Advertisement

Efficient Plant Supervision Strategy Using NN Based Techniques

  • Ramon Ferreiro Garcia
  • Jose Luis Calvo Rolle
  • Francisco Javier Perez Castelo
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6076)

Abstract

Most of non-linear type one and type two control systems suffers from lack of detectability when model based techniques are applied on FDI (fault detection and isolation) tasks. In general, all types of processes suffer from lack of detectability also due to the ambiguity to discriminate the process, sensors and actuators in order to isolate any given fault. This work deals with a strategy to detect and isolate faults which include massive neural networks based functional approximation procedures associated to recursive rule based techniques applied to a parity space approach.

Keywords

Backpropagation Conjugate Gradient Fault Detection Fault Isolation Neural Networks Parity Space Residual Generation 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Willsky, A.S.: A survey of design methods for failure detection systems. Automatica 12, 601–611 (1976)MathSciNetCrossRefzbMATHGoogle Scholar
  2. 2.
    Isermann, R.: Process fault detection based on modeling and estimation methods - a survey. Automatica 20(4), 387–404 (1984)CrossRefzbMATHGoogle Scholar
  3. 3.
    Frank, P.M.: Fault Diagnosis in Dynamic systems via State Estimation - A Survey. In: Tzafestas, et al. (eds.) System Fault Diagnostics, Reliability and Related Knowledge-Based Approaches, vol. 1, pp. 35–98. D. Reidel Publíshing Company, Dordrecht (1987)CrossRefGoogle Scholar
  4. 4.
    Gertler, J.J.: Survey of Model-Based Failure Detection and Isolation in Complex Plants. IEEE Control Systems Magazine 8(6), 3–11 (1988)CrossRefGoogle Scholar
  5. 5.
    Patton, R.J., Chen, J.: A review of parity space approaches to fault diagnosis. In: IFAC Symposium SAFEPROCE5S 1991, Baden-Baden, Germany, vol. I, pp. 239–256 (1991) (preprints)Google Scholar
  6. 6.
    Himmelblau, D.M.: Fault detection and diagnosis in chemical and petrochemical processes. Elsevier, Amsterdam (1978)Google Scholar
  7. 7.
    Pau, L.F.: Failure Diagnosis and Performance Monitoring. Marcel Dekker, New York (1981)zbMATHGoogle Scholar
  8. 8.
    Basseville, M.: Optimal Sensor Location for Detecting Changes in Dynamical Behaviour, Rapport de Recherche No. 498, INRIA (1986)Google Scholar
  9. 9.
    Clark, R.N.: A simplified instrument detection scheme. IEEE Trans. Aerospace Electron. Syst. 14, 558–563 (1978)CrossRefGoogle Scholar
  10. 10.
    Mehra, R.K., Peschon, J.: An innovations approach to fault detection and diagnosis in dynamic systems. Automatica 7, 637–640, 316 (1971)CrossRefGoogle Scholar
  11. 11.
    Beard, R.V.: Failure accommodation in linear systems through self-reorganization, Rept. MVT-71-1. Man Vehicle Laboratory, Cambridge, Massachusetts (1971)Google Scholar
  12. 12.
    Gertler, J.J.: Analytical Redundancy Methods in Fault Detection and Isolation - Survey and Synthesis. In: Preprints of the IFAC/IMACS-Symposium on Fault Detection, Supervision and Safety for Technical Processes, SAFEPROCESS 1991, Baden-Baden, FRG, September 10-13, vol. 1, pp. 9–21 (1991)Google Scholar
  13. 13.
    Patton, R.J., Chen, J.: A review of parity space approaches to fault diagnosis for aerospace systems. J. of Guidance Control Dynamics 17(2), 278–285 (1994)CrossRefzbMATHGoogle Scholar
  14. 14.
    Ragot, J., Maquin, D., Kratz, F.: Observability and redundancy decomposition application to diagnosis. In: Patton, R.J., Frank, P.M., Clark, R.N. (eds.) Issues of Fault Diagnosis for Dynamic Systems, ch. 3, pp. 52–85. Springer, London (2000)Google Scholar
  15. 15.
    Hong, S.J., May, G.S.: Neural Network-Based Real-Time Malfunction Diagnosis of Reactive Ion Etching Using In Situ Metrology Data. IEEE Transactions on Semiconductor Manufacturing 17(3), 408–421 (2004)CrossRefGoogle Scholar
  16. 16.
    Rouhani, M., Soleymani, R.: Neural Networks based Diagnosis of heart arrhythmias using chaotic and nonlinear features of HRV signals. In: International Association of Computer Science and Information Technology - Spring Conference, pp. 545–549 (2009)Google Scholar
  17. 17.
    Ma, Y.-G., Ma, L.-Y., Ma, J.: RBF neural network based fault diagnosis for the thermodynamic system of a thermal power generating unit. In: Proceedings of the Fourth International Conference on Machine Learning and Cybernetics, Guangzhou, pp. 4738–4843 (2005)Google Scholar
  18. 18.
    Abe, Y., Konishi, M., Imai, J.: Neural network based diagnosis method for looper height controller of hot strip mills. In: Proceedings of the First International Conference on Innovative Computing, Information and Control (ICICIC 2006), 0-7695-2616-0/06 $20.00 © 2006. IEEE, Los Alamitos (2006)Google Scholar
  19. 19.
    Patan, K., Witczak, M., Korbicz, J.: Towards robustness in neural network based fault diagnosis. Int. J. Appl. Math. Computers. Sci. 18(4), 443–454 (2008)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Ramon Ferreiro Garcia
    • 1
  • Jose Luis Calvo Rolle
    • 2
  • Francisco Javier Perez Castelo
    • 2
  1. 1.ETSNM, Dept. Industrial Eng.University of La CorunaSpain
  2. 2.EUP, Dept. Industrial Eng.University of La CorunaSpain

Personalised recommendations