基于线性矩阵不等式的不确定延迟神经网络鲁棒稳定性分析

LMI-Based Robust Stability Analysis for Uncertain Delayed Neural Networks

论文研究了时变时滞的不确定延迟神经网络的鲁棒稳定性问题。系统矩阵中包含范数有界不确定性。去掉了时变延迟的导数约束,这意味着利用一种快速时变延迟是允许的。利用Lyapunov-Krasovskii函数和线性矩阵不等式(LMI)的方法,提出一些新的时滞及时滞导数相关的稳定性准则。通过给出一个数值例子,来阐述文中所提方法的有效性和创新性。

The problem of robust stability for uncertain neural networks with time-varying delays was investigated.The norm-bounded uncertainties are included in the system matrices.The constraint on time-varying delays is removed,which means that a fast time-varying delay is admissible.Some new stability criteria which are correlated with time delays and its derivatives were presented by using Lyapunov-Krasovskii function and linear matrix ineguality（LMI） approaches.A numerical example was given to illustrate the effectiveness and less conservative of the developed techniques.