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 |
Machine Learning Based Intelligent Framework for Discovering High Entropy Alloy |
Author(s) |
Debasis Sengupta, Stephen Giles, Scott Broderick, Krishna Rajan |
On-Site Speaker (Planned) |
Debasis Sengupta |
Abstract Scope |
High-entropy alloys (HEA) are a promising class of materials that show elevated-temperature yield strengths, which are superior to superalloys. However, exploring the vast HEAs compositional space by traditional trial-and-error protocol is challenging. Consequently, only a small fraction of this space has been explored to date. The work presented here addresses this challenge and initiates the development of a framework by coupling the state-of-the-art machine learning (ML) and optimization method to intelligently explore the vast compositional space and drive the search in a direction that improves HEA mechanical properties at high-temperatures, thereby discovering new HEAs. We first develop a forward prediction model by coupling feature selection, boot strapping, and-k-fold validation. The forward model is the then used for discovering new HEAs with improved yield strengths. The computational framework developed is fully automatic and particularly useful for materials scientists to narrow the HEA design space. |
Proceedings Inclusion? |
Undecided |