A method, system, equipment, and medium for detecting burrs on lithium battery slitting electrode sheets.

Abstract

This invention provides a method, system, device, and medium for detecting burrs on lithium battery slitting electrode sheets. The method includes: acquiring images of the electrode sheet to be tested at multiple preset detection positions, including longitudinal and transverse electrode sheet images; performing real-time burr detection on the images at each preset detection position to obtain corresponding positional burr detection results, including longitudinal and transverse burr detection results; and obtaining the burr detection result of the electrode sheet to be tested based on the positional burr detection results. This invention not only enables efficient and reliable automated detection of burrs on lithium battery slitting electrode sheets, but also features low cost, high versatility, and wide applicability, providing a reliable guarantee for improving lithium battery product quality and reducing safety hazards, thus possessing high practical value.

Description

Technical Field

[0001] This invention relates to the field of lithium battery testing technology, and in particular to a method, system, computer equipment, and storage medium for detecting burrs on lithium battery slitting electrode sheets. Background Technology

[0002] In lithium battery production, the quality of the electrodes determines the battery's safety and range. The complex manufacturing process and the randomness of defects can lead to quality abnormalities, and different types of defects pose different safety hazards. For example, during electrode slitting, high cutting speeds, blade wear, and the metallic properties of aluminum and copper can result in residual micro-metal strips, scraps, or cracks near the cut surface and on both sides of the electrode. These residues can easily cause short circuits between the cathode and cathode, affecting the battery's safe operation. Furthermore, in actual production, unstable motor power in the slitting blade or acceleration / deceleration fluctuations during electrode operation can easily lead to incomplete cutting or tearing of the electrodes, resulting in non-standard cut surfaces and similar safety hazards. Therefore, online electrode defect detection is a crucial step in lithium battery quality control.

[0003] Currently, the quality monitoring of electrode slitting in the power battery production process generally relies on human observation or experience to replace the slitting blade or drive system equipment to improve product quality. However, online detection of the electrode slitting process requires the simultaneous use of multiple 3D and 2D cameras to capture images of the cut surface and burrs on both sides. Mounting multiple cameras in appropriate positions not only makes the slitting equipment structure extremely complex but also significantly increases costs, making it difficult to meet the needs of widespread applications. Furthermore, the linear speed of the slitting machine is typically in the range of 60–120 m / min, and existing 3D cameras struggle to meet the speed adaptability requirements, thus affecting the quality of the acquired images and resulting in poor automatic machine vision detection, failing to truly meet practical application needs. Therefore, there is an urgent need for a low-cost, versatile, and intelligently effective method for detecting burrs on lithium battery slitting electrodes. Summary of the Invention

[0004] The purpose of this invention is to provide a method for detecting burrs on lithium battery slitting electrode sheets. This method involves deploying longitudinal and transverse area array cameras around the electrode sheet conveying device based on the image processing cycle and electrode sheet running speed. The transverse area array camera is then calibrated using images acquired by the longitudinal area array camera. These images are then used to acquire longitudinal and transverse images from multiple detection positions and undergo image recognition processing to obtain the corresponding longitudinal and transverse burr detection results. This method overcomes the shortcomings of existing lithium battery slitting electrode sheet burr detection methods. It not only provides efficient and reliable automated detection of burrs on lithium battery slitting electrode sheets but also boasts low cost, high versatility, and wide applicability, offering a reliable guarantee for improving lithium battery product quality and reducing safety hazards. It has high practical value.

[0005] To achieve the above objectives, it is necessary to provide a method, system, computer equipment, and storage medium for detecting burrs on lithium battery slitting electrode sheets, addressing the aforementioned technical problems.

[0006] In a first aspect, embodiments of the present invention provide a method for detecting burrs on lithium battery slitting electrode sheets, the method comprising the following steps:

[0007] Images of the electrode to be tested are acquired at multiple preset detection positions; the images to be tested include vertical electrode images and horizontal electrode images.

[0008] Real-time burr detection is performed on the image to be detected at each preset detection position to obtain the corresponding positional burr detection result; the positional burr detection result includes longitudinal burr detection result and transverse burr detection result;

[0009] Based on the burr detection results at each location, the burr detection results of the electrode to be tested are obtained.

[0010] Furthermore, before the step of acquiring images of the electrode to be detected at multiple preset detection positions, the method further includes:

[0011] Based on the preset image processing cycle and electrode running speed, the station camera deployment distance is obtained, and based on the station camera deployment distance, longitudinal station area array cameras and transverse station area array cameras are deployed around the electrode conveying device to be inspected.

[0012] Furthermore, the distance between the workstation cameras is expressed as follows:

[0013] L cam =α*v*T

[0014] Among them, L cam The distance between the workstation cameras is indicated; v and T represent the electrode running speed and the preset image processing cycle, respectively; α represents the distance adjustment coefficient.

[0015] Furthermore, the horizontal workstation area array camera is an area array camera with a liquid lens; the focusing parameters of the liquid lens of the horizontal workstation area array camera include the initial object distance and the initial potential value.

[0016] The calibration steps for the focusing parameters of the liquid lens of the horizontal workstation area array camera include:

[0017] The longitudinal image of the electrode to be tested at a preset position is acquired by the longitudinal workstation area array camera with fixed focus, and the longitudinal image is processed to obtain the calibration correction distance.

