A STUDY METHOD ON WET-MEMBRANE EVAPORATIVE COOLING PROCESS
During evaporative cooling process, the actual area of the water-air interface can’t be predicted because the process of water droplets or falling film is complex. So, it is difficult to calculate the value of heat transfer coefficient and mass transfer coefficient.In this paper, BP network is employed to study the complex process of evaporative cooling. The training data are employed to train the network. Examination data were employed to examine the network, and the results showed that the best linear regression slope of supply air dry-ball temperature is 0.983 and y-intercept is 0.525, while perfect fit slope is 1 and y-intercept is 0. Similarly, the best linear regression slope of supply air relative humidity is 1.01 and y-intercept is -0.811.This research has proved that artificial neural network is capable to predict performance of direct evaporative cooling process.
T.QIANG X.HUANG J.WU Z.DONG
Department of Environmental & Chemical, Xi’an Polytechnic University, 19 Jin-Hua Road (south),Xi’an, Department of Computer Science, Zhongyuan University of Technology, 41 Zhong-yuan Road (west),Zheng
国际会议
The 22nd International Congress of Refrigeration(第22届国际制冷大会)
北京
英文
2007-08-21（万方平台首次上网日期，不代表论文的发表时间）