Solving the fluid pressure with an iterative multi-resolution guided network
Authors: 
Rong-Jie Xu, Bo RenAuthors Info & Claims
Rong-Jie Xu, Bo RenAuthors Info & ClaimsAbstract
In Eulerian methods, the simulation of an incompressible fluid field requires a pressure field solution, which takes a large amount of time and computation resources to solve a large coarse linear system. The pressure solver has two mathematical features. The first is that it obtains the pressure solution from a velocity divergence distribution in high-dimensional space. The second is that the pressure is iteratively solved in the projection step. Based on these two features, we investigate a convolutional-based neural network, which learns to map the fluid quantities to pressure solution iteratively by inferring from multiple grid scales. Our proposed network extracts features from multiple scales and then aligns them to obtain a pressure field in the original resolution. We trim our network structure to be compact and fast and design it to be iterative like to improve performance. Our approach requires less computation cost, while it achieves comparable performance with recently proposed data-driven methods. Our method can easily be parallelized in GPU devices, and we demonstrate its speed-up ability with the fluid field in larger input scenes.
References
[1]
Bridson R Fluid Simulation for Computer Graphics 2015 Boca Raton AK Peters/CRC Press
[2]
Chen DY, Tian XP, Shen YT, and Ouhyoung M On visual similarity based 3d model retrieval Comput. Graph. Forum 2003 22 223-232
[3]
Cornelis J, Bender J, Gissler C, Ihmsen M, and Teschner M An optimized source term formulation for incompressible SPH Vis. Comput. 2019 35 4 579-590
[4]
Dupont TF and Liu Y Back and forth error compensation and correction methods for removing errors induced by uneven gradients of the level set function J. Comput. Phys. 2003 190 1 311-324
[5]
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
[6]
Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1125–1134 (2017)
[7]
Jeong S, Solenthaler B, Pollefeys M, Gross M, et al. Data-driven fluid simulations using regression forests ACM Trans. Graph. (TOG) 2015 34 6 199
[8]
Kim B, Azevedo VC, Thuerey N, Kim T, Gross M, and Solenthaler B Deep fluids: a generative network for parameterized fluid simulations Comput. Graph. Forum 2019 38 59-70
[9]
Kim T, Thürey N, James D, and Gross M Wavelet turbulence for fluid simulation ACM Trans. Graph. (TOG) 2008 27 20
[10]
Lagaris IE, Likas A, and Fotiadis DI Artificial neural networks for solving ordinary and partial differential equations IEEE Trans. Neural Netw. 1998 9 5 987-1000
[11]
Lagaris IE, Likas AC, and Papageorgiou DG Neural-network methods for boundary value problems with irregular boundaries IEEE Trans. Neural Netw. 2000 11 5 1041-1049
[12]
LeCun Y, Bengio Y, et al. Convolutional networks for images, speech, and time series Handb Brain Theory Neural Netw 1995 3361 10 1995
[13]
Lim, B., Son, S., Kim, H., Nah, S., Mu Lee, K.: Enhanced deep residual networks for single image super-resolution. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp. 136–144 (2017)
[14]
Lim JG, Kim BJ, and Hong JM Water simulation using a responsive surface tracking for flow-type changes Vis. Comput. 2016 32 5 641-651
[15]
Losasso, F., Gibou, F., Fedkiw, R.: Simulating water and smoke with an octree data structure. In: ACM SIGGRAPH 2004 Papers, pp. 457–462 (2004)
[16]
Ma P, Tian Y, Pan Z, Ren B, and Manocha D Fluid directed rigid body control using deep reinforcement learning ACM Trans. Graph. (TOG) 2018 37 4 96
[17]
McAdams, A., Sifakis, E., Teran, J.: A parallel multigrid poisson solver for fluids simulation on large grids. In: Proceedings of the 2010 ACM SIGGRAPH/Eurographics Symposium on Computer Animation, pp. 65–74. Eurographics Association (2010)
[18]
Monaghan JJ Smoothed particle hydrodynamics Ann. Rev. Astron. Astrophys. 1992 30 1 543-574
[19]
Raissi, M., Perdikaris, P., Karniadakis, G.E.: Physics informed deep learning (part i): Data-driven solutions of nonlinear partial differential equations. arXiv preprint arXiv:1711.10561 (2017)
[20]
Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: International Conference on Medical image computing and computer-assisted intervention, pp. 234–241. Springer (2015)
[21]
Selle A, Fedkiw R, Kim B, Liu Y, and Rossignac J An unconditionally stable maccormack method J. Sci. Comput. 2008 35 2–3 350-371
[22]
Sirignano J and Spiliopoulos K Dgm: a deep learning algorithm for solving partial differential equations J. Comput. Phys. 2018 375 1339-1364
[23]
Stam J Stable fluids Siggraph 1999 99 121-128
[24]
Szegedy, C., Toshev, A., Erhan, D.: Deep neural networks for object detection. In: Proceedings of the 26th international conference on neural information processing systems, vol 2, no. 9, pp. 2553–2561. Curran Associates Inc., Lake Tahoe, Nevada (2013). https://doi.org/10.5555/2999792.2999897
[25]
Temam, R.: In: Lions, J.L., Papanicolaou, G., Rockafellar, R.T. (eds.) Navier Stokes equations: theory and numerical analysis, 2nd edn, p. 530. North Holland (1979). https://www.elsevier.com/books/navier-stokes-equations/temam/978-0-444-85307-3
[26]
Thuerey, N., Pfaff, T.: MantaFlow (2018). http://mantaflow.com
[27]
Thuerey N, Weißenow K, Prantl L, and Hu X Deep learning methods for Reynolds-averaged Navier-Stokes simulations of airfoil flows AIAA J. 2019 58 1-12
[28]
Tompson, J., Schlachter, K., Sprechmann, P., Perlin, K.: Accelerating eulerian fluid simulation with convolutional networks. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 3424–3433. JMLR. org (2017)
[29]
Wiewel S, Becher M, and Thuerey N Latent Space Physics: Towards Learning the Temporal Evolution of Fluid Flow. Computer Graphics Forum 2019 Amsterdam Wiley Online Library 71-82
[30]
Xie Y, Franz E, Chu M, and Thuerey N tempogan: a temporally coherent, volumetric gan for super-resolution fluid flow ACM Trans. Graph. (TOG) 2018 37 4 95
[31]
Yang C, Yang X, and Xiao X Data-driven projection method in fluid simulation Comput. Anim. Virtual Worlds 2016 27 3–4 415-424
Index Terms
- Solving the fluid pressure with an iterative multi-resolution guided network
Index terms have been assigned to the content through auto-classification.
Recommendations
A fast pressure-correction method for incompressible two-fluid flows
We have developed a new pressure-correction method for simulating incompressible two-fluid flows with large density and viscosity ratios. The method's main advantage is that the variable coefficient Poisson equation that arises in solving the ...
Numerical simulations of fluid pressure in the human eye
In this article we present computational results for the pressure in the human eye. Pressure computations for different flow rates of the aqueous humor, viscosity of the aqueous humor, and permeability of the trabecular meshwork are given. The fluid ...
Comments
Information & Contributors
Information
Published In
© Springer-Verlag GmbH Germany, part of Springer Nature 2021.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 01 February 2022
Accepted: 12 November 2020
Author Tags
Qualifiers
- Research-article
Funding Sources
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 19 Oct 2024
Other Metrics
Citations
View Options
View options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in