New energy battery packing detection method, device, electronic equipment and storage medium

Abstract

The present application relates to a new energy battery packing detection method, device, electronic device and storage medium, which control the code scanning camera to shoot the battery within the corresponding field of view to obtain a scanned image; control the wide-angle camera to take a picture of the battery to obtain a wide-angle image; perform image recognition processing on each of the scanned images to obtain the position information and identification code information of each battery, and identify the bare shell and positive and negative pole directions of the battery through the template matching method and the position information; map the identified position information, identification code information, bare shell and positive and negative pole directions to the wide-angle image through dual-camera calibration technology to obtain a summary image; count the positive and negative pole directions of the battery according to the summary image, and mark the battery cell marks with fewer directions in the summary image to obtain a detection image of the battery. The solution provided by the present application solves the cumbersome operation and error-prone problems of battery cell pre-packaging detection, and the positioning and identification are accurate and fast.

Description

Technical Field

[0001] The present application relates to the technical field of battery packaging detection, and in particular to a new energy battery cell packaging detection method, device, electronic equipment and storage medium. Background Art

[0002] In the production of new energy batteries, there are many automated processes, but the degree of automation at the end of the production line is not high enough. For example, before packing, the production line workers need to check the appearance of the batteries one by one, put them on the pallet in order, and then scan the QR code one by one to record the outbound information; at the same time, there will be multiple layers of batteries on a pallet, separated by foam pallets, each layer needs to have desiccant and must have it in the four corners, and no foreign matter can appear inside; the battery has positive and negative electrodes, so it needs to be placed in a unified direction when arranged, and if it is placed in the wrong direction, it needs to be discovered and corrected in time; during the production process, normal batteries will be coated on the outside and a black cover plate covering the surface will be attached to the top. Due to operation or other factors, the black cover plate may fall off. If it does not fall off, it is considered to be a bare shell, and it also needs to be discovered and reworked in time. These processes are extremely cumbersome to operate manually, including scanning the code one by one, and long-term bending requires high requirements for personnel. During the inspection, it is greatly affected by the subjective influence of personnel, and it is easy to make mistakes due to fatigue. Existing barcode scanning devices generally scan in a small range, that is, the field of view is relatively small. For the case of a layer of battery cells, a single barcode scanning camera can only scan one-ninth of the cases while ensuring the accuracy and success rate; directly combining the barcode scanning cameras together will cause the problem of cross-field and repeated scanning. Summary of the invention

[0003] The embodiments of the present application provide a method, device, electronic device and storage medium for new energy battery packing detection, so as to at least solve the problem of low accuracy of barcode scanning recognition in battery packing detection in the related art.

[0004] In a first aspect, an embodiment of the present application provides a new energy battery packing detection method, which is applied to a new energy battery packing device, wherein the new energy battery packing device includes a wide-angle camera and multiple code scanning cameras, and the method includes:

[0005] Control the barcode scanning camera to shoot the battery cells within the corresponding field of view to obtain a scanned image, wherein different barcode scanning cameras have different field of view; control the wide-angle camera to take a picture of the battery cells to obtain a wide-angle image, wherein the wide-angle image contains all the battery cells;

[0006] Performing image recognition processing on each of the scanned images to obtain position information and identification code information of each battery cell, and identifying the bare shell and positive and negative electrode directions of the battery cell by using a template matching method and the position information;

[0007] Mapping the identified position information, identification code information, bare shell and positive and negative electrode directions onto the wide-angle image through dual-camera calibration technology to obtain a summary image;

[0008] The positive and negative directions of the battery cells are counted according to the summary image, and the battery cell marks in the directions with fewer numbers are marked in the summary image to obtain a detection image of the battery cells.

[0009] In one embodiment, the method further comprises:

[0010] Performing desiccant target recognition and foreign object target recognition on the wide-angle image to determine whether there is desiccant information and foreign objects in the packaging device;

[0011] If desiccant or foreign matter is identified, desiccant location information and foreign matter location information are extracted;

[0012] The positions of the desiccant and the foreign matter are marked in the detection image according to the desiccant position information and the foreign matter position information to obtain a comprehensive detection image.

