Global robust stability for delayed neural networks with polytopic type uncertainties
Global robust stability for delayed neural networks with polytopic type uncertainties
复制标题
DOI：
10.1016/j.chaos.2005.04.005
复制
发表时间：
2005-12
影响因子：
7.8
通讯作者：
Yong He;Qing‐Guo Wang;W. Zheng
中科院分区：
文献类型：
--
作者：
Yong He;Qing‐Guo Wang;W. Zheng
研究了时滞神经网络的全局鲁棒稳定性问题。首先用自由权矩阵来表示系统方程中各项之间的关系，并利用S-过程导出了时滞神经网络的稳定性条件。然后将这一结果推广到具有多面体型不确定性的时滞神经网络的全局鲁棒稳定性判据。研究了[IEEE Trans Circuits Syst II 52（2005）33-36]中给出的区间延迟神经网络的一个数值例子。证明了所提出的全局鲁棒稳定性判据的有效性及其对已有结果的改进。
In this paper, global robust stability for delayed neural networks is studied. First the free-weighting matrices are employed to express the relationship between the terms in the system equation, and a stability condition for delayed neural networks is derived by using the S-procedure. Then this result is extended to establish a global robust stability criterion for delayed neural networks with polytopic type uncertainties. A numerical example given in [IEEE Trans Circuits Syst II 52 (2005) 33–36] for interval delayed neural networks is investigated. The effectiveness of the presented global robust stability criterion and its improvement over the existing results are demonstrated.