About this Abstract |
| Meeting |
2026 TMS Annual Meeting & Exhibition
|
| Symposium
|
Advances in Multi-Principal Element Alloys V: Mechanical Behavior
|
| Presentation Title |
Quantum Machine Learning Design of Ductile Compositionally Complex Alloys |
| Author(s) |
Joseph Poon, Diego Ibarra Hoyos, Peter Connors, Jie Qi, Xuesong Fan, Nathan Grain, Peter Liaw, John Scully |
| On-Site Speaker (Planned) |
Joseph Poon |
| Abstract Scope |
While artificial intelligence/machine leaning (AI/ML) methods can classify Compositionally Complex Alloys (CCAs) with notable accuracy, state-of-the-art ML tools remain limited in predicting ductility, typically measured by fracture strain. This shortcoming hinders effective screening of the CCA space for multi-objective targets, particularly the combined optimization of cost and corrosion resistance. We present an adaptive design strategy that integrates computation and experimentation to explore which and how alloy parameters influence ductility. This effort stands to benefit significantly from quantum annealing machine learning (QAML), which excels in finding interpretable and optimal solutions and is well-suited for advancing CCA design. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Computational Materials Science & Engineering, High-Entropy Alloys, Mechanical Properties |