Flight welding visual synchronous deviation correction method, device and equipment and storage medium

Abstract

The invention discloses a flight welding visual synchronization deviation correction method, device and equipment and a storage medium, applied to power battery flight welding, and the method comprises the steps that photographing point position coordinates are determined through a welding motion reference track, and a coordinate transformation matrix of image coordinates and actual coordinates is calculated; the collected real-time image of the battery to be welded is recognized, and actual welding coordinates are determined in combination with the coordinate transformation matrix; and real-time synchronous flying welding is conducted on the to-be-welded point position according to the actual welding coordinates and the welding reference coordinates. In the flying welding process, the photographing point positions of all the actual welding coordinates can be accurately recognized, the image information of the to-be-welded point positions is collected at a high speed in real time, synchronous flying welding can be conducted after the actual welding coordinates are recognized every time, and the overall welding efficiency and welding quality are effectively improved.

Description

Technical Field

[0001] The present application relates to the technical field of flying welding, and more specifically, to a flying welding visual synchronous correction method, device, equipment and storage medium. Background Art

[0002] Power batteries are widely used in new energy vehicles, mobile devices and other fields due to their lightweight and long life. Power battery welding technology has also become one of the important technologies in the development of power batteries. However, traditional spot welding technology is prone to problems such as low welding efficiency and poor welding quality when used in power battery welding.

[0003] The traditional welding positioning method requires the camera to be gradually moved to the top of each battery to take pictures, and then its coordinates are calculated for correction welding. This process frequently starts and stops the camera and mechanical equipment, resulting in welding and inspection being out of sync, leading to low welding efficiency and slow production cycle. Summary of the invention

[0004] In response to at least one defect or improvement need in the prior art, the present invention provides a flying welding visual synchronous correction method, device, equipment and storage medium, which are used to solve the problem in the prior art that welding and detection are not synchronized during battery welding, resulting in low welding efficiency and slow production cycle.

[0005] To achieve the above-mentioned purpose, according to a first aspect of the present invention, a flying welding vision synchronization correction method is provided, which is applied to flying welding of power batteries, comprising: The coordinates of the photographing points are determined through the welding motion reference trajectory, and the coordinate conversion matrix between the image coordinates and the actual coordinates is calculated; Identify the collected real-time image of the battery to be welded, and determine the actual welding coordinates in combination with the coordinate transformation matrix; The welding points are subjected to real-time synchronous flying welding according to the actual welding coordinates and the welding reference coordinates.

[0006] In a possible implementation, the coordinates of the photographing points are determined by simulating the welding motion trajectory, and the coordinate conversion matrix between the image coordinates and the actual coordinates is calculated, including: When the welding robot moves along the welding motion reference trajectory, it takes multiple photos to determine the coordinates of the photo points; A calibration plate is set below the coordinates of the photographing point to calculate the coordinate transformation matrix between the image coordinates and the actual coordinates.

[0007] In a possible implementation, when the welding robot moves along the welding motion reference trajectory, multiple photographs are taken to determine the coordinates of the photographing points, including: The position relationship of the welding point to be welded in the captured image is determined. When the welding point to be welded is within the preset range of the captured image, the corresponding welding robot coordinates are the photographing point coordinates.

[0008] In a possible implementation, a calibration plate is set below the coordinates of the photographing point to calculate the coordinate conversion matrix between the image coordinates and the actual coordinates, including: Obtain the image coordinate information of the calibration plate by taking photos and record the actual coordinate information of the calibration plate; The coordinate transformation matrix from the image coordinates to the actual coordinates is calculated based on the image coordinate information of the calibration plate and the actual coordinate information of the calibration plate.

[0009] In a possible implementation, the real-time image of the battery to be welded is recognized, and the actual welding coordinates are determined in combination with the coordinate transformation matrix, including: When the welding robot moves to the coordinates of the photographing point, it automatically takes a photo to obtain a real-time image of the battery to be welded; The real-time image of the battery to be welded is processed by image recognition and combined with the coordinate transformation matrix to obtain the actual welding coordinates.

[0010] In a possible implementation, image recognition processing is performed on the real-time image of the battery to be welded and the actual welding coordinates are obtained in combination with the coordinate transformation matrix, including: Extracting the image area to be welded from the real-time image of the battery to be welded using a first preset algorithm; Using a second preset algorithm to fit the image area to be welded to determine the welding image coordinates; The welding image coordinates are converted into actual welding coordinates based on the coordinate transformation matrix.