[0013] In one embodiment, the method further comprises:

[0014] Acquire a battery cell packaging template image, and perform matching analysis between the summary image and the battery cell packaging template image to obtain a matching result;

[0015] Determine whether the battery is missing according to the matching result, and if so, mark the position of the missing battery on the detection image to obtain missed detection information;

[0016] If the missed inspection information indicates that there is a battery cell at the current missed inspection position, but the corresponding identification code information is missing, the operator is guided to use a barcode scanner to perform a supplementary scan of the missed inspection position according to the missed inspection information to obtain a supplementary scan image;

[0017] The scanned image is fused with the summary image to obtain a complete detection image.

[0018] In one embodiment, the new energy battery packing detection further includes an optical projector, and the method further includes:

[0019] Acquire the location information, identification code information, desiccant location information, foreign matter location information and missed detection information to set corresponding indication icons;

[0020] Acquire an indication requirement for setting, and control the optical projector according to the indication requirement to map a corresponding indication icon on a surface of a battery cell at a corresponding position.

[0021] In a second aspect, an embodiment of the present application provides a new energy battery packing detection device, comprising:

[0022] The movable shaft bracket that can move up and down is installed on the industrial computer to support the code scanning module and light source;

[0023] A code scanning module, mounted on the movable shaft bracket, for collecting images of the chip;

[0024] A light source, mounted on the movable shaft bracket, for providing a stable lighting environment;

[0025] The industrial computer is used to control the movable shaft bracket, the code scanning module and the light source to perform corresponding actions, and execute the new energy battery cell packaging detection method described in any of the above embodiments.

[0026] In one embodiment, the code scanning module includes:

[0027] A plurality of barcode scanning cameras are installed on the movable shaft bracket, each of the barcode scanning cameras is used to photograph the battery cells within the corresponding field of view to obtain a scanned image;

[0028] A wide-angle camera is installed in the middle of the barcode scanning camera and is used to take pictures of all the cells to obtain a wide-angle image;

[0029] An optical projector is installed around the wide-angle camera and is used to project detection information onto the surface of the battery cell.

[0030] In one embodiment, the code scanning cameras are distributed in an equidistant grid, and the fields of view of adjacent code scanning cameras overlap.

[0031] In one embodiment, the device further comprises a movable carrier, wherein the movable carrier is used to carry the industrial computer and the movable shaft bracket, and transport the industrial computer and the movable shaft bracket to the position of the battery cell to be identified.

[0032] In a third aspect, an embodiment of the present application provides a computer device, comprising 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, the new energy battery cell packaging detection method as described in the second aspect above is implemented.

[0033] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the new energy battery cell packaging detection method as described in the second aspect above.

[0034] The array code scanning device, recognition method, equipment and storage medium of the identification code provided in the embodiments of the present application have at least the following technical effects:

[0035] The solution provided in this application solves the cumbersome operations and error-prone problems of pre-packaging inspection of battery cells. It has accurate positioning and fast speed. It only takes about 12 seconds from taking pictures to giving results. Compared with the 3-4 minutes of manual scanning inspection one by one, the time is greatly shortened, which can well meet production needs.

[0036] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0038] Figure 1 This is a flow chart of a new energy battery packing detection method provided in one embodiment of the present application;

[0039] Figure 2 It is a structural schematic diagram of a new energy battery packing detection device provided in one embodiment of the present application;

[0040] Figure 3 This application Figure 2 A schematic diagram of the structure of a code scanning module provided in an embodiment;

[0041] Figure 4 is a flow chart of a new energy battery packing detection method provided by another embodiment of the present application;

[0042] Figure 5 is a flow chart of a new energy battery packing detection method provided by another embodiment of the present application;

[0043] Figure 6 It is a test effect diagram of the new energy battery packing test method of the present application;

[0044] Figure 7 It is a schematic diagram of the structure of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0046] Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. In addition, it can also be understood that although the efforts made in this development process may be complicated and lengthy, for ordinary technicians in this field related to the content disclosed in this application, some changes in design, manufacturing or production based on the technical content disclosed in this application are just conventional technical means, and should not be understood as insufficient content disclosed in this application.

