Battery piece positioning method, system and equipment based on five-camera system

Abstract

The invention relates to a battery piece positioning method, system and equipment based on a five-camera system. Five cameras in the five-camera system are arranged in a central symmetry manner, namely, one central vertical camera and four edge cameras form a'one-master four-slave 'structure. The method comprises the following steps: determining a first position of a central point of a battery piece through a main camera image acquired by a main camera; determining second positions of a plurality of feature points of the battery piece based on the slave camera images acquired by the slave cameras; based on the central symmetry constraint relation and the second positions of the multiple feature points, the translation amount and the rotation angle generated when the battery piece is placed on the laser engraving platform are determined; and determining the absolute position coordinates of the battery piece according to the translation amount and the rotation angle. Through the method, the positioning precision of the battery piece can be improved.

Description

Technical Field

[0001] The present application relates to the field of battery cell manufacturing technology, and in particular to a battery cell positioning method, system and equipment based on a five-phase system. Background Art

[0002] Laser engraving of cell patterns is a key step in cell manufacturing. During the laser engraving process for cells (such as back-contact BC cells), the accuracy of the cell's position directly impacts the alignment accuracy between the electrode pattern and the PN junction, which in turn impacts the cell's conversion efficiency.

[0003] Traditional methods often use single-camera or dual-camera systems to locate cells. However, these systems often suffer from a limited field of view, requiring the camera to be mechanically moved multiple times to expand the field of view. This introduces motion errors that affect positioning accuracy.

[0004] Therefore, there is an urgent need to propose a solution that can improve the positioning accuracy of battery cells. Summary of the Invention

[0005] Based on this, it is necessary to provide a battery cell positioning method, system, computer equipment, computer-readable storage medium and computer program product based on a five-camera system that can improve positioning accuracy in response to the above technical problems.

[0006] In its first aspect, the present application provides a method for positioning a cell based on a five-camera system, comprising one master camera and four slave cameras; the master camera is vertically mounted directly above a laser engraving platform, with its optical axis coinciding with the center perpendicular of the laser engraving platform; the four slave cameras are symmetrically distributed at 90° with the master camera as the center; and the fields of view of the four slave cameras are spliced ​​together to cover the entire area of ​​the cell on the laser engraving platform. The method comprises:

[0007] Determining a first position of a center point of the battery cell using a main camera image captured by the main camera;

[0008] determining second positions of a plurality of feature points of the battery cell based on the slave camera images captured by each of the slave cameras;

[0009] Determining, based on the central symmetry constraint relationship and the second positions of the plurality of feature points, a translation amount and a rotation angle generated when the battery cell is placed on the laser engraving platform;

[0010] The absolute position coordinates of the battery cell are determined according to the translation amount and the rotation angle.

[0011] In one embodiment, the battery cell is rectangular, the field of view of a single slave camera covers an edge area of ​​the battery cell on the laser engraving platform, and a feature point is determined from each slave camera image; the four feature points determined from the camera image are in a centrally symmetrical constraint relationship with the center point of the battery cell as the center.

[0012] In one embodiment, the first position of the center point is a first global coordinate of the center point in a global coordinate system, and the second position of the feature point is a second global coordinate of the feature point in the global coordinate system;

[0013] The origin of the global coordinate system is the intersection of the main camera optical axis and the laser engraving platform, the XY plane of the global coordinate system is the placement plane of the battery cell on the laser engraving platform, and the Z axis of the global coordinate system is the optical axis of the main camera.

[0014] In one embodiment, determining the first position of the center point of the battery cell by using the main camera image captured by the main camera includes:

[0015] Based on the central marker point in the feature template library, identifying the first local coordinates of the central marker point in the main camera coordinate system from the main camera image;

[0016] The first local coordinate corresponding to the central marking point is converted to the global coordinate system to obtain the first global coordinate of the central point.

[0017] In one embodiment, determining the second positions of the plurality of feature points of the battery cell based on the slave camera images captured by each of the slave cameras includes:

[0018] determining a correction parameter according to the first global coordinate, and adjusting the ROI area in the slave camera image according to the correction parameter;

[0019] According to the preset feature marks respectively set at the four edge positions of the battery cell in the feature template library, identifying the second local coordinates of the feature point in the corresponding slave camera coordinate system from the ROI area in the corresponding slave camera image;

[0020] The second local coordinates of each of the feature points are converted to the global coordinate system to obtain the second global coordinates of each of the feature points.

[0021] In one embodiment, the method further comprises:

[0022] When there is no abnormality in the feature point in the slave camera image, executing the preset feature marks respectively set at the four edge positions of the battery cell in the feature template library, and identifying the second local coordinates of the feature point in the corresponding slave camera coordinate system from the ROI area in the corresponding slave camera image;

[0023] In any case where the feature point in the camera image is abnormal data, the second local coordinates of the feature point are derived based on the central symmetry constraint relationship; wherein the case where the feature point is abnormal data includes: there is at least one of stains on the feature point, the feature point is blocked, or there is a film color difference on the feature point.

