Adjustable delay interval method based stochastic robust stability analysis of delayed neural networks

详细信息    查看全文

• 作者：Qihe Shan^a ; ^{shanqihe@gmail.com}Author Vitae ; Huaguang Zhang^a ; ^b ; ^{hgzhang@ieee.org}Author Vitae ; Zhanshan Wang^a ; ^{wangzhanshan@ise.neu.edu.cn}Author Vitae ; Junyi Wang^a ; ^{wjyi168@126.com}Author Vitae
• 关键词：Adjustable delay interval ; Stability ; Neural networks ; Delay ; Generalized Finsler lemma
• 刊名：Neurocomputing
• 出版年：2017
• 出版时间：5 January 2017
• 年：2017
• 卷：219
• 期：Complete
• 页码：389-395
• 全文大小：849 K
• 卷排序：219

文摘

The issue of mean-square exponential (MSE) stability of stochastic delayed neural networks (NNs) with parametric uncertainties is considered in this paper. An adjustable delay interval (ADI) method is proposed to construct a novel Lyapunov-Krasovskii functional (LKF). This method relaxes the restriction on fixed upper and lower bounds of the delay intervals. Combining with the generalized Finsler lemma, ADI method leads to a much less conservative delay-dependent stability criterion based on linear matrix inequality (LMI) for concerned system. Some simulations are described to show the usefulness of the proposed approach.