Approximative weighting for a covariance-matching approach for identifying errors-in-variables systems

Abstract

A covariance-matching approach for identifying errors-in-variables systems has previously been proposed and analyzed. It has been demonstrated that the gain in accuracy can be substantial if an optimal weighting is used. The computation of the optimal weighting requires knowledge of true parameters of signals and systems. This paper describes how the optimal weighting can be computed approximately from the available noisy data and thereby offers a way to identify errors-in-variables systems with high accuracy. Numerical examples indicate that using this approximately optimal weighting gives an accuracy that is close to the accuracy obtained by using the optimal weighting.

Identification of dual‐rate sampled errors‐in‐variables systems with time delays

“…[14][15][16][17] Therefore, it is necessary to develop new identification methods for EIV systems. An overview of EIV system identification methods can be found in Reference 18, including the instrumental variable method, 19 the bias-eliminating LS method, 20,21 the covariance matching method, 22,23 the maximum likelihood (ML) method, 24 the total least squares (TLS) method, 25 the asymptotic method, 26 and so on. Recently, Zhang et al developed a novel version of the extended ML estimator, which can deal with EIV systems containing arbitrary but persistent excitations and colored disturbing noises.…”