[0011] In a possible implementation, real-time synchronous flying welding is performed on the welding points according to the actual welding coordinates and the welding reference coordinates, including: Calculate welding coordinate deviation based on actual welding coordinate and welding reference coordinate; When the welding coordinate deviation does not exceed the preset range, real-time synchronous flying welding is performed on the welding points.

[0012] According to a second aspect of the present invention, there is also provided a flying welding vision synchronous correction device, which is applied to a welding robot and is characterized in that it comprises: A calculation module, which is configured to determine the coordinates of the photographing points through the welding motion reference trajectory, and calculate the coordinate conversion matrix between the image coordinates and the actual coordinates; A coordinate recognition module, which is configured to recognize the collected real-time image of the battery to be welded and determine the actual welding coordinates in combination with the coordinate conversion matrix; The flying welding module is configured to perform real-time synchronous flying welding on the welding points according to the actual welding coordinates and the welding reference coordinates.

[0013] According to the third aspect of the present invention, there is also provided a flying welding visual synchronous deviation correction device, which includes at least one processing unit and at least one storage unit, wherein the storage unit stores a computer program, and when the computer program is executed by the processing unit, the processing unit executes the steps of any one of the above-mentioned flying welding visual synchronous deviation correction methods.

[0014] According to a fourth aspect of the present invention, there is also provided a storage medium storing a computer program executable by an access authentication device, wherein when the computer program runs on the access authentication device, the access authentication device executes any of the steps of the above-mentioned flying welding visual synchronous correction method.

[0015] In general, the above technical solutions conceived by the present invention can achieve the following beneficial effects compared with the prior art: The present invention provides a flying welding visual synchronous correction method, which determines in advance the coordinates of multiple photographing points in the welding motion reference trajectory of the welding robot, so that multiple welding points of multiple batteries to be welded can be identified, thereby realizing real-time and high-speed acquisition of image information of the points to be welded, and after each identification of the actual welding coordinates, the welding robot can perform real-time synchronous flying welding on the points to be welded, realizing the synchronization of detection and welding, thereby improving the overall welding efficiency, while improving the production rhythm and ensuring the welding quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 A schematic diagram of a flow chart of an embodiment of a flying welding vision synchronous correction method provided by the present invention; Figure 2 A schematic diagram of a flow chart of an embodiment of obtaining actual welding coordinates provided by the present invention; Figure 3 A schematic structural diagram of an embodiment of a flying welding vision synchronous correction method device provided by the present invention; Figure 4 A schematic diagram of the structure of the on-the-fly welding visual synchronous correction equipment provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0019] The terms "first", "second", "third", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0020] The present invention provides a flying welding visual synchronous correction method, device, equipment and storage medium, which are described below respectively.

[0021] See also Figure 1 , Figure 1 The present invention provides a flowchart of an embodiment of a method for visual synchronization correction of flying welding. In a specific embodiment of the present invention, a method for visual synchronization correction of flying welding is disclosed, which is applied to flying welding of power batteries, and includes: S101, determining the coordinates of the photographing points through the welding motion reference trajectory, and calculating the coordinate conversion matrix between the image coordinates and the actual coordinates; S102, identifying the collected real-time image of the battery to be welded, and determining the actual welding coordinates in combination with the coordinate conversion matrix; S103, performing real-time synchronous flying welding on the welding points according to the actual welding coordinates and the welding reference coordinates.

[0022] In the above embodiment, the welding robot has a shooting camera and a welding galvanometer. The welding galvanometer has an independent motion mechanism. During the movement of the robot, the welding galvanometer adjusts the laser for welding by controlling the motion mechanism and is not affected by the movement of the robot. The welding robot moves on the welding motion reference track to identify the real-time image of the battery to be welded and determine the actual welding coordinates. Each time the actual welding coordinates are identified, real-time welding can be performed through the welding galvanometer, realizing the synchronous flying welding of the real-time image of the battery to be welded and the welding point.

[0023] In order to determine the welding motion reference trajectory, the shooting camera on the welding robot can be turned on for real-time image acquisition. The motion trajectory of the welding robot can be set according to the welding position of the battery to be welded and the real-time image of the camera to ensure that the robot's motion trajectory can pass above the product welding position. This trajectory can be used as the welding motion reference trajectory of the robot.

