|Table of Contents|

Fast and intelligent acquisition method for refined urban RC building information(PDF)

《建筑科学与工程学报》[ISSN:1673-2049/CN:61-1442/TU]

Issue:
2025年02期
Page:
101-113
Research Field:
建筑结构
Publishing date:

Info

Title:
Fast and intelligent acquisition method for refined urban RC building information
Author(s):
LIU Hongru;  YU Dinghao;  LI Gang;  DONG Zhiqian
(State Key Laboratory of Coastal and Offshore Engineering, Dalian University of Technology, Dalian 116024, Liaoning, China)
Keywords:
building information;  fuzzy inference;  machine learning;  refined finite element model;  urban building
PACS:
TU364
DOI:
10.19815/j.jace.2023.03075
Abstract:
In order to facilitate the fine-grained seismic simulation in urban areas, a refined and rapid information acquisition method applicable to urban buildings was proposed. The low-altitude telemetry based on unmanned aerial vehicle(UAV)tilt photography was adopted to obtain the external geometric information of regional buildings through 3D reconstruction. Then combining convolutional neural network and fuzzy inference methods, the fast identification of building layers and structure types were achieved. Finally, the AdaBoost and Random Forest integration algorithms were compared to predict the internal component information of the frame and frame-shear structure, and the method of determining the hidden information of the RC frame and RC frame-shear structure commonly used in urban areas was proposed. This method was used to predict the parameters and simulate the seismic damage of two actual buildings. The results show that the method can make fast and refined prediction of member-level information such as column section size, column spacing and reinforcement rate inside the structure. By using the method to establish a structural finite element analysis model, fine-grained seismic simulation of regional buildings can be realized, and the method can effectively improve the efficiency and refinement of urban building parameter acquisition and modeling. The structural seismic response calculated based on the method has higher computational accuracy compared with the traditional methods of regional building information acquisition and seismic simulation.

References:

[1] 熊 琛.基于时程分析和三维场景可视化的区域建筑震害模拟研究[D].北京:清华大学,2016.
XIONG Chen. Study on seismic damage simulation of regional buildings based on time-history analysis and 3D scene visualization[D]. Beijing: Tsinghua University, 2016.
[2]李岩玮.四川省甘孜州木雅祖庆学校综合楼震害损伤评估及加固方案分析[D].重庆:重庆大学,2016.
LI Yanwei. Seismic damage assessment and strengthening analysis of Muyazuqing school in Sichuan province[D]. Chongqing: Chongqing University, 2016.
[3]许 镇.城市综合数字防灾:地震及次生灾害情景仿真与韧性评估[M].北京:中国建筑工业出版社,2021.
XU Zhen. Urban comprehensive digital disaster prevention:scenario simulation and resilience assessment of earthquake and secondary disaster[M]. Beijing: China Architecture & Building Press, 2021.
[4]庄钰蓥,熊 峰,吕 洋,等.基于GIS的城市建筑群动力响应分析模型建模方法研究[J].世界地震工程,2021,37(4):137-147.
ZHUANG Yuying, XIONG Feng, LU Yang, et al. Research on a GIS-based method of model establishment for seismic response analysis of urban building groups[J]. World Earthquake Engineering, 2021, 37(4): 137-147.
[5]HORI M, OGUNI K, ICHIMURA T. Integrated simulation for earthquake hazard and disaster prediction[J]. Journal of Earthquake and Tsunami, 2009, 3(3): 121-141.
[6]李 钢,张鹏程,董志骞,等.村镇砌体建筑群信息智能获取与震害预测[J].建筑结构学报,2022,43(8):196-208.
LI Gang, ZHANG Pengcheng, DONG Zhiqian, et al. Intelligent information acquisition methods and seismic damage prediction of rural masonry building groups[J]. Journal of Building Structures,2022, 43(8): 196-208.
[7]尹菲菲.城市震害模拟中的RC框架结构自动化精细建模方法研究[D].哈尔滨:中国地震局工程力学研究所,2017.
YIN Feifei. Research on automatic fine modeling method of RC frame structure in urban earthquake damage simulation[D]. Harbin: Institute of Engineering Mechanics, China Earthquake Administration, 2017.
[8]杨 辉,崔 阳,罗 盛,等.无人机倾斜摄影技术在建筑工程三维建模中应用[J].建筑技术开发,2022,49(2):88-90.
YANG Hui, CUI Yang, LUO Sheng, et al. Three-dimensional modeling application of drone tilt photography technology in architecture[J]. Building Technology Development, 2022, 49(2): 88-90.
[9]岳亚男.基于卷积神经网络的RC框架结构损伤识别研究[D].哈尔滨:哈尔滨工业大学,2020.
YUE Yanan. Research on damage identification of RC frame structure based on convolutional neural network[D]. Harbin: Harbin Institute of Technology, 2020.
[10]彭慧君.松原地区群体建筑结构抗震性能分析[D].哈尔滨:哈尔滨工业大学,2020.
PENG Huijun. Seismic performance analysis of group building structures in Songyuan area[D]. Harbin: Harbin Institute of Technology, 2020.
[11]王士同.模糊推理理论与模糊专家系统[M].上海:上海科学技术文献出版社,1995.
WANG Shitong. Fuzzy inference theory and fuzzy expert system[M]. Shanghai: Shanghai Scientific and Technological Literature Press, 1995.
[12]高层建筑混凝土结构技术规程:JGJ 3—2010[S].北京:中国建筑工业出版社,2011.
Technical specification for concrete structures of tall building: JGJ 3—2010[S]. Beijing: China Architecture & Building Press, 2011.
[13]梅清良,宋海威.浅谈建筑层数与结构的选择[J].科技信息(科学教研),2008(6):94.
MEI Qingliang, SONG Haiwei. A brief discussion on the selection of building stories and structure[J]. Science & Technology Information, 2008(6): 94.
[14]建筑抗震设计规范:GB 50011—2001[S].北京:中国建筑工业出版社,2004.
Code for seismic design of buildings: GB 50011—2001[S]. Beijing: China Architecture & Building Press, 2004.
[15]何振华,许俊杰.关于大跨度钢结构设计的一些探讨[J].中华民居,2014(1):28.
HE Zhenhua, XU Junjie. Some discussions on the design of large-span steel structures[J]. China Homes, 2014(1): 28.
[16]巩敦卫,孙晓燕.智能控制技术简明教程[M].北京:国防工业出版社,2010.
GONG Dunwei, SUN Xiaoyan. A concise tutorial on intelligent control technology[M]. Beijing: National Defence Industry Press, 2010.
[17]FREUND Y, SCHAPIRE R E. A decision-theoretic generalization of on-line learning and an application to boosting[J]. Journal of Computer and System Sciences, 1997, 55(1): 119-139.
[18]BREIMAN L.Random forests[J]. Machine Learning,2001, 45(1): 5-32.
[19]STEINBRUNN M, MOERKOTTE G, KEMPER A. Heuristic and randomized optimization for the join ordering problem[J]. The VLDB Journal, 1997, 6(3): 191-208.
[20]程庆乐,曾 翔,熊 琛,等.区域建筑震害模拟方法分析对比[J].工程力学,2017,34(增1):105-110,128.
CHENG Qingle, ZENG Xiang, XIONG Chen, et al. Comparison of seismic damage simulation methods for different regional buildings[J]. Engineering Mechanics, 2017, 34(S1): 105-110, 128.

Memo

Memo:
-
Last Update: 2025-03-20