An LMI approach to delay-dependent state estimation for delayed neural networks
Introduction
Various classes of neural networks have been increasingly studied in the past few years, due to their practical importance and successful applications in many areas such as combinatorial optimization, signal processing and communication [8], [13], [16]. These applications greatly depend on the dynamic behaviors of the underlying neural networks. As is well known, time delay may occur in the process of information storage and transmission in neural networks. In electronic implementation of neural networks, the time delay is often time-variant, and even varies dramatically with time because of the finite switch speed of amplifiers and faults in the electrical circuits. Up to now, the stability analysis for delayed neural networks has attracted considerable attention, and a large amount of results have been available in the literature, see, for example, [1], [3], [4], [5], [7], [9], [15], [17], [21], [22], [23], [24], [25], [26], [27], [28].
On the other hand, the neuron states are not often completely available in the network outputs in many applications. Therefore, the state estimation problem of neural networks becomes significant for many applications [14], [20]. The main objective of the problem is to estimate the neuron states through available output measurements such that the dynamics of the error-state system is globally stable. Recently, the state estimation problem for neural networks has attracted certain attention and some progresses have been made [6], [12], [19]. Wang et al. firstly investigated the state estimation problem for neural networks with time-varying delay in [20]. Under the precondition that the time-derivative of the time-varying delay was smaller than 1, a linear matrix inequality (LMI) condition was derived to guarantee the existence of the expected state estimator. In [14], the problem of state estimation was also addressed for delayed neural networks under a weak assumption that the time-varying delay was required to be differentiable. However, the proposed condition was expressed in terms of a matrix inequality, not an LMI, which corresponds to a nonlinear programming problem. The authors in [18] dealt with the state estimation problem for a class of neural networks with discrete and distributed delays. The existing results related to this issue can be generally classified into two categories: delay-independent criteria [20] and delay-dependent criteria [14], [18]. The delay-independent case is irrespective of the size of the time delay. While the delay-dependent case is relevant to the size of the time delay. Generally speaking, the delay-dependent case is considered to be less conservative than the delay-independent case, especially when the size of time delay is small.
In this paper, the state estimation problem is studied for a class of neural networks with time-varying delays. As mentioned above, the time-varying delay in [14], [20] must satisfy the assumptions that it was differentiable and its time-derivative was less than 1 or a constant. This would greatly limit the applications of the results proposed in [14], [20]. Here, such restrictions on the time-varying delay are removed. By defining a new Lyapunov–Krasovskii functional, the boundedness of the time-varying delay is only required. A delay-dependent condition is developed to estimate the neuron states through available output measurements such that the error-state system is globally asymptotically stable. The criterion is formulated in terms of an LMI, which can be checked efficiently by using some standard numerical packages [2], [10].
Notations: For a real square matrix X, the notation () means that X is symmetric and positive definite (positive semi-definite, negative definite, negative semi-definite, respectively). The shorthand notation denotes a block diagonal matrix with diagonal blocks being the matrices . I is the identity matrix with appropriate dimension. The superscript “T” represents the transpose. is the Euclidean norm in . Let denote the family of all -measurable -valued variables such that . Matrices, if their dimensions are not explicitly stated, are assumed to be compatible dimensions for algebra operations.
Section snippets
Problem formulation
The model of neural networks with time-varying delay considered in this paper is described by the following state equation:where is the state vector associated with n neurons, is a diagonal matrix with positive entries . The matrices and are, respectively, the connection weight matrix and the delayed connection weight matrix. denotes the neuron
State estimator for delayed neural networks
This section is dedicated to designing a state estimator for the neural network with time-varying delay (1), such that the error-state system is globally asymptotically stable. The following theorem presents a delay-dependent condition for the existence of the desired state estimator for the delayed neural network based on an LMI approach. Theorem 1 The error-state system (7) of the delayed neural network described by (1) and (4) is globally asymptotically stable if there exist three positive scalars
A numerical example
A simple example with simulation results is provided to demonstrate the effectiveness of the developed LMI approach to the state estimator design for delayed neural networks.
Consider the delayed neural network with the following parametersThe activation function is assumed to be with . The nonlinear disturbance is of
Conclusion
In this paper, the delay-dependent state estimation problem has been studied for a class of neural networks with time-varying delays. The differentiability of the time-varying delay has been no longer needed to address this issue. A sufficient condition has been presented to guarantee the existence of the desired state estimator for delayed neural networks. The criterion is dependent on the size of the time-varying delay and formulated by means of the feasibility of a strict LMI. Two slack
Acknowledgments
The authors would like to thank the associate editor and the anonymous reviewers for their constructive comments that have greatly improved the quality of this paper. The work was partially supported by a grant from the Research Grants Council of the Hong Kong Special Administrative Region of China [Project no.: CityU 1353/04E], and partially supported by the National Natural Science Foundation of China under Grant no. 60574043, International Joint Project funded by NSFC and the Royal Society
He Huang received the B.S. degree in mathematics from Gannan Normal University, Ganzhou, China, in 2000, and the M.S. degree in applied mathematics from Southeast University, Nanjing, China, in 2003. He is now working toward his Ph.D. degree at City University of Hong Kong, Hong Kong, China. His current research interests include neural networks, intelligent control, nonlinear systems, and applied mathematics.
