An interpretable framework of data-driven turbulence modeling using deep neural networks

• Published in: Physics of fluids (1994) Vol. 33; no. 5
• Main Author: Vinuesa, Ricardo
• Format: Journal Article
• Language: English
• Published: Melville American Institute of Physics 01.05.2021
• Subjects: Artificial neural networks; Aspect ratio; Computational fluid dynamics; Constraints; Fluid dynamics; Fluid flow; Knowledge representation; Machine learning; Modelling; Physics; Realizability; Reynolds number; Reynolds stress; Three dimensional flow; Training; Turbulence models; Turbulent flow

Reynolds-averaged Navier–Stokes simulations represent a cost-effective option for practical engineering applications, but are facing ever-growing demands for more accurate turbulence models. Recently, emerging machine learning techniques have had a promising impact on turbulence modeling, but are st...