[0024] Compared with the prior art, the present embodiment provides a flying welding visual synchronous correction method, which determines in advance the coordinates of multiple photographing points in the welding motion reference trajectory of the welding robot, thereby realizing the recognition of multiple welding points of multiple batteries to be welded, and thus improving the overall efficiency of battery welding, thereby realizing real-time and high-speed acquisition of image information of the points to be welded, and each time after the actual welding coordinates are identified, the welding robot can perform real-time synchronous flying welding on the points to be welded, realizing the synchronization of detection and welding, thus improving the overall welding efficiency, while improving the production rhythm and ensuring the welding quality.

[0025] In some embodiments of the present invention, the coordinates of the photographing points are determined by simulating the welding motion trajectory, and the coordinate conversion matrix between the image coordinates and the actual coordinates is calculated, including: When the welding robot moves along the welding motion reference trajectory, it takes multiple photos to determine the coordinates of the photo points; A calibration plate is set below the coordinates of the photographing point to calculate the coordinate transformation matrix between the image coordinates and the actual coordinates.

[0026] In the above embodiment, on the welding motion reference trajectory, key positions can generally be selected or photographing points can be set at certain intervals according to the needs of welding quality monitoring. The selection of these points should ensure that the state of the welding process can be fully reflected. In order to enable the welding robot to automatically take pictures through the shooting camera every time it passes through the coordinates of the photographing point, the welding robot can be controlled by programming to slow down the running speed at these points and trigger the camera to take pictures, so as to obtain a clear and complete real-time image of the battery to be welded.

[0027] Set a calibration plate with known geometric features (such as a checkerboard calibration plate, a dot calibration plate, etc.) under each photo point. The function of the calibration plate is to provide a set of known correspondences between image coordinates and actual coordinates, which serves as the basis for subsequent calculation of the coordinate transformation matrix. When taking photos, ensure that the camera can capture both the welding area and part of the calibration plate at the same time, so as to facilitate subsequent image processing and coordinate transformation.

[0028] In some embodiments of the present invention, when the welding robot moves along the welding motion reference trajectory, multiple photographs are taken to determine the coordinates of the photographing points, including: The position relationship of the welding point to be welded in the captured image is determined. When the welding point to be welded is within the preset range of the captured image, the corresponding welding robot coordinates are the photographing point coordinates.

[0029] In the above embodiment, in order to ensure welding quality and efficiency during the welding automation process, the welding robot needs to accurately operate according to the preset welding motion reference trajectory. In order to monitor the welding process in real time and adjust the welding parameters, the robot will take multiple photos during the movement to determine the coordinates of the key photo points.

[0030] After each photo is taken, the acquired image is first preprocessed, including denoising, contrast enhancement, color correction and other steps to improve the image quality and make the points to be welded clearer and easier to identify. The features of the points to be welded are extracted from the image. These features may include geometric shapes such as points, lines, and surfaces, or specific patterns based on image texture, color and other attributes. After each photo is taken and the position of the points to be welded is identified, the extracted features are compared with the camera image to determine the specific position of the points to be welded in the captured image.

[0031] Before the welding procedure begins, the preset image center range is determined according to the welding process requirements and the camera image. This image center range can be a rectangular frame, a circular area or other shapes based on pixel coordinates. If the point to be welded is within the preset image center range, the coordinates of the welding robot at this time are recorded as the coordinates of the photographing point. It should be noted that the preset image center range can be specifically set according to the size of the actual image, and the present invention does not impose further restrictions on this.

[0032] In summary, the process of taking multiple photos to determine the coordinates of the photo points while the welding robot moves along the welding motion reference trajectory is a complex process that combines image processing, machine vision and robot control technology. By accurately identifying the positional relationship of the points to be welded in the captured image and recording the welding robot coordinates when the points are within the preset image center range, it provides strong support for real-time monitoring and precise control of the welding process.

[0033] In some embodiments of the present invention, a calibration plate is set below the coordinates of the photographing point to calculate the coordinate conversion matrix between the image coordinates and the actual coordinates, including: Obtain the image coordinates of the calibration plate by taking photos and record the actual coordinate information of the calibration plate; The coordinate transformation matrix from the image coordinates to the actual coordinates is calculated based on the image coordinate information of the calibration plate and the actual coordinate information of the calibration plate.

