Surrogate modeling of fluid dynamics with a multigrid inspired neural network architecture

Machine Learning with Applications

Chinchun Ooi¹  Quang Tuyen Le² 

[1] Corresponding author.;Department of Fluid Dynamics, Institute of High Performance Computing, 1 Fusionopolis Way, 16-16 Connexis, Singapore 138632, Singapore;

关键词: Surrogate modeling;    Machine learning;    Convolutional Neural Network (CNN);    Multigrid;    Computational Fluid Dynamics (CFD);   

DOI  :  

来源: DOAJ

【 摘 要 】

Algebraic or geometric multigrid methods are commonly used in numerical solvers as they are a multi-resolution method able to handle problems with multiple scales. In this work, we propose a modification to the commonly-used U-Net neural network architecture that is inspired by the principles of multigrid methods, referred to here as U-Net-MG. We then demonstrate that this proposed U-Net-MG architecture can successfully reduce the test prediction errors relative to the conventional U-Net architecture when modeling a set of fluid dynamic problems. In total, we demonstrate an improvement in the prediction of velocity and pressure fields for the canonical fluid dynamics cases of flow past a stationary cylinder, flow past 2 cylinders in out-of-phase motion, and flow past an oscillating airfoil in both the propulsion and energy harvesting modes. In general, while both the U-Net and U-Net-MG models can model the systems well with test RMSEs of less than 1%, the use of the U-Net-MG architecture can further reduce RMSEs by between 20% and 70%.

【 授权许可】

Unknown