基于径向基函数神经网络的严寒地区建筑能耗与舒适度优化研究

贺龙; 吕保; 马德宇

doi:10.13204/j.gyjzG21111518

基于径向基函数神经网络的严寒地区建筑能耗与舒适度优化研究

doi: 10.13204/j.gyjzG21111518

内蒙古工业大学建筑学院, 呼和浩特 010051

基金项目:

国家自然科学基金项目（51968054）；内蒙古自治区科技计划项目（2021GG0249）。

详细信息

作者简介:
贺龙,男,1984年出生,博士,教授。电子信箱:helongjianzhu@163.com

计量
- 文章访问数: 97
- HTML全文浏览量: 22
- PDF下载量: 5
- 被引次数: 0
出版历程
- 收稿日期: 2021-11-15
- 网络出版日期: 2023-12-18

Research on Multi-Objective Optimization of Building Energy Efficiency and Comfort Based on RBF Neural Network

College of Architecture, Inner Mongolia University of Technology, Hohhot 010051, China

摘要

摘要: 建筑形态作为建筑方案设计阶段需要重点考虑的设计因素，对建筑的多项性能指标有直接的影响。以严寒地区不同子气候区的气象参数为研究背景，将建筑形态分解为8个量化因子，以建筑能耗和基于ANSI/ASHRAE 55-2004《人类居住热环境条件》评价标准的建筑全年不舒适时间为优化指标，基于EnergyPlus仿真模拟平台获取评价指标的原始数据，引入径向基函数（RBF）神经网络建立影响因子与优化指标之间的快速反应模型，结合正交试验法分别对各研究地区的中小型办公建筑能耗与全年不舒适时间进行了单目标寻优计算，分析了严寒地区3个代表城市中小型办公建筑的形态因子对于不同优化指标的影响权重以及优化潜力，并进一步探究了各研究地区形态因子基于节能与舒适的最佳组合方案与最不利组合方案。结果表明：建筑形态的量化设计参数对于降低建筑能耗以及建筑的全年不舒适时间均有比较可观的优化潜力。
- 建筑形态 /
- 建筑节能 /
- 热舒适 /
- RBF神经网络
Abstract: Building morphology, as a design factor to be focused on in the design phase of building scheme, has a direct impact on several performance indicators of the building. The meteorological parameters of different sub-climatic zones in severe cold regions were used as the research background, and the building form was decomposed into 8 quantitative factors, and the building energy consumption and the annual discomfort time of the building based on Thermal Environmental Conditions for Human Occupancy(ANSI/ASHRAE 55-2004) evaluation standard were used as the optimization indexes. Based on the EnergyPlus simulation platform, the original data of the evaluation indexes was obtained, the radial basis function neural network was introduced to establish the rapid response model between the influencing factors and the optimization indexes, combined with the orthogonal test method, the single-objective optimization calculation of the building energy consumption and the annual discomfort time in each study area were carried out, and the influence weight and optimization potential of the three morphological factors representing urban buildings in severe cold regions on different optimization indexes were analyzed. The optimal combination of energy saving and comfort based on morphological factors in each study area was further investigated. The results showed that the quantitative design parameters of building morphology had considerable optimization potential for reducing building energy consumption and building discomfort time throughout the year.
- building form /
- building energy efficiency /
- thermal comfort /
- RBF neural network

HTML全文

参考文献(29)

