본문 바로가기
KERD
논문KCI 등재

Application of artificial neural network for the critical flow prediction of discharge nozzle

Tao Tang|Hong Xu|Baorui Zhang|Yuechan Liu
한국원자력학회 (Korean Nuclear Society)|2022.03|Nuclear Engineering and Technology|제54권 제3호|pp. 834-841|DOI https://doi.org/10.1016/j.net.2021.08.038

1

조회

0

다운로드

0

인용

0

참고문헌

키워드

Artificial neural network (ANN)Nuclear safetyGenetic algorithm (GA)Two-phase critical flowGenetic neural network (GNN)Critical pressure ratio
주제분류원자력공학

초록

System thermal-hydraulic (STH) code is adopted for nuclear safety analysis. The critical flow model(CFM) is significant for the accuracy of STH simulation. To overcome the defects of current CFMs (lowprecision or long calculation time), a CFM based on a genetic neural network (GNN) has been developedin this work. To build a powerful model, besides the critical mass flux, the critical pressure and criticalquality were also considered in this model, which was seldom considered before. Comparing with thetraditional homogeneous equilibrium model (HEM) and the Moody model, the GNN model can predictthe critical mass flux with a higher accuracy (approximately 80% of results are within the ±20% errorlimit); comparing with the Leung model and the Shannak model for critical pressure prediction, the GNNmodel achieved the best results (more than 80% prediction results within the ±20% error limit). For thecritical quality, similar precision is achieved. The GNN-based CFM in this work is meaningful for the STHcode CFM development

Abstract

System thermal-hydraulic (STH) code is adopted for nuclear safety analysis. The critical flow model(CFM) is significant for the accuracy of STH simulation. To overcome the defects of current CFMs (lowprecision or long calculation time), a CFM based on a genetic neural network (GNN) has been developedin this work. To build a powerful model, besides the critical mass flux, the critical pressure and criticalquality were also considered in this model, which was seldom considered before. Comparing with thetraditional homogeneous equilibrium model (HEM) and the Moody model, the GNN model can predictthe critical mass flux with a higher accuracy (approximately 80% of results are within the ±20% errorlimit); comparing with the Leung model and the Shannak model for critical pressure prediction, the GNNmodel achieved the best results (more than 80% prediction results within the ±20% error limit). For thecritical quality, similar precision is achieved. The GNN-based CFM in this work is meaningful for the STHcode CFM development

참고문헌 (33)

  1. L. Yang, "Analysis of flow path blockage accident in cased assembly", Ann. Nucl. Energy, 45, pp.8~13 (2012)
  2. M. Hofer, "ATHLET extensions for the simulation of supercritical carbon dioxide driven power cycles", Kerntechnik, 84(5), pp.390~396 (2019)
  3. H. Xu, "Optimization of the nodalization of nuclear system thermal-hydraulic code applied on PKL benchmark", J. Nucl. Eng. Radiat. Sci, 147, pp.107732~ (2021)
  4. H. Xu, "Sensitivity analysis of thermal-hydraulic models based on FFTBM-MSM two-layer method for PKL IBLOCA experiment", Ann. Nucl. Energy, 147, pp.107732~ (2020)
  5. H. Xu, "Studies on the criterion for choking process in two-phase flow", Prog. Nucl. Energy, 133, pp.103640~ (2021)
  6. H. S. Isbin, "steam-water critical flow", Am. Ins. Chem. Eng. J, 3(3), pp.361~365 (1957)
  7. R. E. Henry, "Two phase critical flow at low qualities Part I : experimental", Nucl. Sci. Eng, 41(1), pp.79~91 (1970)
  8. E. Elias, "Two-phase critical flow", Int. J. Multiphas. Flow, 20(Suppl), pp.91~168 (1994)
  9. S. Yin, "Characteristic of vapor leakage behavior from a pressurized pipeline system : experiment and model study", Int. J. Heat Mass Tran, 162, pp.120335~ (2020)
  10. H. Xu, "Analysis of two phase critical flow with a nonequilibrium model", Nucl. Eng. Des, 372, pp.110998~ (2021)
  11. H. Xu, "Development of a new full-range critical flow model based on non-homogeneous non-equilibrium model", Ann. Nucl. Energy, 158, pp.108286~ (2021)
  12. T. Cong, "Applications of ANNs in flow and heat transfer problems in nuclear engineering : a review work", Prog. Nucl. Energy, 62, pp.54~71 (2013)
  13. M. Gomez-Fernandez, "Status of research and development of learning-based approaches in nuclear science and engineering : a review", Nucl. Eng. Des, 359, pp.110479~ (2020)
  14. R. A. Azim, "Prediction of multiphase flow rate for artificially flowing wells using rigorous artificial neural network technique", Flow Meas. Instrum, 76, pp.101835~ (2020)
  15. C. L. Zhang, "Generalized correlation of refrigerant mass flow rate through adiabatic capillary tubes using artificial neural network", Int. J. Refrig, 28(4), pp.506~514 (2005)
  16. C. L. Zhang, "Model-based neural network correlation for refrigerant mass flow rates through adiabatic capillary tubes", Int. J. Refrig, 30(4), pp.690~698 (2007)
  17. A. A. Aly, "Mass flow rate assessment in capillary tubes of refrigeration cycle powered by solar energy using back propagation artificial neural network", Int. J. Eng. Res. Technol, 12(7), pp.965~976 (2019)
  18. J. Zhang, "Prediction of LBB leakage for various conditions by genetic neural network and genetic algorithms", Nucl. Eng. Des, 325, pp.33~43 (2017)
  19. Y. J. An, "Critical flow prediction using simplified cascade fuzzy neural networks", Ann. Nucl. Energy, 136, pp.107047~ (2020)
  20. 박지훈, "Leak flow prediction during loss of coolant accidents using deep fuzzy neural networks", Nuclear Engineering and Technology, 53(8), pp.2547~2555 (2021), 한국원자력학회[DOI]
  21. G.L. Sozzi, "Critical Flow of Saturated and Subcooled Water at High Pressure", pp.1~24 (1975), General Electric Co
  22. S. Ghoshray, "More efficient genetic algorithm for solving optimization problems", Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, 5, pp.4515~4520 (1995)
  23. F. H. F. Leung, "Tuning of the structure and parameters of a neural network using an improved genetic algorithm", IEEE Trans. Neural Network, 14(1), pp.79~88 (2003)
  24. S. Ding, "An optimizing BP neural network algorithm based on genetic algorithm", Artif. Intell. Rev, 36, pp.153~162 (2011)
  25. H. J. Richter, "Separated two-phase flow model : application to critical twophase flow", Int. J. Multiphas. Flow, 9, pp.511~530 (1983)
  26. C. F. Schwellnus, "A two-fluid model for non-equilibrium twophase critical discharge", Can. J. Chem. Eng, 69, pp.188~197 (1991)
  27. H. S. Hillbrath, "The choking pressure ratio of a critical flow venturi", J. Eng. Ind, 97(4), pp.1251~1256 (1975)
  28. F. Hardekopf, "Critical pressure ratio of two-phase flows", J. Loss Prev. Process. Ind, 1(3), pp.134~140 (1989)
  29. G. Rudolph, "Convergence analysis of canonical genetic algorithms", IEEE Trans. Neural Network, 5(1), pp.96~101 (1994)
  30. F. J. Moody, "Maximum two-phase vessel blowdown from pipes", Trans. ASME J. Trans, 88, pp.285~293 (1966)
  31. H. Xu, "Improvement of PWR(LOCA)Safety Analysis Based on PKL Experimental Data", pp.2020
  32. J. C. Leung, "A generalized correlation for one-component homogeneous equilibrium flashing choked flow", AIChE J, 32(10), pp.1743~1746 (1986)
  33. B. A. Shannak, "Experimental investigation of critical pressure ratio in orifices", Exp. Fluid, 33, pp.508~511 (2002)

