State estimation for delayed neural networks with stochastic communication protocol: The finite-time case

Abstract This paper is concerned with the finite-time state estimation problem for a class of delayed artificial neural networks under the stochastic communication protocol. The underlying time delay is time-varying yet bounded. Compared with the common-used sigmoid-type nonlinearity, a more general type of nonlinearity is adopted to describe the neuron activation function and the nonlinearity of the measurement output, respectively. In order to avoid the communication collision, the stochastic communication protocol is introduced between the transmitter and the receiver, and the corresponding scheme is characterised with the help of a Markov chain. By introducing an auxiliary vector, a novel state estimator structure is proposed. The stochastic finite-time stability of the error dynamics is first analyzed via the stochastic analysis techniques and the Lyapunov stability theory, and then the sufficient condition for the existence of the desired state estimator is obtained. Subsequently, the estimator gain is parameterized by using a set of easy-to-check computational condition. Finally, a numerical example is provided to show the effectiveness of the proposed algorithm.

[1]  Alberto Bemporad,et al.  Stability analysis of stochastic Networked Control Systems , 2010, Proceedings of the 2010 American Control Conference.

[2]  Jinde Cao,et al.  Finite-time boundedness and stabilization of uncertain switched neural networks with time-varying delay , 2015, Neural Networks.

[3]  Renquan Lu,et al.  Finite-Time State Estimation for Coupled Markovian Neural Networks With Sensor Nonlinearities , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[4]  Goutam Saha,et al.  Lung sound classification using cepstral-based statistical features , 2016, Comput. Biol. Medicine.

[5]  Peng Shi,et al.  Stochastic finite-time state estimation for discrete time-delay neural networks with Markovian jumps , 2015, Neurocomputing.

[6]  Jeremy Wyatt,et al.  Connectionist models in medicine: an investigation of their potential , 1989, AIME.

[7]  Lei Zou,et al.  Observer-based H∞ control of networked systems with stochastic communication protocol: The finite-horizon case , 2016, Autom..

[8]  Jinde Cao,et al.  Nonsmooth Finite-Time Synchronization of Switched Coupled Neural Networks , 2016, IEEE Transactions on Cybernetics.

[9]  Wolfram Burgard,et al.  The dynamic window approach to collision avoidance , 1997, IEEE Robotics Autom. Mag..

[10]  Robert J. Marks,et al.  Electric load forecasting using an artificial neural network , 1991 .

[11]  Emilia Fridman,et al.  A Round-Robin Type Protocol for Distributed Estimation with H∞ Consensus , 2014, Syst. Control. Lett..

[12]  R. Westervelt,et al.  Stability of analog neural networks with delay. , 1989, Physical review. A, General physics.

[13]  Şükrü Özşahin,et al.  An application of artificial neural networks for modeling formaldehyde emission based on process parameters in particleboard manufacturing process , 2017, Clean Technologies and Environmental Policy.

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

[15]  Linda Bushnell,et al.  Stability analysis of networked control systems , 2002, IEEE Trans. Control. Syst. Technol..

[16]  Yurong Liu,et al.  State estimation for jumping recurrent neural networks with discrete and distributed delays , 2009, Neural Networks.

[17]  Carlos Silvestre,et al.  Volterra Integral Approach to Impulsive Renewal Systems: Application to Networked Control , 2012, IEEE Transactions on Automatic Control.

[18]  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..

[19]  Alan Colvin.  CSMA with collision avoidance , 1983, Comput. Commun..

[20]  P. Dorato,et al.  Finite time stability under perturbing forces and on product spaces , 1967, IEEE Transactions on Automatic Control.

[21]  Indra Widjaja,et al.  IEEE 802.11 Wireless Local Area Networks , 1997, IEEE Commun. Mag..

[22]  Dragan Nesic,et al.  Input–Output Stability of Networked Control Systems With Stochastic Protocols and Channels , 2008, IEEE Transactions on Automatic Control.

[23]  Keith J. Burnham,et al.  On designing observers for time-delay systems with non-linear disturbances , 2002 .

[24]  Guoshan Zhang,et al.  Non-fragile robust finite-time H∞ control for nonlinear stochastic itô systems using neural network , 2012 .

[25]  Francesco Amato,et al.  Finite-time control of linear systems subject to parametric uncertainties and disturbances , 2001, Autom..

[26]  Guanrong Chen,et al.  LMI-based approach for asymptotically stability analysis of delayed neural networks , 2002 .

[27]  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.

[28]  P. Dorato.  SHORT-TIME STABILITY IN LINEAR TIME-VARYING SYSTEMS , 1961 .

[29]  Francesco Amato,et al.  Finite-time control of discrete-time linear systems , 2005, IEEE Transactions on Automatic Control.

[30]  Roman M. Balabin,et al.  Neural network approach to quantum-chemistry data: accurate prediction of density functional theory energies. , 2009, The Journal of chemical physics.

[31]  Dimitrios Zissis,et al.  A cloud based architecture capable of perceiving and predicting multiple vessel behaviour , 2015, Appl. Soft Comput..

[32]  Zhidong Teng,et al.  Finite-time synchronization for memristor-based neural networks with time-varying delays , 2015, Neural Networks.