A neural network model of non-linear hysteretic inductors is presented
. The proposed neural network model is shown to reproduce the dynamic
scalar hysteretic behavior proper of the current-flux relationship. Mo
reover, the intrinsic characteristics of the neural network approach y
ield the model particularly suitable when dependencies on different pa
rameters are present, e.g., influence of mobile part positions, of tem
perature etc.. Both theoretical comparisons (e.g., Chua-Stronsmoe mode
l and Jiles-Atherton model) and experimental measurements (e.g,, varia
ble reluctance linear motor) are considered. Results point out the num
erical accuracy and computational efficiency of the proposed NN approa
ch, that results in a general framework useful in the field of electri
cal machinery, of electronic power circuits, of control and identifica
tion.