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 |
ON DEMAND: High-throughput Screening of Structural High Entropy Alloys Using a Machine Learning Approach |
Author(s) |
Novana Utama Hutasoit, Pragalathan Apputhurai |
On-Site Speaker (Planned) |
Novana Utama Hutasoit |
Abstract Scope |
High entropy alloys consist of five or more elements pose a hyper-dimension compositional space that screening the potential chemical composition through conventional synthesis-test route is time-wise impractical. Therefore, turning to the machine learning method is deemed adequate to establish algorithms capable of identifying chemical composition space that yields high entropy alloys with a set of desired mechanical properties. In this study, data-driven machine learning is explored. The chemical composition and mechanical properties of high entropy alloys; and physical properties of each element composing high entropy alloys reported in the are literature are retrieved and archived in a database. A decision-tree-based ensemble machine learning algorithm using the input of features constructed from elemental composition and properties exhibits a capability to predict the mechanical properties of given high entropy alloys chemical composition. The algorithm developed in this study aid in the development of high entropy alloys with tailored mechanical properties. |
Proceedings Inclusion? |
Undecided |