Efficient machine-learning model for fast assessment of elastic properties of high-entropy alloys

TL;DR

This paper introduces an efficient analytical model combining descriptor-based methods and mean-field techniques to rapidly predict elastic properties of high-entropy alloys, aiding materials design.

Contribution

It develops an optimal elastic property prediction model using SIS and SO methods with atomic features, improving accuracy and computational efficiency over previous approaches.

Findings

High-accuracy elastic property predictions comparable to experimental data.

Identification of alloy concentration regions with promising ductility and strength.

Demonstration of electronegativity variance as a predictor for alloy mechanical behavior.

Abstract

We combined descriptor-based analytical models for stiffness-matrix and elastic-moduli with mean-field methods to accelerate assessment of technologically useful properties of high-entropy alloys, such as strength and ductility. Model training for elastic properties uses Sure-Independence Screening (SIS) and Sparsifying Operator (SO) method yielding an optimal analytical model, constructed with meaningful atomic features to predict target properties. Computationally inexpensive analytical descriptors were trained using a database of the elastic properties determined from density functional theory for binary and ternary subsets of Nb-Mo-Ta-W-V refractory alloys. The optimal Elastic-SISSO models, extracted from an exponentially large feature space, give an extremely accurate prediction of target properties, similar to or better than other models, with some verified from existing experiments. We also show that electronegativity variance and elastic-moduli can directly predict trends in ductility and yield strength of refractory HEAs, and reveals promising alloy concentration regions.