Skip to main content
SpringerLink
Log in

Artificial Neural Networks in Fault Diagnosis

  • Chapter
Fault Diagnosis

Abstract

In recent years there has been observed an increasing demand for dynamic systems in industrial plants to become safer and more reliable. These requirements go beyond the normally accepted safety-critical systems of nuclear reactors, chemical plants or aircraft. An early detection of faults can help avoid a system shut-down, components failures and even catastrophes involving large economic losses and human fatalities. A system that gives an opportunity to detect, isolate and identify faults is called a fault diagnosis system (Chen and Patton, 1999). The basic idea is to generate signals that reflect inconsistencies between the nominal and faulty system operating conditions. Such signals, called residuals, are usually calculated using analytical methods such as observers (Chen and Patton, 1999), parameter estimation (Isermann, 1994) or parity equations (Gertler, 1999). Unfortunately, the common disadvantage of these approaches is that a precise mathematical model of the diagnosed plant is required and that their application is limited. An alternative solution can be obtained using artificial intelligence. Artificial neural networks seem to be particularly very attractive when designing fault diagnosis schemes. Artificial neural networks can be effectively applied to both the modelling of the plant operating conditions and decision making (Korbicz et al., 2002).

The work was supported by the EU FP 5 Project Research Training Network DAMADICS: Development and Application of Methods for Actuators Diagnosis in Industrial Control Systems, 2000–2003.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 259.00
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 329.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 329.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  • Ayoubi M. (1994): Fault diagnosis with dynamic neural structure and application to a turbo-charger. — Proc. Int. Symp. Fault Detection Supervision and Safety for Technical Processes, SAFEPROCESS, Espoo, Finland, Vol. 2, pp. 618–623.

    Google Scholar 

  • Auda G. and Kamel M. (1997): CMNN: Cooperative Modular Neural Networks for pattern recognition. — Pattern Recognition Letters, Vol. 18, No. 5, pp. 1391–1398.

    Article  Google Scholar 

  • Bartyś M. and Kościelny J.M. (2002): Application of fuzzy logic fault isolation methods for actuator diagnosis. — Proc. 15th IFAC Triennial World Congress, Barcelona, Spain, CD-ROM.

    Google Scholar 

  • Calado J.M.F., Korbicz J., Patan K., Patton R.J. and Sá da Costa J.M.G. (2001): Soft computing approaches to fault diagnosis for dynamic systems. — European Journal of Control, Vol. 7, No. 2–3, pp. 248–286.

    Article  Google Scholar 

  • Chen J. and Patton R.J. (1999): Robust Model Based Fault Diagnosis for Dynamic Systems. — Berlin: Kluwer Academic Publishers.

    Book  MATH  Google Scholar 

  • Crowther W.J., Edge K.A., Burrows C.R., Atkinson R.M. and Woollons D.J. (1998): Fault diagnosis of a hydraulic actuator circuit using NNs: An output vector space classification approach. — J. Syst. and Control Engineering, Vol. 212, No. 1, pp. 57–68.

    Google Scholar 

  • Duch W., Korbicz J., Rutkowski L. and Tadeusiewicz R. (Eds.) (2000): Biocybernetics and Biomedical Engineering 2000. Neural Networks. — Warsaw: Akademicka Oficyna Wydawnicza, EXIT, Vol. 6, (in Polish).

    Google Scholar 

  • Elman J.L. (1990): Finding structure in time. — Cognitive Science, Vol. 14, pp. 179–211.

    Article  Google Scholar 

  • Fasconi P., Gori M. and Soda G. (1992): Local feedback multilayered networks. Neural Computation, Vol. 4, pp. 120–130.

    Article  Google Scholar 

  • Farlow S.J. (Ed.) (1984): Self-Organizing Methods in Modeling — GMDH Type Algorithms. — New York: Marcel Dekker.

    MATH  Google Scholar 

  • Fine T.L. (1999): Feed-forward Neural Network Methodology. — New York: Springer-Verlag.

