Data-driven multi-objective optimization of laser welding parameters of 6061-T6 aluminum alloy

In this paper, a data-driven multi-objective optimization approach using optimal Latin hypercube sampling (OLHS), Kriging (KRG) metamodel and the non-dominated sorting genetic algorithm II (NSGA-II) is presented for the laser welding process parameters on 6061-T6 aluminum alloy. The experiments are designed by OLHS and carried out to obtain the data results. The complex relationship between the process parameters and the bead profile geometry is established by KRG using the data results. The accuracy of the established KRG metamodel is validated using experiments. Then, NSGA-II is used to explore the design space and search the Pareto optimal solutions of process parameters. Besides, the validation experiments were carried out to obtain ideal LW bead profile, which shows that the approach can bring dependable guidance for LW experiments.