Plane short weld joint identification method, welding method and device
Through a single camera two-step photography method and system calibration equation, combined with three-dimensional matching relationship and morphological processing, the problems of low efficiency and poor autonomy in flat short weld welding are solved, efficient independent welding trajectory recognition and positioning are achieved, and welding is improved Accuracy and flexibility.
Patent Information
- Application Number
- CN202411261418.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-10
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2044-09-10
AI Technical Summary
The prior art has low efficiency in flat short weld welding, cannot independently identify and locate arc starting points and arc extinguishing points, and the sensor auxiliary methods are complex and do not adapt to complex environments, making it difficult to meet the requirements of high-precision welding.
The single camera two-step photography method is used to identify the welding trajectory through systematic calibration equations and stereo matching relationships, and combine brightness and contrast enhancement, morphological processing and B-spline fitting to achieve autonomous identification and positioning of the welding trajectory.
It improves the autonomy and flexibility of robot welding, and can efficiently identify and locate the arc starting points and arc extinguishing points of planar short welds. It is suitable for a variety of planar short weld welding occasions and meets the requirements of high-precision welding.
Smart Images

Figure CN119057318A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the field of automated welding, and in particular to a planar short weld identification method, a welding method and a device. Background Art
[0002] Manual teaching welding cannot adapt to the changing external environment, and cannot automatically correct possible welding trajectory errors under non-ideal conditions. It is rapidly transforming into autonomous welding. Autonomous welding is difficult to achieve because it is difficult for robots to get rid of the recognition and programming of teaching trajectories, and it is difficult to perceive the effective information of the weld as dynamically and flexibly as humans, such as the position of the arc starting point, the position of the arc extinguishing point, and the position of the weld area. For this reason, mechanical sensors, arc sensors, infrared sensors, ultrasonic sensors, electromagnetic sensors, and optical sensors are widely used in robot welding systems. At present, the main forms of intelligent welding include sensor-assisted real-time tracking welding, pre-welding scanning trajectory recognition welding, and pre-welding photography trajectory recognition welding.
[0003] Sensor-assisted real-time tracking welding has the advantage of efficient welding for long straight welds and large-volume standard welds. However, it has the following technical deficiencies for short flat welds: 1. As the length of the weld becomes shorter, the efficiency of this welding method becomes lower, because when the length of the weld is lower than the front distance of the sensor, the tracking welding function will fail; 2. Tracking welding is not completely separated from the teaching track and runs completely independently. It needs the guidance of the teaching track, so when the workpiece placement error is too large, tracking welding cannot be carried out effectively; 3. Tracking welding mainly controls the trajectory of the welding gun during the welding process, but lacks the identification and positioning of the arc starting point and arc extinction point.
[0004] Although the sensor-assisted pre-weld scanning trajectory recognition welding form can enable the robot to autonomously identify the welding trajectory before welding to a certain extent without relying on the teaching playback method, it requires editing the sensor scanning trajectory in advance, which is very inconvenient and inefficient for the robot welding system. The sensor-assisted pre-weld photography trajectory recognition welding form mainly uses binocular vision assistance. Although it has improved the degree of autonomy of planar short weld welding to a certain extent, there are still problems: First, the binocular vision sensor is a composite sensor with a very complex internal structure; it is also very difficult to determine the spatial stereo relationship between the two cameras inside the sensor; second, the lack of a weld stripe extraction algorithm with high adaptability under complex ambient light is also the main reason why binocular vision cannot be widely used in actual welding; third, there are a lot of noise, reflection, bright spots and dark spots at the arc starting point and arc extinction point, which makes it easy for conventional weld stripe extraction algorithms to obtain incomplete weld stripes; the traditional binocular vision-assisted welding method does not determine the positioning method of the arc starting point and arc extinction point, and it is difficult to meet the high-precision welding requirements.
