A CAD import-based automatic search for cell pole post welding method

Abstract

The application discloses a kind of based on CAD import's automatic search battery pole welding method, comprising: obtaining battery pole and MARK point according to the CAD drawing of product, the relative theoretical position of battery pole and MARK point is calculated, and preparation is completed;Actual position coordinates of MARK point are obtained, and the theoretical shooting coordinates of battery pole are obtained according to actual position coordinates and relative theoretical position;Robot is operated to shoot image at theoretical shooting coordinates, and the offset of actual position coordinates of battery pole relative to theoretical position coordinates is obtained using multi-template matching method;Whether the offset is in the preset threshold range;Yes, then the theoretical shooting coordinates of battery pole are added to offset, and are marked as qualified welding position;No, then the theoretical shooting coordinates of battery pole are marked as failure welding position.The application relates to the technical field of automatic welding, solves the technical problems of insufficient precision and low efficiency in traditional welding method.

Description

TECHNICAL FIELD

[0001] The application belongs to the field of automatic welding, and relates to a CAD data processing technology, in particular to an automatic searching and welding method for a battery cell pole based on CAD import. BACKGROUND

[0002] The battery cell pole is a core component of energy storage devices such as lithium ion batteries, and bears the key function of current input and output. The welding quality directly affects the internal resistance, thermal stability and long-term reliability of the battery. In the rapidly developing battery industry, the production of battery cells tends to be automated and precise, and the welding of the pole needs to meet the requirements of high precision, high efficiency and strong consistency.

[0003] However, the traditional positioning method for welding the battery cell pole mainly relies on manual operation or simple mechanical positioning. In terms of positioning accuracy, the traditional method has the problems of insufficient accuracy and poor repeatability. Since manual operation mainly relies on experience and visual judgment of the pole position, it is difficult to achieve high-precision positioning; and simple mechanical positioning is also limited by its own structure and technology, and cannot achieve precise positioning requirements, resulting in large deviation of the welding position, affecting the internal current conduction of the battery cell, reducing the performance of the battery, and long-term use may cause problems such as virtual welding and welding, seriously damaging the reliability of the battery cell and shortening its service life. In terms of production efficiency, the manual adjustment and calibration process is time-consuming and laborious, and under the current situation of large-scale production of battery cell manufacturing, this inefficient operation process hinders the improvement of production capacity and cannot meet the rapid and efficient production demand. SUMMARY

[0004] The present application aims to solve at least one of the technical problems existing in the prior art; for this purpose, the present application proposes an automatic searching and welding method for a battery cell pole based on CAD import, which is used to solve the problems of insufficient accuracy, low production efficiency and poor repeatability in the existing positioning method for welding the battery cell pole.

[0005] To achieve the above-mentioned purpose, the present application provides an automatic searching and welding method for a battery cell pole based on CAD import, comprising:

[0006] S1, calculating the relative theoretical position of the battery cell pole and a plurality of MARK points according to the CAD drawing of the product, and completing the preparation work according to the CAD drawing of the product;

[0007] S2, obtaining the actual position coordinates of the plurality of MARK points, and obtaining the theoretical shooting coordinates of the battery cell pole according to the actual position coordinates and the relative theoretical position;

[0008] S3, operating the robot to shoot a plurality of images at the theoretical shooting coordinates, and using a multi-template matching method to obtain the offset of the actual position coordinates of the battery cell pole relative to the theoretical position coordinates according to the plurality of images;

[0009] S4, judging whether the offset is within a preset threshold range; if yes, adding the theoretical shooting coordinate of the cell pole to the offset and marking as a qualified welding position; if no, marking the theoretical shooting coordinate of the cell pole as a failed welding position.

[0010] Through the above technical steps, the application realizes the automation and precision of cell pole welding, solves the problems of insufficient precision and low efficiency in traditional welding methods, and significantly improves the welding quality and production efficiency.

[0011] Further, the relative theoretical position of the cell pole and the MARK points is calculated according to the CAD drawing of the product, comprising:

[0012] S11-1, converting the CAD drawing of the product into a dxf file, and performing lightweight processing on the dxf file according to the attribute data of the cell pole and the MARK points to obtain a lightweight file;

[0013] S11-2, using a target detection algorithm to automatically detect the cell pole and the MARK points in the lightweight file to obtain the theoretical position coordinates of the cell pole and the coordinates of the MARK points;

[0014] S11-3, calculating the relative distance between the cell pole and each MARK point according to the theoretical position coordinates of the cell pole and the coordinates of the MARK points to obtain the relative theoretical position of the cell pole and the MARK points.