[0018] The transverse workstation array camera continuously acquires transverse cross-sectional images of the electrode to be tested at different focal lengths at a preset position, and obtains the acquisition potential value corresponding to the clearest image in the transverse cross-sectional images as the current calibration potential value.

[0019] The distance between the transverse cross-sectional edge of the electrode to be tested and the liquid lens is obtained, and the initial object distance is obtained based on the distance between the transverse cross-sectional edge and the liquid lens and the calibration correction distance.

[0020] The initial potential value is obtained based on the calibration correction distance, the current calibration potential value, and the corresponding potential displacement value; the initial potential value is expressed as:

[0021] Grade0 = Grade cal -positionPerGrade*correctLength

[0022] Where Grade0 represents the initial potential value; Grade cal `positionPerGrade` and `positionPerGrade` represent the current calibration potential value and the corresponding displacement value, respectively; `correctLength` represents the calibration correction distance.

[0023] Furthermore, the step of acquiring images of the electrode to be detected at multiple preset detection positions includes:

[0024] Based on the field of view of the longitudinal workstation array camera, the longitudinal shooting interval is obtained, and based on the longitudinal shooting interval, the longitudinal image of the electrode to be tested is acquired at each preset detection position to obtain longitudinal electrode images at multiple preset detection positions.

[0025] Based on the longitudinal shooting interval and the distance between the workstation cameras, the lateral shooting interval is obtained. Based on the lateral shooting interval, the lateral workstation area array camera is used to acquire lateral cross-sectional images of the electrode to be tested at each preset detection position, thereby obtaining lateral electrode images at multiple preset detection positions.

[0026] Furthermore, the step of acquiring lateral cross-sectional images of the electrode to be inspected at various preset detection positions using the lateral imaging interval and the lateral workstation area array camera includes:

[0027] Based on the longitudinal electrode images of the electrode to be tested at each preset detection position, the corresponding position focusing correction distance is obtained;

[0028] Based on the focusing correction distance, the initial potential value, and the corresponding potential displacement value, the corresponding position focusing potential value is obtained; the position focusing potential value is expressed as:

[0029] Grade i =Grade0-positionPerGrade i *correctLength i

[0030] Where Grade0 represents the initial potential value; Grade i positionPerGrade i and correctLength i These represent the position focusing potential value, the displacement value corresponding to the potential, and the position focusing correction distance corresponding to the i-th preset detection position, respectively.

[0031] After focusing the horizontal workstation area array camera according to the position focusing potential value, the horizontal workstation area array camera is used to acquire horizontal cross-sectional images of the electrode to be tested at each preset detection position according to the horizontal shooting interval.

[0032] Furthermore, the step of performing real-time burr detection on the image to be detected at each preset detection position to obtain the corresponding positional burr detection result includes:

[0033] The image to be detected is subjected to mean filtering and threshold segmentation in sequence to obtain the edge region of the electrode, and the edge region of the electrode is subjected to edge recognition and edge fitting in sequence to obtain the corresponding image edge line.

[0034] Obtain the center point coordinates of the image edge line, and based on the center point coordinates, the image size of the obtained electrode edge region, and the pixel equivalent value, obtain the current position correction distance;

[0035] Morphological processing is performed on the edge region of the electrode to obtain a rectangular region. Then, the image difference operator is used to process the edge region of the electrode and the rectangular region to obtain the corresponding burr region.

[0036] According to the preset area conditions, the burr area is filtered to obtain the burr area to be analyzed, and the contour recognition of the burr area to be analyzed is performed to obtain the burr contour image.

[0037] Obtain the coordinate values ​​of each contour point in the burr contour image, and take the contour point with the smallest row coordinate among the contour point coordinate values ​​as the coordinate value of the highest point of the burr.

[0038] The burr pixel length is obtained based on the coordinates of the highest point of the burr and the straight line of the image edge, and the maximum burr length at the current position is obtained based on the burr pixel length and the pixel equivalent value.

[0039] The burr detection result at the current position is obtained based on the maximum burr length at the current position and the corresponding preset burr length threshold.

[0040] Secondly, embodiments of the present invention provide a lithium battery electrode sheet burr detection system, the system comprising:

[0041] The image acquisition module is used to acquire images of the electrode to be detected at multiple preset detection positions; the images to be detected include vertical electrode images and horizontal electrode images.

[0042] The image detection module is used to perform real-time burr detection on the image to be detected at each preset detection position to obtain the corresponding position burr detection result; the position burr detection result includes longitudinal burr detection result and transverse burr detection result;

[0043] The result generation module is used to obtain the burr detection results of the electrode to be tested based on the burr detection results at each location.

[0044] Thirdly, embodiments of the present invention also provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described method.

[0045] Fourthly, embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the above-described method.

