Convergence behaviour of connectionist models in large scale diagnostic problems

  • Laszlo Monostori
  • Achim Bothe
Pattern Recognition
Part of the Lecture Notes in Computer Science book series (LNCS, volume 604)


Though artificial neural networks have been successfully applied for diagnostic problems of different natures, difficulties arise by applying this approach, especially the most frequently used back propagation (BP) procedure, for large scale technical diagnostic problems. Therefore, some acceleration techniques of the BP procedure are described and investigated in the paper. Some network models isomorphic to conventional pattern recognition techniques are also enumerated, with special emphasis on the Condensed Nearest Neighbour Network (CNNN), which is a new, self-organizing network model with supervised learning ability. The surveyed techniques are analyzed and compared on a diagnostic problem with more than 300 pattern features.


Technical diagnosis Pattern recognition Artificial neural networks 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    D. Barschdorff, Th. Dressler, W. Nitsche: Real-time failure detection on complex mechanical structures via parallel data processing, tNorth-Holland, Computers in Industry, Vol. 7., 1986, pp. 23–30.Google Scholar
  2. 2.
    D. Barschdorff, A. Bothe, G. Wöstenkühler: Vergleich lernender Mustererkennungsverfahren und neuronaler Netze zur Prüfung und Beurteilung von Maschinengeräuschen, Proc. Schalltechnik'90, VDI Berichte Nr. 813, pp. 23–41.Google Scholar
  3. 3.
    D. Barschdorff, D. Becker: Neural networks as signal and pattern classificators, Technisches Messen, No. 11, 1990, pp. 437–444.Google Scholar
  4. 4.
    D. Barschdorff, A. Bothe: Signal classification using a new self-organising and fast converging neural network, Noise & Vibration, Vol. 22, No. 9, Oct. 1991, pp. 11–19.Google Scholar
  5. 5.
    D. Barschdorff: Case studies in adaptive fault diagnosis using neural networks, Proc. of the IMACS Annals on Computing and Applied Mathematics, MIM-S2, 3–7, Sept, 1990, Brüssels, pp. III.A.1/1–1/6.Google Scholar
  6. 6.
    D. Barschdorff, L. Monostori, A.F. Ndenge, G. Wöstenkühler: Multiprocessor systems for connectionist diagnosis of technical processes, Computers in Industry, Special Issue on Learning in IMS, 1991, pp. 131–145.Google Scholar
  7. 7.
    D. Barschdorff, L. Monostori: Neural networks, their applications and perspectives in the intelligent machining, A survey paper, Computers in Industry, Special Issue on Learning in IMS, 1991, pp. 101–119.Google Scholar
  8. 8.
    P. Bartal, L. Monostori: A pattern recognition based vibration monitoring module for machine tools, Robotics & Computer-Integrated Manufacturing, Vol. 4, No. 3/4, 1988, pp. 465–469.Google Scholar
  9. 9.
    DARPA neural network study, AFCEA International Press, 1988Google Scholar
  10. 10.
    D.A. Dornfeld: Unconventional sensors and signal conditioning for automatic supervision, AC'90, III. CIRP International Conference on Automatic Supervision, Monitoring and Adaptive Control in Manufacturing, 3–5. Sept, 1990, Rydzyna, Poland, pp. 197–233.Google Scholar
  11. 11.
    P.E. Hart: The condensed nearest neighbour rule, IEEE Transaction on Information Theory, May, 1968, pp. 515–516.CrossRefGoogle Scholar
  12. 12.
    R. Lippmann: An introduction to computing with neural nets, IEEE ASSP Magazine, April 1987, pp. 4–21.Google Scholar
  13. 13.
