盾形冷凝模块用于蒸发冷却设备消雾的消光值预测
Extinction value prediction of defogging effect for evaporative cooling equipments with shield condensation module
摘要：
针对蒸发冷却设备冬季存在的羽雾问题，搭建了盾形冷凝模块+混风腔消雾实验装置。采用Logistic分布函数对消光值与混风比关系的实验结果进行了拟合，平均拟合度为0.985 4。通过建立BP神经网络模型对出口羽雾的消光值进行了预测研究，并提出以消光值作为消雾效果的评价指标。预测结果表明，BP神经网络对消光值的预测精度较高，在95%的置信度下，30组消光预测值的相关系数、平均相对误差和均方根误差分别为0.998 99±0.000 08、(0.763 3±0.020 4)%和(6.441±0.222)×10-3。
Abstract：
According to the plume fog problem of evaporative cooling equipment in winter, builds a defogging experimental device with shield condensation module and mixed air chamber. The Logistic distribution function is used to fit the experimental results of the relationship between extinction value and mixed wind ratio, and the average fit degree is 0.985 4. The extinction value of the outlet plume fog is predicted by establishing a BP neural network model, and the extinction value is proposed as an evaluation index for the defogging effect. The prediction results show that the BP neural network has high prediction accuracy for extinction value, and the correlation coefficient, mean relative error and root mean square error of the 30 groups of extinction prediction values are 0.998 99±0.000 08, (0.763 3±0.020 4)% and (6.441±0.222)×10-3, respectively, under 95% confidence.
Keywords:shieldcondensationmodule;evaporationcoolingequipment;defogging;backpropagationneuralnetwork;extinctionvalue;prediction