| About this Abstract |
| Meeting |
TMS Specialty Congress 2024
|
| Symposium
|
Accelerating Discovery for Mechanical Behavior of Materials 2024
|
| Presentation Title |
Discovering Superhard High-entropy Diboride Ceramics via a Hybrid Data-driven and Knowledge-enabled Model |
| Author(s) |
Jiaqi Lu, William Yi Wang |
| On-Site Speaker (Planned) |
Jiaqi Lu |
| Abstract Scope |
Materials descriptors with multivariate, multiphase, and multiscale of a complex system have been treated as the remarkable materials genome, addressing the composition–processing–structure–property–performance relationships during the development of advanced materials. With the aid of high-performance computations, big-data, and artificial intelligence technologies, this work derive an explainable model of composition–property–performance relationships via a hybrid data-driven and knowledge-enabled model, and designing 14 potential superhard high-entropy diboride ceramics with a cost-effective approach. Five dominate features and optimal model were screened out from 149 features and nine algorithms by machine learning and validated in first-principles calculations. The HEBs component electronic-property influence trend and mechanism has been analysis effectively from the atomic and electronic bottom layer. Moreover, this electron work function-machine learning model not only has better capability to distinguish the differences of solutes in same group of periodic table but is also a more effective method for material design than that of valence electron concentration. |
| Proceedings Inclusion? |
Definite: Other |