Visionbased pipeline girthwelding robot and image processing of weld seam

Purpose The purpose of this paper is to introduce structured light image processing technology into pipeline welding automation projects, and develop a visionbased pipeline girthwelding robot. The welding torch can accurately track the weld and complete the omniorientation welding automatically. Designmethodologyapproach Weld image processing adopts the base theory including Laplacian of Gaussian filter, neighbourhood mean filter, largest variance threshold segmentation and morphologic, etc. obtains good effect of weld recognition. Findings The paper uses a vision sensor to achieve the weld character's recognition and extraction, directly control the robot tracking weld to complete automation welding. Compared with the existing pipeline welding devices, it does not need the lay orbit or plot tracking mark, which can shorten the assistant time to improve the productivity. Practical implications The research findings can satisfy the need of wholedirectional automation welding for large diameter transportation pipe's circular abutting weld. It fits for the automation welding for the longdistance transportation pipe of petroleum, natural gas, and water. Originalityvalue Aiming at the character recognition and extract of Vtype weld, the method combining the neighbourhood mean filter algorithm with the largest variance threshold segmentation is proposed to obtain the quick weld image processing speed.