About this Abstract |
Meeting |
2023 TMS Annual Meeting & Exhibition
|
Symposium
|
Environmental Degradation of Multiple Principal Component Materials
|
Presentation Title |
Enabling Oxidation-resistant Refractory Complex, Concentrated Alloys via a Machine Learning for Accelerated Materials Discovery Framework |
Author(s) |
Michael S. Titus, Sharmila Karumuri, Saswat Mishra, Vincent Mika, Collin Scott, Austin Hernandez, Nimish Awalgaonkar, Kenneth Sandhage, Ilias Bilionis, Alejandro Strachan |
On-Site Speaker (Planned) |
Michael S. Titus |
Abstract Scope |
Refractory complex, concentrated alloys (RCCAs) are refractory-based alloys comprising four or more elements with near equimolar compositions, and some of these alloys can exhibit superior oxidation resistance compared to traditional refractory-based alloys. In this work, we will present a new machine learning for accelerated materials discovery (ML-AMD) framework that utilizes multi-fidelity and multi-cost experiments with physics-based modeling. This framework includes the integration of an oxidation database containing mass gain data from single- and multiple-component alloys, CALPHAD-based thermodynamic predictions of phase equilibria, first-principles-based predictions of oxide formation, and limited experiments with machine learning and active learning algorithms to accelerate the discovery process. This framework already led to the discovery of new ultra-high strength Al-based solid-solution BCC RCCAs, exceeding strengths found in literature. A new oxidation database of RCCAs and preliminary analysis will be presented, and recent efforts in optimizing oxidation resistance in RCCAs will be shown. |
Proceedings Inclusion? |
Planned: |
Keywords |
High-Entropy Alloys, Environmental Effects, Machine Learning |