Weld joint visual identification method of welding equipment
A technology of visual recognition and welding equipment, applied in the field of visual recognition, can solve problems such as difficult recognition, large changes in weld seam, deformation, etc.
Active Publication Date: 2021-10-22
宁波博视达焊接机器人有限公司
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, for curved surface welds, due to material problems of the material itself and processing accuracy requirements, local deformation is prone to occur, resulting in large changes in the weld seam
On the other hand, the environment of the curved surface will also affect the visual recognition
Therefore, it is difficult to obtain the correct weld position only through two-dimensional image recognition
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0041] Such as Figure 1-16 As shown, the welding seam visual recognition method of welding equipment described in this embodiment uses a line laser emitter, a parallel light source and a camera, and is characterized in that the line laser emitter, parallel light source and camera are first fixed, and the workpiece is mounted on the robot , use the robot to control the movement of the workpiece in space, the robot moves the workpiece to the target position in the space, and then both the parallel light source and the line laser emitter irradiate the welding position on the workpiece, the camera acquires the image of the workpiece welding position, and then proceed as follows Spot identification:
[0042] a) The camera acquires picture A, and performs two Gaussian pyramids on picture A. After picture A is reduced by 4 times, it is filtered by Gable to get picture B;
[0043] b) First perform grayscale normalization on image B line by line, and then perform full Figure II valu...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention designs welding joint visual identification method of welding equipment. The position of a welding spot is obtained through calculation on a two-dimensional picture in a calculation processing mode, and the position of the welding spot is not obtained by directly identifying the intersection point of the welding joint and a laser line but is obtained through speculation of the relation among a welding joint line, the laser line and the surrounding environment. By means of the method, adverse effects caused by the surrounding environment are avoided, meanwhile, identification errors caused by shielding of spot welding traces on materials on the welding joint are reduced as much as possible, and finally the complete and smooth curve welding joint is obtained. It needs to be further explained that due to the fact that the mode that an identification device is fixed and a workpiece moves is adopted, the third parameter of the transverse coordinate position of the welding spot on the two-dimensional image can be further determined through a trigonometric function, and therefore conversion from the two-dimensional coordinate to the three-dimensional coordinate is achieved.
Description
technical field [0001] The invention relates to a visual recognition method, in particular to a welding seam visual recognition method of welding equipment. Background technique [0002] In the prior art, machine vision recognizes the position of the weld by directly identifying the intersection of the laser line and the weld. This method is relatively effective on plane welds, because the welds on the plane are relatively straight and easy to predict. At the same time, the reflection of the plane is better, and the environment is relatively pure. However, for curved surface welds, due to the material problems of the material itself and the requirements for processing accuracy, local deformation is prone to occur, resulting in large changes in the weld seam. On the other hand, the environment of the curved surface will also affect the visual recognition. Therefore, it is difficult to obtain the correct weld seam position only through two-dimensional image recognition. Co...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): B23K37/00B23K9/127
CPCB23K37/00B23K9/127
Inventor 王一刚瞿波程荣源徐亚男吕隆斐陈亮刘思彤
Owner 宁波博视达焊接机器人有限公司