[0046] This application provides a method and system for detecting burrs on lithium battery slitting electrode sheets. The method acquires images of the electrode sheet to be inspected at multiple preset inspection positions, including longitudinal and transverse electrode images. Real-time burr detection is then performed on these images at each preset inspection position to obtain corresponding positional burr detection results, including longitudinal and transverse burr detection results. Based on these positional burr detection results, the burr detection result of the electrode sheet to be inspected is obtained. Compared with existing technologies, this lithium battery slitting electrode sheet burr detection method not only provides efficient and reliable automated detection of burrs on lithium battery slitting electrode sheets, but also allows for the establishment of inspection standards based on specifications. Full inspection or sampling inspection can be performed according to actual needs. The detection capability is not affected by fluctuations in electrode position during actual production. Furthermore, it is low-cost, highly versatile, and easy to widely apply, providing a reliable guarantee for improving lithium battery product quality and reducing safety hazards, thus possessing high practical value. Attached Figure Description

[0047] Figure 1 This is a schematic diagram of the burrs present in the cutting of electrode sheets for existing lithium batteries;

[0048] Figure 2 This is a flowchart illustrating the method for detecting burrs on lithium battery slitting electrode sheets in an embodiment of the present invention.

[0049] Figure 3 This is a schematic diagram of the application scenario layout of the longitudinal workstation area array camera 101 and the transverse workstation area array camera 102 in this embodiment of the invention.

[0050] Figure 4 This is a schematic diagram of the configuration of the liquid lens focusing parameter calibration values ​​of the horizontal workstation area array camera 102 in this embodiment of the invention;

[0051] Figure 5 In the figure, a, b, c, d and e respectively represent the longitudinal image, the electrode area, the image of the electrode edge within the rectangular range, the image edge curve and the image edge straight line acquired by the longitudinal workstation area array camera 101 in the embodiment of the present invention.

[0052] Figure 6 This is a schematic diagram of the horizontal workstation area array camera 102 dynamically focusing and acquiring horizontal electrode images in an embodiment of the present invention;

[0053] Figure 7 In this embodiment of the invention, a, b, c, and d respectively represent schematic diagrams of the outlines of the polarimeter edge region, rectangular region, burr region, and burr region to be analyzed in the image to be detected.

[0054] Figure 8In this embodiment of the invention, a and b respectively represent schematic diagrams of the longitudinal burr detection results and the transverse burr detection results corresponding to a certain longitudinal electrode image and a certain transverse electrode image;

[0055] Figure 9 This is a schematic diagram of the lithium battery electrode burr detection system in an embodiment of the present invention;

[0056] Figure 10 This is an internal structural diagram of the computer device in an embodiment of the present invention. Detailed Implementation

[0057] To make the objectives, technical solutions, and beneficial effects of this application clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Obviously, the embodiments described below are only part of the embodiments of the present invention and are used to illustrate the present invention, but are not intended to limit the scope of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0058] The lithium battery electrode burr detection method provided by this invention addresses the shortcomings of existing electrode slitting monitoring methods in power battery production, such as high application cost, poor versatility, and inability to achieve truly automated online detection, thus failing to meet the application requirements for real-time intelligent and accurate detection. This invention proposes a method based on image processing cycle and electrode running speed, deploying longitudinal and transverse area array cameras around the electrode conveying device. The images acquired by the longitudinal area array cameras are used to focus and calibrate the transverse area array cameras, which are then used to acquire longitudinal and transverse images from multiple detection positions. These images are then processed by a specially developed image recognition system to obtain the corresponding longitudinal and transverse burr detection results. This low-cost and highly versatile online real-time detection method for lithium battery electrode burrs aims to achieve accurate and precise online detection of electrode burrs. Figure 1 The automated intelligent detection method for burrs on diced electrode sheets, as shown, provides efficient, reliable, and accurate protection for improving lithium battery product quality and reducing safety hazards. The following embodiments will provide a detailed description of the lithium battery diced electrode sheet burr detection method of the present invention.

[0059] In one embodiment, such as Figure 2 As shown, a method for detecting burrs on lithium battery slitting electrode sheets is provided, including the following steps:

[0060] S11. Acquire images of the electrode to be tested at multiple preset detection positions; the images to be tested include longitudinal electrode images and transverse electrode images; wherein, the preset detection positions can be understood as those pre-set according to the structure of the electrode conveying device and the speed of conveying the electrode, ensuring that the acquired images can cover all image acquisition positions of the entire electrode, and can be set according to actual application requirements, without specific limitations here; it should be noted that the electrode conveying device is the operating device used in actual applications to place and convey the electrode produced by the slitting equipment so that cameras deployed around it can acquire clear images of various parts of the electrode as needed, without specific limitations here either.

[0061] As described above, the automated intelligent detection method provided by this invention relies on the deployment of cameras for image acquisition. To ensure that actual detection requirements are met while minimizing costs, this embodiment preferably employs the following method: Figure 3 As shown, a longitudinal workstation area array camera 101 is deployed near a preset position after the electrode sheet is received by the electrode sheet conveying device to acquire images from the front of the electrode sheet. Simultaneously, another transverse workstation area array camera 102 is deployed at a certain distance to acquire images of the transverse cut surface of the electrode sheet. This ensures that a complete image of the electrode sheet can be acquired, and that both longitudinal and transverse images of the same position on the electrode sheet are captured, enabling refined inspection of different parts of the electrode sheet. Specifically, before the step of acquiring images of the electrode sheet at multiple preset inspection positions, the following steps are also included:

[0062] Based on the preset image processing cycle and the electrode running speed, the station camera deployment distance is obtained. Based on this station camera deployment distance, a longitudinal station area array camera 101 and a transverse station area array camera 102 are deployed around the electrode conveying device to be inspected. The preset image processing cycle can be understood as the time cycle for an image recognition system to process a set of images for identification and analysis. The electrode running speed can be understood as the speed at which the electrode moves on the electrode conveying device to be inspected while the station camera is acquiring electrode images. To ensure comprehensive image acquisition of different parts of the longitudinal front and transverse cutting surfaces of the electrode, as well as real-time image processing, this embodiment preferably sets the interval between the longitudinal station area array camera 101 and the transverse station area array camera 102 based on the image processing cycle and the electrode running speed. Specifically, the station camera deployment distance is expressed as follows:

[0063] L cam =α*v*T

[0064] Among them, L cam This indicates the distance between the workstation cameras; v and T represent the electrode running speed and preset image processing cycle, respectively; α represents the distance adjustment coefficient.

