基于性能遮阳设计的混合机器学习和优化工具的开发
Development of a hybrid machine-learning and optimization tool for performance-based solar shading design
摘要:
遮阳设计应在设计初期就进行,以达到室内环境质量的要求。这个领域可能非常具有挑战性和耗时,还需要专家,复杂的软件和大量的资金。这项研究的主要目的是设计一个简单的工具来研究各种太阳阴影模型,并在早期阶段更容易、更快地做出决策。数据库生成方法、人工智能和优化已被用于实现这一目标。该工具包括两个主要部分1.预测用户选择的模型的性能以及提出有效参数;以及2.向用户建议最佳的预先准备的模型。在这方面,最初,一个侧光鞋盒模型与可变参数进行了参数化建模,五个常见的遮阳模型及其变量应用于空间。对于每个遮阳和没有遮阳的状态,模拟与日光和眩光、视图和初始成本相关的指标。在这项研究中产生的数据库包括87912个替代品和六个计算的度量引入到优化的机器学习模型,包括神经网络,随机福雷斯特,支持向量回归,k最近邻。根据结果,最准确和最快的估计模型是Random Forrest,r2_score为0.967至1。然后,进行敏感性分析,以确定最有影响力的参数为每个遮阳模型和状态没有它。该分析区分最有效的参数,包括窗口方向,WWR,房间的宽度,长度和遮阳深度。最后,通过NSGA II算法优化机器学习模型的估计函数,识别出约7300个最优模型。开发的工具可以在不到几秒钟的时间内评估各种设计方案。
英文摘要:
Solar shading design should be done for the desired Indoor Environmental Quality (IEQ) in the early design stages. This field can be very challenging and time-consuming also requires experts, sophisticated software, and a large amount of money. The primary purpose of this research is to design a simple tool to study various models of solar shadings and make decisions easier and faster in the early stages. Database generation methods, artificial intelligence, and optimization have been used to achieve this goal. This tool includes two main parts of 1. predicting the performance of the user-selected model along with proposing effective parameters and 2. proposing optimal pre-prepared models to the user. In this regard, initially, a side-lit shoebox model with variable parameters was modeled parametrically, and five common solar shading models with their variables were applied to the space. For each solar shadings and the state without shading, metrics related to daylight and glare, view, and initial costs were simulated. The database generated in this research includes 87912 alternatives and six calculated metrics introduced to optimized machine learning models, including neural network, random Forrest, support vector regression, and k nearest neighbor. According to the results, the most accurate and fastest estimation model was Random Forrest, with an r2_score of 0.967 to 1. Then, sensitivity analysis was performed to identify the most influential parameters for each shading model and the state without it. This analysis distinguished the most effective parameters, including window orientation, WWR, room width, length, and shading depth. Finally, by optimizing the estimation function of machine learning models with the NSGA II algorithm, about 7300 optimal models were identified. The developed tool can evaluate various design alternatives in less than a few seconds for each.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。