Predicting Coherent Turbulent Structures via Deep Learning

Frontiers in Physics

F. Alcántara-Ávila¹  R. Vinuesa¹  D. Schmekel¹  S. Hoyas² 

[1] FLOW, Engineering Mechanics, KTH Royal Institute of Technology, Stockholm, Sweden;Instituto de Matemática Pura y Aplicada, Universitat Politècnica de València, València, Spain;

关键词: turbulence;    coherent turbulent structures;    machine learning;    convolutional neural networks;    deep learning;   

DOI  :  10.3389/fphy.2022.888832

来源: DOAJ

【 摘 要 】

Turbulent flow is widespread in many applications, such as airplane wings or turbine blades. Such flow is highly chaotic and impossible to predict far into the future. Some regions exhibit a coherent physical behavior in turbulent flow, satisfying specific properties; these regions are denoted as coherent structures. This work considers structures connected with the Reynolds stresses, which are essential quantities for modeling and understanding turbulent flows. Deep-learning techniques have recently had promising results for modeling turbulence, and here we investigate their capabilities for modeling coherent structures. We use data from a direct numerical simulation (DNS) of a turbulent channel flow to train a convolutional neural network (CNN) and predict the number and volume of the coherent structures in the channel over time. Overall, the performance of the CNN model is very good, with a satisfactory agreement between the predicted geometrical properties of the structures and those of the reference DNS data.

【 授权许可】

Unknown