| About this Abstract |
| Meeting |
2025 TMS Annual Meeting & Exhibition
|
| Symposium
|
Materials Aging and Compatibility: Experimental and Computational Approaches to Enable Lifetime Predictions
|
| Presentation Title |
Predicting Electrochemical Responses Using Machine Learning |
| Author(s) |
Matthew Roop, David Montes de Oca Zapiain, Aditya Venkatraman, Sam Moran, Rebecca Schaller, Ryan Katona |
| On-Site Speaker (Planned) |
Matthew Roop |
| Abstract Scope |
The electrochemical response of metals can be ascertained through various methods. Potentiodynamic polarizations provide electrochemical behavior of a metal in an electrolyte solution. Polarization curves are generated through physical experiments which can be costly. Machine Learning (ML) was used to predict polarization curves from metal and electrolyte properties without conducting physical experiments, saving time and resources. However, there is no suitable repositories for holding polarization curves properly that is easily accessible to ML. To solve this issue, a database has been constructed using python specifically for storing electrochemical data and extracted properties. This database, however, is sparse. The database uses ML to identify experimental conditions so that minimal scans need to be obtained through physical experiments to produce a satisfactory model able to predict electrochemical materials’ performance.
Acknowledgements
SNL is managed and operated by NTESS under DOE NNSA contract DE-NA0003525.
SAND2024-08538A |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Computational Materials Science & Engineering, Machine Learning, |