[0005] Therefore, planning the welding trajectory of planar welds has always been the key to autonomous robot welding. However, identifying and positioning welds, arc starting and arc extinction points, and programming welding trajectories are often achieved through inefficient manual teaching. It is impossible to simply and efficiently identify the arc starting and arc extinction points of short planar welds, and it is impossible to simply and efficiently fit the welding trajectory, which is insufficient for intelligent and efficient welding. Summary of the invention
[0006] The purpose of the present invention is to provide a method for identifying short planar welds, which is achieved through two-step photography and is particularly suitable for robot welding of short planar welds, and can achieve efficient welding, such as short planar butt welds with grooves, short planar butt welds without grooves, short planar lap welds or short planar fillet welds.
[0007] The above-mentioned object of the present invention is achieved by the following technical solutions:
[0008] A method for identifying a short weld in a plane comprises the following steps:
[0009] Step 1: Use a single camera installed on the robot to take global photos of the workpiece in two random postures, substitute the camera coordinates of a spatial point in the first shooting posture and the camera coordinates of the point in the second shooting posture into the system calibration equation, and obtain the three-dimensional coordinates of the point in the robot base coordinate system;
[0010] The system calibration equation is as follows:
[0011]
[0012] Where: (X B ,Y B ,Z B ) is a space point in the robot base coordinate system O under the first shooting posture and the second shooting posture B X B Y B Z B The coordinates below; The tool coordinate system O in the first shooting posture H1 X H1 Y H1 Z H1 To the robot base coordinate system O B X B Y B Z B The transformation matrix of is the tool coordinate system O in the second camera posture H2 X H2 Y H2 Z H2 To the robot base coordinate system O B XB Y B Z B The transformation matrix (X C1 ,Y C1 ,Z C1 ) is a spatial point in the camera coordinate system O in the first shooting posture C1 X C1 Y C1 Z C1 The coordinates below; is the camera coordinate system O C1 X C1 Y C1 Z C1 To tool coordinate system O H1 X H1 Y H1 Z H1 The transformation matrix (X C2 ,Y C2 ,Z C2 ) is a spatial point in the camera coordinate system O in the second shooting posture C2 X C2 Y C2 Z C2 The coordinates below; is the camera coordinate system O C2 X C2 Y C2 Z C2 To tool coordinate system O H2 X H2 Y H2 Z H2 The transformation matrix.
[0013] Step 2: Identify and fit the welding trajectory:
[0014] Extract the arc starting point, arc extinguishing point, weld area and four corner point information of the workpiece; calculate the coordinates of the corner points in the camera coordinate system under the first shooting posture and the coordinates in the camera coordinate system under the second camera pose Substitute the stereo matching relationship to obtain the stereo matching relationship T between the two images R ;
[0015] The stereo matching relationship is as follows:
[0016]
[0017] After the weld stripe image is extracted, the weld stripe image is morphologically processed by first corrosion and then expansion, so that the weld stripe point cloud on the image under the first camera posture after processing is The weld stripe point cloud on the image under the second camera pose is: The camera coordinate system O C1 XC1 Y C1 Z C1 Down The coordinates of each point are obtained through the stereo matching relationship T R Obtain the corresponding stereo matching point cloud The camera coordinate system O C2 X C2 Y C2 Z C2 Down The coordinates of each point are obtained through the stereo matching relationship T R Obtain the corresponding stereo matching point cloud
[0018] Step 3, obtaining welding trajectory;
[0019] Will Each point is in the camera coordinate system O C1 X C1 Y C1 Z C1 The coordinates below and Each point is in the camera coordinate system O C2 X C2 Y C2 Z C2 Substitute the coordinates under into the system calibration equation to obtain the welding trajectory F1; Each point is in the camera coordinate system O C2 X C2 Y C2 Z C2 The coordinates below and Each point is in the camera coordinate system O C1 X C1 Y C1 Z C1 Substitute the coordinates of the welding trajectory F1 into the system calibration equation to obtain the welding trajectory F2; obtain the center curve F1 of the welding trajectory F2. 中 , and the center curve F 中 Perform B-spline curve fitting; the trajectory curve F after B-spline curve fitting 焊 Determined as the final weld trajectory.
