GA-neural network based position control of Traveling Wave Ultrasonic Motor

Modeling of special kind of ultrasonic motor i.e. Traveling Wave Ultrasonic Motor (TWUSM) by means of genetic algorithm (GA) & neural network (NN) based Hammerstein model and its control by GA-NN based Model Predictive Control (MPC) is presented in this paper, in which the nonlinear static part of model is approximated by a GA-based radial basis function neural network (RBFNN) and the linear dynamic part is modeled by experimental measurement. GA is also adopted to optimize the hidden centers, the radial basis function widths and the weights of the RBFNN. A nonlinear MPC based on the Hammerstein model is developed to obtain precise USM position control. The simulation results show that the proposed approach is very effective, suitable and useful for control of TWUSM.