» Download Article

Authors
Bo Wahlberg; Hakan Hjalmarsson; Marta Barenthin

Identifier
10.3182/20060329-3-AU-2901.00076

Index Terms
system identification,input design,robust control,model validation,linear quadratic control

Abstract
System identification concerns the construction and validation of mathematical models of dynamical systems from experimental data. The objective of this contribution is to discuss new research directions in experiment design, e.g. how to design informative experiments which satisfy specifications on the resulting model quality and practical limitations such as constraints on input and output signals, but also experimental time. In particular, we discuss how input design is instrumental for alleviating the problem of modelling complex systems. Many optimal experiment design problems can be formulated as optimal control problems, but with nonstandard cost functions. A difficulty is that the solution often depends on the true system. To solve optimal control problems, we can exploit recent advances in numerical optimization for control design, including convex optimization and relaxation methods. As a more concrete example, we study how to estimate the H∞ norm of a system.

References

[1] Alkire, B. and L. Vandenberghe (2002). Convex optimization
     problems involving finite autocorrelation
     sequences. Mathematical Programming, Series
     A 93, 331-359.
[2] Åström, K. J. and T. Hägglund (1984). Automatic
    tuning of simple regulators with specifications
    on phase and amplitude margin. Automatica
    20(5), 645-651.
[3] Barenthin, M. and H. Hjalmarsson (2005). Identification
     and control: Joint input design and H∞ state
    feedback with ellipsoidal parametric uncertainty.
    In: IEEE Conference on Decision and Control.
    Seville, Spain. To appear.
[4] Barenthin, M., B. Wahlberg, M. Enqvist and H. Hjalmarsson
     (2006). Gain estimation for hammerstein
     systems. In: IFAC Symposium on System
    Identification. Newcastle, Australia. To appear.
[5] Barenthin, M., H. Mosskull, H. Hjalmarsson and
    B. Wahlberg (2005). Validation of stability for an
    induction machine drive using power iterations.
    In: 16th World Congress on Automatic Control.
    IFAC. Prague.
[6] Barker, H. A., A. H. Tan and K. R. Godfrey (2004a).
    Criteria for determining the optimal levels of
    multilevel perturbation signals for nonlinear
    system identification. In: Proceedings American
     Control Conference. Denver, Colorado.
    pp. 4409-4414.
[7] Barker, H. A., A. H. Tan and K. R. Godfrey (2004b).
    Design of multi-level perturbation signals with
    harmonic properties suitable for nonlinear system
    identification. IEE Proceedings - Control Theory
    and Applications 151(2), 145-151.
[8] Bittanti, S. (1991). The periodic riccati equation. In:
    The Riccati Equation (A. J. Laub S. Bittanti
    and J. C. Willems, Eds.). pp. 127-162. Springer-Verlag.
    
[9] Bombois, X., G. Scorletti, M. Gevers, R. Hildebrand
    and P. Van den Hof (2004). Cheapest open-loop
    identification for control. In: Conference on Decision
     and Control. IEEE. Paradise Island, Bahamas.
    
[10] Braun, M. W., R. Ortiz-Mojica and D. E. Rivera (2002).
     Design of minimum crest factor multisinusoidal
     signals for plant-friendly identification of nonlinear
      process systems. Control Engineering Practice
      3(3), 301-313.
[11] Cohn, D. A., Z. Ghabramani and M. I. Jordan (1996).
     Active learning with statistical models. J. Artif.
     Intell. Res. 4, 129-145.
[12] Davidsson, T. N., Z.-Q. Luo and J. F. Sturm (2002).
     Linear matrix inequality formulation of spectral
      mask constraints with applications to FIR
     filter design. IEEE Trans. Signal Processing
     50(11), 2702-2715.
[13] Dumitrescu, B., I. Tabus and P. Stoica (2001). On
     the parameterization of positive real sequences
     and ma parameter estimation. IEEE Trans. Sign
     Process 49, 2630-2639.
[14] Forssell, U. and L. Ljung (2000). Some results on optimal
      experiment design. Automatica 36(5), 749-
     756.
[15] Gerencsér, L. and H. Hjalmarsson (2005). Adaptive
     input design in system identification. In: IEEE
     Conference on Decision and Control. Seville,
     Spain. to appear.
[16] Gevers, M. and L. Ljung (1986). Optimal experiment
     designs with respect to the intended model application.
      Automatica 22(5), 543-554.
[17] Goodwin, G. and R. L. Payne (1977). Dynamic System
      Identification: Experiment Design and Data
     Analysis. Academic Press. New York.
[18] Hjalmarsson, H. (2005). From experiment design to
     closed loop control. Automatica 41, 393-438.
[19] Hjalmarsson, H., M. Gevers and F. De Bruyne (1996).
     For model based control design criteria, closed
     loop identification gives better performance. Automatica
      32(12), 1659-1673.
[20] Iwasaki, T. and S. Hara (2005). Generalized KYP
     Lemma: Unified frequency domain inequalities
     with design applications. IEEE Trans. Automat.
     Control 50(1), 41-59.
[21] Jansson, H. and H. Hjalmarsson (2004a). A framework
      for mixed H∞ and H2 input design. In:
     MTNS'04. Leuven, Belgium.
[22] Jansson, H. and H. Hjalmarsson (2004b). A general
     framework for mixed H∞ and H2 input design.
     IEEE Transactions on Automatic Control. to appear.
     
