不确定区间时滞Markov跳变BAM神经网络的鲁棒指数稳定性  

Robust exponential stability for uncertain BAM neural networks with Markovian jump parameters and interval-time-varying delays

作　　者：邢军[1] 殷丽文[2] 焦明华[3] 

机构地区：[1]辽宁科技大学理学院,辽宁鞍山114051 [2]吉林石化公司乙烯厂,吉林吉林132022 [3]山东济宁模具厂,山东济宁272400

出　　处：《辽宁科技大学学报》2010年第2期113-120,共8页Journal of University of Science and Technology Liaoning

摘　　要：讨论了具有不确定区间时滞的BAM神经网络的鲁棒均方指数稳定性问题。通过构造适当的Lya-punov-Krasovskii泛函,利用一些新的定界技术,以线性矩阵不等式形式给出了Markov跳变BAM神经网络的时滞且区间相关的全局鲁棒指数稳定性判据,该判据利用Matlab的LMI工具很容易进行检验。给出数值示例,说明了判据的有效性与优越性。The problem of robust exponential stability in the mean square for uncertain bidirectional associative memory（BAM） neural networks with Markovian jump parameters and time-varying delays is investigated.The time-varying delay is assumed to belong to an interval.By defining an appropriate Lyapunov-Krasovskii functional（LKF） and using some new bounding techniques,some delay-range-dependent stabilitycriteria are presented in terms of linear matrix inequalities（LMIs）,which can be solved efficiently by using existing LMI toolbox in MATLAB.A umerical example demonstrates the effectiveness and advantage of criterion.

关 键 词：鲁棒指数稳定 双向联想记忆神经网络 线性矩阵不等式 时滞区间相关 

分 类 号：TP202[自动化与计算机技术—检测技术与自动化装置]