Robust Exponential Stability Analysis of Switched Neural Networks with Interval Parameter Uncertainties and Time Delays

In this paper, the stability of switched neural networks (SNNs) with interval parameter uncertainties and time delays is investigated. First, the conditions for the existence and uniqueness of the equilibrium point of the system are discussed. Second, the average dwell time approach and M-matrix pro...

Full description

Saved in:
Bibliographic Details
Published in:Complexity (New York, N.Y.) N.Y.), 2018-01, Vol.2018 (2018), p.1-16
Main Authors: Zhang, Jiye, Peng, Yiqiang, Xue, Huanbin, Xu, Xiaohui
Format: Article
Language:English
Subjects:
Analysis
Automation
Commonality
Control theory
Dwell time
Dynamical systems
Liapunov functions
Neural networks
Parameter uncertainty
Robustness (mathematics)
Stability analysis
Switching theory
Systems science
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 stability of switched neural networks (SNNs) with interval parameter uncertainties and time delays is investigated. First, the conditions for the existence and uniqueness of the equilibrium point of the system are discussed. Second, the average dwell time approach and M-matrix property are employed to obtain conditions to ensure the globally exponential stability of the delayed SNNs under constrained switching. Third, by resorting to inequality technique and the idea of vector Lyapunov function, sufficient condition to ensure the robust exponential stability of the delayed SNNs under arbitrary switching is derived. The form of the constructed Lyapunov functions is simple, which has certain commonality in studying delayed SNNs, and the proposed results not only are explicit but also reveal the relationship between the constrained switching and the arbitrary switching of the SNNs. Finally, two numerical examples are presented to illustrate the effectiveness and less conservativeness of the main results compared with the existing literature.
ISSN:1076-2787
1099-0526
DOI:10.1155/2018/6318986