| About this Abstract |
| Meeting |
2024 TMS Annual Meeting & Exhibition
|
| Symposium
|
Accelerated Discovery and Insertion of Next Generation Structural Materials
|
| Presentation Title |
Design of Alloys Resistant to Molten Salt Corrosion via Machine Learning and Optimization Algorithms |
| Author(s) |
Rafael Herschberg, Franck Tancret |
| On-Site Speaker (Planned) |
Rafael Herschberg |
| Abstract Scope |
The search of the most resistant alloys to molten salt corrosion environments is imperative in the development of future nuclear reactors. Nonetheless, the comparison of their performance in absolute terms remains a challenge due to the many variables involved (salt composition, temperature, exposure time…). The present study tackles this obstacle and accelerates the evaluation of superior alloys by means of artificial intelligence approaches. Firstly, a database is built upon a literature survey where several alloys have been previously tested at identical experimental conditions. Secondly, their performance is ranked with a pairwise comparison algorithm, where each alloy constitutes a node in a directed network. Then, the assigned score is fitted as a function of alloy composition by a Gaussian process regression. Lastly, a multi-objective optimization algorithm is applied to obtain the best compromise between molten salt corrosion resistance and microstructural constitution (evaluated by computational thermodynamics). |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Modeling and Simulation, Machine Learning, |