About this Abstract |
Meeting |
2024 TMS Annual Meeting & Exhibition
|
Symposium
|
Computational Thermodynamics and Kinetics
|
Presentation Title |
Phase Prediction and Optimization of Refractory High-entropy Alloys in Data-driven Approach |
Author(s) |
Jiwon Park, Chang-Seok Oh |
On-Site Speaker (Planned) |
Jiwon Park |
Abstract Scope |
In searching for novel structural alloys for high-temperature applications, refractory high-entropy alloys (RHEAs) draw vast attention due to their superior mechanical properties to nickel-based superalloys in elevated temperatures. The absence of principal elements in RHEAs requires new physical and thermodynamic models apart from accumulated knowledge in conventional structural alloy systems. In this work, we propose a feature selection strategy for the phase prediction models for the RHEA dataset constructed from the literature survey and CALPHAD computations using a genetic algorithm and feature explanation from SHAP analysis. The most relevant material descriptors are suggested among 49 features of the input dataset. Then the candidate compositions using Bayesian optimization and genetic algorithm are proposed and experimentally validated. |
Proceedings Inclusion? |
Planned: |
Keywords |
Machine Learning, High-Entropy Alloys, |