Back to Search
Start Over
Improving CFD simulations by local machine-learned correction
- Source :
- In ASME International Mechanical Engineering Congress and Exposition, vol. 87660, p. V009T10A062. American Society of Mechanical Engineers, 2023
- Publication Year :
- 2023
-
Abstract
- High-fidelity computational fluid dynamics (CFD) simulations for design space explorations can be exceedingly expensive due to the cost associated with resolving the finer scales. This computational cost/accuracy trade-off is a major challenge for modern CFD simulations. In the present study, we propose a method that uses a trained machine learning model that has learned to predict the discretization error as a function of largescale flow features to inversely estimate the degree of lost information due to mesh coarsening. This information is then added back to the low-resolution solution during runtime, thereby enhancing the quality of the under-resolved coarse mesh simulation. The use of a coarser mesh produces a non-linear benefit in speed while the cost of inferring and correcting for the lost information has a linear cost. We demonstrate the numerical stability of a problem of engineering interest, a 3D turbulent channel flow. In addition to this demonstration, we further show the potential for speedup without sacrificing solution accuracy using this method, thereby making the cost/accuracy trade-off of CFD more favorable.<br />Comment: 7 pages, under review at ASME IMECE 2023 conference
- Subjects :
- Physics - Fluid Dynamics
Computer Science - Machine Learning
Subjects
Details
- Database :
- arXiv
- Journal :
- In ASME International Mechanical Engineering Congress and Exposition, vol. 87660, p. V009T10A062. American Society of Mechanical Engineers, 2023
- Publication Type :
- Report
- Accession number :
- edsarx.2305.00114
- Document Type :
- Working Paper
- Full Text :
- https://doi.org/10.1115/IMECE2023-113724