Two-stage attention Unet3d model under airfoil 3D turbulence field prediction with SDF expression

Abstract

Various fluid mechanics software, due to inherent factors such as algorithms and boundary conditions, cannot quickly simulate 3D flow fields in batches, and the calculation of each model still takes a lot of time.In order to realize the rapid prediction of the three-dimensional flow field around the airfoil, this paper uses a new SDF geometric expression to describe the shape of the airfoil, and combines the prediction accuracy of the velocity and pressure channels, and proposes a two-stage Unet3d convolution prediction model based on the SDF expression, which greatly improves the prediction accuracy of the pressure channel.In addition, the introduced two-stage convolutional network is optimized by combining lightweight network and attention mechanism. On the premise of ensuring the accuracy of the network, it can effectively reduce the parameters of the network model and improve the operating efficiency of the network. The two-stage method was tested on the Naca0012 and RAE2822 three-dimensional datasets, and the average accuracy rates were 95.44% and 98.22% respectively, which were 2 to 3 percentage points higher than the original method.

Keywords

deep learning 3D flow field prediction lightweight network two-stage convolution attention mechanism

Get full access to this article

View all access options for this article.

References

McKetta

J.J.

, Turbulence: An introduction to it’s mechanism and theory (hinze, jo), 1960.

Sharp

Kendra V.

and Adrian

Ronald J.

, Transition from laminar to turbulent flow in liquid filled microtubes, Experiments in fluids 36 (2004), 741–747.

Tritton

David J.

, Physical fluid dynamics, Springer Science & Business Media, 2012.

Swinney

Harry L.

and Gollub

Jerry P.

, Hydrodynamic instabilities and the transition to turbulence, Hydrodynamic Instabilities and the Transition to Turbulence, 1981.

Wilcox

David C.

, et al., Turbulence modeling for CFD, volume 2. DCW industries La Canada, CA, 1998.

Schmidhuber

, Deep learning in neural networks: An overview, Neural networks 61 (2015), 85–117.

Hennigh

, Lat-net: compressing lattice boltzmann flow simulations using deep neural networks, arXiv preprint arXiv:1705.09036, 2017.

Zhang

, Sung

W.J.

and Mavris

Dimitri N.

, Application of convolutional neural network to predict airfoil lift coefficient. In 2018 AIAA/ASCE/AHS/ASC structures, structural dynamics, and materials conference (2018), pp. 1903.

Thuerey

, Weisenow

, Prantl

and Hu

, Deep learning methods for reynolds-averaged navier–stokes simulations of airfoil flows, AIAA Journal 58(1) (2020), 25–36.

10.

Russo

and Smereka

, A remark on computing distance functions, Journal of Computational Physics 163(1) (2000), 51–67.

11.

Guo

, Li

and Iorio

, Convolutional neural networks for steady flow approximation. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining (2016), pp. 481–490.

12.

Bhatnagar

, Afshar

, Pan

, Duraisamy

and Kaushik

, Prediction of aerodynamic flow fields using convolutional neural networks, Computational Mechanics 64 (2019), 525–545.

13.

Duru

, Alemdar

and Baran

Ö. Uğraş

, Cnnfoil: Convolutional encoder decoder modeling for pressure fields around airfoils, Neural Computing and Applications 33(12) (2021), 6835–6849.

14.

Rogers

D.F.

, Adams

J.A.

, Mathematical elements for computer graphics, McGraw-Hill, Inc., 1989 .

15.

Woo

, Park

, Lee

J.-Y.

and Kweon

In So

. Cbam: Convolutional block attention module. In Proceedings of the European conference on computer vision (ECCV) (2018), pp. 3–19.

16.

Selig

M.S.

UIUC airfoil data site, Department of Aeronautical and Astronautical Engineering University of Illinois at Urbana-Champaign, 1996.

17.

Szegedy

, Liu

, Jia

, Sermanet

, Reed

, Anguelov

, Erhan

, Vanhoucke

and Rabinovich

, Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition (2015), pp. 1–9.

18.

, Wang

, Zhang

, Wang

and Jiang

, Satellite image super-resolution via multi-scale residual deep neural network, Remote Sensing 11(13) (2019), 1588.

19.

Mengqian

and Li

, Coarse-to-fine two-stage convolutional neural network algorithm, Journal of Frontiers of Computer Science & Technology 15(8) (2021), 1501.

20.

Wang

, Wu

, Zhu

, Li

, Zuo

and Hu

, Eca-net: Efficient channel attention for deep convolutional neural networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (2020), pp. 11534–11542.

21.

Iandola

F.N.

, Han

, Moskewicz

M.W.

, Ashraf

, Dally

W.J.

and Keutzer

, Squeezenet: Alexnet-level accuracy with 50x fewer parameters and <0.5 mb model size. arXiv preprint arXiv:1602.07360, 2016.

22.

Howard

A.G.

, Zhu

, Chen

, Kalenichenko

, Wang

, Weyand

, Andreetto

and Adam

, Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXivpreprint arXiv:1704.04861, 2017.

23.

Kaiser

, Gomez

A.N.

and Chollet

, Depthwise separable convolutions for neural machine translation. arXiv preprint arXiv:1706.03059, 2017.

24.

Zhang

, Zhou

, Lin

and Sun

, Shufflenet: An extremely efficient convolutional neural network for mobile devices. In Proceedings of the IEEE conference on computer vision and pattern recognition (2018), pp. 6848–6856.