Receding Horizon Stabilization and Disturbance Attenuation for Neural Networks With Time-Varying Delay

Author

Choon Ki Ahn ; Peng Shi ; Ligang Wu

Author_Institution

Sch. of Electr. Eng., Korea Univ., Seoul, South Korea

Volume

45

Issue

12

fYear

2015

Firstpage

2680

Lastpage

2692

Abstract

This paper is concerned with the problems of receding horizon stabilization and disturbance attenuation for neural networks with time-varying delay. New delay-dependent conditions on the terminal weighting matrices of a new finite horizon cost functional for receding horizon stabilization are established for neural networks with time-varying or time-invariant delays using single- and double-integral Wirtinger-type inequalities. Based on the results, delay-dependent sufficient conditions for the receding horizon disturbance attenuation are given to guarantee the infinite horizon H_∞ performance of neural networks with time-varying or time-invariant delays. Three numerical examples are provided to illustrate the effectiveness of the proposed approach.

Keywords

H^∞ control; delay systems; infinite horizon; integral equations; neurocontrollers; stability; time-varying systems; delay-dependent condition; delay-dependent sufficient condition; double-integral Wirtinger-type inequalities; finite horizon cost functional; infinite horizon H∞ performance; neural network; receding horizon disturbance attenuation; receding horizon stabilization; single-integral Wirtinger-type inequalities; terminal weighting matrices; time-invariant delay; time-varying delay; Attenuation; Biological neural networks; Delay effects; Delays; Linear matrix inequalities; Symmetric matrices; Cost functional; disturbance attenuation; neural network; receding horizon stabilization; time delay;

fLanguage

English

Journal_Title

Cybernetics, IEEE Transactions on

Publisher

ieee

ISSN

2168-2267

Type

jour

DOI

10.1109/TCYB.2014.2381604

Filename

6999917