Nuclear Engineering and Technology

  • 제54권2호
  • /
  • Pages.617-626
  • /
  • 2022
  • /
  • 1738-5733(pISSN)
  • /
  • 2234-358X(eISSN)
한국원자력학회 (Korean Nuclear Society)
권호 표지
DOI QR코드

DOI QR Code

Artificial neural network reconstructs core power distribution

  • Li, Wenhuai (China Nuclear Power Technology Research Institute Co., Ltd) ;
  • Ding, Peng (China Nuclear Power Technology Research Institute Co., Ltd) ;
  • Xia, Wenqing (China Nuclear Power Technology Research Institute Co., Ltd) ;
  • Chen, Shu (China Nuclear Power Technology Research Institute Co., Ltd) ;
  • Yu, Fengwan (China Nuclear Power Technology Research Institute Co., Ltd) ;
  • Duan, Chengjie (China Nuclear Power Technology Research Institute Co., Ltd) ;
  • Cui, Dawei (China Nuclear Power Technology Research Institute Co., Ltd) ;
  • Chen, Chen (China Nuclear Power Technology Research Institute Co., Ltd)
  • 투고 : 2021.03.10
  • 심사 : 2021.08.10
  • 발행 : 2022.02.25
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

To effectively monitor the variety of distributions of neutron flux, fuel power or temperatures in the reactor core, usually the ex-core and in-core neutron detectors are employed. The thermocouples for temperature measurement are installed in the coolant inlet or outlet of the respective fuel assemblies. It is necessary to reconstruct the measurement information of the whole reactor position. However, the reading of different types of detector in the core reflects different aspects of the 3D power distribution. The feasibility of reconstruction the core three-dimension power distribution by using different combinations of in-core, ex-core and thermocouples detectors is analyzed in this paper to synthesize the useful information of various detectors. A comparison of multilayer perceptron (MLP) network and radial basis function (RBF) network is performed. RBF results are more extreme precision but also more sensitivity to detector failure and uncertainty, compare to MLP networks. This is because that localized neural network could offer conservative regression in RBF. Adding random disturbance in training dataset is helpful to reduce the influence of detector failure and uncertainty. Some convolution neural networks seem to be helpful to get more accurate results by use more spatial layout information, though relative researches are still under way.

키워드

과제정보

The work described in this paper was fully supported by the grant from the Natural Science Foundation of Guangdong Province (No. 2020A1515110753 and 2019A1515110261).

