About this Abstract |
Meeting |
MS&T23: Materials Science & Technology
|
Symposium
|
High Entropy Materials: Concentrated Solid Solutions, Intermetallics, Ceramics, Functional Materials and Beyond IV
|
Presentation Title |
Machine Learning-assisted Property Mapping of Al-Co-Cr-Fe-Ni High-Entropy Alloys from First-principles Calculations |
Author(s) |
Guangchen Liu, Songge Yang, Yu Zhong |
On-Site Speaker (Planned) |
Yu Zhong |
Abstract Scope |
The application of the first-principles calculations is extensively employed in studying high-entropy materials. However, this approach can be computationally demanding for intricate systems, which poses a significant limitation in developing property maps for related materials across the entire composition spectrum. In this study, we have chosen the popular Al-Co-Cr-Fe-Ni HEA system (FCC and BCC) as our research target. By leveraging the outcomes of first-principles calculations and machine learning, we have established a comprehensive repository of properties, encompassing phase stabilities and elastic properties. We initiated our investigation from unary, binary, ternary, and quaternary systems to the quinary system. Subsequently, we utilized this database to develop a comparable software program. Furthermore, we conducted a rigorous screening and statistical analysis to gain a complete understanding of the information and mechanism underlying the database. |