Abstract
In this work, we are studying the use of Deep Convolutional Generative Adversarial Networks (DCGANs) for numerical simulations in the field of Computational Fluid Dynamics (CFD) for engineering problems. We claim that these DCGANs could be used in order to represent in an efficient fashion high-dimensional realistic samples. Let us take the example of fluid flows’ unsteady velocity and pressure fields computation when subjected to random variations associated for example with different design configurations or with different physical parameters such as the Reynolds number and the boundary conditions. The evolution of all these variables is usually very hard to parameterize and to reproduce in a reduced order space. We would like to be able to reproduce the time coherence of these unsteady fields and their variations with respect to design variables or physical ones. We claim that the use of the data generation field in Deep Learning will enable this exploration in numerical simulations of large dimensions for CFD problems in engineering sciences. Therefore, it is important to precise that the training procedure in DCGANs is completely legitimate because we need to explore afterwards large dimensional variabilities within the Partial Differential Equations. In literature it is stated that theoretically the generative model could learn to memorize training examples, but in practice it is shown that the generator did not memorize the training samples and was capable of generating new realistic ones. In this work, we show an application of DCGANs to a 2D incompressible and unsteady fluid flow in a channel with a moving obstacle inside. The input of the DCGAN is a Gaussian vector field of dimension 100 and the outputs are the generated unsteady velocity and pressure fields in the 2D channel with respect to time and to an obstacle position. The training set is constituted of 44 unsteady and incompressible simulations of 450 time steps each, on a cartesian mesh of dimension \(79\times 99\). We discuss the architectural and the optimization hyper-parameters choice in our case, following guidelines from the literature on stable GANs. We quantify the GPU cost needed to train a generative model to the 2D unsteady flow fields, to 892 s on one Nvidia Tesla V100 GPU, for 40 epochs and a batch size equal to 128.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Tompson, J., Schlachter, K., Sprechmann, P., Perlin, K.: Accelerating Eulerian fluid simulation with convolutional networks. arXiv 2016 (2016). https://arxiv.org/abs/1607.03597
Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial networks. In: Proceedings of the International Conference on Neural Information Processing Systems (NIPS 2014), pp. 2672–2680 (2014)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Susskind, J., Anderson, A., and Hinton, G.E.: The Toronto face dataset. Technical report UTML TR 2010-001, U. Toronto (2010)
Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Technical report, University of Toronto (2009)
Goodfellow, I.J.: NIPS 2016 Tutorial. arXiv:1701.00160
Byungsoo, K., Vinicius, C.A., Nils, T., Theodore, K., Markus, G., Barbara, S.: Deep fluids: a generative network for parameterized fluid simulations. Eurographics 38(2), 59–70 (2019)
Inkawhich, N.: Pytorch tutorial, DCGAN. https://pytorch.org/tutorials/beginner/dcgan_faces_tutorial.html
Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. In: Conference paper at ICLR 2016 (2016)
Xie, Y., Franz, E., Chu, M., Thuerey, N.: tempGAN: a temporally coherent, volumetric gan for super-resolution fluid flow. ACM Trans. Graph. 37, 4 (2018). Article 95. arXiv:1801.09710
Akkari, N., Mercier, R., Moureau, V.: Geometrical reduced order modeling (ROM) by proper orthogonal decomposition (POD) for the incompressible Navier Stokes equations. In: 2018 AIAA Aerospace Sciences Meeting, AIAA SciTech Forum, (AIAA 2018-1827) (2018)
Akkari, N., Casenave, F., Moureau, V.: Time stable reduced order modeling by an enhanced reduced order basis of the turbulent and incompressible 3D Navier–Stokes equations. Math. Comput. Appl. 24(45), 2019. http://www.mdpi.com/2297-8747/24/2/45
Akkari, N.: A Velocity Potential Preserving Reduced Order Approach for the Incompressible and Unsteady Navier-stokes Equations. AIAA Scitech forum and exposition (2020)
Akkari, N., Casenave, F., Ryckelynck, D.: A novel Gappy reduced order method to capture non-parameterized geometrical variation in fluid dynamics problems. Working paper (2019). https://hal.archives-ouvertes.fr/hal-02344342
Abgrall, R., Beaugendre, H., Dobrzynski, C.: An immersed boundary method using unstructured anisotropic mesh adaptation combined with level-sets and penalization techniques. J. Comput. Phys. 257(Part A), 83–101 (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Akkari, N., Casenave, F., Perrin, ME., Ryckelynck, D. (2020). Deep Convolutional Generative Adversarial Networks Applied to 2D Incompressible and Unsteady Fluid Flows. In: Arai, K., Kapoor, S., Bhatia, R. (eds) Intelligent Computing. SAI 2020. Advances in Intelligent Systems and Computing, vol 1229. Springer, Cham. https://doi.org/10.1007/978-3-030-52246-9_18
Download citation
DOI: https://doi.org/10.1007/978-3-030-52246-9_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-52245-2
Online ISBN: 978-3-030-52246-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)