A fuzzy inference system for fault detection and isolation

application to a fluid system

Christopher J. White, H. Lakany

    Research output: Contribution to journalArticle

    20 Citations (Scopus)

    Abstract

    This work focuses on the design and implementation of a fuzzy inference system for fault detection and isolation (FDI) which can learn from example fault data, and the determination of a suitable optimisation strategy for the membership functions. A FDI system was developed which is based on adaptive fuzzy rules. A number of optimisation strategies were then applied; it was found that an evolutionary algorithm not only produced the best results but did so with relatively little processing effort and with excellent consistency. The adaptive fuzzy system, thus optimised, was tested against a neural network, which was trained to produce analogue outputs as an indication of fault magnitude. The fuzzy solution produced the best accuracy. We can conclude that an adaptive fuzzy inference system for FDI, using an evolutionary algorithm to learn from examples, can provide an accurate and readily comprehensible solution to diagnosing and evaluating fluid process plant faults.
    Original languageEnglish
    Pages (from-to)1021-1033
    Number of pages13
    JournalExpert Systems with Applications
    Volume35
    Issue number3
    DOIs
    Publication statusPublished - Oct 2008

    Fingerprint

    Fuzzy inference
    Fault detection
    Evolutionary algorithms
    Fluids
    Fuzzy rules
    Fuzzy systems
    Membership functions
    Neural networks
    Processing

    Keywords

    • fuzzy inference system
    • fault detection
    • fluid system
    • bioengineering
    • optimisation

    Cite this

    White, Christopher J. ; Lakany, H. / A fuzzy inference system for fault detection and isolation : application to a fluid system. In: Expert Systems with Applications. 2008 ; Vol. 35, No. 3. pp. 1021-1033.
    @article{69f1ba9503fa4b4ab43aca5fa25dcba2,
    title = "A fuzzy inference system for fault detection and isolation: application to a fluid system",
    abstract = "This work focuses on the design and implementation of a fuzzy inference system for fault detection and isolation (FDI) which can learn from example fault data, and the determination of a suitable optimisation strategy for the membership functions. A FDI system was developed which is based on adaptive fuzzy rules. A number of optimisation strategies were then applied; it was found that an evolutionary algorithm not only produced the best results but did so with relatively little processing effort and with excellent consistency. The adaptive fuzzy system, thus optimised, was tested against a neural network, which was trained to produce analogue outputs as an indication of fault magnitude. The fuzzy solution produced the best accuracy. We can conclude that an adaptive fuzzy inference system for FDI, using an evolutionary algorithm to learn from examples, can provide an accurate and readily comprehensible solution to diagnosing and evaluating fluid process plant faults.",
    keywords = "fuzzy inference system, fault detection, fluid system, bioengineering, optimisation",
    author = "White, {Christopher J.} and H. Lakany",
    year = "2008",
    month = "10",
    doi = "10.1016/j.eswa.2007.08.029",
    language = "English",
    volume = "35",
    pages = "1021--1033",
    journal = "Expert Systems with Applications",
    issn = "0957-4174",
    number = "3",

    }

    A fuzzy inference system for fault detection and isolation : application to a fluid system. / White, Christopher J.; Lakany, H.

    In: Expert Systems with Applications, Vol. 35, No. 3, 10.2008, p. 1021-1033.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - A fuzzy inference system for fault detection and isolation

    T2 - application to a fluid system

    AU - White, Christopher J.

    AU - Lakany, H.

    PY - 2008/10

    Y1 - 2008/10

    N2 - This work focuses on the design and implementation of a fuzzy inference system for fault detection and isolation (FDI) which can learn from example fault data, and the determination of a suitable optimisation strategy for the membership functions. A FDI system was developed which is based on adaptive fuzzy rules. A number of optimisation strategies were then applied; it was found that an evolutionary algorithm not only produced the best results but did so with relatively little processing effort and with excellent consistency. The adaptive fuzzy system, thus optimised, was tested against a neural network, which was trained to produce analogue outputs as an indication of fault magnitude. The fuzzy solution produced the best accuracy. We can conclude that an adaptive fuzzy inference system for FDI, using an evolutionary algorithm to learn from examples, can provide an accurate and readily comprehensible solution to diagnosing and evaluating fluid process plant faults.

    AB - This work focuses on the design and implementation of a fuzzy inference system for fault detection and isolation (FDI) which can learn from example fault data, and the determination of a suitable optimisation strategy for the membership functions. A FDI system was developed which is based on adaptive fuzzy rules. A number of optimisation strategies were then applied; it was found that an evolutionary algorithm not only produced the best results but did so with relatively little processing effort and with excellent consistency. The adaptive fuzzy system, thus optimised, was tested against a neural network, which was trained to produce analogue outputs as an indication of fault magnitude. The fuzzy solution produced the best accuracy. We can conclude that an adaptive fuzzy inference system for FDI, using an evolutionary algorithm to learn from examples, can provide an accurate and readily comprehensible solution to diagnosing and evaluating fluid process plant faults.

    KW - fuzzy inference system

    KW - fault detection

    KW - fluid system

    KW - bioengineering

    KW - optimisation

    U2 - 10.1016/j.eswa.2007.08.029

    DO - 10.1016/j.eswa.2007.08.029

    M3 - Article

    VL - 35

    SP - 1021

    EP - 1033

    JO - Expert Systems with Applications

    JF - Expert Systems with Applications

    SN - 0957-4174

    IS - 3

    ER -