流体机械

2020, v.48;No.574(04) 72-77

[打印本页] [关闭]
本期目录(Current Issue) | 过刊浏览(Past Issue) | 高级检索(Advanced Search)

基于神经网络模型的冷库冷风机除霜控制研究
Research on Defrost Control of Cold Storage Cooling Fan Based on Neural Network Model

申江;窦伟;向鹏程;胡开永;张自强;
Shen Jiang;Dou Wei;Xiang Pengcheng;Hu Kaiyong;Zhang Ziqiang;Tianjin Key Laboratory of Refrigeration,Tianjin University of Commerce;Beijing Aerospace Xinfeng Machanical Equipment Co.,Ltd.;

摘要(Abstract):

冷库冷风机"按需除霜",可有效降低冷库能耗、提高能源利用率。本文将湿空气物性参数、冷风机运行时间作为神经网络输入变量,建立基于BP算法训练的多层前馈神经网络结霜量与除霜时长预测模型,并利用相关试验数据进行模型训练与测试。结果表明:结霜量预测模型计算值与试验测量值平均误差为10.11%,除霜预测模型计算值与试验测量值的误差均小于5%。本文所建立的基于人工神经网络结霜量预测模型与除霜时长预测模型可较好地预测冷风机结霜量与除霜时长,为实际工程应用中通过确定除霜起始点和除霜时长实现冷风机"按需除霜"提供了参考价值。
The"defrosting on demand"of cold storage chillers can effectively reduce the energy consumption of cold storage and improve energy efficiency.The wet air physical parameters and the cooling fan running time were taken as the neural network input variables,and the frosting amount of the multi-layer feedforward neural network trained based on BP algorithm was used to establish the frosting amount and defrosting duration prediction model.The experimental data was used to train and test the model.The results show that the average error between the calculated value of the frosting prediction model and the experimental measurement value was 10.11%,and the average error between the calculated value of the defrosting prediction model and the experimental measurement value was less than 5%.The artificial neural network frosting prediction model and the defrosting duration prediction model established can well predict the frosting amount and defrosting time of the chiller,and realize the defrosting starting point and the defrosting time in practical engineering applications.The"Defrost on Demand"of the air cooler provides a reference value.

关键词(KeyWords): 人工神经网络;预测模型;按需除霜;除霜控制
artificial neural network;prediction model;defrosting on demand;defrosting control

Abstract:

Keywords:

基金项目(Foundation): 北京航天新风机械设备有限责任公司试验室创新基金项目(QT-2018-004)

作者(Author): 申江;窦伟;向鹏程;胡开永;张自强;
Shen Jiang;Dou Wei;Xiang Pengcheng;Hu Kaiyong;Zhang Ziqiang;Tianjin Key Laboratory of Refrigeration,Tianjin University of Commerce;Beijing Aerospace Xinfeng Machanical Equipment Co.,Ltd.;

Email:

DOI:

参考文献(References):

扩展功能
本文信息
服务与反馈
本文关键词相关文章
本文作者相关文章
中国知网
分享