Abstract

A novel decentralized neural network (DNN) controller is proposed for a class of large-scale nonlinear systems with unknown interconnections. The objective is to design a DNN for a class of large-scale systems which do not satisfy the matching condition requirement. The NNs are used to approximate the unknown subsystem dynamics and the interconnections. The DNN is designed using the back stepping methodology with only local signals for feedback. All of the signals in the closed loop (system states and weights estimation errors) are guaranteed to be uniformly ultimately bounded and eventually converge to a compact set.

Meeting Name

43rd IEEE Conference on Design and Control (2004: Dec. 14-17, The Bahamas)

Department(s)

Electrical and Computer Engineering

Second Department

Computer Science

Sponsor(s)

National Science Foundation (U.S.)

Keywords and Phrases

Adaptive Neural Network Control; Backstepping; Decentralized Control; Neural Networks

International Standard Serial Number (ISSN)

0191-2216

Document Type

Article - Conference proceedings

Document Version

Final Version

File Type

text

Language(s)

English

Rights

© 2004 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.

Full Text Link

Share

 
COinS