Open AccessImproved least‐squares identification for multiple‐output non‐linear stochastic systems
Author(s) -
Xia Huafeng,
Ji Yan,
Yang Yongqing,
Ding Feng,
Hayat Tasawar
Publication year - 2020
Publication title -
iet control theory and applications
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.059
H-Index - 108
eISSN - 1751-8652
pISSN - 1751-8644
DOI - 10.1049/iet-cta.2019.0915
Subject(s) - least squares function approximation , identification (biology) , recursive least squares filter , mathematics , linear system , key (lock) , mathematical optimization , linear least squares , iteratively reweighted least squares , control theory (sociology) , generalized least squares , algorithm , linear model , system identification , computer science , estimation theory , non linear least squares , singular value decomposition , artificial intelligence , statistics , adaptive filter , data modeling , botany , computer security , control (management) , database , estimator , biology , mathematical analysis
This study considers the identification problems of multiple‐output non‐linear equation‐error moving average systems. There exist the product items of the parameters between the non‐linear and linear parts. To solve this difficulty, the key term separation technique is adopted. By using the model decomposition technique and the hierarchical identification principle, a maximum likelihood‐based recursive extended least‐squares estimation algorithm with reduced computational complexity is presented to estimate the parameters of the non‐linear part and the linear part interactively. The simulation results demonstrate the effectiveness of the proposed method.