Finite-time state estimation for jumping recurrent neural networks with deficient transition probabilities and linear fractional uncertainties

Finite-time state estimation for jumping recurrent neural networks with deficient transition probabilities and linear fractional uncertainties
复制标题

具有缺陷转移概率和线性分数不确定性的跳跃循环神经网络的有限时间状态估计

DOI:
10.1016/j.neucom.2017.04.039
复制
发表时间:
2017-10
期刊:
影响因子:
6
通讯作者:
Abdullah M. Dobaie
Abdullah M. Dobaie
中科院分区:
计算机科学2区
文献类型:
--
作者:
Yuqiang Luo;Baoye Song;Jinling Liang;Abdullah M. Dobaie

文献摘要

参考文献

被引文献

相似文献

研究了一类具有马尔可夫跳变参数的连续时间不确定递归神经网络估计问题的有限时间稳定性和有限时间有界性问题。不确定性参数用线性分式不确定性描述,跳变参数服从具有可能亏概率转移矩阵的齐次马尔可夫过程。构造了一个全阶状态估计器来估计神经元状态,在存在不确定和跳跃参数的情况下,使得状态估计的所得误差动态(i)在无干扰的情况下是有限时间稳定的;以及(ii)在测量上的外源干扰的情况下是有限时间有界的。利用李雅普诺夫稳定性理论和随机分析技术,建立了有限时间状态估计器存在的充分条件,并给出了有限时间状态估计器的显式表达式,证明了该状态估计器对于一个凸优化问题的可行性,该凸优化问题可以用半定规划方法求解.数值算例验证了该方法的有效性和实用性。
This paper is concerned with the finite-time stability and the finite-time boundedness issues on the estimation problem for a class of continuous-time uncertain recurrent neural networks with Markovian jumping parameters. The uncertain parameters are described by the linear fractional uncertainties and the jumping parameters obey the homogeneous Markov process with possibly deficient probability transition matrix. A full-order state estimator is constructed to estimate the neuron state, in presence of the uncertain and jumping parameters, such that the resulting error dynamics of the state estimation is (i) finite-time stable in the disturbance-free case; and (ii) finite-time bounded in case of exogenous disturbances on the measurements. By employing the Lyapunov stability theory and stochastic analysis techniques, sufficient conditions are established that ensure the existence of the desired finite-time state estimator, and then the explicit expression of such state estimators is characterized in terms of the feasibility to a convex optimization problem that can be easily solved by using the semi-definite programme method. Validity and effectiveness of the developed design method are demonstrated by a numerical example.
DOI: 10.1016/s0076-5392(08)x6039-4
发表时间: 2012-01
期刊: --
影响因子: --
作者:
H. Kushner
通讯作者: H. Kushner
一类具有时变延迟的复杂网络的基于事件的状态估计:一种比较原理方法
DOI: 10.1016/j.physleta.2016.10.002
发表时间: 2017
期刊: Physics Letters A
影响因子: 2.6
作者:
Zhang Wenbing;Liu Yurong;Wang Zidong;Ding Derui;Liu Yurong;Alsaadi Fuad E.;Liu YR
通讯作者: Liu YR
具有缺失测量和相关噪声的线性离散时间系统的未知输入和状态估计
DOI: 10.1080/03081079.2015.1106732
发表时间: 2016-04
影响因子: 2
作者:
Huisheng Shu;Sijing Zhang;Bo Shen;Yurong Liu
通讯作者: Yurong Liu
具有乘性噪声和连续丢包的非线性随机系统的基于观测器的 H 模糊控制
DOI: 10.1016/j.neucom.2015.08.042
发表时间: 2016-01
期刊: Neurocomputing
影响因子: 6
作者:
Ming Gao;Li Sheng;Yurong Liu;Zhengmao Zhu
通讯作者: Zhengmao Zhu
DOI: 10.1162/neco.1996.8.6.1135
发表时间: 1996-08
期刊: Neural Computation
影响因子: 2.9
作者:
Michael Casey
通讯作者: Michael Casey