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.
W. Liu et al., "Decentralized Neural Network Control of a Class of Large-Scale Systems with Unknown Interconnection," Proceedings of the 43rd IEEE Conference on Decision and Control (2004, The Bahamas), vol. 5, pp. 4972-4977, Institute of Electrical and Electronics Engineers (IEEE), Jan 2004.
The definitive version is available at https://doi.org/10.1109/CDC.2004.1429594
43rd IEEE Conference on Design and Control (2004: Dec. 14-17, The Bahamas)
Electrical and Computer Engineering
National Science Foundation (U.S.)
Keywords and Phrases
Adaptive Neural Network Control; Backstepping; Decentralized Control; Neural Networks
International Standard Serial Number (ISSN)
Article - Conference proceedings
© 2004 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.
01 Jan 2004