Binocular vision system for both weld pool and root gap in robot welding process

Abstract

Purpose The purpose of this paper is to develop a kind of low cost measuring system based on binocular vision sensor to detect both the weld pool geometry and root gap simultaneously for robot welding process. Design/methodology/approach Two normal charge coupled device cameras are used for capturing clear images from two directions; one of them is used to measure the root gap and another one is used to measure the geometric parameters of the weld pool. Efforts are made from both hardware and software aspects to decrease the strong interferences in pulsed gas tungsten arc welding process, so that clear and steady images can be obtained. The grey level distribution characteristics of root gap edge and weld pool edge in images are analyzed and utilized for developing the image processing algorithms. Findings A solid foundation for seam tracking and penetration control of robot welding process can be established based on the binocular vision sensor. Practical implications The results show that the algorithms can extract the root gap edges and the contour of weld pool effectively, and then some geometric parameters can be calculated from the results. Originality/value The binocular vision system provides a new method for sensing of robot welding process.