大型集中供热系统热力站耗热量基准研究  

Heat Consumption Benchmark of Thermal Power Station of Large-scale Central Heating System

作　　者：孙春华[1] 冯浩宇 高晓宇 曹姗姗 夏国强[1] SUN Chun-hua;FENG Hao-yu;GAO Xiao-yu;CAO Shan-shan;XIA Guo-qiang(School of Energy and Environmental Engineering,Hebei University of Technology,Tianjin 300400,China)

机构地区：[1]河北工业大学能源与环境工程学院,天津300400

出　　处：《建筑节能（中英文）》2022年第12期9-15,共7页Building Energy Efficiency

基　　金：住房和城乡建设部科技示范项目(2019-2-167)。

摘　　要：以某大型集中供热系统热力站耗热量数据为对象,采用箱线图法及洛伦兹曲线法相结合研究耗热量基准模型建立方法,通过建立每一类热力站耗热量基准模型获得基准值。通过K-means聚类算法及DBSCAN聚类算法对热力站耗热量数据中的异常值及离群值进行辨识,得出采用DBSCAN聚类算法对异常值数据敏感;对预处理后的数据采用统计分析的方式进行热力站耗热量数据分类,其中热力站数量较少的类别采用箱线图法建立耗热量基准模型并得到基准值,热力站数量较多的类别采用基于洛伦兹曲线的方式建立热力站的能耗基准模型并得到经验公式,通过两种方法建立的热力站耗热量基准模型可为后续热力站耗热量的节能潜力分析提供重要依据。This paper takes the heat consumption data of a large-scale central heating system thermal station as the object,uses the box plot method and the Lorentz curve method to study the method of establishing the heat consumption benchmark model,and obtains the benchmark value by establishing the heat consumption benchmark model of each type of thermal station.First,the K-means clustering algorithm and the DBSCAN clustering algorithm are used to identify the outliers and outliers in the heat consumption data of the thermal station,and it is concluded that the DBSCAN clustering algorithm is sensitive to the outlier data;the preprocessed data is used the method of statistical analysis is used to classify the heat consumption data of thermal power stations.Among them,the category with a small number of thermal stations uses the box plot method to establish a reference model of heat consumption and obtain the reference value,and the category with a large number of thermal stations uses the method based on the Lorentz curve.The energy consumption benchmark model of the thermal power station is established and the empirical formula is obtained.The benchmark heat consumption model of the thermal power station established by the two methods can provide an important basis for the subsequent analysis of the energy-saving potential of the heat power consumption of the thermal power station.

关 键 词：热力站耗热量基准 数据预处理 聚类算法 箱线图法 洛伦兹曲线法 

分 类 号：TU83[建筑科学—供热、供燃气、通风及空调工程]