Advertisement

Model-Based Recurrent Neural Network for Fault Diagnosis of Nonlinear Dynamic Systems

  • C. Gan
  • K. Danai
Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 67)

Abstract

A model-based recurrent neural network (MBRNN) is presented for modeling dynamic systems and their fault diagnosis. This network has a fixed structure that is defined according to the linearized state-space model of the plant. Therefore, the MBRNN has the ability to incorporate the analytical knowledge of the plant in its formulation. Leaving the original topology intact, the MBRNN can subsequently be trained to represent the plant nonlinearities through modifying its nodes’ activation functions, which consist of contours of Gaussian radial basis functions (RBFs). Training in MBRNN involves adjusting the weights of the RBFs so as to modify the contours representing the activation functions. The performance of the MBRNN is demonstrated via several examples, and in application to the IFAC Benchmark Problem. The results indicate that MBRNN requires much shorter training than needed by ordinary recurrent networks. This efficiency in training is attributed to the MBRNN’s fixed topology which is independent of training In application to fault diagnosis, a salient feature of MBRNN is that it can be formulated according to the present model-based fault diagnostic solutions as its starting point, and subsequently improve these solutions via training by adapting them to plant nonlinearities. The diagnostic results indicate that the MBRNN performs better than ‘black box’ neural networks.

