Overall Layout Method of Frame Structure Plane Based on Generative Adversarial Network

ZHONG Yan; LEI Xin; LONG Danbing; FANG Changjian; KANG Yongjun

doi:10.12454/j.jsuese.202300661

您当前的位置：

首页 >

文章列表页 >

Overall Layout Method of Frame Structure Plane Based on Generative Adversarial Network

GREEN BUILDING AND SMART CONSTRUCTION | 更新时间：2026-01-24

- Overall Layout Method of Frame Structure Plane Based on Generative Adversarial Network
  增强出版
- Advanced Engineering Sciences Vol. 57, Issue 3, Pages: 72-81(2025)
- 作者机构：
  
  1.西南交通大学土木工程学院，四川成都 610031
  2.中国建筑西南设计研究院有限公司，四川成都 610041
- 作者简介：
- 基金信息：
- DOI：10.12454/j.jsuese.202300661
  CLC： TU375.4
- Received：24 August 2023，
  
  Published：20 May 2025
- 稿件说明：
移动端阅览
钟燕,雷昕,龙丹冰,等.基于生成对抗网络的框架结构平面整体布置方法[J].工程科学与技术,2025,57(3):72‒81.

Zhong Yan,Lei Xin,Long Danbing,et al.Overall layout method of frame structure plane based on generative adversarial network[J].Advanced Engineering Sciences,2025,57(3):72‒81.
钟燕,雷昕,龙丹冰,等.基于生成对抗网络的框架结构平面整体布置方法[J].工程科学与技术,2025,57(3):72‒81. DOI： 10.12454/j.jsuese.202300661.

Zhong Yan,Lei Xin,Long Danbing,et al.Overall layout method of frame structure plane based on generative adversarial network[J].Advanced Engineering Sciences,2025,57(3):72‒81. DOI： 10.12454/j.jsuese.202300661.

摘要

建筑改建或增建时的结构设计是房屋结构设计中不容忽视的内容。本文面向建筑初步设计阶段，针对部分结构已确定的情况提出了基于生成对抗网络的框架结构平面整体布置方法，在建筑和部分结构双重约束条件下进行框架结构设计。该方法的核心为框架结构平面整体布置模型。在有限数据样本下，为减少模型训练参数，凝练样本特征，达到更好的模型训练效果，提出了建筑信息表达方法用于表达与结构特征有强关联性的建筑特征；提出了框架梁信息表达方法用于在平面图形中表达梁截面特征；提出框架柱信息表达方法用于在平面图形中表达柱截面特征。通过叠加特征图、裁剪和增广等手段，构造了用于训练生成式算法模型的5 120对数据作为数据集。同时，除沿用交并比评价指标外，为更合理地评价模型的“设计”能力，基于框架结构设计规则提出了原柱率、不合理指数和综合指标，并依据指标确定了最佳的框架结构平面整体布置模型。使用时将建筑和部分结构特征图输入最佳模型，即可生成框架结构平面布置图。最后，通过案例分析论证了本文提出的框架结构平面整体布置方法能快速地生成布置合理且满足经验要求的结构设计。

Abstract

Objective

In the process of architectural renovation or expansion

structural design is a crucial aspect of building design. After the initial completion of the scheme design

architects often need to consider the compatibility between the architecture and its structure. Therefore

early intervention and immediate response in the structural scheme design are urgently needed. In this paper

addressing the preliminary design phase of architecture and focusing on situations where parts of the structure have already been determined

we propose a framework for the overall layout of the structural plan based on a Generative Adversarial Network (GAN)

termed PF‒structGAN. This framework facilitates the design of the structural framework under the dual constraints of both architectural forms and predetermined structural elements. The core of this method involves constructing a model for the overall layout of the structural plan

which includes three main stages: constructing datasets

training and evaluating the model

and applying the model.

Methods

In the dataset construction stage

due to the limited number of data samples

and to reduce model training parameters

refine sample features

and improve training outcomes

this paper proposes three information representation methods for architecture

beams

and columns. It utilizes RGB color channels to store information separately: architectural space information is stored in the blue channel (B)

beam information in the green channel (G)

and column information in the red channel (R)

thereby avoiding feature overlap in overlapping regions. The architectural information representation method is used to express architectural features strongly correlated with structural features. The beam information representation method is designed to express beam cross-sectional features in planar graphics. The column information representation method is designed to express column cross-sectional features in planar graphics. These three methods establish correlations between architectural and structural features. To integrate architectural and structural features

the feature maps are superimposed. The architectural feature map

partial beam feature map

and partial column feature map are superimposed to obtain the architectural and partial structural feature map. The beam and column feature maps are superimposed to obtain the structural feature map. The architectural and partial structural

feature map

along with the structural feature map

constitute a pair of feature superposition maps. To address the problem that column features occupy too few pixels in the image

and to help the model learn these features more effectively

the paired feature superposition maps are cropped into four parts to increase the column feature ratio. Further augmentation of the original dataset is achieved by rotating it at 0°

