Nuclear Engineering and Technology

  • 제53권10호
  • /
  • Pages.3275-3285
  • /
  • 2021
  • /
  • 1738-5733(pISSN)
  • /
  • 2234-358X(eISSN)
한국원자력학회 (Korean Nuclear Society)
권호 표지
DOI QR코드

DOI QR Code

Artificial neural network for predicting nuclear power plant dynamic behaviors

  • El-Sefy, M. (Department of Civil Engineering, NSERC-CREATE Program on Canadian Nuclear Energy Infrastructure Resilience Under Systemic Risk, McMaster University) ;
  • Yosri, A. (Department of Civil Engineering, Institute for Multi-hazard Systemic Risk Studies (INTERFACE), McMaster University) ;
  • El-Dakhakhni, W. (Department of Civil Engineering, and Director, NSERC-CaNRisk-CREATE Program and teh INTERFACE Institute, McMaster University) ;
  • Nagasaki, S. (Department of Engineering Physics, McMaster University) ;
  • Wiebe, L. (Department of Civil Engineering, NSERC-CREATE Program on Canadian Nuclear Energy Infrastructure Resilience Under Systemic Risk, McMaster University)
  • 투고 : 2020.11.14
  • 심사 : 2021.05.04
  • 발행 : 2021.10.25
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

A Nuclear Power Plant (NPP) is a complex dynamic system-of-systems with highly nonlinear behaviors. In order to control the plant operation under both normal and abnormal conditions, the different systems in NPPs (e.g., the reactor core components, primary and secondary coolant systems) are usually monitored continuously, resulting in very large amounts of data. This situation makes it possible to integrate relevant qualitative and quantitative knowledge with artificial intelligence techniques to provide faster and more accurate behavior predictions, leading to more rapid decisions, based on actual NPP operation data. Data-driven models (DDM) rely on artificial intelligence to learn autonomously based on patterns in data, and they represent alternatives to physics-based models that typically require significant computational resources and might not fully represent the actual operation conditions of an NPP. In this study, a feed-forward backpropagation artificial neural network (ANN) model was trained to simulate the interaction between the reactor core and the primary and secondary coolant systems in a pressurized water reactor. The transients used for model training included perturbations in reactivity, steam valve coefficient, reactor core inlet temperature, and steam generator inlet temperature. Uncertainties of the plant physical parameters and operating conditions were also incorporated in these transients. Eight training functions were adopted during the training stage to develop the most efficient network. The developed ANN model predictions were subsequently tested successfully considering different new transients. Overall, through prompt prediction of NPP behavior under different transients, the study aims at demonstrating the potential of artificial intelligence to empower rapid emergency response planning and risk mitigation strategies.

키워드

과제정보

The financial support for the study was provided through the Canadian Nuclear Energy Infrastructure Resilience under Seismic Systemic Risk (CaNRisk) - Collaborative Research and Training Experience (CREATE) program of the Natural Science and Engineering Research Council (NSERC) of Canada. Additional support from the INTERFACE Institute and the INViSiONLab is also acknowledged.

