开放办公空间智能遮阳百叶天然采光眩光预测模型建构研究  

Research on the Construction of Glare Prediction Model for Daylighting with Intelligent Sunshade Louvers in Open Office Spaces

作　　者：骆肇阳 齐轩宁 董琪[1,2] LUO Zhaoyang;QI Xuanning;DONG Qi(School of Architecture and Design,Harbin Institute of Technology,Harbin 150000,China;Key Laboratory of Cold Region Urban and Rural Human Settlement Environment Science and Technology,Ministry of Industry and Information Technology,Harbin 150000,China)

机构地区：[1]哈尔滨工业大学建筑设计学院,黑龙江哈尔滨150000 [2]寒地城乡人居环境科学与技术工业和信息化部重点实验室,黑龙江哈尔滨150000

出　　处：《照明工程学报》2024年第4期69-80,共12页China Illuminating Engineering Journal

基　　金：国家自然科学基金青年项目(52008129);哈尔滨工业大学助理教授科研启动项目“基于机器学习的办公建筑室内天然采光智能调控研究”(AUGA5630109423);中央高校基本科研任务费专项资助(HIT.DZJJ.2023083)。

摘　　要：在多窗户、多区域的开放办公空间中,利用智能遮阳百叶对天然采光引发的眩光进行调控具有挑战性,既需协同不同区域视觉舒适性最佳,又需考虑不同百叶遮阳形式下的复合影响效应。受惠人工智能技术浪潮,采用机器学习算法建构有效的眩光预测模型成为解决开放办公空间智能遮阳百叶眩光调控的有力手段。基于此,本研究通过相关实验,对不同机器学习算法的眩光预测模型建构性能进行综合对比,得出最佳机器学习算法,以实现有效开放办公空间智能遮阳百叶天然采光眩光预测模型的建构。In multi-window and multi-zone an open office spaces,it is challenging to regulate the glare caused by natural daylighting using intelligent sunshade louvers.It is necessary to coordinate the best visual comfort in different areas and also consider the combined influence effects under different sunshade forms of louvers.Benefiting from the wave of artificial intelligence technology,using machine learning algorithms to construct effective glare prediction models has become a powerful means to solve the glare regulation of intelligent sunshade louvers in open office spaces.Based on this,through relevant experiments,this study comprehensively compares the construction performance of glare prediction models of different machine learning algorithms and obtains the best machine learning algorithm to achieve the construction of an effective glare prediction model for natural daylighting with intelligent sunshade louvers in open office spaces.

关 键 词：智能遮阳 眩光调控 眩光预测模型 机器学习 

分 类 号：TU243.2[建筑科学—建筑设计及理论]