Machine-learning assisted additive manufacturing of a TiCN reinforced AlSi10Mg composite with tailorable mechanical properties

Abstract

A Gaussian process regression-based machine learning approach was used to establish a processing window optimized for high density additive manufacturing of a 2 vol% TiCN reinforced AlSi10Mg composite by laser powder bed fusion. The optimized window for TiCN reinforced AlSi10Mg was found to be smaller than for AlSi10Mg. Within the optimized window, it was found that the Si eutectic cell size can be increased by raising the laser power/scanning speed at the constant energy density of 50 J/mm3 to control the tensile properties of the fabricated composites.