[0047] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0048] Unless otherwise defined, the technical terms or scientific terms involved in this application shall be understood by persons with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantity limitation and may indicate the singular or plural. The terms "include", "comprise", "have" and any of their variations involved in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, battery cell or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include unlisted steps or units, or may also include other steps or units inherent to these processes, methods, batteries or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships, for example, "A and / or B" may mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0049] In one embodiment, the embodiment of the present application provides a new energy battery cell packaging detection device, including: a movable shaft bracket that can move up and down, installed on an industrial computer, used to support a barcode scanning camera and a light source; a barcode scanning module, installed on the movable shaft bracket, used to obtain a scanned image of the identification code; a light source, used in conjunction with the barcode scanning camera to provide a stable lighting environment; an industrial computer, used to control the movable shaft bracket, the barcode scanning module and the light source to perform corresponding actions, and analyze the image to identify the location information of the battery cell. The device of the present application also includes a display device. After the industrial computer obtains the image captured by the barcode scanning module and performs image processing, it displays the processing result on the display device for the operator to observe.

[0050] The code scanning module includes: a plurality of code scanning cameras installed on a movable axis bracket, the code scanning cameras are distributed in an equidistant grid, and the field of view of adjacent code scanning cameras overlaps. Each of the code scanning cameras is used to scan the identification code of some battery cells to obtain a scanned image; a wide-angle camera is located in the middle of the plurality of code scanning cameras to take pictures of all battery cells to obtain a wide-angle image; an optical projector is installed around the wide-angle camera to project the code scanning result onto the surface of the battery cell.

[0051] In another preferred embodiment, the device further comprises a carrying device and a movable carrier, specifically Figure 1 As shown, the carrying device is fixed on the movable carrier and is used to carry the industrial computer and the movable shaft bracket; the movable carrier is used to transport the carrying device to the position of the battery cell to be scanned.

[0052] In one embodiment, a new energy battery packing detection method is provided for identifying the position, bare shell, and direction of the battery, and mapping the information onto a wide-angle camera image. The new energy battery packing detection method of the embodiment of the present application is applied to a new energy battery packing device, which includes a wide-angle camera and multiple code scanning cameras. Figure 1 , the application method includes the following steps.

[0053] Step S1, controlling the barcode scanning camera to shoot the battery cells within the corresponding field of view to obtain a scanned image, wherein different barcode scanning cameras have different field of view; controlling the wide-angle camera to shoot the battery cells to obtain a wide-angle image, wherein the wide-angle image contains all the battery cells;

[0054] Step S2, performing image recognition processing on each of the scanned images to obtain the position information and identification code information of each battery cell, and identifying the bare shell and the positive and negative electrode directions of the battery cell by a template matching method and the position information;

[0055] Step S3, mapping the identified position information, identification code information, bare shell and positive and negative electrode directions onto the wide-angle image through dual-camera calibration technology to obtain a summary image;

[0056] Step S4, counting the positive and negative directions of the battery cells according to the summary image, and marking the battery cell marks in the directions with fewer numbers in the summary image to obtain a detection image of the battery cells.

[0057] In another preferred embodiment, desiccant target recognition and foreign matter target recognition are performed on the wide-angle image to determine whether there is desiccant information and foreign matter in the packaging device; if desiccant or foreign matter is identified, the desiccant position information and the foreign matter position information are extracted; the positions of the desiccant and the foreign matter are marked in the detection image according to the desiccant position information and the foreign matter position information to obtain a comprehensive detection image.

