| About this Abstract |
| Meeting |
2023 TMS Annual Meeting & Exhibition
|
| Symposium
|
Materials Genome, CALPHAD, and a Career over the Span of 20, 50, and 60 Years: An FMD/SMD Symposium in Honor of Zi-Kui Liu
|
| Presentation Title |
M-24: Revealing the Materials Genome for Advanced High-entropy Materials |
| Author(s) |
Jiaqi Lu, William Yi Wang , Fengpei Zhang, Pingxiang Zhang, Jinshan Li |
| On-Site Speaker (Planned) |
Jiaqi Lu |
| Abstract Scope |
The fundamental understandings of the atomic and electronic principles are important to reveal the origins for the excellent mechanical and physical properties of High entropy Materials (HEMs). Herein, we propose a machine learning and theoretical knowledge-based design system of super-hard high-entropy boride ceramics (HEBs) to designing HEBs more efficient and target in vast composition space. This evaluation model was obtained by screened and trained from 149 characteristics and 9 algorithms, which can screen out intrinsic features closely related to performance mechanism. Thus, realized the performance evaluation and screening design of multivariate, multiphase and multiparameter coupling complex systems quickly. Moreover, the Shapley additive explanation the key influence trend for material hardness with the change of HEBs electronic properties. Combined with first-principles calculation, the material component-property influence mechanism can be analysis effectively from the atomic and electronic bottom layer. This strategy can reveal the target performance design for HEMs efficiently from knowledge. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Machine Learning, Ceramics, High-Temperature Materials |