본문 바로가기
KERD
논문KCI 등재

Application of POD reduced-order algorithm on data-driven modeling of rod bundle

Lei Li|Huilun Kang|Zhaofei Tian|Guangliang Chen|Tianyu Wang
한국원자력학회 (Korean Nuclear Society)|2022.01|Nuclear Engineering and Technology|제54권 제1호|pp. 36-48|DOI https://doi.org/10.1016/j.net.2021.07.010

2

조회

0

다운로드

0

인용

0

참고문헌

키워드

Machine learningCFDProper orthogonal decompositionReduced-order modelFuel rod bundle
주제분류원자력공학

초록

As a valid numerical method to obtain a high-resolution result of a flow field, computational fluid dynamics (CFD) have been widely used to study coolant flow and heat transfer characteristics in fuel rod bundles. However, the time-consuming, iterative calculation of Navier-Stokes equations makes CFD unsuitable for the scenarios that require efficient simulation such as sensitivity analysis and uncertainty quantification. To solve this problem, a reduced-order model (ROM) based on proper orthogonal decomposition (POD) and machine learning (ML) is proposed to simulate the flow field efficiently. Firstly, a validated CFD model to output the flow field data set of the rod bundle is established. Secondly, based on the POD method, the modes and corresponding coefficients of the flow field were extracted. Then, an deep feed-forward neural network, due to its efficiency in approximating arbitrary functions and its ability to handle high-dimensional and strong nonlinear problems, is selected to build a model that maps the non-linear relationship between the mode coefficients and the boundary conditions. A trained surrogate model for modes coefficients prediction is obtained after a certain number of training iterations. Finally, the flow field is reconstructed by combining the product of the POD basis and coefficients. Based on the test dataset, an evaluation of the ROM is carried out. The evaluation results show that the proposed POD-ROM accurately describe the flow status of the fluid field in rod bundles with high resolution in only a few milliseconds.

Abstract

As a valid numerical method to obtain a high-resolution result of a flow field, computational fluid dynamics (CFD) have been widely used to study coolant flow and heat transfer characteristics in fuel rod bundles. However, the time-consuming, iterative calculation of Navier-Stokes equations makes CFD unsuitable for the scenarios that require efficient simulation such as sensitivity analysis and uncertainty quantification. To solve this problem, a reduced-order model (ROM) based on proper orthogonal decomposition (POD) and machine learning (ML) is proposed to simulate the flow field efficiently. Firstly, a validated CFD model to output the flow field data set of the rod bundle is established. Secondly, based on the POD method, the modes and corresponding coefficients of the flow field were extracted. Then, an deep feed-forward neural network, due to its efficiency in approximating arbitrary functions and its ability to handle high-dimensional and strong nonlinear problems, is selected to build a model that maps the non-linear relationship between the mode coefficients and the boundary conditions. A trained surrogate model for modes coefficients prediction is obtained after a certain number of training iterations. Finally, the flow field is reconstructed by combining the product of the POD basis and coefficients. Based on the test dataset, an evaluation of the ROM is carried out. The evaluation results show that the proposed POD-ROM accurately describe the flow status of the fluid field in rod bundles with high resolution in only a few milliseconds.

참고문헌 (40)

