精细化城市RC建筑信息的快速智能获取方法  

Fast and intelligent acquisition method for refined urban RC building information

作　　者：刘鸿儒 余丁浩 李钢[1] 董志骞 LIU Hongru;YU Dinghao;LI Gang;DONG Zhiqian(State Key Laboratory of Coastal and Offshore Engineering,Dalian University of Technology,Dalian 116024,Liaoning,China)

机构地区：[1]大连理工大学海岸和近海工程国家重点实验室,辽宁大连116024

出　　处：《建筑科学与工程学报》2025年第2期101-113,共13页Journal of Architecture and Civil Engineering

基　　金：国家自然科学基金项目(52008075,52225804);中央高校基本科研业务费专项资金项目(DUT22RC3038);辽宁省博士科研启动基金项目(2022-BS-089)。

摘　　要：为便于开展城市区域精细化震害模拟工作,提出一种适用于城市建筑的精细化快速信息获取方法。首先采用基于无人机倾斜摄影的低空遥测技术,通过三维重建获取区域建筑外部几何信息;然后结合卷积神经网络和模糊推理方法,实现建筑层数和结构类型的快速识别;最后利用AdaBoost和Random Forest两种集成算法对框架和框剪结构内部构件信息进行预测,提出城市区域常用RC框架和RC框剪结构内部隐蔽信息的确定方法,并采用该方法对两栋实际建筑进行参数预测和震害模拟。结果表明:采用该方法可对结构内部柱截面尺寸、柱距、配筋率等构件级信息进行快速精细化预测,建立的结构有限元分析模型可实现区域建筑的精细化震害模拟,有效提高城市建筑参数获取及建模的效率和精细化程度,基于该方法计算出的结构地震响应相比于传统区域建筑信息获取方法和震害模拟方法具有更高的计算精度。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.

关 键 词：建筑信息 模糊推理 机器学习 精细化有限元模型 城市建筑 

分 类 号：TU364[建筑科学—结构工程]