참고문헌

  1. IAEA, Accident Monitoring Systems for Nuclear Power Plants, vol. 16, IAEA Nuclear Energy series NP-T-3, 2015.
  2. J.H. Min, D. Kim, C. Park, Demonstration of the validity of the early warning in online monitoring system for nuclear power plants, Nucl. Eng. Des. 349 (2019) 56-62, https://doi.org/10.1016/j.nucengdes.2019.04.028.
  3. N. Tamimi, S. Samani, M. Minaei, F. Harirchi, An Artificial Intelligence Decision Support System for Unconventional Field Development Design, 2019, https://doi.org/10.15530/urtec-2019-249.
  4. I.S. Korovin, I.A. Kalyaev, Modern decision support systems in oil industry: types, approaches and applications, in: Int. Conf. Test, Meas. Comput. Method, 2015, pp. 141-144.
  5. S. Ahmad, S.P. Simonovic, An intelligent decision support system for management of floods, Water Resour. Manag. (2006) 391-410, https://doi.org/10.1007/s11269-006-0326-3.
  6. F.G. Filip, Decision support and control for large-scale complex systems, Annu. Rev. Contr. 32 (2008) 61-70, https://doi.org/10.1016/j.arcontrol.2008.03.002.
  7. G. Phillips-Wren, Intelligent Decision Support Systems, Wiley-Blackwell, Hoboken, NJ, USA, 2013, https://doi.org/10.1002/9781118522516.ch2.
  8. M. Ratz, A.P. Javadi, M. Baranski, K. Finkbeiner, D. Muller, Automated data-driven modeling of building energy systems via machine learning algorithms, Energy Build. 202 (2019), 109384, https://doi.org/10.1016/j.enbuild.2019.109384.
  9. H. Bao, N.T. Dinh, J.W. Lane, R.W. Youngblood, A data-driven framework for error estimation and mesh-model optimization in system-level thermal-hydraulic simulation, Nucl. Eng. Des. 349 (2019) 27-45, https://doi.org/10.1016/j.nucengdes.2019.04.023.
  10. D. Solomatine, A. Ostfeld, Data-driven modelling: some past experiences and new approaches approaches, J. Hydroinf. 10 (2008), https://doi.org/10.2166/hydro.2008.015.
  11. T.M. Mitchell, Machine Learning, McGraw-Hill, New York, 1997.
  12. F.J. Montans, F. Chinesta, R. Gomez-Bombarelli, J.N. Kutz, Data-driven modeling and learning in science and engineering, Compt. Rendus Mec. 347 (2019) 845-855, https://doi.org/10.1016/j.crme.2019.11.009.
  13. K.R. Holdaway, Harness Oil and Gas Big Data with Analytics: Optimize Exploration and Production with Data-Driven Models, John Wiley and Sons, Hoboken, New Jersey., 2014.
  14. A. Burchard-levine, S. Liu, F. Vince, M. Li, A. Ostfeld, A hybrid evolutionary data driven model for river water quality early warning, J. Environ. Manag. 143 (2014) 8-16, https://doi.org/10.1016/j.jenvman.2014.04.017.
  15. J. Zhang, F. Wang, K. Wang, W. Lin, X. Xu, C. Chen, Data-driven intelligent transportation Systems : a survey, IEEE Trans. Intell. Transport. Syst. 12 (2011) 1624-1639, https://doi.org/10.1109/TITS.2011.2158001.
  16. N.P. Oxtoby, A.L. Young, D.M. Cash, T.L.S. Benzinger, A.M. Fagan, J.C. Morris, R.J. Bateman, N.C. Fox, J.M. Schott, D.C. Alexander, Data-driven models of dominantly-inherited Alzheimer's disease progression, Brain (2018) 1-16, https://doi.org/10.1093/brain/awy050.
  17. M. Gomez, A. Tokuhiro, K. Welter, Q. Wu, Nuclear energy system's behavior and decision making using machine learning, Nucl. Eng. Des. 324 (2017) 27-34, https://doi.org/10.1016/j.nucengdes.2017.08.020.
  18. T. Foshch, F. Portela, J. Machado, M. Maksimov, Regression models of the nuclear power unit VVER-1000 using data mining techniques, Procedia Comput. Sci. 100 (2016) 253-262, https://doi.org/10.1016/j.procs.2016.09.151.
  19. L. Fahrmeir, T. Kneib, S. Lang, B. Marx, Regression Models, Springer, Berlin, Heidelberg, 2013, https://doi.org/10.1007/978-3-642-34333-9_2.
  20. S.R. Patra, R. Jehadeesan, S. Rajeswari, S.A. Satyamurthy, Artificial neural network model for intermediate heat exchanger of nuclear reactor, Int. J. Comput. Appl. 1 (2010).
  21. D. Maljovec, S. Liu, B. Wang, D. Mandelli, P. Bremer, V. Pascucci, C. Smith, Analyzing simulation-based PRA data through traditional and topological clustering : a BWR station blackout case study, Reliab. Eng. Syst. Saf. 145 (2016) 262-276, https://doi.org/10.1016/j.ress.2015.07.001.
  22. O.I. Abiodun, A. Jantan, A.E. Omolara, K.V. Dada, N.A. Mohamed, H. Arshad, State-of-the-art in artificial neural network applications: a survey, Heliyon (2018), e00938, https://doi.org/10.1016/j.heliyon.2018.
  23. H.H. Kang, M. Kaya, S. Hajimirza, A data driven artificial neural network model for predicting radiative properties of metallic packed beds, Quant. Spectrosc. Radiat. Transf. (2019) 66-72, https://doi.org/10.1016/j.jqsrt.2019.01.013.
