Developing a new Decision Support System using Population Analysis to analyze safety and performance of Civil Infrastructures
Advisor Information
Hesham Ali
Location
MBSC Omaha Room 304 - G
Presentation Type
Oral Presentation
Start Date
4-3-2022 9:00 AM
End Date
4-3-2022 10:15 AM
Abstract
It has been reported that over half the bridges around the world are not safe and nearly 20% of rural bridges in the United States are in serious safety conditions. Various budget constraints and scarcity in human resources to inspect bridges have contributed to the challenges of keeping bridges safe while performing at higher levels. This has motivated the research community to develop new approaches for bridge health monitoring, particularly in identifying bridges that need immediate attention. National Bridge Inventory (NBI) database houses extensive data points that allows researchers to explore novel big data solutions to address pressing problems related to bridge safety and performance. In this study, we proposed the use of correlation networks to model the time-series data of condition ratings. The condition ratings from the NBI database are decks, superstructures, and substructures, and considered as outcome ratings. The basic idea behind the population analysis is to compare various groups of bridges with similarity patterns and check for the significantly enriched input parameters. This study has are three objectives: 1) developing a Relational Database Management System to store all available data and make it possible to extract useful information through various types of queries; 2) constructing a correlation network to identify clusters of bridges with similar outcome behavior; and 3) applying graph-theoretic algorithms and population analysis approaches to analyze the obtained cluster the groups and developing a decision support system to provide domain experts and professionals with rich information needed to manage civil infrastructures more efficiently and achieve higher degrees of safety and performance.
Scheduling Link
1
Developing a new Decision Support System using Population Analysis to analyze safety and performance of Civil Infrastructures
MBSC Omaha Room 304 - G
It has been reported that over half the bridges around the world are not safe and nearly 20% of rural bridges in the United States are in serious safety conditions. Various budget constraints and scarcity in human resources to inspect bridges have contributed to the challenges of keeping bridges safe while performing at higher levels. This has motivated the research community to develop new approaches for bridge health monitoring, particularly in identifying bridges that need immediate attention. National Bridge Inventory (NBI) database houses extensive data points that allows researchers to explore novel big data solutions to address pressing problems related to bridge safety and performance. In this study, we proposed the use of correlation networks to model the time-series data of condition ratings. The condition ratings from the NBI database are decks, superstructures, and substructures, and considered as outcome ratings. The basic idea behind the population analysis is to compare various groups of bridges with similarity patterns and check for the significantly enriched input parameters. This study has are three objectives: 1) developing a Relational Database Management System to store all available data and make it possible to extract useful information through various types of queries; 2) constructing a correlation network to identify clusters of bridges with similar outcome behavior; and 3) applying graph-theoretic algorithms and population analysis approaches to analyze the obtained cluster the groups and developing a decision support system to provide domain experts and professionals with rich information needed to manage civil infrastructures more efficiently and achieve higher degrees of safety and performance.