Advertisement

A Training Algorithm for Locally Recurrent NN Based on Explicit Gradient of Error in Fault Detection Problems

  • Sara Carcangiu
  • Augusto Montisci
  • Patrizia Boi
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 311)

Abstract

In this work a diagnostic approach for nonlinear systems is presented. The diagnosis is performed resorting to a neural predictor of the output of the system, and by using the error prediction as a feature for the diagnosis. A locally recurrent neural network is used as predictor, after it has been trained on a reference behavior of the system. In order to model the system under test a novel training algorithm that uses an explicit calculation of the cost function gradient is proposed. The residuals of the prediction are affected by the deviation of the parameters from their nominal values. In this way, by a simple statistical analysis of the residuals, we can perform a diagnosis of the system. The Rössler hyperchaotic system is used as benchmark problem in order to validate the diagnostic neural approach proposed.

Keywords

Locally recurrent neural networks nonlinear systems diagnosis gradient-based training 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Isermann, R.: Fault diagnosis of machines via parameter estimation and knowledge processing. Automatica 29, 815–835 (1993)MathSciNetzbMATHCrossRefGoogle Scholar
  2. 2.
    Chen, J., Patton, R.J.: Robust model-based fault diagnosis for dynamic systems. Kluwer Academic Publishers, Boston (1999)zbMATHCrossRefGoogle Scholar
  3. 3.
    Isermann, R., Balle, P.: Trends in the application of model-based fault detection and diagnosis of technical processes. Control Engineering Practice 5, 709–719 (1997)CrossRefGoogle Scholar
  4. 4.
    Korbicz, J., Koscielny, J.M., Kowalczuk, Z., Cholewa, W.: Fault Diagnosis. Models, Artificial Intelligence, Applications. Springer, Berlin (2004)zbMATHGoogle Scholar
  5. 5.
    Patton, R.J., Korbicz, J.: Advances in Computational Intelligence for Fault Diagnosis Systems. International Journal of Applied Mathematics and Computer Science 9, 468–735 (1999)Google Scholar
  6. 6.
    Nelles, O.: Nonlinear System Identification. From Classical Approaches to Neural Networks and Fuzzy Models. Springer, Berlin (2001)zbMATHCrossRefGoogle Scholar
  7. 7.
    Tsoi, A.C., Back, A.D.: Locally Recurrent Globally Feedforward Networks: A Critical Review of Architectures. IEEE Transactions on Neural Networks 5, 229–239 (1994)CrossRefGoogle Scholar
  8. 8.
    Chang, L.C., Chang, F.J., Chiang, Y.M.: A two-step-ahead recurrent neural network for stream-flow forecasting. Hydrological Processes 18, 81–92 (2004)CrossRefGoogle Scholar
  9. 9.
    Zio, E., Di Maio, F., Stasi, M.: A data-driven approach for predicting failure scenarios in nuclear systems. Annals of Nuclear Energy 37, 482–491 (2010)CrossRefGoogle Scholar
  10. 10.
    Campolucci, P., Uncini, A., Piazza, F., Rao, B.D.: Online learning algorithms for locally recurrent neural networks. IEEE Transactions on Neural Networks 10, 253–271 (1999)CrossRefGoogle Scholar
  11. 11.
    Boi, P., Montisci, A.: A Neural Based Approach and Probability Density Approximation for Fault Detection and Isolation in Nonlinear Systems. In: Iliadis, L., Jayne, C. (eds.) EANN/AIAI 2011, Part I. IFIP AICT, vol. 363, pp. 296–305. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  12. 12.
    Cannas, B., Cincotti, S., Marchesi, M., Pilo, F.: Learning of Chua’s circuit attractors by locally recurrent neural networks. Chaos, Solitons and Fractals 12, 2109–2115 (2001)zbMATHCrossRefGoogle Scholar
  13. 13.
    Peng, C.C., Magoulas, G.D.: Nonmonotone BFGS-trained recurrent neural networks for temporal sequence processing. Applied Mathematics and Computation 217, 5421–5441 (2011)MathSciNetzbMATHCrossRefGoogle Scholar
  14. 14.
    Patan, K.: Stability Analysis and the Stabilization of a Class of Discrete-Time Dynamic Neural Networks. IEEE Transactions on Neural Networks 18, 660–673 (2007)CrossRefGoogle Scholar
  15. 15.
    Rössler, O.E.: An equation for hyperchaos. Physics Letters A 71, 155–157 (1979)MathSciNetzbMATHCrossRefGoogle Scholar
  16. 16.
    Wang, G.Y., Zhang, X., Zheng, Y., Li, Y.X.: A new modified hyperchaotic Lü system. Physica A 371, 260–272 (2006)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Sara Carcangiu
    • 1
  • Augusto Montisci
    • 1
  • Patrizia Boi
    • 1
  1. 1.Department of Electrical and Electronic EngineeringUniversity of CagliariCagliariItaly

Personalised recommendations