Ultrasonic motor (USM) is a newly developed motor and it has an excellent performance and many useful features, so it has been expected to be of practical use. However, this motor has a heavy nonlinearity which varies with driving conditions. Therefore, precise speed control of ultrasonic motor is difficult. This paper proposes a new speed control scheme for ultrasonic motor using a neural network. The proposed controller can approximate the nonlinear input-output mappings of the motor using the neural network, and can compensate the characteristic variations by online learning. The usefulness and validity of the proposed control scheme is examined by experiments.

No abstract

No abstract

No abstract

Ultrasonic motor is a newly developed rnokar and it has excellent performance and many useful features, therefore, the ultrasonic motor i s expected for many practical applications. However, the drive principle of ultrasanic motor is diEeserit from that of other electromagnetic type motors, and the ~a t~~~i a~~~a~ model of the motor $evetoped yet. Furthermore, the spee tics 0% the motor hold heavy n o~~~n~~~~y and they rive conditions. Therefore, the precise position control of ~ltrasonic motor is generally difficult. h i this paper. we propose a new position control scheme for ultrasonic matex using a neural network. The proposed controller can ~p p~~x~~a t e the nonlinear input-output mappings of the motor using the neural network, and can compensate the characteristic variations by online learning based on &he general ~~~~~~o~a~a t~o~ algorithm. The trained network A n d y makes an inverse model of the plant. 'The usefulness and validity of the praposed control scheme is examined in experiments, 0-7803-3334-9/96/$5.00 0 1996 IEEE. 368