[0020] As a more optimal technical solution of the present invention, the process of solving the system calibration equation is as follows:
[0021] Rewrite the step system calibration equation as Ax = b; sample the coefficient matrix A of Ax = b and construct 6 standard linear equations A i x=b i (i=1,2,3,4,5,6); Solve each linear equation system A i x=b i The standard solution x of (i=1,2,3,4,5,6)i (i=1,2,3,4,5,6); calculate Chebyshev residual r i (x) = ‖Ax i -b‖ ∞ ; r i The solution corresponding to the minimum absolute value of (x) is identified as the solution to the system calibration equation.
[0022] As a more optimal technical solution of the present invention, the extraction process of the weld stripe image is as follows:
[0023] The brightness and contrast of the weld area are enhanced. The brightness and contrast enhancement functions are:
[0024] g(u,v)=α·f(u,v)+β
[0025] Where: α is the gain, α>0; β is the pixel deviation parameter; f(u,v) is the pixel value of the input image; g(u,v) is the pixel value of the output image.
[0026] The weld stripes are detected as follows:
[0027] s(u,v)=|Δ x f|+|Δ y f|
[0028] Where: s(u,v) is the gradient of the pixel; Δ x f is the horizontal edge pixel gradient; Δ y f is the vertical edge pixel gradient.
[0029] As a more optimal technical solution of the present invention, the process of establishing the system calibration equation is as follows:
[0030] Convert the camera coordinate system to the tool coordinate system;
[0031]
[0032] Where: (X C1 ,Y C1 ,Z C1 ) is a spatial point in the camera coordinate system O in the first shooting posture C1 X C1 Y C1 Z C1 The coordinates below; (X H1 ,Y H1 ,Z H1 ) is the tool coordinate system O of the point in the first shooting posture H1 X H1 Y H1 Z H1 The coordinates below; is the camera coordinate system OC1 X C1 Y C1 Z C1 To tool coordinate system O H1 X H1 Y H1 Z H1 The transformation matrix.
[0033]
[0034] Where: (X C2 ,Y C2 ,Z C2 ) is a spatial point in the camera coordinate system O in the second shooting posture C2 X C2 Y C2 Z C2 The coordinates below; (X H2 ,Y H2 ,Z H2 ) is the tool coordinate system O of the point in the second shooting posture H2 X H2 Y H2 Z H2 The coordinates below; is the camera coordinate system O C2 X C2 Y C2 Z C2 To tool coordinate system O H2 X H2 Y H2 Z H2 The transformation matrix.
[0035] The tool coordinate system is converted to the robot base coordinate system;
[0036]
[0037] Where: (X B ,Y B ,Z B ) is a space point in the robot base coordinate system O under the first shooting posture and the second shooting posture B X B Y B Z B The coordinates below; The tool coordinate system O in the first shooting posture H1 X H1 Y H1 Z H1 To the robot base coordinate system O B X B Y B Z B The transformation matrix of is the tool coordinate system O in the second camera posture H2 X H2 Y H2 Z H2 To the robot base coordinate system O B X B Y B Z B The transformation matrix.
[0038] The system calibration equation is obtained based on the above two conversions.
[0039] Another object of the present invention is to provide a planar short weld welding device, comprising a robot 3, a welding gun 5 fixed on the robot 3, a camera 4 fixed on the welding gun 5, and a workpiece 7 to be welded placed on a welding platform 6;
[0040] The welding process of the flat short weld welding device is as follows:
[0041] To ensure that the camera can capture the entirety of the workpiece in each photographing posture, the robot 3 arbitrarily sets the first photographing posture of the robot 3 to take a photograph of the workpiece 7 to be welded, and then arbitrarily sets the second photographing posture of the robot 3 to take a photograph of the workpiece 7 to be welded, so as to locate the arc starting point and the arc extinction point, identify and fit the welding trajectory; then the final welding trajectory is obtained through the above-mentioned planar short weld recognition method, and finally the final welding trajectory and the arc starting point position and the arc extinction point position are transmitted to the robot system, and the robot drives the welding gun to perform welding.
