Neural Network Using Genetic Algorithm for Magnetic Performance Prediction of Toroidal Wound Cores at 50 Hz

Ilker Kucuk; Naim Derebasi

doi:10.3390/mca8020201

You are currently viewing a new version of our website. To view the old version click .

Mathematical and Computational Applications is published by MDPI from Volume 21 Issue 1 (2016). Previous articles were published by another publisher in Open Access under a CC-BY (or CC-BY-NC-ND) licence, and they are hosted by MDPI on mdpi.com as a courtesy and upon agreement with Association for Scientific Research (ASR).

Article

1 August 2003

Neural Network Using Genetic Algorithm for Magnetic Performance Prediction of Toroidal Wound Cores at 50 Hz

and

Uludag University, Arts and Sciences Faculty, Physics Department, 16059 Gorukle-Bursa, Turkey

Authors to whom correspondence should be addressed.

Math. Comput. Appl.2003, 8(2), 201-208;https://doi.org/10.3390/mca8020201

Version Notes

Order Reprints

Abstract

Geometrical and building parameters have a strong influence on magnetic performance of toroidal wound cores made from grain oriented 3% SiFe electrical steel. From a sample of 40 cores with dimensions ranging from 35 to 160 mm outer diameter, 25 to 100 mm inner diameter and JO to 70 mm strip width and a flux density range of 0.1 to 1.7 T have been obtained and used as training data to a generalised feedforward neural network.

Keywords:

Artificial neural network; Genetic algorithm; toroidal wound core; magnetic performance

Article Metrics

Citations

Article Access Statistics

Journal Statistics

Multiple requests from the same IP address are counted as one view.

Differential Transform Technique for Solving Fifth-Order Boundary Value Problems

Determination of Hardness of Pre-Aged AA 6063 Aluminum Alloy by Means of Artificial Neural Networks Method