| About this Abstract |
| Meeting |
2023 TMS Annual Meeting & Exhibition
|
| Symposium
|
Accelerated Discovery and Insertion of Next Generation Structural Materials
|
| Presentation Title |
Computational Design of High Entropy Alloy Hardmetals |
| Author(s) |
Joshua Berry, Robert Snell, Magnus Anderson, 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 new wear resistant hardmetals, to replace the conventional WC-Co cemented carbides, used in demanding metal forming applications. However, the vast compositional space occupied by HEAs, results in unguided experimental searches being unfeasible. Here, a random forest machine learning architecture, in conjunction with the CALPHAD method, is trained from experimental HEA databases, to perform high-throughput phase formation and hardness predictions. Nine of the hardest predicted FCC solid solution forming HEA compositions from the machine learning model were selected and fabricated. Mechanical and thermal assessments of these selected alloys will demonstrate their potential suitability for WC-Co replacement, while simultaneously enabling comparison and verification of the machine learning methodology and providing further data for future model development.
This work was supported by Oerlikon AM Europe GmbH, Engineering and Physical Sciences Research Council UK [EP/S022635/1] and Science Foundation Ireland [18/EPSRC-CDT/3584]. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
High-Entropy Alloys, Machine Learning, |