Delayed Standard Neural Network Models for Control Systems

In order to conveniently analyze the stability of recurrent neural networks (RNNs) and successfully synthesize the controllers for nonlinear systems, similar to the nominal model in linear robust control theory, the novel neural network model, named delayed standard neural network model (DSNNM) is presented, which is the interconnection of a linear dynamic system and a bounded static delayed (or nondelayed) nonlinear operator. By combining a number of different Lyapunov functionals with S-procedure, some useful criteria of global asymptotic stability and global exponential stability for the continuous-time DSNNMs (CDSNNMs) and discrete-time DSNNMs (DDSNNMs) are derived, whose conditions are formulated as linear matrix inequalities (LMIs). Based on the stability analysis, some state-feedback control laws for the DSNNM with input and output are designed to stabilize the closed-loop systems. Most RNNs and neurocontrol nonlinear systems with (or without) time delays can be transformed into the DSNNMs to be stability-analyzed or stabilization-synthesized in a unified way. In this paper, the DSNNMs are applied to analyzing the stability of the continuous-time and discrete-time RNNs with or without time delays, and synthesizing the state-feedback controllers for the chaotic neural-network-system and discrete-time nonlinear system. It turns out that the DSNNM makes the stability conditions of the RNNs easily verified, and provides a new idea for the synthesis of the controllers for the nonlinear systems.

[1]  B. Anderson,et al.  A generalization of the Popov criterion , 1968 .

[2]  Kevin Warwick.  Neural networks: an introduction , 1995 .

[3]  Kazuo Tanaka,et al.  An approach to stability criteria of neural-network control systems , 1996, IEEE Trans. Neural Networks.

[4]  Meiqin Liu,et al.  Stability analysis of discrete-time recurrent neural networks based on standard neural network models , 2009, Neural Computing and Applications.

[5]  Lihua Xie,et al.  Robust H/sub infinity / control for linear systems with norm-bounded time-varying uncertainty , 1992 .

[6]  Jinde Cao,et al.  Global Asymptotical Stability of Recurrent Neural Networks With Multiple Discrete Delays and Distributed Delays , 2006, IEEE Transactions on Neural Networks.

[7]  P. Chandrasekharan.  Robust Control of Linear Dynamical Systems , 1996 .

[8]  John Galletly,et al.  Neural Networks: : An Introduction ‐ 2nd edition , 1998 .

[9]  Xuemei Li,et al.  Exponential stability and global stability of cellular neural networks , 2004, Appl. Math. Comput..

[10]  Ernesto Rios-Patron,et al.  A General Framework for the Control of Nonlinear Systems , 2000 .

[11]  Amir F. Atiya,et al.  How delays affect neural dynamics and learning , 1994, IEEE Trans. Neural Networks.

[12]  Lakhmi C. Jain,et al.  Recurrent Neural Networks: Design and Applications , 1999 .

[13]  Jun Wang,et al.  Global stability of a class of discrete-time recurrent neural networks , 2002 .

[14]  J. Si,et al.  Neural network-based control design: an LMI approach , 1998, Proceedings of the 1998 American Control Conference. ACC (IEEE Cat. No.98CH36207).

[15]  Tsuyoshi Otake,et al.  The template optimization of discrete time CNN for image compression and reconstruction , 2002, 2002 IEEE International Symposium on Circuits and Systems. Proceedings (Cat. No.02CH37353).

[16]  E. Yaz.  Linear Matrix Inequalities In System And Control Theory , 1998, Proceedings of the IEEE.

[17]  P.J. Werbos,et al.  An overview of neural networks for control , 1991, IEEE Control Systems.

[18]  Nikita Barabanov,et al.  Stability analysis of discrete-time recurrent neural networks , 2002, IEEE Trans. Neural Networks.

[19]  Zhigang Zeng,et al.  Improved conditions for global exponential stability of recurrent neural networks with time-varying delays , 2006, IEEE Transactions on Neural Networks.

[20]  Meiqin Liu,et al.  A neural network model and its application , 2004, SMC.

[21]  Korris Fu-Lai Chung,et al.  Global exponential convergence of Cohen-Grossberg neural networks with time delays , 2005, IEEE Trans. Neural Networks.

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

[23]  Xiaofeng Liao,et al.  (Corr. to) Delay-dependent exponential stability analysis of delayed neural networks: an LMI approach , 2002, Neural Networks.

[24]  刘妹琴,et al.  LMI-based approach for global asymptotic stability analysis of continuous BAM neural networks , 2005 .

[25]  L. Xie,et al.  Robust H^∞ Control for Linear Systems with Norm-Bounded Time-Varying Uncertainty , 1990 .

[26]  张森林,et al.  Stability analysis of discrete-time BAM neural networks based on standard neural network models , 2005 .

[27]  Mancia Anguita,et al.  Analog CMOS implementation of a discrete time CNN with programmable cloning templates , 1993 .

[28]  Tsai-Yuan Lin,et al.  An H∞ design approach for neural net-based control schemes , 2001, IEEE Trans. Autom. Control..

[29]  Kazuo Tanaka,et al.  Stability analysis and design of fuzzy control systems , 1992 .

[30]  Johan A. K. Suykens,et al.  Artificial Neural Networks for Modeling and Control of Non-Linear Systems , 1995 .

[31]  Xiaofeng Liao,et al.  New stability conditions for BAM neural networks with time delays , 2000, IEEE APCCAS 2000. 2000 IEEE Asia-Pacific Conference on Circuits and Systems. Electronic Communication Systems. (Cat. No.00EX394).

[32]  Guanrong Chen,et al.  LMI-based approach for asymptotically stability analysis of delayed neural networks , 2002 .