Development of a building information model-guided post-earthquake building inspection framework using 3D synthetic environments

作     者：Nathaniel M.Levine Yasutaka Narazaki Billie F.Spencer Nathaniel M.Levine;Yasutaka Narazaki;Billie F.Spencer,Jr.

作者机构：Department of Civil and Environmental EngineeringUniversity of Illinois at Urbana-ChampaignUrbanaIllinois 61801USA Zhejiang University-University of Illinois at Urbana-Champaign InstituteZhejiang UniversityHaining 314400China 

出 版 物：《Earthquake Engineering and Engineering Vibration》 (地震工程与工程振动（英文刊）)

年 卷 期：2023年第22卷第2期

页      面：279-307页

核心收录：

学科分类：0710[理学-生物学] 08[工学] 081402[工学-结构工程] 0837[工学-安全科学与工程] 0814[工学-土木工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Financial support for this research was provided in part by the US Army Corps of Engineers through a subaward from the University of California San Diego USA 

主　　题：computer vision earthquake engineering building information model physics-based graphics model synthetic environment 

摘      要：Computer vision-based inspection methods show promise for automating post-earthquake building *** methods survey a building with unmanned aerial vehicles and automatically detect damage in the collected ***,assessing the damage′s impact on structural safety requires localizing damage to specific building components with known design and *** paper proposes a BIM-based automated inspection framework to provide context for visual surveys.A deep learning-based semantic segmentation algorithm is trained to automatically identify damage in *** BIM automatically associates any identified damage with specific building ***,components are classified into damage states consistent with component fragility models for integration with a structural *** demonstrate the framework,methods are developed to photorealistically simulate severe structural damage in a synthetic computer graphics environment.A graphics model of a real building in Urbana,Illinois,is generated to test the framework;the model is integrated with a structural analysis to apply earthquake damage in a physically realistic manner.A simulated UAV survey is flown of the graphics model and the framework is *** method achieves high accuracy in assigning damage states to visible structural *** assignment enables integration with a performance-based earthquake assessment to classify building safety.