Gradient-Informed Machine Learning in Electromagnetics
IEEE Transactions on Magnetics · 2026-07 · 62 (7) · 7000907-7000907
DOI: 10.1109/tmag.2026.3702291 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Magnetics, 2026-07. Verfasst von Matteo Zorzetto und 5 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: German Academic Exchange Service (DAAD) through the Program Research Grants in Germany, 2025, Joint German Research Foundation, Austrian Science Fund (FWF) Collaborative Research Center CREATOR at TU Darmstadt, TU Graz, and JKU Linz.
Abstract (Originalsprache)
Simulation techniques, such as the finite element method are essential for designing electrical devices, but their computational cost can be prohibitive for repeated or real-time computations. Projection-based model order reduction techniques mitigate this by reducing the model size and complexity, yet face challenges when extended to nonlinear or non-affine parametric models. In this work, isogeometric analysis (IGA) is combined with proper orthogonal decomposition and Gaussian process regression to construct a non-intrusive surrogate model of a parametric nonlinear model of a permanent magnet synchronous machine. The differentiable nature of IGA allows for computationally efficient extraction of parametric sensitivities, which are leveraged for gradient-enhanced surrogate modeling.
Förderung
- German Academic Exchange Service (DAAD) through the Program Research Grants in Germany, 2025
- Joint German Research Foundation
- Austrian Science Fund (FWF) Collaborative Research Center CREATOR at TU Darmstadt, TU Graz, and JKU Linz
Zitieren
APA
Zorzetto, M., Backmeyer, M., Wiesheu, M., Torchio, R., Dughiero, F., & Schöps, S. (2026). Gradient-Informed Machine Learning in Electromagnetics. IEEE Transactions on Magnetics, 62(7), 7000907-7000907. https://doi.org/10.1109/tmag.2026.3702291
Vancouver
Zorzetto M, Backmeyer M, Wiesheu M, Torchio R, Dughiero F, Schöps S. Gradient-Informed Machine Learning in Electromagnetics. IEEE Transactions on Magnetics. 2026;62(7):7000907-7000907. doi:10.1109/tmag.2026.3702291
BibTeX
@article{Zorzetto2026,
author = {Zorzetto, Matteo and Backmeyer, Merle and Wiesheu, Michael and Torchio, Riccardo and Dughiero, Fabrizio and Schöps, Sebastian},
title = {Gradient-Informed Machine Learning in Electromagnetics},
journal = {IEEE Transactions on Magnetics},
year = {2026},
volume = {62},
number = {7},
pages = {7000907--7000907},
doi = {10.1109/tmag.2026.3702291}
}
EUVIMED