A new neural-network-based scalar hysteresis model

Author

Kuczmann, M. ; Iványi, A.

Author_Institution

Dept. of Electromagn. Theor., Budapest Univ. of Technol. & Econ., Hungary

Volume

38

Issue

2

fYear

2002

fDate

3/1/2002 12:00:00 AM

Firstpage

857

Lastpage

860

Abstract

A neural network (NN)-based model of scalar hysteresis characteristics has been developed for modeling the behavior of magnetic materials. The virgin curve and a set of the first-order reversal branches can be stored preliminary in a system of three NNs. Different properties of magnetic materials can be simulated by a simple if-then type knowledge-based algorithm. Hysteresis characteristics of different materials predicted by the introduced model are compared with the results of the classical Preisach simulation technique. Comparisons are plotted in figures

Keywords

electromagnetic fields; feedforward neural nets; magnetic hysteresis; transfer functions; Preisach simulation technique; feedforward-type neural networks; first-order reversal branches; if-then type knowledge-based algorithm; magnetic materials; neural-network-based model; scalar hysteresis model; virgin curve; Computational modeling; Function approximation; Magnetic field measurement; Magnetic fields; Magnetic hysteresis; Magnetic materials; Magnetization; Neural networks; Predictive models; Training data;

fLanguage

English

Journal_Title

Magnetics, IEEE Transactions on

Publisher

ieee

ISSN

0018-9464

Type

jour

DOI

10.1109/20.996221

Filename

996221