韩莎莎,李兴涛,何畅,张冰剑,陈清林

• 1:中山大学材料科学与工程学院
• 2:广东省石化过程节能工程技术研究中心
• 3:中山大学化学工程与技术学院

摘要(Abstract)：

为了准确预测蒸发器中流体流动沸腾传热性能，基于实验数据驱动，采用机器学习中多层感知器(MLPN)为通用逼近器，粒子群算法(PSO)用于优化网络权重和偏置，建立PSO-MLPN模型预测12种流体流动沸腾传热特性。神经网络输入参数包括管内径、质量流密度、热流密度、气相质量分数、液体物性参数组合和其他参数(Martinelli数，摩尔质量和汽化潜热)，输出参数为流动沸腾传热系数。网络隐藏层数和神经元数由模型精度和灵敏度分析决定。结果表明，预测值与实验值的平均绝对误差、均方根偏差和决定系数分别为3.74%、10.09%和0.984，其中约90%数据的偏差在±20%以内，与传统经验关联式对比也证明了预测模型的优越性。研究提出的PSO-MLPN模型可为今后两相流传热性能研究提供参考，并可用于实际蒸发器设计优化。

关键词(KeyWords)： 流体;流动沸腾;神经网络;传热系数;蒸发器

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金(22078373)

作者(Author): 韩莎莎,李兴涛,何畅,张冰剑,陈清林

参考文献(References)：

• [1]刘延斌,王学生,王浩,等.单根C型管外过冷沸腾传热特性实验及分析[J].高校化学工程学报, 2022, 36(3):346-353.LIU Y B, WANG X S, WANG H, et al. Experimental analysis of heat transfer characteristics out of single C-shaped tube under subcooled boiling conditions[J]. Journal of Chemical Engineering of Chinese Universities, 2022, 36(3):346-353.
• [2] SU G H, FUKUDA K, JIA D N, et al. Application of an artificial neural network in reactor thermohydraulic problem:Prediction of critical heat flux[J]. Journal of Nuclear Science and Technology, 2002, 39(5):564-571.
• [3]徐立,李玉秀,徐进良,等.微通道中纳米流体流动沸腾换热性能研究[J].高校化学工程学报, 2011, 25(4):559-564.XU L, LI Y X, XU J L, et al. Flow boiling heat transfer performance of nanofluids in a microchannel[J]. Journal of Chemical Engineering of Chinese Universities, 2011, 25(4):559-564.
• [4] LALLEMAND M, BRANESCU C, HABERSCHILL P. Local heat transfer coefficients during boiling of R22 and R407C in horizontal smooth and microfin tubes[J]. International Journal of Refrigeration, 2001, 24(1):57-72.
• [5] SHAH M M. Chart correlation for saturated boiling heat transfer:Equations and further study[J]. ASHRAE Transactions, 1982,88(1):185-196.
• [6] GUNGOR K E, WINTERTON R H S. Simplified general correlation for saturated flow boiling and comparisons of correlations with data[J]. Chemical Engineering Research&Design, 1987, 65(2):148-156.
• [7] KANDLIKAR S G. A general correlation for saturated two-phase flow boiling heat transfer inside horizontal and vertical tubes[J].ASME Journal of Heat and Mass Transfer, 1990, 112(1):219-228.
• [8] LIU Z, WINTERTON R H S. A general correlation for saturated and subcooled flow boiling in tubes and annuli, based on a nucleate pool boiling equation[J]. International Journal of Heat and Mass Transfer, 1991, 34(11):2759-2766.
• [9] JUNG D, RADERMACHER R. Transport properties and surface tension of pure and mixed refrigerants[J]. ASHRAE Transactions,1991, 97(1):90-99.
• [10] FANG X D, WU Q, YUAN Y L. A general correlation for saturated flow boiling heat transfer in channels of various sizes and flow directions[J]. International Journal of Heat and Mass Transfer, 2017, 107:972-981.
• [11] SCALABRIN G, CONDOSTA M, MARCHI P. Mixtures flow boiling:Modeling heat transfer through artificial neural networks[J].International Journal of Thermal Sciences, 2006, 45(7):664-680.
• [12] WEN X L, WANG H T, WANG H. Prediction model of flow boiling heat transfer for R407C inside horizontal smooth tubes based on RBF neural network[J]. Procedia Engineering, 2012, 31:233-239.
• [13] LIANG M L, ZHANG X H, ZHAO R, et al. Optimization of R245fa flow boiling heat transfer prediction inside horizontal smooth tubes based on the GRNN neural network[J]. Complexity, 2018, 2018:9318048.
• [14] WANG W J, ZHAO L X, ZHANG C L. Generalized neural network correlation for flow boiling heat transfer of R22 and its alternative refrigerants inside horizontal smooth tubes[J]. International Journal of Heat and Mass Transfer, 2006, 49(15/16):2458-2465.
• [15] ZHANG J, MA Y C, WANG M J, et al. Prediction of flow boiling heat transfer coefficient in horizontal channels varying from conventional to small-diameter scales by genetic neural network[J]. Nuclear Engineering and Technology, 2019, 51(8):1897-1904.
