Using machine learning to detect the turbulent region in flow past a circular cylinder

• Published in: Journal of fluid mechanics Vol. 905
• Main Authors: Li, Binglin, Yang, Zixuan, Zhang, Xing, He, Guowei, Deng, Bing-Qing, Shen, Lian
• Format: Journal Article
• Language: English
• Published: Cambridge, UK Cambridge University Press 25.12.2020
• Subjects: Circular cylinders; Classification; Clustering; Computational fluid dynamics; Cylinders; Detectors; Flow control; Fluid flow; Fluid mechanics; Interfaces; JFM Papers; Learning algorithms; Machine learning; Mathematical models; Methods; Physics; Reynolds number; Robustness (mathematics); Sensors; Simulation; Strain rate; Tensors; Training; Transport equations; Turbulence; Turbulent flow; Velocity; turbulent transition; wakes

Detecting the turbulent/non-turbulent interface is a challenging topic in turbulence research. In the present study, machine learning methods are used to train detectors for identifying turbulent regions in the flow past a circular cylinder. To ensure that the turbulent/non-turbulent interface is in...