严寒地区住宅供暖季开窗行为研究  

Window Opening Behavior During the Heating Season in Severe Cold Region

作　　者：陈永康 李慧星[1] 冯国会[1] 宋博伦 CHEN Yongkang;LI Huixing;FENG Guohui;SONG Bolun(School of Municipal and Environmental Engineering,Shenyang Jianzhu University,Shenyang 110168,China)

机构地区：[1]沈阳建筑大学市政与环境工程学院,沈阳110168

出　　处：《建筑节能(中英文)》2025年第2期151-155,163,共6页Building Energy Efficiency

基　　金：“十三五”国家重点研发计划资助项目:“净零能耗建筑适宜技术研究与集成示范”(2019YFE0100300)。

摘　　要：开窗行为是影响建筑能耗和室内空气质量的一个关键因素。确定驱动因素并建立可靠的预测模型,对于提高建筑能耗模拟的准确性具有显著意义。以往研究主要集中在夏热冬冷地区,对严寒地区研究甚少,尤其是供暖季开窗行为会造成大量的热能损耗。在严寒地区城市选择4户具有代表性的住宅,进行为期5个月的供暖季监测。使用LightGBM算法建立供暖季住户窗口状态模型并与Logistic回归模型进行比较。结果表明,供暖季客厅和卧室的窗户操作存在差异。所建立的LightGBM模型对于供暖季不平衡的开窗数据具有良好的预测效果。研究结果为严寒地区建筑能耗模拟提供理论支持。Window opening behavior is a key factor affecting building energy consumption and indoor air quality.Identifying the driving factors and establishing reliable prediction models are of great significance for improving the accuracy of building energy consumption simulation.Previous studies mainly focused on hot summer and cold winter regions,while there is little research on severe cold regions,especially the window opening behavior during the heating season,which will cause a lot of heat loss.This study selected four representative residential buildings in a severe cold region city and monitored them for five months during the heating season.Establishing a window state model for households during the heating season using the LightGBM algorithm,and comparing it with the Logistic regression model.The results showed that there were differences in window operation between the living room and bedroom during the heating season.The established LightGBM model has a good prediction effect for imbalanced window opening data.The results of this study provide theoretical support for building energy consumption simulation in severe cold regions.

关 键 词：开窗行为 居住建筑 驱动因素 预测模型 

分 类 号：TU832[建筑科学—供热、供燃气、通风及空调工程]