变时滞神经网络的时滞相关指数稳定性判据  

Criterion of delay-dependent exponential stability of neural networks with time-varying delays

作　　者：孔宪明[1] 马晓燕[1] 鞠培军[1] 

机构地区：[1]泰山学院数学与系统科学学院,山东泰安271021

出　　处：《兰州理工大学学报》2010年第4期152-155,共4页Journal of Lanzhou University of Technology

基　　金：山东省教育厅科研发展计划项目(J06P55;J07WJ23)

摘　　要：研究其具有变时滞的神经网络的时滞相关指数稳定性问题.利用Lyapunov-Krasovskii泛函和自由权矩阵方法,提出此类神经网络有唯一稳定点和全局指数稳定的充分条件.不要求激活函数的单调递增性和时滞导数小于1,具有较弱的保守性.通过算例验证所给方法的正确性.The problem of delay-dependent exponential stability of neural networks with time-varying delays was investigated.It was proposed that for this kind of neural networks there were sufficient conditions of existence of a unique equilibrium point and global exponential stability,by using Lyapunov-Krasovskii functional and free weighting matrices method.It was not required that the activation functions should be monotonic,and the derivative of the time-varying delay function should be less than unit so that there was less conservativeness.An example was given to demonstrate the validity of the method proposed.

关 键 词：神经网络 时变时滞系统 全局指数稳定 自由权矩阵 

分 类 号：O231.2[理学—运筹学与控制论]