» Download Article

Authors
Kenneth Hsu; Tyrone Vincent; Kameshwar Poolla

Identifier
10.3182/20060329-3-AU-2901.00194

Index Terms
nonlinear system identification,kernel,identifiability,persistence of excitation,convergence

Abstract
In (Hsu et al., 2005c), an algorithm for the identification of structured nonlinear systems was proposed and its computational properties were explored. In this paper, we continue the investigation and formalize notions of identifiability and persistence of excitation. Conditions under which the estimated nonlinearity converges uniformly to the true nonlinearity are developed for a class of kernel based dispersion functions.

References

[1] Aronszajn, N. (1950). Theory of reproducing kernels.
     Trans. Amer. Math. Soc. 68, 337-404.
[2] Barron, A. R. (1993). Uniform approximation
    bounds for superpositions of a sigmoidal function.
     IEEE Transactions on Information Theory
     39, 930-945.
[3] Claassen, M. (2001). System identification for
    structured nonlinear systems. Ph.D. Dissertation,
     University of California at Berkeley.
[4] Greblicki, W. (1997). Nonparametric approach to
    wiener system identification. IEEE Transactions
     on Circuits and Systems 44, 538-545.
[5] Hsu, K., C. Novara, M. Milanese and K. Poolla
    (2005a). Parametric identification of static
    nonlinearities in a general interconnected system.
     Proceedings of the 16th IFAC World
    Congress.
[6] Hsu, K., M. Claassen, C. Novara, P. Khargonekar,
    M. Milanese and K. Poolla (2005b). Nonparametric
     identification of static nonlinearities in
    a general interconnected system. Proceedings
    of the 16th IFAC World Congress.
[7] Hsu, K., T. Vincent and K. Poolla (2005c). A
    kernel based approach to structured nonlinear
     system identification part I: Algorithms.
    Proceedings of the 2006 IFAC Symposium on
    System ID.
[8] Hsu, K., T. Vincent, C. Novara, M. Milanese and
    K. Poolla (2005d). Identification of nonlinear
    maps in interconnected systems. Proceedings
    of the 2005 Conference on Decision and Control
    .
[9] Juditsky, A., H. Hjalmarsson, A. Benveniste,
    B. Delyon, L. Ljung, J. Sjöberg and Q. Zhang
    (1995). Nonlinear black-box models in system
     identification: Mathematical foundations.
     Automatica 31, 1725-1750.
[10] Ljung, L. (1999). System Identification Theory for
     the User, 2nd Edition. Prentice Hall. Upper
     Saddle River, N.J.
[11] Schölkopf, B. and A. J. Smola (2002). Learning
     with Kernels. MIT Press. Cambridge.
[12] Sjöberg, J., Q. Zhang, L. Ljung, A. Benveniste,
     B. Delyon, P. Y. Glorennec, H. Hjalmarsson
     and A. Juditsdy (1995). Nonlinear black-box
     modeling in system identification: A unified
     overview. Automatica 31, 1691-1724.
[13] Suykens, J. A. K., T. V. Gestel, J. D. Brbanter,
     B. De Moor and J. Vanderwalle (2002). Least
     squares support vector machines.
[14] Wemhoff, E. (2003). Signal estimation in structured
      nonlinear systems with unknown functions.
      Ph.D. Dissertation, University of California
      at Berkeley.
[15] Wemhoff, E., A. Packard and K. Poolla (1999).
     On the identification of nonlinear maps in a
     general interconnected system. Proceedings of
     the 1999 American Controls Conference.