Filtering-based recursive least-squares identification algorithm for controlled autoregressive moving average systems using the maximum likelihood principle

This paper considers the parameter estimation problem of controlled autoregressive moving average systems. The basic idea is to use the noise polynomial to filter the input-output data, then a controlled moving average identification model and a noise model are obtained. A maximum likelihood recursive least squares algorithm and a recursive least squares algorithm are used to interactively estimate the parameters of the two identification models by using the hierarchical identification principle. A numerical example is provided to show the effectiveness of the proposed algorithms.