[0034] In the above embodiments, the calibration plate is usually selected with a pattern having obvious feature points (such as corner points, center of a circle, etc.) to facilitate accurate identification in the image. As a preferred embodiment, the calibration plate selected in the present invention is a nine-point calibration plate. The nine-point calibration plate is placed in the welding work area to ensure that its position is stable and below the coordinates of the photographing point, so that its image can be clearly captured every time a photo is taken.

[0035] Use the camera integrated on the welding robot or an external camera to capture an image containing the nine-point calibration plate, identify the nine feature points of the nine-point calibration plate from the image, and record their image coordinate information (usually pixel coordinates). Use precise measurement tools (such as laser rangefinders, coordinate measuring machines, etc.) to measure the three-dimensional coordinates of each feature point on the nine-point calibration plate in the actual space and record them. These coordinates are the real positions of the nine-point calibration plate in the actual working environment.

[0036] According to the camera imaging principle (such as the pinhole camera model), the mathematical relationship between the image coordinates and the actual coordinates is established, which usually involves the camera's internal parameters (focal length, optical center position, etc.) and external parameters (the camera's posture and position relative to the world coordinate system). The image coordinates and actual coordinate information of multiple feature points on the calibration plate are used to solve the coordinate transformation matrix through the least squares method or other optimization algorithms. The coordinate transformation matrix can transform the image coordinates into actual three-dimensional space coordinates. Additional calibration points or points in the actual welding task are used to verify the accuracy of the coordinate transformation matrix, and adjustments are made as needed to ensure that the accuracy of the conversion meets the welding requirements.

[0037] In some embodiments of the present invention, the real-time image of the battery to be welded is recognized, and the actual welding coordinates are determined in combination with the coordinate conversion matrix, including: When the welding robot moves to the coordinates of the photographing point, it automatically takes a photo to obtain a real-time image of the battery to be welded; The real-time image of the battery to be welded is processed by image recognition and combined with the coordinate transformation matrix to obtain the actual welding coordinates.

[0038] In the above embodiment, when the robot reaches the photo-taking point and stabilizes, the camera is automatically activated to take photos through a built-in trigger mechanism (such as a position sensor signal, a time delay, or an external signal). The camera's exposure time, aperture size, ISO and other parameters will be automatically adjusted according to the ambient light conditions or set by preset parameters to obtain the best image quality. Position differential calculation is used to collect the robot's position information in real time and at high speed, and the position data is compared with the set photo-taking point position to ensure that the robot can trigger the photo-taking at the same point every time. Due to the use of software position comparison method, the addition and deletion of detection points in actual production are not affected by external hardware limitations, which is significantly better than using hardware triggering photo-taking solutions such as sensors. The camera uses a high-precision camera with high frame rate, high speed and low exposure. While ensuring the detection accuracy, it can also shorten the time consumption of image acquisition and transmission, providing the prerequisite for subsequent welding while shooting.

[0039] On the basis of image recognition, the coordinates of the identified battery to be welded in the image (usually pixel coordinates) are converted into actual three-dimensional space coordinates. The coordinate transformation matrix previously calculated by the nine-point calibration plate is required. Through the coordinate matrix transformation, the image coordinates are mapped to the actual working environment. Since various factors in the actual working environment (such as illumination changes, camera distortion, etc.) may affect the accuracy of coordinate transformation, it may be necessary to further correct and optimize the converted coordinates. This can be achieved by introducing additional sensor data (such as ranging data from a laser rangefinder), using multi-view image fusion technology, or using more complex mathematical models. After correction and optimization, the precise actual coordinates of the battery to be welded are finally determined. These coordinates will serve as the basis for the welding robot to perform welding operations, guide the robot to accurately move to the welding position, and perform welding tasks.

[0040] In summary, the process of identifying the real-time images of the batteries to be welded and determining the actual welding coordinates in combination with the coordinate transformation matrix is ​​an indispensable part of welding automation. Through this process, the welding robot can achieve precise control of the welding position and improve the accuracy and efficiency of welding.

[0041] See also Figure 2 , Figure 2 A schematic diagram of a flow chart of an embodiment of obtaining actual welding coordinates provided by the present invention. In some embodiments of the present invention, image recognition processing is performed on the real-time image of the battery to be welded and the actual welding coordinates are obtained in combination with the coordinate conversion matrix, including: S201, extracting the image area to be welded from the real-time image of the battery to be welded using a first preset algorithm; S202, using a second preset algorithm to fit the image area to be welded to determine the welding image coordinates; S203, converting the welding image coordinates into actual welding coordinates based on the coordinate conversion matrix.