[0024] In one embodiment, determining the translation amount and rotation angle generated when the battery cell is placed on the laser engraving platform based on the central symmetry constraint relationship and the second positions of the multiple feature points includes:

[0025] Based on the centrosymmetric constraint relationship, a centrosymmetric constraint equation is constructed, and based on the centrosymmetric constraint equation, the second global coordinate of each of the feature points is optimized and adjusted to obtain a third global coordinate corresponding to each of the feature points;

[0026] Determine a first objective function; the first objective function is the sum of squares of first error functions corresponding to the plurality of feature points, the first error function corresponding to each feature point being used to characterize the difference between the third global coordinate of the feature point and the first reference coordinate; the first reference coordinate is the coordinate obtained by transforming the ideal global coordinate of the feature point when the cell is not offset according to the rotation angle and translation to be solved;

[0027] The first objective function is optimized using a least squares method to obtain the rotation angle and the translation amount.

[0028] In one embodiment, before determining the first position of the center point of the battery cell using the main camera image captured by the main camera, the method further includes:

[0029] Controlling the robot to move the battery sheet to the laser engraving platform;

[0030] The master camera and the four slave cameras are synchronously triggered to capture images of the battery cell placed on the laser engraving platform.

[0031] In a second aspect, the present application further provides a cell positioning system based on a five-camera system, the system comprising a five-camera system and a computer device; the five-camera system comprising a master camera and four slave cameras; the master camera is vertically mounted directly above a laser engraving platform, with the optical axis of the master camera coinciding with a central perpendicular line of the laser engraving platform; the four slave cameras are symmetrically distributed at 90° with the master camera as the center; the fields of view of the four slave cameras are spliced ​​together to cover the entire area of ​​the cell on the laser engraving platform;

[0032] The computer device is used to determine a first position of a center point of the battery cell based on a main camera image captured by the main camera; and determine a second position of a plurality of feature points of the battery cell based on the slave camera images captured by each of the slave cameras;

[0033] The computer device is also used to determine the translation amount and rotation angle generated when the battery cell is placed on the laser engraving platform based on the central symmetry constraint relationship and the second positions of the multiple feature points; and determine the absolute position coordinates of the battery cell according to the translation amount and the rotation angle.

[0034] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method mentioned in the first aspect when executing the computer program.

[0035] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method mentioned in the first aspect.

[0036] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method mentioned in the first aspect.

[0037] The above-mentioned cell positioning method, system, computer device, computer-readable storage medium and computer program product based on the five-camera system propose a new camera system - a five-camera system. The five cameras in the five-camera system are arranged in a central symmetrical layout, that is, one central vertical camera + four edge cameras, forming a "one master and four slaves" structure. The one-master and four-slave camera array utilizes the geometric symmetry of the cell to accurately capture the global image (i.e., the master camera image) and the local image (i.e., the slave camera image) at one time. Based on the central symmetry constraint relationship, the global image and the local image captured by the master and slave cameras are combined to more accurately and conveniently determine the translation and rotation angle generated when the cell is placed on the laser engraving platform, thereby improving the positioning accuracy of the cell based on the translation and rotation angle. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 is a schematic diagram of a five-camera system in one embodiment;

[0039] Figure 2 is a schematic diagram of the field of view from a camera in one embodiment;

[0040] Figure 3 1 is a flow chart of a method for positioning a cell based on a five-camera system in one embodiment;

[0041] Figure 4 1. A structural block diagram of a cell positioning system based on a five-camera system in one embodiment;

[0042] Figure 5 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0044] When a cell is placed on a laser engraving platform, its actual position may be rotated or translated to a certain extent from its ideal position due to manipulation or the cell's own structure. Therefore, during the laser engraving process, it is necessary to locate the cell's actual position to guide the laser beam's positioning and thus control the laser engraving on the cell.

[0045] In some solutions that use single-camera systems / dual-camera systems for positioning, the camera is moved multiple times by machinery. In addition to the problem of low positioning accuracy caused by motion errors, the feature matching calculation is huge, resulting in relatively low positioning efficiency.

[0046] In other solutions, a four-camera system is proposed. The four cameras in the four-camera system are set at the edge area of ​​the battery cell, so the four cameras will have different viewing angles for the central area of ​​the battery cell, which will cause image distortion. After the images captured by the four cameras are stitched together, complex distortion correction processing is required for the stitched central area, which consumes computing resources. The battery cell can only be positioned after distortion correction, which is relatively inefficient. Secondly, due to the limited effect of distortion correction, the stitching error of the images captured by the four edge cameras is often relatively large, resulting in low positioning accuracy of the battery cell. The electrode pattern of the battery cell (for example, BC battery cell) generally requires high-precision positioning, so the positioning accuracy after the accumulation of stitching errors cannot meet the requirements of the BC battery cell.

[0047] Furthermore, the four cameras acquire image data asynchronously before stitching them together. This makes the image data fusion and stitching process complex, leading to low cell positioning efficiency and difficulty meeting the real-time requirements of high-speed production lines.

[0048] In some embodiments of the present application, a new camera system is provided, namely a five-camera system. The five-camera system includes one master camera and four slave cameras, which is a one-master and four-slave camera array. The main camera is vertically installed directly above the laser engraving platform, and the optical axis of the main camera coincides with the central vertical line of the laser engraving platform. In this way, the main camera can more accurately capture the overall outline of the battery cell, which is equivalent to accurately capturing the global image of the battery cell. The four slave cameras are symmetrically distributed at 90° with the main camera as the center, and the field of view of a single slave camera covers the edge area of ​​the battery cell on the laser engraving platform. In this way, a single slave camera can accurately capture a part of the battery cell area within its own field of view, and the fields of view of the four slave cameras are spliced ​​together to cover the entire area of ​​the battery cell on the laser engraving platform. This is equivalent to the four slave cameras being able to accurately capture a partial image of the battery cell.

