Estimation of Neutronic Performance of a High Power Density Hybrid Reactor by Multilayer Perceptron Neural Networks

Abstract

Artificial neural networks (ANNs) have recently been utilized in the nuclear technology applications since they are fast, precise and flexible vehicles to modeling, simulation and optimization. This paper presents a new approach based on multilayer perceptron neural networks (MLPNNs) for the estimation of some important neutronic parameters (net 239Pu production, tritium breeding ratio, cumulative fissile fuel enrichment, and fission rate) of a high power density fusion–fission (hybrid) reactor using light water reactor (LWR) spent fuel. A comparison of the results obtained by the MLPNNs and those found by using the code (Scale 4.3) was carried out. The results pointed out that the MLPNNs trained with least mean squares (LMS) algorithm could provide an accurate computation of the main neutronic parameters for the high power density reactor.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

References

  1. 1.

    L. Fausett, Fundamentals of Neural Networks Architectures, Algorithms, and Applications (Prentice Hall, Inc., Englewood Cliffs, 1994)

    MATH  Google Scholar 

  2. 2.

    B.B. Chaudhuri, U. Bhattacharya, Efficient training and improved performance of multilayer perceptron in pattern classification. Neurocomputing 34, 11–27 (2000)

    MATH  Article  Google Scholar 

  3. 3.

    S. Haykin, Neural Networks: A Comprehensive Foundation (Macmillan, New York, 1994)

    MATH  Google Scholar 

  4. 4.

    I.A. Basheer, M. Hajmeer, Artificial neural networks: fundamentals, computing, design, and application. J. Microbiol. Methods 43, 3–31 (2000)

    Article  Google Scholar 

  5. 5.

    R.E. Uhrig, L.H. Tsoukalas, Soft computing technologies in nuclear engineering applications. Prog. Nucl. Energy 34(1), 13–75 (1999)

    Article  Google Scholar 

  6. 6.

    J. Reifman, Survey of artificial intelligence methods for detection and identification of component faults in nuclear power plants. Nucl. Technol. 119, 76–97 (1997)

    Google Scholar 

  7. 7.

    K.S. Narendra, K. Parthasarathy, Identification and control of dynamical systems using neural networks. IEEE Trans. Neural Netw. 1(1), 4–27 (1990)

    Article  Google Scholar 

  8. 8.

    M. Boroushaki, M.B. Ghofrani, C. Lucas, Identification of a nuclear reactor core (VVER) using recurrent neural networks. Ann. Nucl. Energy 29, 1225–1240 (2002)

    Article  Google Scholar 

  9. 9.

    Y.J. Choi, H.K. Kim, W.P. Baek, S.H. Chang, Hybrid accident simulation methodology using artificial neural networks for nuclear power plants. Inf. Sci. 160, 207–224 (2004)

    Article  ADS  Google Scholar 

  10. 10.

    E.B. Bartlett, R.E. Uhrig, Nuclear power plant status diagnostics using artificial neural networks. Nucl. Technol. 97, 272–281 (1992)

    Google Scholar 

  11. 11.

    K. Kim, T.L. Aljundi, E.B. Bartlett, Confirmation of artificial neural networks: nuclear power plant fault diagnostics. Trans. Am. Nucl. Soc. 66, 112 (1992)

    Google Scholar 

  12. 12.

    P.F. Fantoni, A. Mazzola, Multiple-failure signal validation in nuclear power plants using artificial neural networks. Nucl. Technol. 113, 368–374 (1996)

    Google Scholar 

  13. 13.

    P.F. Fantoni, A. Mazzola, A pattern recognition-artificial neural networks based model for signal validation in nuclear power plants. Ann. Nucl. Energy 23(13), 1069–1076 (1996)

    Article  Google Scholar 

  14. 14.

    R. Kozma, K. Nabeshima, Studies on the detection of incipient coolant boiling in nuclear reactors using artificial neural networks. Ann. Nucl. Energy 22(7), 483–496 (1995)

    Article  Google Scholar 

  15. 15.

    Y. Ogha, H. Seki, Using a neural network for abnormal event identification in BWRs. Trans. Am. Nucl. Soc. 63, 110–111 (1991)

    Google Scholar 

  16. 16.

    R. Kozma, S. Sato, M. Sakuma, M. Kitamura, T. Sugiyama, Generalization of knowledge acquired by a reactor core monitoring system based on a neuro-fuzzy algorithm. Prog. Nucl. Energy 29(3–4), 203–214 (1995)

    Article  Google Scholar 

  17. 17.

    J. Thibault, B.P.A. Grandjean, A neural network methodology for heat transfer data analysis. Int. J. Heat Mass Transf. 34(8), 2063–2070 (1991)

    Article  ADS  Google Scholar 

  18. 18.

