Applying MLP and RBF classifiers in embedded condition monitoring and fault diagnosis applications

Yuhua Li, Michael J Pont, N Barrie Jones, John A Twiddle

    Research output: Contribution to journalArticle

    11 Citations (Scopus)

    Abstract

    In this paper, results are presented from a comprehensive series of studies aimed at assessing the suitability of multilayered perceptron (MLP) and radial basis function (RBF) networks for use in embedded, microcontroller-based, condition monitoring and fault diagnosis (CMFD) applications. Our assessment criteria include the performance of each classifier on a range of CMFD-related problems, such as situations where there may be multiple faults present simultaneously, or where 'unknown' faults may occur. In addition, the processor and memory requirements of each classifier are compared and discussed. On the basis of the results obtained in these studies, it is argued that each form of classifier has both strengths and weaknesses, and that neither is suitable for use in all CMFD applications. The paper concludes by demonstrating that, where memory and processor limits allow, the best performance may be obtained through use of a fusion classifier containing both MLP and RBF components.
    LanguageEnglish
    Pages315-343
    JournalTransactions of the Institute of Measurement and Control
    Volume23
    Issue number5
    DOIs
    Publication statusPublished - Dec 2001

    Fingerprint

    Condition monitoring
    Failure analysis
    Classifiers
    Neural networks
    Data storage equipment
    Radial basis function networks
    Microcontrollers
    Fusion reactions

    Cite this

    Li, Yuhua ; Pont, Michael J ; Jones, N Barrie ; Twiddle, John A. / Applying MLP and RBF classifiers in embedded condition monitoring and fault diagnosis applications. In: Transactions of the Institute of Measurement and Control. 2001 ; Vol. 23, No. 5. pp. 315-343.
    @article{081e06e01bc949a0955df1df5bcd9ccc,
    title = "Applying MLP and RBF classifiers in embedded condition monitoring and fault diagnosis applications",
    abstract = "In this paper, results are presented from a comprehensive series of studies aimed at assessing the suitability of multilayered perceptron (MLP) and radial basis function (RBF) networks for use in embedded, microcontroller-based, condition monitoring and fault diagnosis (CMFD) applications. Our assessment criteria include the performance of each classifier on a range of CMFD-related problems, such as situations where there may be multiple faults present simultaneously, or where 'unknown' faults may occur. In addition, the processor and memory requirements of each classifier are compared and discussed. On the basis of the results obtained in these studies, it is argued that each form of classifier has both strengths and weaknesses, and that neither is suitable for use in all CMFD applications. The paper concludes by demonstrating that, where memory and processor limits allow, the best performance may be obtained through use of a fusion classifier containing both MLP and RBF components.",
    author = "Yuhua Li and Pont, {Michael J} and Jones, {N Barrie} and Twiddle, {John A}",
    year = "2001",
    month = "12",
    doi = "10.1177/014233120102300504",
    language = "English",
    volume = "23",
    pages = "315--343",
    journal = "Transactions of the Institute of Measurement and Control",
    issn = "0142-3312",
    number = "5",

    }

    Applying MLP and RBF classifiers in embedded condition monitoring and fault diagnosis applications. / Li, Yuhua; Pont, Michael J; Jones, N Barrie; Twiddle, John A.

    In: Transactions of the Institute of Measurement and Control, Vol. 23, No. 5, 12.2001, p. 315-343.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Applying MLP and RBF classifiers in embedded condition monitoring and fault diagnosis applications

    AU - Li, Yuhua

    AU - Pont, Michael J

    AU - Jones, N Barrie

    AU - Twiddle, John A

    PY - 2001/12

    Y1 - 2001/12

    N2 - In this paper, results are presented from a comprehensive series of studies aimed at assessing the suitability of multilayered perceptron (MLP) and radial basis function (RBF) networks for use in embedded, microcontroller-based, condition monitoring and fault diagnosis (CMFD) applications. Our assessment criteria include the performance of each classifier on a range of CMFD-related problems, such as situations where there may be multiple faults present simultaneously, or where 'unknown' faults may occur. In addition, the processor and memory requirements of each classifier are compared and discussed. On the basis of the results obtained in these studies, it is argued that each form of classifier has both strengths and weaknesses, and that neither is suitable for use in all CMFD applications. The paper concludes by demonstrating that, where memory and processor limits allow, the best performance may be obtained through use of a fusion classifier containing both MLP and RBF components.

    AB - In this paper, results are presented from a comprehensive series of studies aimed at assessing the suitability of multilayered perceptron (MLP) and radial basis function (RBF) networks for use in embedded, microcontroller-based, condition monitoring and fault diagnosis (CMFD) applications. Our assessment criteria include the performance of each classifier on a range of CMFD-related problems, such as situations where there may be multiple faults present simultaneously, or where 'unknown' faults may occur. In addition, the processor and memory requirements of each classifier are compared and discussed. On the basis of the results obtained in these studies, it is argued that each form of classifier has both strengths and weaknesses, and that neither is suitable for use in all CMFD applications. The paper concludes by demonstrating that, where memory and processor limits allow, the best performance may be obtained through use of a fusion classifier containing both MLP and RBF components.

    U2 - 10.1177/014233120102300504

    DO - 10.1177/014233120102300504

    M3 - Article

    VL - 23

    SP - 315

    EP - 343

    JO - Transactions of the Institute of Measurement and Control

    T2 - Transactions of the Institute of Measurement and Control

    JF - Transactions of the Institute of Measurement and Control

    SN - 0142-3312

    IS - 5

    ER -