From coarse wall measurements to turbulent velocity fields through deep learning

Abstract

This work evaluates the applicability of super-resolution generative adversarial networks (SRGANs) as a methodology for the reconstruction of turbulent-flow quantities from coarse wall measurements. The method is applied both for the resolution enhancement of wall fields and the estimation of wall-parallel velocity fields from coarse wall measurements of shear stress and pressure. The analysis has been carried out with a database of a turbulent open-channel flow with a friction Reynolds number [Formula: see text] generated through direct numerical simulation. Coarse wall measurements have been generated with three different downsampling factors [Formula: see text] from the high-resolution fields, and wall-parallel velocity fields have been reconstructed at four inner-scaled wall-normal distances [Formula: see text]. We first show that SRGAN can be used to enhance the resolution of coarse wall measurements. If compared with the direct reconstruction from the sole coarse wall measurements, SRGAN provides better instantaneous reconstructions, in terms of both mean-squared error and spectral-fractional error. Even though lower resolutions in the input wall data make it more challenging to achieve highly accurate predictions, the proposed SRGAN-based network yields very good reconstruction results. Furthermore, it is shown that even for the most challenging cases, the SRGAN is capable of capturing the large-scale structures that populate the flow. The proposed novel methodology has a great potential for closed-loop control applications relying on non-intrusive sensing.

Application and Advances in Radiographic and Novel Technologies Used for Non-Intrusive Object Inspection

“…Deep learning, also referred to as deep structured learning, is a branch of machine learning, which is based on a set of algorithms aiming to simulate higher level abstraction in datasets, implementing depth graphs with several processing layers built up with several linear or non-linear transformations. Deep learning architectures include recurrent neural networks [ 84 ], convolutional neural networks [ 85 , 86 , 87 ], deep belief networks, and others [ 88 ], including more sophisticated approaches such as generative adversarial networks (GANs) which can be effectively used to improve the resolution of the obtained images [ 89 ]. They could be applied to such fields, as drug design and recognition, bioinformatics, computer visioning, image recognition, and analysis [ 90 , 91 , 92 , 93 ], facial analysis [ 94 , 95 , 96 , 97 , 98 ], etc.…”

Flow Control in Wings and Discovery of Novel Approaches via Deep Reinforcement Learning

“…Note that these authors also took into account the data by Kornilov and Boiko [106] to formulate a more realistic estimate of the power consumption by blowing, and they reported a net-energy saving of around 5%. It is interesting to note that other data-driven methods may help to model the near-wall region and, consequently, may provide novel venues for improved flow control [107][108][109][110][111].…”

Machine-Learning Methods for Complex Flows

“…Another area where ML has shown quite high potential is non-intrusive sensing, where the information measured at the wall can be used to obtain details of the flow without disrupting it. This has been achieved via convolutional neural networks (CNNs) [21], as well as generative adversarial networks (GANs) [22], which have shown great potential for super-resolution tasks in turbulence [23]. Flow control is another topic where deep learning exhibits potential, in particular, through deep reinforcement learning [24,25].…”