Abstract

A partial state feedback based direct adaptive control scheme is developed using Orthonormal Activation Function based Neural Networks (OAFNN), for real time trajectory tracking control of a class of nonlinear systems. The OAFNNs are employed in the controller for feed-forward compensation of unknown system dynamics. The network weights are tuned on-line, in real time using Desired Compensation based Adaptive Laws (DCAL). The overall stability of the system and the neural networks is guaranteed using Lyapunov analysis and a modified integral version of projection algorithm. The developed neural controllers are evaluated experimentally and the experimental results support theoretical analysis.

Volume Subject Area:
Expert and Intelligent Sytems
Topics:
Control equipment, State feedback, Artificial neural networks, Adaptive control, Algorithms, Feedforward control, Nonlinear systems, Stability, System dynamics, Theoretical analysis, Tracking control, Trajectories (Physics)
This content is only available via PDF.
Copyright © 1997 by The American Society of Mechanical Engineers
You do not currently have access to this content.