Optimal H∞ synchronization of general discrete-time delayed chaotic neural networks via dynamic output feedback

This paper deals with robust H∞ synchronization of general discrete-time chaotic neural networks with external disturbance. This general discrete-time model, which is the interconnection of a linear delayed dynamic system and a bounded static nonlinear operator, covers not only several well-known discrete-time delayed neural networks, such as Hopfield neural networks, cellular neural networks (CNNs), bidirectional associative memory (BAM) networks, and recurrent multilayer perceptrons (RMLPs), but also Lur'e systems. Based on Lyapunov stability and H∞ control theories, dynamic output feedback controllers are established to not only guarantee exponentially stable synchronization of both master and slave systems with time delays, but also reduce the effect of external disturbance to an H∞-norm constraint. Furthermore, two classes of optimal controllers are presented, one minimizing the H∞-norm bound, the other maximizing the exponential synchronization rate. The control design equations are shown to be a set of linear matrix inequality (LMI) standard problems which can be easily solved by various convex optimization algorithms to determine the optimal H∞ control laws and the optimal exponential synchronization rates.

[1]  Meiqin Liu.  Discrete-time delayed standard neural network model and its application , 2006, Science in China Series F: Information Sciences.

[2]  Kate Smith-Miles,et al.  Experimental analysis of chaotic neural network models for combinatorial optimization under a unifying framework , 2000, Neural Networks.

[3]  T. Liao,et al.  H∞ synchronization of chaotic systems using output feedback control design , 2007 .

[4]  Mona E. Zaghloul,et al.  SYNCHRONIZATION OF CHAOTIC NEURAL NETWORKS AND APPLICATIONS TO COMMUNICATIONS , 1996 .

[5]  L. Glass,et al.  Oscillation and chaos in physiological control systems. , 1977, Science.

[6]  Carroll,et al.  Synchronization in chaotic systems. , 1990, Physical review letters.

[7]  Ju H. Park,et al.  H∞ synchronization of chaotic systems via dynamic feedback approach , 2008 .

[8]  D. H. Ji,et al.  ' s personal copy H 1 synchronization of time-delayed chaotic systems , 2008 .

[9]  Hamid Reza Karimi,et al.  Delay-range-dependent exponential H∞ synchronization of a class of delayed neural networks , 2009 .

[10]  K. Aihara,et al.  Chaotic neural networks , 1990 .

[11]  Robin J. Evans,et al.  Control of chaos: Methods and applications in engineering, , 2005, Annu. Rev. Control..

[12]  Yonghui Sun,et al.  Adaptive lag synchronization of unknown chaotic delayed neural networks with noise perturbation , 2007 .

[13]  Meiqin Liu,et al.  Exponential synchronization of general chaotic delayed neural networks via hybrid feedback , 2008 .

[14]  Y. Kuramoto,et al.  Dephasing and bursting in coupled neural oscillators. , 1995, Physical review letters.

[15]  Z. Tan,et al.  ASSOCIATIVE MEMORY USING SYNCHRONIZATION IN A CHAOTIC NEURAL NETWORK , 2001 .

[16]  Liu Meiqin,et al.  Discrete-time delayed standard neural network model and its application , 2006 .

[17]  Stephen P. Boyd,et al.  Linear Matrix Inequalities in Systems and Control Theory , 1994 .

[18]  Ju H. Park,et al.  Hinfinity synchronization of time-delayed chaotic systems , 2008, Appl. Math. Comput..