上海交通大学学报

上海交通大学学报 ›› 2020, Vol. 54 ›› Issue (7): 668-673.doi: 10.16183/j.cnki.jsjtu.2019.147

• 学报（中文） • 上一篇    下一篇

反向传播神经网络对多结构翅片管换热器变工况性能预测适应性研究

李强林1，曾炜杰1，田镇1,2，谷波1   

  1. 1. 上海交通大学 制冷及低温工程研究所， 上海 200240； 2. 上海海事大学 商船学院， 上海 201306
  • 出版日期:2020-07-28 发布日期:2020-07-31
  • 通讯作者: 谷波，男，教授，博士生导师，电话(Tel.):021-34206260; E-mail:gubo@sjtu.edu.cn.
  • 作者简介:李强林(1994-)，男，江苏省盐城市人，硕士生，主要研究方向为空调系统数字化设计.
  • 基金资助:
    国家自然科学基金(51976114)，中国博士后科学基金(2019M650084)资助项目

Adaptability of Multi-Structure of Finned Tube Heat Exchanger Under Variable Operation Conditions Based on Back Propagation Neural Network

LI Qianglin 1,ZENG Weijie 1,TIAN Zhen 1,2,GU Bo 1   

  1. 1. Institute of Refrigeration and Cryogenics, Shanghai Jiao Tong University, Shanghai 200240, China; 2. Merchant Marine College, Shanghai Maritime University, Shanghai 201306, China
  • Online:2020-07-28 Published:2020-07-31

PDF (PC)

361

摘要： 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.

关键词: 翅片管换热器, 反向传播神经网络, 变结构, 网络结构

Abstract: 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.

Key words: finned tube heat exchanger, back propagation (BP) neural network, variable structure, network architecture

中图分类号: