Magnetic microstructure machine learning analysis

Lukas Exl, Johann Fischbacher, Alexander Kovacs, Harald Oezelt, Markus Gusenbauer, Kazuya Yokota, Tetsuya Shoji, Gino Hrkac, Thomas Schrefl (Korresp. Autor*in)

Veröffentlichungen: Beitrag in FachzeitschriftArtikelPeer Reviewed


We use a machine learning approach to identify the importance of microstructure characteristics in causing magnetization reversal in ideally structured large-grained Nd$_2$Fe$_{14}$B permanent magnets. The embedded Stoner-Wohlfarth method is used as a reduced order model for determining local switching field maps which guide the data-driven learning procedure. The predictor model is a random forest classifier which we validate by comparing with full micromagnetic simulations in the case of small granular test structures. In the course of the machine learning microstructure analysis the most important features explaining magnetization reversal were found to be the misorientation and the position of the grain within the magnet. The lowest switching fields occur near the top and bottom edges of the magnet. While the dependence of the local switching field on the grain orientation is known from theory, the influence of the position of the grain on the local coercive field strength is less obvious. As a direct result of our findings of the machine learning analysis we show that edge hardening via Dy-diffusion leads to higher coercive fields.
FachzeitschriftJournal of Physics: Materials
PublikationsstatusVeröffentlicht - 2019

ÖFOS 2012

  • 101014 Numerische Mathematik
  • 102019 Machine Learning
  • 103018 Materialphysik


Untersuchen Sie die Forschungsthemen von „Magnetic microstructure machine learning analysis“. Zusammen bilden sie einen einzigartigen Fingerprint.