Abstract

A physics-based model is used to predict melt pool properties in the processing of a large database of nickel-based superalloys for different process parameters via metal additive manufacturing. The input space is a high-dimensional space composed of a common 19-dimensional composition space for each alloy and the process parameters (laser power and scan velocity). Gaussian Process-based regression frameworks are developed by training surrogates on data generated by a validated analytical model. These surrogates are thereafter used to predict and define relationships between the composition, resulting thermophysical properties, process parameters, and the subsequent melt pool property. The probabilistic predictions are augmented by uncertainty quantification and sensitivity analysis to further substantiate the findings.