High-throughput experiments and machine learning strategies for efficient exploration of additively manufactured Inconel 625

Metal additive manufacturing has been a recent area of growth resulting in the need to optimize additive manufacturing processes and materials so they may be qualified for industrial applications. The additive manufacturing development pipeline currently relies on Edisonian trial-and-error methodologies that come at a high expense and delay potential game-changing advancements. High-throughput testing in conjunction with machine learning can decrease the time and cost associated with obtaining experimental data and create methods to derive the greatest value from that experimental data. This study demonstrates how Small Punch Test, a highthroughput mechanical testing method, and a machine learning framework suited for small datasets, namely Gaussian Process Regression, can be applied to a set of seven additive manufactured Inconel 625 samples to extract Process-Structure-Property linkages. Models are built with and without the inclusion of microstructure information, namely delta phase precipitates, so we may assess the value of this information that accounts for a significant portion of the data collection expenses.