具时滞离散递归神经网络稳定性分析的一种延迟剖分方法

Delay-Partitioning Approach to the Stability Analysis of Discrete-Time Recurrent Neural Networks with Time-Varying Delays

运用延迟剖分的方法,研究了一类具有时滞的非线性离散递归神经网络平衡点的渐进稳定性问题。结合Laypunov-Krasovskii稳定性理论和线性矩阵不等式方法,得到了具时滞非线性离散递归神经网络模型在平衡点渐进稳定的条件;考虑了延迟下界为零时的神经网络在平衡点的稳定性条件。数值仿真验证了结果的有效性。

By utilizing the delay partitioning idea, this paper studies the asymptotic stability of the equilibrium point for a class of discrete-time recurrent neural networks with time-varying delays. The Laypunov-Krasovskii stability theory is applied and combined with liner matrix inequality, the conditions for asymptotic stability of discrete-time recurrent neural networks with time-varying delays are obtained. In addition, we considered the case where the lower bound of the delay is zero. A numerical example is presented to illustrate the effectiveness of the obtained results.