Recurrent fuzzy neural network control for piezoelectric ceramic linear ultrasonic motor drive

In this study, a recurrent fuzzy neural network (RFNN) controller is propos ed to control a piezoelectric ceramic linear ultrasonic motor (LUSM) drive system to track periodic reference trajectories with robust control perform ance. First, the structure and operating principle of the LUSM are describe d in detail. Second, because the dynamic characteristics of the LUSM are no nlinear and the precise dynamic model is difficult to obtain, a RFNN is pro posed to control the position of the moving table of the LUSM to achieve hi gh precision position control with robustness. The back propagation algorit hm is used to train the RFNN on-line. Moreover, to guarantee-the convergenc e of tracking error for periodic commands tracking, analytical methods base d on a discrete-type Lyapunov function are proposed to determine the varied learning rates of the RFNN. Then, the RFNN is implemented in a PC-based co mputer control system, and the LUSM is driven by a unipolar switching full bridge voltage source inverter using LC resonant technique. Finally, the ef fectiveness of the RFNN-controlled LUSM drive system is demonstrated by som e experimental results. Accurate tracking response and superior dynamic per formance can be obtained because of the powerful on-line learning capabilit y of the RFNN controller, Furthermore, the RFNN control system is robust wi th regard to parameter variations and external disturbances.