Search:
Computing and Library Services - delivering an inspiring information environment

Application of novelty detection methods to health monitoring and typical fault diagnosis of a turbopump

Hu, Lei, Hu, Niaoqing, Fan, Bin and Gu, Fengshou (2012) Application of novelty detection methods to health monitoring and typical fault diagnosis of a turbopump. Journal of Physics: Conference Series, 364. 012128. ISSN 1742-6596

[img]
Preview
PDF - Accepted Version
Download (1323kB) | Preview

    Abstract

    Novelty detection is the identification of deviations from a training set. It is suitable for monitoring the health of mechanical systems where it usually is impossible to know every potential fault. In this paper, two novelty detectors are presented. The first detector which integrates One-Class Support Vector Machine (OCSVM) with an incremental clustering algorithm is designed for health monitoring of the turbopump, while the second one which is trained on sensor fault samples is designed to recognize faults from sensors and faults actually from the turbopump. Analysis results showed that these two detectors are both sensitive and efficient for the health monitoring of the turbopump.

    Item Type: Article
    Subjects: T Technology > TJ Mechanical engineering and machinery
    Schools: School of Computing and Engineering
    School of Computing and Engineering > Automotive Engineering Research Group
    School of Computing and Engineering > Diagnostic Engineering Research Centre
    School of Computing and Engineering > Diagnostic Engineering Research Centre > Energy, Emissions and the Environment Research Group
    School of Computing and Engineering > Diagnostic Engineering Research Centre > Machinery Condition and Performance Monitoring Research Group
    School of Computing and Engineering > Diagnostic Engineering Research Centre > Measurement System and Signal Processing Research Group
    School of Computing and Engineering > Informatics Research Group
    School of Computing and Engineering > Informatics Research Group > XML, Database and Information Retrieval Research Group
    Related URLs:
    Depositing User: Cherry Edmunds
    Date Deposited: 11 Jul 2012 11:01
    Last Modified: 11 Jul 2012 11:01
    URI: http://eprints.hud.ac.uk/id/eprint/14196

    Document Downloads

    Downloader Countries

    More statistics for this item...

    Item control for Repository Staff only:

    View Item

    University of Huddersfield, Queensgate, Huddersfield, HD1 3DH Copyright and Disclaimer All rights reserved ©