Ultrasonic motor (USM) is a newly developed motor, and it has excellen
t performance and many useful features, therefore, it has been expecte
d to be of practical use. However, the driving principle of USM is dif
ferent from that of other electromagnetic-type motors, and the mathema
tical model is complex to apply to motor control. Furthermore, the spe
ed characteristics of the motor have heavy nonlinearity and vary with
driving conditions. Hence, the precise speed control of USM is general
ly difficult, This paper proposes a new speed-control scheme for USM u
sing a neural network. The proposed controller can approximate the non
linear input-output mappings of the motor using a neural network and c
an compensate the characteristic variations by on-line learning using
the error backpropagation algorithm. Then, the trained network finally
makes an inverse model of the motor. The usefulness and validity of t
he proposed control scheme are examined in experiments.