[0015] Further, the preparation work further comprises:

[0016] S12-1, establishing a robot tool coordinate system and parallelizing the robot tool coordinate system with the XY plane of the copper nozzle three-axis;

[0017] S12-2, unifying the camera center with the robot tool coordinate system using a nine-point calibration method, and calculating the pixel equivalent using a calibration board; wherein the calibration board is placed on the product to be welded for calibration tasks;

[0018] S12-3, using a laser ranging sensor to obtain the relative height of the robot and the welding surface, and setting the spatial position parameters of the copper nozzle three-axis according to the CAD drawing and the relative height.

[0019] Further, the pixel equivalent is calculated using the calibration board, comprising:

[0020] Divide the calibration board into N×M rectangular regions with side length L to obtain a plurality of rectangular frames;

[0021] The camera is used to take a picture of the calibration board, and a machine learning algorithm is used to obtain the upper left corner coordinates (X1, Y1) and the lower right corner coordinates (X2, Y2) of a single rectangular frame in the photographed image;

[0022] The right lower corner coordinates (X2, Y2) and the left upper corner coordinates (X1, Y1) are subtracted in the horizontal and vertical coordinates, respectively, to obtain the length A1 and the width B1 of the rectangular frame.

[0023] According to the formula E=(A / A1+B / B1) / 2, the pixel equivalent E is calculated; wherein A and B represent the length and width of the calibration board, and A=N*L, B=M*L.

[0024] Further, the laser ranging sensor is used to obtain the relative height of the robot and the welding surface, comprising:

[0025] Adjust the mirror center and the ranging center of the robot, calculate the relative position coordinates of the mirror center and the ranging center of the robot and the camera center at a fixed position, and obtain the vibration-vision position and the measurement-vision position;

[0026] Fix the vibration-vision position and the measurement-vision position, and adjust the robot to emit light at a preset rated power on the metal plate of the product to be welded;

[0027] The laser ranging sensor is used to measure the distance of the calibration board, and the relative height DZ1 of the robot and the welding surface is obtained.

[0028] Further, the space position parameters of the copper nozzle three-axis are set according to the CAD drawing and the relative height, comprising:

[0029] The robot is operated to move to a plurality of MARK points in the lightweight file, and the coordinates of the robot after moving are recorded to obtain the photographing positions of the plurality of MARK points;

[0030] The center of the copper nozzle is aligned with the center of each MARK point in turn, and the positions of the copper nozzle three-axis X and Y are recorded and fixed;

[0031] The Z-axis of the copper nozzle three-axis is adjusted to completely press the busbar of the battery cell pole, and the current Z-axis data DZ is obtained by triggering the laser ranging sensor;

[0032] Determine whether the difference between DZ and the relative height DZ1 is less than the preset height deviation; if yes, record and fix the Z-axis position of the copper nozzle three-axis; if no, jump to S2-1 to recalibrate the vibration-vision position and the measurement-vision position.

[0033] Further, the preset height deviation is obtained by:

[0034] The robot is operated to move to the battery cell pole welding position, the laser ranging spot is adjusted to align with the pole surface, and the current Z-axis data DZ2 is measured and recorded.

[0035] The preset height deviation is calculated according to a formula ΔZ=DZ2-DZ1, and ΔZ is recorded into the robot control parameter.

[0036] Further, the actual position coordinates of the MARK points are acquired, and the acquisition comprises:

[0037] The robot moves to the photographing positions of the MARK points to take photographs, and a plurality of MARK point images are obtained.

[0038] The point coordinates in the MARK point images are detected by using a template matching method, and the actual positions of the MARK points are obtained. Wherein, i represents the index of the MARK point.

[0039] Further, the theoretical photographing coordinates of the battery cell pole are obtained according to the actual position coordinates and the relative theoretical position, and the obtaining comprises:

[0040] The theoretical photographing coordinates (X j ,Y j ) of the battery cell pole are calculated according to a formula ; wherein, represents the theoretical position coordinates of the battery cell pole.

[0041] Further, the offset of the actual position coordinates of the battery cell pole relative to the theoretical position coordinates is acquired by using a multi-template matching method according to a plurality of images, and the acquiring comprises:

[0042] A plurality of pole region photos are collected to obtain a module library containing a plurality of templates.

