Power loss modelling on different types of amorphous ribbons

Abstract

This paper presents a new artificial neural network approach based on dynamic Preisach model and finite element method to compute power loss on amorphous ribbons. The power loss values on these ribbons obtained from the finite element method and dynamic Preisach model have been used as a training data in this artificial neural network model. The model is fast, does not require a large set of measurement data and does not require tremendous computational efforts. The results obtained by using the proposed new model are in good agreement with experimental results previously reported. Copyright © 2007 American Scientific Publishers. All rights reserved.