Application of the machine learning technique for the development of a condensation heat transfer model for a passive containment cooling system
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
A condensation heat transfer model is essential to accurately predict the performance of the passivecontainment cooling system (PCCS) during an accident in an advanced light water reactor. However,most of existing models tend to predict condensation heat transfer very well for a specific range ofthermal-hydraulic conditions. In this study, a new correlation for condensation heat transfer coefficient(HTC) is presented using machine learning technique. To secure sufficient training data, a large numberof pseudo data were produced by using ten existing condensation models. Then, a neural network modelwas developed, consisting of a fully connected layer and a convolutional neural network (CNN) algorithm, DenseNet. Based on the hold-out cross-validation, the neural network was trained and validatedagainst the pseudo data. Thereafter, it was evaluated using the experimental data, which were not usedfor training. The machine learning model predicted better results than the existing models. It was alsoconfirmed through a parametric study that the machine learning model presents continuous andphysical HTCs for various thermal-hydraulic conditions. By reflecting the effects of individual variablesobtained from the parametric analysis, a new correlation was proposed. It yielded better results foralmost all experimental conditions than the ten existing models.
Abstract
A condensation heat transfer model is essential to accurately predict the performance of the passivecontainment cooling system (PCCS) during an accident in an advanced light water reactor. However,most of existing models tend to predict condensation heat transfer very well for a specific range ofthermal-hydraulic conditions. In this study, a new correlation for condensation heat transfer coefficient(HTC) is presented using machine learning technique. To secure sufficient training data, a large numberof pseudo data were produced by using ten existing condensation models. Then, a neural network modelwas developed, consisting of a fully connected layer and a convolutional neural network (CNN) algorithm, DenseNet. Based on the hold-out cross-validation, the neural network was trained and validatedagainst the pseudo data. Thereafter, it was evaluated using the experimental data, which were not usedfor training. The machine learning model predicted better results than the existing models. It was alsoconfirmed through a parametric study that the machine learning model presents continuous andphysical HTCs for various thermal-hydraulic conditions. By reflecting the effects of individual variablesobtained from the parametric analysis, a new correlation was proposed. It yielded better results foralmost all experimental conditions than the ten existing models.
참고문헌 (44)
- B. G. Jeon, "Conceptual design of passive containment cooling system with air holdup tanks in the concrete containment of improved APRþ", Nucl. Eng. Des, 267, pp.180~188 (2014)
- Interim Report on Safety Assessment and Facilities Establishment Project for June 1965. No. 1, "T. Tagami", Japanese Atomic Energy Agency, ~ (1965)
- A.A. Dehbi, "The Effects of Non-condensable Gases on Steam Condensation under Turbulent Natural Convection Conditions", PhD, Department of Nuclear Eng., pp.1991
- J. Su, "Experimental study of the effect of noncondensable gases on steam condensation over a vertical tube external surface", Nucl. Eng. Des, 262, pp.201~208 (2013)
- J. Su, "Analysis of experiments for the effect of noncondensable gases on steam condensation over a vertical tube external surface under low wall subcooling", Nucl. Eng. Des, 278, pp.644~650 (2014)
- Y. G. Lee, "An experimental study of airesteam condensation on the exterior surface of a vertical tube under natural convection conditions", Int. J. Heat Mass Tran, 104, pp.1034~1047 (2017)
- G. Fan, "Development of a new empirical correlation for steam condensation rates in the presence of air outside vertical smooth tube", Ann. Nucl. Energy, 113, pp.139~146 (2018)
- 장영준, "비응축성 기체 존재 시 수직관 외벽에서의 응축 열전달계수 상관식 개발", 대한기계학회논문집 B, 42(3), pp.187~196 (2018), 대한기계학회
- U. K. Kim, "Measurement of heat transfer coefficients for steam condensation on a vertical 21. 5-mm-OD tube in the presence of air", J. Nucl. Sci. Technol, 57(8), pp.905~916 (2020)
- J. H. Kang, "Condensation of steam mixed with non-condensable gas on vertical heat exchanger tubes in circumstances with free convection", Int. J. Heat Mass Tran, 169, pp.120925~ (2021)
- H. Liu, "An experimental investigation of A passive cooling unit for nuclear plant containment", Nucl. Eng. Des, 199(3), pp.243~255 (2000)
- A. A. Dehbi, "A generalized correlation for steam condensation rates in the presence of air under turbulent free convection", Int. J. Heat Mass Tran, 86, pp.1~15 (2015)
