Modeling and Identification of Hammerstein System by using Triangular Basis Functions

This paper deals with modeling and parameter identification of nonlinear systems described by Hammerstein model having Piecewise nonlinear characteristics such as Dead-zone nonlinearity characteristic. The simultaneous use of both an easy decomposition technique and the triangular basis functions leads to a particular form of Hammerstein model. The approximation by using Triangular basis functions for the description of the static nonlinear block conducts to a linear regressor model, so that least squares techniques can be used for the parameter estimation. Singular Values Decomposition (SVD) technique has been applied to separate the coupled parameters. The proposed approach has been efficiently tested on academic examples of simulation.

Authors:

• K. Elleuch
• A. Chaari

Keywords:

• Identification
• Hammerstein model
• Piecewisenonlinear characteristic
• Dead-zone nonlinearity
• Triangular basisfunctions
• Singular Values Decomposition

References:

[1] Bai E.W., "Identification of linear systems with hard input nonlinearities
of known structure," Automatica, 2002, vol. 38, no. 5, pp. 853-860.
[2] Kara T., and Eker I., "Nonlinear modelling and identification of a DC
motor for bidirectional operation with real time experiments," 2004,
Energy Conversion and Management, vol. 45, pp. 1087-1106.
[3] T. H. van Pelt and D. S Bernstein, "Nonlinear system identification
using Hammerstein and nonlinear feedback models with piecewice linear
static maps," 2001, Int. J. Control, vol. 74, n┬░ 18, pp. 1807-1823.
[4] Vörös J., "Parameter Identification of Discontinuous Hammerstein
Systems," 1997, Automatica 33 No. 6, 1141-1146.
[5] Vörös J., "Iterative algorithm for parameter identification of
Hammerstein systems with two-segment nonlinearities," 1999, IEEE
Transactions on Automatic Control (44). pp. 2145-2149.
[6] Vörös J., "Modelling and parameter identification of systems with multi
segment piecewise-linear characteristics," 2002, IEEE Transactions on
Automatic Control, vol. AC 47, N┬░ 1, pp. 184-188.
[7] Elleuch K., M. Kharrat, A. Chaari and M. Chaabane, "Modeling and
identification of block-oriented heat transfer process," Int. J. of
Information and Systems Sciences, 2009, vol. 5, n┬░ 1. , pp. 41-56.
[8] Ljung L., "System Identification: Theory for the User," 1999, second
ed., Prentice-Hall, Inc., Englewood Cliffs, NJ.
[9] Chidambaram M., "Computer Control of Processes, 2001," New York:
CRC.
[10] Kung, M. C. and Womack, B. F., "Discrete time adaptive control of
linear systems with preload nonlinearity," 1984b, Automatica 20, 477-
479.
[11] Guo F., G. Bretthauer, "Identification of MISO Wiener and
Hammerstein systems," 2003, Proceedings of the 7th European Control
Conference, TEE, University of Cambridge, UK, September.
[12] Vörös J., "Identification of Hammerstein systems with time-varying
piecewise-linear characteristics nonlinearities," 2005, Journal of
electrical engineering, vol. 57, No. 1, pp. 42-46.
[13] Zhu Y., "Estimation of an N-L-N Hammerstein-Wiener model", 2002,
Automatica, vol. 38, no. 9, pp. 1607-1614.
[14] Vörös J., "Recursive Identification of Systems with Noninvertible
Output Nonlinearities" 2010, Informatica, , Vol. 21, No. 1, 139-148.
[15] Billings S., S. Fakhouri, "Identification of systems containing linear
dynamic and static nonlinear elements," Automatica, 1982, pp. 15-26.
[16] Gomez J.C., E. Baeyens, "Identification of nonlinear systems using
orthonormal bases," 2001, Proceedings of the IASTED International
Conference on Intelligent Systems and Control, Clearwater, FL, USA,
November, pp. 126-131.
[17] Gomez J.C., E. Baeyens, "Identification of block-oriented nonlinear
systems using orthonormal bases," 2004, Journal of Process Control 14,
pp. 685-697.
[18] Chaari A., K. Elleuch, M. Kharrat and S. Kamoun, "Identification of
discrete time nonlinear system described by Hammerstein model:
Application to a thermal system," ICGST, Automatic Control and
Systems Engineering, ACSE journal, 2006, Vol. 6, Issue (2): pp. 63-69.
[19] Dolanc G. and S. Strmcnik, "Identification of nonlinear systems using a
piecewise-linear Hammerstein model," Syst. Contr. Lett., 2005, vol. 54,
no. 2, pp. 145-158.
[20] Gu, X., Bao, Y. and Lang, Z., "A parameter identification method for a
class of discrete time nonlinear systems," 1988,. In Proc. 12fh IMACS
World Congress, Paris, Vol. 4, pp. 627-629.
[21] Golub G., C. Van Loan, "Matrix Computations," 1989, second ed., The
Johns Hopkins University Press, Baltimore and London.
[22] Hasiewicz Z., M. Pawlak, and P. Sliwinski, "Nonparametric
identification of nonlinearities in block-oriented systems by orthogonal
wavelets with compact support," Feb. 2005, IEEE Trans. Circuits Syst. I,
Reg. Papers, vol. 52, no. 2, pp. 427-442.
[23] Lang Z. Q., "Controller design oriented model identification method
system, Identification of Hammerstein system," 1993, Automatica, vol.
29, n┬░. 3, pp. 767-771.
[24] Ninness B., F. Gustafsson, "A unifying construction of orthonormal
bases for system identification," 1997, IEEE Transactions on Automatic
Control AC-42 (4), pp. 515-521.
[25] Pearson R., M. "Pottmann, Gray-box identification of block-oriented
nonlinear models," 2000, Journal of Process Control 10, pp. 301-315.
[26] Tao G. and M. Tian, "Discrete-time adaptive control of systems with
multisegment piecewise-linear nonlinearities," May.1998, IEEE Trans.
Autom. Control, vol. 43, no. 5, pp. 719-723.
[27] Vörös J., "Recursive Identification of Systems with Noninvertible
Output Nonlinearities" 2010, Informatica, , Vol. 21, No. 1, 139-148.