Efficient temporal prediction of compressible flows in irregular domains using Fourier neural operators
This work addresses the challenge of simulating compressible flows in irregular domains for computational fluid dynamics applications, representing an incremental improvement by adapting existing neural operator methods to handle temporal predictions and irregular geometries.
This paper tackles the problem of predicting the temporal evolution of high-speed compressible fluids in irregular domains using Fourier Neural Operators, achieving high accuracy with maximum relative L2 errors of 0.78%, 0.57%, and 0.35% for pressure, temperature, and velocity, respectively, while significantly surpassing traditional methods in computational efficiency.
This paper investigates the temporal evolution of high-speed compressible fluids in irregular flow fields using the Fourier Neural Operator (FNO). We reconstruct the irregular flow field point set into sequential format compatible with FNO input requirements, and then embed temporal bundling technique within a recurrent neural network (RNN) for multi-step prediction. We further employ a composite loss function to balance errors across different physical quantities. Experiments are conducted on three different types of irregular flow fields, including orthogonal and non-orthogonal grid configurations. Then we comprehensively analyze the physical component loss curves, flow field visualizations, and physical profiles. Results demonstrate that our approach significantly surpasses traditional numerical methods in computational efficiency while achieving high accuracy, with maximum relative $L_2$ errors of (0.78, 0.57, 0.35)% for ($p$, $T$, $\mathbf{u}$) respectively. This verifies that the method can efficiently and accurately simulate the temporal evolution of high-speed compressible flows in irregular domains.