  1. Klaus Rehme, "The structure of turbulence in rod bundles and the implications on natural mixing between the subchannels", International Journal of Heat and Mass Transfer, 35(2), pp.567~581 (1992), Elsevier BV[DOI]
  2. D.S. Rowe, "Implications concerning rod bundle crossflow mixing based on measurements of turbulent flow structure", International Journal of Heat and Mass Transfer, 17(3), pp.407~419 (1974), Elsevier BV[DOI]
  3. C.M. Lee, "Comparison of thermo-hydraulic performances of large scale vortex flow (LSVF) and small scale vortex flow (SSVF) mixing vanes in 17×17 nuclear rod bundle", Nuclear Engineering and Design, 237(24), pp.2322~2331 (2007), Elsevier BV[DOI]
  4. Wenhai Qu, "PIV measurement of turbulent flow downstream of mixing vane spacer grid in 5×5 rod bundle", Annals of Nuclear Energy, 132, pp.277~287 (2019), Elsevier BV[DOI]
  5. Han Wang, "PIV measurement and CFD analysis of the turbulent flow in a 3 × 3 rod bundle", Annals of Nuclear Energy, 140, pp.107135~ (2020), Elsevier BV[DOI]
  6. Sang Yong Han, "Measurements of the flow characteristics of the lateral flow in the 6×6 rod bundles with Tandem Arrangement Vanes", Nuclear Engineering and Design, 239(12), pp.2728~2736 (2009), Elsevier BV[DOI]
  7. A.C. Trupp, "The structure of turbulent flow in triangular array rod bundles", Nuclear Engineering and Design, 32(1), pp.47~84 (1975), Elsevier BV[DOI]
  8. Jinbiao Xiong, "CFD simulation of swirling flow induced by twist vanes in a rod bundle", Nuclear Engineering and Design, 338, pp.52~62 (2018), Elsevier BV[DOI]
  9. Wang Yingjie, "CFD simulation of flow and heat transfer characteristics in a 5×5 fuel rod bundles with spacer grids of advanced PWR", Nuclear Engineering and Technology, 52(7), pp.1386~1395 (2020), 한국원자력학회[DOI]
  10. Jinguang Zang, "The flow resistance experiments of supercritical pressure water in 2 × 2 rod bundle", International Journal of Heat and Mass Transfer, 147, pp.118873~ (2020), Elsevier BV[DOI]
  11. Y. Wang, "CFD assist in design of spacer-grid with mixing-vane for a rod bundle", Applied Thermal Engineering, 149, pp.565~577 (2019), Elsevier BV[DOI]
  12. Xiang-Zhe CUI, "Three-Dimensional Analysis of Turbulent Heat Transfer and Flow through Mixing Vane in A Subchannel of Nuclear Reactor", Journal of Nuclear Science and Technology, 40(10), pp.719~724 (2003), Informa UK Limited[DOI]
  13. Wang-Kee In, "Numerical Computation of Heat Transfer Enhancement of a PWR Rod Bundle with Mixing Vane Spacers", Nuclear Technology, 161(1), pp.69~79 (2008), Informa UK Limited[DOI]
  14. Moysés A. Navarro, "Evaluation of a numeric procedure for flow simulation of a 5 × 5 PWR rod bundle with a mixing vane spacer", Progress in Nuclear Energy, 53(8), pp.1190~1196 (2011), Elsevier BV[DOI]
  15. Guangliang Chen, "Design of a CFD scheme using multiple RANS models for PWR", Annals of Nuclear Energy, 102, pp.349~358 (2017), Elsevier BV[DOI]
  16. Xiaochang Li, "Methods of simulating large-scale rod bundle and application to a 17×17 fuel assembly with mixing vane spacer grid", Nuclear Engineering and Design, 267, pp.10~22 (2014), Elsevier BV[DOI]
  17. Tenglong Cong, "Applications of ANNs in flow and heat transfer problems in nuclear engineering: A review work", Progress in Nuclear Energy, 62, pp.54~71 (2013), Elsevier BV[DOI]
  18. Jing Zhang, "Prediction of flow boiling heat transfer coefficient in horizontal channels varying from conventional to small-diameter scales by genetic neural network", Nuclear Engineering and Technology, 51(8), pp.1897~1904 (2019), 한국원자력학회[DOI]
  19. N. Amanifard, "Modelling and Pareto optimization of heat transfer and flow coefficients in microchannels using GMDH type neural networks and genetic algorithms", Energy Conversion and Management, 49(2), pp.311~325 (2008), Elsevier BV[DOI]
  20. Dongliang Ma, "Supercritical water heat transfer coefficient prediction analysis based on BP neural network", Nuclear Engineering and Design, 320, pp.400~408 (2017), Elsevier BV[DOI]
  21. Pedro L.S. Serra, "Two-phase flow void fraction estimation based on bubble image segmentation using Randomized Hough Transform with Neural Network (RHTN)", Progress in Nuclear Energy, 118, pp.103133~ (2020), Elsevier BV[DOI]
  22. Hae Min Park, "Wall temperature prediction at critical heat flux using a machine learning model", Annals of Nuclear Energy, 141, pp.107334~ (2020), Elsevier BV[DOI]
  23. Nima Vaziri, "Critical heat flux prediction by using radial basis function and multilayer perceptron neural networks: A comparison study", Nuclear Engineering and Design, 237(4), pp.377~385 (2007), Elsevier BV[DOI]
  24. Jingjing Li, "Sensitivity analysis of CHF parameters under flow instability by using a neural network method", Annals of Nuclear Energy, 71, pp.211~216 (2014), Elsevier BV[DOI]
  25. B.T. Jiang, "Prediction of critical heat flux for water flow in vertical round tubes using support vector regression model", Progress in Nuclear Energy, 68, pp.210~222 (2013), Elsevier BV[DOI]
  26. Y. Mi, "Flow regime identification methodology with neural networks and two-phase flow models", Nuclear Engineering and Design, 204(1-3), pp.87~100 (2001), Elsevier BV[DOI]
  27. Roberto N. de Mesquita, "Classification of natural circulation two-phase flow image patterns based on self-organizing maps of full frame DCT coefficients", Nuclear Engineering and Design, 335, pp.161~171 (2018), Elsevier BV[DOI]
  28. J. Huang, "Online in situ prediction of 3-D flame evolution from its history 2-D projections via deep learning", J. Fluid Mech, 875 (2019)[DOI]
  29. Luning Sun, "Surrogate modeling for fluid flows based on physics-constrained deep learning without simulation data", Computer Methods in Applied Mechanics and Engineering, 361, pp.112732~ (2020), Elsevier BV[DOI]
  30. T. Aaron, "Spectral proper orthogonal decomposition and its relationship to dynamic mode decomposition and resolvent analysis", J. Fluid Mech, 847, pp.821~867 (2017)[DOI]
  31. Z. Luo, "A reduced stabilized mixed finite element formulation based on proper orthogonal decomposition for the nonstationary Navier-Stokes equations", Int. J. Numer. Methods Eng, 88(1), pp.31~46 (2011)[DOI]
  32. Xu Wang, "Multi‐fidelity surrogate reduced‐order modeling of steady flow estimation", International Journal for Numerical Methods in Fluids, 92(12), pp.1826~1844 (2020), Wiley[DOI]
  33. Lawrence Sirovich, "Turbulence and the dynamics of coherent structures. II. Symmetries and transformations", Quarterly of Applied Mathematics, 45(3), pp.573~582 (1987), American Mathematical Society (AMS)[DOI]
  34. Z. Karoutas, "3-D flow analyses for design of nuclear fuel spacer", Proceedings of the 7th International Meeting on Nuclear Reactor Thermal-Hydraulics, pp.3153~3174 (1995)
  35. Guangliang Chen, "CFD simulation for the optimal design and utilization of experiment to research the flow process in PWR", Annals of Nuclear Energy, 94, pp.1~9 (2016), Elsevier BV[DOI]
  36. G. Chen, "Optimal meshing methods and schemes for the simulation of assembly", Trans. Am. Nucl. Soc, 111, pp.1572~1575 (2014)
  37. C.C. Liu, "CFD evaluation of turbulence models for flow simulation of the fuel rod bundle with a spacer assembly", Applied Thermal Engineering, 40, pp.389~396 (2012), Elsevier BV[DOI]
  38. M.V. Holloway, "Investigation of swirling flow in rod bundle subchannels using computational fluid dynamics", International Conference on Nuclear Engineering, Proceedings, ICONE (2006)
  39. M. D. McKay, "Comparison of three methods for selecting values of input variables in the analysis of output from a computer code", Technometrics, 21, pp.239~245 (1979)[DOI]
  40. D. Balduzzi, "The shattered gradients problem: if resnets are the answer, then what is the question?", 34th International Conference on Machine Learning, ICML, 1, pp.536~549 (2017)

