About this Abstract |
Meeting |
2022 TMS Annual Meeting & Exhibition
|
Symposium
|
Materials and Chemistry for Molten Salt Systems
|
Presentation Title |
High-throughput and Machine Learning Accelerated Discovery of Corrosion-resistant Alloy for Molten Salt Applications |
Author(s) |
Yafei Wang, Bonita Goh, Phalgun Nelaturu, Thien Duong, Najlaa Hassan, Raphaelle David, Michael Moorehead, Santanu Chaudhuri, Jason Hattrick-Simpers, Dan Thoma, Kumar Sridharan, Adrien Couet |
On-Site Speaker (Planned) |
Yafei Wang |
Abstract Scope |
Insufficient availability of molten salt corrosion-resistant alloys severely limits the deployment of a variety of promising molten salt technologies that could otherwise have significant societal impacts. To accelerate the alloy development for molten salt applications, a set of high-throughput alloy synthesis, corrosion testing, characterization, and modelling techniques were developed to examine the corrosion resistances of more than 100 FeCrMnNi alloys in molten salt. By using these techniques, the corrosion resistances were characterized and used as a performance metric for a random forest regressor machine learning algorithm to predict the most corrosion-resistant alloys in molten salt. The predicted corrosion-resistant alloys were further tested and their corrosion resistances were compared with the existing commercial alloys, such as Hastelloy-N, alloy 617, alloy 800 H and 316 stainless steel. This study demonstrates the successful deployment of an integrated platform to accelerate corrosion-resistant alloy development by about three orders of magnitude. |
Proceedings Inclusion? |
Planned: |
Keywords |
Additive Manufacturing, Machine Learning, Nuclear Materials |