Data partitioning and association mining for identifying VRF energy consumption patterns under various part loads and refrigerant charge conditions

详细信息    查看全文

• 作者：Guannan Li^a ; ^{leegna@163.com} ; Yunpeng Hu^b ; ^d ; Huanxin Chen^a ; ^{chenhuanxin@tsinghua.org.cn} ; Haorong Li^c ; Min Hu^a ; Yabin Guo^a ; Jiangyan Liu^a ; Shaobo Sun^a ; Miao Sun^a
• 关键词：Association rules mining ; Clustering analysis ; Energy consumption patterns ; Part load character ; Refrigerant charge fault ; Variable refrigerant flow air conditioning system
• 刊名：Applied Energy
• 出版年：2017
• 出版时间：1 January 2017
• 年：2017
• 卷：185
• 期：part_P1
• 页码：846-861
• 全文大小：4084 K
• 卷排序：185

文摘

Proposed a data mining based method analyzing VRF energy consumptions. 72 test conditions: 3 part load ratios, 8 refrigerant charges, 3 cooling conditions. Data clustering identifies 3 distinct energy consumption patterns. Association rules find undercharge, compressor frequency switch control patterns. Domain knowledge is used to interpret VRF energy consumption patterns and rules.