基于数据挖掘技术的地铁站环控系统用能诊断
|
摘要
本文提出了一种地铁站环控系统用能诊断方法,通过数据挖掘技术建立评价模型来评价地铁环控系统的用能特性。首先,通过相关性分析,确定影响地铁环控系统能耗的关键变量:室外温度、客流量;其次,根据所选取的关键变量,采用决策树划分不同的用能模式,进而根据各个模式建立相应的的用能基准;最后,根据不同模式的用能基准对地铁环控系统实际运行数据进行用能诊断。诊断结果表明:环境和客流的变化会引起用能水平的波动,但仍然贴近用能基准。该用能诊断方法能够诊断地铁站用能、识别异常用能模式和识别低能耗的用能模式,有助于地铁站运营漏洞、故障排查和环控模式优化,为单个地铁站的节能工作提供理论依据和实际参考。
This paper proposes an energy consumption diagnosis method and establishes an evaluation model based on data mining technology to evaluate the condition of energy utilization of HVAC system in subway stations. Firstly,through the correlation analysis,the key variables that influence the energy consumption of the subway environmental control system are determined: outdoor temperature and passenger flows. Then,according to the selected key variables,different energy utilization modes are generated by using the decision tree and after that the energy benchmark is established on the basis of the energy consumption models. Finally,an energy consumption diagnosis method based on the energy benchmark of different energy utilization models is used in actual data of HVAC system. The results of energy consumption diagnosis show that energy levels can be influenced by the change of environment and passenger flow but still conform to energy benchmark. This energy consumption diagnosis method can diagnose the condition of energy utilization and recognize models of abnormal or low energy consumption,which can optimize energy utilization and provide a theoretical basis and practical reference value for the energy saving a of single subway station.
This paper proposes an energy consumption diagnosis method and establishes an evaluation model based on data mining technology to evaluate the condition of energy utilization of HVAC system in subway stations. Firstly,through the correlation analysis,the key variables that influence the energy consumption of the subway environmental control system are determined: outdoor temperature and passenger flows. Then,according to the selected key variables,different energy utilization modes are generated by using the decision tree and after that the energy benchmark is established on the basis of the energy consumption models. Finally,an energy consumption diagnosis method based on the energy benchmark of different energy utilization models is used in actual data of HVAC system. The results of energy consumption diagnosis show that energy levels can be influenced by the change of environment and passenger flow but still conform to energy benchmark. This energy consumption diagnosis method can diagnose the condition of energy utilization and recognize models of abnormal or low energy consumption,which can optimize energy utilization and provide a theoretical basis and practical reference value for the energy saving a of single subway station.
引文
[1]常莉,冯炼,李鹏.地铁环控系统不同区域能耗分析[J].制冷与空调(四川),2009,23(5):115-118.(CHANG Li,FENG Lian,LI Peng.Energy consumption analysis of different areas on subway ECS[J].Refrigeration and Air Conditioning,2009,23(5):115-118.)
[2]WANG Yongcai,FENG Haoran,XI Xiangyu.Sense,model and identify the load signatures of HVAC systems in metro stations[R].National Harbor,MD,United States:2014 IEEE Power and Energy Society General Meeting,2014.
[3]WANG Yongcai,FENG Haoran,QI Xiao.SEED:public energy and environment dataset for optimizing HVAC operation in subway stations[R].National Harbor,MD,United States:2014 IEEE Power and Energy Society General Meeting,2014.
[4]ZHU Yingxin,QIN Ouyang.Airflow fluctuationsandthermal environment:A literature review[R].Beijing:The 4 th International Symposium on Heating,Ventilating and Air Conditioning,2003:78-86.
[5]朱颖心,秦绪忠,江亿.站台屏蔽门在地铁热环境控制中的经济性分析[J].建筑科学,1997(4):21-25.(ZHU Yingxin,QIN Xuzhong,JIANG Yi.Economic analysis for platform screen door in subway thermal environment control[J].Building Science,1997(4):21-25.)
[6]江亿.从实际运行数据出发开展地铁站节能工作[R].北京:清华大学,2015.(JIANG Yi.Carrying out energysaving work in subway stations based on actual operating data[R].Beijing:Tsinghua University,2015.)
[7]石静雅,苏永清,岳继光.轨道交通能耗影响因素分析及能耗评价体系的建立[J].铁道运输与经济,2008,30(9):46-49.(SHI Jingya,SU Yongqing,YUE Jiguang.The analysis of influence factors in energy consumption of railway transportand theestablishment of the energy evaluation system[J].Railway Transport and Economy,2008,30(9):46-49.)
[8]孙宁,李照星,戴华明.城市轨道交通能耗指标体系与节能措施研究——设备监理在节能减排中的创新实践[J].设备监理,2011(1):15-22.(SUN Ning,LI Zhaoxing,DAI Huaming.The study of energy consumption index system and energy saving measure of urban rail transit:the innovation practice of the equipment supervision in energysaving emission reduction[J].Plant Engineering Consultants,2011(1):15-22.)
[9]郑玲芳.上海市轨道交通规划环评能耗指标体系初探[J].环境科学与技术,2013,36(12):402-405.(ZHENG Lingfang.The enengy index system of shanghai urban transit rail instrategy environmental assessment[J].Environmental Science&Technology,2013,36(12):402-405.)