[0058] In another preferred embodiment, a battery missed detection re-scanning technology is included, which is used to re-scan the battery cells whose barcodes are not scanned or whose identification fails. Specifically, the battery cell packaging template image is obtained, and the summary image is matched and analyzed with the battery cell packaging template image to obtain a matching result; based on the matching result, it is determined whether the battery is missing, and if so, the position of the missing battery is marked on the detection image to obtain missed detection information; if the missed detection information indicates that there is a battery cell at the current missed detection position, but the corresponding identification code information is missing, then according to the missed detection information, the operator is guided to use a barcode scanner to re-scan the missed detection position to obtain a re-scanned image; the re-scanned image is merged with the summary image to obtain a complete detection image.

[0059] In a preferred embodiment, the new energy battery cell packaging detection also includes an optical projector. Therefore, the industrial computer can also obtain the position information, identification code information, desiccant position information, foreign matter position information and missed detection information to set corresponding indication icons; obtain the indication requirements for setting, and control the optical projector to map the corresponding indication icons on the battery cell surface at the corresponding position according to the indication requirements.

[0060] In this application, objects in images are mainly identified through deep learning algorithms. First, the collected images need to be preprocessed, including denoising, grayscale, binarization, etc., to improve image quality and reduce the complexity of subsequent processing, thereby ensuring that the image data is suitable for deep learning and template matching operations.

[0061] Then, using a deep learning algorithm, an image recognition model is trained to identify bare shell cells in the image. During the model training process, a data set needs to be constructed, that is, a large number of images of bare shell and non-bare shell cells are collected for training and verifying the deep learning model. A deep learning architecture such as a convolutional neural network (CNN) can be used to train the model to identify bare shell features. Through the high recognition ability of the image recognition model, bare shell cells can be automatically detected, improving the accuracy and efficiency of detection.

[0062] More specifically, building an image recognition model based on deep learning mainly includes the following steps:

[0063] 1. Data collection: collect image data of bare-shell cells and non-bare-shell cells. These images should be diverse, including different backgrounds, lighting conditions, angles, etc.

[0064] 2. Data preprocessing, including image cropping, scaling, rotation correction, grayscale, standardization, etc. At the same time, the image is annotated to mark the location of the bare shell battery cell;

[0065] 3. Select the model architecture and determine the deep learning model architecture suitable for the task. You can choose an existing convolutional neural network (CNN) architecture, such as AlexNet, VGGNet, ResNet, etc., or design a custom network structure;

[0066] 4. Model training: Use the collected and preprocessed data to train the deep learning model, and divide the data set into training set, validation set, and test set. Use the training set to train the model, and use the validation set to adjust the model parameters to prevent overfitting;

[0067] 5. Hyperparameter tuning: find the optimal model parameters, improve model performance, adjust hyperparameters such as learning rate, batch size, and number of iterations, and use methods such as cross-validation to evaluate the performance of different parameter combinations;

[0068] 6. Finally, a trained image recognition model is obtained, and then the trained model is applied to the actual bare shell battery cell recognition task, such as integrating the model into the image recognition system of the production line (such as the packaging detection device of this application) to achieve real-time or batch bare shell battery cell recognition.

[0069] For the template matching in this application to identify the battery direction, first prepare a standard image, such as creating a standard template image of the battery packaging state, in which the placement of the battery cells, desiccant, etc. meet the user's requirements. Then match the collected cell image with the template image, and determine the direction of the battery by calculating the similarity. In the image recognition process, cell recognition can also be performed through feature extraction, such as extracting features from the image that help identify the bare shell and direction, such as the edge, shape, and tab position of the battery, and using these features to improve the accuracy of the recognition algorithm.

[0070] In this application, the local image information obtained by each barcode scanning camera is mapped to the image of the wide-angle camera by using dual-camera calibration technology. The dual-camera calibration technology involves a calibration process between two camera systems to ensure that images obtained from two different perspectives can be accurately associated and analyzed. In the dual-camera calibration technology process, each camera has its own internal and external parameters. The internal parameters include focal length, principal point coordinates, etc., while the external parameters describe the position and orientation of the camera in the world coordinate system. The camera parameters are usually determined using a calibration plate with a known pattern (such as a checkerboard or dot pattern). In a dual-camera system, the same object will present different projections in the images of the two cameras, and the calibration process needs to associate these projections into a unified spatial coordinate system.

