Support vector machines for detection of analyzer faults- a case study

Mats Nikus, Mikko Vermasvuori, Nikolai Vatanski, Sirkka-Liisa Jämsä-Jounela

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

    245 Downloads (Pure)

    Abstract

    The aim of the work presented in this paper is to assess the ability of support vector machines (SVM) for detecting measurement faults. Two different support vector machine approaches for detecting faults are tested and compared to neural networks. The first method is based on a SVM regression model together with an analysis of the residuals whereas the second method is based on a SVM classifier. The methods were applied to a rigorous first principles based dynamic simulator of a dearomatization process.
    Original languageEnglish
    Title of host publicationALSIS 2006, Finland, 2006
    EditorsL. Leiviskä
    Place of PublicationHelsinki
    PublisherSuomen Automaatioseura
    ISBN (Electronic)952-5183-28-9
    Publication statusPublished - 2006
    MoE publication typeA4 Article in a conference publication

    Keywords

    • fault detection
    • monitoring
    • support vector machines
    • classification
    • regression
    • dearomatization process

    Fingerprint Dive into the research topics of 'Support vector machines for detection of analyzer faults- a case study'. Together they form a unique fingerprint.

  • Cite this

    Nikus, M., Vermasvuori, M., Vatanski, N., & Jämsä-Jounela, S-L. (2006). Support vector machines for detection of analyzer faults- a case study. In L. Leiviskä (Ed.), ALSIS 2006, Finland, 2006 Helsinki: Suomen Automaatioseura.