Prandtl-Ishlinskii Modeling for Giant Magnetostrictive Actuator Based on Internal Time-Delay Recurrent Neural Network

Giant magnetostrictive actuator (GMA) becomes more promising in precision positioning, sophisticated manufacturing, and microelectronic system, because of the excellent performance such as high resolution, rapid response, and large mechanical force. However, the intrinsic hysteresis of GMA is the main sticking point preventing its application in the high precision positioning. In this paper, a Prandtl-Ishlinskii (PI) model is established. To obtain the parameters of the model, the internal time-delay recurrent neural network (RNN) with self-tuning ability is proposed. A series of simulations are conducted to testify the availability of proposed method and the results indicates that the PI model identified by the internal time-delay RNN can accurately describe the hysteresis of GMA with the increase of frequency.