This paper investigates the exponential state estimation problem for competitive neural networks via stochastic sampled-data control with packet losses. Based on this strategy, a switched system model is used to describe packet dropouts for the error system. In addition, transmittal delays between neurons are also considered. Instead of the continuous measurement, the sampled measurement is used to estimate the neuron states, and a sampled-data estimator with probabilistic sampling in two sampling periods is proposed. Then the estimator is designed in terms of the solution to a set of linear matrix inequalities (LMIs), which can be solved by using available software. When the missing of control packet occurs, some sufficient conditions are obtained to guarantee that the exponentially stable of the error system by means of constructing an appropriate Lyapunov function and using the average dwell-time technique. Finally, a numerical example is given to show the effectiveness of the proposed method.

本文研究了具有丢包的随机采样数据控制下竞争神经网络的指数状态估计问题。基于此策略，使用交换系统模型来描述错误系统的数据包丢失。另外，还考虑了神经元之间的传递延迟。代替连续测量，采样的测量被用于估计神经元状态，并且提出了在两个采样周期中具有概率采样的采样数据估计器。然后，根据一组线性矩阵不等式（LMI）的解来设计估计器，可以使用可用的软件来解决。当控制数据包丢失时，通过构造适当的Lyapunov函数并使用平均驻留时间技术，可以获得一些足够的条件以保证误差系统的指数稳定。最后，通过数值例子说明了该方法的有效性。