Data-driven modeling of process-structure-property relationships in metal additive manufacturing

Abstract

Metal additive manufacturing (AM) faces challenges in rapid selection and optimization of manufacturing parameters for desired part quality. As a more efficient alternative to experiments and high-fidelity physics-based models, data-driven modeling is effective in understanding process–structure–property relationships. This brief review explores data-driven modeling in metal AM, focusing on “process”, “structure”, and “property”, further identifying limitations in current applications and accordingly presenting future outlook on the possible advancements in this domain.