Identification of multivariable bilinear state space systems based on subspace techniques and separable least squares optimization

We discuss identification of discrete-time bilinear state space systems with multiple inputs and multiple outputs. Subspace identification methods for bilinear systems suffer from the curse of dimensionality. Already for relatively low order systems, the matrices involved become so large that the method cannot be used in practice. We have modified the subspace algorithm such that it reduces the dimension of the matrices involved. Only the rows that have the largest influence on the model are selected; the remaining rows are discarded. This obviously leads to an approximation error. The initial model that we get from the subspace method is optimized using the principle of separable least squares. According to this principle, we can first solve for the matrices that enter non-linearly in the output error criterion and then obtain the others by solving a linear least squares problem.

[1]  A. Isidori.  Direct construction of minimal bilinear realizations from nonlinear input-output maps , 1973 .

[2]  C. Bruni,et al.  Bilinear systems: An appealing class of "nearly linear" systems in theory and applications , 1974 .

[3]  H. Spang,et al.  Second-order correlation method for bilinear system identification , 1977, 1977 IEEE Conference on Decision and Control including the 16th Symposium on Adaptive Processes and A Special Symposium on Fuzzy Set Theory and Applications.

[4]  R. Mohler,et al.  Bilinear system identification by Walsh functions , 1978 .

[5]  R. Mohler.  An Overview of Bilinear System Theory and Applications , 1980 .

[6]  Mahmoud M. Gabr,et al.  ON THE IDENTIFICATION OF BILINEAR SYSTEMS FROM OPERATING RECORDS , 1982 .

[7]  B. Cheng,et al.  Analysis and parameter estimation of bilinear systems via block-pulse functions , 1982 .

[8]  W. Larimore.  System Identification, Reduced-Order Filtering and Modeling via Canonical Variate Analysis , 1983, 1983 American Control Conference.

[9]  T. Subba Rao,et al.  On the identification of bilinear systems from operating records , 1984 .

[10]  M. Inagaki,et al.  Bilinear system identification by Volterra kernels estimation , 1984 .

[11]  U. Deasi.  Realization of Bilinear Stochastic Systems , 1985, 1985 American Control Conference.

[12]  M. E. Ahmed,et al.  Parameter estimation in bilinear systems by instrumental variable method , 1986 .

[13]  L. Ljung,et al.  Recursive identification of bilinear systems , 1987 .

[14]  M. Verhaegen.  The minimal residual QR-factorization algorithm for reliably solving subset regression problems , 1987 .

[15]  M. B. Priestley,et al.  Non-linear and non-stationary time series analysis , 1990 .

[16]  Heinz Unbehauen,et al.  Structure identification of nonlinear dynamic systems - A survey on input/output approaches , 1990, Autom..

[17]  Hong Wang,et al.  An improved recursive method for bilinear system identification , 1993 .

[18]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[19]  Michel Verhaegen,et al.  Identification of the deterministic part of MIMO state space models given in innovations form from input-output data , 1994, Autom..

[20]  Charles L. Lawson,et al.  Solving least squares problems , 1976, Classics in applied mathematics.

[21]  Jinyoung Kim,et al.  Extended generalized total least squares method for the identification of bilinear systems , 1996, IEEE Trans. Signal Process..

[22]  A. Zinober,et al.  Strong consistency and convergence rate of parameter identification for bilinear systems , 1996 .

[23]  V. Verdult,et al.  Efficient and systematic identification of MIMO bilinear state space models , 1998, Proceedings of the 37th IEEE Conference on Decision and Control (Cat. No.98CH36171).

[24]  Bart De Moor,et al.  Subspace identification of bilinear systems subject to white inputs , 1999, IEEE Trans. Autom. Control..

[25]  Michel Verhaegen,et al.  Identification of MIMO bilinear state space models using separable least squares , 1999, Proceedings of the 1999 American Control Conference (Cat. No. 99CH36251).

[26]  V. Verdult,et al.  Subspace-based identification of MIMO bilinear systems , 1999, 1999 European Control Conference (ECC).