Yang Rongni, Zhang Zexu, Shi Peng
Space Control and Inertial Technology Research Center, Department of Control Science and Engineering, Harbin Institute of Technology, Harbin 150001, China.
IEEE Trans Neural Netw. 2010 Jan;21(1):169-75. doi: 10.1109/TNN.2009.2036610. Epub 2009 Dec 8.
This brief addresses the stability analysis problem for stochastic neural networks (SNNs) with discrete interval and distributed time-varying delays. The interval time-varying delay is assumed to satisfy 0 < d(1) <or= d(t) <or= d(2) and is described as d(t) = d(1)+h(t) with 0 <or= h(t) <or= d(2)-d(1). Based on the idea of partitioning the lower bound d(1), new delay-dependent stability criteria are presented by constructing a novel Lyapunov-Krasovskii functional, which can guarantee the new stability conditions to be less conservative than those in the literature. The obtained results are formulated in the form of linear matrix inequalities (LMIs). Numerical examples are provided to illustrate the effectiveness and less conservatism of the developed results.
本文研究了具有离散区间和分布时变延迟的随机神经网络（SNNs）的稳定性分析问题。假设区间时变延迟满足(0 < d(1) \leq d(t) \leq d(2))，并描述为(d(t) = d(1) + h(t))，其中(0 \leq h(t) \leq d(2) - d(1))。基于划分下界(d(1))的思想，通过构造一个新颖的Lyapunov-Krasovskii泛函，提出了新的依赖延迟的稳定性准则，这可以保证新的稳定性条件比文献中的条件保守性更低。所得结果以线性矩阵不等式（LMIs）的形式给出。提供了数值例子来说明所得到结果的有效性和较低的保守性。
