High-Throughput Exploration of Refractory High-Entropy Alloys for Strength and Plasticity

TL;DR

This study uses advanced deep learning models to rapidly predict and identify refractory high-entropy alloys with exceptional strength and plasticity, validated through experimental synthesis.

Contribution

It introduces a data-driven approach leveraging deep learning to efficiently explore vast composition spaces for RHEAs with balanced mechanical properties.

Findings

Identified multiple RHEA candidates with superior strength and plasticity.

Experimental validation confirmed the predicted materials outperform existing RHEAs.

Demonstrated the effectiveness of deep learning in multi-property materials discovery.

Abstract

Refractory high-entropy alloys (RHEAs) are compositionally complex materials which have been demonstrated to have the potential for exceptional strength at high operating temperatures. However, their composition space is vast, and other property requirements, such as acceptable plasticity at room-temperature, must be met. Here, we leverage recently published, state-of-the-art deep learning models to predict compressive yield strength at 1,000 {\deg}C and room-temperature plasticity of >100,000 RHEAs. Multiple candidate materials were identified which exhibited exceptional balance between strength and plasticity. Upon experimental synthesis, multiple candidates were proven to outperform any previously reported RHEAs for simultaneous strength and plasticity. Our work demonstrates the power of data-driven approaches for rapid materials design, and enables continued multi-property optimization and materials discovery.