Skip to main navigation Skip to search Skip to main content

Study of sensor fault detection based on modified SVM algorithm

  • Zhijia Yu
  • , Yinan Xu
  • , Yonghu Ma*
  • , Yujing Wu
  • , Jin Gyun Chung
  • *Corresponding author for this work
  • Yanbian University
  • Jeonbuk National University

Research output: Contribution to conferenceConference paperpeer-review

Abstract

Sensor is an essential device in automation control system, and the reliable sensor signal has the massive benefits of the normal operation of whole system. This paper proposed an improved support vector machine (SVM) which is modified by clone select algorithm (CSA) for sensor fault detection. CSA - SVM observer is established by monitoring sensor in real-time, so as to find sensor fault in time. Simulation results show that the algorithm can be effective for fault detection.

Original languageEnglish
Title of host publicationISOCC 2014 - International SoC Design Conference
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages294-295
Number of pages2
ISBN (Electronic)9781479951260
DOIs
StatePublished - 2015.04.16
Event11th International SoC Design Conference, ISOCC 2014 - Jeju, Korea, Republic of
Duration: 2014.11.32014.11.6

Publication series

NameISOCC 2014 - International SoC Design Conference

Conference

Conference11th International SoC Design Conference, ISOCC 2014
Country/TerritoryKorea, Republic of
CityJeju
Period14.11.314.11.6

Keywords

  • Clonal Selection
  • Fault detection
  • Support Vector Machine

Quacquarelli Symonds(QS) Subject Topics

  • Computer Science & Information Systems

Fingerprint

Dive into the research topics of 'Study of sensor fault detection based on modified SVM algorithm'. Together they form a unique fingerprint.

Cite this