United States Department of Transportation
i
Data-Driven Bridge Management Using Descriptive and Predictive Machine Learning Models
-
2022-12-01
[PDF-2.38 MB]
Details:
-
Creators:
-
Corporate Creators:
-
Corporate Contributors:
-
Subject/TRT Terms:
-
Publication/ Report Number:
-
Resource Type:
-
Geographical Coverage:
-
Edition:Final Report
-
Corporate Publisher:
-
Abstract:Bridges deteriorate with time and use. To monitor deterioration of the bridges, several US Acts mandate the state and local governmental agencies (including cities, state transportation agencies, etc.) to perform regular bridge inspections. The aforementioned inspections across the nation, which have been conducted since 1970’s (including our region), have generated valuable historic databases of bridge data based in local and state governmental agencies. While these agencies currently use these inspections to prevent failure and to administrate the national bridge network by setting priorities and establishing criteria to allocate available resources to the structures in most critical conditions, we believe these databases are heavily underutilized. In particular, with the advent of machine learning and data mining methods, we envision data-driven solutions that can derive much more valued hidden knowledge that can be utilized for enhanced bridge management. While in the past, various data-driven deterioration models are proposed in the literature to model bridge deterioration, these models either suffer from low accuracy or are too complex to be applicable. Recently deep learning is shown to significantly outperform other analytical modeling methodologies in a variety of application domains. In this study, we present new deep learning models for enhanced bridge management. In particular, we focus on the two problems of bridge subtyping (descriptive analysis) and bridge deterioration forecasting (predictive analysis). Through empirical evaluation with real data, we demonstrate that our solutions for these problems significantly enhance the state-of-the-art in bridge management.
-
Format:
-
Collection(s):
-
Main Document Checksum:
-
Download URL:
-
File Type:
