EUVIMEDEUVIMED entdecken
Crossref

DeepTRNet: Time-resolved reconstruction of flow around a circular cylinder via spatiotemporal deep neural networks

Shujin Laima, Xuxi Zhou, Xiaowei Jin, Donglai Gao, Hui Li

Physics of Fluids · 01.01.2023 · 35 (1)

DOI: 10.1063/5.0129049 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Physics of Fluids, online erschienen am 05.01.2023. Verfasst von Shujin Laima und 4 weiteren Autor:innen. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 48 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Guangdong Science and Technology Department, Natural Science Foundation of Heilongjiang Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We propose spatiotemporal deep neural networks for the time-resolved reconstruction of the velocity field around a circular cylinder (DeepTRNet) based only on two flow data types: the non-time-resolved wake velocity field and sparse time-resolved velocity measurements at specific discrete points. The DeepTRNet consists of two operations, i.e., compact spatial representations extraction and sequential learning. We use the convolutional autoencoder (CAE) in DeepTRNet to extract compact spatial representations embedded in the non-time-resolved velocity field. The nonlinear CAE modes and corresponding CAE coefficients are thus obtained. Based on the nonlinear correlation analysis of the velocity field, we use the bidirectional recurrent neural networks (RNN) with the gated recurrent unit for mapping the sparse time-resolved velocity measurements to the CAE coefficients via sequential learning. The early stopping technique is used to train the DeepTRNet to avoid overfitting. With the well-trained DeepTRNet, we can reconstruct the time-resolved velocity field around the circular cylinder. The DeepTRNet is verified on the simulated datasets at two representative Reynolds numbers, 200 and 500, and the experimental dataset at Reynolds number 3.3 × 104 with the steady jet at the rear stagnation point of the cylinder. We systematically compare the DeepTRNet method and the RNN-proper orthogonal decomposition (POD) approach. The DeepTRNet can obtain the accurate time-resolved velocity field depending on the two data types mentioned above. The DeepTRNet method outperforms the RNN-POD method in the reconstruction accuracy, especially for the reconstruction of small-scale flow structures. In addition, we get the reliable velocity field even for the high-frequency components.

Förderung

  • National Natural Science Foundation of China
  • Guangdong Science and Technology Department
  • Natural Science Foundation of Heilongjiang Province
  • Postdoctoral Scientific Research Development Fund of Heilongjiang Province

Zitieren

APA

Laima, S., Zhou, X., Jin, X., Gao, D., & Li, H. (2023). DeepTRNet: Time-resolved reconstruction of flow around a circular cylinder via spatiotemporal deep neural networks. Physics of Fluids, 35(1). https://doi.org/10.1063/5.0129049

Vancouver

Laima S, Zhou X, Jin X, Gao D, Li H. DeepTRNet: Time-resolved reconstruction of flow around a circular cylinder via spatiotemporal deep neural networks. Physics of Fluids. 2023;35(1). doi:10.1063/5.0129049

BibTeX
@article{Laima2023,
  author = {Laima, Shujin and Zhou, Xuxi and Jin, Xiaowei and Gao, Donglai and Li, Hui},
  title = {DeepTRNet: Time-resolved reconstruction of flow around a circular cylinder via spatiotemporal deep neural networks},
  journal = {Physics of Fluids},
  year = {2023},
  volume = {35},
  number = {1},
  doi = {10.1063/5.0129049}
}
Kostenlos starten →