A general method for automatic welding seam contour extraction
A technology of contour extraction and general method, applied to welding equipment, welding accessories, welding rod characteristics, etc., can solve problems such as cost and unfavorable promotion, and achieve the effect of facilitating integration and reducing software development costs
Active Publication Date: 2021-09-03
华东交通大学理工学院
View PDF9 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
As we all know, developing an effective algorithm to achieve online extraction of a certain weld profile requires considerable cost, and is not conducive to popularization
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
[0111] 1. The welding torch is in the welding posture and in the initial welding position, the laser vision sensing system is in working state, and the image of the weld without arcing before welding is collected as a reference image, such as figure 2 As shown in the leftmost image;
[0112] 2. Perform the following steps on the reference image figure 2 The processing process shown in the figure, namely, the adaptive local threshold segmentation processing, the strip weld contour center acquisition processing, and then the region of interest, feature points and filter angles are obtained respectively. (m=1,2,…);
[0113] 3. Use the obtained filter angle (m=1,2,…) Perform Gabor filtering, process the weld image collected during the welding process, and combine the region of interest and the region divided by feature points to determine the final multi-directional feature map, such as image 3 shown;
[0114] 4. Take the region of interest of the reference image and the ...
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 discloses a general method for automatic welding seam profile extraction, which relates to the field of welding technology, comprising the following steps: collecting the weld seam image without arcing before welding as a reference image, and using the reference image to automatically determine the filter angle and the Gabor filter Region of interest; collect the welding image, perform adaptive Gabor filtering on the welding image to obtain the multi-directional feature map, and obtain the region of interest part of the reference image and the direction feature map at the same time; use the scale invariant feature transformation algorithm to process the above two regions of interest part, obtain the matching position of the similar points of the two images; perform adaptive local threshold segmentation on the region of interest of the multi-directional feature map to obtain a binary image, and extract the weld outline according to the obtained coordinates of the matching position and the clustering results . The invention is effective for typical butt joints and fillet joints, and can be extended to the extraction of other joint contour welds, which is beneficial to the integration of welding information collection and processing systems.
Description
technical field [0001] The invention relates to the field of welding technology, in particular to a general method for extracting weld contours of typical butt joints of thick plates and GMAW automatic welding of corner joints under laser vision sensing. Background technique [0002] At present, in the GMAW automatic welding of robot thick plates, the laser vision sensing system is mostly used to detect the feature information of the weld seam contour to guide the welding torch to complete the seam tracking, so the online effective extraction of the weld seam contour is the prerequisite for automatic welding. At present, for the GMAW automatic welding of thick plates with different joints, many studies have proposed different weld profile extraction methods. These methods are all proposed for the weld profile in a specific application background, and are not widely used. As we all know, developing an effective algorithm to realize the online extraction of a certain weld pro...
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 Patents(China)
IPC IPC(8): B23K9/00B23K9/28B23K9/32
CPCB23K9/00B23K9/287B23K9/32
Inventor 余卓骅胡艳梅何银水龚平华蒋吴曦张国涛吴谣黄怡彬金书强涂亮
Owner 华东交通大学理工学院