| Abstract Scope |
Additive manufacturing (AM) needs to address many challenges due to its multi-physical processes in various materials systems before replacing traditional manufacturing. Specifically, the primary aim of this investigation is to study the microstructural changes (texture, grain size, etc.) that affect material properties, such as elastic modulus and Poisson's ratio, and then to search for the optimized processing parameters. The influence of microstructural evolution on material properties is measured. Despite the process-structure-property relationship, analytical prediction models have been built, there’s still no established simulation approach for searching for optimized processing parameters. In this work, the inverse method is utilized to analytically find the optimized processing parameters with a general machine learning (ML) model. The time-consuming computational cost has been enhanced further. Several paradigms are constructed to optimize manufacturing processes, utilizing combined analytical and data/ML or semi-analytical frameworks. This study bridges the gap between optimized processing parameters and desired properties in AM. |