[0042] Another object of the present invention is to provide a planar short weld welding method. First, the final welding trajectory is obtained through the above-mentioned planar short weld identification method, and then the final welding trajectory and the arc starting point position and arc extinguishing point position are transmitted to the robot system, and the robot drives the welding gun to perform welding.
[0043] The beneficial effects are:
[0044] The present invention uses a single camera two-step photography method to achieve autonomous welding, so that the robot can autonomously locate and identify the welding trajectory of a planar weld, thereby improving the autonomy and flexibility of robot welding. The assembly position and assembly accuracy of the workpiece are not strictly constrained. The welding trajectory can be identified by a single and simple camera without the aid of complex sensors, thereby assisting the robot in achieving autonomous welding. BRIEF DESCRIPTION OF THE DRAWINGS
[0045] The drawings described herein are used to provide further understanding of the present invention and constitute a part of this application. The illustrative examples of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.
[0046] Figure 1This is a welding device of the present invention, wherein: 1. a first photographing posture; 2. a second photographing posture; 3. a robot; 4. a camera; 5. a welding gun; 6. a welding platform; 7. a workpiece to be welded; 8. a weld.
[0047] Figure 2 This is the result of identifying the information of interest of the workpiece in Example 1 of the present invention; from left to right are photos taken in the first shooting posture and the photos taken in the second shooting posture, A is the corner point, B is the welding seam area, C is the arc starting point, and D is the arc extinguishing point.
[0048] Figure 3 Schematic diagram of weld stripe extraction in Example 1 of the present invention; from left to right are weld area, brightness and contrast enhancement, weld stripe detection, and morphological processing.
[0049] Figure 4 This is a weld stereo matching effect diagram in Example 1 of the present invention.
[0050] Figure 5 The effect diagram is obtained for the welding trajectory of the planar short weld in Example 1 of the present invention. DETAILED DESCRIPTION
[0051] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments.
[0052] The present invention firstly proposes a two-step photography method autonomous welding model of a single camera, which can accurately identify the three-dimensional coordinates of spatial points in the robot base coordinate system, and endows the robot with autonomy in welding non-standard planar welds or batch planar welds; secondly, the YOLOv5 neural network is used to locate the arc starting point, arc extinguishing point, workpiece corner point and weld area, which greatly improves the robot's perception ability of spatial targets; then, the weld point cloud is accurately extracted from the weld area through the brightness and contrast enhancement algorithm, edge detection algorithm and morphological processing algorithm; the welding trajectory is identified and fitted from the irresistible, dynamic and irregular interference information through the stereo matching algorithm and the B-spline curve fitting algorithm; finally, the fitted welding trajectory is transmitted to the robot system for autonomous welding of the planar weld.
[0053] The welding method provided by the present invention comprises three modules: S1, establishing a two-step photography method autonomous welding model; S2, identifying and fitting welding trajectories; S3, autonomous welding.
[0054] S1. Establish a two-step photography method autonomous welding model;
[0055] S1.1, Model establishment;
[0056] The first photographing posture and the second photographing posture are set arbitrarily, and it is ensured that the camera can take a picture of the whole workpiece in each photographing posture. The robot 3 takes pictures of the workpiece in the first photographing posture and in the second photographing posture, and a two-step photographing method autonomous welding model can be established.
[0057] S1.2, system calibration equation is established;
[0058] The purpose of establishing the calibration equation is to convert the coordinates of the space point in the camera coordinate system under two positions into three-dimensional coordinates in the base coordinate system that can be recognized by the robot.
[0059] S1.2.1, convert the camera coordinate system to the tool coordinate system;
[0060]
[0061] Where: (X C1 ,Y C1 ,Z C1 ) is a spatial point in the camera coordinate system O in the first shooting posture C1 X C1 Y C1 Z C1 The coordinates below; (X H1 ,Y H1 ,Z H1 ) is the tool coordinate system O of the point in the first shooting posture H1 X H1 Y H1 Z H1 The coordinates below; is the camera coordinate system O C1 X C1 Y C1 Z C1 To tool coordinate system O H1 X H1 Y H1 Z H1 The transformation matrix.
