Abstract
In this paper, we extend the deterministic learning theory to sampled-data nonlinear systems. Based on the Euler approximate model, the adaptive neural network identifier with a normalized learning algorithm is proposed. It is proven that by properly setting the sampling period, the overall system can be guaranteed to be stable and partial neural network weights can exponentially converge to their optimal values under the satisfaction of the partial persistent excitation (PE) condition. Consequently, locally accurate learning of the nonlinear dynamics can be achieved, and the knowledge can be represented by using constant-weight neural networks. Furthermore, we present a performance analysis for the learning algorithm by developing explicit bounds on the learning rate and accuracy. Several factors that influence learning, including the PE level, the learning gain, and the sampling period, are investigated. Simulation studies are included to demonstrate the effectiveness of the approach.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
Ljung L. System Identification: Theory for the User. 2nd ed. Englewood Cliffs, NJ: Prentice Hall, 1999
Gevers M A. A personal view of the development of system identification. IEEE Contr Syst Mag, 2006, 26: 93–105
Poggio T, Girosi F. Networks for approximation and learning. P IEEE, 1990, 78: 1481–1497
Jagannathan S. Neural Network Control of Nonlinear Discrete-Time Systems. Boca Raton: CRC Press, 2006
Kosmatopoulos E B, Christodoulou M A, Ioannou P A. Dynamical neural networks that ensure exponential identification error convergence. Neural Netw, 1997, 10: 299–314
Lu S, Basar T. Robust nonlinear system identification using neural-network models. IEEE Trans Neural Netw, 1998, 9: 407–429
Sanner R M, Slotine J E. Gaussian networks for direct adaptive control. IEEE Trans Neural Netw, 1992, 3: 837–863
Kurdila A J, Narcowich F J, Ward J D. Persistency of excitation in identification using radial basis function approximations. SIAM J Control Optim, 1995, 33: 625–642
Gorinevsky D. On the persistency of excitation in radial basis function network identification of nonlinear systems. IEEE Trans Neural Netw, 1995, 6: 1237–1244
Wang C, Hill D J. Learning form neural control. IEEE Trans Neural Netw, 2006, 17: 130–146
Vapnik V N. Statistical Learning Theory: Adaptive and Learning Systems for Signal Processing, Communications, and Control. NewYork: Wiley, 1998
Narendra K S, Annaswamy A M. Stable Adaptive Systems. New Jersey: Prentice-Hall, 1989
Sastry S, Bodson M. Adaptive Control: Stability, Convergence, and Robustness. New Jersey: Prentice-Hall, 1989
Wang C, Hill D J. Deterministic learning and rapid dynamical pattern recognition. IEEE Trans Neural Networ, 2007, 18: 617–630
Xue Z, Wang C, Liu T. Deterministic learning and robot manipulator control. In: Proceedings of IEEE International Conference on Robotics and Biomimetics, Sanya, 2007. 1989–1994
Wang C, Chen T. Rapid detection of oscillation faults via deterministic learning. In: Proceedings of 8th IEEE International Conference on Control and Automation, Xiamen, 2010. 1629–1634
Narendra K S, Parthasarathy K. Identification and control of dynamic systems using neural networks. IEEE Trans Neural Networ, 1990, 1: 4–27
Jagannathan S, Lewis F L. Identification of nonlinear dynamical systems using multilayer neural networks. Automatica, 1996, 32: 1707–1712
Wang C, Chen T, Liu T. Deterministic learning and data-based modeling and control. ACTA Automat Sin, 2009, 35: 693–706
Anderson B D O, Bitmead R R, Johnson C R, et al. Stability of Adaptive Systems. Cambridge, MIT Press, 1986
Wang C, Hill D J. Deterministic Learning Theory for Identification, Recognition and Control. Boca Raton: CRC Press, 2009
Anderson B O, Johnson C R. Exponential convergence of adaptive identification and control algorithms. Automatica, 1982, 18: 1–13
Park J, Sandberg I W. Universal approximation using radial-basis-function networks. Neural Comput, 1991, 3: 246–257
Lo J T. Finite-dimensional sensor orbits and optimal nonlinear filtering. IEEE Trans Inform Theory, 1972, 18: 583–588
Bai E W, Sastry S S. Persistency of excitation, sufficient richness and parameter convergence in discrete time adaptive control. Syst Control Lett, 1985, 6: 153–163
Shilnikov L P. Methods of Qualitative Theory in Nonlinear Dynamics, Part II. Singapore: World Scientific, 2001
Liu T, Wang C, Hill D J. Deterministic learning and rapid dynamical pattern recognition of discrete-time systems. In: Proceedings of 2008 IEEE Multi-Conference on Systems and Control, San Antonio, 2008. 1091–1096
Kudva P, Narendra K S. An identification procedure for discrete multivariable systems. IEEE Trans Automat Contr, 1974, 19: 549–552
Bitmead P R, Anderson B D O. Lyapunov techniques for the exponential stability of linear difference equations with random coefficients. IEEE Trans Automat Contr, 1980, 25: 782–787
Yuan C, Wang C. Persistency of excitation and performance of deterministic learning. Syst Control Lett, 2011, 60: 952–959
Ioannou P A, Sun J. Robust Adaptive Control. Englewood Cliffs: Prentice Hall, 1995
Tao G, Ioannou P A. Persistency of excitation and overparameterization in model reference adaptive control. In: Proceedings of 27th IEEE Conference on Decision and Control, Austin, 1988. 757–758
Rossler O E. An equation for continuous chaos. Phys Lett, 1976, 57: 397–398
Sondhi M M, Mitra D. New results on the performance of a well-known class of adaptive filters. P IEEE, 1976, 64: 1583–1597
Weiss A, Mitra D. Digital adaptive filters: conditions for convergence, rates of convergence, effects of noise and errors arising from the implementation. IEEE Trans Inform Theory, 1979, 25: 637–652
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Open Access This article is distributed under the terms of the Creative Commons Attribution 2.0 International License ( https://creativecommons.org/licenses/by/2.0 ), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
About this article
Cite this article
Yuan, C., Wang, C. Design and performance analysis of deterministic learning of sampled-data nonlinear systems. Sci. China Inf. Sci. 57, 1–18 (2014). https://doi.org/10.1007/s11432-012-4731-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11432-012-4731-3