[0043] The similarity of the plurality of templates and a single image is calculated by using a multi-template matching algorithm, and the template coordinates (X, Y) with the highest similarity are screened.

[0044] The template coordinates (X, Y) with the highest similarity are multiplied by pixel equivalent to obtain the offset (EX, EY) of the battery cell pole.

[0045] Compared with the prior art, the present application has the following beneficial effects:

[0046] By importing the CAD drawing and combining with the visual system, the precise positioning of the battery cell pole is realized; the automatic process reduces manual intervention, significantly improves the welding efficiency; and the same product only needs to be prepared once, and the subsequent task can be automatically completed; the accurate ranging and positioning ensure the consistency of the welding quality; the method is suitable for welding of battery cell poles of different models and specifications, and has strong universality. BRIEF DESCRIPTION OF DRAWINGS

[0047] In order to make the technical solutions of the embodiments of the present application or the prior art clearer, the accompanying drawings needed in the embodiments or prior art description will be briefly introduced. Obviously, the accompanying drawings in the following description only need to be some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort.

[0048] Figure 1 A flowchart of a CAD import-based automatic search for cell pole welding method provided by the present application. DETAILED DESCRIPTION

[0049] The technical solutions of the present application will be described clearly and completely in combination with the embodiments. Obviously, the described embodiments are only some of the embodiments of the present application, but not all. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without any creative effort are within the protection scope of the present application.

[0050] Please refer to Figure 1 The embodiment of the present application provides a CAD import-based automatic search for cell pole welding method, which comprises the following steps.

[0051] S1, obtaining the cell pole and a plurality of MARK points according to the CAD drawing of the product, calculating the relative theoretical position of the cell pole and the plurality of MARK points, and completing the preparation work according to the CAD drawing of the product;

[0052] S2, obtaining the actual position coordinates of the plurality of MARK points, and obtaining the theoretical shooting coordinates of the cell pole according to the actual position coordinates and the relative theoretical position;

[0053] S3, operating the robot to shoot a plurality of images at the theoretical shooting coordinates, and obtaining the offset of the actual position coordinates of the cell pole relative to the theoretical position coordinates by using a multi-template matching method according to the plurality of images;

[0054] S4, judging whether the offset is within a preset threshold range; if yes, adding the theoretical shooting coordinates of the cell pole to the offset, and marking as a qualified welding position; if no, marking the theoretical shooting coordinates of the cell pole as a failed welding position.

[0055] Specifically, the present application mainly comprises two parts of preparation work and formal work. The preparation work is used to build an accurate coordinate system and obtain key parameters, to provide a basis for accurate positioning and welding in the subsequent formal work. The formal work is based on the data obtained and the coordinate system established by the preparation work, to realize the automatic positioning and welding of the cell pole.

[0056] In one implementation, the preparation in step S1 is completed according to the CAD drawing of the product, including:

[0057] The preparation is an important basis for the automatic search of the welding method of the cell pole based on the CAD import, and the operation process is as follows:

[0058] 1. Process the CAD drawing;

[0059] Format conversion and lightweight processing: convert the CAD drawing of the product into a dxf file, perform lightweight processing on the dxf file according to the attribute data of the cell pole and the MARK point, only keep the pole and MARK point information, generate a lightweight file, and speed up the inference speed of subsequent data processing, improve the overall work efficiency, and reduce the burden of software data processing;

[0060] Detection and calculation: use a target detection algorithm to automatically detect the cell poles and MARK points in the lightweight file to obtain the theoretical position coordinates of the cell poles and a plurality of MARK point coordinates;

[0061] Then, the relative distance between the cell pole and each MARK point is calculated according to these coordinates, so as to obtain the relative theoretical position of the cell pole and the plurality of MARK points, thereby providing key data support for subsequent positioning.

[0062] 2. Build a coordinate system;

[0063] First, establish a robot tool coordinate system and make it parallel to the XY of the copper nozzle three-axis, so as to ensure that the movement of the copper nozzle has a clear direction and position reference in a specific coordinate system during the operation of the robot, and ensure the accuracy of the welding operation;

[0064] Then, using the nine-point calibration method, the calibration plate placed on the product to be welded is used as a calibration tool to realize the unification of the camera center and the robot tool coordinate system, and to calculate the pixel equivalent. The specific steps are as follows:

[0065] Divide the calibration plate into NXM rectangular regions with a side length of L to obtain a plurality of rectangular frames. After the camera takes a picture of the calibration plate, the machine learning algorithm is used to obtain the left upper corner coordinates (X1, Y1) and the right lower corner coordinates (X2, Y2) of a single rectangular frame in the captured image. Then, by calculating the length A1 and the width B1 of the rectangular frame, the pixel equivalent E is calculated according to the formula E=(A / A1+B / B1) / 2 (where A=N*L, B=M*L);

[0066] The pixel equivalent is to establish a connection between the image coordinates and the actual physical coordinates, and to provide a conversion basis for subsequent image-based position calculation;

[0067] Then, the relative height of the robot and the welding surface is obtained:

[0068] First, the galvanometer center and the ranging center of the robot are adjusted, and the relative position coordinates of the galvanometer center and the ranging center of the robot to the camera center when the galvanometer center and the ranging center are fixed are calculated to obtain the galvanometer-vision position and the ranging-vision position;

[0069] The specific operation steps can include:

[0070] A metal plate is placed on the trolley where the product to be welded is placed, and the robot posture is adjusted only in the horizontal and vertical directions so that the galvanometer is at the preset focal length position directly above the metal plate, and the robot coordinate values (mainly the X and Y values) of this position are recorded;

[0071] A temporary cross file is established at the galvanometer center point, and using the file, the galvanometer center emits weak power (20% of the rated power) laser to draw a visually recognizable cross pattern on the metal plate. The robot posture is adjusted only in the horizontal and vertical directions so that the cross pattern on the metal plate is at the center of the camera, and the robot position of this point is recorded again. The X-axis and Y-axis positions of the robot are subtracted twice to obtain the relative position coordinates (DX1, DY1) of the galvanometer center relative to the vision center.

[0072] Similarly, the robot posture is adjusted only in the horizontal and vertical directions so that the cross pattern on the metal plate is at the center of the camera, and the robot position of this point is recorded. The robot posture is adjusted only in the horizontal and vertical directions so that the laser ranging spot is at the center of the cross pattern, and the robot position of this point is recorded. The X-axis and Y-axis positions of the robot are subtracted twice to obtain the relative position coordinates (DX2, DY2) of the ranging center relative to the vision center.

[0073] After fixing the two positions, the robot is adjusted to emit light at a preset rated power (in this embodiment, 20% of the rated power is weak power, which is the preset rated power light emission) on the metal plate of the product to be welded. Then, the laser ranging sensor is used to range the calibration plate to obtain the relative height DZ1 of the robot to the welding surface, and the Z-axis data of the robot is recorded and defined into the robot axis variable Z1 to ensure that the copper nozzle maintains a suitable distance from the welding surface during welding.

[0074] Next, the robot is moved to the battery cell pole welding position, the laser ranging spot is adjusted to align with the pole surface, the current Z-axis data DZ2 is measured and recorded, the preset height deviation is calculated according to the formula ΔZ = DZ2 - DZ1, and the robot control parameters are recorded;

[0075] 3. Set the spatial position parameters of the copper nozzle three-axis;

[0076] Firstly, the robot is moved to several MARK points in the lightweight file, and the coordinates of the robot after movement are recorded to obtain the shooting positions of the MARK points;

[0077] The center of the copper nozzle is aligned with the center of the MARK points in turn, and the positions of the three axes X and Y of the copper nozzle are recorded and fixed;

[0078] Then, the Z axis of the copper nozzle three-axis is adjusted to completely press the busbar of the battery cell pole, triggering the laser ranging sensor to obtain the current Z axis data DZ;

[0079] The final position of the Z axis of the copper nozzle three-axis is determined by judging whether the difference between DZ and the relative height DZ1 is less than the preset height deviation. If the difference is less than the preset height deviation, the Z axis position of the copper nozzle three-axis is recorded and fixed; if not, the sighting position and the measuring position are recalibrated.

[0080] It should be noted that only one preparation work is needed for the same type of product, and there is no need to repeat multiple times.

[0081] In one embodiment, the method for obtaining the actual position coordinates of the MARK points and the theoretical shooting coordinates of the battery cell pole in step S2 can include:

[0082] The robot is moved to the shooting positions of the MARK points to take pictures, obtaining MARK point images;

[0083] The point coordinates in the MARK point images are detected using a template matching method to obtain the actual positions of the MARK points wherein i represents the index of the MARK point;

[0084] The theoretical shooting coordinates (X j ,Y j ) of the battery cell pole are calculated according to the formula j ,Y j ).

[0085] In one embodiment, the method for obtaining the offset of the actual position coordinates of the battery cell pole relative to the theoretical position coordinates in step S3 can include:

[0086] Collecting several pole region photos to obtain a module library containing several templates;

[0087] Using a multi-template matching algorithm to calculate the similarity of several templates and a single image, and screening to obtain the template coordinates (X, Y) with the highest similarity;

[0088] Multiplying the template coordinates (X, Y) with the highest similarity by the pixel equivalent to obtain the offset (EX, EY) of the battery cell pole.

[0089] Finally, in step S4, it is judged whether the offset amounts (EX, EY) of the X-axis and the Y-axis are within the preset threshold range, respectively; if yes, the theoretical shooting coordinates of the cell pole are added with the offset amounts, and are marked as qualified welding positions, and then the robot is controlled to weld at the qualified welding positions; if no, the theoretical shooting coordinates of the cell pole are marked as invalid welding positions.

[0090] Part of the data in the above formula is calculated by removing the dimension, and the formula is obtained by software simulation of a large amount of collected data to be closest to the real situation; the preset parameters and the preset threshold in the formula are set by the person skilled in the art according to the actual situation or obtained by a large amount of data simulation.

[0091] Working principle of the present application:

[0092] Firstly, the CAD drawing is converted and lightened to obtain the relative theoretical position of the cell pole and the MARK point. Then, the coordinate system is constructed, the camera and the robot tool coordinate system are unified, and the pixel equivalent is calculated to obtain the relative height of the robot and the welding surface and the preset height deviation. Finally, the MARK point shooting position is determined, the copper nozzle three-axis position is adjusted, and the preparation work is completed.

[0093] Then, the robot is operated to shoot the MARK point to obtain the actual position coordinates, and the theoretical shooting coordinates of the cell pole are calculated combined with the relative theoretical position. Then, the coordinates are shot, the offset amount is obtained, and it is judged whether it is within the threshold. If yes, the qualified welding position is obtained according to the offset amount; if no, it is marked as an invalid position.

[0094] The above examples are only used to illustrate the technical method of the present application and are not limited. Although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical method of the present application can be modified or replaced equivalently without departing from the spirit and scope of the technical method of the present application.

Claims

1. A CAD import based automated finding of cell tab welding method, characterized in that, The method comprises the following steps: S1, calculating the relative theoretical position of the cell pole and a plurality of MARK points according to the CAD drawing of the product, and completing the preparation work according to the CAD drawing of the product; S2, obtaining the actual position coordinates of a plurality of MARK points, and obtaining the theoretical shooting coordinates of the cell pole according to the actual position coordinates and the relative theoretical position, comprising: S11-1, converting the CAD drawing of the product into a dxf file, and performing lightweight processing on the dxf file according to the attribute data of the cell pole and the MARK points to obtain a lightweight file; S11-2, using a target detection algorithm to automatically detect the cell pole and the MARK points in the lightweight file to obtain the theoretical position coordinates of the cell pole and a plurality of MARK point coordinates; S11-3, calculating the relative distance between the cell pole and each MARK point according to the theoretical position coordinates of the cell pole and a plurality of MARK point coordinates to obtain the relative theoretical position of the cell pole and a plurality of MARK points; S3, operating the robot to shoot a plurality of images at the theoretical shooting coordinates, and using a multi-template matching method to obtain the offset of the actual position coordinates of the cell pole relative to the theoretical position coordinates according to the plurality of images; The method for obtaining the offset of the actual position coordinates of the cell pole relative to the theoretical position coordinates according to the plurality of images using a multi-template matching method comprises: Collecting a plurality of pole region photos to obtain a module library containing a plurality of templates; Using a multi-template matching algorithm to calculate the similarity of a plurality of templates and a single image, and screening to obtain the template coordinates (X, Y) with the highest similarity; Multiplying the template coordinates (X, Y) with the highest similarity by the pixel equivalent to obtain the cell pole offset (EX, EY); S4, determining whether the offset is within a preset threshold range; if yes, adding the theoretical shooting coordinates of the cell pole to the offset and marking as a qualified welding position; if no, marking the theoretical shooting coordinates of the cell pole as an invalid welding position.

