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.
@article{arxiv.2601.18300,
title = {Gradient-Informed Machine Learning in Electromagnetics},
author = {Matteo Zorzetto and Merle Backmeyer and Michael Wiesheu and Riccardo Torchio and Fabrizio Dughiero and Sebastian Schöps},
journal= {arXiv preprint arXiv:2601.18300},
year = {2026}
}
Comments
This work has been submitted to the IEEE for possible publication