Vector neural network hysteresis model

Abstract

A neural network model of scalar hysteresis phenomena has been developed for modeling the behavior of isotropic magnetic materials. The function approximation ability of artificial neural networks has been applied. The virgin curve and a set of the first-order reversal branches can be stored preliminarily in a system of three neural networks. Different properties of magnetic materials can be simulated by a knowledge-based algorithm. Finally, hysteresis characteristics of different materials predicted by the introduced model are compared with the results of the classical Preisach simulation. Theoretical achievement and results of vector generalization of the method are also introduced.