文献类型：期刊文献

英文题名：Distributed reliable L2 - L∞ state estimation for discrete-time delayed neural networks with missing measurements

作者：Zhang, Hao[1,2]; Yan, Huaicheng[1,2]; Wang, Mengling[1,2]; Shi, Hongbo[1,2]

机构：[1] Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education, Shanghai, 200237, China; [2] School of Information Science and Engineering, East China University of Science and Technology, Shanghai, 200237, China

年份：2016

卷号：2016-September

起止页码：53

外文期刊名：Proceedings of the World Congress on Intelligent Control and Automation (WCICA)

收录：EI(收录号：20164302935168)

语种：英文

外文关键词：Uncertainty analysis - Stochastic systems - Linear matrix inequalities - Neural networks - Time delay

摘要：This paper is concerned with the distributed L2 - L∞ state estimation for discrete-time delayed neural networks with missing measurements and sensor failures. The model of neural networks is constructed by the combination with nonlinear functions and state space expressions. Time-varying delays are assumed to have the lower bounds and the upper bounds, and the missing measurements and the sensor failures are described by a stochastic Bernoulli distributed variable and uncertainties, respectively. By using a distributed network, Kronecker product, linear matrix inequalities(LMIs) technology and the solving optimization problems, a sufficient condition is derived to ensure that the filtering error system is stochastically asymptotically stable and achieves the optimal L2 - L∞ performance. Finally, a simulation example is given to demonstrate the effectiveness of the proposed method. ? 2016 IEEE.