Title :
Adaptive optimal control of a class of uncertain nonlinear systems using fuzzy logic and neural networks
Author :
Chen, Dingguo ; Yang, Jiaben ; Xu, Bowen
Author_Institution :
Siemens Power Transmission & Distribution Inc., MN, USA
Abstract :
A study on the synthesis of neural network and fuzzy logic based controllers for optimally controlling uncertain nonlinear systems linear in control is presented in this paper. Three different kinds of hierarchical controller architectures are proposed, which include a hierarchical neuro-fuzzy controller architecture, a hierarchical fuzzy-neuro controller architecture, and a hierarchical fuzzy logic controller architecture. This study concludes that the proposed neural-network and fuzzy logic based control schemes are useful for nonlinear system applications. It first shows that fuzzy controllers, besides neural controllers, can be synthesized to approximately identify the switching manifold for optimal control. It then shows that the neuro-fuzzy controller, fuzzy-neuro controller, and hierarchical fuzzy controller can deal with system parametric uncertainties. Further, the adaptive neuro-fuzzy controllers, fuzzy-neuro controllers, and hierarchical fuzzy controllers are developed to deal with systems with time varying parametric uncertainties.
Keywords :
adaptive control; fuzzy control; fuzzy logic; hierarchical systems; neurocontrollers; nonlinear control systems; optimal control; uncertain systems; adaptive optimal control; fuzzy logic; hierarchical fuzzy logic controller architecture; hierarchical fuzzy-neuro controller architecture; hierarchical neuro-fuzzy controller architecture; neural networks; switching manifold; system parametric uncertainties; time varying parametric uncertainties; uncertain nonlinear systems; Adaptive control; Control system synthesis; Control systems; Fuzzy control; Fuzzy logic; Neural networks; Nonlinear control systems; Nonlinear systems; Optimal control; Programmable control;
Conference_Titel :
Decision and Control, 2004. CDC. 43rd IEEE Conference on
Print_ISBN :
0-7803-8682-5
DOI :
10.1109/CDC.2004.1429615