Exponential H∞ State Estimation for Memristive Neural Networks: Vector Optimization Approach

This article presents the theoretical results on the H_\infty state estimation problem for a class of discrete-time memristive neural networks. By utilizing a Lyapunov-Krasovskii functional, sufficient conditions are derived to guarantee that the error system is exponentially mean-square stable; s...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transaction on neural networks and learning systems 2021-11, Vol.32 (11), p.5061-5071
Main Authors: Li, Ruoxia, Cao, Jinde
Format: Article
Language:English
Subjects:
Attenuation
Discrete-time
Discrete-time systems
Disturbance
exponential mean-square stability
Neural networks
Optimization
State estimation
vector optimization
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:This article presents the theoretical results on the H_\infty state estimation problem for a class of discrete-time memristive neural networks. By utilizing a Lyapunov-Krasovskii functional, sufficient conditions are derived to guarantee that the error system is exponentially mean-square stable; subsequently, the prespecified H_\infty disturbance rejection attenuation level is also guaranteed. It should be noted that the vector optimization method is employed to find the maximum bound of function and the minimum disturbance turning simultaneously. Finally, the corresponding simulation results are included to show the effectiveness of the proposed methodology.
ISSN:2162-237X
2162-2388
DOI:10.1109/TNNLS.2020.3026707