Non-fragile state estimation for discrete Markovian jumping neural networks

In this paper, the non-fragile state estimation problem is investigated for a class of discrete-time neural networks subject to Markovian jumping parameters and time delays. In terms of a Markov chain, the mode switching phenomenon at different times is considered in both the parameters and the discrete delays of the neural networks. To account for the possible gain variations occurring in the implementation, the gain of the estimator is assumed to be perturbed by multiplicative norm-bounded uncertainties. We aim to design a non-fragile state estimator such that, in the presence of all admissible gain variations, the estimation error converges to zero exponentially. By adopting the Lyapunov-Krasovskii functional and the stochastic analysis theory, sufficient conditions are established to ensure the existence of the desired state estimator that guarantees the stability of the overall estimation error dynamics. The explicit expression of such estimators is parameterized by solving a convex optimization problem via the semi-definite programming method. A numerical simulation example is provided to verify the usefulness of the proposed methods.

[1]  Lothar Litz,et al.  Estimation of unmeasured inputs using recurrent neural networks and the extended Kalman filter , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[2]  Peng Shi,et al.  Non-fragile guaranteed cost control for uncertain stochastic nonlinear time-delay systems , 2009, J. Frankl. Inst..

[3]  Zidong Wang,et al.  $H_{\infty}$ State Estimation for Complex Networks With Uncertain Inner Coupling and Incomplete Measurements , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[4]  Jun Hu,et al.  State estimation for a class of discrete nonlinear systems with randomly occurring uncertainties and distributed sensor delays , 2014, Int. J. Gen. Syst..

[5]  Jinde Cao,et al.  Synchronization of Randomly Coupled Neural Networks With Markovian Jumping and Time-Delay , 2013, IEEE Transactions on Circuits and Systems I: Regular Papers.

[6]  Zidong Wang,et al.  Non-fragile H ∞ control with randomly occurring gain variations, distributed delays and channel fadings , 2015 .

[7]  Jianliang Wang,et al.  Robust nonfragile Kalman filtering for uncertain linear systems with estimator gain uncertainty , 2001, IEEE Trans. Autom. Control..

[8]  Hongyi Li,et al.  Robust exponential stability for uncertain stochastic neural networks with discrete and distributed time-varying delays☆ , 2008 .

[9]  E. Yaz.  Linear Matrix Inequalities In System And Control Theory , 1998, Proceedings of the IEEE.

[10]  Huijun Gao,et al.  Event-Based $H_{\infty}$ Filter Design for a Class of Nonlinear Time-Varying Systems With Fading Channels and Multiplicative Noises , 2015, IEEE Transactions on Signal Processing.

[11]  Zidong Wang,et al.  Robust ℋ︁∞ sliding mode control for nonlinear stochastic systems with multiple data packet losses , 2012 .

[12]  Huijun Gao,et al.  On H-infinity Estimation of Randomly Occurring Faults for A Class of Nonlinear Time-Varying Systems With Fading Channels , 2016, IEEE Transactions on Automatic Control.

[13]  Jigui Jian,et al.  Global stability in Lagrange sense for BAM-type Cohen–Grossberg neural networks with time-varying delays , 2015 .

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

[15]  Mourad Kchaou,et al.  A new approach to non-fragile H ∞ observer-based control for discrete-time fuzzy systems , 2012, Int. J. Syst. Sci..

[16]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[17]  Zidong Wang,et al.  State estimation for discrete-time Markovian jumping neural networks with mixed mode-dependent delays ☆ , 2008 .

[18]  Mohsen Farahani,et al.  Intelligent control of a DC motor using a self-constructing wavelet neural network , 2014 .

[19]  Daniel W. C. Ho,et al.  Robust ${{\cal H}}_{\infty}$ Filtering for Markovian Jump Systems With Randomly Occurring Nonlinearities and Sensor Saturation: The Finite-Horizon Case , 2011, IEEE Transactions on Signal Processing.

[20]  Zidong Wang,et al.  Stability and Synchronization of Discrete-Time Markovian Jumping Neural Networks With Mixed Mode-Dependent Time Delays , 2009, IEEE Transactions on Neural Networks.

[21]  Zidong Wang,et al.  Envelope-constrained H∞ filtering with fading measurements and randomly occurring nonlinearities: The finite horizon case , 2015, Autom..

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

[23]  Yung C. Shin,et al.  Radial basis function neural network for approximation and estimation of nonlinear stochastic dynamic systems , 1994, IEEE Trans. Neural Networks.

[24]  Huijun Gao,et al.  Finite-horizon reliable control with randomly occurring uncertainties and nonlinearities subject to output quantization , 2015, Autom..

[25]  Jianbin Qiu,et al.  A Combined Adaptive Neural Network and Nonlinear Model Predictive Control for Multirate Networked Industrial Process Control , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[26]  P. Dorato,et al.  Non-fragile controller design: an overview , 1998, Proceedings of the 1998 American Control Conference. ACC (IEEE Cat. No.98CH36207).

[27]  Zidong Wang,et al.  Exponential stability of delayed recurrent neural networks with Markovian jumping parameters , 2006 .

[28]  Zidong Wang,et al.  Non-fragile H∞ control with randomly occurring gain variations , 2014, 2014 20th International Conference on Automation and Computing.

[29]  Y. Jia,et al.  Non-fragile dynamic output feedback control for linear systems with time-varying delay , 2009 .

[30]  Zidong Wang,et al.  Finite-horizon ℋ 2/ℋ ∞ control for a class of nonlinear Markovian jump systems with probabilistic sensor failures , 2011, Int. J. Control.

[31]  Fuad E. Alsaadi,et al.  Nonfragile $H_{\infty}$ Fuzzy Filtering With Randomly Occurring Gain Variations and Channel Fadings , 2016, IEEE Transactions on Fuzzy Systems.

[32]  Mingyu Wang,et al.  Approximation-Based Adaptive Tracking Control for MIMO Nonlinear Systems With Input Saturation , 2015, IEEE Transactions on Cybernetics.

[33]  Zidong Wang,et al.  H∞ state estimation with fading measurements, randomly varying nonlinearities and probabilistic distributed delays , 2015 .

[34]  James Lam,et al.  Finite-Horizon ${\cal H}_{\infty}$ Control for Discrete Time-Varying Systems With Randomly Occurring Nonlinearities and Fading Measurements , 2015, IEEE Transactions on Automatic Control.

[35]  Bing Chen,et al.  Robust Stability for Uncertain Delayed Fuzzy Hopfield Neural Networks With Markovian Jumping Parameters , 2009, IEEE Trans. Syst. Man Cybern. Part B.

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

[37]  Yeung Sam Hung,et al.  Distributed $H_{\infty}$ Filtering for Polynomial Nonlinear Stochastic Systems in Sensor Networks , 2011, IEEE Transactions on Industrial Electronics.

[38]  Jun Hu,et al.  Gain-Constrained Recursive Filtering With Stochastic Nonlinearities and Probabilistic Sensor Delays , 2013, IEEE Transactions on Signal Processing.

[39]  Rathinasamy Sakthivel,et al.  Combined H∞ and passivity state estimation of memristive neural networks with random gain fluctuations , 2015, Neurocomputing.

[40]  Huijun Gao,et al.  Finite-horizon estimation of randomly occurring faults for a class of nonlinear time-varying systems , 2014, Autom..

[41]  F. Salam,et al.  Adaptive neural observer with forward co-state propagation , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[42]  Zidong Wang,et al.  On global asymptotic stability of neural networks with discrete and distributed delays , 2005 .

[43]  Peter Ti.  Markovian Architectural Bias of Recurrent Neural Networks , 2004 .