Motion control with deadzone estimation and compensation using GRNN for TWUSM drive system

Authors:
Tien-Chi Chen;Chih-Hsien Yu
Affiliations:
Department of Electrical Engineering, Kun Shan University, Tainan, Taiwan, ROC;Department of Engineering Science, National Cheng Kung University, No. 1, University Road, Tainan 701, Taiwan, ROC
Venue:
Expert Systems with Applications: An International Journal
Year:
2009

Citing 5
Cited 3

Robust adaptive control of a class of nonlinear systems with unknown dead-zone

Automatica (Journal of IFAC)
Application of radial basis function and generalized regression neural networks in non-linear utility function specification for travel mode choice modelling

Mathematical and Computer Modelling: An International Journal
A general regression neural network

IEEE Transactions on Neural Networks
Learning and convergence analysis of neural-type structured networks

IEEE Transactions on Neural Networks
Neural network control of a class of nonlinear systems with actuator saturation

IEEE Transactions on Neural Networks

Adaptive fuzzy model based inverse controller design using BB-BC optimization algorithm

Expert Systems with Applications: An International Journal
Neural observer-based adaptive compensation control for nonlinear time-varying delays systems with input constraints

Expert Systems with Applications: An International Journal
A hybrid annual power load forecasting model based on generalized regression neural network with fruit fly optimization algorithm

Knowledge-Based Systems

Quantified Score

Hi-index	12.05

Visualization

Abstract

The traveling wave ultrasonic motor (TWUSM) drive has a strong nonlinearity, which varies with driving conditions and possesses variable deadzone in the control input associated with the phase difference of applied two-phase AC driving voltages. This deadzone is a problem as an accurate positioning actuator for industrial application, and it is important to eliminate the deadzone in order to improve the control performance. To overcome the above problems, a new motion control scheme with deadzone estimation and compensation using generalized regression neural network (GRNN) is proposed in this paper to improve the control performance of the TWUSM drive system. One of them is to approach the nonlinearity deadzone part of the TWUSM drive system, and another one with extension form is to approach the inverse of nonlinearity deadzone to realize the dynamic compensation. Once the nonlinearity of deadzone is compensated exactly by its inverse compensation, the whole TWUSM drive system can be treated as linear, and the estimated parameters of the linear system can be adopted to design a controller for a desired reference command.