  24. J. Li, J. Cheng, J. Shi, F. Huang, Brief introduction of back propagation (BP) neural network algorithm and its improvement, Adv. Comput. Sci. Inf. Eng. 169 (2012), https://doi.org/10.1007/978-3-642-30223-7_87.
  25. K. O'Shea, R. Nash, An introduction to convolutional neural networks, 2015. https://arxiv.org/abs/1511.08458.
  26. T. Mikolov, M. Karafiat, L. Burget, J. Cernock, S. Khudanpur, Recurrent neural network based language model, in: Interspeech, 2010.
  27. Y. Singh, A.S. Chauhan, Neural networks in data mining, J. Theor. Appl. Inf. Technol. 5 (2009) 36-42.
  28. N.M. Nawi, R.S. Ransing, M.R. Ransing, An improved conjugate gradient based learning algorithm for back propagation neural networks, Int. J. Comput. Intell. (2008) 46-55.
  29. M.F. Moller, A scaled conjugate gradient algorithm for fast supervised learning, Neural Network. 6 (1993) 525-533. https://doi.org/10.1016/S0893-6080(05)80056-5
  30. M. Moller, Efficient Training of Feed-Forward Neural Networks, Aarhus University, Computer Science Department, Ph.D. Thesis, 1997.
  31. R. Battiti, First- and second-order methods for learning: between steepest descent and Newton's method, Neural Comput. 4 (1992) 141-166. https://doi.org/10.1162/neco.1992.4.2.141
  32. M.T. Hagan, M.B. Menhaj, Training feedforward networks with the marquardt algorithm, IEEE Trans. Neural Network. 5 (1994) 2-6.
  33. B. Sharma, P.K. Venugopalan, Comparison of neural network training functions for hematoma classification in brain CT images, IOSR J. Comput. Eng. 16 (2014) 31-35.
  34. H. Mustafidah, S. Hartati, R. Wardoyo, A. Harjoko, Selection of most appropriate backpropagation training algorithm in data pattern recognition, Int. J. Comput. Trends Technol. 14 (2014) 92-95. https://doi.org/10.14445/22312803/IJCTT-V14P120
  35. H. Sug, The effect of training set size for the performance of neural networks of classification, WSEAS Trans. Comput. 9 (2010) 1297-1306.
  36. S. Lawrence, C.L. Giles, A.C. Tsoi, Lessons in neural network training: overfitting may be harder than expected, in: Proc. Fourteenth Natl. Conf. Artif. Intell. AAAI-97, AAAI Press, Menlo Park, California, 1997, pp. 540-545.
  37. R.E. Uhrig, Use of neural networks in nuclear power plants, ISA Trans. 32(1993) 139-145. https://doi.org/10.1016/0019-0578(93)90036-V
  38. Z. Guo, R.E. Uhrig, Use of artificial neural networks to analyze nuclear power plant performance, Nucl. Technol. 5450 (2017), https://doi.org/10.13182/NT92-A34701.
  39. A. Varuttamaseni, Bayesian Network Representing System Dynamics in Risk Analysis of Nuclear Systems, Ph.D. Thesis, University of Michigan, 2011.
  40. M. Knochenhauer, J.E. Holmberg, Guidance for the Definition and Application of Probabilistic Safety Criteria, Swedish Radiation Safety Authority, 2011.
  41. United States Nuclear Regulatory Commission, Acceptance criteria for emergency core cooling systems for light-water nuclear power reactors, 2017. https://www.nrc.gov/reading-rm/doc-collections/cfr/part050/part050-0046.html.
  42. M. El-Sefy, M. Ezzeldin, W. El-Dakhakhni, L. Wiebe, S. Nagasaki, System dynamics simulation of the thermal dynamic processes in nuclear power plants, Nucl. Eng. Technol. 51 (2019) 1540-1553, https://doi.org/10.1016/j.net.2019.04.017.
  43. J.G. Thakkar, Correlation of Theory and Experiment for the Dynamics of a Pressurized Water Reactor, University of Tennessee, 1975. https://trace.tennessee.edu/utk_gradthes/2696%0A%0A.
  44. T.W. Kerlin, E.M. Katz, J.G. Thakkar, J.E. Strange, Theoretical and experimental dynamic analysis of the HB Robinson nuclear plant, Nucl. Technol. 30 (1976) 299-316, https://doi.org/10.13182/NT76-A31645.
  45. M. Ali, Lumped Parameter, State Variable Dynamic Models for U-Tube Recirculation Type Nuclear Steam Generators, Ph.D. Thesis, University of Tennessee, 1976, https://trace.tennessee.edu/utk_graddiss/2548%0A%0A.
  46. S. Arda, K.E. Holbert, J. Undrill, Development of a linearized model of a pressurized water reactor generating station for power system dynamic simulations, in: 45th North Am. Power Symp, NAPS, 2013, https://doi.org/10.1109/NAPS.2013.6666832, 2013.
  47. S. Arda, Implementing a Nuclear Power Plant Model for Evaluating Load-Following Capability on a Small Grid, MASc Thesis, Arizona State University, 2013.