    Google Scholar 

  • Frank P.M. and Köppen-Seliger B. (1997): New development using AI in fault diagnosis. — Eng. Applic. Artif. Intell., Vol. 10, No. 1, pp. 3–14.

    Article  Google Scholar 

  • Frank P.M. and Marcu T. (2000): Diagnosis strategies and systems: Principles, fuzzy and neural approaches, In: Intelligent Systems and Interfaces (H.-N. Teodorescu, D. Mlynek, A. Kandel and H.-J. Zimmermann, Eds.). — Boston: Kluwer, pp. 1–39.

    Google Scholar 

  • Fuente M.J. and Saludes S. (2000): Fault detection and isolation in a non-linear plant via neural networks. — Proc. 4th IFAC Symp. Fault Detection, Supervision and Safety for Technical Processes, SAFEPROCESS, Budapest, Hungary, Vol. 1, pp. 472–477.

    Google Scholar 

  • Gertler J. (1999): Fault Detection and Diagnosis in Engineering Systems. — New York: Marcel Dekker, Inc.

    Google Scholar 

  • Gori M., Bengio Y. and Mori R.D. (1989): BPS: A learning algorithm for capturing the dynamic nature of spech. — Int. Joint Conf. Neural Networks, Vol. II, pp. 417–423.

    Article  Google Scholar 

  • Haykin S. (1999): Neural Networks. A Comprehensive Foundation. — New Jersey: Prentice Hall.

    MATH  Google Scholar 

  • Hunt K.J., Sbarbaro D., Żbikowski R. and Gathrop P.J. (1992): Neural networks for control systems. A survey. — Automatica, Vol. 28, No. 6, pp. 1083–1112.

    Article  MathSciNet  MATH  Google Scholar 

  • Isermann R. (1994): Fault diagnosis of machines via parameter estimation and knowledge processing — A tutorial paper. — Automatica, Vol. 29, No. 4, pp. 815–835.

    Article  MathSciNet  Google Scholar 

  • Ivakhnenko A.G. (1971): Polynominal theory of complex systems. — IEEE Trans. System, Man and Cybernetics, Vol. SMC-1, No. 4. pp. 44–58

    Google Scholar 

  • Ivakhnenko A.G. and Müller J.A. (1995): Self-organizing of nets of active neurons. — System Analysis Modelling Simulation, Vol. 20, pp. 93–106.

    Google Scholar 

  • Kohonen T. (1984): Self-organization and Associative Memory. — Berlin: Springer-Verlag.

    MATH  Google Scholar 

  • Koivo H.N. (1994): Artificial neural networks in fault diagnosis and control. — Control Eng. Practice, Vol. 2, No. 7, pp. 89–101.

    Article  Google Scholar 

  • Korbicz J., Mrugalski M. and Parisini Th. (2002): Designing state-space models with neural networks. — Proc. 15th IFAC Triennial Word Congres, Barcelona, Spain, CD ROM.

    Google Scholar 

  • Korbicz J., Obuchowicz A. and Patan K. (1998): Network of dynamic neurons in fault detection systems. — Proc. IEEE Int. Conf. Systems, Man and Cybernetics, San Diego, USA, CD-ROM.

    Google Scholar 

  • Korbicz J., Patan K. and Obuchowicz A. (1999): Dynamic neural networks for process modelling in fault detection and isolation systems. — Int. J. Appl. Math. and Compo Sci., Vol. 9, No. 3, pp. 519–546.

    MATH  Google Scholar 

  • Korbicz J., Kościelny J. M., Kowalczuk Z. and Cholewa W. (2002): Diagnostics of Processes. Models, Artificial Intelligence Methods, Applications. — Warsaw: Wydawnictwa Naukowo-Techniczne, WNT, (in Polish).

    Google Scholar 

  • Koza J.R. (1992): Genetic Programming: On the Programming of Computers by Means of Natural Selection. — Cambridge, MA: The MIT Press.

    MATH  Google Scholar 

  • Kuschewski J.G., Hui S. and Zak S. (1993): Application of feedforward neural network to dynamical system identification and control. — IEEE Trans. Control Systems Technology, Vol. 1, No. 1, pp. 37–49.

