Physics-Constrained Supersonic Flow Prediction across a Discrete Speed Ladder in a Confined Channel

Deep learning models show great promise for rapid computational fluid dynamics (CFD), yet the comparative effectiveness of data-driven and physics-informed approaches for complex high-speed flows has been unclear. We conducted a rigorous comparative analysis of purely data-driven and physics-constrained neural network models for predicting flow fields in confined channels across a wide Mach number range. The analysis systematically evaluated the model’s performance in interpolating and extrapolating flow conditions. The overall error level remained around 0.1%. The results demonstrate that the introduction of physics-based loss functions is critical for enhancing the physical consistency of predictions. Although purely data-driven models may achieve fewer local errors in certain regions, the physics-constrained approach ensures solutions that are globally consistent with governing physical principles, even near strong discontinuities like shock waves. This comes with the added benefit of significantly improved training efficiency. For these reasons, our work demonstrates that physics constraints are indispensable for generating physically plausible results in complex flow regimes. The developed model achieves rapid flow field prediction in under 1 s, offering a robust and efficient tool for the rapid iteration of supersonic flow designs.