On selecting pre-processing techniques for fault classification using neural networks

Yuhua Li, Michael J Pont

    Research output: Contribution to journalArticle

    Abstract

    This paper introduces a measure for selecting an appropriate pre-processing strategy for use in neural network-based condition monitoring and fault diagnosis (CMFD) applications. The proposed selection measure is derived from a non-parametric separability matrix: no knowledge of the underlying distribution of the data is required. The effectiveness of this measure is explored on a problem of engine misfire detection.
    LanguageEnglish
    Pages80-87
    JournalInternational Journal of Knowledge-Based Intelligent Engineering Systems
    Volume6
    Issue number2
    Publication statusPublished - 2002

    Fingerprint

    Condition monitoring
    Failure analysis
    Engines
    Neural networks
    Processing

    Cite this

    @article{0369f29b8d83472b8f4c0005da0a6f47,
    title = "On selecting pre-processing techniques for fault classification using neural networks",
    abstract = "This paper introduces a measure for selecting an appropriate pre-processing strategy for use in neural network-based condition monitoring and fault diagnosis (CMFD) applications. The proposed selection measure is derived from a non-parametric separability matrix: no knowledge of the underlying distribution of the data is required. The effectiveness of this measure is explored on a problem of engine misfire detection.",
    author = "Yuhua Li and Pont, {Michael J}",
    year = "2002",
    language = "English",
    volume = "6",
    pages = "80--87",
    journal = "International Journal of Knowledge-Based and Intelligent Engineering Systems",
    issn = "1327-2314",
    publisher = "IOS Press",
    number = "2",

    }

    On selecting pre-processing techniques for fault classification using neural networks. / Li, Yuhua; Pont, Michael J.

    In: International Journal of Knowledge-Based Intelligent Engineering Systems, Vol. 6, No. 2, 2002, p. 80-87.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - On selecting pre-processing techniques for fault classification using neural networks

    AU - Li, Yuhua

    AU - Pont, Michael J

    PY - 2002

    Y1 - 2002

    N2 - This paper introduces a measure for selecting an appropriate pre-processing strategy for use in neural network-based condition monitoring and fault diagnosis (CMFD) applications. The proposed selection measure is derived from a non-parametric separability matrix: no knowledge of the underlying distribution of the data is required. The effectiveness of this measure is explored on a problem of engine misfire detection.

    AB - This paper introduces a measure for selecting an appropriate pre-processing strategy for use in neural network-based condition monitoring and fault diagnosis (CMFD) applications. The proposed selection measure is derived from a non-parametric separability matrix: no knowledge of the underlying distribution of the data is required. The effectiveness of this measure is explored on a problem of engine misfire detection.

    UR - http://www.iospress.nl/loadtop/load.php?isbn=13272314

    M3 - Article

    VL - 6

    SP - 80

    EP - 87

    JO - International Journal of Knowledge-Based and Intelligent Engineering Systems

    T2 - International Journal of Knowledge-Based and Intelligent Engineering Systems

    JF - International Journal of Knowledge-Based and Intelligent Engineering Systems

    SN - 1327-2314

    IS - 2

    ER -