[0071] The specific calibration process is described in the following steps:

[0072] 1. Camera calibration, calibrate each individual camera to determine its internal and external parameters. This is usually done by taking images of the calibration plate at different positions and angles;

[0073] 2. Feature extraction: extract feature points from the calibration plate image taken by each camera. These feature points are identifiable in the image and can be matched in different images.

[0074] 3. Feature matching, finding corresponding feature point pairs in the images of the two cameras. This can be achieved through a variety of feature matching algorithms, such as descriptor-based matching or geometric consistency-based matching;

[0075] 4. Establish spatial coordinates. Use feature point pairs and camera parameters to establish the spatial coordinates of the object under the perspectives of two cameras through mathematical methods (such as epipolar geometry);

[0076] 5. Calibration matrix calculation, calculate a calibration matrix that transforms the image coordinates of one camera into the coordinate system of another camera, or into a common world coordinate system;

[0077] 6. Verification and optimization, verify the accuracy of the calibration results and improve the calibration accuracy through an iterative optimization process.

[0078] Dual-camera calibration is a key step in ensuring that multiple camera systems can work together and provide accurate spatial information. In automated inspection and quality control systems, this technology can help achieve more precise object positioning and measurement.

[0079] The recognition results (including location information, bare shell and direction information) are marked and displayed on the wide-angle camera image and uploaded to the system for subsequent processing. At the same time, for cells identified as bare shell or with the wrong direction, the system will issue a warning and classify or rework them as needed.

[0080] In summary, the device and method provided by the embodiment of the present application replace the traditional manual detection method with an automated image recognition system, significantly improving the detection speed. It only takes about 12 seconds from taking pictures to giving results, which greatly shortens the time consumption compared to 3-4 minutes of manual scanning detection one by one. The automated detection process reduces the reliance on manual operation, reduces the physical requirements of operators for repetitive labor such as long-term bending, and reduces fatigue and errors caused by manual operation. Using deep learning and template matching methods, this solution can more accurately identify key information such as the position, bare shell, and direction of the battery, reducing the uncertainty affected by subjective factors during manual inspection. Enhance the flexibility and scalability of the system. The array scanning technology allows the number and layout of cameras to be adjusted as needed, so that the system can adapt to production lines of different sizes and different types of battery detection requirements. By reducing manual participation and increasing the detection speed, this solution helps to reduce the overall production cost, and at the same time, due to the reduction of errors and rework, it also reduces the cost loss caused by quality problems. Improve the working environment. Automated detection reduces the need for manual operation on the production line, thereby improving the working environment and reducing work intensity. Improve data management efficiency. This solution can quickly and accurately integrate and record test data, facilitate subsequent data management and analysis, and improve data management efficiency. Enhance system reliability and stability. Through the optimized design of hardware and software, this solution provides a stable and reliable detection system, reducing production interruptions caused by equipment failure. Realize automation of quality control. This solution uses automation technology to control battery quality, including automatic detection of battery appearance, QR code, positive and negative pole direction, desiccant and foreign matter, ensuring the consistency and reliability of product quality. Provide real-time feedback and processing capabilities. The system can feedback test results in real time, facilitating quick decision-making or subsequent processing, such as automatic sorting and marking of defective products. It has a missed detection re-scanning function. For cells that fail to scan barcodes or fail to identify, the system provides re-scanning technology to ensure the integrity of the detection and reduce the possibility of missed detection.

[0081] In a specific embodiment, a battery cell packaging detection device is provided, such as Figure 2 and Figure 3 As shown, Figure 2 The left side is the initial state, the right side is the working state, the yellow part is the tray, and the purple small square is the chip. The bottom of the device in this embodiment is an electric forklift 40, which can carry the code scanning device to the designated area; it carries an industrial computer 30 and a movable shaft bracket 10 that can move up and down; a code scanning module 20 and a light source 40 for lighting (the light source 40 used in this embodiment is a light strip, Figure 1 Not shown) is mounted next to the code scanning module on the bracket 10.

