Distilling physical origins of hardness in multi-principal element alloys directly from ensemble neural network models

• Published in: npj computational materials Vol. 8; no. 1; pp. 1 - 11
• Main Authors: Beniwal, D., Singh, P., Gupta, S., Kramer, M. J., Johnson, D. D., Ray, P. K.
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 18.07.2022; Nature Publishing Group; Nature Portfolio
• Subjects: 639/301/1034; 639/301/119; Alloying elements; Alloys; Characterization and Evaluation of Materials; Chemistry and Materials Science; Clustering; Computational Intelligence; Datasets; Decision making; Density functional theory; Distillation; Hardness; Machine learning; Materials Science; Mathematical and Computational Engineering; Mathematical and Computational Physics; Mathematical Modeling and Industrial Mathematics; Mechanical properties; Neural networks; Phase stability; Physical properties; Surface hardness; Theoretical
• ISSN: 2057-3960; 2057-3960
• DOI: 10.1038/s41524-022-00842-3

Despite a plethora of data being generated on the mechanical behavior of multi-principal element alloys, a systematic assessment remains inaccessible via Edisonian approaches. We approach this challenge by considering the specific case of alloy hardness, and present a machine-learning framework that captures the essential physical features contributing to hardness and allows high-throughput exploration of multi-dimensional compositional space. The model, tested on diverse datasets, was used to explore and successfully predict hardness in Al x Ti y (CrFeNi) 1- x - y , Hf x Co y (CrFeNi) 1- x - y and Al x (TiZrHf) 1- x systems supported by data from density-functional theory predicted phase stability and ordering behavior. The experimental validation of hardness was done on TiZrHfAl x . The selected systems pose diverse challenges due to the presence of ordering and clustering pairs, as well as vacancy-stabilized novel structures. We also present a detailed model analysis that integrates local partial-dependencies with a compositional-stimulus and model-response study to derive material-specific insights from the decision-making process.