H∞ state estimation for discrete-time delayed neural networks with randomly occurring quantizations and missing measurements

Abstract This paper is concerned with the H ∞ state estimation problem for a class of discrete-time neural networks with time-varying delays, randomly occurring quantizations (ROQs) as well as missing measurements. The phenomena of ROQ and missing measurements are governed by a Bernoulli distributed stochastic sequence. The purpose of the addressed problem is to design a state estimator such that the dynamics of the estimation error is exponentially stable in the mean square and the prescribed H ∞ performance constraint is satisfied. By constructing proper Lyapunov–Krasovskii functionals and employing stochastic analysis techniques, sufficient conditions are derived to ensure the existence of the desired estimator. Furthermore, the explicit expression of the gain of the desired estimator is described in terms of the solution to a convex optimization problem that can be easily solved by using the semi-definite programme method. Finally, a numerical example is employed to demonstrate the effectiveness and applicability of the proposed estimator design approach.

[1]  Jinling Liang,et al.  Finite-horizon H∞ filtering for time-varying delay systems with randomly varying nonlinearities and sensor saturations , 2014 .

[2]  Donghua Zhou,et al.  State estimation for networked systems with randomly occurring quantisations , 2013, Int. J. Syst. Sci..

[3]  Tingwen Huang,et al.  A mode-dependent approach to state estimation of recurrent neural networks with Markovian jumping parameters and mixed delays , 2013, Neural Networks.

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

[5]  James Lam,et al.  Decay rate constrained stability analysis for positive systems with discrete and distributed delays , 2014 .

[6]  James Lam,et al.  Stability Analysis of Discrete-Time Recurrent Neural Networks With Stochastic Delay , 2009, IEEE Transactions on Neural Networks.

[7]  A. Sakly,et al.  Stability analysis for a class of switched nonlinear time-delay systems , 2014 .

[8]  Zhenjiang Zhao,et al.  Cluster, local and complete synchronization in coupled neural networks with mixed delays and nonlinear coupling , 2013, Neural Computing and Applications.

[9]  Jinde Cao,et al.  Robust impulsive synchronization of coupled delayed neural networks with uncertainties , 2007 .

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

[11]  Qingsong Liu,et al.  Hopf bifurcation in a partial dependent predator–prey system with multiple delays , 2014 .

[12]  J. Hopfield.  Neurons withgraded response havecollective computational properties likethoseoftwo-state neurons , 1984 .

[13]  James Lam,et al.  Stability and Synchronization of Discrete-Time Neural Networks With Switching Parameters and Time-Varying Delays , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[14]  Qiankun Song,et al.  Passivity analysis of discrete-time stochastic neural networks with time-varying delays , 2009, Neurocomputing.

[15]  Magdi S. Mahmoud,et al.  Dissipativity analysis for discrete stochastic neural networks with Markovian delays and partially known transition matrix , 2014, Appl. Math. Comput..

[16]  Jinde Cao,et al.  Matrix measure strategies for stability and synchronization of inertial BAM neural network with time delays , 2014, Neural Networks.

[17]  Joydeb Bhattacharyya,et al.  Dynamics of a stage-structured system with harvesting and discrete time delays , 2014 .

[18]  S. Arik.  Stability analysis of delayed neural networks , 2000 .

[19]  Huijun Gao,et al.  Finite-Horizon $H_{\infty} $ Filtering With Missing Measurements and Quantization Effects , 2013, IEEE Transactions on Automatic Control.

[20]  Rathinasamy Sakthivel,et al.  State estimation for switched discrete-time stochastic BAM neural networks with time varying delay , 2013 .

[22]  G. Samanta,et al.  Analysis of a delayed hand–foot–mouth disease epidemic model with pulse vaccination , 2014 .

[23]  Vimal Singh,et al.  Simplified LMI condition for global asymptotic stability of delayed neural networks , 2006 .

[24]  Rajendran Samidurai,et al.  Dissipativity of discrete-time BAM stochastic neural networks with Markovian switching and impulses , 2013, J. Frankl. Inst..

[25]  Huijun Gao,et al.  Distributed Filtering for a Class of Time-Varying Systems Over Sensor Networks With Quantization Errors and Successive Packet Dropouts , 2012, IEEE Transactions on Signal Processing.

[26]  Peng Shi,et al.  Exponential Synchronization of Neural Networks With Discrete and Distributed Delays Under Time-Varying Sampling , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[27]  Zidong Wang,et al.  Quantized $H_{\infty }$ Control for Nonlinear Stochastic Time-Delay Systems With Missing Measurements , 2012, IEEE Transactions on Automatic Control.

[28]  Zhigang Zeng,et al.  Global exponential synchronization of memristor-based recurrent neural networks with time-varying delays , 2013, Neural Networks.

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

[30]  Tae H. Lee,et al.  Stochastic sampled-data control for state estimation of time-varying delayed neural networks , 2013, Neural Networks.

[31]  Jinde Cao,et al.  Multistability and instability of delayed competitive neural networks with nondecreasing piecewise linear activation functions , 2013, Neurocomputing.

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

[33]  P. Balasubramaniam,et al.  Delay decomposition approach to state estimation of neural networks with mixed time‐varying delays and Markovian jumping parameters , 2013 .