Physics-informed machine learning and stray field computation with application to micromagnetic energy minimization

Autor(en)

Sebastian Schaffer, Thomas Schrefl, Harald Oezelt, Alexander Kovacs, Leoni Breth, Norbert J. Mauser, Dieter Suess, Lukas Exl

Abstrakt

We study the full 3d static micromagnetic equations via a physics-informed neural network (PINN) ansatz for the continuous magnetization configuration. PINNs are inherently mesh-free and unsupervised learning models. In our approach we can learn to minimize the total Gibbs free energy with additional conditional parameters, such as the exchange length, by a single low-parametric neural network model. In contrast, traditional numerical methods would require the computation and storage of a large number of solutions to interpolate the continuous spectrum of quasi-optimal magnetization configurations. We also consider the important and computationally expensive stray field problem via PINNs, where we use a basically linear learning ansatz, called extreme learning machines (ELM) within a splitting method for the scalar potential. This reduces the stray field training to a linear least squares problem with precomputable solution operator. We validate the stray field method by means of numerical example comparisons from literature and illustrate the full micromagnetic approach via the NIST μMAG standard problem #3.

Organisation(en)

Forschungsplattform MMM Mathematics-Magnetism-Materials, Physik Funktioneller Materialien, Institut für Mathematik, Experimentelle Grundausbildung und Hochschuldidaktik

Externe Organisation(en)

Wolfgang Pauli Institute (WPI) Vienna, Universität für Weiterbildung Krems

Journal

Journal of Magnetism and Magnetic Materials

Band

576

ISSN

0304-8853

DOI

https://doi.org/10.1016/j.jmmm.2023.170761

Publikationsdatum

06-2023

Peer-reviewed

Ja

ÖFOS 2012

101014 Numerische Mathematik, 103043 Computational Physics, 102001 Artificial Intelligence

Schlagwörter

ASJC Scopus Sachgebiete

Electronic, Optical and Magnetic Materials, Condensed Matter Physics

Link zum Portal

https://ucrisportal.univie.ac.at/de/publications/physicsinformed-machine-learning-and-stray-field-computation-with-application-to-micromagnetic-energy-minimization(081805b4-9a65-4db2-9d1e-557df468ebfb).html