[0082] The code scanning module 20 is as follows Figure 3 As shown, it includes a barcode scanning camera 21, a wide-angle camera 22 and an optical projector 23. The barcode scanning cameras 21 of this embodiment are installed on the bracket 10 in three rows and four columns. A wide-angle camera 22 (blue) is installed in the middle of all the barcode scanning cameras 21. All cameras face directly downward, and an optical projector 23 (brown) is installed next to the wide-angle camera 22. The green line is a strip light source 40, which is installed between every two rows of barcode scanning cameras 21 to ensure that there is a strip light source 40 on both sides of each row of barcode scanning cameras 21. In this application, the shooting area of ​​each barcode scanning camera 21 is different, and each barcode scanning camera 21 is responsible for a different area. The purpose of including all batteries in the shooting range is achieved through multiple barcode scanning cameras 21, but there will be some cross-fields between every two barcode scanning cameras 21 to ensure that a code will not be captured by only half of the two cameras because it is at the junction.

[0083] The embodiments of the present invention are directed to Figure 1 and Figure 2 The device provides a packaging detection method based on an array scanning camera, such as Figure 4, including: using a barcode scanning camera to obtain all battery pictures; processing each barcode scanning camera picture to identify the battery position; and using deep learning and template matching to identify the bare shell and direction at the identified position; mapping the information obtained by each barcode scanning camera to the wide-angle camera image through dual-camera calibration technology. Specifically, this application maps the battery position and the position and code value of the QR code, as well as the bare shell information, direction, desiccant position, and foreign matter position to the wide-angle camera to obtain summary information; because there needs to be a certain cross-repetitive field of view between each two cameras, all detected information will be repeated, so it is necessary to repeatedly filter the summarized information; according to the summarized information, the battery position is sorted into rows and columns; according to the summarized information, the majority of the positions in the positive and negative directions are judged to distinguish the batteries with the wrong direction. Positive and negative are the matched directions mentioned above. Generally, there are only two directions for placing a layer of batteries, and the direction is required to be unified, so the majority direction is counted as the correct direction, and the other direction is marked as the wrong direction; it is indeed the minority obeys the majority.

[0084] In this application, it is necessary to identify each image of the barcode scanning camera, because the images of the barcode scanning camera are basically front-view and less affected by perspective deformation; the deep learning target detection algorithm is used to locate the position of all batteries in the image and frame the position of the battery. While using the deep learning target detection algorithm to detect the battery position, the battery type label can be output at the same time to distinguish the bare shell; after locating the battery position, the entire battery area is cut out from the original image, and a pre-made directional template is used for matching to determine the direction.

[0085] In the embodiment of the present application, dual-camera calibration means that the information captured by each camera is based on the current camera, that is, the position of the object relative to the current camera. If the position observed by the current camera is to be transferred to the position observed by another camera (that is, the reference system has changed), it is necessary to know the relative position relationship of the two cameras. At this time, calibration is required. After the calibration is completed, the relative positions of the same object under the two cameras can be matched.

[0086] In this application, the summary is divided into rows and columns according to the location of the battery, such as Figure 6 All batteries are arranged in neat rows and columns. The center point of the battery is extracted and divided into a specified number of rows and columns, and then divided into intervals based on the location of the center point.

[0087] In a preferred embodiment, deep learning can also be used to detect desiccant targets on wide-angle camera images, and to detect the presence of desiccant in specified areas; deep learning can be used to detect foreign objects on wide-angle camera images; all information is drawn and displayed on the wide-angle image, and uploaded to the system at the same time. Similar to the previous battery cell position detection and bare shell recognition, a batch of data is first collected, and the foreign objects in the image are manually identified, and the labeled data is sent to the deep learning framework for training to obtain a model. The information drawn on the wide-angle image includes the battery position, the position and total number of QR codes, the success mark of each battery, the position of the desiccant, the position of the foreign object, the row and column information of each battery, the bare shell mark, and the direction mark; the purpose is to display the test results, and the workers can see the result map to know which ones are successful and which ones have problems and need to be adjusted.

