A decision support system for scour management of road and railway bridges based on Bayesian networks

Andrea Maroni, Enrico Tubaldi, Dimitri Val, Hazel McDonald, Stewart Lothian, Oliver Riches, Daniele Zonta

Research output: Contribution to conferencePaper

Abstract

Flood-induced scour is the excavation of material around bridge foundations due to the erosive action of flowing water and it is by far the leading cause of bridge failures worldwide. In the United States, scour is the cause of 22 bridges fail every year whereas in the UK, it contributed significantly to the 138 collapses of bridges in the last century. Monitoring an entire infrastructure network against scour is not economically feasible. A way to overcome this limitation is to install scour monitoring systems (SMSs) at critical bridge locations, and then extend information gained to the entire asset through a probabilistic approach. In this paper, we propose a Decision Support System (DSS) for road and railway bridge scour management that exploits information from a limited number of scour monitoring systems to achieve a more confined estimate of the scour risk for a bridge network. A Bayesian network (BN) is used to describe conditional dependencies among the random variables involved. It allows estimating the present and future scour depth distribution using real-time information from monitoring of scour depth and river flow characteristics. Data collected by SMSs and BN’s outcomes are then used to inform a decision model and thus support transport agencies’ decision frameworks. The idea is to use this information to update the scour threshold after which bridges are closed. A case study consisting of several road bridges in Scotland is built to demonstrate the functioning of the DDS. They cross the same river and only one of them is instrumented with a SMS. The BN is found to estimate accurately the scour depth at unmonitored bridges and the decision model provides higher values of scour threshold compared to the ones implicitly chosen by transport agencies.

Conference

ConferenceThe 12th International Workshop on Structural Health Monitoring, IWSHM 2019
Abbreviated titleIWSHM 2019
CountryUnited States
CityStanford
Period10/09/1912/09/19

Fingerprint

Scour
Bayesian networks
Decision support systems
Monitoring
Rivers
Information use
Excavation
Random variables

Keywords

  • scour
  • road and rail bridges
  • structural health monitoring
  • Bayesian network
  • Decision Support System

Cite this

Maroni, A., Tubaldi, E., Val, D., McDonald, H., Lothian, S., Riches, O., & Zonta, D. (2019). A decision support system for scour management of road and railway bridges based on Bayesian networks. 2437-2444. Paper presented at The 12th International Workshop on Structural Health Monitoring, IWSHM 2019, Stanford, United States.
Maroni, Andrea ; Tubaldi, Enrico ; Val, Dimitri ; McDonald, Hazel ; Lothian, Stewart ; Riches, Oliver ; Zonta, Daniele. / A decision support system for scour management of road and railway bridges based on Bayesian networks. Paper presented at The 12th International Workshop on Structural Health Monitoring, IWSHM 2019, Stanford, United States.8 p.
@conference{5d2e78a744d14e7bae280bde8e16a424,
title = "A decision support system for scour management of road and railway bridges based on Bayesian networks",
abstract = "Flood-induced scour is the excavation of material around bridge foundations due to the erosive action of flowing water and it is by far the leading cause of bridge failures worldwide. In the United States, scour is the cause of 22 bridges fail every year whereas in the UK, it contributed significantly to the 138 collapses of bridges in the last century. Monitoring an entire infrastructure network against scour is not economically feasible. A way to overcome this limitation is to install scour monitoring systems (SMSs) at critical bridge locations, and then extend information gained to the entire asset through a probabilistic approach. In this paper, we propose a Decision Support System (DSS) for road and railway bridge scour management that exploits information from a limited number of scour monitoring systems to achieve a more confined estimate of the scour risk for a bridge network. A Bayesian network (BN) is used to describe conditional dependencies among the random variables involved. It allows estimating the present and future scour depth distribution using real-time information from monitoring of scour depth and river flow characteristics. Data collected by SMSs and BN’s outcomes are then used to inform a decision model and thus support transport agencies’ decision frameworks. The idea is to use this information to update the scour threshold after which bridges are closed. A case study consisting of several road bridges in Scotland is built to demonstrate the functioning of the DDS. They cross the same river and only one of them is instrumented with a SMS. The BN is found to estimate accurately the scour depth at unmonitored bridges and the decision model provides higher values of scour threshold compared to the ones implicitly chosen by transport agencies.",
keywords = "scour, road and rail bridges, structural health monitoring, Bayesian network, Decision Support System",
author = "Andrea Maroni and Enrico Tubaldi and Dimitri Val and Hazel McDonald and Stewart Lothian and Oliver Riches and Daniele Zonta",
year = "2019",
month = "9",
day = "12",
language = "English",
pages = "2437--2444",
note = "The 12th International Workshop on Structural Health Monitoring, IWSHM 2019, IWSHM 2019 ; Conference date: 10-09-2019 Through 12-09-2019",

}

Maroni, A, Tubaldi, E, Val, D, McDonald, H, Lothian, S, Riches, O & Zonta, D 2019, 'A decision support system for scour management of road and railway bridges based on Bayesian networks' Paper presented at The 12th International Workshop on Structural Health Monitoring, IWSHM 2019, Stanford, United States, 10/09/19 - 12/09/19, pp. 2437-2444.

