A New Iterative Least Squares Parameter Estimation Approach for Equation-error Autoregressive Systems

Abstract

This paper investigates the identification methods for controlled autoregressive systems with autoregressive noise (i.e., equation-error autoregressive systems) from given input and output data. By applying the iterative technique and the hierarchical identification principle, an iterative least squares identification algorithm is presented and a recursive generalized least squares algorithm is given for comparison. The basic idea is to replace the unknown noise terms in the information vector with their estimated residuals. The simulation test results show the effectiveness of these algorithms.