  48. B. Puchalski, T.A. Rutkowski, K. Duzinkiewicz, Nodal models of Pressurized Water Reactor core for control purposes - a comparison study, Nucl. Eng. Des. 322 (2017) 444-463, https://doi.org/10.1016/j.nucengdes.2017.07.005.
  49. A.I. Sanchez, J.F. Villanueva, S. Carlos, S. Martorell, Uncertainty analysis of a large break loss of coolant accident in a pressurized water reactor using nonparametric methods, Reliab. Eng. Syst. Saf. 174 (2018) 19-28, https://doi.org/10.1016/j.ress.2018.02.005.
  50. Y. Perin, J. Jimenez, Application of the best-estimate plus uncertainty approach on a BWR ATWS transient using the NURESIM European code platform, Nucl. Eng. Des. 321 (2017) 48-56, https://doi.org/10.1016/j.nucengdes.2017.05.018.
  51. M.I. Radaideh, W.A. Wieselquist, O. Ridge, T. Kozlowski, A new framework for sampling-based uncertainty quantification of the six-group reactor kinetic parameters, Ann. Nucl. Energy (2018), https://doi.org/10.1016/j.anucene.2018.11.043.
  52. C.S. Brown, H. Zhang, Uncertainty quantification and sensitivity analysis with CASL Core Simulator VERA-CS, Ann. Nucl. Energy J. 95 (2016) 188-201, https://doi.org/10.1016/j.anucene.2016.05.016.
  53. C. Demaziere, I. P azsit, Evaluation of the boron dilution method for moderator temperature coefficient measurements, Nucl. Technol. 140 (2002) 147-163. https://doi.org/10.13182/nt02-a3329
  54. S.G. Zimmerman, J.C. Brittingham, M.L. Reed, R.P. Bandera, P.F. Crawley, PWR Reactor Physics Methodology Using CASMO-4/SIMULATE-3, Arizona Public Service Company, 1999.
  55. P. Romojaro, F. Alvarez-Velarde, N. Garcia-Herranz, Sensitivity methods for effective delayed neutron fraction and neutron generation time with summon, Ann. Nucl. Energy 126 (2019) 410-418, https://doi.org/10.1016/j.anucene.2018.11.042.
  56. M. El-Sefy, M. Ezzeldin, W. El-Dakhakhni, S. Nagasaki, L. Wiebe, Dynamic probabilistic risk assessment of core damage under different transients using system dynamics simulation approach, Chapter 4, Ph.D. Thesis, 2021, http://hdl.handle.net/11375/26246.
  57. MATLAB and Statistics Toolbox Release 2018a, The MathWorks, Inc., Natick, Massachusetts, United States, 2018.
  58. C. Perez, Neural Networks Using Matlab. Cluster Analysis and Classification, Lulu Press, Inc, 2019.
  59. E. Arce-Medina, J.I. Paz-Paredes, Artificial neural network modeling techniques applied to the hydrodesulfurization process, Math. Comput. Model. 49 (2009) 207-214, https://doi.org/10.1016/j.mcm.2008.05.010.
  60. R. Rallo, A. Arenas, F. Giralt, Neural virtual sensor for the inferential prediction of product quality from process variables, Comput. Chem. Eng. 26 (2002) 1735-1754, 26. https://doi.org/10.1016/S0098-1354(02)00148-5
  61. S. Haykin, Neural Networks, second ed., A Comprehensive Foundation, Prentice Hall PTR, Upper Saddle River, NJ, United States, 1999.
  62. G. Cybenkot, Approximation by superpositions of a sigmoidal function, Math. Control. Signals, Syst. 2 (1989) 303-314. https://doi.org/10.1007/BF02551274
  63. A.H. Gandomi, D.A. Roke, Advances in Engineering Software Assessment of artificial neural network and genetic programming as predictive tools, Adv. Eng. Software 88 (2015) 63-72, https://doi.org/10.1016/j.advengsoft.2015.05.007.
  64. S. Xu, L. Chen, A novel approach for determining the optimal number of hidden layer neurons for FNN's and its application in data mining, in: 5th Int. Conf. Inf. Technol. Appl, 2008, pp. 683-686.
  65. R. Hecht-Nielsen, Kolmogorov's mapping neural network existence theorem, in: IEEE First Int. Conf, Neural Networks, San Diego, CA, 1987.
  66. A.Y. Krylatov, A.P. Hirokolobova, Projection approach versus gradient descent for network' s flows assignment problem, Learn. Intell. Optim. (2017) 7-69404, https://doi.org/10.1007/978-3-319-69404-7_29.
  67. E.M. Johansson, F.U. Dowla, D.M. Goodman, Backpropagation learning for multilayer feed-forward neural networks using the conjugate gradient method, Int. J. Neural Syst. 2 (1992) 291-301. https://doi.org/10.1142/s0129065791000261
  68. R. Setiono, L.C.K. Hui, Use of a quasi-Newton method in a feedforward neural network construction algorithm, IEEE Trans. Neural Network. 6 (1995), 0-4. https://doi.org/10.1109/72.363426

피인용 문헌

  1. Explainable Machine learning on New Zealand strong motion for PGV and PGA vol.34, 2021, https://doi.org/10.1016/j.istruc.2021.10.085
  2. Gradient descent-particle swarm optimization based deep neural network predictive control of pressurized water reactor power vol.145, 2021, https://doi.org/10.1016/j.pnucene.2021.104108