| About this Abstract |
| Meeting |
2021 TMS Annual Meeting & Exhibition
|
| Symposium
|
Hume-Rothery Symposium: Accelerated Measurements and Predictions of Thermodynamics and Kinetics for Materials Design and Discovery
|
| Presentation Title |
High-throughput Experiments and Machine Learning Modeling for Designing Next Generation Superalloys |
| Author(s) |
Akane Suzuki, Chen Shen |
| On-Site Speaker (Planned) |
Akane Suzuki |
| Abstract Scope |
High-throughput experiments and machine learning modeling are increasingly becoming essential tools for efficiently and successfully designing new alloy chemistries that are tailored to achieve desired combinations of properties. In this talk, we will present examples of applying high-throughput experiments using diffusion multiples and machine learning modeling of physical, mechanical and environmental properties using historical and/or new datasets in designing next generation Ni-based and Co-based superalloys for industrial power generation gas turbines and aircraft engines. Current limitations of these tools and challenges for future industrial applications will be discussed. |
| Proceedings Inclusion? |
Planned: |