Closed Loop Identification of Nuclear Steam Generator Water Level Using ESN Network Tuned by Genetic Algorithm

  • Glauco Martins
  • Marley VellascoEmail author
  • Roberto Schirru
  • Pedro Vellasco
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 517)


The behavior of Steam Generators Water Level from nuclear power plants is highly nonlinear. Its parameters change when facing different operational conditions. Simulating this system can be very useful to train people involved in the real plant operation. However, in order to simulate this system the identification process must be performed. Echo State Networks are a special type of Recurrent Neural Networks that are well suited to nonlinear dynamic systems identification, with the advantage of having a simpler and faster training algorithm than conventional Recurrent Neural Networks. Echo State Networks have an additional advantage over other conventional methods of dynamic systems identification, since it is not necessary to specify the model’s structure. However, some other parameters of the Echo State Network must be tuned in order to attain its best performance. Therefore, this study proposes the use of an Echo State Network, automatically tuned by Genetic Algorithms, to a closed loop identification of a nuclear steam generator water level process. The results obtained demonstrate that the proposed Echo State Networks can correctly model dynamical nonlinear system in a large range of operation.


Recurrent Neural Networks Echo State Networks Nonlinear identification systems Closed loop identification Genetic algorithm Steam generator water level Nuclear power plant 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Aguirre, L.: Introdução À Identificação de Sistemas: Técnicas Lineares e Não-Lineares Aplicadas a Sistemas Reais. 2a. UFMG (2004). ISBN 8570415842 (in Portuguese)Google Scholar
  2. 2.
    Jervis, M.: Models and Simulation in Nuclear Power Station Design and Operation. Advances in Nuclear Science and Technology 17, 77–115 (1986)CrossRefGoogle Scholar
  3. 3.
    Digital Instrumentation and Control Design Guide. EPRI, Product ID: 3002002989 (2014)Google Scholar
  4. 4.
    Aguirre, L.: Enciclopédia de Automática-Controle e Automação, vol. 3. 1a. Edgar Blucher (2007). ISBN 8521204108 (in Portuguese)Google Scholar
  5. 5.
    Narendra, K., Parthasarathy, K.: Identification and control of dynamical systems using neural networks. IEEE Trans. on Neural Networks 1(1), 4–27 (1990)CrossRefGoogle Scholar
  6. 6.
    Gang, Z., Xin, C., Weicheng, Y., Wei, P.: Identification of dynamics for nuclear steam generator water level process using RBF neural networks. In: 8th ICEMI, pp. 3–379 (2007)Google Scholar
  7. 7.
    Haykin S.: Neural Networks: a Comprehensive Foudantion, 2nd edn. Prentice Hall (1998)Google Scholar
  8. 8.
    Jaeger, H.: A tutorial on training recurrent n. networks, covering bppt, rtrl, and the echo state network approach. Tech. report, Fraunhofer Inst. for Aut. Intelligent Systems (2013)Google Scholar
  9. 9.
    Jaeger, H.: The “echo state” approach to analyzing and training recurrent neural networks. Technical report, Fraunhofer Institute for Autonomous Intelligent Systems (2010)Google Scholar
  10. 10.
    Irving, E., Miossec, C., Tassart, J.: Toward efficient full automatic operation of the PWR steam generator with water level adaptive control. In: Proc. Int. Conf. Boiler Dynamics Contr. Nuclear Power Stations, London, U.K., pp. 309–329 (1980)Google Scholar
  11. 11.
    Ablay, G.: Steam generator level control with an observer-based algebraic approach. In.: 8th Int. Conf. in Electrical and Electronics Engineering (ELECO), pp. 137–141 (2013)Google Scholar
  12. 12.
    Ahmed, Z.: Data-driven controller of nuclear steam generator by set membership function approximation. Annual of Nuclear Energy 37, 512–521 (2010)CrossRefGoogle Scholar
  13. 13.
    Mousa, H., Koutb, M., El-Araby, M., Ali, E.: Design of optimal fuzzy controller for water level of U-Tube steam generator in nuclear power station. J. A. Science, 629–636 (2011)Google Scholar
  14. 14.
    Zhao, F., Ou, J., Du, W.: Simulation Modeling of Nuclear Steam Generator Water Level Process-a Case Study. ISA Transactions 39, 143–151 (2000)CrossRefGoogle Scholar
  15. 15.
    Billings, S.: Nonlinear System Identification: NARMAX, Methods in the Time, Frequency, and Spatio-Temporal Domains. Wiley (2013)Google Scholar
  16. 16.
    Billings, S.A.: Identif. of nonlinear systems – a survey. IEE proc. Pt. D 127(6), 272–285Google Scholar
  17. 17.
    Ferreira, A., Ludermir, T.: Comparing evolutionary methods for reservoir computing pre-training. In: 2011 Proc. Int. Joint Conf. on Neural Networks (JCNN), pp. 283–290Google Scholar
  18. 18.
    Goldberg, D.: Genetic Algorithms in Search, Optimization and Machine Learning. Addison Wesley (1989)Google Scholar
  19. 19.
    Jaeger, H.: Simple toolbox for ESNs (2009).
  20. 20.

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Glauco Martins
    • 1
  • Marley Vellasco
    • 1
    Email author
  • Roberto Schirru
    • 2
  • Pedro Vellasco
    • 3
  1. 1.Pontifical Catholic University of Rio de Janeiro, PUC-RioRio de JaneiroBrazil
  2. 2.Federal University of Rio de Janeiro, Post-Graduation Nuclear Engineering ProgramRio de JaneiroBrazil
  3. 3.State University of Rio de Janeiro, UERJRio de JaneiroBrazil

Personalised recommendations