Robust identification of linear ARX models with recursive EM algorithm based on Student’s t-distribution

•The outliers in the measurements are coped with the Student’s t-distribution, which assigns robustness to the algorithm according to its property of heavy-tails.•The robust identification issue is solved under recursive expectation-maximization algorithm. The online updating of the parameters are r...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of the Franklin Institute Jg. 358; H. 1; S. 1103 - 1121
Hauptverfasser: Chen, Xin, Zhao, Shunyi, Liu, Fei
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elmsford Elsevier Ltd 01.01.2021
Elsevier Science Ltd
Schlagworte:
Algorithms
Autoregressive models
Continuously stirred tank reactors
Linear systems
Noise
Numerical analysis
Probability distribution
Random variables
Recursive functions
Robustness (mathematics)
ISSN:0016-0032, 1879-2693, 0016-0032
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:•The outliers in the measurements are coped with the Student’s t-distribution, which assigns robustness to the algorithm according to its property of heavy-tails.•The robust identification issue is solved under recursive expectation-maximization algorithm. The online updating of the parameters are realized based on a recursive Q-function.•The degree of freedom of the Student’s t-distribution is online updated with the implementation of a recursive auxiliary quantity. This paper considers the robust identification issue of linear systems represented by autoregressive exogenous models using the recursive expectation-maximization (EM) algorithm. In this paper, a recursive Q-function is formulated based on the maximum likelihood principle. Meanwhile, the outliers that frequently appear in practical processes are accommodated with the Student’s t-distribution. The parameter vector, variance of noise, and the degree of freedom are recursively estimated. Finally, a numerical example, as well as a simulated continuous stirred tank reactor (CSTR) system, is performed to verify the effectiveness of the proposed recursive EM algorithm.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0016-0032
1879-2693
0016-0032
DOI:10.1016/j.jfranklin.2020.06.003