Contributed paper
New developments using AI in fault diagnosis

https://doi.org/10.1016/S0952-1976(96)00072-3Get rights and content

Abstract

This paper is intended to give a survey on the state of the art of model-based fault diagnosis for dynamic processes employing artificial intelligence approaches. Emphasis is placed upon the use of fuzzy models for residual generation and fuzzy logic for residual evaluation. By the suggestion of a knowledge-based observer-like concept for residual generation, the basic idea of a novel observer concept, the so-called “knowledge observer”, is introduced. The neural-network approach for residual generation and evaluation is outlined as well.

References (48)

  • B. Dubuisson

    Diagnostic et Reconnaissances de Formes

    (1990)
  • D. Dvorak et al.

    Model-based monitoring of dynamic systems

  • K.D. Forbus

    Interpreting measurements of physical systems

  • C. Frélicot

    Un systéme adaptif de diagnostic par reconnaissance des formes floue

    Thèse Université de Technologie de Compiègne

    (1992)
  • J. Gertler

    An evidential reasoning extension to quantitative model-based failure diagnosis

    IEEE Transactions on Systems, Man and Cybernetics

    (1992)
  • D.M. Himmelblau

    Use of artificial neural networks to monitor faults and for troubleshooting in the process industries

  • D.M. Himmelblau et al.

    Fault classification with the aid of artificial neural networks

  • J.C. Hoskins et al.

    Fault diagnosis in complex chemical plants using artificial neural networks

    AICHE J.

    (1991)
  • R. Isermann

    Wissensbasierte Fehlerdiagnose technischer Prozesse

    at-Automatisierungstechnik

    (1988)
  • R. Isermann

    Fault diagnosis of machines via parameter estimation and knowledge processing

    Automatica

    (1993)
  • S. Jen Chang et al.

    Failure propagation trees for diagnosis in manufacturing systems

    IEEE Transactions on Systems, Man and Cybernetics

    (1991)
  • N. Kiupel et al.

    Process supervision with the aid of fuzzy logik

  • I. de Kleer et al.

    A qualitative physics based on confluences

    Artificial Intelligence

    (1984)
  • I. de Kleer et al.

    Diagnosing multiple faults

    Artificial Intelligence

    (1987)
  • Cited by (114)

    • Artificial Intelligence techniques applied as estimator in chemical process systems - A literature survey

      2015, Expert Systems with Applications
      Citation Excerpt :

      Nevertheless, one disadvantages of fuzzy logic is that the results sometimes depend on the number of rules, inference systems and the type of membership function applied. Furthermore, there is no guideline to obtain them but with trial and error or based on past experiences similar to ANN (Delrot, Guerra, Dambrine, & Delmotte, 2012; Frank & Köppen-Seliger, 1997; Liu, 2007). Table 2.2(b) lists out all the application of fuzzy logic as estimators in chemical process systems.

    • Hybrid computing techniques for fault detection and isolation, a review

      2015, Computers and Electrical Engineering
      Citation Excerpt :

      By applying a fuzzy rule-based approach, the fault decision process can be made robust to the uncertainties so that false and missed alarm rates can be minimized. Considering supervisory control [5,6] with tasks such as system management, process monitoring, identification, fault detection, diagnosis and adaptive capability reduces the control system to lower level models for developing simpler structures for observers and controllers using TS fuzzy models [7,8,14,29]. Genetic Algorithms (GAs) are a special type of evolutionary algorithms that simulate biological processes to solve search and optimization problems.

    View all citing articles on Scopus
    View full text