Abstract: A newly developed input-output recurrent neural network (IORNN) identifier of USM is constructed. A bimodal neural network controller is designed where both the driving frequency and amplitude of the applied voltage are used as control inputs. The dynamic recurrent back-prop agation algorithm of the identifier and controller are developed. Numerical results show that the proposed IORNN identifier can approximate the nonlinear input-output mappings of the ultrasonic motor quite well. Good effectiveness of the proposed bimodal IORNN controller is also obtained for some different kinds of reference speeds.