应用模式识别的酒店冷水机组系统节能分析  

Energy-saving Analysis of Hotel Chiller System Based on Pattern Recognition

作　　者：谭时锴 徐成良[1] 陈焕新[1] 吴俊峰 TAN Shikai;XU Chengliang;CHEN Huanxin;WU Junfeng(School of Energy and Power Engineering,Huazhong University of Science and Technology,Wuhan 430074,Hubei,China;State Key Laboratory of Compressor Technology(Anhui Laboratory of Compressor Technology),Hefei 230031,Anhui,China)

机构地区：[1]华中科技大学能源与动力工程学院,湖北武汉430074 [2]压缩机技术国家重点实验室(压缩机技术安徽省实验室),合肥230031

出　　处：《制冷技术》2021年第4期48-56,共9页Chinese Journal of Refrigeration Technology

基　　金：国家自然科学基金(No.51576074,No.51328602);压缩机技术国家重点实验室(压缩机技术安徽省实验室)开放基金(No.SKL-YSJ201801)。

摘　　要：本文研究了模式识别技术在冷水机组系统节能分析方向的应用,采用聚类分析的方法,利用某酒店冷水机组系统的实际运行数据,分析了该系统可以采取的节能运行策略。对聚类后的数据进行相关性分析,结果表明:温度设定与3个天气变量的相关性很低,分别为0.11、0.03和0.23,因此用户应该随天气变化适当调整温度设定;能耗与1#压缩机和2#压缩机开启状态之间的相关性系数分别为0.99和0.36,因此相对于2#压缩机,要更多考虑1#压缩机的节能措施;定量得出6个聚类的节能潜力指标,依次为2.70、2.91、2.86、2.69、2.82和2.47。The application of pattern recognition technology in the energy-saving analysis of chiller system is studied in this paper. The actual operation data of a hotel chiller system is used to analyze the energy-saving operation strategy that the system can adopt with cluster analysis method. Correlation analysis is performed on the clustered data, and the results shows that the correlation coefficients between the temperature setting and the three weather variables are very low, which are 0.11, 0.03, and 0.23, respectively. So, the user should adjust the temperature setting more appropriately as the weather changes. The correlation coefficients between the energy consumption and the on-state of No. 1 and No. 2 compressors are 0.99 and 0.36, respectively. Therefore, compared with No. 2 compressor, energysaving measures should be more considered in the No. 1 compressor. In addition, the energy-saving potential indicators of the six clusters can be quantitatively derived, which are 2.70, 2.91, 2.86, 2.69, 2.82, 2.47, respectively.

关 键 词：数据挖掘 机器学习 聚类算法 模式识别 

分 类 号：TQ051.5[化学工程] TP391.9[自动化与计算机技术—计算机应用技术]