Asymptotic properties of least-squares estimates of Hammerstein-Wiener models

This paper investigates the asymptotic properties of least squares estimates of Hammerstein-Wiener model structures, and in doing so establishes consistency and asymptotic normality under fairly mild conditions on the additive noise process, the inputs and the static non-linearities. In relation to the asymptotic distributional results, a consistent procedure for the estimation of the asymptotic variance of the parameter estimates is provided. A key theme of this paper is to demonstrate how recent results from the econometrics literature may be employed in an engineering setting. In this respect the Hammerstein-Wiener model structure serves as a demonstration example. A simulation study complements the theoretical findings.

[1]  Raimund J. Ober,et al.  Balanced realizations: canonical form, parametrization, model reduction , 1987 .

[2]  K. Poolla,et al.  New results for Hammerstein system identification , 1995, Proceedings of 1995 34th IEEE Conference on Decision and Control.

[3]  D. Andrews.  Laws of Large Numbers for Dependent Non-Identically Distributed Random Variables , 1988, Econometric Theory.

[4]  L. Ljung.  Nonlinear Black Box Models in Systems Identification , 1997 .

[5]  Brian D. O. Anderson,et al.  A Parametrization for the closed-loop identification of nonlinear time-varying systems , 1996, Autom..

[6]  Håkan Hjalmarsson,et al.  Aspects on Incomplete Modeling in System Identification , 1993 .

[7]  Eduardo D. Sontag,et al.  For neural networks, function determines form , 1992, [1992] Proceedings of the 31st IEEE Conference on Decision and Control.

[8]  Brett Ninness,et al.  Quantifying the accuracy of Hammerstein model estimation , 2000, Autom..

[9]  L. Ljung,et al.  Asymptotic normality of prediction error estimators for approximate system models , 1978, 1978 IEEE Conference on Decision and Control including the 17th Symposium on Adaptive Processes.

[10]  H. White,et al.  A Unified Theory of Estimation and Inference for Nonlinear Dynamic Models , 1988 .

[11]  Tor Arne Johansen,et al.  On Tikhonov regularization, bias and variance in nonlinear system identification , 1997, Autom..

[12]  Wlodzimierz Greblicki,et al.  Nonlinearity estimation in Hammerstein systems based on ordered observations , 1996, IEEE Trans. Signal Process..

[13]  Kurt Hornik,et al.  Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks , 1990, Neural Networks.

[14]  T. W. Anderson,et al.  Statistical analysis of time series , 1972 .

[15]  S. A. Billings,et al.  Identification of continuous time nonlinear systems using delayed state variable filters , 1994 .

[16]  D. Signorini,et al.  Neural networks , 1995, The Lancet.

[17]  E. Hannan,et al.  The statistical theory of linear systems , 1989 .

[18]  L. Ljung.  Convergence analysis of parametric identification methods , 1978 .

[19]  B. M. Pötscher,et al.  Dynamic Nonlinear Econometric Models , 1997 .

[20]  P. Caines,et al.  Asymptotic normality of prediction error estimators for approximate system models , 1980 .

[21]  D. McLeish.  A Maximal Inequality and Dependent Strong Laws , 1975 .

[22]  Lennart Ljung,et al.  System Identification: Theory for the User , 1987 .

[23]  Bernard Delyon,et al.  Nonlinear black-box models in system identification: Mathematical foundations , 1995, Autom..

[24]  Gang Tao,et al.  Adaptive Control of Systems with Actuator and Sensor Nonlinearities , 1996 .

[25]  Lennart Ljung,et al.  Nonlinear black-box modeling in system identification: a unified overview , 1995, Autom..

[26]  E. Hannan,et al.  The Statistical Theory of Linear Systems. , 1990 .

[27]  Torsten Bohlin,et al.  Issues in Nonlinear Stochastic Grey-Box Identification , 1994 .