Novel stability condition of stochastic fuzzy neural networks with Markovian jumping under impulsive perturbations

For the first time, this paper investigates the global asymptotic stability of stochastic fuzzy neural networks with mixed delays and Markovian jumping under impulsive perturbations in mean square. The mixed delays include time-varying delay and continuously distributed delay. By using stochastic analysis method, linear convex combination technique, Jensen integral inequality and the free-weight matrix method, a novel sufficient condition is derived to ensure the global asymptotic stability of the equilibrium point of the considered networks in mean square. The proposed result, which is expressed in terms of linear matrix inequalities, can be easily checked via Matlab software. Finally, a numerical example is given to demonstrate the effectiveness and less conservativeness of our theoretical results over existing literature.

[1]  K. Gu.  An integral inequality in the stability problem of time-delay systems , 2000, Proceedings of the 39th IEEE Conference on Decision and Control (Cat. No.00CH37187).

[2]  L. Arnold.  Stochastic Differential Equations: Theory and Applications , 1992 .

[3]  Yan Gao,et al.  Mode and Delay-Dependent Adaptive Exponential Synchronization in $p$th Moment for Stochastic Delayed Neural Networks With Markovian Switching , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[4]  Ta-lun Yang,et al.  The global stability of fuzzy cellular neural network , 1996 .

[5]  Shaocheng Tong,et al.  A Combined Backstepping and Stochastic Small-Gain Approach to Robust Adaptive Fuzzy Output Feedback Control , 2013, IEEE Transactions on Fuzzy Systems.

[6]  Chen An,et al.  The Global Stability of Fuzzy Cellular Neural Networks , 2001 .

[7]  Alexander S. Poznyak,et al.  Nonlinear System Approximation by Neural Networks: Error Stability Analysis , 1995, Intell. Autom. Soft Comput..

[8]  John Lygeros,et al.  Stabilization of a class of stochastic differential equations with Markovian switching , 2005, Syst. Control. Lett..

[9]  Guijun Wang,et al.  Parameters optimization of polygonal fuzzy neural networks based on GA-BP hybrid algorithm , 2014, International Journal of Machine Learning and Cybernetics.

[10]  Da Lin,et al.  Dynamic fuzzy neural networks modeling and adaptive backstepping tracking control of uncertain chaotic systems , 2010, Neurocomputing.

[11]  Xuerong Mao,et al.  Exponential stability of stochastic delay interval systems with Markovian switching , 2002, IEEE Trans. Autom. Control..

[12]  Xiaodi Li,et al.  Existence and global stability analysis of equilibrium of fuzzy cellular neural networks with time delay in the leakage term under impulsive perturbations , 2011, J. Frankl. Inst..

[13]  Shaocheng Tong,et al.  Observer-Based Adaptive Fuzzy Backstepping Control for a Class of Stochastic Nonlinear Strict-Feedback Systems , 2011, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[14]  Chunmei He,et al.  Approximation of polygonal fuzzy neural networks in sense of Choquet integral norms , 2014, Int. J. Mach. Learn. Cybern..

[15]  Pagavathigounder Balasubramaniam,et al.  Robust stability of uncertain fuzzy BAM neural networks of neutral-type with Markovian jumping parameters and impulses , 2011, Comput. Math. Appl..

[16]  Da Lin,et al.  Observer-based decentralized fuzzy neural sliding mode control for interconnected unknown chaotic systems via network structure adaptation , 2010, Fuzzy Sets Syst..

[17]  Dong Yue,et al.  New stability criteria of neural networks with interval time-varying delay: A piecewise delay method , 2009, Appl. Math. Comput..

[18]  Yang Tang,et al.  On the exponential synchronization of stochastic jumping chaotic neural networks with mixed delays and sector-bounded non-linearities , 2009, Neurocomputing.

[19]  Huaguang Zhang,et al.  Novel stability criterions of a new fuzzy cellular neural networks with time-varying delays , 2009, Neurocomputing.

[20]  Yan Liu,et al.  Global exponential stability of delayed fuzzy cellular neural networks with Markovian jumping parameters , 2011, Neural Computing and Applications.