface of the cured glue to promptly identify defects such as bubbles and cracks. If the curing is found to be unqualified, the curing equipment is automatically adjusted and rework is performed to ensure the curing quality of each battery. This method uses image processing, deep learning, thermal imaging and other technologies to achieve real-time monitoring and feedback of each process, and can automatically adjust equipment parameters (such as folding accuracy, glue coating amount, curing temperature, etc.), thereby improving production efficiency and ensuring product quality consistency. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 This is a flow chart of a battery glue-applying, folding, and wrapping method according to the present invention;

[0054] Figure 2 This is a structural diagram of a battery glue-laminating, folding and wrapping device according to the present invention. DETAILED DESCRIPTION

[0055] The specific implementation methods of the present invention are further described in detail to make the technical solutions of the present invention easier to understand and grasp.

[0056] Example

[0057] See Figure 1 As shown, a battery adhesive folding and wrapping method includes the following steps:

[0058] The folding process of the battery film is monitored in real time by a camera, and the folding angle and position of the film are detected using a feature point detection algorithm. If the folded plate fails to meet the requirements, the folding accuracy of the mechanical equipment is adjusted based on the image processing results. If the folded plate meets the requirements, the film enters the glue winding process.

[0059] Use visual sensors to monitor the glue coating during the glue winding process, and use image segmentation and deep learning technology to determine the uniformity and thickness of the glue layer. If the glue winding fails, the glue winding speed and glue coating equipment are adjusted in real time based on the test results. If the glue winding passes, the curing process begins.

[0060] Thermal imaging technology is used to monitor the temperature distribution during the glue curing process, and a high-resolution camera is used to check the surface of the cured glue to identify bubbles and cracks. If the curing is unqualified, the curing equipment is automatically adjusted and rework is performed. If the curing is qualified, the material enters the discharge process.

[0061] This method significantly reduces the need for manual intervention and adjustments by monitoring production equipment parameters (such as glue application amount, folding accuracy, and glue winding speed) in real time and automatically adjusting them based on feedback data. Automated control reduces human error and response time, improving production continuity and efficiency. Relying on efficient automated detection and adjustment systems, it reduces the need for manual intervention and lowers the cost of manual operation and detection. Furthermore, intelligent adjustments to equipment ensure efficient production line operation and shorten production cycles.

[0062] Through real-time data collection and monitoring of each process (such as image data, temperature distribution, and glue application amount), the entire production process has strong traceability. Production data for each batch can be recorded to facilitate subsequent quality review and troubleshooting. Thermal imaging technology is used to precisely monitor the curing process, ensuring temperature uniformity and quality during the glue curing process. This allows for the timely detection of defects such as bubbles and cracks, preventing unstable product performance caused by incomplete curing. This process not only optimizes product quality but also improves battery safety and durability.

[0063] The method for detecting the folding angle and position of the film using the feature point detection algorithm is as follows:

[0064] Use industrial cameras to monitor the battery membrane folding process in real time, ensuring that the camera can obtain full-view images of the membrane;

[0065] Preprocess the captured original image, including noise removal, contrast enhancement, and edge enhancement;

[0066] The reference images of the membrane before and after folding are used as templates and compared with the real-time captured images;

[0067] Compare the similarity between the template and the real-time image through a sliding window to find the location of the folded part and determine the folded area of ​​the membrane;

[0068] The degree of match between the template and the real-time image is calculated. If the degree of match exceeds a preset threshold, the folding angle and position are considered to meet the requirements.

[0069] By comparing reference images of the film before and after folding, the feature point detection algorithm accurately identifies the position and angle of the folding area. Sliding window technology compares the template and the real-time image pixel by pixel for similarity, ensuring high-precision detection of the folding position and angle. This method accurately determines whether the film is folded as expected, thereby reducing human error and ensuring product quality. Real-time camera monitoring can quickly capture any non-conforming conditions during the folding process, and algorithm-based feedback can quickly guide equipment adjustments to ensure folding accuracy and quality. Compared to traditional manual inspection, automated systems can respond in a shorter time, improving production efficiency.

