State estimation of memristor-based recurrent neural networks with time-varying delays based on passivity theory

This article deals with the state estimation problem of memristor-based recurrent neural networks MRNNs with time-varying delay based on passivity theory. The main purpose is to estimate the neuron states, through available output measurements such that for all admissible time delay, the dynamics of the estimation error is passive from the control input to the output error. Based on the Lyapunov-Krasovskii functional LKF involving proper triple integral terms, convex combination technique, and reciprocal convex technique, a delay-dependent state estimation of MRNNs with time-varying delay is established in terms of linear matrix inequalities LMIs. The information about the neuron activation functions and lower bound of the time-varying delays is fully used in the LKF. Then, the desired estimator gain matrix is accomplished by solving LMIs. Finally, a numerical example is provided to demonstrate the effectiveness of the proposed theoretical results. © 2013 Wiley Periodicals, Inc. Complexity 19: 32-43, 2014

[1]  Aleksej F. Filippov,et al.  Differential Equations with Discontinuous Righthand Sides , 1988, Mathematics and Its Applications.

[2]  Xin Yang,et al.  New delay-variation-dependent stability for neural networks with time-varying delay , 2013, Neurocomputing.

[3]  Tianping Chen,et al.  Global $\mu$ -Stability of Delayed Neural Networks With Unbounded Time-Varying Delays , 2007, IEEE Transactions on Neural Networks.

[4]  Vladimir E. Bondarenko,et al.  Information processing, memories, and synchronization in chaotic neural network with the time delay , 2005, Complex..

[5]  Zhigang Zeng,et al.  Passivity analysis of memristive neural networks with different memductance functions , 2014, Commun. Nonlinear Sci. Numer. Simul..

[6]  M. Forti,et al.  Global convergence of neural networks with discontinuous neuron activations , 2003 .

[7]  A. Isidori,et al.  Passivity, feedback equivalence, and the global stabilization of minimum phase nonlinear systems , 1991 .

[8]  Peng Shi,et al.  Exponential Stability on Stochastic Neural Networks With Discrete Interval and Distributed Delays , 2010, IEEE Transactions on Neural Networks.

[9]  Jinde Cao,et al.  An LMI approach to delay-dependent state estimation for delayed neural networks , 2008, Neurocomputing.

[10]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

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

[12]  Ting Wang,et al.  Combined Convex Technique on Delay-Dependent Stability for Delayed Neural Networks , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[13]  Shouming Zhong,et al.  Improved delay-dependent stability criterion for neural networks with time-varying delay , 2011, Appl. Math. Comput..

[14]  KAYVAN NAJARIAN.  On learning of Sigmoid Neural Networks , 2001, Complex..

[15]  Ju H. Park,et al.  State estimation of neural networks with time-varying delays and Markovian jumping parameter based on passivity theory , 2012 .

[16]  Dong Yue,et al.  Delay-Distribution-Dependent Stability and Stabilization of T–S Fuzzy Systems With Probabilistic Interval Delay , 2009, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

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

[18]  D. Yue,et al.  A piecewise analysis method to stability analysis of linear continuous/discrete systems with time‐varying delay , 2009 .

[19]  J. Liu,et al.  Note on stability of discrete-time time-varying delay systems , 2012 .

[20]  Jinde Cao,et al.  Guaranteed performance state estimation of static neural networks with time-varying delay , 2011, Neurocomputing.

[21]  C. Ahn.  Switched exponential state estimation of neural networks based on passivity theory , 2012 .

[22]  Ju H. Park,et al.  New approaches on stability criteria for neural networks with interval time-varying delays , 2012, Appl. Math. Comput..

[23]  A. Bacciotti,et al.  Liapunov functions and stability in control theory , 2001 .

[24]  Zhenjiang Zhao,et al.  Passivity analysis of stochastic neural networks with time-varying delays and leakage delay , 2014, Neurocomputing.

[25]  Wei Xing Zheng,et al.  Passivity-based sliding mode control of uncertain singular time-delay systems , 2009, Autom..

[26]  L. Chua.  Memristor-The missing circuit element , 1971 .

[27]  Yu. S. Ledyaev,et al.  Nonsmooth analysis and control theory , 1998 .

[28]  Chai Wah Wu.  Synchronization in arrays of coupled nonlinear systems: passivity circle criterion and observer design , 2001, ISCAS 2001. The 2001 IEEE International Symposium on Circuits and Systems (Cat. No.01CH37196).

[29]  PooGyeon Park,et al.  Reciprocally convex approach to stability of systems with time-varying delays , 2011, Autom..

[30]  Marc Ebner,et al.  How neutral networks influence evolvability , 2001, Complex..

[31]  Zhigang Zeng,et al.  Dynamics Analysis of a Class of Memristor-Based Recurrent Networks with Time-Varying Delays in the Presence of Strong External Stimuli , 2011, Neural Processing Letters.

[32]  Zhigang Zeng,et al.  Passivity analysis of memristor-based recurrent neural networks with time-varying delays , 2013, J. Frankl. Inst..

[33]  Sabri Arik,et al.  An analysis of global asymptotic stability of delayed cellular neural networks , 2002, IEEE Trans. Neural Networks.

[34]  R. Rakkiyappan,et al.  Passivity analysis for neural networks of neutral type with Markovian jumping parameters and time delay in the leakage term , 2011 .

[35]  Pagavathigounder Balasubramaniam,et al.  Delay-dependent asymptotic stability for stochastic delayed recurrent neural networks with time varying delays , 2008, Appl. Math. Comput..

[36]  Jeffrey Johnson,et al.  How to train a neural network: An introduction to the new computational paradigm , 1996, Complex.

[37]  P. Moylan,et al.  The stability of nonlinear dissipative systems , 1976 .

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