Strathprints logo
Strathprints Home | Open Access | Browse | Search | User area | Copyright | Help | Library Home | SUPrimo

Learning models of plant behavior for anomaly detection and condition monitoring

Brown, A.J. and Catterson, V.M. and Fox, M. and Long, D. and McArthur, S.D.J. (2007) Learning models of plant behavior for anomaly detection and condition monitoring. Engineering Intelligent Systems for Electrical Engineering and Communications, 15 (2). pp. 61-67. ISSN 1472-8915

[img]
Preview
PDF - Draft Version
Download (502Kb) | Preview

    Abstract

    Providing engineers and asset managers with a too] which can diagnose faults within transformers can greatly assist decision making on such issues as maintenance, performance and safety. However, the onus has always been on personnel to accurately decide how serious a problem is and how urgently maintenance is required. In dealing with the large volumes of data involved, it is possible that faults may not be noticed until serious damage has occurred. This paper proposes the integration of a newly developed anomaly detection technique with an existing diagnosis system. By learning a Hidden Markov Model of healthy transformer behavior, unexpected operation, such as when a fault develops, can be flagged for attention. Faults can then be diagnosed using the existing system and maintenance scheduled as required, all at a much earlier stage than would previously have been possible.

    Item type: Article
    ID code: 17089
    Notes: Also presented at: International Conference on Intelligent Systems Applications to Power Systems, Toki Messe, Niigata, 5-8 Nov 2007.
    Keywords: cooperative systems, decision support systems, Hidden Markov models, intelligent systems, learning systems, monitoring, partial discharges, power systems, power transformers, Electrical engineering. Electronics Nuclear engineering
    Subjects: Technology > Electrical engineering. Electronics Nuclear engineering
    Department: Faculty of Engineering > Electronic and Electrical Engineering
    Faculty of Science > Computer and Information Sciences
    Related URLs:
    Depositing user: Strathprints Administrator
    Date Deposited: 14 May 2010 18:05
    Last modified: 21 Jul 2013 03:04
    URI: http://strathprints.strath.ac.uk/id/eprint/17089

    Actions (login required)

    View Item

    Fulltext Downloads: