Identification of parameters of dynamic Preisach model by neural networks

Trapanese M

Risultato della ricerca: Article

5 Citazioni (Scopus)

Abstract

This paper presents a methodology for identifying Reduced Vector Preisach Model parameters by using neural networks. The neural network used is a multiplayer perceptron trained with the Levenberg-Marquadt training algorithm. The network is trained by some hysteresis data, which are generated by using Reduced Vector Preisach Model with pre-assigned parameters. It is shown how a properly trained network is able to find the parameters needed to best fit a magnetization hysteresis curve.
Lingua originaleEnglish
pagine (da-a)07D929-1-07D929-3
RivistaJournal of Applied Physics
Volume103
Stato di pubblicazionePublished - 2008

Fingerprint

dynamic models
hysteresis
self organizing systems
education
methodology
magnetization
curves

All Science Journal Classification (ASJC) codes

  • Physics and Astronomy(all)

Cita questo

Identification of parameters of dynamic Preisach model by neural networks. / Trapanese M.

In: Journal of Applied Physics, Vol. 103, 2008, pag. 07D929-1-07D929-3.

Risultato della ricerca: Article

Trapanese M 2008, 'Identification of parameters of dynamic Preisach model by neural networks', Journal of Applied Physics, vol. 103, pagg. 07D929-1-07D929-3.
Trapanese M. Identification of parameters of dynamic Preisach model by neural networks. Journal of Applied Physics. 2008;103:07D929-1-07D929-3.
Trapanese M. / Identification of parameters of dynamic Preisach model by neural networks. In: Journal of Applied Physics. 2008 ; Vol. 103. pagg. 07D929-1-07D929-3.
@article{128f2b41697745aabc659f2af19960e6,
title = "Identification of parameters of dynamic Preisach model by neural networks",
abstract = "This paper presents a methodology for identifying Reduced Vector Preisach Model parameters by using neural networks. The neural network used is a multiplayer perceptron trained with the Levenberg-Marquadt training algorithm. The network is trained by some hysteresis data, which are generated by using Reduced Vector Preisach Model with pre-assigned parameters. It is shown how a properly trained network is able to find the parameters needed to best fit a magnetization hysteresis curve.",
author = "{Trapanese M} and Marco Trapanese",
year = "2008",
language = "English",
volume = "103",
pages = "07D929--1--07D929--3",
journal = "Journal of Applied Physics",
issn = "0021-8979",
publisher = "American Institute of Physics Publising LLC",

}

TY - JOUR

T1 - Identification of parameters of dynamic Preisach model by neural networks

AU - Trapanese M

AU - Trapanese, Marco

PY - 2008

Y1 - 2008

N2 - This paper presents a methodology for identifying Reduced Vector Preisach Model parameters by using neural networks. The neural network used is a multiplayer perceptron trained with the Levenberg-Marquadt training algorithm. The network is trained by some hysteresis data, which are generated by using Reduced Vector Preisach Model with pre-assigned parameters. It is shown how a properly trained network is able to find the parameters needed to best fit a magnetization hysteresis curve.

AB - This paper presents a methodology for identifying Reduced Vector Preisach Model parameters by using neural networks. The neural network used is a multiplayer perceptron trained with the Levenberg-Marquadt training algorithm. The network is trained by some hysteresis data, which are generated by using Reduced Vector Preisach Model with pre-assigned parameters. It is shown how a properly trained network is able to find the parameters needed to best fit a magnetization hysteresis curve.

UR - http://hdl.handle.net/10447/24800

M3 - Article

VL - 103

SP - 07D929-1-07D929-3

JO - Journal of Applied Physics

JF - Journal of Applied Physics

SN - 0021-8979

ER -

Accesso al documento