About this Abstract |
| Meeting |
2026 TMS Annual Meeting & Exhibition
|
| Symposium
|
Environmental Degradation of Multiple Principal Component Materials
|
| Presentation Title |
Oxidation-Modeling for Alloy Performance Using Machine Learning Algorithms |
| Author(s) |
Dennis Boakye, Chuang Deng |
| On-Site Speaker (Planned) |
Dennis Boakye |
| Abstract Scope |
Accelerating the design of high-entropy alloys (HEA) with superior oxidation resistance demands advanced data-driven approaches to navigate their
complex compositional space. Traditional experimental methods are limited
in their ability to efficiently explore the vast possibilities of element combinations, environmental conditions, and processing variables. This study
introduces OXMAP, a machine learning model trained on experimental data
points that span various compositions, temperatures, environments, and oxidation durations. By integrating physics-based descriptors, OXMAP enables
the rapid identification of optimal HEA compositions with superior oxidation
resistance, transforming alloy design through accelerated discovery, reduced
costs, and enhanced performance in extreme environments. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Computational Materials Science & Engineering, High-Entropy Alloys, Machine Learning |