[0062]
[0063] Where: (X C2 ,Y C2 ,Z C2 ) is a spatial point in the camera coordinate system O in the second shooting posture C2 X C2 Y C2 Z C2The coordinates below; (X H2 ,Y H2 ,Z H2 ) is the tool coordinate system O of the point in the second shooting posture H2 X H2 Y H2 Z H2 The coordinates below; is the camera coordinate system O C2 X C2 Y C2 Z C2 To tool coordinate system O H2 X H2 Y H2 Z H2 The transformation matrix.
[0064] S1.2.2. Convert the tool coordinate system to the robot base coordinate system
[0065]
[0066] Where: (X B ,Y B ,Z B ) is a space point in the robot base coordinate system O under the first shooting posture and the second shooting posture B X B Y B Z B The coordinates below; The tool coordinate system O in the first shooting posture H1 X H1 Y H1 Z H1 To the robot base coordinate system O B X B Y B Z B The transformation matrix of is the tool coordinate system O in the second camera posture H2 X H2 Y H2 Z H2 To the robot base coordinate system O B X B Y B Z B The transformation matrix.
[0067] S1.2.3, solve the system calibration equation;
[0068] From steps S1.2.1 and S1.2.2, the system calibration equation can be obtained as follows:
[0069]
[0070] S1.3. Solution of system calibration equation
[0071] The system calibration equation is an overdeterministic equation and cannot be solved using conventional equation solving methods (X B ,Y B ,Z B ), for this purpose, the present invention sets an algorithm for solving superdeterministic equations based on Chebyshev's idea, which is divided into 5 steps:
[0072] S1.3.1. Rewrite the system calibration equation obtained in step S1.2.3 as Ax=b;
[0073] S1.3.2. Sample the coefficient matrix A of Ax=b and construct 6 standard linear equations
[0074] A i x=b i (i=1,2,3,4,5,6);
[0075] S1.3.3. Solve each linear system A i x=b i Standard solution for (i=1,2,3,4,5,6)
[0076] x i (i=1,2,3,4,5,6);
[0077] S1.3.4. Calculate the Chebyshev residual r i (x) = ‖Ax i -b‖ ∞ ;
[0078] S1.3.5. i The solution corresponding to the minimum absolute value of (x) is identified as the solution to the system calibration equation.
[0079] It can be seen that the coordinates (X C1 ,Y C1 ,Z C1 ) and the coordinates of the point in the second camera pose (X C2 ,Y C2 ,Z C2 ) is substituted into the system calibration equation, and the superdeterministic equation solving algorithm based on Chebyshev's idea can be used to obtain the point in the robot base coordinate system O B X B Y B Z B The three-dimensional coordinates of .
[0080] S2, identifying and fitting welding trajectory;
[0081] S2.1, extract interesting information of artifacts;
[0082] YOLOv5 is used to identify the workpiece information of interest on the two images taken; the workpiece information of interest includes four workpiece corners, arc starting point, arc extinction point and weld area, see Figure 2 shown.
[0083] S2.2, Extract weld stripes, see Figure 3 As shown;
[0084] S2.2.1. Brightness and contrast enhancement of weld area;
[0085] The brightness and contrast enhancement functions are:
[0086] g(u,v)=α·f(u,v)+β
[0087] Where: α is the gain, α>0; β is the pixel deviation parameter; f(u,v) is the pixel value of the input image; g(u,v) is the pixel value of the output image.
[0088] S2.2.2, weld streak detection;
[0089] Use Sobel algorithm to detect weld stripes:
[0090] s(u,v)=|Δ x f|+|Δ y f|
[0091] Where: s(u,v) is the gradient of the pixel; Δ x f is the horizontal edge pixel gradient; Δ y f is the vertical edge pixel gradient.
[0092] S2.2.3, morphological treatment of weld stripes;
[0093] The weld stripe image is morphologically processed by first corrosion and then expansion.
