BP神经网络方法对露点间接蒸发冷却器性能预测及分析  

Performance of Indirect Evaporative Cooler with Dew Point by BP Neural Network Method Forecast and Analysis

作　　者：屈悦滢 黄翔[1] 孙铁柱[1] Qu Yueying;Huang Xiang;Sun Tiezhu(Xi'an Polytechnic University,Xi'an,710048)

机构地区：[1]西安工程大学,西安710048

出　　处：《制冷与空调（四川）》2021年第2期151-156,共6页Refrigeration and Air Conditioning

基　　金：西安市科技计划项目(2020KJRC0023);国家自然科学基金(51676145);西安工程大学研究生创新基金项目资助(编号:chx2020039)。

摘　　要：通过对露点间接蒸发冷却空调机组的实际测试,在机组其他条件不变的情况下,仅考虑机组进风口空气的干球温度和含湿量对机组出风口空气的干球温度和含湿量以及机组效率的影响,采用MATLAB软件建立预测露点蒸发冷却器性能的人工神经网络模型。同时对神经网络模型进行检验,使网络预测模型达到预期效果,以完成对模型性能分析和评价。结果表明应用BP神经网络方法对露点间接蒸发冷却空调机组的性能预测是可行的,网络拟合效果总相关性为0.92026。Through the actual test of the dew point indirect evaporative cooling air conditioning unit,under the condition that the other conditions of the unit are unchanged,only the dry bulb temperature and moisture content of the air inlet air of the unit and the dry bulb temperature and moisture content of the air outlet air of the unit and the For the effect of unit efficiency,MATLAB software is used to establish an artificial neural network model for predicting the performance of dew point evaporative coolers.Combined with the actual test data,the neural network prediction model is tested to make the network prediction model achieve the expected effect to complete the performance analysis and evaluation of the model.The results show that it is feasible to predict the performance of the air conditioning unit using the BP neural network method.The total correlation of the combined effect is 0.92026.

关 键 词：露点间接蒸发冷却 空调机组 神经网络 性能预测 

分 类 号：TU831.5[建筑科学—供热、供燃气、通风及空调工程]