Sensitivity Analysis of Computer Vision System for Visual Control of Butt Joints Weld Defects

Abstract

Computer vision systems are successfully used for surface defect inspection. The use of computer vision systems to inspect surface defects in welding is an urgent task, as it allows inspection of defects in the weld and heat-affected zone after the welding cycle. The iRVision 3DL computer vision system can be used for this purpose. The angles at which the sensitivity of the robotic welding inspection system is at its best must be determined to evaluate the quality of the defect detection. When used in combination with industrial robots, vision systems have so far fulfilled only a minimal range of tasks in the process. They are reduced to the tasks of recognizing the object position relative to a given coordinate system of objects or coordinate system with the origin within the object itself. In this work, we investigate the possibility of using the iRVision 3DL vision system to solve the problem of analyzing the quality of welds obtained after welding for the presence of surface defects. The capability of the system to detect surface pores of butt welds on a specially prepared specimen is investigated. The possibility of robotic visual inspection using the iRVision 3DL computer vision system and surface pore detection is established. The most preferred angles of the FANUC robot position with the iRVision 3DL computer vision system mounted on it, at which the pores have pronounced bursts on the laser line, be preferable.