2. The CAD import based automated finding of cell tab welding method of claim 1, wherein, The preparation work comprises: S12-1, establishing a robot tool coordinate system, and making the robot tool coordinate system parallel to the XY plane of the copper nozzle three-axis; S12-2, unifying the camera center and the robot tool coordinate system using a nine-point calibration method, and calculating the pixel equivalent using a calibration board; wherein the calibration board is placed on the product to be welded for calibration; S12-3, using a laser ranging sensor to obtain the relative height of the robot and the welding surface, and setting the spatial position parameters of the copper nozzle three-axis according to the CAD drawing and the relative height.

3. The CAD import based automated finding of cell tab welding method of claim 2, wherein, The method for calculating the pixel equivalent using the calibration board comprises: Dividing the calibration board into N×M rectangular regions with a side length of L to obtain a plurality of rectangular frames; Using a camera to take a photo of the calibration board, and using a machine learning algorithm to obtain the upper left corner coordinates (X1, Y1) and the lower right corner coordinates (X2, Y2) of a single rectangular frame in the shooting image; Subtracting the horizontal and vertical coordinates of the lower right corner coordinates (X2, Y2) from the upper left corner coordinates (X1, Y1) to obtain the length A1 and the width B1 of the rectangular frame; A pixel equivalent E is calculated according to the formula E=(A / A1+B / B1) / 2; wherein A and B represent the length and width of the calibration board, and A=N*L and B=M*L.

4. The method of claim 3, wherein, The relative height of the robot and the welding surface is obtained by using the laser ranging sensor, and the relative height of the robot and the welding surface is obtained by using the laser ranging sensor. The mirror center and the ranging center of the robot are adjusted, the relative position coordinates of the mirror center and the ranging center of the robot in the fixed position and the camera center are calculated, and the vibration-vision position and the measurement-vision position are obtained. The vibration-vision position and the measurement-vision position are fixed, and the robot is adjusted to emit light at a preset rated power on the metal plate of the product to be welded. The laser ranging sensor is used to measure the distance of the calibration board, and the relative height DZ1 of the robot and the welding surface is obtained.

5. The CAD import based automated finding of cell tab welding method of claim 2, wherein, The space position parameters of the copper nozzle three-axle are set according to the CAD drawing and the relative height, and the space position parameters of the copper nozzle three-axle are set according to the CAD drawing and the relative height. The robot is moved to a plurality of MARK points in the lightweight file, and the coordinates of the robot after moving are recorded to obtain the photographing positions of the plurality of MARK points. The center of the copper nozzle is aligned with the center of the plurality of MARK points in sequence, and the positions of the X and Y axes of the copper nozzle three-axle are recorded and fixed. The Z axis of the copper nozzle three-axle is adjusted to completely press the busbar of the cell pole, and the current Z axis data DZ is obtained by triggering the laser ranging sensor. It is judged whether the difference between DZ and the relative height DZ1 is less than a preset height deviation; if yes, the Z axis position of the copper nozzle three-axle is recorded and fixed; if no, jump to S2-1, and recalibrate the vibration-vision position and the measurement-vision position.

6. The CAD import based automated finding of cell tab welding method of claim 5, wherein, The preset height deviation is obtained by: The robot is moved to the cell pole welding position, the laser ranging spot is adjusted to align with the pole surface, the current Z axis data DZ2 is measured and recorded, and the current Z axis data DZ2 is measured and recorded. The preset height deviation is calculated according to the formula ΔZ=DZ2-DZ1, and ΔZ is recorded in the robot control parameters.

7. The method of claim 1, wherein, The actual position coordinates of the plurality of MARK points are obtained, and the actual position coordinates of the plurality of MARK points are obtained. The robot is moved to the photographing position of the plurality of MARK points to take pictures, and a plurality of MARK point images are obtained. The template matching method is used to detect the point coordinates in the MARK point images, and actual positions of the MARK points are obtained ; wherein, i represents an index of the MARK point.

8. The CAD import based automated finding of cell tab welds method of claim 1, wherein, The theoretical shooting coordinates of the cell pole are obtained according to the actual position coordinates and the relative theoretical position, and the theoretical shooting coordinates of the cell pole are obtained according to the actual position coordinates and the relative theoretical position. According to the formula The theoretical shooting coordinates of the cell pole are calculated ; wherein represent the theoretical position coordinates of the cell pole.

Images