Utilization of Classification Methods on Bridge Databases in Virginia
Copeland, Christopher, Civil Engineering - School of Engineering and Applied Science, University of Virginia
Chase, Steven, Department of Civil Engineering, University of Virginia
The National Bridge Inventory (NBI) was created in 1972, and stores all the information collected from these inspections. It is the largest collection of bridge data in the world and contains detailed information on more than 600,000 United States highway bridges and large culverts. Pontis is a bridge management system and product of the American Association of State Highway and Transportation Officials (AASHTO). Pontis has the capability of storing and analyzing bridge inspection and inventory data, recommending optimal preservation policies, predicting needs and performance measures for bridges, and developing projects to include in an agency’s capital plan.
Previously, there has been little analysis performed on the VDOT Pontis and NBI from the perspective of data mining; therefore, the objectives of this study are to consolidate and compile multiple bridge data sets, and to discover previously unknown patterns and trends in the data using data mining and classification methods. The scope of the study includes the application of six classification methods on bridge inspection data to determine when certain bridge types will become structurally deficient. Bridge attributes studied include age, average daily traffic (ADT), truck percentage, district, element condition state, and presence of smart flag elements, and the significance of each is discussed.
Overall, classification methods produced strong results as classifiers of structural deficiency of bridges. The comparison of each classification method using the Orange data mining software is conducted and descriptions and performance of bridges in Virginia have been investigated and are presented in the following sections.
MS (Master of Science)
Data Mining, Bridge Management Systems, Classification Methods
All rights reserved (no additional license for public reuse)