Solidification phenomenon has been an integral part of the manufacturing processes of metals, where the quantification ofstochastic variations and manufacturing uncertainties is critically important. Accurate molecular dynamics (MD) simulations ofmetal solidification and the resulting properties require excessive computational expenses for probabilistic stochastic analyseswhere thousands of random realizations are necessary. The adoption of inadequate model sizes and time scales in MD simulationsleads to inaccuracies in each random realization, causing a large cumulative statistical error in the probabilistic results obtainedthrough Monte Carlo (MC) simulations. In this work, we present a machine learning (ML) approach, as a data-driven surrogate to MDsimulations, which only needs a few MD simulations. This efficient yet high-fidelity ML approach enables MC simulations for full-scale probabilistic characterization of solidified metal properties considering stochasticity in influencing factors like temperatureand strain rate. Unlike conventional ML models, the proposed hybrid polynomial correlated function expansion here, being aBayesian ML approach, is data efficient. Further, it can account for the effect of uncertainty in training data by exploiting mean andstandard deviation of the MD simulations, which in principle addresses the issue of repeatability in stochastic simulations with lowvariance. Stochastic numerical results for solidified aluminum are presented here based on complete probabilistic uncertaintyquantification of mechanical properties like Young’s modulus, yield strength and ultimate strength, illustrating that the proposederror-inclusive data-driven framework can reasonably predict the properties with a significant level of computational efficiency.
A. Mahata, T. Mukhopadhyay, S. Chakraborty, M. Asle Zaeem. Atomistic simulation assisted error-inclusive Bayesian machine learning for probabilistically unraveling the mechanical properties of solidified metals. npj Comput Mater 10, 22 (2024).
https://www.nature.com/articles/s41524-024-01200-1
