Finite-time stability analysis for neutral-type neural networks with hybrid time-varying delays without using Lyapunov method
Finite-time stability analysis for neutral-type neural networks with hybrid time-varying delays without using Lyapunov method
复制标题
不使用李亚普诺夫方法的混合时变时滞中性型神经网络有限时间稳定性分析
DOI：
10.1016/j.neucom.2017.01.037
复制
发表时间：
2017
期刊：
影响因子：
6
通讯作者：
Li LX
中科院分区：
文献类型：
--
作者：
Zheng Mingwen;Xiao Jinghua;Zhao Hui;Zheng Mingwen;Li Lixiang;Peng Haipeng;Xiao Jinghua;Li LX
本文研究了具有各种混合时变时滞的中立型神经网络的有限时间稳定性问题。这些时延包括一般时变时延、有限分布时变时延、中立型时变时延和无限分布时变时延。在有限时间稳定性定义的基础上，代替Lyapunov函数方法，借助不等式技术，导出了保证网络模型有限时间稳定性的一些简单新颖的充分条件。演绎过程简单易懂。最后给出了三个仿真算例，验证了主要结果的有效性。
In this paper, we study the finite-time stability problem of neutral-type neural networks with various hybrid time-varying delays. These delays include general time-varying delays, finite distributed time-varying delays, neutral-type time-varying delays and infinite distributed time-varying delays. Based on the definition of finite-time stability instead of Lyapunov function method, with the aid of inequality techniques, some simple and novel sufficient conditions are derived to guarantee the finite-time stability of our proposed network model. The deduction process is simple and easy to understand. Finally, three simulation examples are given to show the effectiveness of our main results.