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

An agent-based implementation of hidden Markov models for gas turbine condition monitoring

Kenyon, Andrew and Catterson, Victoria and McArthur, Stephen and Twiddle, John (2014) An agent-based implementation of hidden Markov models for gas turbine condition monitoring. IEEE Transactions on Systems Man and Cybernetics: Systems, 44 (2). pp. 186-195. ISSN 2168-2216

[img]
Preview
PDF (Agent Based HMMs for GT monitoring) - Submitted Version
Download (421Kb) | Preview

    Abstract

    This paper considers the use of a multi-agent system (MAS) incorporating hidden Markov models (HMMs) for the condition monitoring of gas turbine (GT) engines. Hidden Markov models utilizing a Gaussian probability distribution are proposed as an anomaly detection tool for gas turbines components. The use of this technique is shown to allow the modeling of the dynamics of GTs despite a lack of high frequency data. This allows the early detection of developing faults and avoids costly outages due to asset failure. These models are implemented as part of a MAS, using a proposed extension of an established power system ontology, for fault detection of gas turbines. The multi-agent system is shown to be applicable through a case study and comparison to an existing system utilizing historic data from a combined-cycle gas turbine plant provided by an industrial partner.

    Item type: Article
    ID code: 41350
    Keywords: Markov models, gas turbine, multi agent system, hidden Markov models, multi-agent systems, Electrical engineering. Electronics Nuclear engineering, Electrical and Electronic Engineering
    Subjects: Technology > Electrical engineering. Electronics Nuclear engineering
    Department: Faculty of Engineering > Electronic and Electrical Engineering
    Related URLs:
    Depositing user: Pure Administrator
    Date Deposited: 08 Oct 2012 12:00
    Last modified: 30 Mar 2014 04:03
    URI: http://strathprints.strath.ac.uk/id/eprint/41350

    Actions (login required)

    View Item

    Fulltext Downloads: