DATA BASED FAULT DETECTION OF THE ONLINE ANALYSERS IN A DEAROMATISATION PROCESS

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

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

    448 Downloads (Pure)

    Abstract

    Fault diagnosis methods based on process history data have been studied widely
    in recent years, and several successful industrial applications have been reported. In this paper a comparison of four monitoring methods, PCA, PLS, subspace identification and self-organising maps, for fault detection of the online analysers in a dearomatisation process is presented. The effectiveness of different statistical process monitoring methods in FDI of the online analysers is evaluated on the basis of a large number of simulation studies. Finally the results are presented and discussed.
    Original languageEnglish
    Title of host publication1st Workshop on Networked Control System and Fault Tolerant Control October 6-7th, 2005, Ajaccio, FRANCE
    Place of PublicationNancy, France
    PublisherNeCST, EU-IST-2004-004303
    Publication statusPublished - 2005
    MoE publication typeA4 Article in a conference publication

    Keywords

    • fault detection
    • input variable selection
    • feature construction
    • subspace identification

    Fingerprint Dive into the research topics of 'DATA BASED FAULT DETECTION OF THE ONLINE ANALYSERS IN A DEAROMATISATION PROCESS'. Together they form a unique fingerprint.

    Cite this