Hidden Markov Model Based Transient Identification in NPPs

  • Kee-Choon Kwon
Part of the Power Systems book series (POWSYS)


In this chapter, a transient identification based on a hidden Markov model (HMM) has been suggested and evaluated experimentally for the classification of transients in nuclear power plants. The transient can be identified by its unique time dependent patterns related to the principal variables. The HMM, a double stochastic process, can be applied to transient identification which is a spatial and temporal classification problem under a statistical pattern recognition framework. The HMM is created for each transient from a set of training data by the maximum-likelihood estimation method. The transient identification is determined by calculating which model has the highest probability for the given test data. Several experimental tests have been performed with normalization methods, clustering algorithms, and a number of states in HMM. Several experimental tests have been performed including superimposing random noise, adding systematic error, and untrained transients. The proposed real-time transient identification system has many advantages, however, there are still a lot of problems that should be solved to apply to a real dynamic process. Further efforts are being made to improve the system performance and robustness to demonstrate reliability and accuracy to the required level.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    I. S. Kim, “Computerized Systems for On-line Management of Failures: A State-Of-The-Art Discussion of Alarm and Diagnostic Systems Applied in the Nuclear Industry,” Reliability Engineering and System Safety, Vol. 44, pp. 279–295, 1994.CrossRefGoogle Scholar
  2. [2]
    A. Ikonomopoulos, R. E. Uhrig, and L. Tsoukalas, “A Hybrid Neural Network-Fuzzy Logic Approach to Nuclear Power Plant Transient Identification,” AI91 Frontiers in Innovative Computing for the Nuclear Industry, pp.217–226, Jackson, Wyoming, Sep. 15–18, 1991.Google Scholar
  3. [3]
    Y. Bartal, J. Lin, and R. Uhrig, “Transients Identification in Nuclear Power Plants Using Probabilistic Neural Networks and the Problem of Knowledge Extrapolation,” 9th Power Plant Dynamics, Control & Testing Symposium, pp.49.01–49.08, Knoxville, TN, USA, May 24–26, 1995.Google Scholar
  4. [4]
    Z. Guo, R. E. Uhrig, “Accident Scenario Diagnostics with Neural Networks,” 8th Power Plant Dynamics, Control & Testing Symposium, pp.53.01–53. 11, Knoxville, TN, USA, May 1992.Google Scholar
  5. [5]
    S. W. Cheon, “Application of Neural Networks to a Connectionist Expert System for Transient Identification in Nuclear Power Plants,” Nuclear Technology, Vol. 102, pp. 177–191, May 1993.Google Scholar
  6. [6]
    T. Iijima, Application Study of Fuzzy Logic method for Plant-State Identification, HWR-432, OECD Halden Reactor Project, Dec. 1995.Google Scholar
  7. [7]
    J. Lin, Y. Bartal, and R. Uhrig, “Using Similarity Based Formulas and Genetic Algorithms to Predict the Severity of Nuclear Power Plant Transients,” 9th Power Plant Dynamics, Control & Testing Symposium, pp.53.01–53.09, Knoxville, TN, USA, May 24–26, 1995.Google Scholar
  8. [8]
    E. Jeong, K. Furuta, and S. Kondo, “Identification of Transient in Nuclear Power Plant Using Adaptive Template Matching with Neural Network,” Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, The Penn State Univ. USA, pp.243–250, May 6–9, 1996.Google Scholar
  9. [9]
    J. W. Hines, D. W. Miller, and B. K. Hajek, “A Hybrid Approach for Detecting and Isolating Faults in Nuclear Power Plant Interacting Systems,” Nuclear Technology, Vol. 115, pp. 342–358, Sep. 1996.Google Scholar
  10. [10]
    P. Smyth, “Tutorial Material; Machine Learning: Theory and Application,” The 3 rd World Congress on Expert Systems, Seoul, Korea, Feb. 5–9, 1996.Google Scholar
  11. [11]
    X. D. Huang, Y. Ariki, and M. A. Jack, Hidden Markov Models for Speech Recognition, Edinburgh University Press, Edinburgh, 1990.Google Scholar
  12. [12]
    Y. Bartal, J. Lin, and R. Uhrig, “Nuclear Power Plant Transient Diagnostics Using Artificial Neural Networks that Allow ”Don’t-Know“ Classifications,” Nuclear Technology, Vol. 110, pp. 436–449, Jun. 1995.Google Scholar
  13. [13]
    C. Couvreur, Environmental Sound Recognition: A Statistical Approach, Ph. D Thesis, Faculté Polytechnique de Mons, Belgium, June 1997.Google Scholar
  14. [14]
    L. R. Rabiner, “A Tutorial on Hidden Markov Models and Selected Application in Speech Recognition,” Proceedings of the IEEE, Vol. 77, No. 2, pp. 257–285, Feb. 1989.CrossRefGoogle Scholar
  15. [15]
    T. Kohonen, “The Self-Organizing Map,” Proceedings of the IEEE, Vol. 78, No. 9, pp. 1464–1480, Sep. 1990.CrossRefGoogle Scholar
  16. [16]
    K. C. Kwon, S. J. Song, W. M. Park, and S. P. Lyu, “The Real-time Functional Test Facility for Advanced Instrumentation and Control in Nuclear Power Plants,” IEEE Transactions on Nuclear Science, Vol. 46, No. 2, pp. 92–99, April 1999.CrossRefGoogle Scholar
  17. [17]
    E. Jeong, K. Furuta, and S. Kondo, “Identification of Transient in Nuclear Power Plant Using Neural Network with Implicit Time Measure,” Proceedings of the Topical Meeting on Computer-Based Human Support Systems, pp.467–474, Philadelphia, PA, USA, June 25–29, 1995.Google Scholar
  18. [18]
    T. Applebaum and B. Hanson, “Enhancing the Discrimination of Speaker Independent Hidden Markov Models with Corrective Training,” Proc. ICASSP-89, pp.302–305, Glasgow, Scotland, May 1989.Google Scholar
  19. [19]
    Y. Ohga and H. Seki, “Abnormal Event Identification in Nuclear Power Plants Using a Neural Network and Knowledge Processing,” Nuclear Technology, Vol.101, pp.159167, Feb. 1993.Google Scholar
  20. [20]
    A. Kundu and G. Chen, “An Integrated Hybrid Neural Network and Hidden Markov Model Classifier for Sonar Signal Classification,” ICASSP, pp. 3587–3590, 1995.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Kee-Choon Kwon
    • 1
  1. 1.Korea Atomic Energy Research InstituteDaejeonKorea

Personalised recommendations