skip to main content
Idioma:

Prediction of wall-bounded turbulence from wall quantities using convolutional neural networks

Guastoni, Luca ; Encinar, Miguel P. ; Schlatter, Philipp ; Azizpour, Hossein ; Vinuesa, Ricardo

Journal of physics. Conference series, 2020-04, Vol.1522 (1), p.12022 [Periódico revisado por pares]

Bristol: IOP Publishing

Texto completo disponível

Citações Citado por
  • Título:
    Prediction of wall-bounded turbulence from wall quantities using convolutional neural networks
  • Autor: Guastoni, Luca ; Encinar, Miguel P. ; Schlatter, Philipp ; Azizpour, Hossein ; Vinuesa, Ricardo
  • Assuntos: Artificial neural networks ; Channel flow ; Computational fluid dynamics ; Datasets ; Direct numerical simulation ; Domain names ; Fluid flow ; Mathematical models ; Open channel flow ; Open channels ; Parameters ; Reynolds number ; Statistical methods ; Training ; Turbulence ; Turbulent flow ; Velocity distribution
  • É parte de: Journal of physics. Conference series, 2020-04, Vol.1522 (1), p.12022
  • Descrição: A fully-convolutional neural-network model is used to predict the streamwise velocity fields at several wall-normal locations by taking as input the streamwise and spanwise wall-shear-stress planes in a turbulent open channel flow. The training data are generated by performing a direct numerical simulation (DNS) at a friction Reynolds number of Reτ = 180. Various networks are trained for predictions at three inner-scaled locations (y+ = 15, 30, 50) and for different time steps between input samples Δt+s. The inherent non-linearity of the neural-network model enables a better prediction capability than linear methods, with a lower error in both the instantaneous flow fields and turbulent statistics. Using a dataset with higher Δt+s improves the generalization at all the considered wall-normal locations, as long as the network capacity is sufficient to generalize over the dataset. The use of a multiple-output network, with parallel dedicated branches for two wall-normal locations, does not provide any improvement over two separated single-output networks, other than a moderate saving in training time. Training time can be effectively reduced, by a factor of 4, via a transfer learning method that initializes the network parameters using the optimized parameters of a previously-trained network.
  • Editor: Bristol: IOP Publishing
  • Idioma: Inglês
Voltar para lista de resultados

  • Realização: ABCD-USP USP   Logos de Redes Sociais: Freepik

Buscando em bases de dados remotas. Favor aguardar.