Modeling hysteresis based on dynamic hysteretic operator

A neural hysteresis model based on dynamic hysteretic operator is proposed. In this method, a novel hysteretic operator is proposed to describe the dynamic property of hysteresis. Then neural network is used to approximate the weight function. Based on the principle of hysteretic operator-superposition, the dynamic hysteresis model based on neural networks is derived. Finally, this method is applied to dynamic modeling of the hysteresis in piezoelectric actuator. The experimental results are presented to illustrate the potential of the proposed modeling technique.