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

Abstract

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 $R{e}_{\tau }=180$. Various networks are trained for predictions at three inner-scaled locations ($y^{+}=15,30,50$) and for different time steps between input samples $\Delta t_s^{+}$. 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 $\Delta t_s^{+}$ 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.

References in corpus (5)

• Machine Learning for Fluid Mechanics
• A critical layer model for turbulent pipe flow
• Accelerating Deep Reinforcement Learning strategies of Flow Control through a multi-environment approach
• Assessment of uncertainties in hot-wire anemometry and oil-film interferometry measurements for wall-bounded turbulent flows
• Machine-aided turbulence theory

Cited by in corpus (8)

• Uncovering near-wall blood flow from sparse data with physics-informed neural networks
• Shallow Neural Networks for Fluid Flow Reconstruction with Limited Sensors
• Deep Neural Networks for Nonlinear Model Order Reduction of Unsteady Flows
• From coarse wall measurements to turbulent velocity fields through deep learning
• Sparse identification of nonlinear dynamics with low-dimensionalized flow representations
• Experimental velocity data estimation for imperfect particle images using machine learning
• Revisiting Tensor Basis Neural Networks for Reynolds stress modeling: application to plane channel and square duct flows
• Deep Learning for Reduced Order Modelling and Efficient Temporal Evolution of Fluid Simulations