A deep learning super-resolution model for turbulent image upscaling and its application to shock wave–boundary layer interaction

Abstract

Upscaling flow features from coarse-grained data is paramount for extensively utilizing computational physics methods across complex flow, acoustics, and aeroelastic environments where direct numerical simulations are computationally expensive. This study presents a deep learning flow image model for upscaling turbulent flow images from coarse-grained simulation data of supersonic shock wave–turbulent boundary layer interaction. It is shown for the first time that super-resolution can be achieved using only the coarsest-grained data as long as the deep learning training is performed using hundreds of fine-grained data. The unsteady pressure data are used in training due to their importance in aeroelasticity and acoustic fatigue occurring on aerospace structures. The effect on the number of images and their resolution features used in training, validation, and prediction is investigated regarding the model accuracy obtained. It is shown that the deep learning super-resolution model provides accurate spectra results, thus confirming the approach's effectiveness.

From Sparse to Dense Representations in Open Channel Flow Images with Convolutional Neural Networks

“…Common values for successful models range between PSNR = 30-40 dB. Nevertheless, higher values have been reported by the multiple path super-resolution convolutional neural network (MPSRC) [30], which has given a value of PSNR > 50.0 dB, while the recent deep learning flow image (DELFI) has also achieved high accuracy and architecture simplicity, with PSNR ∼ = 39 dB [31].…”