[0042] In the above embodiment, the first preset algorithm is mainly used to roughly process the real-time image of the battery to be welded. The first preset algorithm used in the embodiment of the present invention can be edge detection, color segmentation, texture analysis or shape-based template matching algorithms, and detects features related to the battery to be welded in the preprocessed image. These features may include the contour edge of the battery, a specific color area, a texture pattern or a specific mark (such as a QR code, a barcode). According to the detected features, the image is segmented into different areas, and the image area containing the part to be welded is identified. The segmented image area to be welded is optimized to remove noise, fill small holes, smooth edges, etc., to ensure that the extracted area is accurate and complete.

[0043] The second preset algorithm is mainly used to extract the welding point position information (that is, the welding image coordinates) in detail. The second preset algorithm used in the embodiment of the present invention can be the least squares method, Hough transform, RANSAC algorithm and other algorithms. In the image area to be welded, feature points or feature lines for fitting are further extracted. These features may include corner points, edge points, center points or contours of specific shapes. For round batteries, circle fitting may be used; for rectangles or irregular shapes, polygon fitting or curve fitting may be used. Through the fitting process, the geometric center of the image area to be welded, the edge point coordinates or the coordinates of the specific welding point are determined. These coordinates are relative to the image coordinate system, that is, the welding image coordinates.

[0044] The coordinate transformation matrix describes the mapping relationship from the image coordinate system to the world coordinate system (i.e., the coordinate system in the actual working environment). The determined welding image coordinates are used as input, and the coordinate transformation matrix is ​​applied to transform the coordinates to obtain the actual welding coordinates. This coordinate is a coordinate in three-dimensional space, which contains the specific position information of the welding point in the actual working environment. After obtaining the actual welding coordinates, verification and adjustment may be required to ensure the accuracy and reliability of the coordinates. This can be achieved by comparing with the preset welding point position or by using external sensor data for verification. If a large deviation is found, it may be necessary to re-perform image recognition processing or adjust the coordinate transformation matrix.

[0045] In some embodiments of the present invention, real-time synchronous flying welding is performed on the welding points according to the actual welding coordinates and the welding reference coordinates, including: Calculate welding coordinate deviation based on actual welding coordinate and welding reference coordinate; When the welding coordinate deviation does not exceed the preset range, real-time synchronous flying welding is performed on the welding points.

[0046] In the above embodiment, the welding reference coordinates represent the position where the welding point should be located under ideal conditions and are the reference reference for the welding operation. The actual welding coordinates previously obtained through image recognition and coordinate conversion are compared with the welding reference coordinates, which usually involves direct subtraction of the coordinate values ​​or using a certain distance measurement formula (such as Euclidean distance) to calculate the difference between the two. Based on the comparison results, the welding coordinate deviation is calculated. This deviation may be a two-dimensional or three-dimensional vector, which represents the offset between the actual welding point and the reference welding point in the X, Y (and possibly Z) axis direction. The calculated coordinate deviation is evaluated to determine whether it is within an acceptable range. This usually involves comparing the deviation value with a preset tolerance threshold (i.e., a preset range). The tolerance threshold is determined based on factors such as welding process requirements, material properties, and equipment accuracy.

[0047] After confirming that the deviation is within the allowable range, the welding galvanometer will automatically enter the welding preparation stage, which may include adjusting welding parameters (such as current, voltage, welding speed), selecting appropriate welding tools or fixtures, preheating the materials to be welded, etc. After preparation, the welding galvanometer will start the welding process, move to the position indicated by the actual welding coordinates in real time and synchronously, and start the welding operation. Synchronous flight welding means that the welding process will be dynamically adjusted according to the real-time changes of the actual welding coordinates to ensure that the welding point always remains in the correct position. Finally, through the rapid acquisition of real-time images of the battery to be welded, the rapid processing of the image recognition algorithm and the independent control of welding, the function of welding while shooting is realized, which improves the welding efficiency and the service life of the shaft and motor.

