Improving CFD simulations by local machine-learned correction
This work addresses the computational cost challenge in CFD for engineering applications, offering an incremental improvement by enhancing coarse mesh simulations with machine-learned corrections.
The authors tackled the high computational cost of CFD simulations by using a machine learning model to predict and correct discretization errors in coarse mesh simulations, achieving a favorable cost/accuracy trade-off with demonstrated speedup while maintaining accuracy in a 3D turbulent channel flow.
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.