    E.D. Übeyli, M. Übeyli, Investigating neutronic parameters of a thorium fusion breeder with recurrent neural networks. J. Fusion Energy 26(4), 323–330 (2007)

    Article  Google Scholar 

  19. 19.

    S. Şahin, M. Übeyli, LWR spent fuel transmutation in a high power density fusion reactor. Ann. Nucl. Energy 31, 871–890 (2004)

    Article  Google Scholar 

  20. 20.

    M. Übeyli, On the tritium breeding capability of Flibe, Flinabe and Li20Sn80 in a fusion-fission (hybrid) reactor. J. Fusion Energy 22, 51–57 (2003)

    Article  Google Scholar 

  21. 21.

    M. Übeyli, Radiation damage study on various structural refractory alloys of a multi-purpose reactor. J. Fusion Energy 22(4), 251–257 (2004)

    Article  ADS  Google Scholar 

  22. 22.

    M. Übeyli, A. Acır, Utilization of thorium in a high power density hybrid reactor with innovative coolants. Energy Conversion Manage. 48, 576–582 (2007)

    Article  Google Scholar 

  23. 23.

    S. Şahin, H. Yapıcı, Neutronic analysis of a thorium fusion breeder with enhanced protection against nuclear weapon proliferation. Ann. Nucl. Energy 26, 13–27 (1999)

    Article  Google Scholar 

  24. 24.

    S. Şahin, T.A. Al-Kusayer, M.A. Raoof, Preliminary design studies of a cylindrical experimental hybrid blanket with deuterium-tritium driver. Fusion Technol. 10, 84–99 (1986)

    Google Scholar 

  25. 25.

    S. Şahin, H. Yapıcı, E. Baltacıoğlu, T.A. Al-Kusayer, A hybrid reactor design concept driven by cold (D,T) fusion neutrons and fueled with metallic thorium. Int. J. Energy Environ. Econ. 1, 167–173 (1991)

    Google Scholar 

  26. 26.

    H. Yapıcı, N. Şahin, M. Bayrak, Investigation of neutronic potential of a moderated (D-T) fusion driven hybrid reactor fueled with thorium to breed fissile fuel for LWRs. Energy Conversion Manage. 41, 435–447 (2000)

    Article  Google Scholar 

  27. 27.

    N.M. Greene, L.M. Petrie, XSDRNPM, A One-Dimensional Discrete-Ordinates Code For Transport Analysis, NUREG/CR-0200, Revision 5, 2, Section F3, ORNL/NUREG/CSD-2/V2/R5, Oak Ridge National Laboratory (1997)

  28. 28.

    W.C. Jordan, S.M. Bowman, Scale Cross-Section Libraries, NUREG/CR-0200, Revision 5, 3, section M4, ORNL/NUREG/CSD-2/V3/R5, Oak Ridge National Laboratory (1997)

  29. 29.

    N.M. Greene, BONAMI, Resonance Self-Shielding by the Bondarenko Method, NUREG/CR-0200, Revision 5, 2, section F1, ORNL/NUREG/CSD-2/V2/R5, Oak Ridge National Laboratory (1997)

  30. 30.

    N.M. Greene, L.M. Petrie, R.M. Westfall, NITAWL-II, Scale System Module For Performing Resonance Shielding and Working Library Production, NUREG/CR-0200, Revision 5, 2, Section F2, ORNL/NUREG/CSD-2/V2/R5, Oak Ridge National Laboratory (1997)

  31. 31.

    N.F. Landers, L.M. Petrie, CSAS, Control Module For Enhanced Criticality Safety Analysis Sequences, NUREG/CR-0200, Revision 5, 1, Section C4, ORNL/NUREG/CSD-2/V1/R5, Oak Ridge National Laboratory (1997)

  32. 32.

    X.-H. Yu, G.-A. Chen, Efficient backpropagation learning using optimal learning rate and momentum. Neural Netw. 10(3), 517–527 (1997)

    Article  MathSciNet  Google Scholar 

  33. 33.

    D.P. Mandic, J.A. Chambers, Towards the optimal learning rate for backpropagation. Neural Process. Lett. 11, 1–5 (2000)

    Article  Google Scholar 

  34. 34.

    J.Y.F. Yam, T.W.S. Chow, Extended least squares based algorithm for training feedforward networks. IEEE Trans. Neural Netw. 8(3), 806–810 (1997)

    Article  Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Mustafa Übeyli.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Übeyli, M., Übeyli, E.D. Estimation of Neutronic Performance of a High Power Density Hybrid Reactor by Multilayer Perceptron Neural Networks. J Fusion Energ 27, 278–284 (2008). https://doi.org/10.1007/s10894-008-9135-4

Download citation

Keywords

  • Neutronic parameters
  • Hybrid reactor
  • Multilayer perceptron neural networks (MLPNNs)
  • Least mean squares (LMS) algorithm