[0048] In order to better implement the flying welding visual synchronization correction method in the embodiment of the present invention, based on the flying welding visual synchronization correction method, correspondingly, please refer to Figure 3 , Figure 3 The structure diagram of an embodiment of a flying welding vision synchronization correction method device provided by the present invention is provided. The embodiment of the present invention provides a flying welding vision synchronization correction method device 300, comprising: A calculation module 310 is configured to determine the coordinates of the photographing points through the welding motion reference trajectory, and calculate the coordinate conversion matrix between the image coordinates and the actual coordinates; A coordinate recognition module 320, which is configured to recognize the collected real-time image of the battery to be welded, and determine the actual welding coordinates in combination with the coordinate conversion matrix; The flying welding module 330 is configured to perform real-time synchronous flying welding on the welding points according to the actual welding coordinates and the welding reference coordinates.

[0049] It should be noted here that: the device 300 provided in the above embodiment can implement the technical solutions described in the above method embodiments. The specific implementation principles of the above modules or units can refer to the corresponding contents in the above method embodiments, which will not be repeated here.

[0050] See also Figure 4 , Figure 4 A schematic diagram of the structure of a flying welding visual synchronization correction device provided by an embodiment of the present invention. Based on the above-mentioned flying welding visual synchronization correction method, the present invention also provides a flying welding visual synchronization correction method device, which can be a computing device such as a mobile terminal, a desktop computer, a notebook, a PDA, and a server. The flying welding visual synchronization correction method device 400 includes a processor 410, a memory 420, and a display 430. Figure 4 Only some components of the synchronous tracking flying welding equipment for real-time measurement of battery height are shown, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead.

[0051] In some embodiments, the memory 420 may be an internal storage unit of the on-the-fly welding visual synchronous deviation correction method device 400, such as a hard disk or memory of the on-the-fly welding visual synchronous deviation correction method device 400. In other embodiments, the memory 420 may also be an external storage device of the on-the-fly welding visual synchronous deviation correction method device 400, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the on-the-fly welding visual synchronous deviation correction method device 400. Further, the memory 420 may also include both an internal storage unit of the on-the-fly welding visual synchronous deviation correction method device 400 and an external storage device. The memory 420 is used to store application software and various data installed in the on-the-fly welding visual synchronous deviation correction method device 400, such as the program code for installing the on-the-fly welding visual synchronous deviation correction method device 400. The memory 420 may also be used to temporarily store data that has been output or is to be output. In one embodiment, a flying welding visual synchronization correction method program 440 is stored in the memory 420, and the flying welding visual synchronization correction method program 440 can be executed by the processor 410, so as to implement the flying welding visual synchronization correction method of each embodiment of the present application.

[0052] In some embodiments, the processor 410 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run program codes or process data stored in the memory 420, such as executing a flying welding vision synchronization correction method.

[0053] In some embodiments, the display 430 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 430 is used to display information on the flying welding visual synchronous deviation correction method device 400 and to display a visualized user interface. The components 410-430 of the flying welding visual synchronous deviation correction method device 400 communicate with each other via a system bus.

[0054] In one embodiment, when the processor 410 executes the on-the-fly welding vision synchronization correction method program 440 in the memory 420 , the steps in the on-the-fly welding vision synchronization correction method described above are implemented.

[0055] This embodiment also provides a computer-readable storage medium, on which a flying welding visual synchronization correction method program is stored. When the flying welding visual synchronization correction method program is executed by a processor, the following steps are implemented: The coordinates of the photographing points are determined through the welding motion reference trajectory, and the coordinate conversion matrix between the image coordinates and the actual coordinates is calculated; Identify the collected real-time image of the battery to be welded, and determine the actual welding coordinates in combination with the coordinate transformation matrix; The welding points are subjected to real-time synchronous flying welding according to the actual welding coordinates and the welding reference coordinates.

[0056] In summary, the present invention provides a flying welding visual synchronous correction method, which determines in advance the coordinates of multiple photographing points in the welding motion reference trajectory of the welding robot, thereby realizing the recognition of multiple welding points of multiple batteries to be welded, and thus improving the overall efficiency of battery welding, thereby realizing real-time and high-speed acquisition of image information of the points to be welded, and each time after the actual welding coordinates are identified, the welding robot can perform real-time synchronous flying welding on the points to be welded, realizing the synchronization of detection and welding, thereby improving the overall welding efficiency, while improving the production rhythm and ensuring the welding quality.

[0057] The present application also provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of the above method are implemented. The computer-readable storage medium may include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a micro drive, and a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nanosystem (including a molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.

[0058] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0059] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0060] In the several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0061] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0062] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0063] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk and other media that can store program codes.

