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

Miti, GK; Moses, AJ; Derebasi, N; Fox, D

doi:10.1016/s0304-8853(02)00788-6

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

Atıf İçin Kopyala

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

JOURNAL OF MAGNETISM AND MAGNETIC MATERIALS, cilt.254, ss.262-264, 2003 (SCI-Expanded)

Yayın Türü: Makale / Tam Makale
Cilt numarası: 254
Basım Tarihi: 2003
Doi Numarası: 10.1016/s0304-8853(02)00788-6
Dergi Adı: JOURNAL OF MAGNETISM AND MAGNETIC MATERIALS
Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
Sayfa Sayıları: ss.262-264
Bursa Uludağ Üniversitesi Adresli: Hayır

Özet

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.