Highway bridges are one of the most critical components in transportation infrastructure systems. Accumulated Internal and concealed damages, due to aging or extreme events (e.g. earthquakes), make highway bridges vulnerable and pose a threat to the resiliency of local community. Therefore, these damages should be detected through structural health monitoring (SHM) algorithms at an early stage. Based on nonlinear time history analysis simulations on the investigated bridge system, a data-driven damage detection approach is explored on bridge columns, the most critical components of bridge systems. The paper starts with presenting damage feature selection where their effectiveness is demonstrated through unsupervised learning. The support vector machine, one of the representative supervised learning algorithm, is applied several classification problems of engineering interests. Very promising results (estimation accuracies) are observed on both binary (damage vs. no damage, collapse vs. non-collapse) and multi-class (damage severity) classifications utilizing support vector machine. Postdoctoral Scholar, Dept. of CEE, UC Berkeley, CA 94720 (email: benliangxiao@berkeley.edu) Taisei Professor of Civil Engineering and Director of PEER, Dept. of CEE, UC Berkeley, CA 94720 Graduate Student Researcher, Dept. of CEE, UC Berkeley, CA 94720 Liang X, Mosalam KM, Muin S. Simulation-Based Data-Driven Damage Detection for Highway Bridge Systems. Proceedings of the 11 National Conference in Earthquake Engineering, Earthquake Engineering Research Institute, Los Angeles, CA. 2018. Eleventh U.S. National Conference on Earthquake Engineering Integrating Science, Engineering & Policy June 25-29, 2018 Los Angeles, California Simulation-Based Data-Driven Damage Detection for Highway Bridge Systems X. Liang, K. Mosalam and S. Muin
[1]
Stuart Barber,et al.
All of Statistics: a Concise Course in Statistical Inference
,
2005
.
[2]
Ross W. Boulanger,et al.
Inelastic Seismic Response of Extended Pile-Shaft-Supported Bridge Structures
,
2004
.
[3]
Farzin Zareian,et al.
Seismic behavior of reinforced concrete bridges with skew-angled seat-type abutments
,
2012
.
[4]
K. Campbell,et al.
NGA Ground Motion Model for the Geometric Mean Horizontal Component of PGA, PGV, PGD and 5% Damped Linear Elastic Response Spectra for Periods Ranging from 0.01 to 10 s
,
2008
.
[5]
Charles R. Farrar,et al.
Structural Health Monitoring: A Machine Learning Perspective
,
2012
.
[6]
Jasper Snoek,et al.
Practical Bayesian Optimization of Machine Learning Algorithms
,
2012,
NIPS.
[7]
Bruce L. Kutter,et al.
PACIFIC EARTHQUAKE ENGINEERING RESEARCH CENTER PACIFIC EARTHQUAKE ENGINEERING Rocking Response of Bridges on Shallow Foundations
,
2010
.
[8]
Khalid M. Mosalam,et al.
Cumulative Absolute Velocity as a Local Damage Indicator of Instrumented Structures
,
2017
.
[9]
Xiao Liang,et al.
Direct Integration Algorithms for Efficient Nonlinear Seismic Response of Reinforced Concrete Highway Bridges
,
2016
.
[10]
Xiao Liang,et al.
Performance-Based Robust Nonlinear Seismic Analysis with Application to Reinforced Concrete Bridge Systems
,
2016
.
[11]
J. Mander,et al.
Theoretical stress strain model for confined concrete
,
1988
.