[0070] Manual inspection in large-scale production is susceptible to fatigue, visual errors, or environmental factors, which can lead to omissions or errors. However, the use of image processing and feature point detection algorithms automates the inspection process, significantly reducing human intervention and ensuring that every product undergoes rigorous, standardized testing. The algorithms provide a unified standard, ensuring that each inspection follows the same rules, eliminating bias and inconsistencies in manual judgment. This makes the inspection results of folding angles and positions more reliable and avoids quality fluctuations caused by varying manual judgment standards.

[0071] Real-time monitoring of the folding process through image processing allows for timely identification and adjustment, avoiding the accumulation of substandard products and the resulting rework. This allows the production line to maintain efficient operation and reduces waste and downtime caused by errors. This automated inspection method reduces reliance on manual operations, reducing the need for labor during the production process, optimizing human resource allocation, and thus reducing overall production costs. Furthermore, reducing rework caused by manual errors also helps save material and time costs.

[0072] The method of using image segmentation and deep learning technology to judge the uniformity and thickness of the glue layer is:

[0073] Use industrial cameras to capture real-time images during the glue winding process;

[0074] Image segmentation technology is used to separate the glue-coated area from the background in the image, and the boundary between the glue-coated area and the background is identified through the threshold segmentation algorithm;

[0075] After image segmentation, the convolutional neural network (CNN) is used to extract the features of the glue coating layer and evaluate the uniformity of the glue layer.

[0076] The network input is the glue area image after image segmentation;

[0077] The network output is a score of the glue layer uniformity, which is a score between 0 and 1. The closer to 1, the more uniform it is, and the closer to 0, the less uniform it is.

[0078] Based on the brightness of the glue layer in the image, the brightness of the coating area is analyzed to estimate the thickness of the glue;

[0079] The uniformity and thickness detection results output by the deep learning model are compared with the preset coating standards to determine whether the coating quality is qualified.

[0080] Image segmentation technology can accurately identify glue coating areas, ensuring detailed analysis of every coating section. Combined with a convolutional neural network (CNN), this method can extract subtle features from the image, assess the uniformity of the glue layer, and accurately estimate the glue thickness through image brightness analysis. This high-precision detection method can effectively identify any unevenness or substandard thickness that may exist during the coating process, ensuring that the coating quality meets the expected standards. Automated detection greatly reduces the subjectivity and operational errors associated with manual inspection, ensuring that each inspection meets uniform standards. This means that the evaluation of coating quality during the production process is more objective and consistent, reducing the errors caused by manual judgment.

[0081] This method uses the uniformity score output by the deep learning model to provide a quantitative quality assessment for each batch of glue coating. This standardized quality inspection process effectively ensures consistency during the coating process, ensuring that every product meets the set quality standards, thereby improving product qualification rates. Accurate thickness estimation avoids quality issues caused by excessively thick or thin coatings, thereby reducing material waste and defective products caused by uneven coating. By adjusting the coating process promptly, glue material can be saved, production costs can be reduced, and rework of substandard products can be avoided.

[0082] The method of using a high-resolution camera to inspect the surface of the cured glue to identify air bubbles and cracks is as follows:

[0083] During the glue curing process, an infrared thermal imager is used to monitor the temperature distribution on the glue surface in real time;

[0084] After curing is completed, an industrial camera is used to capture images of the glue surface;

[0085] The uniformity of glue curing is judged by thermal imaging, and surface defects after curing are confirmed by visual inspection.

[0086] Infrared thermal imagers can monitor the temperature distribution on the glue surface in real time, thereby reflecting the uniformity of the glue curing. Temperature differences during the curing process often indicate uneven curing, which can lead to defects such as bubbles and cracks. Thermal imaging can detect uneven curing areas early, allowing adjustments to prevent problems. For example, areas that cure too quickly or too slowly can cause surface stress concentration, forming bubbles or cracks. By monitoring the curing process in real time, potential problems can be identified and resolved promptly, avoiding complex repairs after curing is complete and reducing overall production costs.

