About this Abstract |
| Meeting |
2026 TMS Annual Meeting & Exhibition
|
| Symposium
|
Advances in Multi-Principal Element Alloys V: Mechanical Behavior
|
| Presentation Title |
Machine Learning Prediction of High Order Slip Energetics and Their Effect on Strain Hardening in Refractory High-entropy Alloys |
| Author(s) |
Christopher Tandoc, Liang Qi, Yong-Jie Hu |
| On-Site Speaker (Planned) |
Yong-Jie Hu |
| Abstract Scope |
Refractory high-entropy alloys (RHEAs) are promising candidates for structural applications in extreme environments, but often exhibit limited ductility and strain hardening. These mechanical properties are strongly influenced by the competition and interactions between dislocation slip on the primary {110} planes and high-order slip planes such as {112} and {123}. In this work, we present a physics-informed machine learning framework, trained on density functional theory (DFT) calculations, to predict the generalized stacking fault energies (GSFEs) of the {112} and {123} planes across a representative 12-element compositional space of RHEAs. Leveraging the predicted GSFEs, we perform data mining to uncover how slip system energetics vary across this complex compositional landscape. We further explore the relationship between the mining results and experimentally observed mechanical behaviors, including toughness, strain hardening, and high-strain plasticity. This framework lays the groundwork for understanding the role of high order slip systems in determining the deformation behavior of RHEAs. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Machine Learning, High-Entropy Alloys, Mechanical Properties |