About this Abstract |
Meeting |
Materials Science & Technology 2020
|
Symposium
|
Computation Assisted Materials Development for Improved Corrosion Resistance
|
Presentation Title |
Machine Learning to Predict Cyclic Oxidation of NiCr-based alloys |
Author(s) |
Jian Peng, Marie Romedenne, Rishi Pillai, Govindarajan Muralidharan, Bruce A. Pint, J. Allen Haynes, Dongwon Shin |
On-Site Speaker (Planned) |
Jian Peng |
Abstract Scope |
Machine learning (ML) can offer many advantages in predicting material properties over traditional materials development methods based solely on limited experimental investigations or physical-based simulations with respect to cost, risk, and time. However, thus far limited efforts have been published to predict alloy oxidation resistance via ML. In this presentation, we compare two different oxidation models (a simple parabolic law and a statistical cyclic-oxidation model) to represent the high-temperature oxidation of NiCr-based alloys in dry- and wet-air within the context of data analytics. We successfully trained ML models with highly ranked key features identified from the extensive correlation analysis. The performance of selected oxidation models in ML was compared and discussed. This research was sponsored by the Department of Energy, Vehicle Technologies Office, Propulsion Materials Program. |