[0094] S2.3, Stereo Matching of Weld Seams
[0095] S2.3.1. Obtaining stereo matching relationship
[0096] The stereo matching relationship between the two images is as follows:
[0097]
[0098] The coordinates of the four workpiece corner points obtained in step S2.1 in the camera coordinate system under the first shooting posture and the coordinates in the camera coordinate system under the second camera pose Substituting the above equation, we can obtain the stereo matching relationship T between the two images. R .
[0099] S2.3.2, Stereo matching of weld point clouds, see Figure 4 As shown;
[0100] Let the weld stripe point cloud on the image in the first camera pose processed in step S2.2.3 be The weld stripe point cloud on the image under the second camera pose is:
[0101] The camera coordinate system O C1 X C1 Y C1 Z C1 Down The coordinates of each point are obtained through the stereo matching relationship T R Obtain the corresponding stereo matching point cloud The camera coordinate system O C2 X C2 Y C2 Z C2 Down The coordinates of each point are obtained through the stereo matching relationship T R Obtain the corresponding stereo matching point cloud
[0102] S2.4, obtaining welding trajectory;
[0103] S2.4.1, preliminary welding trajectory determination;
[0104] Will Each point is in the camera coordinate system O C1 X C1 Y C1 Z C1 The coordinates below and Each point is in the camera coordinate system O C2 X C2 Y C2 Z C2 Substituting the coordinates under into the system calibration equation can obtain the welding trajectory F1;
[0105] Will Each point is in the camera coordinate system O C2 X C2 Y C2 Z C2 The coordinates below and Each point is in the camera coordinate system O C1 X C1 Y C1 Z C1 Substitute the coordinates into the system calibration equation to obtain the welding trajectory F2.
[0106] S2.4.2, obtain the final welding trajectory;
[0107] Obtain the center curve F of welding trajectory F1 and welding trajectory F2 中 , and the center curve F 中 Perform B-spline curve fitting. The trajectory curve F after B-spline curve fitting 焊 It is considered as the final welding trajectory, such as Figure 5 shown.
[0108] S3, autonomous welding;
[0109] The final welding trajectory F 焊 The arc starting point position and arc extinguishing point position are transmitted to the robot system to realize autonomous welding of short flat welds by the robot.
[0110] It can be seen from the above embodiments that the welding method provided by the present invention can realize simple and efficient identification and positioning of the arc starting point, arc extinction point and fitting welding trajectory of a planar short weld, and is extremely suitable for welding of planar short welds in the welding field.
[0111] In addition to the above method, the present invention also proposes a planar short weld welding device, see Figure 1 As shown, it includes a robot 3, a camera 4, a welding platform 6 and a workpiece 7 to be welded; the camera 4 is fixed on the welding gun 5 and is connected to the welding gun 5 as a whole; the welding gun 5 is at the end of the robot 3; the workpiece 7 to be welded is placed on the welding platform 6 at will; the weld 8 on the workpiece 7 to be welded can be a flat short butt weld with a groove, a flat short butt weld without a groove, a flat short lap weld, a flat short fillet weld, etc.; the robot 3 takes a picture of the workpiece 7 to be welded on the welding platform 6 through a first photographing posture and a second photographing posture that are set at will, so as to locate the arc starting point, locate the arc extinction point, and identify and fit the welding trajectory.
[0112] It should be understood that specific embodiments of the present disclosure are described with reference to the accompanying drawings; however, they are presented for illustrative purposes only, and the present disclosure is not limited thereto. Figure 1 The welded parts 7 shown are for illustration only; in practical applications, such as shipbuilding applications, the structure of the welding object may be quite complex; however, based on similar principles and operations, welds of complex structures can also be identified. In addition, the welding object is illustrated as a combination of rectangular parallelepipeds; however, the present disclosure is not limited thereto, and the welding object may include various combinations of various objects, such as cylinders, cones, spheres, hemispheres, or any other shapes or combinations thereof, and therefore those skilled in the art may also identify their welds from the teachings provided herein.
