随机马尔科夫跳变时滞神经网络的状态估计

State Estimation for Stochastic Neural Networks with Markov Jump and Distributed Delays

研究了一类具有离散和分布时滞的随机马尔科夫跳变神经网络的状态估计问题。基于伊藤引理、Lyapunov-Krasovskii泛函等理论,通过积分不等式方法得到时滞神经网络全局渐近均方稳定条件,再以线性矩阵不等式为求解工具,设计出状态估计器,最后通过数值例子对所提方法的有效性进行验证。

This paper considers the issue of state estimation for stochastic Markov jump neural networks with both discrete and distributed delays. Based on the It lemma and Lyapunov-Krasovskii functional,and through integral inequality,it finds the neural networks with delays sufficient conditions for asymptotic mean square stability. And then designs a state estimator by using linear matrix inequalities. Finally,a numerical example verifies the effectiveness of the proposed method.