[0064] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable memory, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0065] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the specification and practicing the disclosure here, those skilled in the art will easily think of the implementation scheme of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field not recorded in the present disclosure. The description and examples are regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

[0066] The technical features of the above embodiments may 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.

[0067] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A flying welding visual synchronization correction method, applied to flying welding of power batteries, characterized in that: include: The coordinates of the photographing points are determined through the welding motion reference trajectory, and the coordinate conversion matrix between the image coordinates and the actual coordinates is calculated; Identify the collected real-time image of the battery to be welded, and determine the actual welding coordinates in combination with the coordinate conversion matrix; The welding points to be welded are subjected to real-time synchronous flying welding according to the actual welding coordinates and the welding reference coordinates.

2. The flying welding visual synchronous deviation correction method according to claim 1 is characterized in that: The method of determining the coordinates of the photographing points by simulating the welding motion trajectory and calculating the coordinate conversion matrix between the image coordinates and the actual coordinates includes: When the welding robot moves along the welding motion reference trajectory, multiple photos are taken to determine the coordinates of the photo points; A calibration plate is arranged below the coordinates of the photographing point to calculate the coordinate conversion matrix between the image coordinates and the actual coordinates.

3. The flying welding visual synchronous correction method according to claim 2 is characterized in that: The method of taking multiple photos to determine the coordinates of the photo points when the welding robot moves along the welding motion reference trajectory includes: The position relationship of the to-be-welded point in the captured image is determined, and when the to-be-welded point is within a preset range of the captured image, the corresponding welding robot coordinates are the photographing point coordinates.

4. The flying welding visual synchronous correction method according to claim 2 is characterized in that: The calibration plate is arranged below the coordinates of the photographing point to calculate the coordinate conversion matrix between the image coordinates and the actual coordinates, including: Acquire the image coordinate information of the calibration plate by taking photos and record the actual coordinate information of the calibration plate; A coordinate conversion matrix for converting image coordinates into actual coordinates is calculated according to the image coordinate information of the calibration plate and the actual coordinate information of the calibration plate.

5. The flying welding vision synchronous correction method according to claim 1 is characterized in that: The method of identifying the collected real-time image of the battery to be welded and determining the actual welding coordinates in combination with the coordinate conversion matrix includes: When the welding robot moves to the coordinates of the photographing point, it automatically takes a photo to obtain a real-time image of the battery to be welded; The real-time image of the battery to be welded is subjected to image recognition processing and combined with the coordinate conversion matrix to obtain the actual welding coordinates.

6. The flying welding vision synchronous correction method according to claim 5 is characterized in that: The performing image recognition processing on the real-time image of the battery to be welded and obtaining the actual welding coordinates in combination with the coordinate conversion matrix includes: Extracting the image area to be welded from the real-time image of the battery to be welded using a first preset algorithm; Using a second preset algorithm to fit the image area to be welded to determine the welding image coordinates; The welding image coordinates are converted into actual welding coordinates based on the coordinate conversion matrix.

7. The flying welding vision synchronous correction method according to claim 1 is characterized in that: The real-time synchronous flying welding of the welding points to be welded according to the actual welding coordinates and the welding reference coordinates comprises: Calculating the welding coordinate deviation according to the actual welding coordinate and the welding reference coordinate; When the welding coordinate deviation does not exceed the preset range, real-time synchronous flying welding is performed on the welding point.

8. A flying welding visual synchronous correction device, characterized in that: Applied to welding robots, characterized by comprising: A calculation module, which is configured to determine the coordinates of the photographing points through the welding motion reference trajectory, and calculate the coordinate conversion matrix between the image coordinates and the actual coordinates; A coordinate recognition module, which is configured to recognize the collected real-time image of the battery to be welded, and determine the actual welding coordinates in combination with the coordinate conversion matrix; The flying welding module is configured to perform real-time synchronous flying welding on the welding points according to the actual welding coordinates and the welding reference coordinates.

9. A flying welding visual synchronous correction device, characterized in that: It comprises at least one processing unit and at least one storage unit, wherein the storage unit stores a computer program, and when the computer program is executed by the processing unit, the processing unit executes the steps of the flying welding visual synchronous correction method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: It stores a computer program executable by an access authentication device. When the computer program runs on the access authentication device, the access authentication device executes the steps of the flying welding visual synchronous correction method according to any one of claims 1 to 7.

Images