4.7 Article

Convolutional-network models to predict wall-bounded turbulence from wall quantities

期刊

JOURNAL OF FLUID MECHANICS
卷 928, 期 -, 页码 -

出版社

CAMBRIDGE UNIV PRESS
DOI: 10.1017/jfm.2021.812

关键词

turbulence simulation

资金

  1. Swedish e-Science Research Centre (SeRC)
  2. G. Gustafsson Foundation
  3. Knut and Alice Wallenberg (KAW) Foundation
  4. European Research Council (ERC) [ERC-2014.AdG-669505]
  5. project ARTURO - Spanish State Research Agency [PID2019-109717RB-I00/AEI/10.13039/501100011033]

向作者/读者索取更多资源

Two convolutional neural network models were trained to predict velocity-fluctuation fields in turbulent open-channel flow, with one directly predicting fluctuations and the other reconstructing flow fields using a linear combination of orthonormal basis functions. Both models outperformed traditional methods in predicting nonlinear interactions in the flow.
Two models based on convolutional neural networks are trained to predict the two-dimensional instantaneous velocity-fluctuation fields at different wall-normal locations in a turbulent open-channel flow, using the wall-shear-stress components and the wall pressure as inputs. The first model is a fully convolutional neural network (FCN) which directly predicts the fluctuations, while the second one reconstructs the flow fields using a linear combination of orthonormal basis functions, obtained through proper orthogonal decomposition (POD), and is hence named FCN-POD. Both models are trained using data from direct numerical simulations at friction Reynolds numbers Re-tau = 180 and 550. Being able to predict the nonlinear interactions in the flow, both models show better predictions than the extended proper orthogonal decomposition (EPOD), which establishes a linear relation between the input and output fields. The performance of the models is compared based on predictions of the instantaneous fluctuation fields, turbulence statistics and power-spectral densities. FCN exhibits the best predictions closer to the wall, whereas FCN-POD provides better predictions at larger wall-normal distances. We also assessed the feasibility of transfer learning for the FCN model, using the model parameters learned from the Re-tau = 180 dataset to initialize those of the model that is trained on the Re-tau = 550 dataset. After training the initialized model at the new Ret, our results indicate the possibility of matching the reference-model performance up to y(+) = 50, with 50% and 25% of the original training data. We expect that these non-intrusive sensing models will play an important role in applications related to closed-loop control of wall-bounded turbulence.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据