[0065] In practical applications, the minimum distance L between the horizontal workstation area array camera 102 and the vertical workstation area array camera 101 can be determined based on the processing cycle (T) of the image recognition software system for a set of images and the running speed (V) of the electrode plates. min =v*T, and then select the corresponding deployment distance adjustment coefficient according to the requirements to determine the actual distance between the cameras at the two workstations. For example, set the deployment distance of the workstation cameras to 1.5L. min The greater the distance between the cameras at each workstation, the more images are buffered. Correspondingly, the control process for image acquisition of the inspected electrode sheets moving on the electrode sheet conveying device by the horizontal workstation area array camera 102 and the vertical workstation area array camera 101 is as follows: The PLC acquires encoder pulse signals, converts the electrode sheet displacement value, and determines the shooting interval based on the field of view of the image captured by the vertical area array camera 101, so that all electrode sheets can be captured as continuous images. When the electrode sheet reaches the set displacement interval value, the PLC sends a trigger signal to the vertical workstation area array camera, and the camera receives the trigger signal and begins image acquisition. The shooting interval of the horizontal workstation area array camera 102 is determined based on the shooting interval of the vertical workstation area array camera 101 and the distance between the two workstation cameras, so that the electrode sheet captures horizontal and vertical images at the same position. When the electrode sheet reaches the set displacement interval value of the horizontal workstation area array camera 102, the PLC sends a trigger signal to the horizontal workstation area array camera 102, and the camera receives the trigger signal and begins image acquisition.

[0066] Considering that in practical applications, the electrode to be tested will pass through multiple driven shafts during transport, even with a polarizer, vibration and offset will still occur during image acquisition, resulting in low image quality and affecting the analysis and testing results. To ensure that clear, high-quality images are acquired at each preset testing position, this embodiment preferably uses a liquid lens area array camera 102 with fast dynamic focusing response and precise focusing for capturing the transverse cross-sectional image of the electrode. This ensures the quality of the transverse electrode image acquisition by dynamically adjusting the focus according to the shooting position. Correspondingly, before the transverse area array camera 102 is officially used for testing, the liquid lens needs to be initially calibrated according to the relevant layout of the usage scenario, serving as the basis for dynamic focusing during subsequent use. Figure 4 As shown, the focusing parameters include the initial object distance and the initial potential value; specifically, the calibration steps for the focusing parameters of the liquid lens of the horizontal workstation area array camera include:

[0067] The longitudinal image of the electrode to be tested at a preset position is acquired by the longitudinal workstation area array camera 101 with fixed focus, and the longitudinal image is processed to obtain the calibration and correction distance; wherein, the preset position can be understood as the image acquisition position used for initial parameter calibration of the liquid lens, which can be a preset detection position in actual use, or another position can be selected, without specific limitation here; if the acquired longitudinal image is as follows Figure 5 As shown in Figure a, the specific process for obtaining the calibration and correction distance is as follows:

[0068] Step 1: Perform mean filtering on the acquired longitudinal image to remove interference (noise), and then extract the image through threshold segmentation. Figure 5 The polar region shown in Figure b;

[0069] Step 2: Generate a rectangular region at the edge of the electrode area, and use the rectangular region for image matting to obtain... Figure 5 The image shown in Figure c is the image of the electrode edge within a rectangular area, i.e., the image of the electrode edge region;

[0070] Step 3: First, use the image edge operator to perform edge recognition on the image of the polarimetric edge region obtained in Step 2, and obtain the following: Figure 5 The image edge curve shown in Figure d is then fitted with a straight line using the least squares method to obtain the edge. Figure 5 The image edge line shown in Figure e (gray dashed line, which becomes a solid line when the image is magnified) is fitted to obtain the coordinate values ​​of the two edge endpoints within the image range corresponding to the line;

[0071] Step 4: Using the image processing line operator, based on the coordinates of the two endpoints of the line obtained in Step 3, obtain the coordinates of the center point of the line, center(X0, Y0), and the tilt angle of the line, Angle.

[0072] Step 5: Based on the image size operator, the height (row) and width (col) of the image edge region can be obtained. Combining these with the center point coordinates (center(X0, Y0)) of the image edge line obtained in Step 4, and the measured pixel equivalent value (perPiexl), the calibration correction distance can be obtained using the following formula:

[0073] correctLength cal =(Y0-row / 2)*perPiexl

[0074] Where, correctLength cal Y0 represents the calibrated correction distance; Y0 represents the ordinate value of the center point of the image edge line; row and perPiexl represent the pixel height and pixel equivalent value of the image in the edge region of the electrode, respectively.

