Post-earthquake assessment of bridges using Bayesian networks with continuous variables

Y. C. Yue, D. Zonta, M. Pozzi

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

Abstract

This paper presents a framework for Bayesian Network-based assessment of the seismic vulnerability of bridges. This framework incorporates a fragility function and capacity and demand models. The fragility function and the capacity model are constructed using Hazus. The demand on the bridge is calculated using an attenuation function. The uncertainty terms are considered in both the capacity and the demand model. In order to apply the exact inference algorithm of continuous Bayesian Networks in this framework, all the variables in the framework are assumed to follow Gaussian distribution and the continuous variables are not allowed to have discrete child variables. Using this framework, the correlation between two bridges is analyzed, and the prior probabilities of the two bridges being in a damage state are calculated during the initialization procedures. When an earthquake occurs, if data such as magnitude and epicenter are known, or the damage state of one bridge is observed by on-site sensors, then the probability of another bridge being in a damage state can be predicted and updated. The framework is applied to the bridge networks in Trentino, Italy.

LanguageEnglish
Title of host publicationSafety, Reliability, Risk and Life-Cycle Performance of Structures and Infrastructures - Proceedings of the 11th International Conference on Structural Safety and Reliability, ICOSSAR 2013
Pages3185-3191
Number of pages7
DOIs
Publication statusPublished - 20 Jun 2013
Event11th International Conference on Structural Safety and Reliability, ICOSSAR 2013 - New York, NY, United States
Duration: 16 Jun 201320 Jun 2013

Conference

Conference11th International Conference on Structural Safety and Reliability, ICOSSAR 2013
CountryUnited States
CityNew York, NY
Period16/06/1320/06/13

Fingerprint

Bayesian networks
Earthquakes
Gaussian distribution
Sensors

Keywords

  • Bayesian networks
  • bridge safety
  • earthquake assessment

Cite this

Yue, Y. C., Zonta, D., & Pozzi, M. (2013). Post-earthquake assessment of bridges using Bayesian networks with continuous variables. In Safety, Reliability, Risk and Life-Cycle Performance of Structures and Infrastructures - Proceedings of the 11th International Conference on Structural Safety and Reliability, ICOSSAR 2013 (pp. 3185-3191) https://doi.org/10.1201/b16387-460
Yue, Y. C. ; Zonta, D. ; Pozzi, M. / Post-earthquake assessment of bridges using Bayesian networks with continuous variables. Safety, Reliability, Risk and Life-Cycle Performance of Structures and Infrastructures - Proceedings of the 11th International Conference on Structural Safety and Reliability, ICOSSAR 2013. 2013. pp. 3185-3191
@inproceedings{8931cb0126004f2fa4f95845d2dc9c67,
title = "Post-earthquake assessment of bridges using Bayesian networks with continuous variables",
abstract = "This paper presents a framework for Bayesian Network-based assessment of the seismic vulnerability of bridges. This framework incorporates a fragility function and capacity and demand models. The fragility function and the capacity model are constructed using Hazus. The demand on the bridge is calculated using an attenuation function. The uncertainty terms are considered in both the capacity and the demand model. In order to apply the exact inference algorithm of continuous Bayesian Networks in this framework, all the variables in the framework are assumed to follow Gaussian distribution and the continuous variables are not allowed to have discrete child variables. Using this framework, the correlation between two bridges is analyzed, and the prior probabilities of the two bridges being in a damage state are calculated during the initialization procedures. When an earthquake occurs, if data such as magnitude and epicenter are known, or the damage state of one bridge is observed by on-site sensors, then the probability of another bridge being in a damage state can be predicted and updated. The framework is applied to the bridge networks in Trentino, Italy.",
keywords = "Bayesian networks, bridge safety, earthquake assessment",
author = "Yue, {Y. C.} and D. Zonta and M. Pozzi",
year = "2013",
month = "6",
day = "20",
doi = "10.1201/b16387-460",
language = "English",
isbn = "9781138000865",
pages = "3185--3191",
booktitle = "Safety, Reliability, Risk and Life-Cycle Performance of Structures and Infrastructures - Proceedings of the 11th International Conference on Structural Safety and Reliability, ICOSSAR 2013",

