Home // COGNITIVE 2015, The Seventh International Conference on Advanced Cognitive Technologies and Applications // View article

Recurrent Fuzzy Neural Network Controller Design for Ultrasonic Motor Rotor Angle Control

Authors:
Tien-Chi Chen
Tsai-Jiun Ren
Yi-Wei Lou

Keywords: ultrasonic motor; recurrent fuzzy neural network; compensated controller; adjustable parameters; on line learning algorithm.

Abstract:
The ultrasonic motor (USM) has significant high precision, fast dynamic, simple structure and no electromagnetic interference features that are useful in many industrial, medical, robotic and automotive applications. The USM, however has nonlinear characteristics and dead-zone problems due to increasing temperature and motor drive issues under various operating conditions. To overcome these problems a recurrent fuzzy neural network controller (RFNNC) combined with a compensated controller with adjustable parameters and on line learning algorithm is presented in this paper. The proposed control scheme can take the nonlinearity into account and compensate for the USM dead-zone. The proposed control scheme provides robust performance against parameter variations. The experimental results demonstrate the effectiveness of the proposed USM control scheme.

Pages: 150 to 155

Copyright: Copyright (c) IARIA, 2015

Publication date: March 22, 2015

Published in: conference

ISSN: 2308-4197

ISBN: 978-1-61208-390-2

Location: Nice, France

Dates: from March 22, 2015 to March 27, 2015