Upper bounds for approximation of continuous-time dynamics using delayed outputs and feedforward neural networks

The problem of approximation of unknown dynamics of a continuous-time observable nonlinear system is considered using a feedforward neural network, operating over delayed sampled outputs of the system. Error bounds are derived that explicitly depend upon the sampling time interval and network architecture. The main result of this note broadens the class of nonlinear dynamical systems for which adaptive output feedback control and state estimation problems are solvable.

[1]  A. Isidori.  Nonlinear Control Systems , 1985 .

[2]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[3]  Manfredi Maggiore,et al.  Output feedback control for stabilizable and incompletely observable nonlinear systems: theory , 2000, Proceedings of the 2000 American Control Conference. ACC (IEEE Cat. No.00CH36334).

[4]  J. Nazuno.  Haykin, Simon. Neural networks: A comprehensive foundation, Prentice Hall, Inc. Segunda Edición, 1999 , 2000 .

[5]  A. Teel,et al.  Global stabilizability and observability imply semi-global stabilizability by output feedback , 1994 .

[6]  Allan Pinkus,et al.  Approximation theory of the MLP model in neural networks , 1999, Acta Numerica.

[7]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[8]  Robert Bartle,et al.  The Elements of Real Analysis , 1977, The Mathematical Gazette.

[9]  A. Barron.  Approximation and Estimation Bounds for Artificial Neural Networks , 1991, COLT '91.

[10]  Anthony J. Calise,et al.  Adaptive output feedback control of uncertain nonlinear systems using single-hidden-layer neural networks , 2002, IEEE Trans. Neural Networks.

[11]  Anthony J. Calise,et al.  Adaptive output feedback control of nonlinear systems using neural networks , 2001, Autom..

[12]  Jooyoung Park,et al.  Approximation and Radial-Basis-Function Networks , 1993, Neural Computation.

[13]  N. Hovakimyan,et al.  An adaptive observer design methodology for bounded nonlinear processes , 2002, Proceedings of the 41st IEEE Conference on Decision and Control, 2002..

[14]  K S Narendra,et al.  Control of nonlinear dynamical systems using neural networks. II. Observability, identification, and control , 1996, IEEE Trans. Neural Networks.

[15]  R. Courant,et al.  Introduction to Calculus and Analysis , 1991 .

[16]  Zhong-Ping Jiang,et al.  A robust adaptive backstepping scheme for nonlinear systems with unmodeled dynamics , 1999, IEEE Trans. Autom. Control..

[17]  Andrew R. Barron,et al.  Universal approximation bounds for superpositions of a sigmoidal function , 1993, IEEE Trans. Inf. Theory.

[18]  Hassan K. Khalil,et al.  Output feedback control of nonlinear systems using RBF neural networks , 2000, IEEE Trans. Neural Networks Learn. Syst..

[19]  Jooyoung Park,et al.  Universal Approximation Using Radial-Basis-Function Networks , 1991, Neural Computation.

[20]  A. Tornambè.  Output feedback stabilization of a class of non-minimum phase nonlinear systems , 1992 .