[0087] After the glue cures, a high-resolution industrial camera captures the cured surface, capturing extremely detailed image data. This image can be used to detect tiny bubbles, cracks, or other surface defects that, if not detected promptly, could impact the quality and performance of the final product. Combining thermal imaging data with visual inspection images allows for even more precise defect location. Thermal imaging helps reveal areas of uneven curing, while the industrial camera provides highly detailed surface images, helping to determine the specific defect type (e.g., bubbles, cracks, etc.), providing precise information for subsequent quality control and repair.

[0088] By promptly detecting surface defects after curing, we can prevent the accumulation of defective products during the production process. Rapidly identifying and removing defective products or repairing them significantly reduces rework and improves production efficiency. Promptly detecting defects during and after the curing process can reduce the flow of defective products and avoid wasting resources and time. Precise inspection and control ensures that the glue material is fully utilized and minimizes scrap during the production process.

[0089] The method for confirming surface defects after curing by visual inspection is:

[0090] Use threshold segmentation to process the image and extract possible defect areas on the glue surface;

[0091] By image segmentation, surface protrusions or circular transparent areas are identified from the image and marked as bubble areas;

[0092] The elongated linear defect areas are identified from the image by Canny edge and marked as crack areas.

[0093] Through threshold segmentation, image segmentation, and Canny edge detection, automated identification of glue surface defects can be achieved, reducing manual intervention. This not only improves detection efficiency but also ensures accuracy and consistency. Threshold segmentation extracts high-contrast areas in the image, accurately locating possible defect areas. Image segmentation methods can be further refined to identify surface ridges or circular transparent areas, clearly marking bubble areas. Canny edge detection is specifically designed to detect elongated cracks, ensuring that various types of defects (such as bubbles and cracks) are clearly located and distinguished.

[0094] This method not only identifies circular, transparent bubbles, but also accurately identifies thin, linear defects such as cracks through Canny edge detection. The combination of these two techniques provides greater flexibility for detecting different types of defects that may occur on glue-cured surfaces, enabling comprehensive capture of surface defects. By adjusting thresholds and segmentation parameters, the solution can flexibly adapt to changing detection requirements for defects that may form with different glue materials or under different curing conditions (such as bubbles and cracks).

[0095] Through image segmentation and edge detection, defect areas can be quickly extracted from large amounts of image data in a short period of time. The automation and efficiency of defect identification can significantly accelerate quality inspection on the production line, thereby improving overall production efficiency. This inspection method can promptly and accurately identify surface defects, ensuring that defective products are quickly eliminated, preventing them from flowing into the next production stage or the end user. This helps maintain product consistency and high quality, reducing rework and resource waste caused by defects.

[0096] See Figure 2 The battery glue folding and wrapping equipment includes:

[0097] The workbench includes a first rotating processing table 1 for driving batteries to be transported to various processing stations, and a plurality of battery processing clamping claws 2 provided on the first rotating processing table 1, and a second rotating processing table 5 for driving batteries to be transported to a recycling channel 3 and a finished product channel 4, and a plurality of battery recycling clamping claws 6 provided on the second rotating processing table 5;

[0098] A folding device 7 is used to fold the battery on the battery processing clamping claw;

[0099] The glue wrapping device 8 is used to wrap glue around the battery on the battery processing clamping claw;

[0100] Curing device 9, used for curing the battery on the battery processing clamping claw;

[0101] The folding plate detection device 10 is used to monitor the folding process of the battery membrane in real time through a camera and detect the folding angle and position of the membrane using a plate matching or feature point detection algorithm;

[0102] The glue winding detection device 11 is used to monitor the glue coating during the glue winding process through a visual sensor and use image segmentation and deep learning technology to determine the uniformity and thickness of the glue layer;

[0103] The curing monitoring device 12 is used to monitor the temperature distribution during the curing process of the glue using thermal imaging technology, and to inspect the surface of the cured glue using a high-resolution camera to identify air bubbles and crack defects.