• [16]李斐.人工神经网络及遗传算法预测流动沸腾传热系数[D].兰州:兰州大学, 2019.LI F. Prediction of flow boiling heat transfer coefficient by artificial neural networks and genetic algorithms[D]. Lanzhou:Lanzhou University, 2019.
• [17] ZHU G Y, WEN T, ZHANG D L. Machine learning based approach for the prediction of flow boiling/condensation heat transfer performance in mini channels with serrated fins[J]. International Journal of Heat and Mass Transfer, 2021, 166:120783.
• [18] AMALFI R L, KIM J. Machine learning-based prediction methods for flow boiling in plate heat exchangers:20th IEEE Intersociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems[C]. San Diego:IEEE, 2021:1131-1139..
• [19] GRECO A, VANOLI G P. Flow-boiling of R22, R134a, R507, R404A and R410A inside a smooth horizontal tube[J]. International Journal of Refrigeration, 2005, 28(6):872-880.
• [20] CHOI K I, CHIEN N B, OH J T. Heat transfer coefficient during evaporation of R-1234yf, R-134a, and R-22 in horizontal circular small tubes[J]. Advances in Mechanical Engineering, 2013, doi:10.1155/2013/132397.
• [21] ANWAR Z, PALM B, KHODABANDEH R. Flow boiling heat transfer, pressure drop and dryout characteristics of R1234yf:Experimental results and predictions[J]. Experimental Thermal and Fluid Science, 2015, 66:137-149.
• [22] LU M C, TONG J R, WANG C C. Investigation of the two-phase convective boiling of HFO-1234yf in a 3.9 mm diameter tube[J].International Journal of Heat and Mass Transfer, 2013, 65:545-551.
• [23] LI M X, DANG C B, HIHARA E. Flow boili ng heat transfer of HFO1234yf and HFC32 refrigerant mixtures in a smooth horizontal tube:Part II. Prediction method[J]. International Journal of Heat and Mass Transfer, 2013, 64:591-608.
• [24] LONGO G A, MANCIN S, RIGHETTI G, et al. HFC32 and HFC410A flow boiling inside a 4 mm horizontal smooth tube[J].International Journal of Refrigeration, 2016, 61:12-22.
• [25] LILLO G, MASTRULLO R, MAURO A W, et al. Flow boiling of R32 in a horizontal stainless steel tube with 6.00 mm ID.Experiments, assessment of correlations and comparison with refrigerant R410A[J]. International Journal of Refrigeration, 2019,97:143-156.
• [26] GRECO A, VANOLI G P. Evaporation of refrigerants in a smooth horizontal tube:Prediction of R22 and R507 heat transfer coefficients and pressure drop[J]. Applied Thermal Engineering, 2004, 24(14/15):2189-2206.
• [27] WANG C C, CHIANG C S. Two-phase heat transfer characteristics for R-22/R-407C in a 6.5 mm smooth tube[J]. International Journal of Heat and Fluid Flow, 1997, 18(6):550-558.
• [28] KIM Y, SEO K, CHUNG J T. Evaporation heat transfer characteristics of R-410A in 7 and 9.52 mm smooth/micro-fin tubes[J].International Journal of Refrigeration, 2002, 25(6):716-730.
• [29] SEO K, KIM Y. Evaporation heat transfer and pressure drop of R-22 in 7 and 9.52 mm smooth/micro-fin tubes[J]. International Journal of Heat and Mass Transfer, 2000, 43(16):2869-2882.
• [30] SAITOH S, DANG C B, NAKAMURA Y, et al. Boiling heat transfer of HFO-1234yf flowing in a smooth small-diameter horizontal tube[J]. International Journal of Refrigeration, 2011, 34(8):1846-1853.
• [31] DEL COL D, BORTOLIN S, TORRESIN D, et al. Flow boiling of R1234yf in a 1 mm diameter channel[J]. International Journal of Refrigeration, 2013, 36(2):353-362.
• [32] GRECO A. Convective boiling of pure and mixed refrigerants:An experimental study of the major parameters affecting heat transfer[J]. International Journal of Heat and Mass Transfer, 2008, 51(3/4):896-909.
• [33] LEMMON E W, HUBER M L, MCLINDEN M O. NIST standard reference database 23, Reference fluid thermodynamic and transport properties-REFPROP, version 9.1[DB/OL]. Gaithersburg:National Institute of Standards and Technology, 2013[2023-08-17]. https://www.nist.gov/publications/nist-standard-reference-database-23-reference-fluid-thermodynamic-and-transport