[1]党向盈,姜代红.神经网络结合遗传算法在建筑优化设计中的应用[J].徐州工程学院学报(自然科学版),2017,(2):66-71.
 DANG Xiangying,JIANG Daihong.Application of Optimal Architectural Design Based on Genetic Algorithms(GA)and Neural Network[J].Journal of Xuzhou Institute of Technology(Natural Sciences Edition),2017,(2):66-71.
点击复制

神经网络结合遗传算法在建筑优化设计中的应用()
分享到:

《徐州工程学院学报》(自然科学版)[ISSN:1674-358X/CN:32-1789/N]

卷:
期数:
2017年第2期
页码:
66-71
栏目:
工程技术
出版日期:
2017-04-28

文章信息/Info

Title:
Application of Optimal Architectural Design Based on Genetic Algorithms(GA)and Neural Network
文章编号:
1674-358X(2017)02-0066-06
作者:
党向盈12姜代红2
1.中国矿业大学 信息与电气工程学院,江苏 徐州 221116; 2.徐州工程学院 江苏省智慧工业控制技术重点建设实验室,江苏 徐州 221018
Author(s):
DANG Xiangying12JIANG Daihong2
1.School of Information and Electrical Engineering, China University of Mining and Technology, Xuzhou 221116,China; 2.Jiangsu Key Laboratory of Smart Industrial Control Technology, Xuzhou Institute of Technology, Xuzhou221018, China
关键词:
遗传算法 神经网络 建筑设计 日照分析
Keywords:
genetic algorithms(GA) neural network architectural design analysis of sunlight
分类号:
TU972,TP399
文献标志码:
A
摘要:
采用遗传算法对建筑设计进行优化,是建筑设计领域一个全新的研究方向,然而,在日照分析下基于遗传算法求解最优值时,需要对每个进化个体进行适应度函数的计算,将消耗大量的运行时间.为了降低算法的复杂性,提出一种神经网络结合遗传算法的建筑优化设计方法.研究结果表明:与传统遗传算法对比,该方法可以有效降低算法的迭代次数和运行时间,提高建筑优化设计的效率.
Abstract:
Architectural design based on genetic algorithms(GA)is a new research direction.However,each individual fitness was calculated in the optimization based on GA program,which consumed large amounts of running time.In order to reduce the complexity of the algorithm, the paper puts forward a kind of building design method based on GA with neural networks.First,building a BP network trained by a certain amount of samples to simulate an the individual's fitness value; Then, roughly calculate the individual's fitness value by the trained BP network, and parse the value to the stand-by GA program; Finally, run the GA program, for the individuals with good estimated fitness values,their precise fitness value will be calculated again.As GA iterations go on,a precise fitness value will be got finally.The experimental results showed that the method could effectively reduce the number of iterations and the time consumption, so as to improve the efficiency of construction design.

参考文献/References:

[1] 方勇.高层民用建筑设计在绿色建筑设计中的应用[J].土木建筑与环境工程,2016,38(7):72-74.
[2] 殷惠光,姚青,李秉南.混凝土框架结构抗震加固设计若干问题的探讨[J].徐州工程学院学报,2006,21(6):1-4.
[3] 曹志明.生态住宅建筑设计探析[J].徐州工程学院学报(社会科学版),2006,21(7):63-65.
[4] 王学宛,张时聪,徐伟,等.超低能耗建筑设计方法与典型案例研究[J].建筑科学,2016,32(4):44-53.
[5] EVÍK L,LEPÍK P,PETRU M,et al.Modern methods of construction design[J].Lecture Notes in Mechanical Engineering,2014:209-233.
[6] THEODOSSIOU N,KOUGIAS I,KARAKATSANIS D.Optimal construction design using the harmony search algorithm as an optimization tool[C]// International Conference on Construction in the 21th Century.2015.
[7] 姜代红,刘一凡.基于分布估计算法的建筑结构设计优化[J].河北大学学报(自然科学版),2015,35(1):83-88.
[8] 王小平.遗传算法:理论应用与软件实现[M].西安:西安交通大学出版社,2002.
[9] FAGHIHI V,REINSCHMIDT K F,KANG J H.Construction scheduling using genetic algorithm based on building Information Model[J].Expert Systems with Applications,2014,41(16):7565-7578.
[10] TUHUS-DUBROW D,KRARTI M.Genetic-algorithm based approach to optimize building envelope design for residential buildings[J].Building & Environment,2010,45(7):1574-1581.
[11] 张岚.遗传算法在日照约束下拟建建筑极限容积计算中的应用[D].天津:河北工业大学,2006.
[12] 成三彬.建筑日照分析及日照约束下最大容积率的计算[D].淮南:安徽理工大学,2011.
[13] RUMELHART D E,MCCLELLAND J L.Parallel distributed processing[M].Cambridge,MA:MIT Press,1986.

相似文献/References:

[1]刘敬宇.改进自适应遗传模拟退火算法的结构优化设计[J].徐州工程学院学报(自然科学版),2011,(2):14.[doi:10.3969/j.issn.1674-358X.2011.02.006]
[2]田玉柱,刘越里,何万生,等.定数截尾Parato分布的遗传算法估计[J].徐州工程学院学报(自然科学版),2010,(3):67.[doi:10.3969/j.issn.1674-358X.2010.03.014]
 TIAN Yu-zhu,LIU Yue-li,HE Wan-sheng,et al.Estimation of Parato Distribution Based on Genetic Algorithm[J].Journal of Xuzhou Institute of Technology(Natural Sciences Edition),2010,(2):67.[doi:10.3969/j.issn.1674-358X.2010.03.014]
[3]吴树猛,张埂.一类指派问题的数学模型与算法研究[J].徐州工程学院学报(自然科学版),2010,(4):13.[doi:10.3969/j.issn.1674-358X.2010.04.004]
 WU Shu-meng,ZHANG Geng.Study on the Model and Algorithms for an Assignment Problem[J].Journal of Xuzhou Institute of Technology(Natural Sciences Edition),2010,(2):13.[doi:10.3969/j.issn.1674-358X.2010.04.004]
[4]堵锡华,朱锦锦,周荣婷,等.神经网络法应用于黄烷酮衍生物抗菌活性的理论研究.[J].徐州工程学院学报(自然科学版),2016,(3):17.
 DU Xihua,ZHU Jinjin,ZHOU Rongting,et al.The Theoretical Research on Fungicidal Activity of Flavanone Derivatives by Neural Network Method[J].Journal of Xuzhou Institute of Technology(Natural Sciences Edition),2016,(2):17.

备注/Memo

备注/Memo:
收稿日期:2017-04-12 基金项目:江苏省建设系统科技项目基金(2014JH18); 徐州市科技项目(KC15SH049); 住房和城乡建设部科学技术项目基金(2014-K5-027) 作者简介:党向盈(1978-),女, 副教授,博士研究生,主要从事建筑结构优化设计智能计算研究.
更新日期/Last Update: 1900-01-01