Skip to main navigation Skip to search Skip to main content

Sensor Fault Detection, Isolation and Accommodation Based on the Stable Kernel Representation

  • Kuan Li
  • , Dejia Tang*
  • , Deyi Zhu
  • , Yang He
  • , Hao Luo
  • *Corresponding author for this work
  • Shanghai Aerospace Control Technology Institute

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

Abstract

This paper proposes a novel sensor fault detection, isolation and accommodation (FDIA) scheme based on the stable kernel representation. The core of the study is to design the virtual sensor for each sensor channel. The virtual sensors are designed based on the data-driven stable kernel representation to capture the system dynamics. In addition, the existence condition of the virtual sensors is also discussed in details. The sensor fault is detected and isolated based on the probability analysis of residuals. The fault accommodation is implemented by switching on the virtual sensor. The proposed method is finally validated on a simulated 2-input-3-output system under the closed-loop conditions.

Original languageEnglish
Title of host publication2022 IEEE 31st International Symposium on Industrial Electronics, ISIE 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages406-411
Number of pages6
ISBN (Electronic)9781665482400
DOIs
StatePublished - 2022
Event31st IEEE International Symposium on Industrial Electronics, ISIE 2022 - Anchorage, United States
Duration: 1 Jun 20223 Jun 2022

Publication series

NameIEEE International Symposium on Industrial Electronics
Volume2022-June

Conference

Conference31st IEEE International Symposium on Industrial Electronics, ISIE 2022
Country/TerritoryUnited States
CityAnchorage
Period1/06/223/06/22

Keywords

  • fault accommodation
  • fault diagnosis
  • Sensor fault
  • stable kernel representation
  • virtual sensor

Fingerprint

Dive into the research topics of 'Sensor Fault Detection, Isolation and Accommodation Based on the Stable Kernel Representation'. Together they form a unique fingerprint.

Cite this