» Download Article

Authors
Sunil L. Kukreja; Johan Lofberg; Martin J. Brenner

Identifier
10.3182/20060329-3-AU-2901.00128

Index Terms
system identification,nonlinear systems,structure detection,aeroelasticity

Abstract
Identification of parametric nonlinear models involves estimating unknown parameters and detecting its underlying structure. Structure computation is concerned with selecting a subset of parameters to give a parsimonious description of the system which may afford greater insight into the functionality of the system or a simpler controller design. In this study, a least absolute shrinkage and selection operator (LASSO) technique is investigated for computing efficient model descriptions of nonlinear systems. The LASSO minimises the residual sum of squares by the addition of a l1 penalty term on the parameter vector of the traditional l2 minimisation problem. Its use for structure detection is a natural extension of this constrained minimisation approach to pseudolinear regression problems which produces some model parameters that are exactly zero and, therefore, yields a parsimonious system description. The performance of this LASSO structure detection method was evaluated by using it to estimate the structure of a nonlinear polynomial model. Applicability of the method to more complex systems such as those encountered in aerospace applications was shown by identifying a parsimonious system description of the F/A-18 Active Aeroelastic Wing using flight test data.

References

[1] Chen, S. S., D. L. Donoho and M. A. Saunders (2001).
    Atomic decomposition by basis pursuit. SIAM J.
    Sci. Comput. 43(1), 129-159.
[2] Draper, N. R. and H. Smith (1981). Applied Regression
    Analysis. second ed., John Wiley & Sons. New
    York.
[3] Grigoriadis, M. D. and K. Ritter (1969). A parametric
     method for semidefinite quadratic programs.
    SIAM J. Control 7(4), 559-577.
[4] Kukreja, S. L., H. L. Galiana and R. E. Kearney (2004).
    A bootstrap method for structure detection of
    NARMAX models. Int. J. Cont. 77(2), 132-143.
[5] Kvasnica, M., P. Grieder, M. Baotić and M. Morari
    (2004). Multi Parametric Toolbox (MPT). In:
    Hybrid Systems: Computation and Control. Vol.
    2993 of Lecture Notes in Computer Science.
    Springer Verlag. Philadelphia. pp. 448-462.
[6] Leontaritis, I. J. and S. A. Billings (1985a). Input-output
     parametric models for non-linear systems
    part I: deterministic non-linear systems. Int. J.
    Control 41(2), 303-328.
[7] Leontaritis, I. J. and S. A. Billings (1985b). Input-output
     parametric models for non-linear systems
    part II: stochastic non-linear systems. Int. J. Control
     41(2), 329-344.
[8] Ljung, L. (1999). System Identification: Theory for the
    User. second ed., Prentice Hall, Inc., Englewood
    Cliffs, New Jersey.
[9] Mészáros, C. (1998). The BPMPD interior point
    solver for convex quadratic problems. Technical
    Report 98-8. Hungarian Acad. of Sci., Budapest.
[10] Osborne, M. R., B. Presnell and B. A. Turlach (2000).
     On the lasso and its dual. J. Comp. Graph. Stat.
     9(2), 319-337.
[11] Pendleton, E. W., D. Bessette, P. B. Field, G. D. Miller
     and K. E. Griffin (2000). Active aeroelastic wing
     flight research program: Technical program and
     model analytical development. AIAA J. Aircraft
     37(4), 554-561.
[12] Shao, J. (1993). Linear model selection by cross-validation.
      J. American Stat. Assoc. 88, 486-494.
[13] Smith, R. S. (1995). Model validation for robust control:
      An experimental process control application.
      Automatica 31(11), 1637-1647.
[14] Tibshirani, R. (1996). Regression shrinkage and selection
      via the lasso. J. R. Statist. Soc. B 58(1), 267-
     288.