Platooning for Improved Safety and Efficiency of Semi-Trucks (PISES – III)

In fluid physics, data-driven models to enhance or accelerate solution methods are becoming increasingly popular for many application domains, such as alternatives to turbulence closures, system surrogates, or for new physics discovery. In the context of reduced order models of high-dimensional time-dependent fluid systems, machine learning methods grant the benefit of automated learning from data, but the burden of a model lies on its reduced-order representation of both the fluid state and physical dynamics. In this work, the authors build a physics-constrained, data-driven reduced order model for the Navier-Stokes equations to approximate spatio-temporal turbulent fluid dynamics. The model design choices mimic numerical and physical constraints by, for example, implicitly enforcing the incompressibility constraint and utilizing continuous Neural Ordinary Differential Equations for tracking the evolution of the differential equation. The authors demonstrate this technique on three-dimensional, moderate Reynolds number turbulent fluid flow. In assessing the statistical quality and characteristics of the machine-learned model through rigorous diagnostic tests, the authors find that the model is capable of reconstructing the dynamics of the flow over large integral timescales, favoring accuracy at the larger length scales. More significantly, comprehensive diagnostics suggest that physically-interpretable model parameters, corresponding to the representations of the fluid state and dynamics, have attributable and quantifiable impact on the quality of the model predictions and computational complexity.

• Record URL:
  https://ppms.cit.cmu.edu/media/project_files/Final_Report_-_309.pdf
• Record URL:
  https://arxiv.org/abs/2110.11528
• 
• Summary URL:
  https://ppms.cit.cmu.edu/projects/detail/309
• Record URL:
  https://rosap.ntl.bts.gov/view/dot/60387
• Supplemental Notes:
  • This document was sponsored by the U.S. Department of Transportation, University Transportation Centers Program. Contains: Validation and parameterization of a novel physics-constrained neural dynamics model applied to turbulent fluid flow.
• Corporate Authors:

  Mobility21 (University Transportation Center)

  Heinz College, Carnegie Mellon University
  5000 Forbes Ave, Hamburg Hall
  Pittsburgh, PA  United States  15213-3890

  Office of the Assistant Secretary for Research and Technology

  University Transportation Centers Program
  Department of Transportation
  Washington, DC  United States  20590
• Authors:
  • Viswanathan, Venkatasubramanian
  • 0000-0003-1060-5495
  • Shankar, Varun
  • 0000-0002-0332-8840
  • Portwood, Gavin D
  • 0000-0002-5685-4000
  • Mohan, Arvind T
  • 0000-0002-9434-7691
  • Mitra, Peetak P
  • 0000-0002-8548-0087
  • Krishnamurthy, Dilip
  • 0000-0001-8231-5492
  • Rackauckas, Christopher
  • 0000-0001-5850-0663
  • Wilson, Lucas A
  • 0000-0002-0686-3152
  • Schmidt, David P
  • 0000-0003-4876-1143
• Publication Date: 2021-11

Language

• English

Media Info

• Media Type: Digital/other
• Edition: Final Research Report
• Features: Figures; References;
• Pagination: 11p

Subject/Index Terms

• TRT Terms: Fluid dynamics; Machine learning; Traffic platooning
• Identifier Terms: Reynolds-Averaged Navier-Stokes Equations
• Subject Areas: Motor Carriers; Operations and Traffic Management; Planning and Forecasting;

Filing Info

• Accession Number: 01790436
• Record Type: Publication
• Contract Numbers: 69A3551747111
• Files: UTC, NTL, TRIS, ATRI, USDOT
• Created Date: Dec 6 2021 5:24PM