    Article  Google Scholar 

  • Kuś J. and Korbicz J. (2000): Static and dynamic GMDH networks, In: Biocybernetics and Biomedical Engineering 2000. Neural Networks (W. Duch, J. Korbicz, L. Rutkowski and R. Tadeusiewicz, Eds.). — Warsaw: Akademicka Oficyna Wydawnicza, EXIT, Vol. 6, pp. 227–256, (in Polish)

    Google Scholar 

  • Lissane Elhaq S., Giri F. and Unbehauen H. (1999): Modelling, identification and control of sugar evaporation. Theoretical design and experimental evaluation. — Control Engineering Practice, Vol. 7, No. 8, pp. 931–942.

    Article  Google Scholar 

  • Magnoubi R.S. (1998): Robust Estimation and Failure Detection. — London: Springer-Verlag.

    Google Scholar 

  • Marciniak A. and Korbicz J. (2001): Diagnosis system based on multiple neural classifiers. — Bulletin of the Polish Academy of Sciences, Technical Sciences, Vol. 49, No. 4, pp. 681–701.

    MATH  Google Scholar 

  • Milanese M., Norton J., Piet-Lahanier H. and Walter E. (Eds.) (1996): Bounding Approaches to System Identification. — New York: Plenum Press.

    MATH  Google Scholar 

  • Mozer M.C. (1989): A focused backpropagation algorithm for temporal pattern recognition. — Complex Systems, Vol. 3, pp. 349–3

    MathSciNet  MATH  Google Scholar 

  • Narendra K.S. and Parthasarathy K. (1990): Identification and control of dynamical systems using neural networks. — IEEE Trans. Neural Networks, Vol. 1, No. 1, pp. 12–18.

    Article  Google Scholar 

  • Nelles O. (2001): Nonlinear System Identification. From Classical Approaches to Neural Networks and Fuzzy Models. — Berlin: Springer-Verlag.

    MATH  Google Scholar 

  • Norgard M., Ravn O., Poulsen N.K. and Hansen L.K. (2000): Neural Networks for Modelling and Control of Dynamic Systems. — London: Springer-Verlag.

    Book  Google Scholar 

  • Parlos A.G., Chong K.T. and Atiya A.F. (1994): Application of the recurrent multilayer perceptron in modelling complex process dynamics. — IEEE Trans. Neural Networks, Vol. 5, No. 2, pp. 255–266.

    Article  Google Scholar 

  • Patan K. and Korbicz J. (2000a): Dynamic neural networks and their application to modelling and identification, In: Biocybernetics and Biomedical Engineering 2000. Neural Networks (W. Duch, J. Korbicz, L. Rutkowski and R. Tadeusiewicz, Eds.). — Warsaw: Akademicka Oficyna Wydawnicza, EXIT, Vol. 6, pp. 389–417, (in Polish).

    Google Scholar 

  • Patan K. and Korbicz J. (2000b): Application of dynamic neural networks in an industrial plant. — Proc. 4th IFAC Symp. Fault Detection, Supervision and Safety for Technical Processes, SAFEPROCESS, Budapest, Hungary, Vol. 1, pp. 186–191.

    Google Scholar 

  • Patan K., Korbicz J. and Mrugalski M. (2002): Artificial neural networks to fault diagnosis, In: Diagnostics of Processes. Models, Artificial Intelligence Methods, Applications (J. Korbicz, J.M. Kościelny, Z. Kowalczuk and W. Cholewa, Eds.). — Warsaw: Wydawnictwa Naukowo-Techniczne WNT, (in Polish).

    Google Scholar 

  • Patan K., Obuchowicz A. and Korbicz J. (1999): Cascade network of dynamic neurons in fault detection systems. — Proc. 5th European Control Conf., ECC, Karlsruhe, CD-ROM.

    Google Scholar 

  • Patan K. and Parisini T. (2002): Stochastic approaches to dynamic neural network training. Actuator fault diagnosis study. — Proc. 15th IFAC Triennial World Congress, Barcelona, Spain, CD-ROM.