[0113] Those skilled in the art will also appreciate that the solutions provided herein may be implemented in hardware, software (including firmware, resident software, microcode, etc.), or in the form of a combination of hardware and software. That is, the object marking and intersection line recognition, edge determination and edge elimination, and weld editing herein may be implemented by electronic components or devices, software stored in a storage device, or a combination of electronic devices and software (e.g., by a microprocessor, a digital signal processor, a simple chip machine, and appropriate programs, etc.).
[0114] Above, embodiments of the present disclosure have been described in detail by embodiments with reference to the accompanying drawings. It should be understood that, although this specification contains many specific implementation details, these details should not be interpreted as limitations on any invention or the scope that may be claimed, but as a description of the features of a specific embodiment that can be dedicated to a specific invention. In this specification, certain features described in the context of a separate embodiment may also be implemented in combination in a single embodiment. On the contrary, the various features described in the context of a single embodiment may also be implemented in multiple embodiments individually or in any appropriate sub-combination. Moreover, although the features may be described above as acting in certain combinations or even initially required to be so, one or more features from the claimed combination may be deleted from the combination in some cases, and the claimed combination may be directed to a variant of a sub-combination or a sub-combination.
[0115] When read in conjunction with the accompanying drawings, in view of the foregoing description, various modifications to the foregoing exemplary embodiments of the present disclosure may be apparent to those skilled in the relevant art. Any and all modifications will still fall within the scope of the non-limiting and exemplary embodiments of the present disclosure. In addition, other embodiments of the present disclosure provided herein will occur to those skilled in the art to which these embodiments of the present disclosure pertain having the benefit of the teachings given in the foregoing description and the associated drawings.
Claims
1. A method for identifying short planar welds, characterized in that: The steps include: Step 1: Use a single camera installed on the robot to take global photos of the workpiece in two random postures, substitute the camera coordinates of a spatial point in the first shooting posture and the camera coordinates of the point in the second shooting posture into the system calibration equation, and obtain the three-dimensional coordinates of the point in the robot base coordinate system; The system calibration equation is as follows: Where: (X B ,Y B ,Z B ) is a space point in the robot base coordinate system O under the first shooting posture and the second shooting posture B X B Y B Z B The coordinates below; The tool coordinate system O in the first shooting posture H1 X H1 Y H1 Z H1 To the robot base coordinate system O B X B Y B Z B The transformation matrix of is the tool coordinate system O in the second camera posture H2 X H2 Y H2 Z H2 To the robot base coordinate system O B X B Y B Z B The transformation matrix (X C1 ,Y C1 ,Z C1 ) is a spatial point in the camera coordinate system O in the first shooting posture C1 X C1 Y C1 Z C1 The coordinates below; is the camera coordinate system O C1 X C1 Y C1 Z C1 To tool coordinate system O H1 X H1 Y H1 Z H1 The transformation matrix (X C2 ,Y C2 ,Z C2 ) is a spatial point in the camera coordinate system O in the second shooting posture C2 X C2 Y C2 Z C2 The coordinates below; is the camera coordinate system O C2 X C2 Y C2 Z C2 To tool coordinate system O H2 X H2 Y H2 Z H2 The transformation matrix of Step 2: Identify and fit the welding trajectory; Extract the arc starting point, arc extinguishing point, weld area and four corner point information of the workpiece; calculate the coordinates of the corner points in the camera coordinate system under the first shooting posture and the coordinates in the camera coordinate system under the second camera pose Substitute the stereo matching relationship to obtain the stereo matching relationship T between the two images R ; The stereo matching relationship is as follows: After the weld stripe image is extracted, the weld stripe image is morphologically processed by first corrosion and then expansion, so that the weld stripe point cloud on the image under the first camera posture after processing is The weld stripe point cloud on the image under the second camera pose is: The camera coordinate system O C1 X C1 Y C1 Z C1 Down The coordinates of each point are obtained through the stereo matching relationship T R Obtain the corresponding stereo matching point cloud The camera coordinate system O C2 X C2 Y C2 Z C2 Down The coordinates of each point are obtained through the stereo matching relationship T R Obtain the corresponding stereo matching point cloud Step 3, obtaining welding trajectory; Will Each point is in the camera coordinate system O C1 X C1 Y C1 Z C1 The coordinates below and Each point is in the camera coordinate system O C2 X C2 Y C2 Z C2 Substitute the coordinates under into the system calibration equation to obtain the welding trajectory F1; Each point is in the camera coordinate system O C2 X C2 Y C2 Z C2 The coordinates below and Each point is in the camera coordinate system O C1 X C1 Y C1 Z C1 Substitute the coordinates of the welding trajectory F1 into the system calibration equation to obtain the welding trajectory F2; obtain the center curve F1 of the welding trajectory F2. 中 , and the center curve F 中 Perform B-spline curve fitting; the trajectory curve F after B-spline curve fitting 焊 Determined as the final weld trajectory.