[0075] The transverse workstation area array camera 102 continuously acquires transverse cross-sectional images of the electrode to be tested at different focal lengths at a preset position, and obtains the acquisition potential value corresponding to the clearest image in the transverse cross-sectional images as the current calibration potential value; wherein, the process of obtaining the current calibration potential value can be understood as: the longitudinal workstation area array camera 101 at a certain preset position (pos) cal After taking a picture, the PLC controls its movement to the corresponding picture position (pos) of the horizontal workstation area scan camera 102. cal +L cam After stopping, while dynamically focusing the liquid lens at this position, continuously photograph the cross-section of the electrode until the image is at its clearest. Record the potential value at this point as the current calibration potential value (Grade) to be used. cal ;

[0076] The distance between the transverse cross-sectional edge of the electrode to be tested and the liquid lens is obtained, and the initial object distance is obtained based on the distance between the transverse cross-sectional edge and the liquid lens, and the calibration correction distance; wherein, the initial object distance can be understood as the initial focusing distance obtained by the following formula based on the calibration correction distance correctLength obtained from the aforementioned longitudinal image analysis and the measured distance L from the transverse cross-sectional edge of the electrode to the liquid lens:

[0077] L0 = correctLength + L

[0078] Where L0 represents the initial object distance; correctLength represents the calibration correction distance; and L represents the distance between the transverse cross-section edge of the electrode to be tested and the liquid lens.

[0079] The initial potential value is obtained based on the calibration correction distance, the current calibration potential value, and the corresponding potential displacement value; the initial potential value is expressed as:

[0080] Grade0 = Grade cal -positionPerGrade*correctLength

[0081] Where Grade0 represents the initial potential value; Grade cal `positionPerGrade` and `positionPerGrade` represent the current calibration potential value and the corresponding displacement value, respectively; `correctLength` represents the calibration correction distance.

[0082] The above steps achieve the initial calibration of the focusing parameters of the liquid lens. Subsequently, during actual testing, when taking pictures using the horizontal workstation area array camera 102, dynamic focusing can be performed based on the obtained initial object distance and initial potential value, combined with the preset detection position of the currently acquired image, to ensure the acquisition of a clear horizontal image of the electrode. Specifically, the steps of acquiring images of the electrode to be tested at multiple preset detection positions include:

[0083] Based on the field of view of the longitudinal workstation array camera, the longitudinal shooting interval is obtained, and based on the longitudinal shooting interval, the longitudinal image of the electrode to be tested is acquired at each preset detection position to obtain longitudinal electrode images at multiple preset detection positions.

[0084] Based on the longitudinal imaging interval and the distance between the station cameras, the lateral imaging interval is obtained. Then, based on the lateral imaging interval, the lateral station area array camera is used to acquire lateral cross-sectional images of the electrode to be tested at various preset detection positions, resulting in multiple lateral electrode images at these preset detection positions. Specifically, when acquiring lateral cross-sectional images of the electrode to be tested at each preset detection position, the corresponding control software can be integrated into the device and the corresponding control software can send the level calculated based on the longitudinal image at the same preset detection position to the liquid lens via a serial port for precise focusing before image acquisition. It should be noted that, as mentioned earlier, the acquisition of the electrode lateral image is related to the position of the longitudinal station area array camera 101. The acquired longitudinal image and the acquired lateral image correspond one-to-one. For example, if the acquisition position values ​​of all the longitudinal images of the electrode obtained from the PLC are (l1, l2, l3, ...), then based on the distance between the two phase cameras, the image positions acquired by the lateral station area array camera 102 should be sequentially (l1 + L...). cam l2+L cam l3+l cam This ensures that the two workstations acquire images at the same location on the electrode and detect the longitudinal and transverse burr lengths at the same location;

[0085] Specifically, the step of acquiring lateral cross-sectional images of the electrode to be tested at various preset detection positions using the lateral imaging interval and the lateral workstation area array camera includes:

[0086] Based on the longitudinal electrode images of the electrode to be tested at each preset detection position, the corresponding position focusing correction distance is obtained; wherein, the process of obtaining the position focusing correction distance can be referred to the calibration correction distance acquisition process of calibrating the liquid lens focusing parameters of the horizontal workstation area array camera 102 mentioned above, and will not be repeated here.

[0087] Based on the focusing correction distance, the initial potential value, and the corresponding potential displacement value, the corresponding position focusing potential value is obtained; the position focusing potential value is expressed as:

[0088] Grade i =Grade0-positionPerGrade i *correctLength i

[0089] Where Grade0 represents the initial potential value; Grade i positionPerGrade i and correctLength i These represent the position focusing potential value, the displacement value corresponding to the potential, and the position focusing correction distance corresponding to the i-th preset detection position, respectively.

[0090] After focusing the horizontal workstation area array camera according to the position focusing potential value, and according to the horizontal imaging interval, the horizontal workstation area array camera is used to acquire horizontal cross-sectional images of the electrode to be tested at various preset detection positions; wherein, after dynamic focusing, the horizontal workstation area array camera 102 can acquire images such as... Figure 6 The clear cross-sectional image shown is used for subsequent detection and analysis of lateral burrs, effectively improving the accuracy of lateral burr detection results.

