LAUSR

Abstract Traditional teaching programing for the welding of large-scale complex structures is extremely difficult, with low efficiency and poor consistency, and it is very difficult to obtain the random change of joint geometry and achieve excellent welding quality along the entire welding path. In this paper, an integrated method of automatic generation of welding paths and adaptive filling of lap welding based on laser-structured light scanning is proposed. First, the point-cloud data of the welding joint on the entire welding path were acquired by laser scanning a workpiece, and the welding-seam model of the lap joint was accurately reconstructed using a cubic smoothing spline algorithm. The key feature points of the welding path were then extracted by Douglas-Peucker algorithm and the corresponding postures calculated and optimized. Furthermore, a neural network model that correlated the optimized process parameters with the gaps in the lap joints was established. During the welding process, the welding parameters were adaptively adjusted according to the variation of the obtained joint geometry based on the model. The results of the experiments showed that the proposed method has excellent adaptability to complex-curve welding seams with gaps randomly distributed between 0 and 2 mm, achieving satisfactory results in both path accuracy and weld appearance.