H∞ State Estimation for Neural Networks Subject to Missing Measurements with Uncertain Missing Probabilities*

This paper addresses the H∞ state estimation problem for a type of neural networks with missing measurements. A series of stochastic variables obeying Bernoulli distributions is adopted to characterize the randomly occurring missing measurements, where the missing probability is considered to be changeable over time and satisfies a norm-bounded condition. This paper aims to construct an effective state estimator such that the mean-square asymptotical stability and the specified Н∞ performance of the augmented estimation error system can be achieved. A criterion is given for the existence of the admissible estimator according to a combination of Lyapunov theory as well as stochastic analysis technique, and the estimator parameters are obtained by dealing with a convex optimization problem. Finally, a simulation example is carried out to illustrate the usefulness of the provided estimation scheme.

[1]  Lei Guo,et al.  Event-Triggered Strategy Design for Discrete-Time Nonlinear Quadratic Games With Disturbance Compensations: The Noncooperative Case , 2018, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[2]  K. Gopalsamy,et al.  Stability of artificial neural networks with impulses , 2004, Appl. Math. Comput..

[3]  Yang Liu,et al.  UKF-based remote state estimation for discrete artificial neural networks with communication bandwidth constraints , 2018, Neural Networks.

[4]  Fuad E. Alsaadi,et al.  State estimation for delayed neural networks with stochastic communication protocol: The finite-time case , 2018, Neurocomputing.

[5]  Jun Hu,et al.  A variance-constrained approach to recursive state estimation for time-varying complex networks with missing measurements , 2016, Autom..

[6]  Zidong Wang,et al.  Fuzzy Filtering With Randomly Occurring Parameter Uncertainties, Interval Delays, and Channel Fadings , 2014, IEEE Transactions on Cybernetics.

[7]  Maozhen Li,et al.  Probability-Dependent Gain-Scheduled Filtering for Stochastic Systems With Missing Measurements , 2011, IEEE Transactions on Circuits and Systems II: Express Briefs.

[8]  Fuad E. Alsaadi,et al.  On passivity and robust passivity for discrete-time stochastic neural networks with randomly occurring mixed time delays , 2017, Neural Computing and Applications.

[9]  Lin-Bao Yang,et al.  Cellular neural networks: theory , 1988 .

[10]  Huajing Fang,et al.  H∞ fault detection for nonlinear networked systems with multiple channels data transmission pattern , 2013, Inf. Sci..

[11]  Fuad E. Alsaadi,et al.  Non-fragile state estimation for discrete Markovian jumping neural networks , 2016, Neurocomputing.

[12]  Jun Hu,et al.  Quantised recursive filtering for a class of nonlinear systems with multiplicative noises and missing measurements , 2013, Int. J. Control.

[13]  Li Sheng,et al.  Robust H∞ control for T-S fuzzy systems subject to missing measurements with uncertain missing probabilities , 2016, Neurocomputing.

[14]  Meiqin Liu,et al.  $H_{\infty }$ State Estimation for Discrete-Time Delayed Systems of the Neural Network Type With Multiple Missing Measurements , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[15]  Fuad E. Alsaadi,et al.  Finite-Time State Estimation for Recurrent Delayed Neural Networks With Component-Based Event-Triggering Protocol , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[16]  Zidong Wang,et al.  Protocol-based state estimation for delayed Markovian jumping neural networks , 2018, Neural Networks.

[17]  Fuad E. Alsaadi,et al.  Event-triggered distributed state estimation for a class of time-varying systems over sensor networks with redundant channels , 2017, Inf. Fusion.

[18]  Fuad E. Alsaadi,et al.  H∞ state estimation for discrete-time neural networks with distributed delays and randomly occurring uncertainties through Fading channels , 2017, Neural Networks.

[19]  Chi-Chuan Hwang,et al.  Exponential synchronization of a class of chaotic neural networks , 2005 .

[20]  Hong Qiao,et al.  Event-Triggered State Estimation for Discrete-Time Multidelayed Neural Networks With Stochastic Parameters and Incomplete Measurements , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[21]  Zidong Wang,et al.  Variance-Constrained State Estimation for Complex Networks With Randomly Varying Topologies , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[22]  Daniel W. C. Ho,et al.  Robust $H_{\infty }$ Fuzzy Output-Feedback Control With Multiple Probabilistic Delays and Multiple Missing Measurements , 2010, IEEE Transactions on Fuzzy Systems.

[23]  Zidong Wang,et al.  Near-Optimal Resilient Control Strategy Design for State-Saturated Networked Systems Under Stochastic Communication Protocol , 2019, IEEE Transactions on Cybernetics.

[24]  Daniel W. C. Ho,et al.  State estimation for delayed neural networks , 2005, IEEE Transactions on Neural Networks.