[0088] A fourth aspect of the embodiments of the present invention provides a battery missed detection scan technology, such as Figure 5 , including: using the third aspect of the embodiment to obtain all required information with the wide-angle camera as the reference coordinate system; displaying the position where the barcode is not scanned or the recognition failure is not determined on the image; displaying the position where the recognition failure is determined on the software interface and can be clicked; clicking the specified position to convert the position under the wide-angle camera to the position under the optical machine (which can be regarded as a camera) through the dual-camera calibration technology; using the optical machine to project the missed inspection information on the corresponding battery surface; manually using the barcode scanner to perform a supplementary scan.

[0089] like Figure 6 As shown, the figure contains a variety of indicator marks, among which the small green square represents a qualified battery, the small yellow square represents a scanned QR code, the green circle represents an identified desiccant, and the red circle represents an identified foreign object; the battery cell detection method of the present application is effective and easy to use, and is perfectly applied in actual production, and has great research significance and reference value for similar pain points and difficulties.

[0090] In a third aspect, an embodiment of the present application provides an electronic device, Figure 7 FIG. 1 is a block diagram of an electronic device according to an exemplary embodiment. Figure 7 As shown, the electronic device may include a processor 71 and a memory 72 storing computer program instructions.

[0091] Specifically, the processor 71 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0092] Among them, the memory 72 may include a large-capacity memory for data or instructions. For example, but not limitation, the memory 72 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 72 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 72 may be inside or outside the data processing device. In a specific embodiment, the memory 72 is a non-volatile memory. In a specific embodiment, the memory 72 includes a read-only memory (ROM) and a random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM) or a flash memory (FLASH), or a combination of two or more of these. Under appropriate circumstances, the RAM can be a static random access memory (SRAM) or a dynamic random access memory (DRAM), wherein the DRAM can be a fast page mode dynamic random access memory (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0093] The memory 72 may be used to store or cache various data files required for processing and / or communication, as well as possible computer program instructions executed by the processor 71 .

[0094] The processor 71 implements any one of the new energy battery cell packaging detection methods in the above embodiments by reading and executing computer program instructions stored in the memory 72.

[0095] In one embodiment, the electronic device may further include a communication interface 73 and a bus 70. Figure 6 As shown, the processor 71, the memory 72, and the communication interface 73 are connected via a bus 70 and communicate with each other.

[0096] The communication interface 73 is used to implement communication between the modules, devices, units and / or equipment in the embodiment of the present application. The communication port 13 can also implement data communication with other components such as: external devices, image / data acquisition equipment, databases, external storage, and image / data processing workstations.

[0097] The bus 70 includes hardware, software or both, and couples the components of the electronic device to each other. The bus 70 includes but is not limited to at least one of the following: a data bus, an address bus, a control bus, an expansion bus, and a local bus. By way of example and not limitation, bus 70 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses or a combination of two or more of these. Where appropriate, bus 70 may include one or more buses. Although embodiments of the present application describe and illustrate a particular bus, the present application contemplates any suitable bus or interconnect.

[0098] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a program stored thereon, and when the program is executed by a processor, the new energy battery cell packaging detection method provided in the first aspect is implemented.

[0099] The readable storage medium may include but is not limited to: a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device or any suitable combination of the above.

[0100] In a possible implementation, the present invention can also be implemented in the form of a program cell, which includes a program code. When the program cell is running on a terminal device, the program code is used to enable the terminal device to execute the steps of the new energy cell packaging detection method provided in the first aspect.

[0101] The program code for executing the present invention may be written in any combination of one or more programming languages, and may be executed entirely on a user device, partially on a user device, as an independent software package, partially on a user device and partially on a remote device, or entirely on a remote device.