[0091] S12. Perform real-time burr detection on the image to be detected at each preset detection position to obtain the corresponding positional burr detection result; the positional burr detection result includes longitudinal burr detection result and transverse burr detection result; wherein, real-time burr detection can be understood as effectively identifying transverse and longitudinal burrs that do not meet the preset burr length requirements; specifically, the step of performing real-time burr detection on the image to be detected at each preset detection position to obtain the corresponding positional burr detection result includes:

[0092] The image to be detected is subjected to mean filtering and threshold segmentation in sequence to obtain the electrode edge region. The electrode edge region is then subjected to edge recognition and edge fitting in sequence to obtain the corresponding image edge line. The method of obtaining the image edge line can also refer to the calibration and correction distance acquisition process for calibrating the liquid lens focusing parameters of the horizontal workstation area array camera 102 mentioned above, and will not be repeated here.

[0093] The center point coordinates of the image edge line are obtained, and the current position correction distance is obtained based on the center point coordinates, the image size of the obtained electrode edge region, and the pixel equivalent value. The current position correction distance can also be obtained by referring to the calibration correction distance acquisition method of calibrating the liquid lens focusing parameters of the horizontal workstation area array camera 102 mentioned above, which will not be repeated here.

[0094] Morphological processing is performed on the edge region of the electrode to obtain a rectangular region. Then, an image difference operator is used to process both the edge region and the rectangular region to obtain the corresponding burr region. There may be multiple burr regions; the following describes them as follows: Figure 7 The specific process of obtaining the burr area is explained using the electrode edge region processing process shown in Figure a as an example: First, the electrode edge region processing process is processed... Figure 7 Morphological operator processing is applied to the edge region of the polar plate shown in Figure a, resulting in the following: Figure 7 The rectangular region shown in Figure b; then the edge region of the pole piece and the rectangular region are processed using the image difference operator to obtain... Figure 7 The burr area shown in Figure c;

[0095] Based on preset area conditions, the burr regions are filtered to obtain the burr regions to be analyzed. Contour recognition is then performed on these burr regions to obtain burr contour images. The preset area conditions can be understood as area size parameters set according to the burr situation in the actual application scenario. Correspondingly, the burr regions to be analyzed can be understood as those obtained by... Figure 7 In the image c, the spur region is processed by an image processing connectivity operator to obtain multiple connected regions, and then processed by an image processing region selection operator to obtain the spur region with the highest height that meets certain area conditions; the spur contour image can be understood as a... Figure 7 The spur area to be analyzed, as shown in Figure d, is obtained by image processing region to XLD (eXtended Line Descriptions) contour operator. Figure 7 The outline of the region shown in Figure e;

[0096] The coordinate values ​​of each contour point in the burr contour image are obtained, and the coordinate value of the contour point with the smallest row coordinate among the contour point coordinate values ​​is taken as the coordinate value of the highest point of the burr. The coordinate values ​​of each contour point can be obtained by the contour point counting operator in the existing image processing and stored in the corresponding contour point coordinate array (Row, Col). The contour point with the smallest row coordinate Row[0] can be understood as the row coordinate value of the highest vertex of the burr. Then, the column coordinate value Col[0] corresponding to Row[0] can be obtained by the corresponding operator of the array, and the coordinate value of the highest point of the burr can be determined.

[0097] Based on the coordinates of the highest point of the burr and the straight line of the image edge, the burr pixel length is obtained. Then, based on the burr pixel length and the pixel equivalent value, the maximum burr length at the current position is obtained. The calculation process for the burr pixel length can be understood as an application of the point-to-line distance formula, which will not be detailed here. Correspondingly, the maximum burr length at the current position can be expressed as:

[0098] L burr =PiexlLength burr *perPiexl

[0099] Where PiexlLength burr and L burr These represent the burr pixel length and the corresponding maximum burr length at the current position, respectively; perPiexl represents the pixel equivalent value.

[0100] The position burr detection result is obtained based on the maximum burr length at the current position and the corresponding preset burr length threshold. The preset burr length threshold includes a preset longitudinal burr length threshold and a preset transverse burr length threshold. The specific threshold selection can be determined according to actual application requirements. The preset longitudinal burr length threshold and the preset transverse burr length threshold can be the same or different. For example, the longitudinal burr length threshold can be set to 150µm, or the transverse burr length threshold can be set to 150µm, or the transverse burr length threshold can be set to 140µm / 160µm, etc. No specific limitation is made here. Correspondingly, the position burr detection result can be understood as obtaining the maximum burr length at the current position that exceeds the predicted preset burr length threshold and the corresponding preset detection position.

[0101] It should be noted that the real-time burr detection method for both vertical and horizontal polarimetric images in this embodiment is consistent. That is, in practical applications, the processing method for the image to be detected described above can be used to obtain the corresponding burr detection result for both vertical and horizontal polarimetric images acquired at any preset location. Figure 8 Figure a shows the longitudinal burr detection results and Figure 8 Figure b shows the results of the horizontal burr detection. As shown in the figure, the vertical burr detection results include the maximum burr length at the current detection position, the correction distance, and whether the corresponding detection result passes (if it exceeds the corresponding preset vertical burr length threshold, it is NG and fails; if it is within the preset vertical burr length threshold range, it is OK and passes). The horizontal burr detection results include the maximum burr length at the current detection position and whether the corresponding detection result passes (if it exceeds the corresponding preset horizontal burr length threshold, it is NG and fails; if it is within the preset horizontal burr length threshold range, it is OK and passes).

[0102] S13. Based on the burr detection results at each location, obtain the burr detection results of the electrode to be tested; wherein, the burr detection results can be understood as real-time detection results that simultaneously include the length and position of all longitudinal burrs exceeding the corresponding burr length threshold on the electrode to be tested, and / or the length and position of transverse burrs, which can provide a reliable basis for the quality assessment of lithium battery slitting electrode sheets.

[0103] This application embodiment employs a method for online real-time detection of burrs on lithium battery slitting electrodes. It involves deploying longitudinal and transverse area array cameras around the electrode conveying device based on image processing cycles and electrode running speed. The images acquired by the longitudinal area array cameras are used to focus and calibrate the transverse area array cameras. These images are then used to acquire longitudinal and transverse images from multiple detection positions. A specially developed image recognition system is used for image recognition processing to obtain the corresponding longitudinal and transverse burr detection results. Compared to existing technologies, this method not only provides efficient and reliable automated detection of burrs on lithium battery slitting electrodes, but also allows for the establishment of detection standards based on specifications. Full inspection or sampling inspection can be performed according to actual needs. The detection capability is unaffected by fluctuations in electrode position during actual production. Furthermore, it is low-cost, highly versatile, and easy to widely apply, providing a reliable guarantee for improving lithium battery product quality and reducing safety hazards, thus possessing high practical value.

[0104] In one embodiment, such as Figure 9 As shown, a lithium battery electrode burr detection system is provided, the system comprising:

[0105] Image acquisition module 1 is used to acquire images of the electrode to be detected at multiple preset detection positions; the images to be detected include vertical electrode images and horizontal electrode images;

[0106] Image detection module 2 is used to perform real-time burr detection on the image to be detected at each preset detection position to obtain the corresponding position burr detection result; the position burr detection result includes longitudinal burr detection result and transverse burr detection result;

[0107] Result generation module 3 is used to obtain the burr detection results of the electrode to be tested based on the burr detection results at each position.

[0108] Specific limitations regarding the lithium battery electrode burr detection system can be found in the above-described limitations of the lithium battery electrode burr detection method, and the corresponding technical effects are equivalent, so they will not be repeated here. Each module in the aforementioned lithium battery electrode burr detection system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.

[0109] Figure 10 An internal structural diagram of a computer device is shown in one embodiment. This computer device may specifically be a terminal or a server. Figure 10 As shown, the computer device includes a processor, memory, network interface, display, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for detecting burrs on lithium battery electrode sheets. The display screen can be an LCD screen or an e-ink display screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device casing, or an external keyboard, touchpad, or mouse.

[0110] Those skilled in the art will understand that Figure 10 The structures shown are merely block diagrams of some structures related to the present application and do not constitute a limitation on the computer devices on which the present application is applied. Specific computing devices may include more or more components than those shown in the diagram.

[0111] Fewer components, or combinations of certain components, or a similar component arrangement.

[0112] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method described above.

[0113] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method.

[0114] In summary, the present invention provides a method, system, computer equipment, and storage medium for detecting burrs on lithium battery slitting electrode sheets. The method involves acquiring images of the electrode sheet to be inspected at multiple preset inspection positions, including longitudinal and transverse electrode images. Real-time burr detection is then performed on these images at each preset inspection position to obtain corresponding positional burr detection results, including longitudinal and transverse burr detection results. Based on these positional burr detection results, the burr detection result of the electrode sheet to be inspected is obtained. This method not only enables efficient and reliable automated detection of burrs on lithium battery slitting electrode sheets, but also allows for the establishment of inspection standards based on specifications. Full inspection or random inspection can be performed according to actual needs. The detection capability is unaffected by fluctuations in electrode position during actual production. Furthermore, it is low-cost, highly versatile, and easy to widely apply, providing a reliable guarantee for improving lithium battery product quality and reducing safety hazards, thus possessing high practical value.

[0115] The various embodiments in this specification are described in a progressive manner. For directly identical or similar parts of the embodiments, refer to each other. Each embodiment focuses on its differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments. It should be noted that the technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification.

[0116] The embodiments described above are merely preferred embodiments of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various improvements and substitutions without departing from the technical principles of this invention, and these improvements and substitutions should also be considered within the scope of protection of this application. Therefore, the scope of protection of this patent application should be determined by the scope of the claims.

Claims

1. A method for detecting burrs on lithium battery slitting electrode sheets, characterized in that, The method includes the following steps: Images of the electrode to be tested are acquired at multiple preset detection positions; the images to be tested include vertical electrode images and horizontal electrode images. Real-time burr detection is performed on the image to be detected at each preset detection position to obtain the corresponding positional burr detection result; the positional burr detection result includes longitudinal burr detection result and transverse burr detection result; Based on the burr detection results at each location, the burr detection results of the electrode to be tested are obtained; Prior to the step of acquiring images of the electrode to be detected at multiple preset detection positions, the method further includes: Based on the preset image processing cycle and electrode running speed, the station camera deployment distance is obtained, and based on the station camera deployment distance, longitudinal station area array cameras and transverse station area array cameras are deployed around the electrode conveying device to be inspected.

2. The method for detecting burrs on lithium battery slitting electrode sheets as described in claim 1, characterized in that, The distance between the workstation cameras is expressed as follows: in, Indicates the distance between workstation cameras; and These represent the electrode running speed and the preset image processing cycle, respectively. This indicates the adjustment coefficient for the deployment distance.

