Machine-Learned Models for Power Magnetic Material Characteristics

We present a general framework for modeling power magnetic materials characteristics using deep neural networks. Magnetic materials represented by multidimensional characteristics (that mimic measurements) are used to train the neural autoencoder model in an unsupervised manner. The encoder is tryin...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on power electronics 2025-01, Vol.40 (1), p.1554-1562
Hauptverfasser:	Leszczynski, Pawel, Kutorasinski, Kamil, Szewczyk, Marcin, Pawlowski, Jaroslaw
Format:	Artikel
Sprache:	eng
Schlagworte:	Current measurement Data models Deep neural networks (NNs) Impedance Magnetic materials magnetic ring materials modeling Physics power magnetics Saturation magnetization synthetic data Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!