基于LMI方法的时滞细胞神经网络稳定性分析

神经网络是一个复杂的大规模非线性系统，而时滞神经网络的动态行为更为丰富和复杂．现有的研究时滞神经网络稳定性的方法中最为流行的是Lyapunov方法．它把稳定性问题变为某些适当地定义在系统轨迹上的泛函，通过这些泛函相应的稳定性条件就可以获得．该文得到了时滞细胞神经网络渐近稳定性的一些充分条件．作者利用了泛函微分方程的Lyapunov—Krasovskii稳定性理论和线性矩阵不等式(LMI)方法，精炼和推广了一些已有的结果．它们比目前文献报道的结果更少保守．该文还给出了确定时滞细胞神经网络稳定性更多的判定准则．

Stability Analysis for Delayed Cellular Neural Networks Based on Linear Matrix Inequality Approach

This paper derives some sufficient conditions for asymptotic stability of cellular neural networks with time delays. The Lyapunov Krasovskii Stability theory for functional differential equations and linear matrix inequality (LMI) approach are employed to investigate the problem. It shows how some well known results can be refined and generalized in a straightforward manner. For the time delays, the stability criteria are delay independent. The results obtained in this paper are less conservative than the ones reported so far in the literature and provide one more set of criteria for determining the stability of delayed cellular neural networks.