Journal of Intelligent Manufacturing

, Volume 16, Issue 6, pp 679–691 | Cite as

Application of a Neural Fuzzy System with Rule Extraction to Fault Detection and Diagnosis



In this paper, the fuzzy min–max (FMM) neural network is integrated with a rule extraction algorithm, and the resulting network is applied to a real-world fault detection and diagnosis task in complex industrial processes. With the rule extraction capability, the FMM network is able to overcome the “black-box” phenomenon by justifying its predictions using fuzzy if–then rules that are comprehensible to domain users. To assess the effectiveness of the FMM network, real sensor measurements are collected and used for detecting and diagnosing the heat transfer and tube blockage conditions of a circulating water (CW) system in a power generation plant. The FMM network parameters are systematically varied and tested, with the results explained. Bootstrapping is employed to quantify stability of the network performance statistically. The extracted rules are found to be compatible with the domain information as well as the opinions of domain experts who are involved in the maintenance of the CW system. Implications of the FMM network with the rule extraction facility as an intelligent and useful fault detection and diagnosis tool are discussed.


Fault detection and diagnosis fuzzy min–max neural network rule extraction 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Al-Najjar, B. 1996Total quality maintenance: An approach for continuous reduction in costs of quality productsJournal of Quality in Maintenance Engineering.2220CrossRefGoogle Scholar
  2. Andrews, R., Diederich, J., Tickle, A.B. 1995A survey and critique of techniques for extracting rules from trained artificial neural networksKnowledge Based Systems.8373389CrossRefGoogle Scholar
  3. Carpenter, G.A., Tan, A.H. 1995Rule extraction: From neural architecture to symbolic representationConnection Science.7327Google Scholar
  4. Craven, M. W. and Shavlik, J. W. (1994). Using sampling and queries to extract rules from trained neural networks. Machine Learning: Proceedings of the Eleventh International Conference, San Francisco, CA, USAGoogle Scholar
  5. Freitas, J.F.G., MacLeod, I.M., Maltz, J.S. 1999Neural networks for pneumatic actuator fault detectionTrans of the SAIEE.902834Google Scholar
  6. Dellomo, M.R. 1999Helicopter gearbox fault detection: a neural network based approachJournal of Vibration and Acoustics.121265272Google Scholar
  7. Denny, G. 1993F16 jet engine trending and diagnostics with neural networksProc. SPIE.1965419412CrossRefGoogle Scholar
  8. Dietz W.E., Kiech E.L., Ali M. (1989). Jet and rocket engine fault diagnosis in real time. Journal of Neural Network Computing, 1Google Scholar
  9. Efron, B. 1979Bootstrap methods. Another look at the jackknifeThe Annals of Statistics.7126Google Scholar
  10. Efron, B. and Tibshirani, R. J. (1993). An Introduction to the Bootstrap, Chapman & HallGoogle Scholar
  11. Fu, L.M. 1994Rule generation from neural networksIEEE Transacations on Systems, Man, and Cybernetics.2811141124Google Scholar
  12. Jack, L.B., NandiA.K., , McCormick, A.C. 1999Diagnosis of rolling element bearing faults using radial basis function networksApplied Sig. Process.62532CrossRefGoogle Scholar
  13. Kohonen, T. 1984Self-Organization and Associative MemorySpringer-VerlagBerlinGoogle Scholar
  14. Kuo, R.J. 1995Intelligent diagnosis for turbine blade faults using artificial neural networks and fuzzy logicEngineering Applications of Artificial Intelligence.82534CrossRefGoogle Scholar
  15. Polycarpou, M.M., Helmicki, A.J. 1995Automated fault detection and accommodation: A learning system approachIEEE Trans on System, Man, and Cybernetics.2514471458Google Scholar
  16. Pari Power Station (1999). System description and operating procedures, Prai Power Station Stage 3, 14Google Scholar
  17. Sharkey, A.J.C., Chandroth, G.O., Sharkey, N.E 2000A multi-net system for the fault diagnosis of a diesel engineNeural Computing and Applications.9152160CrossRefGoogle Scholar
  18. Simpson, P. 1992Fuzzy min-max neural networks—Part 1: ClassificationIEEE Transacations on Neural Networks.3776786CrossRefGoogle Scholar
  19. Tan, S.C., Lim, C.P. 2004Application of an adaptive neural network with symbolic rule extraction to fault detection and diagnosis in a power generation plantIEEE Trans. On Energy Conversion.19369377CrossRefGoogle Scholar
  20. Tikle, A. B., Orlowski, M. and Diederich, J. (1996). DEDEC: A methodology for extracting rule from trained artificial neural networks. In Proceedings of the Rule Extraction From Trained Artificial Neural Network Workshop, Society For the Study of Artificial Intelligence and Simulation of Behaviour Workshop Series (AISB’96), University of Sussex, Brighton, UK, 90–102Google Scholar
  21. Venkatasubramanian, V., Rengaswamy, R., Yin, K., Kavuri, S.N 2003aA review of process fault detection and diagnosis. Part I: Quantitative model-based methodsComputers and Chemical Engineering.27293311CrossRefGoogle Scholar
  22. Venkatasubramanian, V., Rengaswamy, R., Kavuri, S.N. 2003bA review of process fault detection and diagnosis. Part II: Qualitative models and search strategiesComputers and Chemical Engineering.27313326CrossRefGoogle Scholar
  23. Venkatasubramanian, V., Rengaswamy, R., Kavuri, S.N., Yin, K. 2003cA review of process fault detection and diagnosis. Part III: Process history based methodsComputers and Chemical Engineering.27327346CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, Inc. 2005

Authors and Affiliations

  1. 1.School of Electrical and Electronic EngineeringUniversity of Science MalaysiaNibong TebalMalaysia
  2. 2.MIMOS BerhadTechnology Park MalaysiaKuala LumpurMalaysia

Personalised recommendations