[0049] To facilitate the understanding of the five-camera system, we now combine Figure 1 For schematic illustration. Figure 1 As shown, the five-camera system includes a master camera C0 and four slave cameras, C1, C2, C3, and C4. The five-camera system is centrally symmetrically arranged on a camera support platform. Specifically, cameras C1 through C4 are arranged 90° symmetrically around the master camera C0. This effectively places the master camera C0 at the center of the five-camera system.

[0050] The cell can be placed in a designated area on the table of the laser engraving platform, and the designated area can be illuminated by a CCD (Charge-coupled Device) light source. Therefore, the designated area can also be called a CCD light source area. The five-camera system in the embodiment of the present application can be based on the camera light source area (i.e. Figure 1 The image of the cell is captured by the CCD light source area and the cross-shaped area in the middle. It should be understood that in order to more clearly illustrate the light source area, Figure 1 The battery cells are not drawn in order to avoid obstruction and unclear illustration.

[0051] from Figure 1 As can be seen, the main camera C0 is mounted vertically directly above the designated area of ​​the laser engraving platform. It should be understood that the main camera's optical axis coincides with the vertical line perpendicular to the center of the laser engraving platform. If a cell is placed in this designated area, it is equivalent to being mounted directly above the cell's center. Therefore, the main camera C0 can accurately capture the cell's overall outline, and thus more precisely locate the cell's center point.

[0052] The four slave cameras (C1 to C4) can relatively accurately and directly capture a portion of the cell area within their respective fields of view (i.e., each captures a corner of the cell, or, in other words, the field of view of a single slave camera covers the edge of the cell on the laser engraving platform), obtaining four partial areas. These four partial areas are stitched together to form a complete cell. In other words, the fields of view of the four slave cameras C1 to C4 are stitched together to form a complete field of view that can fully cover the entire cell (i.e., the fields of view of the four slave cameras, when stitched together, cover the entire area of ​​the cell).

[0053] For example, Figure 2 As shown in the figure, the size of the cell is 300mm×300mm, and the field of view of a single camera covers the edge area of ​​the cell of 150mm×150mm. Then, the fields of view of the four cameras C1 to C4 are spliced ​​together to form a complete field of view of 300mm×300mm. For easy distinction, Figure 2 The four edge areas of the solar cell are represented by different patterns.

[0054] It should be understood that the computer device can more accurately locate the absolute position of the battery cell based on the more accurate global image taken by the main camera and the more accurate local image taken by the battery cell, combined with the method in the embodiment of the present application.

[0055] In one embodiment, a cell positioning method based on a five-camera system is provided, and the method is executed by a computer device. Figure 3 As shown, the method specifically includes the following steps:

[0056] S31, determining a first position of a center point of the battery cell through a main camera image captured by the main camera.

[0057] In some embodiments, the first position of the center point is a first global coordinate of the center point in a global coordinate system, wherein the origin of the global coordinate system is the intersection of the optical axis of the main camera and the laser engraving platform, the XY plane of the global coordinate system is the placement plane of the cell on the laser engraving platform, and the Z axis of the global coordinate system is the optical axis of the main camera.

[0058] In some embodiments, the battery cell has a corresponding feature template library. For example, the feature template library can be generated by pre-loading design drawings of the battery cell. The computer device can identify the first position of the center point based on the feature template library and the main camera image.

[0059] Specifically, the feature template library contains a marker point for the center area of ​​the cell (which may be referred to as the center marker point). For example, a circular marker P0 is set at the center point. Then, the center marker point can be identified from the main camera image (for example, the circular marker P0 is identified) to obtain the first local coordinates of the center marker point in the main camera coordinate system. Furthermore, the computer device can convert the first local coordinates P0 (μ0, v0) corresponding to the center marker point to the global coordinate system to obtain the first global coordinates O (x0, y0) of the center point of the cell, that is, the first position of the center point of the cell in the global coordinate system.

[0060] This is equivalent to achieving coarse positioning through the main camera, that is, locating the position of the center point of the battery cell (i.e., the first position) based on the image of the global outline of the battery cell captured by the main camera. It should be understood that the conversion relationship between the main camera coordinate system and the global coordinate system is pre-calibrated and can be recorded as a first coordinate conversion relationship (e.g., including a first rotation matrix and a first translation matrix). Based on this first coordinate conversion relationship, the first local coordinate of the center point in the main camera coordinate system can be converted to the global coordinate system to obtain the first global coordinate.

[0061] In some embodiments, a camera light source can be combined to more accurately identify the first position of the center point. Specifically, the camera light source can eliminate reflections from the velvet surface of the cell, thereby enhancing the contrast between the edge and the marked point, thereby assisting in more accurately identifying the first position of the center point.

[0062] S32: Determine second positions of a plurality of feature points of the battery cell based on the slave camera images captured by each of the slave cameras.

[0063] It should be understood that the four slave cameras (eg, C1 to C4) are symmetrically distributed at 90° with the master camera as the center, so the angle between the optical axis of each slave camera and the optical axis of the master camera is 45°.

[0064] In some embodiments, the cell is rectangular, the field of view of a single slave camera covers an edge region of the cell on the laser engraving platform, and each slave camera image determines a feature point; the four feature points determined from the slave camera image are centrally symmetrically constrained about the center point of the cell. Exemplarily, each feature point determined from the slave camera image is a right angle point (also referred to as a right-angle feature point) of the rectangular cell.

[0065] In some embodiments, the four feature points include a first feature point, a second feature point, a third feature point and a fourth feature point, wherein the first feature point and the third feature point are in a centrally symmetrical relationship, and the second feature point and the fourth feature point are in a centrally symmetrical relationship.

[0066] In some embodiments, the first position of the center point is the first global coordinate of the center point in the global coordinate system, and the second position of each feature point is the second global coordinate of the feature point in the global coordinate system. Step S32 includes: determining a correction parameter based on the first global coordinate, and adjusting the ROI (Region of Interest) of each slave camera image based on the correction parameter; identifying the feature points in the ROI region (i.e., the adjusted ROI region) of each slave camera image, obtaining the second local coordinate of each feature point in the corresponding slave camera coordinate system, and converting the second local coordinate of each feature point to the global coordinate system to obtain the second global coordinate of each feature point.

[0067] It should be understood that the transformation relationship between the camera coordinate system and the global coordinate system is pre-calibrated and can be recorded as a second coordinate transformation relationship (such as including a second rotation matrix and a second translation matrix). Based on this second coordinate transformation relationship, the second local coordinate of the feature point in the camera coordinate system can be transformed to the global coordinate system to obtain the second global coordinate.

[0068] Exemplarily, the correction parameter is used to characterize the difference between the first global coordinate of the center point and the ideal global coordinate of the center point. For example, after acquiring the image, the master camera can complete coarse positioning within 150ms, determine the correction parameter, adjust the ROI area of ​​each slave camera image according to the correction parameter, and perform feature extraction in parallel (taking ≤80ms), that is, identify and extract feature points from the ROI. This is equivalent to using the slave camera for fine positioning based on the coarse positioning of the master camera, combining the master and slave camera data to more quickly and accurately identify and locate feature points.

[0069] In some embodiments, the feature template library includes corresponding preset feature markers for each of the four edge positions of the cell, for a total of four preset feature markers. These four preset feature markers are located at different edge positions, for example, at the four corners of the cell. Each slave camera corresponds to a preset feature marker at one edge position. Therefore, the computer device can identify the second local coordinates of each feature point in the corresponding slave camera coordinate system from the ROI region of each of the four slave camera images based on the four preset feature markers.

[0070] For example, the preset feature mark can be an isosceles right triangle mark or a trapezoid mark, which is not limited. Taking an isosceles right triangle mark (for example, a side length of 10 mm) as an example, the right angle vertex of the isosceles right triangle mark can be used as the feature point Q i , i∈[1,4], so that the right-angled vertex (also called right-angle point, corner point or right-angled feature point) of the corresponding isosceles right triangle mark can be identified in the camera image, that is, the feature point Q from the camera image is obtained.i The second local coordinate Q in the corresponding slave camera coordinate system i (μ i , v i ). Then, the computer device can calculate the second local coordinate Q corresponding to the feature point i (μ i , v i ) is converted to the global coordinate system to obtain the second global coordinate P corresponding to the feature point i (x i ,y i For example, based on the second local coordinate Q1(μ1, v1) of the feature point Q1 identified from the camera C1, it is converted to the global coordinate system to obtain P1(x1, y1). In this way, the second global coordinate system of each of the four feature points can be determined, that is, the second position of each feature point can be determined.

[0071] This is equivalent to achieving precise positioning through four slave cameras, that is, accurately locating the position of the characteristic point of the battery cell (ie, the second position) based on the local image including the edge area captured by the slave camera.

[0072] S33, based on the central symmetry constraint relationship and the second positions of the plurality of feature points, determining the translation amount and rotation angle generated when the battery cell is placed on the laser engraving platform.

[0073] The central symmetry constraint relationship is used to constrain the second positions of the plurality of feature points to be symmetrical about the first position of the central point.

[0074] In this embodiment, when solving the rotation angle and translation of the battery cell, it is equivalent to integrating multiple feature points collected from the camera (that is, the precise positioning results from the camera) and combining the central symmetry constraint relationship, thereby improving the positioning accuracy, correcting the rough error of the main camera, and achieving the "rough first, fine later, multi-source complementary" positioning effect.

[0075] In some embodiments, the second positions of the plurality of feature points are second global coordinates. The second global coordinates of each feature point can be optimized using a centrosymmetric constraint relationship. Thus, the optimized global coordinates (i.e., third global coordinates) satisfy the centrosymmetric constraint relationship. Therefore, based on the third global coordinates satisfying the centrosymmetric constraint relationship, the translation amount and rotation angle can be more accurately calculated, thereby improving positioning accuracy.

[0076] Exemplarily, step S33 includes: constructing a central symmetric constraint equation based on the central symmetric constraint relationship, optimizing and adjusting the second global coordinates of each of the feature points based on the central symmetric constraint equation to obtain the third global coordinates corresponding to each of the feature points; determining a first objective function; the first objective function is the sum of the squares of the first error functions corresponding to multiple feature points, and the first error function corresponding to each feature point is used to characterize the difference between the third global coordinates of the feature point and the first reference coordinates; the first reference coordinates are the ideal global coordinates of the feature point when the battery cell is not offset, and are transformed according to the rotation angle and translation to be solved; the first objective function is optimized using the least squares method to solve the rotation angle and the translation.