[23] Jansson, H. and H. Hjalmarsson (2004c). Mixed H∞
     and H2 input design. In: IEEE Conference on
     Decision and Control. Bahamas.
[24] Karimi, A., D. Garcia and R. Longchamp (2002). Iterative
      controller tuning using Bode's integrals. In:
     Proceedings 41st IEEE Conference on Decision
     and Control. Las Vegas, Nevada. pp. 4227-4232.
[25] Kell, D. B. and S. G. Oliver (2003). Here is the evidence,
      now what is the hypothesis? The complementary
      roles of inductive and hypothesisdriven
      science in the post-genomic era. BioEssays
      26, 99-105.
[26] Lacy, S. L., D. S. Bernstein and R. S. Erwin (2003).
     Finite-horizon input selection for system identification.
      In: Proceedings 42nd IEEE Conference
     on Decision and Control. pp. 6485-6490.
[27] Landau, I. D. (2001). Identification in closed loop: a
     powerful design tool (better design models, simpler
      controllers). Control Engineering Practice
     9, 51-65.
[28] Lee, J. H. (2003). Control-relevant design of periodic
     test input signals for iterative open-loop identification
      of multivariable FIR systems. In: Proceedings
      13th IFAC Symposium on System Identification
     . Rotterdam, The Netherlands. pp. 935-940.
[29] Lindqvist, K. and H. Hjalmarsson (2000). Optimal input
      design using linear matrix inequalities. In:
     SYSID 2000, IFAC Symp. on System Identification
     .
[30] Lindqvist, K. and H. Hjalmarsson (2001). Identification
      for control: Adaptive input design using
     convex optimization. In: Proceedings 40th IEEE
     Conference on Decision and Control. Orlando,
     Florida, USA.
[31] Ljung, L. (1999). System Identification: Theory for the
     User. 2nd ed., Prentice-Hall. Englewood Cliffs,
     NJ.
[32] Mårtensson, J. and H. Hjalmarsson (2006). Robust
     input design using sum of squares constraints.
     In: IFAC Symposium on System Identification.
     Newcastle, Australia. To appear.
[33] Mårtensson, J., H. Hjalmarsson and B. Wahlberg
     (2006). On some robustness issues in input design.
      In: IFAC Symposium on System Identification
     . Newcastle, Australia. To appear.
[34] Mehra, R. (1974). Optimal inputs for linear system
     identification. IEEE Transactions on Automatic
     Control AC. 19(3), 192-200.
[35] Mårtensson, J., H. Jansson and H. Hjalmarsson
     (2005). Input design for identification of zeros.
     In: 16th World Congress on Automatic Control.
     IFAC. Prague.
[36] Pintelon, R. and J. Schoukens (2001). System Identification.
      A frequency domain approach. Wiley-IEEE
      Press.
[37] Prajna, S., P. A. Parillo and A. Rantzer (2004). Non-linear
      control synthesis by convex optimization.
     IEEE Trans. Automat. Control 49(2), 310-314.
[38] Richards, J. A. (1983). Analysis of periodically time
     varying systems. Communications and control
     engineering series. Springer-Verlag.
[39] Rivera, D. E., H. Lee, M. W. Braun and H. D. Mittelmann
      (2003). Plant-friendly system identification:
      A challenge for the process industries.
     In: Proceedings 13th IFAC Symposium on System
      Identification. Rotterdam, The Netherlands.
     pp. 917-922.
[40] Sjöberg, J., Q. Zhang L. Ljung, A. Benveniste, B. Deylon,
      P.-Y. Glorennec, H. Hjalmarsson and A. Juditsky
      (1995). Nonlinear black-box models in
     system identification: a unified overview. Automatica
      31, 1691-1724.
[41] Varga, A. (2003). Periodic lyapunov equations: some
     applications and new algorithms. International
     Journal of Control 67(1), 69-88.
[42] Zarrop, M. (1979). Design for Dynamic System Identification
     . Lecture Notes in Control and Information
      Sciences. Sci. 21. Springer Verlag, Berlin.
[43] Zhao, J. and I. Kanellakopoulos (2002). Active identification
      for discrete-time nonlinear control - part
     i: Output-feedback systems. IEEE Transactions
     on Automatic Control 47, 210-224.
[44] Zhu, Y. C. and P. P. J. van den Bosch (2000). Optimal
     closed-loop identification test design for internal
     model control. Automatica 36, 1237-1241.