Keywords

Regularization Parameter Fault Diagnosis Extend Kalman Filter Recurrent Neural Network Radial Basis Function Network 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Nerrand, O., Roussel-Ragot, P., Urbani, D., Personnaz, L., and Dreyfus, G. (1994), “Training recurrent neural networks: why and how? An illustration in dynamical process modeling,” IEEE Trans. on Neural Networks, vol. 5, no. 2, pp. 178–184.CrossRefGoogle Scholar
  2. [2]
    Albus, J. (1975), “A new approach to manipulator control: the cerebellar model articulation controller,” ASME J. of Dynamic System, Measurement and Control, vol. 97, pp. 220–227.MATHCrossRefGoogle Scholar
  3. [3]
    Miller, W.T. (1989), “Real time application of neural networks for sensor-based control of robots with vision,” IEEE Trans. on Systems, Man, and Cybernetics, vol. 19, pp. 825–831.Google Scholar
  4. [4]
    Parlos, A.G., Chong, K.T., and Atiya, A.F. (1994), “Application of the recurrent multilayer perceptron in modeling complex process dynamics,” IEEE Trans. on Neural Networks, vol. 5, no. 2, pp. 255266.Google Scholar
  5. [5]
    Srinivasan, A. and Batur, C. (1994), “Hopfield/art-1 neural network-based fault detection and isolation,” IEEE Trans. on Neural Networks, vol. 5, no. 6, pp. 890–899.CrossRefGoogle Scholar
  6. [6]
    Srinivasan, B., Prasad, U.R., and Rao, N.J. (1994), “Back propagation through adjoints for the identification of nonlinear dynamic systems using recurrent neural models,” IEEE Trans. on Neural Networks, vol. 5, no. 2, pp. 213–227.CrossRefGoogle Scholar
  7. [7]
    Obradovic, D. (1996), “On-line training of recurrent neural networks with continuous topology adaptation,” IEEE Trans. on Neural Networks, vol. 7, pp. 222–228.CrossRefGoogle Scholar
  8. [8]
    Ku, C.C. and Lee, K.Y. (1995), “Diagonal recurrent neural networks for dynamic systems control,” IEEE Trans. on Neural Networks, vol. 6, no. 1, pp. 144–156.CrossRefGoogle Scholar
  9. [9]
    Denoeux, T. and Lengelle, R. (1993), “Initializing back propagation networks with prototypes,” IEEE Trans. on Neural Networks, vol. 6, pp. 351–363.CrossRefGoogle Scholar
  10. [10]
    Narendra, K.S. and Parthasarathy, K. (1990), “Identification and control of dynamical systems using neural networks,” IEEE Trans. on Neural Networks, vol. 1, no. 1, pp. 4–27.CrossRefGoogle Scholar
  11. [11]
    Jang, J.S. and Sun, C.T. (1993), “Functional equivalence between radial basis function networks and fuzzy inference systems,” IEEE Trans. on Neural Networks, vol. 4, pp. 156–159.CrossRefGoogle Scholar
  12. [12]
    Hunt, K.J., Haas, R., and Murray-Smith, R. (1996), “Extending the functional equivalence of radial basis function networks and fuzzy inference systems,” IEEE Trans. on Neural Networks, vol. 7, pp. 776–781.CrossRefGoogle Scholar
  13. [13]
    Towell, G.G. and Shavlik, J.W. (1994), “Knowledge-based artificial neural networks,” Artificial Intelligence, vol. 70, pp. 110–165.CrossRefGoogle Scholar
  14. [14]
    Omlin, C.W. and Giles, C.L. (1996), “Rule revision with recurrent neural networks,” IEEE Trans. on Knowledge and Data Engineering, vol. 8, no. 1, pp. 183–197.CrossRefGoogle Scholar
  15. [15]
    Livstone, M.M., Farrell, J.A., and Baker, W.L. (1992), “A computationally efficient algorithm for training recurrrent connectionist networks,” ACC/WM2, pp. 555–561.Google Scholar
  16. [16]
    Hocking, R.R. (1976), “The analysis and selection of variables in linear regression,” Biometrics, vol. 32, pp. 1–49.MathSciNetMATHCrossRefGoogle Scholar
  17. [17]
    Hocking, R.R. (1983), “Developments in linear regression methodology,” Technometrics, vol. 25, pp. 219–249.MathSciNetMATHGoogle Scholar
  18. [18]
    Orr, M.J.L. (1996), “Introduction to radial basis function networks,” Tech. Rep., Centre for Cognitive Science, University of Edinburgh.Google Scholar
  19. [19]
    Werbos, P.J. (1990), “Backpropagation through time: what it does and how to do it,” Proc. IEEE, vol. 78, no. 10, pp. 1550–1560.CrossRefGoogle Scholar
  20. [20]
    Narendra, K.S. and Parthasarathy, K. (1991), “Gradient methods for the optimization of dynamical systems containing neural networks,” IEEE Trans. on Neural Networks, vol. 2, no. 2, pp. 252–262.CrossRefGoogle Scholar
  21. [21]
    Gelb, A. (1974), Applied Optimal Estimation, Cambridge, MA: MIT Press.Google Scholar
  22. [22]
    Rumelhart, D.E. and McClelland, J.L. (1986), Parallel distributed processing: Explorations in microstructure of cognition, Cambridge, MA: MIT Press.Google Scholar
  23. [23]
    Hagan, M.T., Demuth, H.B., and Beale, M. (1996), Neural Networks Design, Boston: PWS Publishing Company.Google Scholar
  24. [24]
    Lewis, F.L., Abdallah, C.T., and Dawson, D.M. (1993), Control of Robot Manipulators,Macmillan Publishing Company.Google Scholar
  25. [25]
    Frank, P.M. (1990), “Fault diagnosis in dynamic systems using analytical and knowledge-based redundancy–a survey and some new results,” Automatica, vol. 26, no. 2, pp. 459–474.MATHCrossRefGoogle Scholar
  26. [26]
    Basseville, M. (1988), “Detecting changes in signals and systems–a survey,” Automatica, vol. 24, no. 3, pp. 309–326.MathSciNetMATHCrossRefGoogle Scholar
  27. [27]
    De Kleer, J. and Williams, B.C. (1987), “Diagnosing multiple faults,” Artificial Intelligence, vol. 32, pp. 97–130.MATHCrossRefGoogle Scholar
  28. [28]
    Jammu, V.B., Danai, K., and Lewicki, D.G. (1998), “Strucuturebased connectionist network for fault diagnosis of helicopter gearboxes,” ASME J. of Mechanical Design, vol. 120, no. 1, pp. 100–105.CrossRefGoogle Scholar
  29. [29]
    Patton, R.J. and Chen, J. (1996), “Neural networks in fault diagnosis of nonlinear dynamic systems,” Engineering Simulation, vol. 13, pp. 905–924.Google Scholar
  30. [30]
    Blanke, M. and Patton, R.J. (1995), “Industrial actuator benchmark for fault detection and isolation,” Control Eng. Practice, vol. 3, no. 12, pp. 1727–1730.CrossRefGoogle Scholar
  31. [31]
    Bogh, S. (1995), “Multiple hypothesis-testing approach to fdi for the industrial actuator benchmark,” Control Eng. Practice, vol. 3, no. 12, pp. 1763–1768.CrossRefGoogle Scholar
  32. [32]
    Grainger, R.W., Holst, J., Isaksson, A.J., and Ninness, B.M. (1995), “A parametric statistical approach to fdi for the industrial actuator benchmark,” Control Eng. Practice, vol. 3, no. 12, pp. 1757–1762.CrossRefGoogle Scholar
  33. [33]
    Hofling, T., Pfeufer, T., Deibert, R., and Isermann, R. (1995), “An observer and signal-processing approach to fdi for the industrial actuator benchmark test,” Control Eng. Practice, vol. 3, no. 12, pp. 1741–1746.CrossRefGoogle Scholar
  34. [34]
    Garcia, E.A., Koppen-Seliger, B., and Frank, P.M. (1995), “A frequency domain approach to residual generation for the industrial actuator benchmark,” Control Eng. Practice, vol. 3, pp. 1747–1750.CrossRefGoogle Scholar
  35. [35]
    Walker, B.K. and Huang, K.Y. (1995), “Fdi by extended kalman filter parameter estimation for an industrial actuator benchmark,” Control Eng. Practice, vol. 3, no. 12, pp. 1769–1774.CrossRefGoogle Scholar
  36. [36]
    Jorgensen, R.B., Patton, R.J., and Chen, J. (1995), “An eigenstructure assignment approach to fdi for the industrial actuator benchmark test,” Control Eng. Practice, vol. 3, no. 12, pp. 1751–1756.CrossRefGoogle Scholar
  37. [37]
    Patton, R.J. and Chen, J.A. (1991), “A review of parity space approaches to fault diagnosis,” No. 1, (Baden-Baden), pp. 239–255.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • C. Gan
  • K. Danai

There are no affiliations available

Personalised recommendations