Real-time recursive identification of unknown linear systems

Abstract

In this thesis an recursive version of ARMA identification algorithm is porposed. The basic algorithm is based on Gram-Schmidt Orthogonalization of automatically selected basis functions from specified function space, but does not require explicit creation of orthogonal functions. By using two dimensional autocorrelations and cross-correlations of input and output with constant data length, identification algorithm is extended to cope slowly timevarying or order varying delayed system. The simulation results are presented to show the preformance of the estimation with slowly time-varying or order varying plant and with or without noise filtering.