A Novel Neural Approach to the Determination of the Distribution Function in Magnetic Preisach Systems

Abstract

This paper presents a novel method to identify both the functional dependence of the Preisach function as well as its numerical parameters on the basis of some known magnetic behavior. In this paper, the identification of the Preisach function of a material is performed by using a neural network trained by a collection of hysteresis curves, whose Preisach functions are known. When a new hysteresis curve is given as input to this neural network, it is able to give as output both the functional dependence of the Preisach function as well as its numerical parameters.