Laser visual sensing for seam tracking in robotic arc welding of titanium alloys

Sensor errors arose from detecting the weld-seam profile of titanium alloys with laser-based vision sensors because the surface of such a material is highly reflective to a laser light. In this study, the correct weld-seam profile was established from the distorted raw data by signal processing. Furthermore, a fully automatic seam-tracking system was developed. This system featured training and saving of the template, autofinding of the starting welding point, auto–calibration, detection of seam position and groove dimensions and tracking control. The system was capable of tracking V-groove, fillet, lap and butt joints of titanium alloys with high accuracy of less than 0.4 mm.