中国电机工程学报2018，Vol.38Issue(5)：1518-1524,后插26,8.DOI:10.13334/j.0258-8013.pcsee.170408
考虑属性重要度的空冷系统背压特性模型
Back Pressure Model of the Direct Air-cooling System Considering Attribute Significance
摘要
Abstract
The direct air-cooling condenser is more sensitive to the changing of various boundary conditions than the traditional water-cooling system. By considering the significance of each attributes, a back pressure model was built with the practical operating data. The historical data in one-month operation was used to calculate the weight of each condition attributes based on fuzzy rough sets (FRS). The weighted support vector regression (SVR) method was introduced to build the regression model. The result shows that the condition attributes, consisting of mass flowrate and pressure of main steam, ambient temperature, frequency of air fan, wind speed and atmospheric pressure, well reflect the back pressure with a RMSE of 0.70kPa in July and 0.76kPa in October; the weighting process would improve the generalization ability and reduce the computation consumption without decreasing the accuracy.关键词
直接空冷系统/背压/属性重要度/加权支持向量回归/模糊粗糙集Key words
direct air-cooling system/back pressure/attributes significant/weighted support vector regression/fuzzy rough sets分类
能源科技引用本文复制引用
李晓恩,王宁玲,张雨檬,杨志平,杨勇平..考虑属性重要度的空冷系统背压特性模型[J].中国电机工程学报,2018,38(5):1518-1524,后插26,8.基金项目
国家重点基础研究发展计划项目(973 计划) (2015CB251505) （973 计划）
中央高校基本科研业务费专项资金项目(2015MS43, 2015XS81,2014XS19,2014XS13). The National Basic Research Program (973 Program) (2015CB251505) （2015MS43, 2015XS81,2014XS19,2014XS13）
Fundamental Research Funds for the Central Universities (2015MS43, 2015XS81, 2014XS19, 2014XS13). （2015MS43, 2015XS81, 2014XS19, 2014XS13）
