A deep learning approach to rapid regional post‐event seismic damage assessment using time‐frequency distributions of ground motions

Author(s):  
Xinzheng Lu ◽  
Yongjia Xu ◽  
Yuan Tian ◽  
Barbaros Cetiner ◽  
Ertugrul Taciroglu
Author(s):  
Xinzheng Lu ◽  
Qingle Cheng ◽  
Yuan Tian ◽  
Yuli Huang

ABSTRACT Regional ground-motion simulation is important for postearthquake seismic damage assessment. Herein, a ground-motion simulation method using recorded ground motions is proposed. Inverse-distance-weighted interpolation of the response spectra is performed to obtain the response spectrum at the target location. Then the ground-motion time history for the target location is obtained by correcting the nearest-station records using the continuous wavelet transform. An evaluation measure for the accuracy of the predicted ground motion, that is, the response-spectrum error, is introduced, and its relationship with the seismic damage of regional buildings is determined via a city-scale nonlinear time-history analysis. The response-spectrum errors under different site conditions, distances, and elevation differences are analyzed. The application conditions for the proposed method are subsequently outlined. The Tsinghua campus is examined as a case study to validate the method. Finally, downtown San Francisco under an Mw 7.0 simulated earthquake on the Hayward fault is selected as an example to demonstrate the proposed method. The proposed method overcomes the difficulties in determining the intrastation ground motions and provides valuable input to postearthquake seismic damage assessment.


2021 ◽  
pp. 147592172199621
Author(s):  
Enrico Tubaldi ◽  
Ekin Ozer ◽  
John Douglas ◽  
Pierre Gehl

This study proposes a probabilistic framework for near real-time seismic damage assessment that exploits heterogeneous sources of information about the seismic input and the structural response to the earthquake. A Bayesian network is built to describe the relationship between the various random variables that play a role in the seismic damage assessment, ranging from those describing the seismic source (magnitude and location) to those describing the structural performance (drifts and accelerations) as well as relevant damage and loss measures. The a priori estimate of the damage, based on information about the seismic source, is updated by performing Bayesian inference using the information from multiple data sources such as free-field seismic stations, global positioning system receivers and structure-mounted accelerometers. A bridge model is considered to illustrate the application of the framework, and the uncertainty reduction stemming from sensor data is demonstrated by comparing prior and posterior statistical distributions. Two measures are used to quantify the added value of information from the observations, based on the concepts of pre-posterior variance and relative entropy reduction. The results shed light on the effectiveness of the various sources of information for the evaluation of the response, damage and losses of the considered bridge and on the benefit of data fusion from all considered sources.


Author(s):  
Daniela Díaz Fuentes ◽  
Pilar Alejandra Baquedano Julià ◽  
Michele D’Amato ◽  
Michelangelo Laterza

2013 ◽  
Vol 316-317 ◽  
pp. 723-726
Author(s):  
Jian Qun Jiang ◽  
Xiao Wen Yao ◽  
Yi Ting Lu

Water supply pipeline system is a key issue in urban lifeline engineering, and the seismic assessment for the system damage is of significant importance. In this study, method of seismic damage assessment on underground water supply pipeline is introduced. With emphasis on the uncertainties of earthquake level, ground condition, soil-pipe interaction and capacity to resist pipe deformation in longitudinal direction, the check point method is applied to the reliability study of water pipeline, and a case study is presented to show the implementation of the proposed model.


Sign in / Sign up

Export Citation Format

Share Document