관련 논문AI추천

Investigation on the nonintrusive multi-fidelity reduced-order modeling for PWR rod bundlesGuangliang Chen, Huilun Kang, Lei Li, Tianhui Chu, Zhaofei Tian한국원자력학회 · Nuclear Engineering and Technology2022 · 제54권 제5호Fast prediction of the flow induced vibration of wire-wrapped fuel rod in a lead-bismuth reactor based on improved DMD and LSTM networkLi Pengzhou, Qiao Hongwei, Zhang Yu한국원자력학회 · Nuclear Engineering and Technology2025 · 제57권 제11호A new surrogate method for the neutron kinetics calculation of nuclear reactor core transientsDu Xianan, Li Xiaoqi, Xiao Bowen, Zheng Youqi한국원자력학회 · Nuclear Engineering and Technology2024 · 제56권 제9호Thermal stratification prediction in reactor system based on CFD simulations accelerated by a data-driven coarse-grid turbulence modelCheng Xu, Florin Badea Aurelian, Liu Zijing, Zhao Pengcheng한국원자력학회 · Nuclear Engineering and Technology2025 · 제57권 제4호Application of data-driven model reduction techniques in reactor neutron field calculationsChen Qiafeng, Xiang Zhaocai, Zhao Pengcheng한국원자력학회 · Nuclear Engineering and Technology2024 · 제56권 제8호Development of reduced-order thermal stratification model for upper plenum of a lead–bismuth fast reactor based on CFDYang Tao, Yu Tao, Zhao Pengcheng, Zhao Yanan한국원자력학회 · Nuclear Engineering and Technology2023 · 제55권 제8호

이 간행물의 다른 논문 (21건)

Possibility of Curium as a Fuel for VVER-1200 ReactorMahmud Hasan Ovi, Afroza Shelleypp. 11-18Analysis and comparison of the 2D/1D and quasi-3D methods with the direct transport code SHARKXingjie Peng, Zhang Chen, Qing Li, Wenbo Zhao, Hongbo Zhang, Chen Zhaopp. 19-29Experimental study on the Influence of Heating Surface Inclination Angle on Heat Transfer and CHF performance for Pool BoilingWenxi Tian, Chenglong Wang, Panxiao Li, Dalin Zhang, Suizheng Qiu, G.H. Su, Jian Dengpp. 61-71Numerical study on thermal-hydraulics of external reactor vessel cooling in high-power reactor using MARS-KS1.5 code: CFD-aided estimation of natural circulation flow rate박일웅, 송민섭, 이연건, 김응수pp. 72-83How to Incorporate Human Failure Event Recovery into Minimal Cut Set Generation Stage for Efficient Probabilistic Safety Assessments of Nuclear Power Plants박성규, Jeff Riley, John E. Weglian, 정우식pp. 110-116
원문 보기