Prediction of laser butt joint welding parameters using back propagation and learning vector quantization networks

Laser welding parameters include not only the laser power, focused spot size, welding speed, focused position, etc., but also the welding gap and the alignment of the laser beam with the center of the welding gap, these latter two parameters being critical for a butt joint. These parameters are controllable in the actual operation of laser welding, but are interconnected and extremely non-linear, such problems limit the industrial applicability of the laser welding for butt joints. The neural network technique is a useful tool for predicting the operation parameters of a non-linear model. Back propagation (BP) and learning vector quantization (LVQ) networks are presented in this paper to predict the laser welding parameters for butt joints. The input parameters of the network include workpiece thickness and welding gap, whilst the output parameters include optimal focused position, acceptable welding parameters of laser power and welding speed, and welding quality, including weld width, undercut and distortion for the associated power and speed used. The results of this research show a comprehensive and usable prediction of the laser welding parameters for butt joints using BP and LVQ networks. As a result, the industrial applicability of laser welding for butt joints can be expanded widely.