A decision support system for scour management of road and railway bridges based on Bayesian networks. / Maroni, Andrea; Tubaldi, Enrico; Val, Dimitri; McDonald, Hazel; Lothian, Stewart; Riches, Oliver; Zonta, Daniele.

2019. 2437-2444 Paper presented at The 12th International Workshop on Structural Health Monitoring, IWSHM 2019, Stanford, United States.

Research output: Contribution to conferencePaper

TY - CONF

T1 - A decision support system for scour management of road and railway bridges based on Bayesian networks

AU - Maroni, Andrea

AU - Tubaldi, Enrico

AU - Val, Dimitri

AU - McDonald, Hazel

AU - Lothian, Stewart

AU - Riches, Oliver

AU - Zonta, Daniele

PY - 2019/9/12

Y1 - 2019/9/12

N2 - Flood-induced scour is the excavation of material around bridge foundations due to the erosive action of flowing water and it is by far the leading cause of bridge failures worldwide. In the United States, scour is the cause of 22 bridges fail every year whereas in the UK, it contributed significantly to the 138 collapses of bridges in the last century. Monitoring an entire infrastructure network against scour is not economically feasible. A way to overcome this limitation is to install scour monitoring systems (SMSs) at critical bridge locations, and then extend information gained to the entire asset through a probabilistic approach. In this paper, we propose a Decision Support System (DSS) for road and railway bridge scour management that exploits information from a limited number of scour monitoring systems to achieve a more confined estimate of the scour risk for a bridge network. A Bayesian network (BN) is used to describe conditional dependencies among the random variables involved. It allows estimating the present and future scour depth distribution using real-time information from monitoring of scour depth and river flow characteristics. Data collected by SMSs and BN’s outcomes are then used to inform a decision model and thus support transport agencies’ decision frameworks. The idea is to use this information to update the scour threshold after which bridges are closed. A case study consisting of several road bridges in Scotland is built to demonstrate the functioning of the DDS. They cross the same river and only one of them is instrumented with a SMS. The BN is found to estimate accurately the scour depth at unmonitored bridges and the decision model provides higher values of scour threshold compared to the ones implicitly chosen by transport agencies.

AB - Flood-induced scour is the excavation of material around bridge foundations due to the erosive action of flowing water and it is by far the leading cause of bridge failures worldwide. In the United States, scour is the cause of 22 bridges fail every year whereas in the UK, it contributed significantly to the 138 collapses of bridges in the last century. Monitoring an entire infrastructure network against scour is not economically feasible. A way to overcome this limitation is to install scour monitoring systems (SMSs) at critical bridge locations, and then extend information gained to the entire asset through a probabilistic approach. In this paper, we propose a Decision Support System (DSS) for road and railway bridge scour management that exploits information from a limited number of scour monitoring systems to achieve a more confined estimate of the scour risk for a bridge network. A Bayesian network (BN) is used to describe conditional dependencies among the random variables involved. It allows estimating the present and future scour depth distribution using real-time information from monitoring of scour depth and river flow characteristics. Data collected by SMSs and BN’s outcomes are then used to inform a decision model and thus support transport agencies’ decision frameworks. The idea is to use this information to update the scour threshold after which bridges are closed. A case study consisting of several road bridges in Scotland is built to demonstrate the functioning of the DDS. They cross the same river and only one of them is instrumented with a SMS. The BN is found to estimate accurately the scour depth at unmonitored bridges and the decision model provides higher values of scour threshold compared to the ones implicitly chosen by transport agencies.

KW - scour

KW - road and rail bridges

KW - structural health monitoring

KW - Bayesian network

KW - Decision Support System

M3 - Paper

SP - 2437

EP - 2444

ER -

Maroni A, Tubaldi E, Val D, McDonald H, Lothian S, Riches O et al. A decision support system for scour management of road and railway bridges based on Bayesian networks. 2019. Paper presented at The 12th International Workshop on Structural Health Monitoring, IWSHM 2019, Stanford, United States.