}

Yue, YC, Zonta, D & Pozzi, M 2013, Post-earthquake assessment of bridges using Bayesian networks with continuous variables. in Safety, Reliability, Risk and Life-Cycle Performance of Structures and Infrastructures - Proceedings of the 11th International Conference on Structural Safety and Reliability, ICOSSAR 2013. pp. 3185-3191, 11th International Conference on Structural Safety and Reliability, ICOSSAR 2013, New York, NY, United States, 16/06/13. https://doi.org/10.1201/b16387-460

Post-earthquake assessment of bridges using Bayesian networks with continuous variables. / Yue, Y. C.; Zonta, D.; Pozzi, M.

Safety, Reliability, Risk and Life-Cycle Performance of Structures and Infrastructures - Proceedings of the 11th International Conference on Structural Safety and Reliability, ICOSSAR 2013. 2013. p. 3185-3191.

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

TY - GEN

T1 - Post-earthquake assessment of bridges using Bayesian networks with continuous variables

AU - Yue, Y. C.

AU - Zonta, D.

AU - Pozzi, M.

PY - 2013/6/20

Y1 - 2013/6/20

N2 - This paper presents a framework for Bayesian Network-based assessment of the seismic vulnerability of bridges. This framework incorporates a fragility function and capacity and demand models. The fragility function and the capacity model are constructed using Hazus. The demand on the bridge is calculated using an attenuation function. The uncertainty terms are considered in both the capacity and the demand model. In order to apply the exact inference algorithm of continuous Bayesian Networks in this framework, all the variables in the framework are assumed to follow Gaussian distribution and the continuous variables are not allowed to have discrete child variables. Using this framework, the correlation between two bridges is analyzed, and the prior probabilities of the two bridges being in a damage state are calculated during the initialization procedures. When an earthquake occurs, if data such as magnitude and epicenter are known, or the damage state of one bridge is observed by on-site sensors, then the probability of another bridge being in a damage state can be predicted and updated. The framework is applied to the bridge networks in Trentino, Italy.

AB - This paper presents a framework for Bayesian Network-based assessment of the seismic vulnerability of bridges. This framework incorporates a fragility function and capacity and demand models. The fragility function and the capacity model are constructed using Hazus. The demand on the bridge is calculated using an attenuation function. The uncertainty terms are considered in both the capacity and the demand model. In order to apply the exact inference algorithm of continuous Bayesian Networks in this framework, all the variables in the framework are assumed to follow Gaussian distribution and the continuous variables are not allowed to have discrete child variables. Using this framework, the correlation between two bridges is analyzed, and the prior probabilities of the two bridges being in a damage state are calculated during the initialization procedures. When an earthquake occurs, if data such as magnitude and epicenter are known, or the damage state of one bridge is observed by on-site sensors, then the probability of another bridge being in a damage state can be predicted and updated. The framework is applied to the bridge networks in Trentino, Italy.

KW - Bayesian networks

KW - bridge safety

KW - earthquake assessment

UR - http://www.scopus.com/inward/record.url?scp=84892391625&partnerID=8YFLogxK

U2 - 10.1201/b16387-460

DO - 10.1201/b16387-460

M3 - Conference contribution book

SN - 9781138000865

SP - 3185

EP - 3191

BT - Safety, Reliability, Risk and Life-Cycle Performance of Structures and Infrastructures - Proceedings of the 11th International Conference on Structural Safety and Reliability, ICOSSAR 2013

ER -

Yue YC, Zonta D, Pozzi M. Post-earthquake assessment of bridges using Bayesian networks with continuous variables. In Safety, Reliability, Risk and Life-Cycle Performance of Structures and Infrastructures - Proceedings of the 11th International Conference on Structural Safety and Reliability, ICOSSAR 2013. 2013. p. 3185-3191 https://doi.org/10.1201/b16387-460