[0077] It should be understood that since the slave camera images are collected separately by each slave camera, it is equivalent to that the second global coordinates of each feature point that are initially converted to the global coordinate system are determined by each slave camera itself, while the first global coordinates of the center point are determined by the master camera. In this way, although they are all converted to the same global coordinate system for calculation, certain errors are inevitable due to different devices.

[0078] Under normal circumstances, the feature points should be centered on the center point and have a centrally symmetrical relationship. Therefore, in order to improve accuracy, a centrally symmetrical constraint equation can be established based on the centrally symmetrical condition (for example: x1 = -x3, y1 = -y3, x2 = -x4, y2 = -y4, where x1 / y1 is the horizontal coordinate / vertical coordinate of the feature point Q1, x3 / y3 is the horizontal coordinate / vertical coordinate of the feature point Q3 that is centrally symmetrical with the feature point Q1, x2 / y2 is the horizontal coordinate / vertical coordinate of the feature point Q2, and x4 / y4 is the horizontal coordinate / vertical coordinate of the feature point Q4 that is centrally symmetrical with the feature point Q2). Based on the centrally symmetrical constraint equation, the second global coordinates of each feature point that has been initially converted are optimized and adjusted to make the third global coordinates of each feature point after optimization more accurate. In addition, since the feature points are centrally symmetrical based on the center point, this optimization adjustment is equivalent to achieving a comprehensive optimization of the positions of the center point and the feature points, avoiding residuals or errors in the positioning of the center point and the feature points.

[0079] Taking the centrally symmetric feature points Q1 and Q3 as an example, the centrally symmetric constraint equation is constructed as follows: x3 = 2x0 - x1, y3 = 2y0 - y1. Similarly, taking the centrally symmetric feature points Q2 and Q4 as an example, the centrally symmetric constraint equation is constructed as follows: x4 = 2x0 - x2, y4 = 2y0 - y2. Based on these centrally symmetric constraint equations, the feature points are constrained to be symmetrical about the center of the cell.

[0080] Furthermore, the rotation angle and translation of the cell can be solved based on the optimized third global coordinates of each feature point. Specifically, a first objective function is determined; the first objective function is the sum of the squares of the first error functions corresponding to the plurality of feature points, where the first error function corresponding to each feature point is used to characterize the difference between the third global coordinate of the feature point and the first reference coordinate; the first reference coordinate is the coordinate obtained by transforming the ideal global coordinate of the feature point when the cell is not offset according to the rotation angle and translation to be solved; the first objective function is optimized using the least squares method to solve for the rotation angle and translation.

[0081] In some embodiments, the first objective function is expressed by the following formula:

[0082]

[0083] Among them, E is the first objective function, P i meas is the third global coordinate of the i-th feature point, P i model (Δx, Δy, θ) is the first reference coordinate of the i-th feature point, that is, the ideal global coordinate of the i-th feature point is transformed according to the rotation angle θ and the translation (Δx, Δy) to be solved to obtain the first reference coordinate P i model (Δx, Δy, θ). Δx represents the translation on the X axis in the global coordinate system, and Δy represents the translation on the Y axis in the global coordinate system. i meas -P i model (Δx, Δy, θ) is the first error function.

[0084] The computer device can optimize the first objective function through the least squares method, gradually obtain the minimum value of the first objective function E, and determine the rotation angle and translation amount when the objective function takes the minimum value as the final rotation angle and translation amount of the entire battery cell.

[0085] In some embodiments, the first objective function may include, in addition to the sum of the squares of the first error functions corresponding to the plurality of feature points, the square of the error function corresponding to the center point. The error function corresponding to the center point is used to characterize the difference between the first global coordinates of the center point and the reference coordinates of the center point; the reference coordinates of the center point are the ideal global coordinates of the center point, if the cell is not offset, transformed according to the rotation angle and translation to be solved. This means that by combining the center point and all feature points, the rotation angle and translation of the cell can be more accurately solved.

[0086] It should be understood that it is also possible to not first optimize and adjust the second global coordinates of each feature point using the centrosymmetric constraint relationship. Instead, when solving the rotation angle and translation using the least squares method, the centrosymmetric constraint relationship is combined to construct the second objective function. In this case, the centrosymmetric constraint relationship is also combined to more accurately and conveniently solve the rotation angle and translation of the battery cell.

[0087] Specifically, in some embodiments, step S32 includes: constructing a second error function corresponding to each of the feature points based on the central symmetry constraint relationship; the second error function is used to characterize the difference between the second global coordinate of the feature point and the second reference coordinate of the feature point; the second reference coordinate is derived based on the central symmetry constraint equation constructed based on the central symmetry constraint relationship, combined with the third reference coordinate of the central symmetric point of the feature point; the third reference coordinate of the central symmetric point is the ideal global coordinate of the central symmetric point when the battery cell is not offset, and the coordinate is obtained after transforming according to the rotation angle and translation to be solved; determining the second objective function; the second objective function is the sum of the squares of the second error functions corresponding to multiple feature points; using the least squares method to optimize the second objective function, and solve the rotation angle and the translation.

[0088] S34, determining the absolute position coordinates of the battery cell according to the translation amount and the rotation angle.

[0089] Specifically, the computer device can determine the final absolute position coordinates (x, y, θ) of the battery cell based on the ideal position coordinates of the battery cell (i.e., the position coordinates when no offset occurs) in combination with the calculated translation amount and the rotation angle.

