摘要
利用自由权值矩阵和不等式分析技巧,研究了一类不确定时滞BAM神经网络的鲁棒稳定性问题。通过构造适当的Lya-punov泛函,对于所有允许的不确定性,以线性矩阵不等式形式给出了时滞BAM神经网络的全局鲁棒稳定性判据,该判据能够利用Matlab的LMI工具箱很容易地进行检验。此外,仿真示例进一步证明了判据的有效性。
By free-weighting matrices and combining the method of inequality analysis,the problem of robust stability of a class of uncertain BAM neural networks with time-varying delays is investigated.Based on Lyapunov-Krasovskii functional,some new stability criteria are presented in terms of Linear Matrix Inequalities(LMIs) to guarantee the delayed BAM neural networks to be robustly stable for all admissible uncertainties.A numerical example is given to demonstrate the usefulness of the proposed robust stability criteria.
出处
《计算机工程与应用》
CSCD
北大核心
2009年第8期36-38,共3页
Computer Engineering and Applications
基金
重庆市自然科学基金No.2006BB2254
重庆市教委科学技术项目No.081501~~
关键词
鲁棒稳定性
不确定双向联想记忆神经网络
变时滞
线性矩阵不等式
robust stability
uncertain Bidirectional Associative Memory(BAM) neural networks
time-varying delays
Linear Matrix Inequalities(LMIs)