基于改进自由权矩阵方法的神经网络时滞相关稳定性分析  

Further Improvement of Free-weighting Matrix Approach for the Stability Analysis of Neural Networks with Time-varying Delay

作　　者：刘芳[1] 吴敏[1] 何勇[1] 

机构地区：[1]中南大学信息科学与工程学院,湖南长沙410083

出　　处：《计算技术与自动化》2008年第1期1-5,87,共6页Computing Technology and Automation

基　　金：国家博士点基金项目(20050533015);国家杰出青年科学基金项目(60425310);国家自然科学基金项目(60574014);教育部新世纪优秀人才支持计划(NCET-06-0679)

摘　　要：针对具有不确定参数的时变时滞神经网络系统,利用改进的自由权矩阵方法,研究其时滞相关稳定性问题。通过考虑时变时滞及其上界和它们的差三者之间关系,同时保留Lyapunov-Krasovskii泛函导数中的有用项,得到具有更低保守性的基于线性矩阵不等式的神经网络系统时滞相关渐近稳定的充分条件。最后,数值例子表明该方法的有效性。This paper investigates the stability problem of uncertain neural networks with time- varying delay by employing a further improved fre.e- weighting matrix approach, The relationship among the time - varying delay, its upper bound and their difference is taken into account. As a result, an less conservative LMI - based delay - dependent asymptotic stability criterion is obtained without ignoring any useful terms in the derivative of Lyapunov- Krasovskii functional. Finally, numerical examples are given to demonstrate the effectiveness and the merits of the proposed methods.

关 键 词：神经网络 自由权矩阵 时变时滞 渐近稳定 线性矩阵不等式(LMI) 

分 类 号：TP202.1[自动化与计算机技术—检测技术与自动化装置]