State estimation of neural networks with time-varying delays and Markovian jumping parameter based on passivity theory

In this paper, the state estimation problem is investigated for neural networks with time-varying delays and Markovian jumping parameter based on passivity theory. The neural networks have a finite number of modes and the modes may jump from one to another according to a Markov chain. The main purpo...

Full description

Saved in:
Bibliographic Details
Published in:Nonlinear dynamics 2012-10, Vol.70 (2), p.1421-1434
Main Authors: Lakshmanan, S., Park, Ju H., Ji, D. H., Jung, H. Y., Nagamani, G.
Format: Article
Language:English
Subjects:
Automotive Engineering
Classical Mechanics
Control
Dynamical Systems
Engineering
Jumping
Linear matrix inequalities
Markov analysis
Markov chains
Matrix methods
Mechanical Engineering
Neural networks
Original Paper
Parameters
Passivity
State estimation
Vibration
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, the state estimation problem is investigated for neural networks with time-varying delays and Markovian jumping parameter based on passivity theory. The neural networks have a finite number of modes and the modes may jump from one to another according to a Markov chain. The main purpose is to estimate the neuron states, through available output measurements such that for all admissible time-delays, the dynamics of the estimation error is globally stable in the mean square and passive from the control input to the output error. Based on the new Lyapunov–Krasovskii functional and passivity theory, delay-dependent conditions are obtained in terms of linear matrix inequalities (LMIs). Finally, a numerical example is provided to demonstrate effectiveness of the proposed method and results.
ISSN:0924-090X
1573-269X
DOI:10.1007/s11071-012-0544-6