Automated Damage Assessment of Bridges Using Machine-Learning-Assisted Structural Health Monitoring
Improving the performance of transportation structures is essential to reduce the likelihood of catastrophic failures and their adverse economic, social, and environmental impacts. Efforts to improve the performance of bridges rely on the application of optimized interventions (e.g., inspections or monitoring actions) to detect and correct damage in a timely manner. In this context, Structural Health Monitoring (SHM) is becoming essential for effectively detecting damage and quickly localizing areas that require close-up investigation. However, traditional SHM activities may require significant effort in data analysis and processing. This precludes the wide adoption of SHM in bridge management activities. Accordingly, there is a need for computationally efficient and more practical SHM-based approaches that can detect and localize damage in real-time. The main goal of this project is to develop an integrated framework for automated damage detection and localization in bridges based on Machine Learning (ML) algorithms. The proposed work involves laboratory testing on large-scale specimens subjected to random variable loading, as well as processing and analysis of long-term monitoring data from an existing highway bridge instrumented as part of a previous Oklahoma Department of Transportation (ODOT) sponsored project. The research team includes graduate, undergraduate, and high school students, with several from underrepresented minorities, fostering effective workforce development activities. The research goals will be accomplished through the following tasks. Task 1: Experimental testing on steel girders will involve applying progressive damage to various locations of the girders for extensive data collection. This experimental work will be conducted at Oklahoma State University (OSU) with assistance from team members from the University of Oklahoma (OU). Task 2: Data from the experimental testing will be used to develop a machine learning model capable of identifying the damage and its location along the girder. This task will be led by OSU team. Task 3: The damage assessment model will be implemented on the I-35 bridge over the Walnut Creek. The OU team will lead the work in this task. Task 4: Technical workshops and other activities will be held at OU and OSU to facilitate knowledge transfer for professionals in the Southern Plains Transportation Center (SPTC) region.
- Record URL:
Language
- English
Project
- Status: Active
- Funding: $100,000.00
-
Contract Numbers:
CY2-OSU-OU-01
69A3552348306
-
Sponsor Organizations:
Office of the Assistant Secretary for Research and Technology
University Transportation Centers Program
Department of Transportation
Washington, DC United States 20590Oklahoma Department of Transportation
200 NE 21st Street
Oklahoma City, OK United States 73105 -
Managing Organizations:
Southern Plains Transportation Center
University of Oklahoma
202 W Boyd St, Room 213A
Norman, OK United States 73019 -
Project Managers:
Dunn, Denise
-
Performing Organizations:
Oklahoma State University, Stillwater
School of Civil & Environmental Engineering
Stillwater, OK United States 74078University of Oklahoma, Norman
School of Civil Engineering and Environmental Science
202 West Boyd Street, Room 334
Norman, OK United States 73019 -
Principal Investigators:
Soliman, Mohamed
Floyd, Royce
- Start Date: 20241001
- Expected Completion Date: 20250930
- Actual Completion Date: 0
- USDOT Program: University Transportation Centers
Subject/Index Terms
- TRT Terms: Automation; Bridges; Data collection; Machine learning; Structural health monitoring
- Geographic Terms: Oklahoma
- Subject Areas: Bridges and other structures; Data and Information Technology; Highways; Maintenance and Preservation;
Filing Info
- Accession Number: 01941676
- Record Type: Research project
- Source Agency: Southern Plains Transportation Center
- Contract Numbers: CY2-OSU-OU-01, 69A3552348306
- Files: UTC, RIP
- Created Date: Jan 1 2025 1:55PM