[0090] Furthermore, the computer device can output the absolute position coordinates (x, y, θ) of the cell to the laser engraving control system to guide the beam positioning. For example, a laser path instruction can be generated and transmitted to the galvanometer control system to implement subsequent laser engraving processing.

[0091] In some embodiments, the computer device can also construct a temperature-deformation compensation model. For example, the computer device can use a standard calibration plate (chessboard + thermal expansion coefficient) to perform temperature-deformation joint calibration to construct a temperature-deformation compensation model. During the laser engraving process, the deformation of the battery cell caused by the change in ambient temperature (i.e., the dimensional change caused by the thermal expansion of the battery cell caused by the change in ambient temperature) can be continuously detected based on the temperature-deformation compensation model, thereby correcting and compensating the absolute position coordinates of the battery cell. Furthermore, the computer device can output the corrected absolute position coordinates (x, y, θ) of the battery cell to the laser engraving control system to guide the positioning of the light beam. For example, during the laser engraving process, the compensation parameters are updated based on the temperature-deformation compensation model every preset period, and the current absolute position coordinates of the battery cell are corrected and compensated based on the compensation parameters. In this way, the position of the battery cell can be located more accurately and in real time, thereby improving the accuracy of laser engraving. In addition, correction and compensation based on the temperature-deformation compensation model achieves fault tolerance for battery cell deformation and enhances robustness.

[0092] The above method proposes a new camera system - a five-camera system. The five cameras in the five-camera system are arranged in a centrally symmetrical layout, that is, one central vertical camera + four edge cameras, forming a "one master and four slave" structure. The one-master-four-slave camera array utilizes the geometric symmetry of the battery cell to accurately capture the global image (i.e., the master camera image) and the local image (i.e., the slave camera image) at one time. Based on the central symmetry constraint relationship, the global image and local image captured by the master and slave cameras are combined to more accurately and conveniently determine the translation and rotation angle generated when the battery cell is placed on the laser engraving platform, thereby improving the positioning accuracy of the battery cell based on the translation and rotation angle.

[0093] In addition, there is no need to perform complex processing such as complex image stitching and image correction like traditional methods. Only by using the central symmetry constraint relationship, only a small number of parameters (i.e., the translation and rotation angle of the battery cell) need to be solved to accurately locate the battery cell, thereby improving the positioning speed.

[0094] In some embodiments, before step S31, the method further includes: controlling the robot to move the battery cell to the laser engraving platform; and synchronously triggering the main camera and the four slave cameras to capture images of the battery cell placed on the laser engraving platform.

[0095] Specifically, the robot can be controlled to move the battery cell to the engraving station, and the vacuum adsorption platform is started, so that the battery cell is adsorbed to the laser engraving platform. It should be understood that the robot may not be precise enough when placing the battery cell, causing the battery cell to have a certain offset (such as rotation or translation) relative to the ideal position. The method in the embodiment of the present application is to more accurately identify the offset generated, so as to more accurately position the battery cell. After the battery cell is fixed and adsorbed, the computer device (such as the hardware trigger module in the computer device) can synchronously trigger five cameras to capture images, which is equivalent to parallel processing, and can quickly and efficiently capture and process images. For example, the single acquisition time is less than 10ms. This improves the positioning efficiency of subsequent battery cells and is more suitable for the efficiency requirements of high-speed assembly lines.

[0096] In some embodiments, the spacing between cameras in a five-camera system can be adjusted by a slide, so that the five-camera system can be adapted to battery cells of different sizes (for example, battery cells with side lengths ranging from 156mm to 210mm) without replacing hardware. This system has high compatibility and greatly reduces or avoids the cost of hardware equipment modification.

[0097] It should be understood that the main camera captures an image with a relatively accurate overall outline of the cell. Therefore, the position of the center point of the cell can be determined based on the main camera image and recorded as the first position. For example, the main camera can be a high-pixel (e.g., 12-megapixel) global shutter camera equipped with a telecentric lens. In this way, a global image with the overall outline of the cell can be accurately captured.

[0098] It should be understood that, when there is no abnormality in the feature point in the slave camera image, the second local coordinates of the feature point in the corresponding slave camera coordinate system can be identified from the ROI area in the corresponding slave camera image based on the preset feature marks set at the four edge positions of the battery cell in the feature template library. However, there may be cases where the feature point is abnormal data, for example, there is stain on the feature point, the feature point is blocked, or there is a film color difference on the feature point, etc. In this case, the second layout coordinates of the feature point cannot be accurately identified through the image (such as the position of the identified feature point is inaccurate, or the feature point cannot be identified). Therefore, in any case where the feature point in the slave camera image is abnormal data, the abnormal data can be eliminated, and the second local coordinates of the feature point can be derived based on the central symmetry constraint relationship.

[0099] For ease of understanding, let's take the case of occluded feature points as an example. For example, feature points Q1 and Q3, and feature points Q2 and Q4 are symmetrical about the center point. If feature point Q3 is occluded and cannot be identified in the corresponding slave camera image captured by slave camera C3, the second local coordinates of feature point Q3 can be derived based on the second local coordinates of feature point Q1, which is also symmetrical about the center point.

