REAL-TIME SENSING OF SAG GEOMETRY DURING GTA WELDING

Seam tracking and weld penetration control are two fundamental issues in automated welding. Although the seam tracking technique has matured , the latter still remains a unique unsolved problem. It was found tha t the full penetration status during GTA welding can Be determined wit h sufficient accuracy using the sag depression. To achieve a new full penetration sensing technique, a structured-light 3D vision system is developed to extract the sag geometry behind the pool. The laser strip e, which is the intersection of the structured-light and weldment, is thinned and then used to acquire the sag geometry. To reduce possible control delay, a small distance is selected between the pool rear and laser stripe. An adaptive dynamic search for rapid thinning of the str ipe and the maximum principle of slope difference for unbiased recogni tion of sag border were proposed to develop art effective real-time im age processing algorithm for sag geometry acquisition Experiments have shown that the proposed sensor and image algorithm can provide reliab le feedback information of sag geometry for the full penetration contr ol system.