90°

180°

and 270°

resulting in an expanded dataset. In the model training phase

the architectural and partial structural feature maps are used as constraint conditions

and the real structural feature maps are used as labels. The generator produces structural feature maps under the given constraints. The discriminator determines whether the generated image is real or synthetic. Through adversarial training

the generator and discriminator iteratively improve until reaching a Nash equilibrium. In the model evaluation phase

to assess the model’s design capability more reasonably

in addition to using the intersection over union (IoU) metric

this paper proposes the original column ratio index (

)

the irrationality index (

)

and the comprehensive index (

all

) based on practical experience and frame structure design rules. These indicators comprehensively evaluate the model’s capability to produce an overall frame structure layout.

evaluates the retention of frame columns generated by the model at their original input positions—the higher the ratio

the better the design compliance.

evaluates the distribution of columns across different building components and spaces—the lower the index

the more reasonable the arrangement.

all

integrates the above indicators—the higher the value

the more reasonable the structural layout. The best-performing model is determined based on these four indicators. Once the PF‒structGAN mode

l is trained

the architectural and partial structure feature maps are input into the optimal model to generate a frame structure layout.

Results and Discussions

A total of 5 120 dataset pairs were created for training the generative model—4 320 for training and 800 for testing. The training set was input into the pix2pixHD framework

and training was stopped once adversarial training reached a Nash equilibrium. Model performance was evaluated using the four indicators. The IoU curve showed a general upward trend as training epochs increased. After the first epoch

remained at 1.

generally trended downward.

all

peaked at epoch 26; therefore

the model from the 26th epoch was selected as the best layout model. To verify the model’s structural design capability

an instance analysis was conducted using a teaching building project. The IoU between the model’s design and the engineer’s design was 0.56

indicating high similarity.

was 1

showing full retention of original column positions.

was 1.78

indicating a reasonable arrangement of columns.

all

reached 0.88

suggesting that the generated structural layout was sound. The model’s generated frame columns met functional requirements

were well-placed

and had appropriate size and density. The layout of columns and beams closely resembled the engineer’s design.

Conclusions

This method enables intelligent and rapid generation of structural designs that comply with regulatory standards and follow conventional design practices. It offers reference solutions for architects during the structural design process.

关键词

Keywords

references

王蒙徽 . 实施城市更新行动 [EB/OL ] .( 2020‒12‒29 )[ 2025‒04‒10 ] . http://www.gov.cn/xin-wen/2020-12/29/content_5574417.htm http://www.gov.cn/xin-wen/2020-12/29/content_5574417.htm . doi: 10.3969/j.issn.1002-0454.2021.01.001 http://dx.doi.org/10.3969/j.issn.1002-0454.2021.01.001

住房城乡建设部 . 关于在实施城市更新行动中防止大拆大建问题的通知 [EB/OL ] .( 2021‒08‒31 )[ 2025‒04‒10 ] . https://www.gov.cn/zhengce/zhengceku/2021-08/31/conte-nt_563 4560.htm https://www.gov.cn/zhengce/zhengceku/2021-08/31/conte-nt_5634560.htm . doi: 10.3969/j.issn.1009-7767.2021.10.001 http://dx.doi.org/10.3969/j.issn.1009-7767.2021.10.001

Cheng Guozhong , Zhou Xuhong , Liu Jiepeng , et al . Intelligent design method of high-rise shear wall structures based on deep reinforcement learning [J ] . Journal of Building Structures , 2022 , 43 ( 9 ): 84 ‒ 91 .

程国忠 , 周绪红 , 刘界鹏 , 等 . 基于深度强化学习的高层剪力墙结构智能设计方法 [J ] . 建筑结构学报 , 2022 , 43 ( 9 ): 84 ‒ 91 .

Zhang Yu , Mueller C . Shear wall layout optimization for conceptual design of tall buildings [J ] . Engineering Structures , 2017 , 140 : 225 ‒ 240 . doi: 10.1016/j.engstruct.2017.02.059 http://dx.doi.org/10.1016/j.engstruct.2017.02.059

Tafraout S , Bourahla N , Bourahla Y , et al . Automatic structural design of RC wall-slab buildings using a genetic algorithm with application in BIM environment [J ] . Automation in Construction , 2019 , 106 : 102901 . doi: 10.1016/j.autcon.2019.102901 http://dx.doi.org/10.1016/j.autcon.2019.102901

Zhou Xuhong , Wang Lufeng , Liu Jiepeng , et al . Automated structural design of shear wall structures based on modified genetic algorithm and prior knowledge [J ] . Automation in Construction , 2022 , 139 : 104318 . doi: 10.1016/j.autcon.2022.104318 http://dx.doi.org/10.1016/j.autcon.2022.104318

Lou Haopeng , Gao Boqing , Jin Fengling , et al . Shear wall layout optimization strategy for high-rise buildings based on conceptual design and data-driven tabu search [J ] . Computers & Structures , 2021 , 250 : 106546 . doi: 10.1016/j.compstruc.2021.106546 http://dx.doi.org/10.1016/j.compstruc.2021.106546

Lu Xinzheng , Liao Wenjie , Gu Donglian , et al . Research progress on building structural design methods:From simulation-based to artificial intelligence-based [J ] . Engineering Mechanics , 2025 , 42 ( 3 ): 1 ‒ 17 .

陆新征 , 廖文杰 , 顾栋炼 , 等 . 从基于模拟到基于人工智能的建筑结构设计方法研究进展 [J ] . 工程力学 , 2025 , 42 ( 3 ): 1 ‒ 17 .

Turhan C G , Bilge H S . Recent trends in deep generative models:A review [C ] // Proceedings of the 2018 3rd International Conference on Computer Science and Engineering (UBMK) . Sarajevo : IEEE , 2018 : 574 ‒ 579 . doi: 10.1109/ubmk.2018.8566353 http://dx.doi.org/10.1109/ubmk.2018.8566353

Abdollahi B , Nasraoui O . Explainable restricted Boltzmann machines for collaborative filtering [EB/OL ] .( 2016‒06‒12 )[ 2025‒04‒10 ] . https://arxiv.org/abs/1606.07129v1 https://arxiv.org/abs/1606.07129v1 . doi: 10.1145/2872518.2889405 http://dx.doi.org/10.1145/2872518.2889405

Salakhutdinov R , Larochelle H . Efficient learning of deep Boltzmann machines [C ] // Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics . Cagliari : JMLR , 2010 : 693 ‒ 700 .

Hinton G E , Zemel R . Autoencoders,minimum description length and Helmholtz free energy [C ] // NIPS’93: Proceedings of the 7th International Conference on Neural Information Processing Systems . Denver : Morgan Kaufmann Publishers Inc. , 1993 : 3 ‒ 10 .

Kingma D P , Welling M . Auto-encoding variational Bayes [EB/OL ] .( 2013‒12‒20 )[ 2025‒04‒10 ] . https://arxiv.org/abs/1312.6114v11 https://arxiv.org/abs/1312.6114v11 . doi: 10.1561/2200000056 http://dx.doi.org/10.1561/2200000056

van den Oord A , Kalchbrenner N , Vinyals O , et al . Conditional image generation with PixelCNN decoders [C ] // NIPS’16: Proceedings of the 30th International Conference on Neural Information Processing Systems , 2016 : 4797 ‒ 4805 .

van D O A , Kalchbrenner N , Kavukcuoglu K . Pixel recurrent neural networks [C ] // International Conference on Machine Learning . New York : PMLR , 2016 : 1747 ‒ 1756 .

Goodfellow I , Pouget‒Abadie J , Mirza M , et al . Generative adversarial networks [J ] . Communications of the ACM , 2020 , 63 ( 11 ): 139 ‒ 144 . doi: 10.1145/3422622 http://dx.doi.org/10.1145/3422622

Mirza M , Osindero S . Conditional generative adversarial Nets [EB/OL ] .( 2014‒11‒06 )[ 2025‒04‒10 ] . https://arxiv.org/abs/1411.1784 https://arxiv.org/abs/1411.1784 . doi: 10.1201/9781003281344-9 http://dx.doi.org/10.1201/9781003281344-9

Nauata N , Hosseini S , Chang K H , et al . House‒GAN++:Generative adversarial layout refinement network towards intelligent computational agent for professional architects [C ] // Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR) . Nashville : IEEE , 2021 : 13627 ‒ 13636 . doi: 10.1109/cvpr46437.2021.01342 http://dx.doi.org/10.1109/cvpr46437.2021.01342

Chaillou S . ArchiGAN:Artificial intelligence x architecture [EB/OL ] //( 2020‒09‒03 )[ 2025‒04‒10 ] . https://doi.org/10.1007/978-981-15-6568-7_82020:117‒127 https://doi.org/10.1007/978-981-15-6568-7_82020:117‒127 .

Zhang Hang , Blasetti E . 3D architectural form style transfer through machine learning [C ] // Proceedings of the CA-ADRIA . Bangkok : CAADRIA , 2020 : 659 ‒ 668 . doi: 10.52842/conf.caadria.2020.2.659 http://dx.doi.org/10.52842/conf.caadria.2020.2.659

Chang K H , Cheng C Y , Luo Jieliang , et al . Building‒GAN:Graph-conditioned architectural volumetric design generation [C ] // Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision(ICCV) . Montreal : IEEE , 2021 : 11936 ‒ 1945 . doi: 10.1109/iccv48922.2021.01174 http://dx.doi.org/10.1109/iccv48922.2021.01174

Zhao Chaowang , Yang Jian , Xiong Wuyue , et al . Two generative design methods of hospital operating department layouts based on healthcare systematic layout planning and generative adversarial network [J ] . Journal of Shanghai Jiaotong University(Science) , 2021 , 26 ( 1 ): 103 ‒ 115 . doi: 10.1007/s12204-021-2265-9 http://dx.doi.org/10.1007/s12204-021-2265-9

Liao Wenjie , Lu Xinzheng , Huang Yuli , et al . Automated structural design of shear wall residential buildings using generative adversarial networks [J ] . Automation in Construction , 2021 , 132 : 103931 . doi: 10.1016/j.autcon.2021.103931 http://dx.doi.org/10.1016/j.autcon.2021.103931

Liao Wenjie , Huang Yuli , Zheng Zhe , et al . Intelligent generative structural design method for shear wall building based on “fused-text-image-to-image” generative adversarial networks [J ] . Expert Systems with Applications , 2022 , 210 : 118530 . doi: 10.1016/j.eswa.2022.118530 http://dx.doi.org/10.1016/j.eswa.2022.118530

Lu Xinzheng , Liao Wenjie , Zhang Yu , et al . Intelligent structural design of shear wall residence using physics-enhanced generative adversarial networks [J ] . Earthquake Engineering & Structural Dynamics , 2022 , 51 ( 7 ): 1657 ‒ 1676 . doi: 10.1002/eqe.3632 http://dx.doi.org/10.1002/eqe.3632

Zhao Pengju , Liao Wenjie , Huang Yuli , et al . Intelligent design of shear wall layout based on attention-enhanced generative adversarial network [J ] . Engineering Structures , 2023 , 274 : 115170 . doi: 10.1016/j.engstruct.2022.115170 http://dx.doi.org/10.1016/j.engstruct.2022.115170

方长建 , 康永君 , 龙丹冰 , 等 . 建筑平面灰度图生成方法、装置、电子设备及存储介质 : CN202310142430.6 [P ] . 2023‒05‒16 .

赵广坡 , 龙丹冰 , 唐军 , 等 . 构件特征数据提取方法、装置、电子设备及存储介质 : CN202310139985.5 [P ] . 2023‒04‒28 .

方长建 , 康永君 , 龙丹冰 , 等 . 结构平面布置整体生成方法、装置、电子设备及存储介质 : CN202310141368.9 [P ] . 2023‒04‒25 .

Wang Tingchun , Liu Mingyu , Zhu Junyan , et al . High-res- olution image synthesis and semantic manipulation with conditional GANs [C ] // Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Salt Lake City : IEEE , 2018 : 8798 ‒ 8807 . doi: 10.1109/cvpr.2018.00917 http://dx.doi.org/10.1109/cvpr.2018.00917

国家质检总局 . 建筑结构可靠性设计统一标准 : GB500 68—2018 [S ] . 北京 : 中国建筑工业出版社 , 2018 .

Views

481

下载量

CNKI被引量

Alert me when the article has been cited

提交

Tools

Publicity Resources

Experimental Study on Cracking of Aerated Concrete Filling Wall Under the Low Cyclic Horizontal Force

Related Author

Zhong Yan

Lei Xin

Long Danbing

Fang Changjian

KANG Yongjun

肖建庄

杜睿

王长青

Related Institution

School of Civil Engineering, Southwest Jiaotong Univ

China Southwest Architecture Design & Research Inst Co., Ltd.

同济大学建筑工程系上海

厦门理工学院土木工程与建筑系

集美大学工程技术学院

⁰