2. The method for identifying a short planar weld according to claim 1, characterized in that: The process of solving the system calibration equation is as follows: Rewrite the step system calibration equation as Ax = b; sample the coefficient matrix A of Ax = b and construct 6 standard linear equations A i x=b i (i=1,2,3,4,5,6); Solve each linear equation system A i x=b i The standard solution x of (i=1,2,3,4,5,6) i (i=1,2,3,4,5,6); calculate Chebyshev residual r i (x) = ‖Ax i -b‖ ∞ ; r i The solution corresponding to the minimum absolute value of (x) is identified as the solution to the system calibration equation.
3. The method for identifying a short planar weld according to claim 1, characterized in that: The extraction process of the weld stripe image is as follows: The brightness and contrast of the weld area are enhanced. The brightness and contrast enhancement functions are: g(u,v)=α·f(u,v)+β Where: α is the gain, α>0; β is the pixel deviation parameter; f(u,v) is the pixel value of the input image; g(u,v) is the pixel value of the output image; The weld stripes are detected as follows: s(u,v)=|Δ x f|+|D y f| Where: s(u,v) is the gradient of the pixel; Δ x f is the horizontal edge pixel gradient; Δ y f is the vertical edge pixel gradient.
4. The method for identifying a short planar weld according to claim 1, characterized in that: The establishment process of the system calibration equation is as follows: Convert the camera coordinate system to the tool coordinate system; Where: (X H1 ,Y H1 ,Z H1 ) is the tool coordinate system O of the point in the first shooting posture H1 X H1 Y H1 Z H1 The coordinates below; Where: (X H2 ,Y H2 ,Z H2 ) is the tool coordinate system O of the point in the second shooting posture H2 X H2 Y H2 Z H2 The coordinates below; Convert the tool coordinate system to the robot base coordinate system; The system calibration equation is obtained based on the above two conversions.
5. A planar short weld welding device, characterized in that: It includes a robot, a welding gun fixed on the robot, a camera fixed on the welding gun, and a workpiece to be welded placed on a welding platform; The welding process of the flat short weld welding device is as follows: To ensure that the camera can capture the entirety of the workpiece in each photographing posture, the robot arbitrarily sets the first photographing posture of the robot to take a photograph of the workpiece to be welded, and then arbitrarily sets the second photographing posture of the robot to take a photograph of the workpiece to be welded, so as to locate the arc starting point and the arc extinction point, identify and fit the welding trajectory; then the final welding trajectory is obtained through the planar short weld recognition method described in claim 1, and finally the final welding trajectory and the arc starting point position and the arc extinction point position are transmitted to the robot system, and the robot drives the welding gun to perform welding.
6. A planar short weld welding method, characterized in that: Firstly, the final welding trajectory is obtained by the planar short weld recognition method described in claim 1, and then the final welding trajectory and the arc starting point position and arc extinction point position are transmitted to the robot system, and the robot drives the welding gun to perform welding.
Citation Information
Patent Citations
CCD-based method and system for automatic identification and track planning of pipeline space weld seams
CN104400279A
Welding seam tracking signal processing method for double-pulse MIG welding
CN109570700A
Welding seam identification and robot welding seam tracking method based on 3D point cloud
CN114571153A
Welding seam extracting and fitting method based on 3D point cloud
CN116542914A
Method and device for monitoring and controlling the processing path of a laser joining process
EP2886239A1
