About this Abstract |
Meeting |
2nd World Congress on High Entropy Alloys (HEA 2021)
|
Symposium
|
2nd World Congress on High Entropy Alloys (HEA 2021)
|
Presentation Title |
Computational Framework for Discovering High Entropy Alloy with Improved Properties |
Author(s) |
Stephen Giles, Debasis Sengupta, Scott Broderick, Krishna Rajan, Peter K Liaw, Hugh Short |
On-Site Speaker (Planned) |
Debasis Sengupta |
Abstract Scope |
One of major challenges in improving the properties of HEAs is the exploration of the vast compositional space experimentally. To circumvent this challenge, material scientists often try to find answers to difficult questions, such as what are the most important parameters that dictate the properties of HEAs; what is the sensitivity of HEA properties with respect to changes in each elemental fraction; how can one systematically improve an HEA property starting from a base alloy; how can one rapidly down select a few HEAs for processing from a large pool of conceptual candidates. The present work addresses these challenges via developing a computational framework that intelligently and systematically improves the properties of HEA in a desired direction. We combine state-of-the art machine learning techniques with sensitivity analysis and optimization to develop a computational framework for discovering HEAs with target properties and phases. |
Proceedings Inclusion? |
Undecided |