Nonfragile l2-l∞ state estimation for discrete-time neural networks with jumping saturations

被引：15
作者：
Xu, Yong [1 ,2 ]
Lu, Renquan [1 ,2 ]
Tao, Jie [3 ]
Peng, Hui [4 ]
Xie, Kan [1 ,2 ]
机构：
[1] Guangdong Univ Technol, Sch Automat, Guangzhou 510006, Guangdong, Peoples R China
[2] Guangdong Key Lab IoT Informat Proc, Guangzhou 510006, Guangdong, Peoples R China
[3] Zhejiang Univ, Inst Cyber Syst & Control, State Key Lab Ind Control Technol, Hangzhou 310027, Zhejiang, Peoples R China
[4] Hangzhou Dianzi Univ, Inst Informat & Control, Key Lab IoT & Informat Fus Technol Zhejiang, Hangzhou 310018, Zhejiang, Peoples R China
来源：
NEUROCOMPUTING | 2016年 / 207卷
基金：
中国国家自然科学基金;
关键词：
Neural networks; Nonfragile estimator; l(2)-l(infinity) performance; Markov jump systems; Sensor saturation; OCCURRING SENSOR SATURATIONS; STABILITY ANALYSIS; INFINITY CONTROL; DELAY SYSTEMS; DESIGN; L-2;
D O I：
10.1016/j.neucom.2016.04.002
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In this paper, the nonfragile l(2)-l(infinity) state estimation problem is investigated for the neural networks with sensor saturations. In order to model the phenomenon that the sensor saturation varies with the environment, a multi-saturation model is proposed and a homogenous Markov chain is introduced to describe the variation. The nonfragile state estimator which can be used to improve the robustness of the estimator with randomly occurring uncertainty is introduced. Sufficient conditions are established to ensure that the estimation error system is stochastically stable and satisfies l(2)-l(infinity) performance, the estimator gains are derived via solving the linear matrix inequalities. Finally, an example is provided to illustrate the effectiveness of the proposed new design techniques. (C) 2016 Published by Elsevier B.V.
引用
收藏
页码：15 / 21
页数：7
相关论文
共 50 条
[31]   Non-fragile finite-time l2 - l∞ state estimation for discrete-time neural networks with semi-Markovian switching and random sensor delays based on Abel lemma approach [J].
Rakkiyappan, R. ;
Maheswari, K. ;
Sivaranjani, K. ;
Joo, Young Hoon .
NONLINEAR ANALYSIS-HYBRID SYSTEMS, 2018, 29 :283-302
[32]   Mean square exponential stability with l2-l∞ gain of discrete-time switched-Markovian jump systems [J].
Hou, Linlin ;
Cui, Shanshan ;
Zhang, Yulu ;
Sun, Haibin ;
Wang, Ruihua .
TRANSACTIONS OF THE INSTITUTE OF MEASUREMENT AND CONTROL, 2024, 46 (15) :2971-2983
[33]   Robust L2-L∞ Filtering for Uncertain Neutral Stochastic System with Markovian Jumping Parameters and Time Delay [J].
Tan, Huasheng ;
Hua, Mingang .
2014 14TH INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION AND SYSTEMS (ICCAS 2014), 2014, :1284-1289
[34]   Robust reduced-order l2-l∞ filtering for network-based discrete-time linear systems [J].
Zhang, Zhuo ;
Zhang, Zexu ;
Yang, Shichun .
SIGNAL PROCESSING, 2015, 109 :110-118
[35]   State estimation for jumping recurrent neural networks with discrete and distributed delays [J].
Wang, Zidong ;
Liu, Yurong ;
Liu, Xiaohui .
NEURAL NETWORKS, 2009, 22 (01) :41-48
[36]   Observer-based finite-time exponential l2-l∞ control for discrete-time switched delay systems with uncertainties [J].
Hou, Linlin ;
Zong, Guangdeng ;
Wu, Yuqiang .
TRANSACTIONS OF THE INSTITUTE OF MEASUREMENT AND CONTROL, 2013, 35 (03) :310-320
[37]   l2-l∞ State Estimation for Persistent Dwell-Time Switched Coupled Networks Subject to Round-Robin Protocol [J].
Shen, Hao ;
Xing, Mengping ;
Wu, Zhengguang ;
Cao, Jinde ;
Huang, Tingwen .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 32 (05) :2002-2014
[38]   Exponential L2-L∞ filtering for distributed delay systems with Markovian jumping parameters [J].
Zhang, Baoyong ;
Li, Yongmin .
SIGNAL PROCESSING, 2013, 93 (01) :206-216
[39]   A new result on L2–L∞ performance state estimation of neural networks with time-varying delay: A new result on L2–L∞ performance state estimation of neural networks with time-varying delay [J].
Tan G. ;
Wang J. ;
Wang Z. .
Neurocomputing, 2021, 398 :166-171
[40]   Robust state estimation for discrete-time BAM neural networks with time-varying delay [J].
Arunkumar, A. ;
Sakthivel, R. ;
Mathiyalagan, K. ;
Anthoni, S. Marshal .
NEUROCOMPUTING, 2014, 131 :171-178
12345