Physics-Informed Machine Learning of Fluid-Structure Interaction for Bridge Safety and Reliability

For many coastal communities, bridges are the only regional transportation lifeline and are critical for the mobility of people, goods, and post-event response. To ensure reliable mobility after extreme events, it is necessary to understand, model, and design for bridge response under tsunami loading. Thus, simulating fluid-structure interaction (FSI) is essential to designing and retrofitting bridges for tsunami loads; however, simulation of FSI is computationally intense, involving both solid and fluid domains. While numerical methods for FSI and computing speed continually improve, more robust and faster computations are required to perform the parametric studies that shape modern bridge design codes for tsunami loading. The objective of this proposal is to use the FSI capabilities of the OpenSees finite element framework to develop a prototype machine learning (ML) algorithm for tsunami loading on bridge superstructures. To ensure robustness, the ML algorithm will be based on deep learning techniques using novel physics-informed neural networks. As the resulting input-output relationships from ML may not obey physical relationships, the learned models will be designed to retain the relevant physics of FSI, whereby momentum and mass balance are preserved throughout the training process by penalizing the learning process if the governing FSI equations are not satisfied.

Language

• English

Project

• Status: Active
• Funding: $80,000
• Contract Numbers:

  69A3551747110

• Sponsor Organizations:

  Pacific Northwest Transportation Consortium

  University of Washington
  More Hall Room 112
  Seattle, WA  United States  98195-2700

  Office of the Assistant Secretary for Research and Technology

  University Transportation Centers Program
  Department of Transportation
  Washington, DC  United States  20590
• Managing Organizations:

  Oregon State University, Corvallis

  Department of Civil Engineering
  202 Apperson Hall
  Corvallis, OR  United States  97331-2302
• Project Managers:

  Scott, Michael

• Performing Organizations:

  Oregon State University, Corvallis

  Department of Civil Engineering
  202 Apperson Hall
  Corvallis, OR  United States  97331-2302
• Principal Investigators:

  Scott, Michael

• Start Date: 20220316
• Expected Completion Date: 20230630
• Actual Completion Date: 0
• USDOT Program: University Transportation Centers Program

Subject/Index Terms

• TRT Terms: Bridge design; Fluid dynamics; Machine learning; Neural networks; Tsunamis
• Subject Areas: Bridges and other structures; Design; Highways; Hydraulics and Hydrology;

Filing Info

• Accession Number: 01872732
• Record Type: Research project
• Source Agency: Pacific Northwest Transportation Consortium
• Contract Numbers: 69A3551747110
• Files: UTC, RIP
• Created Date: Feb 7 2023 4:31PM