Identification of continuous-time models

Abstract

The paper considers the problem of estimation of the transfer function of a continuous-time dynamic system in the presence of colored noise. The author introduces an operator transformation that allows for keeping a continuous-time parametrization whereas the parameter estimation can be made by means of a discrete-time maximum-likelihood algorithm. A comparison is made between the performance of the new method in comparison with a standard identification of an ARMAX-model. The method is useful in cases where it is important to estimate the coefficients of a continuous-time transfer function and where it is important to maintain a physical interpretation of the transfer function results.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>