Solenoid valve diagnosis for railway braking systems with embedded sensor signals and physical interpretation

Boseong Seo, Soo Ho Jo, Hyunseok Oh, Byeng D. Youn

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

8 Scopus citations

Abstract

This paper proposes a fault diagnosis method for solenoid valves in urban railway braking systems. For dominant failure modes of solenoid valves, sensor signals including electrical current, and input and output pressure were acquired and analyzed. The physical behaviors of the solenoid valves are modeled analytically. Numerous forces including magnetic, elastic, and gravity forces are incorporated in the model. With the analytical model and sensor signals, health indices are defined. The health indices are used to quantify the condition of the solenoid valves with different failure modes. Finally, a fault diagnosis method is proposed with the health indices and failure criteria. We anticipate that this study can help decrease maintenance costs and improve reliability of urban railway braking systems.

Original languageEnglish
Title of host publicationPHM 2016 - Proceedings of the Annual Conference of the Prognostics and Health Management Society
EditorsMatthew J. Daigle, Anibal Bregon
PublisherPrognostics and Health Management Society
Pages337-343
Number of pages7
ISBN (Electronic)9781936263059
StatePublished - 2016
Event2016 Annual Conference of the Prognostics and Health Management Society, PHM 2016 - Denver, United States
Duration: 3 Oct 20166 Oct 2016

Publication series

NameProceedings of the Annual Conference of the Prognostics and Health Management Society, PHM
Volume2016-October
ISSN (Print)2325-0178

Conference

Conference2016 Annual Conference of the Prognostics and Health Management Society, PHM 2016
Country/TerritoryUnited States
CityDenver
Period3/10/166/10/16

Fingerprint

Dive into the research topics of 'Solenoid valve diagnosis for railway braking systems with embedded sensor signals and physical interpretation'. Together they form a unique fingerprint.

Cite this