01626540

Component

As a significant number of steel bridges are approaching the end of their service life, understanding deterioration characteristics will help bridge stakeholders better prioritize bridge maintenance, repair, and rehabilitation. This paper applies data mining techniques including logistic regression, decision trees, neural networks, gradient boosting, and support vector machine to the 2013 National Bridge Inventory to estimate the probability of steel bridge superstructures reaching deficiency. Deterioration factors considered included age, average daily traffic, design load, maximum span length, and structure length. The impacts of these factors affecting steel bridge superstructure deterioration were identified. Outcomes of the analysis afford bridge stakeholders the opportunity to better understand factors that relate to steel bridge deterioration as well as provide a means to assess other risks associated with bridge maintenance, repair, and rehabilitation.

This paper was sponsored by TRB committee AFF20 Standing Committee on Steel Bridges.

01618707

17-02296

English

15p

2017

Transportation Research Board 96th Annual Meeting

Digital/other

Figures; References; Tables

Bridge superstructures; Data mining; Decision trees; Deterioration; Logistic regression analysis; Neural networks; Probability; Risk assessment; Steel bridges

National Bridge Inventory

Bridges and other structures; Data and Information Technology; Highways; Maintenance and Preservation

Transportation Research Board Annual Meeting 2017 Paper #17-02296

TRIS, TRB, ATRI

Dec 8 2016 10:51AM