L2 − L∞ state estimation for discrete-time delayed neural networks with missing measurements and randomly occurring sensor linearity

This paper is concerned with the L2 - L∞ state estimation problem for discrete-time delay neural networks with missing measurements and randomly occurring sensor linearity. The phenomena of missing measurements and randomly occurring sensor linearity are constructed with two sequences of random variables, which obey the partial Bernoulli distribution. A sufficient condition is firstly given such that the augmented filtering error system is stochastically stable with a guaranteed optimal L2 - L∞ performance by solving a set of linear matrix inequalities(LMIs). Finally, a simulation example is given to show the effectiveness of the proposed method.

[1]  Zidong Wang,et al.  $H_{\infty}$ State Estimation for Discrete-Time Complex Networks With Randomly Occurring Sensor Saturations and Randomly Varying Sensor Delays , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[2]  Jinde Cao,et al.  Analysis of global exponential stability and periodic solutions of neural networks with time-varying delays , 2005, Neural Networks.

[3]  Hongye Su,et al.  H∞ state estimation of static neural networks with time-varying delay , 2012, Neurocomputing.

[4]  Jean-Pierre Richard,et al.  Stability of some linear systems with delays , 1999, IEEE Trans. Autom. Control..

[5]  Sabri Arik,et al.  Global stability of a class of neural networks with time-varying delay , 2005, IEEE Transactions on Circuits and Systems II: Express Briefs.

[6]  J. Geromel,et al.  Stability and stabilization of discrete time switched systems , 2006 .

[7]  Tingwen Huang,et al.  Exponential Generalized $$H_2$$H2 Filtering of Delayed Static Neural Networks , 2014, Neural Processing Letters.

[8]  He Huang,et al.  Mixed H2/H∞ robust model predictive control with saturated inputs , 2014, Int. J. Syst. Sci..

[9]  Zidong Wang,et al.  State estimation for discrete-time delayed neural networks with fractional uncertainties and sensor saturations , 2013, Neurocomputing.

[10]  Jie Zhang,et al.  H∞ state estimation for discrete-time delayed neural networks with randomly occurring quantizations and missing measurements , 2015, Neurocomputing.

[11]  Zidong Wang,et al.  H∞ filtering with randomly occurring sensor saturations and missing measurements , 2012, Autom..

[12]  Jinde Cao,et al.  Robust State Estimation for Uncertain Neural Networks With Time-Varying Delay , 2008, IEEE Transactions on Neural Networks.

[13]  Tingwen Huang,et al.  Brief Papers Further Result on Guaranteed H∞ Performance State Estimation of Delayed Static Neural Networks , 2015 .

[14]  S. Arik.  Global asymptotic stability of a larger class of neural networks with constant time delay , 2003 .

[15]  He Huang,et al.  An XML-based machining energy estimation tool from process plans , 2016, Int. J. Comput. Integr. Manuf..

[16]  Qing-Guo Wang,et al.  Delay-Dependent State Estimation for Delayed Neural Networks , 2006, IEEE Transactions on Neural Networks.

[17]  Ju H. Park,et al.  H∞ state estimation for discrete-time neural networks with interval time-varying delays and probabilistic diverging disturbances , 2015, Neurocomputing.

[18]  Gang Feng,et al.  State estimation of recurrent neural networks with time-varying delay: A novel delay partition approach , 2011, Neurocomputing.