Study of conditional ML estimators in time and frequency-domain system identification

DOI10.1016/S0005-1098(98)00140-XMaRDI QIDQ1295116zbMATH OpenFDO

Authors Johan Schoukens, Rik Pintelon, Y. Rolain

Publication date 5 December 1999

Published in Automatica (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/S0005-1098(98)00140-X

zbMATH Keywords

covariance matrixfrequency domainidentificationinitial conditionmain diagonalmaximum likelihood estimationnoise model

Mathematics Subject Classification ID

System identification (93B30)

Review text

Linear dynamic systems are considered in the time domain and in the frequency domain. It is shown that the full covariance matrix can be replaced by its main diagonal in maximum likelihood estimation, and both respective estimates have an identical asymptotical behaviour. The result is very important because it provides a theoretical justification for the common practise to neglect the initial condition effects of the noise model.

Recommendations

• Optimally conditioned instrumental variable approach for frequency-domain system identification
• Maximum likelihood estimators and worst case optimal algorithms for system identification
• Identification of time-varying systems using combined parameter estimation and filtering
• Consistent identification of Wiener systems: a machine learning viewpoint
• Identification of Time-Varying Autoregressive Systems Using Maximuma PosterioriEstimation
• Identification of continuous-time systems. Linear and robust parameter estimation
• On the identification of models with conditional characteristic functions
• Mixed model identification for linear time-invariant systems with mixed noises in frequency domain
• Worst-case conditional system identification in a general class of norms
• On the equivalence of time and frequency domain maximum likelihood estimation

Cited in

(7)

• An estimator of the inverse covariance matrix and its application to ML parameter estimation in dynamical systems
• Identification of linear systems with nonlinear distortions
• Dual time-frequency domain system identification
• A note on the estimation of real- and complex-valued parameters in frequency domain maximum likelihood identification
• Box-Jenkins identification revisited. I: Theory
• Grey-box state-space identification of nonlinear mechanical vibrations
• Box-Jenkins alike identification using nonparametric noise models

This page was built for publication: Study of conditional ML estimators in time and frequency-domain system identification

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1295116)