| About this Abstract |
| Meeting |
2024 TMS Annual Meeting & Exhibition
|
| Symposium
|
Advances in Magnetism and Magnetic Materials
|
| Presentation Title |
High Entropy Magnetic and Invar Alloys |
| Author(s) |
Dierk R. Raabe, Liuliu Han, Ziyuan Rao |
| On-Site Speaker (Planned) |
Dierk R. Raabe |
| Abstract Scope |
High-entropy alloys target solid solutions of multiple principal elements, capable of reaching composition and feature regimes that are often inaccessible for dilute materials (1). Discovering those with valuable properties, however, often relies on serendipity, as thermodynamic alloy design rules alone often fail in high-dimensional composition spaces (2,3). In this talk we present an active-learning strategy to accelerate the design of novel high-entropy Invar and magnetic alloys in a practically infinite compositional space, based on sparse data (2-4). Our approach works as a closed-loop, integrating machine learning with density-functional theory, thermodynamic calculations, and experiments.
1. George EP et al. 2019. Nature Rev. Mater. 4(8):515–34
2. Rao Z et al. 2022. Science (80). 85:78–85
3. Raabe D, Mianroodi JR, Neugebauer J. 2023. Nature Comput. Sci. 3(March):198–209
4. Han L et al. 2022. Nature. 608(7922):310–16 |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Magnetic Materials, Machine Learning, High-Entropy Alloys |