| About this Abstract |
| Meeting |
2024 TMS Annual Meeting & Exhibition
|
| Symposium
|
Accelerated Discovery and Insertion of Next Generation Structural Materials
|
| Presentation Title |
Machine Learning and CALPHAD Assisted Design of High Performance Structural High Entropy Alloys |
| Author(s) |
Joshua Berry, Yunus Azakli, Matthew Turton, Olivier M.D.M. Messe, Iain Todd, Katerina A. Christofidou |
| On-Site Speaker (Planned) |
Joshua Berry |
| Abstract Scope |
High-Entropy Alloys (HEAs) present an opportunity for the design and development of structural alloys due to the potential to tailor their mechanical and structural properties. Machine learning is a powerful computational tool that can streamline exploration of the HEA compositional space, locating suitable alloy compositions to fulfil the required design constraints. Conventional applications of machine learning to HEA design problems focus on the search for single-phase solid solutions. In contrast, here we utilise a machine learning approach, assisted by CALPHAD, to design for FCC based multiphase HEAs, with subsequent in-situ carbide reinforcement to suppress formation of embrittling intermetallic phases and increase alloy hardness. A second use case of BCC solid solution alloys for fusion applications will also be discussed. Experimental analysis of the microstructural and mechanical properties of the downselected alloys will be presented.
This work was supported by Oerlikon AM Europe GmbH, EPSRC UK [EP/S022635/1] and SFI [18/EPSRC-CDT/3584]. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
High-Entropy Alloys, Machine Learning, |