Real‐time image capturing and processing of seam and pool during robotic welding process

Purpose – The purpose of this paper is to analyze the technology of capturing and processing weld images in real‐time, which is very important to the seam tracking and the weld quality control during the robotic gas tungsten arc welding (GTAW) process.Design/methodology/approach – By analyzing some main parameters on the effect of image capturing, a passive vision sensor for welding robot was designed in order to capture clear and steady welding images. Based on the analysis of the characteristic of the welding images, a new improved Canny algorithm was proposed to detect the edges of seam and pool, and extract the seam and pool characteristic parameters. Finally, the image processing precision was verified by the random welding experiments.Findings – It was found that the seam and pool images can be clearly acquired by using the passive vision system, and the welding image characteristic parameters were accurately extracted through processing. The experiment results show that the precision range of the i...