Title :
Speed sensorless control of ultrasonic motors using neural network
Author :
Senjyu, Tomonobu ; Yoshida, Tomohiro ; Uezato, Katsumi ; Urasaki, Naomitsu ; Panda, S.K.
Author_Institution :
Fac. of Eng., Ryukyus Univ., Okinawa, Japan
Abstract :
This paper presents a speed sensorless control for ultrasonic motors using a neural network. In the proposed method, a three-layered NN is used with offline training. The drive frequency, the root mean square value of input voltage and the surface temperature of USM are used as the inputs of NN for speed estimator. The validity of the proposed method is confirmed by experimental results.
Keywords :
angular velocity control; machine control; multilayer perceptrons; neurocontrollers; parameter estimation; ultrasonic motors; USM drive frequency; USMs surface temperature; offline training; root mean square value; speed estimation; speed sensorless control; three layered neural network; ultrasonic motors; Electromagnetic forces; Frequency estimation; Neural networks; Rotors; Sensorless control; Temperature sensors; Torque; Velocity control; Velocity measurement; Voltage;
Conference_Titel :
Industrial Electronics Society, 2003. IECON '03. The 29th Annual Conference of the IEEE
Print_ISBN :
0-7803-7906-3
DOI :
10.1109/IECON.2003.1280003
