基于氛围感知的服装店照明环境设计研究  

Research on Lighting Environment Design of Clothing Stores Based on Atmosphere Perception

作　　者：熊晔 郝佳惠 XIONG Ye;HAO Jiahui(Tianjin Urban Construction Binhai Road&Bridge Co.,Ltd.,Tianjin 300350,China;School of Architecture and Art,Hebei University of Engineering,Handan 056038,China)

机构地区：[1]天津城建滨海路桥有限公司,天津300350 [2]河北工程大学建筑与艺术学院,河北邯郸056038

出　　处：《中国照明电器》2025年第2期57-63,共7页China Light & Lighting

摘　　要：本文研究了服装店的照明环境与氛围感知的影响规律,并提出照明环境优化建议。以1091家服装店作为研究对象,通过主客观调研收集数据,通过集成学习XGBoost极限梯度提升算法建立了两种多元回归预测模型,分别得出了氛围维度的重要性排序和各氛围维度下照明环境参数的重要性排序。采用SHAP法解释照明环境指标对氛围感知的贡献程度及影响规律。基于本文研究路径,总结出照明环境指标的优化建议区间。使用DIALux evo软件进行模拟分析表明,在3种灯具布置方式下,采用多种灯具组合布置可实现最佳的照明环境效果。This study investigates the impact of lighting environment and atmosphere perception in clothing stores,and proposes optimization suggestions for lighting environment.Using 1091 clothing stores as the research object,data was collected through subjective and objective surveys.Two multiple regression prediction models were established using the XGBoost extreme gradient enhancement algorithm based on ensemble learning.The importance ranking of the atmosphere dimension and the importance ranking of lighting environment parameters under each atmosphere dimension were obtained,respectively.Using SHAP method to explain the contribution and impact of lighting environmental indicators on atmosphere perception.Based on the research path of this article,summarize the optimization suggestions for lighting environment indicators.The simulation analysis using DIALux evo software shows that using multiple lamp combinations can achieve the best lighting environment effect under three lamp arrangement methods.

关 键 词：服装店 照明环境 氛围感知 XGBoost SHAP DIALux evo 

分 类 号：TU113.6[建筑科学—建筑理论]