About this Abstract |
| Meeting |
2026 TMS Annual Meeting & Exhibition
|
| Symposium
|
Accelerated Discovery and Insertion of Next Generation Structural Materials
|
| Presentation Title |
Machine-Learning Prediction of Yield Strength for W-Ta-Nb Alloy from Room Temperature to 2000°C |
| Author(s) |
Zhiyang An, Bo Ni, Benjamin Glaser, Amaranth Karra, Bryan Webler, S. Mohadeseh Taheri-Mousavi |
| On-Site Speaker (Planned) |
Zhiyang An |
| Abstract Scope |
W-Ta-Nb alloys are promising candidates for extreme temperature applications given their refractory nature. However, getting reliable yield strength predictions for these alloys from room temperature up to 2000 °C remains difficult yet crucial for developing next-generation engines and reactors. In this work, we gather not only experimental strength data from literature but also modeling predictions using atomistic simulations and theoretical models. The data are fed into an integrated computational materials engineering workflow that links alloy composition and temperature to yield strength. We test three models: a phenomenological model that adopts the Walbrühl solid-solution rule, a mechanics-based model that considers dislocation-based mechanisms, and a machine-learning model trained on both experimental and simulation data. We will compare the three approaches, reveal the limitations of each model, and finally will combine to demonstrate a more reliable model that can predict strength over the whole 25–2000 °C range. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
High-Entropy Alloys, Mechanical Properties, Additive Manufacturing |