Neural Basis Functions for Accelerating Solutions to High Mach Euler Equations
This work addresses computational fluid dynamics challenges for high-speed flows, offering a method to accelerate CFD simulations, though it appears incremental as a variation of existing operator learning approaches.
The authors tackled the problem of solving high Mach number Euler equations by proposing Neural Basis Functions (NBF), a novel variation of POD DeepONet that regresses neural networks onto a reduced-order POD basis, and demonstrated that using NBF predictions as initial conditions for a CFD solver accelerated convergence in 2D flow around a cylinder at Mach 10-30.
We propose an approach to solving partial differential equations (PDEs) using a set of neural networks which we call Neural Basis Functions (NBF). This NBF framework is a novel variation of the POD DeepONet operator learning approach where we regress a set of neural networks onto a reduced order Proper Orthogonal Decomposition (POD) basis. These networks are then used in combination with a branch network that ingests the parameters of the prescribed PDE to compute a reduced order approximation to the PDE. This approach is applied to the steady state Euler equations for high speed flow conditions (mach 10-30) where we consider the 2D flow around a cylinder which develops a shock condition. We then use the NBF predictions as initial conditions to a high fidelity Computational Fluid Dynamics (CFD) solver (CFD++) to show faster convergence. Lessons learned for training and implementing this algorithm will be presented as well.