A neural network-based tool for magnetic performance prediction of toroidal cores


Miti G., Moses A., Derebasi N., Fox D.

JOURNAL OF MAGNETISM AND MAGNETIC MATERIALS, vol.254, pp.262-264, 2003 (Peer-Reviewed Journal) identifier identifier

  • Publication Type: Article / Article
  • Volume: 254
  • Publication Date: 2003
  • Doi Number: 10.1016/s0304-8853(02)00788-6
  • Journal Name: JOURNAL OF MAGNETISM AND MAGNETIC MATERIALS
  • Journal Indexes: Science Citation Index Expanded, Scopus
  • Page Numbers: pp.262-264

Abstract

Geometrical and building parameters have a strong influence on magnetic performance of wound toroidal cores made from electrical steel or similar strip products. This paper presents a neural network-based approach to predict losses and permeability in such cores of varying geometries over an induction range of 0.2-1.8 T (50 Hz). The approach is shown to be successful. (C) 2002 Elsevier Science B.V. All rights reserved.