EUVIMEDEUVIMED entdecken
Crossref

Fast fluid–structure interaction simulation method based on deep learning flow field modeling

Jiawei Hu, Zihao Dou, Weiwei Zhang

Physics of Fluids · 01.04.2024 · 36 (4)

DOI: 10.1063/5.0200188 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Physics of Fluids, online erschienen am 01.04.2024. Verfasst von Jiawei Hu und 2 weiteren Autor:innen. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 46 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Numerical Wind Tunnel Project of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid acquisition of high-fidelity flow field information is of great significance for engineering applications such as multi-field coupling. Current research in flow field modeling predominantly focuses on low Reynolds numbers and periodic flows, exhibiting weak generalization capabilities and notable issues with temporal inferring error accumulation. Therefore, we establish a reduced order model (ROM) based on Convolutional Auto-Encoder (CAE) and Long Short-Term Memory (LSTM) neural network and propose an unsteady flow field modeling method for the airfoil with a high Reynolds number and strong nonlinear characteristics. The attention mechanism and weak physical constraints are integrated into the model architecture to improve the modeling accuracy. A broadband excitation training strategy is proposed to overcome the error accumulation problem of long-term inferring. With only a small amount of latent codes, the relative error of the flow field reconstructed by CAE can be less than 5‰. By training LSTM with broadband excitation signals, stable dynamic evolution can be achieved in the time dimension. CAE-LSTM can accurately predict the forced response and complex limit cycle behavior of the airfoil in a wide range of amplitude and frequency under subsonic/transonic conditions. The relative errors of predicted variables and integral force are less than 1%. The fluid–structure interaction framework is built by coupling the ROM and motion equations of the structure. CAE-LSTM predicts the time series response of pitch displacement and moment coefficient at different reduced frequencies, which is in good agreement with computational fluid dynamics, and the simulation time savings exceed one order of magnitude.

Förderung

  • National Natural Science Foundation of China
  • National Numerical Wind Tunnel Project of China

Zitieren

APA

Hu, J., Dou, Z., & Zhang, W. (2024). Fast fluid–structure interaction simulation method based on deep learning flow field modeling. Physics of Fluids, 36(4). https://doi.org/10.1063/5.0200188

Vancouver

Hu J, Dou Z, Zhang W. Fast fluid–structure interaction simulation method based on deep learning flow field modeling. Physics of Fluids. 2024;36(4). doi:10.1063/5.0200188

BibTeX
@article{Hu2024,
  author = {Hu, Jiawei and Dou, Zihao and Zhang, Weiwei},
  title = {Fast fluid–structure interaction simulation method based on deep learning flow field modeling},
  journal = {Physics of Fluids},
  year = {2024},
  volume = {36},
  number = {4},
  doi = {10.1063/5.0200188}
}
Kostenlos starten →