About this Abstract |
Meeting |
MS&T21: Materials Science & Technology
|
Symposium
|
High Entropy Materials: Concentrated Solid Solutions, Intermetallics, Ceramics, Functional Materials and Beyond II
|
Presentation Title |
Machine Learning Enabled Defect Energies in Concentrated Alloys |
Author(s) |
Gaurav Arora, Anus Manzoor, Dilpuneet S. Aidhy |
On-Site Speaker (Planned) |
Dilpuneet S. Aidhy |
Abstract Scope |
Concentrated alloys, including high entropy alloys, consist of multiple principal elements randomly distributed on a crystal lattice that causes large variations in defect energies in a given alloy composition. Statistically capturing the variation requires performing large number of calculations which is computationally highly expensive. The challenge is compounded due to the exponentially large number of compositions that are possible in these alloys. We use machine learning approach to predict defect energies, where a database of simpler alloys is used to predict defect energies in complex alloys. We demonstrate predictions of vacancy formation and migration energies in five-element Ni-based alloys and stacking fault energies in ternary alloys. A benefit of this approach is that once the binary database is built and the model is trained, defect energies can be predicted with little computational expense thereby bypassing large number of calculations every time a new composition is discovered. |