Atomic Energy

, Volume 121, Issue 3, pp 173–178 | Cite as

Prediction of Oscillations of the Thermodynamic Parameters of the Cooling System of the IBR-2M Reactor Using Neural Nets

  • Yu. N. Pepelyshev
  • Ts. Tsogtsaikhan

The problem of predicting the oscillations of the main thermodynamic parameters of the core in the first loop of the sodium cooling system of IBR-2M reactor is examined. Attention is focused mainly on the prediction of the temperature and sodium flow at the entry into the core as well as the thermal power. It is shown that the prediction makes it possible to reduce by a factor of 3 the influence of slow oscillations of reactivity on the power and thereby reduce the operational requirements for the automatic power stabilization system. Neural-net prediction using nonlinear autoregression nets with feedback is proposed. The results agree with experiment to within ~5%.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    1 Yu. N. Pepelyshev, Ts. Tsogtsaikhan, and G. A. Ososkov, The Use of Cluster Analysis and Autoregression Neural Nets for Diagnostics of Noise in the IBR-2M Reactor, JINR Preprint R13-2015-47 (2015).Google Scholar
  2. 2.
    C. Bishop, Neural Networks for UK, Oxford University Press (1997).Google Scholar
  3. 3.
    C. Granger and P. Newbold, Forecasting Economic Time Series, Academic Press, San Diego (1986).MATHGoogle Scholar
  4. 4.
    Anil K. Jain, Jianchang Mao, and K. Mohiuddin, “Artificial neural networks: a tutorial,” IEEE Computer, 29, No. 3, 31–44 (1996)Google Scholar
  5. 5.
    J. Huang, M. Korolkiewicz, M. Agrawal, and J. Boland, “Forecasting solar radiation on an hourly time scale using a coupled autoregressive and dynamical systems (CARDS) model,” Solar Energy, 87, 136–149 (2013).ADSCrossRefGoogle Scholar
  6. 6.
    S. Haykin, Neural Networks: A Comprehensive Foundation, Prentice Hall, Upper Saddle River, New Jersey (1998).MATHGoogle Scholar
  7. 7.
    L. Ljung, System Identification: Theory for the User, Prentice Hall, Upper Saddle River, New Jersey (1998).CrossRefMATHGoogle Scholar
  8. 8.
    C. Lee Giles, S. Lawrence, and Ah Chung Tsoi, “Noisy time series prediction using recurrent neural networks,” Machine Learn., 44, 161–183 (2001).Google Scholar
  9. 9.
    K. Levenberg, “Method for the solution of certain problems in least squares,” Appl. Math., 2, 164–168 (1944).MathSciNetMATHGoogle Scholar
  10. 10.
    D. Marquardt, “An algorithm for least-squares estimation of nonlinear parameters,” Appl. Math., 11, 431–441 (1963).MathSciNetMATHGoogle Scholar
  11. 11.
    P. Narendra, “A separable median filter for image noise smoothing,” IEEE Trans. Pattern Analysis and Machine Intell., PAMI-3, No. 1, 20–29 (1981).ADSCrossRefGoogle Scholar
  12. 12.
    G. Arce, Nonlinear Signal Processing: A Statistical Approach, Wiley, New Jersey (2005).MATHGoogle Scholar
  13. 13.
    T. Huang, G. Yang, and G. Tang, “A fast two-dimensional median filtering algorithm,” IEEE Trans. Acoust., Speech, Signal Proces., 27, No. 1, 13–18 (1979).CrossRefGoogle Scholar
  14. 14.
    V. D. Anan’ev, A. V. Vinogradov, A. V. Dolgikh, et al., Power Start-Up of the Modernized IBR-2 (IBR-2M), Preprint JINR R13-2012-42 (2012).Google Scholar
  15. 15.
    V. D. Anan’ev, A. V. Vinogradov, A. V. Dolgikh, et al., Physical Startup of the Pulse Research Reactor IBR-2, JINR Report R13-2012-41 (2012).Google Scholar
  16. 16.
    Yu. N. Pepelyshev and Ts. Tsogtsaikhan, Effect of Sodium Core Cooling System Noise of the IBR-2M on Reactivity Fluctuations, JINR Report R13-2014-61 (2014).Google Scholar

Copyright information

© Springer Science+Business Media New York 2017

Authors and Affiliations

  • Yu. N. Pepelyshev
    • 1
  • Ts. Tsogtsaikhan
    • 1
  1. 1.Joint Institute for Nuclear Research (JINR)DubnaRussia

Personalised recommendations