References (28)
An analysis of exponential stability of delayed neural networks with time varying delays
Neural Networks
(2004)- et al.
Global exponential stability and periodic solutions of recurrent neural networks with delays
Phys. Lett. A
(2002) - et al.
Hopfield neural networks for optimization: study of the different dynamics
Neurocomputing
(2002) - et al.
Global exponential stability of generalized recurrent neural networks with discrete and distributed delays
Neural Networks
(2006) - et al.
Design of exponential state estimators for neural networks with mixed time delays
Phys. Lett. A
(2007) - et al.
On global asymptotic stability of neural networks with discrete and distributed delays
Phys. Lett. A
(2005) - et al.
Robust stability for stochastic Hopfield neural networks with time delays
Nonlinear Anal.: R. World Appl.
(2006) - et al.
Robust stability analysis of generalized neural networks with discrete and distributed time delays
Chaos Solitons Fractals
(2006) - et al.
LMI-based robust stability analysis of neural networks with time-varying delay
Neurocomputing
(2005) - et al.
Delay-dependent exponential stability of cellular neural networks with time-varying delays
Chaos Solitons Fractals
(2005)
Linear Matrix Inequalities in System and Control Theory
A set of stability criteria for delayed cellular neural networks
IEEE Trans. Circuits Syst. I
Global asymptotic stability of a general class of recurrent neural networks with time-varying delays
IEEE Trans. Circuits Syst. I
Global asymptotic and robust stability of recurrent neural networks with time delays
IEEE Trans. Circuits Syst. I
Cited by (0)
He Huang received the B.S. degree in mathematics from Gannan Normal University, Ganzhou, China, in 2000, and the M.S. degree in applied mathematics from Southeast University, Nanjing, China, in 2003. He is now working toward his Ph.D. degree at City University of Hong Kong, Hong Kong, China. His current research interests include neural networks, intelligent control, nonlinear systems, and applied mathematics.
Gang Feng received the B.Eng. and M.Eng. degrees in automatic control (of electrical engineering) from Nanjing Aeronautical Institute, Nanjing, China, in 1982 and in 1984, respectively, and the Ph.D. degree in electrical engineering from the University of Melbourne, Melbourne, Australia, in 1992.
He has been an Associate Professor and then Professor at City University of Hong Kong since 2000, and was a Lecturer/Senior Lecturer at the School of Electrical Engineering, University of New South Wales, Australia, from 1992 to 1999. He was a visiting Fellow at the National University of Singapore (1997) and Aachen Technology University, Germany (1997–1998). He has authored and/or coauthored numerous referred technical papers. His current research interests include robust adaptive control, signal processing, piecewise linear systems, and intelligent systems and control.
Dr. Feng was awarded an Alexander von Humboldt Fellowship in 1997–1998. He is an Associate Editor of the IEEE Transactions on Automatic Control, the IEEE Transactions on Fuzzy Systems and the Journal of Control Theory and Applications. He was an Associate Editor of the IEEE Transactions on Systems, Man, and Cybernetics, Part C, and the Conference Editorial Board of the IEEE Control System Society.
Jinde Cao received the B.S. degree from Anhui Normal University, Wuhu, China, the M.S. degree from Yunnan University, Kunming, China, and the Ph.D. degree from Sichuan University, Chengdu, China, all in mathematics/applied mathematics, in 1986, 1989, and 1998, respectively. From March 1989 to May 2000, he was with Yunnan University. In May 2000, he joined the Department of Mathematics, Southeast University, Nanjing, China. From July 2001 to June 2002, he was a Post doctoral Research Fellow in the Department of Automation and Computer-aided Engineering, Chinese University of Hong Kong, Hong Kong. From August 2002 to October 2002, he was a Senior Visiting Scholar at the Institute of Mathematics, Fudan University, Shanghai, China. From February 2003 to May 2003, he was a Senior Research Associate in the Department of Mathematics, City University of Hong Kong, Hong Kong. From July 2003 to September 2003, he was a Senior Visiting Scholar in the Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei, China. From January 2004 to April 2004, he was a Research Fellow in the Department of Manufacturing Engineering and Engineering Management, City University of Hong Kong, Hong Kong. From January 2005 to April 2005, he was a Research Fellow in the Department of Mathematics, City University of Hong Kong, Hong Kong. From January 2006 to April 2006, he was a Research Fellow in the Department of Electronics Engineering, City University of Hong Kong, Hong Kong. From July 2006 to September 2006, he was a Visiting Research Fellow of Royal Society in the School of Information Systems, Computing and Mathematics, Brunel University, UK. From February 2007 to April 2007, he was a Research Fellow in the Department of Manufacturing Engineering and Engineering Management, City University of Hong Kong, Hong Kong.
He is currently a Professor and Doctoral Advisor at the Southeast University. Prior to this, he was a Professor at Yunnan University from 1996 to 2000. He is the author or coauthor of more than 130 journal papers and five edited books and a reviewer of Mathematical Reviews and Zentralblatt-Math. His research interests include nonlinear systems, neural networks, complex systems and complex networks, control theory, and applied mathematics.
Professor Cao is a Senior Member of the IEEE, and an Associate Editor of the IEEE Transaction on Neural Networks, Journal of the Franklin Institute, Mathematics and Computers in Simulation, and Neurocomputing.