Efficient Optimization of Magnetic Properties of Fe–4.5Si Alloy in Laser Powder Bed Fusion (LPBF)

Abstract Existing studies have successfully identified optimal process parameters to enhance relative density and mechanical properties. However, these optimizations often incur high experimental costs due to the need for repetitive experiments. This research introduces an efficient optimization framework using two design of experiment (DoE) methods and machine learning algorithms, aimed at optimizing the magnetic properties of Fe–4.5Si material. The framework consists of three steps: (1) identification of the process parameter region that ensures high relative density using cubic specimens, (2) development of surrogate models to predict magnetic properties, such as maximum relative permeability and core loss, using toroidal specimens, and (3) multi-objective optimization using the surrogate models and a multi-objective genetic algorithm (MOGA) to enhance magnetic properties. The results demonstrate that this method can efficiently optimize process parameters with a limited number of experiments. Furthermore, the versatility of this framework allows its application to other materials in the early stages of research, even without prior knowledge of specific materials.