Delay-dependent exponential stability analysis of bi-directional associative memory neural networks with time delay: an LMI approach
Delay-dependent exponential stability analysis of bi-directional associative memory neural networks with time delay: an LMI approach
复制标题
DOI：
10.1016/j.chaos.2004.09.052
复制
发表时间：
2005-05
影响因子：
7.8
通讯作者：
Chuandong Li;X. Liao;Rong Zhang
中科院分区：
文献类型：
--
作者：
Chuandong Li;X. Liao;Rong Zhang
针对具有不同常时延和时变时延的双向联想记忆神经网络，研究了其指数稳定性的确定和指数收敛率的估计问题。采用Lyapunov-Krasovskii泛函与线性矩阵不等式（LMI）相结合的方法研究了该问题，给出了互连矩阵和激活函数的界，从而保证了系统的指数稳定性。给出了指数稳定性的一些判据，给出了时滞相关性质的信息。本文的结果为确定延迟BAM （DBAM）神经网络的指数稳定性提供了一套易于验证的准则，它比目前文献报道的保守性和限制性更小。给出了一些典型的例子来说明本文所得准则的应用。
For bi-directional associative memory (BAM) neural networks (NNs) with different constant or time-varying delays, the problems of determining the exponential stability and estimating the exponential convergence rate are investigated in this paper. An approach combining the Lyapunov–Krasovskii functional with the linear matrix inequality (LMI) is taken to study the problems, which provide bounds on the interconnection matrix and the activation functions, so as to guarantee the system’s exponential stability. Some criteria for the exponential stability, which give information on the delay-dependent property, are derived. The results obtained in this paper provide one more set of easily verified guidelines for determining the exponential stability of delayed BAM (DBAM) neural networks, which are less conservative and less restrictive than the ones reported so far in the literature. Some typical examples are presented to show the application of the criteria obtained in this paper.