    Google Scholar 

  • Patton R.J., Frank P.M. and Clark R.N. (Eds.) (2000): Issues of Fault Diagnosis for Dynamic Systems. — Berlin: Springer-Verlag.

    Google Scholar 

  • Patton R.J. and Korbicz J. (Eds.) (1999): Advances in Computational Intelligence for Fault Diagnosis Systems. — Int. J. Appl. Math. and Compo Sci., Vol. 9, No. 3, Special Issue.

    Google Scholar 

  • Pham D.T. and Xing L. (1995): Neural Networks for Identification, Prediction and Control. — London: Springer Verlag.

    Book  Google Scholar 

  • Poddar P. and Unnikrishnan K.P. (1991): Memory neuron networks: A prolegomenon. — Technical Report of the General Motors Research Laboratories, GMR-7493.

    Google Scholar 

  • Sharif M.A. and Grosvenor R.I. (1998): Process plant condition monitoring and fault diagnosis. — J. Proc. Mech. Eng., Vol. 212, No. 1, pp. 13–30.

    Article  Google Scholar 

  • Tsoi A.Ch. and Back A.D. (1994): Locally recurrent globally feedforward networks: A critical review of architectures. — IEEE Trans. Neural Networks, Vol. 5, pp. 229–239.

    Article  Google Scholar 

  • Walter E. and Pronzato L. (1997): Identification of Parametric Models from Experimental Data. — London: Springer.

    MATH  Google Scholar 

  • Watton J. and Pham D.T. (1997): An artificial NN based approach to fault diagnosis and classification of fluid power systems. — J. Syst. and Control Engineering, Vol. 211, No. 4, pp. 307–317.

    Google Scholar 

  • Weerasinghe M., Gomm J.B. and Williams D. (1998): Neural networks for fault diagnosis of a nuclear fuel processing plant at different operating points. — Control Engineering Practice, Vol. 6, No. 2, pp. 281–289.

    Article  Google Scholar 

  • Williams R.J. and Zipser D. (1989): A learning algorithm for continually running fully recurrent neural networks. — Neural Computation, Vol. 1, pp. 270–289.

    Article  Google Scholar 

  • Vemuri A.T. and Polycarpou M.M. (1997): Neural-network-based robust fault diagnosis in robotic systems. — IEEE Trans. Neural Networks, Vol. 8, No. 6, pp. 1410–1420.

    Article  Google Scholar 

  • Yu D.L., Gomm J.B. and Williams D. (1999): Sensor fault diagnosis in a chemical process via RBF neural networks. — Control Engineering Practice, Vol. 7, No. 1, pp. 49–55.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Institute of Control and Computation Engineering, University of Zielona Góra, ul. Podgórna 50, 65-246, Zielona Góra, Poland

    Krzysztof Patan & Józef Korbicz

Authors
  1. Krzysztof Patan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Józef Korbicz
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Institute of Control and Computation Engineering, University of Zielona Góra, ul. Podgorna 50, 65-246, Zielona Góra, Poland

    Józef Korbicz

  2. Dept. of Automatic Control W.E.T.I., Technical University of Gdańsk, ul. Narutowicza 11/12, 80-952, Gdańsk, Poland

    Zdzisław Kowalczuk

  3. Institute of Automatic Control and Robotics, Warsaw University of Technology, ul. Chodkiewicza 8, 02-525, Warszawa, Poland

    Jan M. Kościelny

  4. Dept. of Fundamentals of Machine Design, Silesian University of Technology Gliwice, Konarskiego 18a, 44-100, Gliwice, Poland

    Wojciech Cholewa

Rights and permissions

Reprints and permissions

Copyright information

© 2004 Springer-Verlag Berlin Heidelberg

About this chapter

Cite this chapter

Patan, K., Korbicz, J. (2004). Artificial Neural Networks in Fault Diagnosis. In: Korbicz, J., Kowalczuk, Z., Kościelny, J.M., Cholewa, W. (eds) Fault Diagnosis. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-18615-8_9

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-18615-8_9

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-62199-4

  • Online ISBN: 978-3-642-18615-8

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation