Open AccessBias compensation‐based recursive least‐squares estimation with forgetting factors for output error moving average systems
Author(s) -
Wu AiGuo,
Qian YangYang,
Wu WeiJun
Publication year - 2014
Publication title -
iet signal processing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.384
H-Index - 42
eISSN - 1751-9683
pISSN - 1751-9675
DOI - 10.1049/iet-spr.2013.0327
Subject(s) - noise (video) , recursive least squares filter , white noise , variance (accounting) , statistics , forgetting , estimation , mathematics , algorithm , computer science , least squares function approximation , generalized least squares , compensation (psychology) , estimation theory , artificial intelligence , estimator , adaptive filter , psychology , psychoanalysis , linguistics , philosophy , accounting , management , economics , business , image (mathematics)
The bias compensation technique combined with the least‐squares estimation algorithm with forgetting factors is applied to the parameter estimation of output error models with moving average noise. It is shown that the bias term induced by the noise is determined by the weighted average variance of the white noise and the parameters of the unknown noise model. Therefore, in order to give a recursive estimation of the bias term, an interactive estimation of the weighted average variance and noise parameters is constructed by using the principle of hierarchical identification. In addition, a recursive form is also established to estimate the so‐called weighted average variance of the white noise. The estimation algorithm is finally established by combining the interactive estimation and the recursive estimation of weighted average variance. A simulation example is employed to show the effectiveness of the proposed bias compensation based least‐squares estimation algorithm with two forgetting factors.