Title :
Neural networks for the adaptive control of nonlinear systems
Author :
Hills, Stacy J. ; Boye, A. John
Author_Institution :
US Naval Undersea Warfare Center, Newport, RI, USA
Abstract :
Neural networks are used in an indirect model reference adaptive control technique to identify, then control, a nonlinear system. First, a neural network is used to identify the system. Then, this identifier is used in place of the nonlinear system to adjust a neural network controller. The effect of model mismatch on system convergence and stability is explored. Examples include the well-known inverted pendulum problem. It is shown that for many cases this technique does a fairly good job of controlling the system
Keywords :
control system analysis; identification; model reference adaptive control systems; neural nets; nonlinear control systems; stability; identifier; indirect MRAC; model mismatch; model reference adaptive control; neural network; nonlinear systems; stability; system convergence; Adaptive control; Biological neural networks; Control system synthesis; Control systems; Cost function; Neural networks; Neurons; Nonlinear control systems; Nonlinear systems; Optimal control;
Conference_Titel :
Circuits and Systems, 1992., Proceedings of the 35th Midwest Symposium on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-0510-8
DOI :
10.1109/MWSCAS.1992.271168