[0102] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0103] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A new energy battery packing detection method, characterized in that: The method is applied to a new energy battery packing device, wherein the new energy battery packing device comprises a wide-angle camera and a plurality of code scanning cameras, wherein the wide-angle camera and the plurality of code scanning cameras are installed on the same bracket, and the wide-angle camera is located in the middle of the code scanning cameras, and the wide-angle camera and the plurality of code scanning cameras have the same orientation; the method comprises: Control the barcode scanning camera to shoot the battery cells within the corresponding field of view to obtain a scanned image, wherein different barcode scanning cameras have different field of view; control the wide-angle camera to take a picture of the battery cells to obtain a wide-angle image, wherein the wide-angle image contains all the battery cells; Performing image recognition processing on each of the scanned images to obtain position information and identification code information of each battery cell, and identifying the bare shell and positive and negative electrode directions of the battery cell by using a template matching method and the position information; Mapping the identified position information, identification code information, bare shell and positive and negative electrode directions onto the wide-angle image through dual-camera calibration technology to obtain a summary image; The positive and negative directions of the battery cells are counted according to the summary image, and the battery cells with a smaller number of directions are marked in the summary image to obtain a detection image of the battery cells.

2. The new energy battery packing detection method according to claim 1 is characterized in that: The method further comprises: Performing desiccant target recognition and foreign object target recognition on the wide-angle image to determine whether there is desiccant information and foreign objects in the packaging device; If desiccant or foreign matter is identified, desiccant location information and foreign matter location information are extracted; The positions of the desiccant and the foreign matter are marked in the detection image according to the desiccant position information and the foreign matter position information to obtain a comprehensive detection image.

3. The new energy battery packing detection method according to claim 1 is characterized in that: It is characterized in that The method further comprises: Acquire a battery cell packaging template image, and perform matching analysis between the summary image and the battery cell packaging template image to obtain a matching result; Determine whether the battery is missing according to the matching result, and if so, mark the position of the missing battery on the detection image to obtain missed detection information; If the missed inspection information indicates that there is a battery cell at the current missed inspection position, but the corresponding identification code information is missing, the operator is guided to use a barcode scanner to perform a supplementary scan of the missed inspection position according to the missed inspection information to obtain a supplementary scan image; The scanned image is fused with the summary image to obtain a complete detection image.

4. The new energy battery packing detection method according to claim 3 is characterized in that: The new energy battery packing detection further includes an optical projector, and the method further includes: Acquire the location information, identification code information, desiccant location information, foreign matter location information and missed detection information to set corresponding indication icons; Acquire an indication requirement for setting, and control the optical projector according to the indication requirement to map a corresponding indication icon on a surface of a battery cell at a corresponding position.

5. A new energy battery packing detection device, characterized in that: include: The movable shaft bracket that can move up and down is installed on the industrial computer to support the code scanning module and light source; A code scanning module, mounted on the movable shaft bracket, for collecting images of the chip; A light source, mounted on the movable shaft bracket, for providing a stable lighting environment; An industrial computer is used to control the movable shaft bracket, the code scanning module and the light source to perform corresponding actions, and to execute the new energy battery cell packaging detection method described in any one of claims 1 to 4.

6. The new energy battery packing detection device according to claim 5 is characterized in that: The code scanning module includes: A plurality of barcode scanning cameras are installed on the movable shaft bracket, each of the barcode scanning cameras is used to photograph the battery cells within the corresponding field of view to obtain a scanned image; A wide-angle camera is installed in the middle of the barcode scanning camera and is used to take pictures of all the cells to obtain a wide-angle image; An optical projector is installed around the wide-angle camera and is used to project detection information onto the surface of the battery cell.

7. The new energy battery packing detection device according to claim 6 is characterized in that: The code scanning cameras are distributed in an equidistant grid, and the fields of view of adjacent code scanning cameras overlap.

8. The new energy battery packing detection device according to claim 5, characterized in that: The device further comprises a movable carrier, wherein the movable carrier is used to carry the industrial computer and the movable shaft bracket, and transport the industrial computer and the movable shaft bracket to the position of the battery cell to be identified.

9. An electronic device, characterized in that: It includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the new energy battery cell packaging detection method as described in any one of claims 1 to 4.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by the processor, the new energy battery cell packaging detection method as described in any one of claims 1 to 4 is implemented.

Images