[0104] A battery glue laminating and folding plate wrapping system, comprising:

[0105] The folding plate detection module is used to monitor the folding process of the battery film in real time through a camera, and uses plate matching or feature point detection algorithms to detect the folding angle and position of the film. If the folding plate fails, the folding accuracy of the mechanical equipment is adjusted according to the detection results;

[0106] The glue winding detection module is used to monitor the glue coating during the glue winding process through visual sensors and use image segmentation and deep learning technology to determine the uniformity and thickness of the glue layer. If the glue winding fails, the glue winding speed and glue coating equipment are adjusted in real time based on the detection results;

[0107] The curing monitoring module uses thermal imaging technology to monitor the temperature distribution during the curing process of the glue. It also uses a high-resolution camera to inspect the surface of the cured glue to identify defects such as bubbles and cracks. If the curing fails, the curing equipment is automatically adjusted and rework is performed.

[0108] The automatic feedback control system is used to adjust the parameters of the corresponding process equipment in real time according to the detection results of each module, including the glue coating amount, glue coating speed, folding accuracy, glue winding speed, glue coating amount, and the temperature and time of the curing equipment.

[0109] This embodiment also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, a battery adhesive laminating, folding, and wrapping method as described above is implemented.

[0110] This embodiment also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, a battery adhesive laminating, folding and wrapping method as described above is implemented.

[0111] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0112] Those skilled in the art will clearly understand that for the sake of convenience and brevity in description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0113] Of course, the above are only typical examples of the present invention. In addition to these, the present invention may also have many other specific embodiments. Any technical solutions formed by equivalent substitution or equivalent transformation shall fall within the scope of protection claimed by the present invention. Of course, the above are only typical examples of the present invention. In addition to these, the present invention may also have many other specific embodiments. Any technical solutions formed by equivalent substitution or equivalent transformation shall fall within the scope of protection claimed by the present invention.

Claims

1. A battery glue folding and wrapping method, characterized in that: The following steps are involved: The folding process of the battery film is monitored in real time by a camera, and the folding angle and position of the film are detected using a feature point detection algorithm. If the folded plate fails, the folding accuracy of the mechanical equipment is adjusted based on the image processing results. If the folded plate passes, the film enters the glue winding process. Use visual sensors to monitor the glue coating during the glue winding process, and use image segmentation and deep learning technology to determine the uniformity and thickness of the glue layer. If the glue winding fails, the glue winding speed and glue coating equipment are adjusted in real time based on the test results. If the glue winding passes, the curing process begins. Thermal imaging technology is used to monitor the temperature distribution during the glue curing process, and a high-resolution camera is used to inspect the cured glue surface to identify air bubbles and cracks. If the curing fails, the curing equipment is automatically adjusted and rework is performed. If the curing passes, the glue enters the discharge process. The method for detecting the folding angle and position of the film using the feature point detection algorithm is as follows: Use industrial cameras to monitor the battery membrane folding process in real time, ensuring that the camera can obtain full-view images of the membrane; Preprocess the captured original image, including noise removal, contrast enhancement, and edge enhancement; The reference images of the membrane before and after folding are used as templates and compared with the real-time captured images; Compare the similarity between the template and the real-time image through a sliding window to find the location of the folded part and determine the folded area of ​​the membrane; Calculate the degree of match between the template and the real-time image. If the match exceeds the preset threshold, the folding angle and position are considered to meet the requirements. The method of using image segmentation and deep learning technology to judge the uniformity and thickness of the glue layer is: Use industrial cameras to capture real-time images during the glue winding process; Image segmentation technology is used to separate the glue-coated area from the background in the image, and the boundary between the glue-coated area and the background is identified through the threshold segmentation algorithm; After image segmentation, the convolutional neural network (CNN) is used to extract the features of the glue coating layer and evaluate the uniformity of the glue layer. The network input is the glue area image after image segmentation; The network output is a score of the glue layer uniformity, which is a score between 0 and 1. The closer to 1, the more uniform it is, and the closer to 0, the less uniform it is. Based on the brightness of the glue layer in the image, the brightness of the coating area is analyzed to estimate the thickness of the glue; Compare the uniformity and thickness test results output by the deep learning model with the preset coating standards to determine whether the coating quality is qualified; The method of using a high-resolution camera to inspect the surface of the cured glue to identify air bubbles and cracks is as follows: During the glue curing process, an infrared thermal imager is used to monitor the temperature distribution on the glue surface in real time; After curing is completed, an industrial camera is used to capture images of the glue surface; Use thermal imaging to determine the uniformity of glue curing, and then use visual inspection to confirm surface defects after curing; The method for confirming surface defects after curing by visual inspection is: Use threshold segmentation to process the image and extract possible defect areas on the glue surface; By image segmentation, surface protrusions or circular transparent areas are identified from the image and marked as bubble areas; The elongated linear defect areas are identified from the image by Canny edge and marked as crack areas.

