Rapid Post-earthquake Structural Inspection and Evaluation of Civil Infrastructure

In the aftermath of an earthquake, rapid structural inspection and evaluation are critical to ensure that the normal order of life, work, and production can be restored quickly. To date, initial assessments of structures are based on visual information collected manually by certified inspectors and are known to be time-consuming, dangerous, and subjective. Moreover, the number of inspectors in an earthquake affected region may be limited, further delaying efforts to conduct these initial inspections. This lecture presents two recently proposed approaches for automated rapid post-earthquake safety assessment. The first approach employs sparse acceleration measurements to define damage-sensitive features that can be used to infer the condition of buildings. A convolutional neural network is then employed to uncover the complex relationship between the damage-sensitive features and the building condition. The proposed framework is validated experimentally using a 1/3-scale 18-story experimental steel building tested on the shaking table at E-Defense in Japan, confirming the efficacy of the proposed approach for rapid post-earthquake safety evaluation for high-rise buildings. Subsequently, a comprehensive strategy for rapid post-earthquake inspection and evaluation using images collected by commercial unmanned aerial vehicles (UAVs) is presented. The proposed approach employs a graphics-based digital twin (GBDT), which is comprised of a finite element (FE) model and a photo-realistic computer graphics (CG) model. The approach is illustrated for a 45-story high-rise building in Guangzhou, China. The results demonstrate the feasibility of the GBDT and highlights its flexibility in representing real-world structures and environmental conditions, enabling rapid evaluation of inspection strategies and efficient decision making in the aftermath of an earthquake.