New identification approaches for disturbed models

DOI10.1016/S0005-1098(03)00147-XMaRDI QIDQ1400943zbMATH OpenOpenAlexFDO

Authors Kueiming Lo, Wook Hyun Kwon

Publication date 17 August 2003

Published in Automatica (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/s0005-1098(03)00147-x

zbMATH Keywords

autoregressive exogenous noise interference modelDisturbed modelEmpirical frequency-domainGeneral prediction errorOptimal frequency-domain estimationoptimal parameter estimatesSystem identification

Mathematics Subject Classification ID

Frequency-response methods in control theory (93C80) Identification in stochastic control theory (93E12)

Review text

The time-domain and the frequency domain estimates are combined to identify the autoregressive exogenous noise interference model. The concept of a general prediction error criterion is introduced for the time-domain estimate, and an optimal frequency estimation is proposed for the frequency domain estimate. An identification method, called the empirical frequency-domain optimal parameter estimate, is suggested for disturbed systems. The algorithm provides the global optimum frequency-domain estimate of the model. Some simulations illustrate the identification method.

Recommendations

• Frequency domain identification of FIR models in the presence of additive input-output noise
• Time and frequency identification methods in over-determined systems
• scientific article; zbMATH DE number 52962
• An identification algorithm for dynamical systems with a functional in the frequency domain
• A time-domain approach to z-domain model identification

Cites work

• A metric for ARMA processes
• Cepstral coefficients, covariance lags, and pole-zero models for finite data strings
• Finite sample properties of system identification of ARX models under mixing conditions
• Identification of unstable systems using output error and Box-Jenkins model structures
• Integral constraints on the accuracy of least-squares estimation
• On the choice of norms in system identification
• Recursive estimation methods for discrete systems
• Subspace-based identification of infinite-dimensional multivariable systems from frequency-response data

Cited in

(6)

• Frequency domain identification of FIR models in the presence of additive input-output noise
• Recursive algorithm for the two-stage EFOP estimation method
• scientific article; zbMATH DE number 4139565 (Why is no real title available?)
• Time and frequency identification methods in over-determined systems
• A Frequency Domain Identification Scheme for Control and Fault Diagnosis
• Mixed model identification for linear time-invariant systems with mixed noises in frequency domain

This page was built for publication: New identification approaches for disturbed models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1400943)