Using a combination of RBFN, MLP and kNN classifiers for engine misfire detection

Yuhua Li, MJ Pont, CR Parikh, NB Jones

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    In this paper, we apply radial basis function networks (RBFN), multilayer Perceptron (MLP) and a conventional statistical classifier, k-nearest neighbour (kNN), to the detection of misfires in a petrol engine. Used alone, each classifier is shown to provide a similar level of performance. We then demonstrate that by combining these techniques using a simple `majority voting' algorithm, the overall performance of the system is improved by approximately 10%.
    LanguageEnglish
    Title of host publicationUnknown Host Publication
    Pages46-51
    Number of pages6
    Publication statusPublished - 2000
    EventSOFT COMPUTING TECHNIQUES AND APPLICATIONS -
    Duration: 1 Jan 2000 → …

    Publication series

    NameADVANCES IN SOFT COMPUTING

    Conference

    ConferenceSOFT COMPUTING TECHNIQUES AND APPLICATIONS
    Period1/01/00 → …

    Fingerprint

    Radial basis function networks
    Multilayer neural networks
    Classifiers
    Engines

    Keywords

    • engine misfire detection
    • neural networks
    • multi-layer Perceptron
    • radial basis function
    • condition monitoring
    • fault classification

    Cite this

    Li, Y., Pont, MJ., Parikh, CR., & Jones, NB. (2000). Using a combination of RBFN, MLP and kNN classifiers for engine misfire detection. In Unknown Host Publication (pp. 46-51). (ADVANCES IN SOFT COMPUTING).
    Li, Yuhua ; Pont, MJ ; Parikh, CR ; Jones, NB. / Using a combination of RBFN, MLP and kNN classifiers for engine misfire detection. Unknown Host Publication. 2000. pp. 46-51 (ADVANCES IN SOFT COMPUTING).
    @inproceedings{bb76dd0aaa424207b1bc5ca46ec42baa,
    title = "Using a combination of RBFN, MLP and kNN classifiers for engine misfire detection",
    abstract = "In this paper, we apply radial basis function networks (RBFN), multilayer Perceptron (MLP) and a conventional statistical classifier, k-nearest neighbour (kNN), to the detection of misfires in a petrol engine. Used alone, each classifier is shown to provide a similar level of performance. We then demonstrate that by combining these techniques using a simple `majority voting' algorithm, the overall performance of the system is improved by approximately 10{\%}.",
    keywords = "engine misfire detection, neural networks, multi-layer Perceptron, radial basis function, condition monitoring, fault classification",
    author = "Yuhua Li and MJ Pont and CR Parikh and NB Jones",
    note = "Workshop 99 on Recent Advances in Soft Computing, LEICESTER, ENGLAND, JUL 01-02, 1999",
    year = "2000",
    language = "English",
    series = "ADVANCES IN SOFT COMPUTING",
    pages = "46--51",
    booktitle = "Unknown Host Publication",

    }

    Li, Y, Pont, MJ, Parikh, CR & Jones, NB 2000, Using a combination of RBFN, MLP and kNN classifiers for engine misfire detection. in Unknown Host Publication. ADVANCES IN SOFT COMPUTING, pp. 46-51, SOFT COMPUTING TECHNIQUES AND APPLICATIONS, 1/01/00.

    Using a combination of RBFN, MLP and kNN classifiers for engine misfire detection. / Li, Yuhua; Pont, MJ; Parikh, CR; Jones, NB.

    Unknown Host Publication. 2000. p. 46-51 (ADVANCES IN SOFT COMPUTING).

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    TY - GEN

    T1 - Using a combination of RBFN, MLP and kNN classifiers for engine misfire detection

    AU - Li, Yuhua

    AU - Pont, MJ

    AU - Parikh, CR

    AU - Jones, NB

    N1 - Workshop 99 on Recent Advances in Soft Computing, LEICESTER, ENGLAND, JUL 01-02, 1999

    PY - 2000

    Y1 - 2000

    N2 - In this paper, we apply radial basis function networks (RBFN), multilayer Perceptron (MLP) and a conventional statistical classifier, k-nearest neighbour (kNN), to the detection of misfires in a petrol engine. Used alone, each classifier is shown to provide a similar level of performance. We then demonstrate that by combining these techniques using a simple `majority voting' algorithm, the overall performance of the system is improved by approximately 10%.

    AB - In this paper, we apply radial basis function networks (RBFN), multilayer Perceptron (MLP) and a conventional statistical classifier, k-nearest neighbour (kNN), to the detection of misfires in a petrol engine. Used alone, each classifier is shown to provide a similar level of performance. We then demonstrate that by combining these techniques using a simple `majority voting' algorithm, the overall performance of the system is improved by approximately 10%.

    KW - engine misfire detection

    KW - neural networks

    KW - multi-layer Perceptron

    KW - radial basis function

    KW - condition monitoring

    KW - fault classification

    M3 - Conference contribution

    T3 - ADVANCES IN SOFT COMPUTING

    SP - 46

    EP - 51

    BT - Unknown Host Publication

    ER -

    Li Y, Pont MJ, Parikh CR, Jones NB. Using a combination of RBFN, MLP and kNN classifiers for engine misfire detection. In Unknown Host Publication. 2000. p. 46-51. (ADVANCES IN SOFT COMPUTING).