基于媒体词云与自然语言处理的城市建筑震损评估  

SEISMIC DAMAGE ASSESSMENT OF URBAN BUILDING STRUCTURES BASE ON ONLINE MEDIA WORLD CLOUD AND NATURAL LANGUAGE PROCESSING

作　　者：孔庆钊 计柯妍 熊冰 周伯昌 熊青松 袁程 KONG Qing-zhao;JI Ke-yan;XIONG Bing;ZHOU Bo-chang;XIONG Qing-song;YUAN Cheng(State Key Laboratory for Disaster Reduction in Civil Engineering,Tongji University,Shanghai 200092,China;Shanghai Earthquake Agency,Shanghai 200062,China;Shanghai Sheshan National Geophysical Observatory,Shanghai 200062,China)

机构地区：[1]同济大学土木工程防灾国家重点实验室,上海200092 [2]上海市地震局,上海200062 [3]上海佘山地球物理国家野外科学观测研究站,上海200062

出　　处：《工程力学》2024年第10期80-88,共9页Engineering Mechanics

基　　金：国家自然科学基金项目(2020YFC1512504,52108470);上海余山地球物理国家野外科学观测研究站项目(SSOP202104)。

摘　　要：地震作用下基础设施工程的损毁会造成区域功能瘫痪,对城市区域的震损评估与救援及重建工作提供重要参考。为了做出快速明智的决策并对重大灾害事件做出快速响应,需要对建筑损坏的空间分布和严重程度进行快速评估。考虑到地震灾情后受灾群体在网络媒体和社交平台的信息要新、要快于专家进行实地评估的速度,而受灾区域的建筑物破坏状态有可能从轻微破坏到完全倒塌,对每一栋建筑逐栋细致评估是复杂且耗时的过程。为此,该研究试图利用自然语言深度学习模型BERT对基于震损破坏的文本描述对建筑物损伤进行分类评估。使用《中国地震烈度表》(GB/T 17742-1999)对受灾区域的单个建筑物的破坏状态进行预分类。为了验证所提方法的有效性,该研究收集了2016年台南地区6.4级地震后的300多座单体建筑物并建立了文本词云数据集。该数据集由343个建筑物(121个轻微破坏标签,128个中度破坏标签,94个严重破坏标签)组成,其中85%作为训练与验证数据集,剩余的15%用于鲁棒性测试。当BERT模型识别测试集的GB/T 17742-1999标签时,整体准确率达到81%。该研究只是试图建立一种新的高效震损评估方法,使用该方法对媒体与社交平台的震损文本描述进行分类评估,能够为应急救援决策提供信息依据并节省一定的战略部署时间。The damage of infrastructure projects under the action of earthquakes may result in regional function paralysis,and the earthquake damage assessment of urban areas can provide important information for rescue and reconstruction work.To make quick and informed decisions and respond quickly to major disaster events,a rapid assessment of the spatial distribution and severity of building damage is required.To this end,this study attempts to use the natural language deep learning model BERT to classify and evaluate building damage based on textual descriptions of earthquake damage.GB/T 17742-1999 is used to pre-classify the damage status of individual buildings in the affected area.To verify the effectiveness of the proposed method,this study collects the data of more than 300 individual buildings after the 2016 M6.4 earthquake in Tainan and establishes a text word cloud database.The dataset consists of 343 buildings(121 labeled light damage,128 labeled moderate damage,94 labeled severe damage),of which 85%are used as training and validation datasets,and the remaining 15%are used for robustness testing.When the BERT model recognizes the GB/T 17742-1999 labels of the test set,the overall accuracy rate reaches 81%.This study is just an attempt to establish a new and efficient earthquake damage assessment method.This method can be used to classify and evaluate the earthquake damage text descriptions on media and social platforms,and provide information for emergency rescue decisions and save a certain amount of time for strategic deployment.

关 键 词：震损评估 自然语言处理 数据驱动 机器学习 抗震性能 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] P315.63[自动化与计算机技术—控制科学与工程]