Switch Machine Fault Diagnosis Method Based on Kalman Filter and Support Vector Machines

  • Xiang Li
  • , Yong Qin
  • , Zhipeng Wang*
  • , Jiayu Kan
  • , Xiaofeng Zhang
  • *Corresponding author for this work

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

Abstract

Switch machines are used for operating railway turnout; its error can cause delays, increase operating costs and may even lead to train accidents. Therefore, the fault diagnosis technology for the switch machine has received more and more attention. This paper proposes a fault diagnosis method based on the action current of switch machine. Firstly, the Kalman filter is used to preprocess the collected action current to reduce the influence of the unavoidable error of the measurement. In addition, we can further improve the accuracy of fault diagnosis by extracting the characteristics of the action current curve, like the maximum, minimum and average value, etc. Finally, we use DAG-SVMs to intelligently diagnose switch failures. Experiments show that the accuracy of classification after Kalman filter preprocessing is better than that of direct classification.

Original languageEnglish
Title of host publicationProceedings of the 4th International Conference on Electrical and Information Technologies for Rail Transportation, EITRT 2019 - Rail Transportation System Safety and Maintenance Technologies
EditorsYong Qin, Limin Jia, Baoming Liu, Zhigang Liu, Lijun Diao, Min An
PublisherSpringer
Pages727-735
Number of pages9
ISBN (Print)9789811528651
DOIs
StatePublished - 2020
Externally publishedYes
Event4th International Conference on Electrical and Information Technologies for Rail Transportation, EITRT 2019 - Qingdao, China
Duration: 25 Oct 201927 Oct 2019

Publication series

NameLecture Notes in Electrical Engineering
Volume639
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

Conference4th International Conference on Electrical and Information Technologies for Rail Transportation, EITRT 2019
Country/TerritoryChina
CityQingdao
Period25/10/1927/10/19

Keywords

  • DAG-SVMs
  • Feature extraction
  • Kalman filter
  • Switch machines

Fingerprint

Dive into the research topics of 'Switch Machine Fault Diagnosis Method Based on Kalman Filter and Support Vector Machines'. Together they form a unique fingerprint.

Cite this