Hermite-neural-network-based adaptive control for a coupled nonlinear chaotic system

doi:10.1007/s00521-012-1154-4

機構典藏 > College of Engineering > Graduate Institute & Department of Electrical Engineering > Journal Article > Item 987654321/91652

Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/91652

Title:	Hermite-neural-network-based adaptive control for a coupled nonlinear chaotic system
Authors:	Hsu, Chun-Fei
Contributors:	淡江大學電機工程學系
Keywords:	Hermite neural network;Adaptive control;Neural control;Coupled chaotic system;Synchronization
Date:	2012-09-14
Issue Date:	2013-07-23 21:49:29 (UTC+8)
Publisher:	London: Springer UK
Abstract:	A TSK-type Hermite neural network (THNN) is studied in this paper. Since the output weights of the THNN use a functional-type form, it provides powerful representation, high learning performance and good generalization capability. Then, a Hermite-neural-network-based adaptive control (HNNAC) system which is composed of a neural controller and a robust compensator is proposed. The neural controller utilizes a THNN to online approximate an ideal controller, and the robust compensator is designed to eliminate the effect of the approximation error introduced by the neural controller upon the system stability. Moreover, a proportional-integral (PI)-type learning algorithm is derived to speed up the convergence of the tracking error. Finally, the proposed HNNAC system is applied to synchronize a coupled nonlinear chaotic system. In the simulation study, it shows that the proposed HNNAC system can achieve favorable synchronization performance without requiring a preliminary offline tuning.
Relation:	Neural Computing and Applications 22, pp.421-433
DOI:	10.1007/s00521-012-1154-4
Appears in Collections:	[Graduate Institute & Department of Electrical Engineering] Journal Article

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	314	View/Open

Loading...