[0100] The above scheme, based on the central symmetry constraint relationship of the four corner feature points, can eliminate abnormal data and determine the location of the feature points more accurately, thereby improving positioning accuracy. Based on the large-scale experimental results of the inventors of this application, it was found that this method can improve positioning accuracy from ±50μm to ±10μm, which obviously greatly improves positioning accuracy. In addition, by eliminating abnormal data through the central symmetry constraint relationship, it has a certain fault tolerance for positioning mark contamination and enhances robustness.

[0101] It should be understood that although the steps in the flowcharts of the above embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts of the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily to be performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0102] Based on the same inventive concept, the present application also provides a five-camera system-based cell positioning system for implementing the methods described in the above embodiments. The solution to the problem provided by this system is similar to the solution described in the above methods. Therefore, the specific limitations of one or more of the following five-camera system-based cell positioning system embodiments can be found in the above-mentioned limitations of the five-camera system-based cell positioning method, and will not be repeated here.

[0103] like Figure 4As shown, in one embodiment, a cell positioning system based on a five-camera system is provided, which includes a five-camera system 41 and a computer device 42. The five-camera system 41 includes a master camera and four slave cameras; the master camera is vertically installed directly above the laser engraving platform, and the optical axis of the master camera coincides with the central perpendicular line of the laser engraving platform; the four slave cameras are symmetrically distributed at 90 degrees with the master camera as the center; the fields of view of the four slave cameras are spliced ​​together to cover the entire area of ​​the cell on the laser engraving platform;

[0104] The computer device 42 is configured to determine a first position of a center point of the battery cell using a main camera image captured by the main camera; and determine second positions of a plurality of feature points of the battery cell based on slave camera images captured by each of the slave cameras;

[0105] The computer device 42 is also used to determine the translation and rotation angle generated when the battery cell is placed on the laser engraving platform based on the central symmetry constraint relationship and the second positions of the multiple feature points; and determine the absolute position coordinates of the battery cell according to the translation and the rotation angle.

[0106] In some embodiments, the battery cell is rectangular, the field of view of a single slave camera covers an edge area of ​​the battery cell on the laser engraving platform, and a feature point is determined from each slave camera image; the four feature points determined from the camera image are in a centrally symmetrical constraint relationship with the center point of the battery cell as the center.

[0107] In some embodiments, the first position of the center point is the first global coordinate of the center point in the global coordinate system, and the second position of the feature point is the second global coordinate of the feature point in the global coordinate system; wherein, the origin of the global coordinate system is the intersection of the optical axis of the main camera and the laser engraving platform, the XY plane of the global coordinate system is the placement plane of the battery cell on the laser engraving platform, and the Z axis of the global coordinate system is the optical axis of the main camera.

[0108] In some embodiments, the computer device 42 is also used to identify the first local coordinates of the center marker point in the main camera coordinate system from the main camera image based on the center marker point in the feature template library; convert the first local coordinates corresponding to the center marker point to the global coordinate system to obtain the first global coordinates of the center point.

[0109] In some embodiments, the computer device 42 is also used to determine correction parameters based on the first global coordinates, and adjust the ROI area in the slave camera image based on the correction parameters; according to the preset feature marks set at the four edge positions of the battery cell in the feature template library, identify the second local coordinates of the feature point in the corresponding slave camera coordinate system from the ROI area in the corresponding slave camera image; convert the second local coordinates of each feature point to the global coordinate system to obtain the second global coordinates of each feature point.

[0110] In some embodiments, the computer device 42 is also used to execute the preset feature marks set respectively at the four edge positions of the battery cell in the feature template library when there is no abnormality in the feature point in the slave camera image, and identify the second local coordinates of the feature point in the corresponding slave camera coordinate system from the ROI area in the corresponding slave camera image; in the case where the feature point in any of the slave camera images is abnormal data, the second local coordinates of the feature point are derived based on the central symmetry constraint relationship; wherein the case where the feature point is abnormal data includes: there is stain on the feature point, the feature point is blocked, or there is at least one of film color difference on the feature point.

[0111] In some embodiments, the computer device 42 is also used to construct a central symmetry constraint equation based on the central symmetry constraint relationship, optimize and adjust the second global coordinates of each of the feature points based on the central symmetry constraint equation, and obtain the third global coordinates corresponding to each of the feature points; determine the first objective function; the first objective function is the sum of the squares of the first error functions corresponding to multiple feature points, and the first error function corresponding to each feature point is used to characterize the difference between the third global coordinate of the feature point and the first reference coordinate; the first reference coordinate is the ideal global coordinate of the feature point when the battery cell is not offset, and the coordinate is obtained after transforming it according to the rotation angle and translation to be solved; use the least squares method to optimize the first objective function to solve the rotation angle and the translation.

[0112] In some embodiments, the computer device 42 is further used to control the robot to move the battery cell to the laser engraving platform; and synchronously trigger the main camera and the four slave cameras to capture images of the battery cell placed on the laser engraving platform.

[0113] In some embodiments, a computer device is provided, whose internal structure diagram can be as follows: Figure 5As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a battery cell positioning method based on a five-camera system is implemented.

[0114] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0115] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in each embodiment of the present application when executing the computer program.

[0116] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in each embodiment of the present application are implemented.

[0117] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in each embodiment of the present application when executed by a processor.

[0118] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions.

[0119] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, etc., but are not limited to these.

[0120] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above 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.

