Abstract
Computational Fluid Dynamics (CFD) simulations are useful to the field of engineering design as they provide deep insights on product or system performance without the need to construct and test physical prototypes. However, they can be very computationally intensive to run. Machine learning methods have been shown to reconstruct high-resolution single-phase turbulent fluid flow simulations from low-resolution inputs. This offers a potential avenue towards alleviating computational cost in iterative engineering design applications. However, little work thus far has explored the application of machine learning image super-resolution methods to multiphase fluid flow (which is important for important for emerging fields such as marine hydrokinetic energy conversion). In this work, we apply a modified version of the Super-Resolution Generative Adversarial Network (SRGAN) model to a multiphase turbulent fluid flow problem, specifically to reconstruct fluid phase fraction at a higher resolution. Two models were created in this work, one with a simple physics-constrained loss function and one without, and the results are discussed and analyzed. We found that both models were able to significantly outperform non-machine learning upsampling methods and can preserve an impressive amount of detail and nuance, showing the versatility of the SRGAN model for upsampling fluid simulations. However, the difference in accuracy between the two models is quite minimal. This indicates that, for these contexts studied here, the additional complexity of a physics-informed approach may not be justified.
