Optimization of laser powder bed fusion process parameter for the fabrication of AlSi12 using NSGA-II and Pareto search algorithm

Abstract

Additive manufacturing, notably laser powder bed fusion (LPBF), excels in producing complex geometries and is widely used in the automotive, aerospace, and naval industries. Laser powder bed fusion enables the creation of components with the required stiffness and strength at a lighter weight than traditional manufacturing methods. Aluminium alloys are particularly promising for laser powder bed fusion in the automotive and aerospace sectors. To enhance the effectiveness of laser powder bed fusion-produced components, optimized process parameters must be designed for specific materials. This study investigates the influence of processing parameters, scan speed, scan strategy, and hatch space, on the relative density, surface roughness, and microhardness of AlSi12 samples fabricated by laser powder bed fusion. A Taguchi L27 orthogonal array was used to systematically analyze the effects of these parameters. A regression model was developed and evaluated through analysis of variance using signal-to-noise (S/N) ratios to identify optimal parameter values. Results indicated that the scan pattern significantly affects relative density, while hatch space impacts surface roughness and microhardness. Optimal solutions were obtained through multi-objective optimization using the non-dominated sorting genetic algorithm (NSGA-II) and Pareto search algorithms. Experimental validation showed average errors of 0.483 % and 0.461 % for NSGA-II and Pareto search algorithms, respectively.