Three‐dimensional weld seam tracking for robotic welding by composite sensing technology

Purpose – This paper aims to develop a method to achieve automatic robotic welding and seam tracking so that three‐dimensional weld seam could be tracked without teaching and good welding formation could be accomplished. Design/methodology/approach – Adaptive image processing method was used for various types of weld seam. Also the relationship between welding height and arc signal was calibrated. Through the decomposition and synthesis, three‐dimensional space type weld seam could be extracted and tracked well. The workpiece without teaching was finally tracked precisely and in a timely way with use of the fuzzy controller. Findings – Composite sensing technology including arc and visual sensing had obvious advantages. Image processing method could be used for tracking plane weld seam efficiently while arc sensing could characterize welding height. Through the coupled controlling algorithm, arc sensing and visual sensing could be fused effectively. Research limitations/implications – How to couple information more accurately and quickly was still one of the most important problems in composite sensing technology. Practical implications – Composite sensing technology could reduce costs to achieve weld seam instead such expensive device as laser sensor. The simulating parts of scalloped segment of bottom board for rockets were tracked in the project. Once more adaptive algorithms were developed, more complicated practical workpieces could be dealt with in robotic welding which promotes the application of industry robots. Originality/value – A useful method for three‐dimensional space type weld seam tracking without teaching was developed. The whole procedure of adaptive image processing method was simple but efficient and robust. The coupled controlling strategy addressed could accomplish seam tracking by composite sensing technology.