About this Abstract |
| Meeting |
TMS Specialty Congress 2026
|
| Symposium
|
4th World Congress on High Entropy Alloys (HEA 2026)
|
| Presentation Title |
Machine Learning-Driven Discovery of Oxidation-Resistant, High-Strength Refractory High Entropy Alloys |
| Author(s) |
Yunhang Tao, Jiyun Kang |
| On-Site Speaker (Planned) |
Yunhang Tao |
| Abstract Scope |
Refractory high-entropy alloys (RHEAs) exhibit significant potential for high-temperature structural applications, yet their use is limited by the difficulty of achieving both high oxidation resistance and mechanical strength. In this study, we develop a machine-learning (ML) framework that integrates experimental oxidation kinetics with high-temperature mechanical data to accelerate RHEA design. Oxidation behavior is quantified through mass gain measurements and detailed characterization of surface and cross-sectional oxide morphologies. Descriptors extracted from these oxidation data are combined with alloy composition and yield strength data to train ML models capable of predicting oxidation resistance and strength simultaneously. The resulting framework enhances quantitative understanding of oxidation behavior in RHEAs and provides data-driven pathways for designing high-strength, oxidation-resistant alloys for long-term high-temperature service. |
| Proceedings Inclusion? |
Undecided |