Analysis and evaluation of heat source data of large-scale heating system based on descriptive data mining techniques. (15th July 2022)

• Record Type: Journal Article
• Authors: Huang, Ke; Yuan, Jianjuan; Zhou, Zhihua; Zheng, Xuejing
• Is Part Of: Energy. Volume 251(2022)
• Publication Date: 2022-07-15
• Subjects: On-demand parameters -- Heat source -- Mathematical model -- Cluster analysis -- Association analysis; Power resources -- Periodicals; Power (Mechanics) -- Periodicals; Energy consumption -- Periodicals; 333.7905
• DOI: 10.1016/j.energy.2022.123834
• Languages: English
• ISSNs: 0360-5442

Abstract

Abstract: The on-demand parameters of heat source are the precondition for ensuring the safe, stable and energy-saving operation of heating system. For large-scale heating system, the existing predictive methods are not applicable due to the complexity of modeling, while the design heating load index method has many influencing factors, resulting in a low accuracy of obtaining accurate values. In this paper, firstly, the simplified mathematical model of the heating substation is built, and the calculation methods of under-demand rate ( η ) and energy-saving rate ( ς ) are proposed for diagnosis thermal balance and evaluation energy-saving potential. Secondly, the variation relationship among heat source parameters is analyzed and the input parameters of the analysis process are determined, then cluster analysis is adopted to identify the operation strategy, and non-on-demand clusters are eliminated from the perspective of professional knowledge. Thirdly, the data in the remaining clusters are discretized, association analysis is used to obtain the frequent item-sets of each cluster, and on-demand heating parameters of each cluster are obtained. Finally, η and ς are used to evaluate the object heating system. This application reveals that the descriptive data mining techniques combined with professional knowledge can successfully identify the on-demand parameters from the historical data of heat source. Highlights: Operation model of the heating substation is built. Evaluation indexes are proposed for diagnosis thermal balance and evaluation energy-saving potential. Cluster analysis is used to identify operation strategy. Association analysis is used to obtain on-demand parameters.