Integrated weld quality control system based on laser strobe vision

Abstract

Arc welding is a complex phenomenon involving intensive interactions among heat, arc and arc force. To minimize the undesirable interference in weld pool imaging, a pulsed laser beam projects a strong illumination onto the weld pool area. The ultra-high shutter speed vision system is synchronized to capture the weld pool image in the given short period. Through image processing, the geometrical information of the weld pool is obtained. It is input to a neurofuzzy logic controller so that the welding parameters like welding current and welding speed can be changed in real time to achieve desired weld dimension in response to the changes in welding conditions. © 2007 Springer-Verlag Berlin Heidelberg.