- P. F. Peterson, "Diffusion layer theory for turbulent vapor condensation with noncondensable gases", J. Heat Tran, 115, pp.998~1003 (1993)
- L. E. Herranz, "A diffusion layer model for steam condensation within the AP600 containment", Nucl. Eng. Des, 183(1-2), pp.133~150 (1998)
- Y. Liao, "A generalized diffusion layer model for condensation of vapor with noncondensable gases", J. Heat Tran, 129, pp.988~994 (2007)
- J. Y. Lee, "Improvement of the condensation heat transfer model of the MARS-KS1. 3 code using a modified diffusion layer model", Prog. Nucl. Energy, 108, pp.260~269 (2018)
- S. Benteboula, "Modeling of wall condensation in the presence of noncondensable light gas", Int. J. Heat Mass Tran, 151, pp.119313~ (2020)
- A. P. Colburn, "Design of cooler condensers for mixtures of vapors with noncondensing gases", Ind. Eng. Chem, 26(11), pp.1178~1182 (1934)
- T. B. Trafalis, "Two-phase flow regime identification with a multiclassification support vector machine(SVM)model", Ind. Eng. Chem. Res, 44(12), pp.4414~4426 (2005)
- H. Wei, "Applications of genetic neural network for prediction of critical heat flux", Int. J. Therm. Sci, 49(1), pp.143~152 (2010)
- J. Cai, "Predicting the critical heat flux in concentric-tube open thermosiphon : a method based on support vector machine optimized by chaotic particle swarm optimization algorithm", Heat Mass Tran, 48(8), pp.1425~1435 (2012)
- B. T. Jiang, "Combination of support vector regression and artificial neural networks for prediction of critical heat flux", Int. J. Heat Mass Tran, 62, pp.481~494 (2013)
- E. Heidari, "Accurate prediction of nanofluid viscosity using a multi-layer perceptron artificial neural network(MLP-ANN)", Chemometr. Intell. Lab. Syst, 155, pp.73~85 (2016)
- S. Azizi, "Prediction of heat transfer coefficient during condensation of R134a in inclined tubes using artificial neural network", Appl. Therm. Eng, 106, pp.203~210 (2016)
- A. M. Ghahdarijani, "Convective heat transfer and pressure drop study on nanofluids in double-walled reactor by developing an optimal multi-layer perceptron artificial neural network", Int. Commun. Heat Mass Tran, 84, pp.11~19 (2017)
- D. Ma, "Supercritical water heat transfer coefficient prediction analysis based on BP neural network", Nucl. Eng. Des, 320, pp.400~408 (2017)
- M. Hojjat, "Modeling heat transfer of non-Newtonian nanofluids using hybrid ANN-Metaheuristic optimization algorithm", J. Part. Sci. Technol, 3, pp.233~241 (2017)
- A. Baghban, "Sensitivity analysis and application of machine learning methods to predict the heat transfer performance of CNT", water nanofluid flows through coils, 2019, pp.128, 825~835
- H. M. Park, "Wall temperature prediction at critical heat flux using a machine learning model", Ann. Nucl. Energy, 141, pp.107334~ (2020)
- N. Giannetti, "Prediction of two-phase flow distribution in microchannel heat exchangers using artificial neural network", Int. J. Refrig, 111, pp.53~62 (2020)
- K. Simonyan, "Very Deep Convolutional Networks for Large-Scale Image Recognition", arXiv preprint arXiv:1409, 1556~ (2014)
- C. Szegedy, "Going deeper with convolutions", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.1~9 (2015)
- K. He, "Deep residual learning for image recognition", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.770~778 (2016)
- G. Huang, "Densely connected convolutional networks", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.4700~4708 (2017)
- J. Hu, "Squeeze-and-excitation networks", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.7132~7141 (2018)
- G. M. Hobold, "Automatic detection of the onset of film boiling using convolutional neural networks and Bayesian statistics", Int. J. Heat Mass Tran, 134, pp.262~270 (2019)
- G. M. Hobold, "Visualization-based nucleate boiling heat flux quantification using machine learning", Int. J. Heat Mass Tran, 134, pp.511~520 (2019)
- J. Kim, "Prediction of turbulent heat transfer using convolutional neural networks", J. Fluid Mech, pp.882~ (2020)
- Y. Suh, "Deep learning predicts boiling heat transfer", Sci. Rep, 11(1), pp.1~10 (2021)
- 김휘융, "Prediction of critical heat flux for narrow rectangular channels in a steady state condition using machine learning", Nuclear Engineering and Technology, 53(6), pp.1796~1809 (2021), 한국원자력학회[DOI]
- J. W. Kim, "Condensation heat transfer characteristic in the presence of non-condensable gas on natural convection at high pressure", Nucl. Eng. Des, 239(4), pp.688~698 (2009)
- C. O. Popiel, "Free convection heat transfer from vertical slender cylinders : a review", Heat Tran. Eng, 29(6), pp.521~536 (2008)
- B. R. Bird, "Transport Phenomena" (1960), John Wiley &Sons Inc
- D.E. Rumelhart, "Parallel Distributed Processing: Explorations in the Microstructures of Cognition. Vol. 1: Foundations", pp.547~611 (1986), MIT Press