Skip to main navigation Skip to search Skip to main content

Identification of ARX system based on shifted asymmetric laplace distribution

  • Miao Yu
  • , Tianyi Zhang
  • , Xianqiang Yang*
  • *Corresponding author for this work
  • Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The identification of AutoRegressive eXogenous (ARX) model by outliers is addressed in this paper. Shifted(non-centralized) asymmetric Laplace (SAL) distribution and expectation maximization (EM) algorithm are employed to estimate the unknown model parameters. Outliers are common in the signal acquisition process and have a serious impact on data-driven modeling method. In this paper, the probability method is used to solve the problem of outliers. When the noise parameter is regarded as a prior exponential distribution, the model output obeys the SAL distribution which is robust to outliers. The known statistical properties of SAL distribution are applied to calculate the M-step in the EM algorithm and get the iterative parametric formula. The accuracy of the proposed algorithm is verified by a numerical simulation example.

Original languageEnglish
Title of host publicationProceedings of the 38th Chinese Control Conference, CCC 2019
EditorsMinyue Fu, Jian Sun
PublisherIEEE Computer Society
Pages1695-1700
Number of pages6
ISBN (Electronic)9789881563972
DOIs
StatePublished - Jul 2019
Event38th Chinese Control Conference, CCC 2019 - Guangzhou, China
Duration: 27 Jul 201930 Jul 2019

Publication series

NameChinese Control Conference, CCC
Volume2019-July
ISSN (Print)1934-1768
ISSN (Electronic)2161-2927

Conference

Conference38th Chinese Control Conference, CCC 2019
Country/TerritoryChina
CityGuangzhou
Period27/07/1930/07/19

Keywords

  • AutoRegressive eXogenous model
  • Expectation maximization algorithm
  • Shifted asymmetric Laplace distribution

Fingerprint

Dive into the research topics of 'Identification of ARX system based on shifted asymmetric laplace distribution'. Together they form a unique fingerprint.

Cite this