Multilayered perceptron neural networks to compute energy losses in magnetic cores


Kucuk I.

JOURNAL OF MAGNETISM AND MAGNETIC MATERIALS, vol.307, no.1, pp.53-61, 2006 (Peer-Reviewed Journal) identifier identifier

  • Publication Type: Article / Article
  • Volume: 307 Issue: 1
  • Publication Date: 2006
  • Doi Number: 10.1016/j.jmmm.2006.03.043
  • Journal Name: JOURNAL OF MAGNETISM AND MAGNETIC MATERIALS
  • Journal Indexes: Science Citation Index Expanded, Scopus
  • Page Numbers: pp.53-61

Abstract

This paper presents a new approach based on multilayered perceptrons (MLPs) to compute the specific energy losses of toroidal wound cores built from 3% SiFe 0.27 mm thick M4, 0.1 and 0.08 mm thin gauge electrical steel strips. The MLP has been trained by a back-propagation and extended delta-bar-delta learning algorithm. The results obtained by using the MLP model were compared with a commonly used conventional method. The comparison has shown that the proposed model improved loss estimation with respect to the conventional method. (c) 2006 Elsevier B.V. All rights reserved.