관련 논문AI추천

Improvement of the subcooled boiling model using a new net vapor generation correlation inferred from artificial neural networks to predict the void fraction profiles in the vertical channel이태범, 정용훈한국원자력학회 · Nuclear Engineering and Technology2022 · 제54권 제12호Predicting the core thermal hydraulic parameters with a gated recurrent unit model based on the soft attention mechanismCheng Zhoukai, Chun Siqi, Zhang Anni, Zhao Pengcheng한국원자력학회 · Nuclear Engineering and Technology2024 · 제56권 제6호A methodology to quantify effects of constitutive equations on safety analysis using integral effect test data오초환, 이정익한국원자력학회 · Nuclear Engineering and Technology2024 · 제56권 제8호Application of data driven modeling and sensitivity analysis of constitutive equations for improving nuclear power plant safety analysis code김도현, 오초환, 이정익한국원자력학회 · Nuclear Engineering and Technology2023 · 제55권 제1호Application of the machine learning technique for the development of a condensation heat transfer model for a passive containment cooling system김휘융, 유지민, 윤병조, 이동현, 정재준, 홍동진한국원자력학회 · Nuclear Engineering and Technology2022 · 제54권 제6호A recurrent neural network for modeling natural circulation density wave instabilitiesDuarte Juliana Pacheco, Hurley Paul한국원자력학회 · Nuclear Engineering and Technology2025 · 제57권 제6호

이 간행물의 다른 논문 (18건)

Neutronics modelling of control rod compensation operation in small modular fast reactor using OpenMCXin Jin, Hui Guo, Xingjie Peng, Yiwei Wu, Kuaiyuan Feng, Hanyang Gupp. 803-810Thermo-mechanical stress analysis of feed-water valves in nuclear power plantsLei Zhao, Yang Yue, Wen-qing Li, Jia-yi Wu, Zhi-jiang Jin, Jin-yuan Qianpp. 849-859Modified θ projection model-based constant-stress creep curve for alloy 690 steam generator tube material최권재, 한상배, 김종민, 문성인, 권준엽, 이봉상, 김민철pp. 917-925Variation of reliability-based seismic analysis of an electrical cabinet in different NPP location for Korean PeninsulaMd Motiur Rahman, Tahmina Tasnim Nahar, 김두기pp. 926-939Henry gas solubility optimization for control of a nuclear reactor: A case studySeyed Mohammad Hossein Mousakazemipp. 940-947
원문 보기