基于多结构翅片管换热器变工况实验数据，研究神经网络模型在水-空气翅片管换热器性能预测方面的可行性.建立2排管、3排管翅片管换热器在制冷、制热工况下的反向传播神经网络模型，优化并确定单隐含层和双隐含层情况下较优的网络结构，模型预测误差达到1%左右.以指定结构翅片管换热器数据作为测试集，对比单隐含层和双隐含层网络模型在性能预测方面的效果.研究结果表明：对于制冷工况，双隐含层模型不能提高模型精度，反而会因为过拟合导致部分参数的预测精度降低；对于制热工况，双隐含层模型在预测结果精度上有明显的提高.
Based on the experimental data of variable structure heat exchangers, the feasibility of neural network model in the performance for the prediction of water-air finned tube heat exchangers is studied. The back propagation (BP) neural network models of 2 rows and 3 rows of finned tubes under refrigeration and heating conditions are established which optimize and determine the optimal network structure under the condition of single hidden layer and double hidden layer. The prediction error of the models is about 1%. The specified structural heat exchanger data is set as a test set, and the performance of the single hidden layer and double hidden layer network model is compared. The research results show that for the refrigeration condition, the double hidden layer model cannot improve the accuracy of the model, but will even reduce the prediction accuracy of some parameters due to over-fitting. For the heating condition, the double hidden layer model has a better accuracy in prediction.
［1］冯梦怡, 曾炜杰, 谷波. 不同回路结构表冷器的变工况性能分析［J］. 流体机械, 2017, 45(9): 82-86.
FENG Mengyi, ZENG Weijie, GU Bo. Analysis on the performance of fin-tube heat exchanger with different structures in variable conditions［J］. Fluid Machinery, 2017, 45(9): 82-86.
［2］张杰, 谷波, 方继华. 受限空间中翅片管换热器的性能分析［J］. 制冷学报, 2014, 35(2): 36-43.
ZHANG Jie, GU Bo, FANG Jihua. Performance analysis on the fin-tube heat exchanger in limited space［J］. Journal of Refrigeration, 2014, 35(2): 36-43.
［3］韩维哲, 丁国良, 胡海涛, 等. 湿工况下翅片管换热器空气侧热质传递的数值模型［J］. 上海交通大学学报, 2013, 47(3): 385-391.
HAN Weizhe, DING Guoliang, HU Haitao, et al. Numerical model of heat and mass transfer for tube-finned heat exchangers under dehumidifying conditions［J］. Journal of Shanghai Jiao Tong University, 2013, 47(3): 385-391.
［4］曾炜杰, 谷波, 李强林. 圆柱型翅片管换热器变工况传热性能模拟与分析［J］. 制冷学报, 2019, 40(2): 28-35.
ZENG Weijie, GU Bo, LI Qianglin. Simulation and analysis of heat transfer performance of cylindrical fin-and-tube heat exchanger under variable conditions［J］. Journal of Refrigeration, 2019, 40(2): 28-35.
［5］WU X Z, ZHAO J N, WANG F H. Simplified number of transfer unit formulas for the thermal performance calculation of multi-pass fin-tube heat exchangers［J］. Science and Technology for the Built Environment, 2015, 21(2): 238-245.
［6］MARKOVI S, JAIMOVI B, GENI S, et al. Air side pressure drop in plate finned tube heat exchangers［J］. International Journal of Refrigeration, 2019, 99: 24-29.
［7］KALOGIROU S. Applications of artificial neural networks in energy systems［J］. Energy Conversion and Management, 1999, 40(10): 1073-1087.
［8］DING G L. Recent developments in simulation techniques for vapour-compression refrigeration systems［J］. International Journal of Refrigeration, 2007, 30(7): 1119-1133.
［9］郭梦茹, 谭泽汉, 陈焕新, 等. 基于遗传算法和BP神经网络的多联机阀类故障诊断［J］. 制冷学报, 2018, 39(2): 119-125.
GUO Mengru, TAN Zehan, CHEN Huanxin, et al. Valve fault diagnosis of variable refrigerant flow system based on genetic algorithm and back propagation neural network［J］. Journal of Refrigeration, 2018, 39(2): 119-125.
［10］HORNIK K, STINCHCOMBE M, WHITE H. Multilayer feedforward networks are universal approximators［J］. Neural Networks, 1989, 2(5): 359-366.
