Fuzzy neural network model-following controller for ultrasonic motor servo drives

This study proposes to employ a fuzzy neural network (FNN) model-following controller to regulate an ultrasonic motor (USM) servo drive. First, the network structure and the on-line learning algorithm of the FNN are described. Next, the proposed driving circuit for the USM, which is a two-phase chopper-inverter combination, is designed. Then a proportional-integral (PI) position controller is adopted to control the position of the USM. Since the dynamic characteristics of the USM are difficult to obtain and the motor parameters are time varying, the FNN model-following controller is added to reduce the influence of parameter uncertainties and external disturbances. Moreover, to test the performance of the FNN the inner loop PI position controller is omitted, instead using only the FNN model-following controller to control the position of the USM. The effectiveness of the proposed controller is demonstrated by some experimental results.