3. The method for detecting burrs on lithium battery slitting electrode sheets as described in claim 1, characterized in that, The horizontal workstation area array camera is an area array camera with a liquid lens; the focusing parameters of the liquid lens of the horizontal workstation area array camera include the initial object distance and the initial potential value. The calibration steps for the focusing parameters of the liquid lens of the horizontal workstation area array camera include: The longitudinal image of the electrode to be tested at a preset position is acquired by the longitudinal workstation area array camera with fixed focus, and the longitudinal image is processed to obtain the calibration correction distance. The transverse workstation array camera continuously acquires transverse cross-sectional images of the electrode to be tested at different focal lengths at a preset position, and obtains the acquisition potential value corresponding to the clearest image in the transverse cross-sectional images as the current calibration potential value. The distance between the transverse cross-sectional edge of the electrode to be tested and the liquid lens is obtained, and the initial object distance is obtained based on the distance between the transverse cross-sectional edge and the liquid lens and the calibration correction distance. The initial potential value is obtained based on the calibration correction distance, the current calibration potential value, and the corresponding potential displacement value; the initial potential value is expressed as: in, Indicates the initial potential value; and These represent the current calibrated potential value and the corresponding displacement value corresponding to the potential, respectively. This indicates the calibration correction distance.

4. The method for detecting burrs on lithium battery slitting electrode sheets as described in claim 3, characterized in that, The step of acquiring images of the electrode to be tested at multiple preset detection locations includes: Based on the field of view of the longitudinal workstation array camera, the longitudinal shooting interval is obtained, and based on the longitudinal shooting interval, the longitudinal image of the electrode to be tested is acquired at each preset detection position to obtain longitudinal electrode images at multiple preset detection positions. Based on the longitudinal shooting interval and the distance between the workstation cameras, the lateral shooting interval is obtained. Based on the lateral shooting interval, the lateral workstation area array camera is used to acquire lateral cross-sectional images of the electrode to be tested at each preset detection position, thereby obtaining lateral electrode images at multiple preset detection positions.

5. The method for detecting burrs on lithium battery slitting electrode sheets as described in claim 4, characterized in that, The step of acquiring lateral cross-sectional images of the electrode to be inspected at various preset detection positions using the lateral imaging interval and the lateral workstation area array camera includes: Based on the longitudinal electrode images of the electrode to be tested at each preset detection position, the corresponding position focusing correction distance is obtained; Based on the focusing correction distance, the initial potential value, and the corresponding potential displacement value, the corresponding position focusing potential value is obtained; the position focusing potential value is expressed as: in, Indicates the initial potential value; , and They represent the first i The position focusing potential value, the displacement value corresponding to the potential, and the position focusing correction distance corresponding to each preset detection position; After focusing the horizontal workstation area array camera according to the position focusing potential value, the horizontal workstation area array camera is used to acquire horizontal cross-sectional images of the electrode to be tested at each preset detection position according to the horizontal shooting interval.

6. The method for detecting burrs on lithium battery slitting electrode sheets as described in claim 1, characterized in that, The step of performing real-time burr detection on the image to be detected at each preset detection position to obtain the corresponding positional burr detection result includes: The image to be detected is subjected to mean filtering and threshold segmentation in sequence to obtain the edge region of the electrode, and the edge region of the electrode is subjected to edge recognition and edge fitting in sequence to obtain the corresponding image edge line. Obtain the center point coordinates of the image edge line, and based on the center point coordinates, the image size of the obtained electrode edge region, and the pixel equivalent value, obtain the current position correction distance; Morphological processing is performed on the edge region of the electrode to obtain a rectangular region. Then, the image difference operator is used to process the edge region of the electrode and the rectangular region to obtain the corresponding burr region. According to the preset area conditions, the burr area is filtered to obtain the burr area to be analyzed, and the contour recognition of the burr area to be analyzed is performed to obtain the burr contour image. Obtain the coordinate values ​​of each contour point in the burr contour image, and take the contour point with the smallest row coordinate among the contour point coordinate values ​​as the coordinate value of the highest point of the burr. The burr pixel length is obtained based on the coordinates of the highest point of the burr and the straight line of the image edge, and the maximum burr length at the current position is obtained based on the burr pixel length and the pixel equivalent value. The burr detection result at the current position is obtained based on the maximum burr length at the current position and the corresponding preset burr length threshold.

7. A lithium battery electrode burr detection system, characterized in that, The system includes: The image acquisition module is used to acquire images of the electrode to be detected at multiple preset detection positions; the images to be detected include vertical electrode images and horizontal electrode images. The image detection module is used to perform real-time burr detection on the image to be detected at each preset detection position to obtain the corresponding position burr detection result; the position burr detection result includes longitudinal burr detection result and transverse burr detection result; The result generation module is used to obtain the burr detection results of the electrode to be tested based on the burr detection results at each location. Before acquiring the images of the electrode to be detected at multiple preset detection positions, the method further includes: Based on the preset image processing cycle and electrode running speed, the station camera deployment distance is obtained, and based on the station camera deployment distance, longitudinal station area array cameras and transverse station area array cameras are deployed around the electrode conveying device to be inspected.

8. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images