[10]陈焕新,刘江岩,胡云鹏,等.大数据在空调领域的应用[J].制冷学报,2015,36(4):16-22.(CHEN Huanxin,LIU Jiangyan,HU Yunpeng,et al.Application of big data in air-conditioning field[J].Journal of Refrigeration,2015,36(4):16-22.)
[11]QUINLAN J R.Induction of decision trees[J].Machine learning,1986,1(1):81-106.
[12]谢妞妞,刘於勋.决策树属性选择标准的改进[J].计算机工程与应用,2010,46(34):115-118.(XIE Niuniu,LIU Yuxun.Improvement of attribute selection criterion of decision trees[J].Computer Engineering and Applications,2010,46(34):115-118.)
[13]QUINLAN J R.C4.5:programs for machine learning[M].Elsevier,2014.
[14]BREIMAN L,FRIEDMAN J H,OLSHEN R A,et al.Classification and regression trees[M].CRC Press,1984.
[15]MEHTA M,AGRAWAL R,RISSANEN J.SLIQ:A fast scalable classifier for data mining[C]//International Conference on Extending Database Technology.Springer Berlin Heidelberg,1996.
[16]PARK H S,LEE M,KANG H,et al.Development of a new energy benchmark for improving the operational rating system of office buildings using various data-mining techniques[J].Applied Energy,2016,173:225-237.
[2]WANG Yongcai,FENG Haoran,XI Xiangyu.Sense,model and identify the load signatures of HVAC systems in metro stations[R].National Harbor,MD,United States:2014 IEEE Power and Energy Society General Meeting,2014.
[3]WANG Yongcai,FENG Haoran,QI Xiao.SEED:public energy and environment dataset for optimizing HVAC operation in subway stations[R].National Harbor,MD,United States:2014 IEEE Power and Energy Society General Meeting,2014.
[4]ZHU Yingxin,QIN Ouyang.Airflow fluctuationsandthermal environment:A literature review[R].Beijing:The 4 th International Symposium on Heating,Ventilating and Air Conditioning,2003:78-86.
[5]朱颖心,秦绪忠,江亿.站台屏蔽门在地铁热环境控制中的经济性分析[J].建筑科学,1997(4):21-25.(ZHU Yingxin,QIN Xuzhong,JIANG Yi.Economic analysis for platform screen door in subway thermal environment control[J].Building Science,1997(4):21-25.)
[6]江亿.从实际运行数据出发开展地铁站节能工作[R].北京:清华大学,2015.(JIANG Yi.Carrying out energysaving work in subway stations based on actual operating data[R].Beijing:Tsinghua University,2015.)
[7]石静雅,苏永清,岳继光.轨道交通能耗影响因素分析及能耗评价体系的建立[J].铁道运输与经济,2008,30(9):46-49.(SHI Jingya,SU Yongqing,YUE Jiguang.The analysis of influence factors in energy consumption of railway transportand theestablishment of the energy evaluation system[J].Railway Transport and Economy,2008,30(9):46-49.)
[8]孙宁,李照星,戴华明.城市轨道交通能耗指标体系与节能措施研究——设备监理在节能减排中的创新实践[J].设备监理,2011(1):15-22.(SUN Ning,LI Zhaoxing,DAI Huaming.The study of energy consumption index system and energy saving measure of urban rail transit:the innovation practice of the equipment supervision in energysaving emission reduction[J].Plant Engineering Consultants,2011(1):15-22.)
[9]郑玲芳.上海市轨道交通规划环评能耗指标体系初探[J].环境科学与技术,2013,36(12):402-405.(ZHENG Lingfang.The enengy index system of shanghai urban transit rail instrategy environmental assessment[J].Environmental Science&Technology,2013,36(12):402-405.)
[10]陈焕新,刘江岩,胡云鹏,等.大数据在空调领域的应用[J].制冷学报,2015,36(4):16-22.(CHEN Huanxin,LIU Jiangyan,HU Yunpeng,et al.Application of big data in air-conditioning field[J].Journal of Refrigeration,2015,36(4):16-22.)
[11]QUINLAN J R.Induction of decision trees[J].Machine learning,1986,1(1):81-106.
[12]谢妞妞,刘於勋.决策树属性选择标准的改进[J].计算机工程与应用,2010,46(34):115-118.(XIE Niuniu,LIU Yuxun.Improvement of attribute selection criterion of decision trees[J].Computer Engineering and Applications,2010,46(34):115-118.)
[13]QUINLAN J R.C4.5:programs for machine learning[M].Elsevier,2014.
[14]BREIMAN L,FRIEDMAN J H,OLSHEN R A,et al.Classification and regression trees[M].CRC Press,1984.
[15]MEHTA M,AGRAWAL R,RISSANEN J.SLIQ:A fast scalable classifier for data mining[C]//International Conference on Extending Database Technology.Springer Berlin Heidelberg,1996.
[16]PARK H S,LEE M,KANG H,et al.Development of a new energy benchmark for improving the operational rating system of office buildings using various data-mining techniques[J].Applied Energy,2016,173:225-237.