Prediction of dynamic hysteresis under highly distorted exciting fields byneural networks and actual frequency transplantation

Neural Network (NN) and actual frequency transplantation (AFT) are combined for prediction of dynamic hysteresis when the exciting field, H(t), is hig hly polluted by harmonies. The NN forecasts the Fourier Series for flux den sity for well-known H(t) waveforms (i.e., triangular, square wave fields et c.). The task of AFT is to approach the arbitrary distortion of H(t) by exp loiting loop predictions by NN under pure sinusoidal excitations and then b y transplanting loop branches related to frequencies detected in short time -windows of the H(t) period. These actual frequencies will be evaluated by an appropriate time-frequency analysis of H(t). Model validations will be p resented in comparison with experimental data.