| Abstract Scope |
Refractory high-entropy alloys (RHEAs) are considered as the next-generation of high-temperature materials with great application prospects due to their excellent mechanic properties. This work focuses on phase stability and machine learning (ML) models for mechanical properties including yield strength at elevated temperature and proposed a systematic composition design rules to accelerate RHEAs design. Specifically, nine refractory metals (Ti, V, Cr, Zr, Nb, Mo, Hf, Ta and W), 466 multicomponent (ternary to novenary) systems and 43425 compositions with the incremental size of 10% in concentration are under consideration in this work. The predicted mechanical properties from ML models are then decoded to the latent space for composition design. With a screener for high yield strength at elevated temperature, 7 new equiatomic alloys are identified with yield strength ranging from 551 to 639 MPa at 1800 K. |