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 Oxidation Resistance in Refractory Alloys and High-throughput Experiments |
Author(s) |
Sharmila Karumuri, Saswat Mishra, Akhil Bejjipurapu, Vincent Mika, Collin Scott, Noah Hallberg, Kenneth Sandhage, Ilias Bilionis, Alejandro Strachan, Michael S. Titus |
On-Site Speaker (Planned) |
Michael S. Titus |
Abstract Scope |
Refractory complex, concentrated alloys (RCCAs) offer new avenues for designing high strength and oxidation resistant materials at elevated temperature. However, RCCAs often exhibit multiple oxidation mechanisms including oxide volatilization, internal oxidation, external scale formation, and pesting. In this talk, we will show recent work developing an open-source, automated framework housed in NanoHub.org for experimental data ingestion and storage of high temperature oxidation experimental data. With this database, and additional atomistic-based descriptors of oxide layering, predictions of mass gain behavior using Gaussian process regression of RCCAs will be presented. Active learning coupled with high-throughput oxidation testing with diffusion multiples will reveal composition space with improved oxidation resistance compared to current literature. Finally, we will show preliminary results from a multi-objective optimization to design RCCAs with high strength, ductility, and oxidation resistance. |