    J. Makhoul, A. El-Jaroudi, R. Schwartz: Formation of disconnected decision regions with a single hidden layer, Proc. of the Int. Joint Conference on Neural Networks, 19–22 June, 1989, Washington, D.C., Vol. I., pp. 455–460.CrossRefGoogle Scholar
  14. 14.
    P. Mertens: Expertensysteme in der Produktion, Oldenburg, München, Wien, 1990.Google Scholar
  15. 15.
    M. Minsky, S. Papert: Perceptrons: an introduction computational geometry, MIT Press, Cambridge, 1969.Google Scholar
  16. 16.
    G. Mirchandi, W. Cao: On hidden nodes for neural nets, IEEE Trans. on Circuits and Systems, Vol. 36, No. 5, May 1989, pp. 661–664.CrossRefGoogle Scholar
  17. 17.
    L. Monostori: Learning procedures in machine tool monitoring, North-Holland, Computers in Industry, Vol. 7., 1986., pp. 53–64.CrossRefGoogle Scholar
  18. 18.
    L. Monostori, J. Nacsa: On the application of neural nets in real-time monitoring of machining processes, Preprints of the 22nd CIRP International Seminar on Manufacturing Systems, 11–12, June, 1990, Enschede, the Netherlands, pp. 6A/15-27.Google Scholar
  19. 19.
    L. Monostori: Signal processing and decision making in machine tool monitoring systems, The Journal of Condition Monitoring, Vol. 3, No. 1, 1989, pp. 1–20.Google Scholar
  20. 20.
    J. Nacsa, L. Monostori: Real-time monitoring of machining processes, Proc. of the AC'90, III. CIRP International Conference on Automatic Supervision, Monitoring and Adaptive Control in Manufacturing, 2a. Poster Papers, 3–5. Sept, 1990, Rydzyna, Poland, pp. 8–22.Google Scholar
  21. 21.
    N. J. Nilsson: Learning machines, Mc Graw-Hill Book Company, New York, 1965.Google Scholar
  22. 22.
    F. Rosenblatt: The perceptron: A probabilistic model for information storage and organization in the brain, Psychological Review, Vol. 65, 1958, pp.386–408.PubMedGoogle Scholar
  23. 23.
    D.E. Rummelhart, J.L. McClelland: Parallel distributed processing, MIT Press, Cambridge, 1986Google Scholar
  24. 24.
    D.F. Specht: Probabilistic neural networks, Neural Networks, Vol. 3, 1990, pp. 109–118.CrossRefGoogle Scholar
  25. 25.
    T. Tollenare: SuperSAB: fast adaptive back propagation with good scaling properties, Neural Networks, Vol. 3, 1990, pp. 561–573.CrossRefGoogle Scholar
  26. 26.
    T.P. Vogl, J.K. Mangis, A.K. Rigler, W.T. Zink, D.L. Alkon: Accelerating the convergence of the back propagation method, Biological Cybernetics, Vol. 59, 1988, pp. 257–263.CrossRefGoogle Scholar
  27. 27.
    M. Weck, L. Monostori, L. Kühne: Universelles System zur Prozess-und Anlagenüberwachung, Vortrag und Berichtsband der VDI/VDE-GMR Tagung Verfahren und Systeme zur technischen Fehlerdiagnose, Langen, FRG, 2–3 Apr. 1984, pp. 139–154.Google Scholar
  28. 28.
    P.J. Werbos: Backpropagation through time: what it does and how to do it, Proceedings of the IEEE, Vol. 78, No. 10, Oct. 1990, pp. 1550–1560.CrossRefGoogle Scholar
  29. 29.
    J.H. Winters, C. Rose: Minimum distance automata in parallel networks for optimum classification, Neural Networks, Vol. 2, 1989, pp. 127–132.CrossRefGoogle Scholar
  30. 30.
    H.C. Yau, M.T. Manry: Iterative improvement of a Gaussian classifier, Neural Networks, Vol. 3, 1990, pp. 437–443.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1992

Authors and Affiliations

  • Laszlo Monostori
    • 1
  • Achim Bothe
    • 1
  1. 1.Institute of Electrical MeasurementUniversity of PaderbornPaderborn

Personalised recommendations