Multi-objective process parameters optimization of hot-wire laser welding using ensemble of metamodels and NSGA-II

Hot-wire laser welding (HLW) can reduce the dispersion of laser energy and improve deposition efficiency by preheating filler wire during laser welding process. In order to obtain sound welding results, it is crucial to select appropriate process parameters. In this study, an optimization methodology based on ensemble metamodels (EM) which take the advantages of the prediction ability of stand-alone metamodels (Kriging, RBF and SVR), and Non-dominated sorting genetic algorithm (NSGA-II) are presented to obtain optimum process parameters during stainless steel 316L hot-wire laser welding. Firstly, EMs are developed through minimizing the generalized mean square Leave-one-out (LOO) errors to find the optimum weight factors of the used stand-alone Kriging, RBF and SVR metamodels. And then the EMs are applied to establish the relationships between process parameters (i,e., laser power (LP), welding speed (WS) and hot-wire current (I)) and welding results (i,e., welding depth-to-width ratio (DW), welding reinforcement (BR) and tensile strength (TS)). During optimization process, NSGA-II is employed to search for multi-objective Pareto optimal solutions based on EMs. In addition, the main effects of multiple process parameters on welding results are analyzed. The verification tests indicate that the obtained optimal process parameters are effective and reliable for producing expected welding results (maximized DW, maximized TS and desired BR value). In general, the proposed optimization method can provide a reliable guidance for HLW in engineering practice.