[0121] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A cell positioning method based on a five-phase system, characterized in that: The five-camera system includes one master camera and four slave cameras; the master camera is vertically mounted directly above a laser engraving platform, with the optical axis of the master camera coinciding with the central perpendicular line of the laser engraving platform; the four slave cameras are symmetrically distributed at 90° with the master camera as the center; the fields of view of the four slave cameras are spliced ​​together to cover the entire area of ​​the battery cell on the laser engraving platform; the method includes: Determining a first position of a center point of the battery cell using a main camera image captured by the main camera; determining second positions of a plurality of feature points of the battery cell based on the slave camera images captured by each of the slave cameras; Determining the translation amount and rotation angle generated when the battery cell is placed on the laser engraving platform based on the central symmetry constraint relationship and the second positions of the multiple feature points; the central symmetry constraint relationship is used to constrain the second positions of the multiple feature points to be symmetrical about the first position of the center point; The absolute position coordinates of the battery cell are determined according to the translation amount and the rotation angle.

2. The method according to claim 1, characterized in that The battery cell is rectangular, and the field of view of a single slave camera covers an edge area of ​​the battery cell on the laser engraving platform. A feature point is determined in each slave camera image; the four feature points determined from the camera image are in a centrally symmetrical constraint relationship with the center point of the battery cell as the center.

3. The method according to claim 1 or 2, characterized in that The first position of the center point is the first global coordinate of the center point in the global coordinate system, and the second position of the feature point is the second global coordinate of the feature point in the global coordinate system; The origin of the global coordinate system is the intersection of the main camera optical axis and the laser engraving platform, the XY plane of the global coordinate system is the placement plane of the battery cell on the laser engraving platform, and the Z axis of the global coordinate system is the optical axis of the main camera.

4. The method according to claim 3, characterized in that Determining a first position of a center point of the battery cell by using a main camera image captured by the main camera includes: Based on the central marking point in the feature template library, identifying the first local coordinates of the central marking point in the main camera coordinate system from the main camera image; The first local coordinate corresponding to the central marking point is converted to the global coordinate system to obtain the first global coordinate of the central point.

5. The method according to claim 4, characterized in that The determining the second positions of the plurality of feature points of the battery cell based on the slave camera images collected by each of the slave cameras includes: determining a correction parameter according to the first global coordinate, and adjusting the ROI area in the slave camera image according to the correction parameter; According to the preset feature marks respectively set at the four edge positions of the battery cell in the feature template library, identifying the second local coordinates of the feature point in the corresponding slave camera coordinate system from the ROI area in the corresponding slave camera image; The second local coordinates of each of the feature points are converted to the global coordinate system to obtain the second global coordinates of each of the feature points.

6. The method according to claim 5, characterized in that The method further comprises: When there is no abnormality in the feature point in the slave camera image, executing the preset feature marks respectively set at the four edge positions of the battery cell in the feature template library, and identifying the second local coordinates of the feature point in the corresponding slave camera coordinate system from the ROI area in the corresponding slave camera image; In any case where the feature point in the camera image is abnormal data, the second local coordinates of the feature point are derived based on the central symmetry constraint relationship; wherein the case where the feature point is abnormal data includes: there is at least one of stains on the feature point, the feature point is blocked, or there is a film color difference on the feature point.

7. The method according to claim 3, characterized in that The determining, based on the central symmetry constraint relationship and the second positions of the plurality of feature points, the translation amount and the rotation angle generated when the battery cell is placed on the laser engraving platform includes: Based on the centrosymmetric constraint relationship, a centrosymmetric constraint equation is constructed, and based on the centrosymmetric constraint equation, the second global coordinate of each of the feature points is optimized and adjusted to obtain a third global coordinate corresponding to each of the feature points; Determine a first objective function; the first objective function is the sum of squares of first error functions corresponding to the plurality of feature points, the first error function corresponding to each feature point being used to characterize the difference between the third global coordinate of the feature point and the first reference coordinate; the first reference coordinate is the coordinate obtained by transforming the ideal global coordinate of the feature point when the cell is not offset according to the rotation angle and translation to be solved; The first objective function is optimized using a least squares method to obtain the rotation angle and the translation amount.

8. The method according to any one of claims 1 to 7, characterized in that Before determining the first position of the center point of the battery cell using the main camera image captured by the main camera, the method further includes: Controlling the robot to move the battery sheet to the laser engraving platform; The master camera and the four slave cameras are synchronously triggered to capture images of the battery cell placed on the laser engraving platform.

9. A cell positioning system based on a five-phase system, characterized in that: The system includes a five-camera system and a computer device; the five-camera system includes a master camera and four slave cameras; the master camera is vertically installed directly above the laser engraving platform, and the optical axis of the master camera coincides with the central perpendicular line of the laser engraving platform; the four slave cameras are symmetrically distributed at 90 degrees with the master camera as the center; the fields of view of the four slave cameras are spliced ​​together to cover the entire area of ​​the battery cell on the laser engraving platform; The computer device is used to determine a first position of a center point of the battery cell based on a main camera image captured by the main camera; and determine a second position of a plurality of feature points of the battery cell based on the slave camera images captured by each of the slave cameras; The computer device is also used to determine the translation amount and rotation angle generated when the battery cell is placed on the laser engraving platform based on the central symmetry constraint relationship and the second positions of the multiple feature points; and determine the absolute position coordinates of the battery cell according to the translation amount and the rotation angle.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

Images