Analysis of the Excess Loss in High-Frequency Magnetization Process Through Machine Learning and Topological Data Analysis
Published in IEEE Transactions on Magnetics, Vol. 60, No. 9, pp. 1–5, 2024
Authors & Affiliations:
- Alexandre Lira Foggiatto, Ryunosuke Nagaoka, Michiki Taniwaki, Takahiro Yamazaki, Chiharu Mitsumata, Masato Kotsugi — Tokyo University of Science
- Takeshi Ogasawara — National Institute of Advanced Industrial Science and Technology (AIST), Japan
- Ippei Obayashi — Okayama University
- Yasuaki Hiraoka — Kyoto University
This study presents a physics-aware machine learning framework for evaluating excess loss mechanisms in high-frequency magnetization processes. By combining topological data analysis (TDA) and feature-based modeling, the work provides a new lens for understanding complex magnetic dynamics, especially in industrial electrical steel systems.
Recommended citation: Foggiatto, A. L., Nagaoka, R., Taniwaki, M., Yamazaki, T., Ogasawara, T., Obayashi, I., Hiraoka, Y., Mitsumata, C., & Kotsugi, M. (2024). "Analysis of the Excess Loss in High-Frequency Magnetization Process Through Machine Learning and Topological Data Analysis." *IEEE Transactions on Magnetics*, 60(9), 1–5. https://doi.org/10.1109/TMAG.2024.3406717
Download Paper