Finite-time stability of Markovian jump neural networks with partly unknown transition probabilities

This paper deals with the finite-time robust stability of Markovian jump neural networks with partly unknown transition probabilities. Based on Lyapunov stability theory, two sufficient conditions are derived such that Markovian jump neural networks with partly unknown transition probabilities and uncertain Markovian jump neural networks with partly unknown transition probabilities are stochastically finite-time stable and robust finite-time stable, respectively. Then, the finite-time stable and robust stability conditions are obtained based on the stability criterion. The stability conditions are expressed in terms of linear matrix inequalities (LMIs), which can be easily solved by standard software. Finally, two numerical examples are given to demonstrate the effectiveness of the proposed results.

[1]  Huijun Gao,et al.  Distributed Robust Synchronization of Dynamical Networks With Stochastic Coupling , 2014, IEEE Transactions on Circuits and Systems I: Regular Papers.

[2]  Vimal Singh,et al.  A generalized LMI-based approach to the global asymptotic stability of delayed cellular neural networks , 2004, IEEE Transactions on Neural Networks.

[3]  Peng Shi,et al.  Fault-Tolerant Control for Nonlinear Markovian Jump Systems via Proportional and Derivative Sliding Mode Observer Technique , 2011, IEEE Transactions on Circuits and Systems I: Regular Papers.

[4]  Fei Liu,et al.  Observer-based finite-time control of time-delayed jump systems , 2010, Appl. Math. Comput..

[5]  Huijun Gao,et al.  Robust Stability Criterion for Discrete-Time Uncertain Markovian Jumping Neural Networks With Defective Statistics of Modes Transitions , 2011, IEEE Transactions on Neural Networks.

[6]  Fei Liu,et al.  Finite-time filtering for non-linear stochastic systems with partially known transition jump rates , 2010 .

[7]  Steven X. Ding,et al.  Real-Time Implementation of Fault-Tolerant Control Systems With Performance Optimization , 2014, IEEE Transactions on Industrial Electronics.

[8]  Shen Yin,et al.  Performance Monitoring for Vehicle Suspension System via Fuzzy Positivistic C-Means Clustering Based on Accelerometer Measurements , 2015, IEEE/ASME Transactions on Mechatronics.

[9]  Hongyi Li,et al.  Robust exponential stability for delayed uncertain Hopfield neural networks with Markovian jumping parameters , 2008 .

[10]  Raja Sengupta,et al.  An H/sub /spl infin// approach to networked control , 2005, IEEE Transactions on Automatic Control.

[11]  Guanghui Wen,et al.  ${\cal H}_{\infty}$ Pinning Synchronization of Directed Networks With Aperiodic Sampled-Data Communications , 2014, IEEE Transactions on Circuits and Systems I: Regular Papers.

[12]  Maozhen Li,et al.  Stability analysis for stochastic Cohen-Grossberg neural networks with mixed time delays , 2006, IEEE Transactions on Neural Networks.

[13]  James Lam,et al.  Semi-Global Leader-Following Consensus of Linear Multi-Agent Systems With Input Saturation via Low Gain Feedback , 2013, IEEE Transactions on Circuits and Systems I: Regular Papers.

[14]  Chun-Guang Li,et al.  Passivity Analysis of Neural Networks With Time Delay , 2005, IEEE Trans. Circuits Syst. II Express Briefs.

[15]  Qian Ma,et al.  Stability and synchronization for Markovian jump neural networks with partly unknown transition probabilities , 2011, Neurocomputing.

[16]  Wenbing Zhang,et al.  Finite-time cluster synchronisation of Markovian switching complex networks with stochastic perturbations , 2014 .

[17]  James Lam,et al.  Semiglobal Observer-Based Leader-Following Consensus With Input Saturation , 2014, IEEE Transactions on Industrial Electronics.

[18]  Xuyang Lou,et al.  Stochastic Exponential Stability for Markovian Jumping BAM Neural Networks With Time-Varying Delays , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[19]  Hamid Reza Karimi,et al.  A sliding mode approach to H∞ synchronization of master-slave time-delay systems with Markovian jumping parameters and nonlinear uncertainties , 2012, J. Frankl. Inst..

[20]  Wen-an Zhang,et al.  Moving Horizon Estimation for Networked Systems With Quantized Measurements and Packet Dropouts , 2013, IEEE Transactions on Circuits and Systems I: Regular Papers.

[21]  X. Lou,et al.  Delay-dependent stochastic stability of delayed Hopfield neural networks with Markovian jump parameters , 2007 .

[22]  Huijun Gao,et al.  New Passivity Analysis for Neural Networks With Discrete and Distributed Delays , 2010, IEEE Transactions on Neural Networks.

[23]  Dennis S. Bernstein,et al.  Finite-Time Stability of Continuous Autonomous Systems , 2000, SIAM J. Control. Optim..

[24]  Zidong Wang,et al.  Robust stability analysis of generalized neural networks with discrete and distributed time delays , 2006 .

[25]  Caixia Liu,et al.  Robust finite-time stabilization of uncertain singular Markovian jump systems , 2012 .

[26]  Hamid Reza Karimi,et al.  Data-driven design of robust fault detection system for wind turbines , 2014 .

[27]  Huijun Gao,et al.  On Controllability of Neuronal Networks With Constraints on the Average of Control Gains , 2014, IEEE Transactions on Cybernetics.

[28]  Tongwen Chen,et al.  A new method for stabilization of networked control systems with random delays , 2005 .

[29]  Feng Qian,et al.  Synchronization in complex networks and its application - A survey of recent advances and challenges , 2014, Annu. Rev. Control..

[30]  Weijian Ren,et al.  Stability analysis for discrete delayed Markovian jumping neural networks with partly unknown transition probabilities , 2011, Neurocomputing.

[31]  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.

[32]  X. Mao.  Stability of stochastic differential equations with Markovian switching , 1999 .

[33]  Wei Xing Zheng,et al.  Generalized H2 fault detection for two-dimensional Markovian jump systems , 2012, Autom..

[34]  Honghai Liu,et al.  Parameter-dependent robust stability for uncertain Markovian jump systems with time delay , 2011, J. Frankl. Inst..

[35]  Carlo Cosentino,et al.  Finite-time stabilization via dynamic output feedback, , 2006, Autom..

[36]  Chong Lin,et al.  Passivity analysis for uncertain neural networks with discrete and distributed time-varying delays ☆ , 2009 .

[37]  Yun Chen,et al.  Finite-Time Stability and Dynamic Output Feedback Stabilization of Stochastic Systems , 2014, Circuits Syst. Signal Process..

[38]  Okyay Kaynak,et al.  Improved PLS Focused on Key-Performance-Indicator-Related Fault Diagnosis , 2015, IEEE Transactions on Industrial Electronics.

[39]  Huijun Gao,et al.  Multiobjective Identification of Controlling Areas in Neuronal Networks , 2013, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[40]  Huijun Gao,et al.  Fault-tolerant control of Markovian jump stochastic systems via the augmented sliding mode observer approach , 2014, Autom..

[41]  Min Wu,et al.  Stability Analysis for Neural Networks With Time-Varying Interval Delay , 2007, IEEE Transactions on Neural Networks.