For the evaluation of the dynamic hysteresis loops, a Neural Network (NN) c
ombined with the Fourier Descriptor (FD) technique can be a simple computat
ional instrument alternative to the classical approach. This method is suit
able in those cases in which a distorted periodic magnetic held H, or flux
density B, excites, in steady state, the ferromagnetic nucleus of a de,ice.
The dependence of the hysteresis loop from the magnetic field frequency; h
as been successfully evaluated by NN while, by means of the Fourier Descrip
tor, the effects of the magnetic field distortion have been efficiently pre
dicted. Numerical results compared with those from other models (i.e. Jiles
model) and experimental data are presented in the end.