2. The glue winding equipment used in the battery glue folding and glue winding method according to claim 1 is characterized in that: Includes: The workbench includes a first rotating processing table for driving the batteries to be transported to each processing station, and a plurality of battery processing clamping claws provided on the first rotating processing table, and a second rotating processing table for driving the batteries to be transported to a recycling channel and a finished product channel, and a plurality of battery recycling clamping claws provided on the second rotating processing table; Gluing device, used for gluing batteries on battery processing clamping claws; A folding device is used to fold the battery on the battery processing clamping claw; The glue wrapping device is used to wrap glue around the battery on the battery processing clamping claw; A curing device, used for curing the battery on the battery processing clamping claw; Glue coating detection device, used to capture images of the glue coating area on the battery surface using an industrial camera and detect glue coating uniformity, thickness, and coating defects using image processing algorithms; A folding plate detection device is used to monitor the folding process of the battery film in real time through a camera and detect the folding angle and position of the film using plate matching or feature point detection algorithms; The glue winding detection device is used to monitor the glue coating during the glue winding process through visual sensors and use image segmentation and deep learning technology to determine the uniformity and thickness of the glue layer; The curing monitoring device is used to monitor the temperature distribution during the glue curing process using thermal imaging technology, and to inspect the surface of the cured glue using a high-resolution camera to identify air bubbles and cracks.

3. The battery adhesive wrapping system of the folding plate wrapping method according to claim 1 is characterized in that: Includes: The glue coating inspection module is used to capture images of the glue coating area on the battery surface using an industrial camera and detect the uniformity, thickness, and coating defects of the glue coating using an image processing algorithm. If the glue coating fails, the coating amount and speed of the glue coating equipment are adjusted in real time based on the inspection results; The folding plate detection module is used to monitor the folding process of the battery film in real time through a camera, and uses plate matching or feature point detection algorithms to detect the folding angle and position of the film. If the folding plate fails, the folding accuracy of the mechanical equipment is adjusted according to the detection results; The glue winding detection module is used to monitor the glue coating during the glue winding process through visual sensors and use image segmentation and deep learning technology to determine the uniformity and thickness of the glue layer. If the glue winding fails, the glue winding speed and glue coating equipment are adjusted in real time based on the detection results; The curing monitoring module uses thermal imaging technology to monitor the temperature distribution during the curing process of the glue. It also uses a high-resolution camera to inspect the surface of the cured glue to identify air bubbles and cracks. If the curing fails, the curing equipment is automatically adjusted and rework is performed. The automatic feedback control system is used to adjust the parameters of the corresponding process equipment in real time according to the detection results of each module, including the glue coating amount, glue coating speed, folding accuracy, glue winding speed, glue coating amount, and the temperature and time of the curing equipment.

4. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor. When the processor executes the program, a battery adhesive laminating, folding and wrapping method as claimed in claim 1 is implemented.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, a battery adhesive laminating, folding and wrapping method as described in claim 1 is implemented.

Images