[1]	PANG Z H, O'NEILL Z, LI Y F, et al.The role of sensitivity analysis in the building performance analysis:a critical review[J]. Energy and Buildings, 2020, 209:1-28.
[2]	LEBRUN J, ANDRE P. IEA annex 30:bringing simulation to application.final report[R].Liège:Laboratoire de Thermodynamique, Université de Liège,1998:5-126.
[3]	洪烽桓,傅绍辉,徐岩,等.建筑师主导下基于能耗模拟的建筑形体与空间组织节能设计研究:以北京市门头沟区体育文化中心为例[J].西部人居环境学刊,2020,35(6):40-48.
[4]	ABDOU N, MGHOUCHI Y E, HAMDAOUI S, et al. Multi-objective optimization of passive energy efficiency measures for net-zero energy building in Morocco[J]. Building and Environment, 2021, 204:108-124.
[5]	DELGARM N, SAJADI B, KOWSARY F, et al. Multi-objective optimization of the building energy performance:a simulation-based approach by means of particle swarm optimization (PSO)[J]. Applied Energy, 2016(170):293-303.
[6]	JAVANROODI K, NIK V M, ADL-ZARRABI B. A multi-objective optimization framework for designing climate-resilient building forms in urban areas[C/OL] IOP Conference Series:Earth and Environmental Science. IOP Publishing, 2020, 588(3). https://iopscience.iop.org/article/10.1088/1755-1315/588/3/032036/meta.
[7]	CHEN K W, JANSSEN P, SCHLUETER A. Multi-objective optimisation of building form, envelope and cooling system for improved building energy performance[J]. Automation in Construction, 2018, 94:449-457.
[8]	YUE N H, LI L L, Alessandro Morandi,et al.A metamodel-based multi-objective optimization method to balance thermal comfort and energy efficiency in a campus gymnasium[J/OL].Energy & Buildings,2021,253[2021-11-15].https://doi.org/10.1016/j.enbuild.2021.111513.
[9]	原野,郭彬彬,徐宗武,等.建筑形体光热性能耦合设计:以寒冷地区高校教学楼建筑为例[J].建筑师,2022(02):76-82.
[10]	唐小谦,陈焕新,郭亚宾.基于数据挖掘的多联机能耗预测[J].制冷技术,2020,40(3):8-12 +23.
[11]	李紫微,林波荣,陈洪钟.建筑方案能耗快速预测方法研究综述[J].暖通空调,2018,48(5):1-8.
[12]	季文娟,顾永松.基于PSO-RBF的建筑能耗预测模型研究[J].建筑节能,2015,43(11):109-112.
[13]	陈锐彬,李泽奇,黄永益.基于BP神经网络模型的大型公共建筑冷负荷预测[J].建设科技,2019(1):38-42.
[14]	杨柳.建筑节能综合设计[M].北京:中国建材工业出版社,2014.
[15]	张峙,李雯喆,应小宇.低能耗办公建筑标准层平面形态参数化研究[J].南方建筑,2019(1):76-81.
[16]	端木琳,王振江,李祥立,等.区域建筑形状对围护结构冷负荷的影响分析[J].土木建筑与环境工程,2011,33(增刊1):1-5.
[17]	王超,张伶伶,吕宵.低能耗目标下的北方高大空间公共建筑形体导控研究[J].建筑学报,2020(增刊1):38-43.
[18]	贺龙,吕保.基于太阳辐射得热的严寒地区中庭空间形态比较研究[J].建筑技术,2021,52(7):867-870.
[19]	徐燊,江海华,王江华.五种气候区条件下建筑窗墙比对建筑能耗影响的参数研究[J].建筑科学,2019,35(4):91-95 ,90.
[20]	中华人民共和国住房和城乡建设部.公共建筑节能设计标准:GB 50189-2015[S].北京:中国建筑工业出版社,2015.
[21]	张辉,韩啸霖,弓南,等.基于RBF与正交试验的高层住宅被动式节能设计多元因素分析[J].工业建筑,2021,51(4):46-52 ,19.
[22]	中华人民共和国住房和城乡建设部.办公建筑设计标准:JGJ/T 67-2019[S].北京:中国建筑工业出版社,2019.
[23]	朱丹丹,燕达,王闯,等.建筑能耗模拟软件对比:DeST、EnergyPlus and DOE-2[J].建筑科学,2012,28(增刊2):213-222.
[24]	中华人民共和国住房和城乡建设部.建筑节能气象参数标准:JGJ/T 346-2014[S].北京:中国建筑工业出版社,2014.
[25]	成雄蕾,王雯翡,张成昱,等.基于数据驱动的办公建筑电耗预测方法[J].建筑节能(中英文),2021,49(2):36-42.
[26]	莫程凯,邰可欣,邓深元,等.基于智能算法的PID控制参数优化策略[J].信息技术与信息化,2021(9):222-223,227.
[27]	ANSI. Thermal environmental conditions for human occupancy:ASHRAE 55-1981[S].Atlanta, USA:American Society of Heating, 1981.
[28]	ANSI.Thermal environmental conditions for human occupancy:ASHRAE 55-2004[S]. Atlanta, USA:American Society of Heating, 2004.
[29]	ANSI.Thermal environmental conditions for human occupancy:ASHRAE 55-2017[S]. Atlanta, USA:American Society of Heating, 2017.