참고문헌

  1. W. Li, C. Wang, The Development of HOLLY Code and Single-Point Ex-Core Detectors Calibration Method, Springer, Singapore, City, 2017.
  2. W. Li, P. Ding, C. Duan, R. Qiu, J. Lin, X. Shi, Comparison of spatial interpolation approaches for in-core power distribution reconstruction, Nucl. Eng. Des. 337 (2018) 66-73. https://doi.org/10.1016/j.nucengdes.2018.06.016
  3. W. Li, P. Ding, C. Duan, D. Cui, R. Qiu, X. Shi, J. Lin, Comparison of three methodologies for optimization of the layout of in-core detectors with a specific number of detectors, Ann. Nucl. Energy 126 (2019) 359-366. https://doi.org/10.1016/j.anucene.2018.11.039
  4. K. Fan, F. Li, J. Guo, X. Zhou, Use readings of thermocouples to reconstruct the power distribution of HTR-PM, Ann. Nucl. Energy 142 (2020) 107414. https://doi.org/10.1016/j.anucene.2020.107414
  5. H. Xia, B. Li, J. Liu, Research on intelligent monitor for 3D power distribution of reactor core, Ann. Nucl. Energy 73 (2014) 446-454. https://doi.org/10.1016/j.anucene.2014.07.033
  6. X. Peng, Q. Li, K. Wang, Core axial power shape reconstruction based on radial basis function neural network, 2014/11/01/, Ann. Nucl. Energy 73 (2014) 339-344. https://doi.org/10.1016/j.anucene.2014.06.055
  7. C. Pei, G. Quan, S. Jing, L. Pengcheng, W. Fang, H. Liqin, W. Yican, An artificial neural network based neutron field reconstruction method for reactor, 2020/04/01/, Ann. Nucl. Energy 138 (2020), 107195. https://doi.org/10.1016/j.anucene.2019.107195
  8. W. Li, X. Zhang, Z. Dang, Development and preliminary verification of the PWR on-line core monitoring software system, SOPHORA (2015).
  9. H. Lu, K. Mo, W. Li, N. Bai, J. Li, Development and Preliminary Verification of the 3D Core Neutronic Code, COCO, 2012.
  10. W.A. Boyd, R.W. Miller, The BEACON On-Line Core Monitoring System: Functional Upgrades and Applications, City, 1996.
  11. A. DiGiovine, A. Noel, GARDEL-PWR: Studsvik's Online Monitoring and Reactivity Management System. Proceedings of Advances in Nuclear Fuel Management III, October 2003, Hilton Head Island, SC, 2003.
  12. Y. Chao, Y. Shatilla, Conformal mapping and hexagonal nodal methods-II: implementation in the ANC-H code, Nucl. Sci. Eng. 121 (2) (1995) 210-225. https://doi.org/10.13182/nse95-a28559
  13. W. Li, P. Ding, X. Zhang, C. Duan, R. Qiu, J. Lin, X. Shi, Ensemble learning methodologies to improve core power distribution abnormal detectability, Nucl. Eng. Des. 351 (2019) 160-166. https://doi.org/10.1016/j.nucengdes.2019.06.004
  14. K.G. Sheela, S.N. Deepa, Review on methods to fix number of hidden neurons in neural networks, Math. Probl Eng. 2013 (2013) 1-11.
  15. D. Tian, J. Deng, G. Vinod, T.V. Santhosh, H. Tawfik, A constraint-based genetic algorithm for optimizing neural network architectures for detection of loss of coolant accidents of nuclear power plants, 2018/12/17/, Neurocomputing 322 (2018) 102-119. https://doi.org/10.1016/j.neucom.2018.09.014
  16. K. Moshkbar-Bakhshayesh, Investigating the performance of the supervised learning algorithms for estimating NPPs parameters in combination with the different feature selection techniques, Ann. Nucl. Energy 158 (2021) 108299. https://doi.org/10.1016/j.anucene.2021.108299
  17. H. Xia, B. Li, J. Liu, Research on 3D power distribution of PWR reactor core based on RBF neural network, Atomic Energy Sci. Technol. 48 (4) (2014) 698-702.
  18. A. Pirouzmand, M.K. Dehdashti, VVER-1000 Reactor Core Monitoring Using Ex-Core Neutron Detect Ors and Neural Networks, City, 2014.
  19. A. Durrant, G. Leontidis, S. Kollias, 3D Convolutional and Recurrent Neural Networks for Reactor Perturbation Unfolding and Anomaly Detection, EPJ Nuclear Sciences & Technologies, 2019.
  20. F.D.S. Ribeiro, F. Caliva, D. Chionis, A. Dokhane, A. Mylonakis, C. Demaziere, G. Leontidis, S. Kollias, Towards a Deep Unified Framework for Nuclear Reactor Perturbation Analysis, City, IEEE, 2018.
  21. C. Cao, Q. Gan, J. Song, P. Long, B. Wu, Y. Wu, A two-step neutron spectrum unfolding method for fission reactors based on artificial neural network, 2020/05/01/, Ann. Nucl. Energy 139 (2020), 107219. https://doi.org/10.1016/j.anucene.2019.107219
  22. A. Pirouzmand, M. Kazem Dehdashti, Estimation of relative power distribution and power peaking factor in a VVER-1000 reactor core using artificial neural networks, 2015/11/01/, Prog. Nucl. Energy 85 (2015) 17-27. https://doi.org/10.1016/j.pnucene.2015.06.001
  23. U. Oparaji, R.J. Sheu, M. Bankhead, J. Austin, E. Patelli, Robust artificial neural network for reliability and sensitivity analyses of complex non-linear systems, Neural Network. 96 (Dec) (2017) 80-90. https://doi.org/10.1016/j.neunet.2017.09.003
  24. J. Sadeghi, M. de Angelis, E. Patelli, Efficient training of interval Neural Networks for imprecise training data, Neural Network. 118 (Oct) (2019) 338-351. https://doi.org/10.1016/j.neunet.2019.07.005
  25. S. Tolo, X. Tian, N. Bausch, V. Becerra, T.V. Santhosh, G. Vinod, E. Patelli, Robust on-line diagnosis tool for the early accident detection in nuclear power plants, Reliab. Eng. Syst. Saf. 186 (2019) 110-119. https://doi.org/10.1016/j.ress.2019.02.015
  26. N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, R. Dropout Salakhutdinov, A simple way to prevent neural networks from overfitting, 15, 1, J. Mach. Learn. Res. (2014) 1929-1958.
  27. M.J. Orr, Introduction to Radial Basis Function Networks, Technical Report, Center for Cognitive Science, University of Edinburgh, City, 1996.
  28. J.A. Hartigan, M.A. Wong, Algorithm AS 136: a k-means clustering algorithm, 1, J. R. Stat. Soc. C 28 (1979) 100-108.
  29. J. Bergstra, R. Bardenet, Y. Bengio, B. Kegl, Algorithms for Hyper-Parameter Optimization, City, 2011.
  30. M. Pecchia, A. Vasiliev, H. Ferroukhi, A. Pautz, A methodology for evaluating weighting functions using MCNP and its application to PWR ex-core analyses, Ann. Nucl. Energy 105 (2017) 121-132. https://doi.org/10.1016/j.anucene.2017.03.008
  31. K. Moshkbar-Bakhshayesh, M.B. Ghofrani, Development of a robust identifier for NPPs transients combining ARIMA model and EBP algorithm, IEEE Trans. Nucl. Sci. 61 (4) (2014) 2383-2391. https://doi.org/10.1109/TNS.2014.2329055
  32. K. Moshkbar-Bakhshayesh, Identification of the appropriate architecture of multilayer feed-forward neural network for estimation of NPPs parameters using the GA in combination with the LM and the BR learning algorithms, Ann. Nucl. Energy 156 (2021) 108222. https://doi.org/10.1016/j.anucene.2021.108222