Learning slosh dynamics by means of data
In this work we study several learning strategies for fluid sloshing problems based on data. In essence, a reduced-order model of the dynamics of the free surface motion of the fluid is developed under rigorous thermodynamics settings. This model is extracted from data by exploring several strategies. First, a linear one, based on the employ of Proper Orthogonal Decomposition techniques is analyzed. Second, a strategy based on the employ of Locally Linear Embedding is studied. Finally, Topological Data Analysis is employed to the same end. All the three distinct possibilities rely on a numerical integration scheme to advance the dynamics in time. This thermodynamically consistent integrator is developed on the basis of the General Equation for Non-Equilibrium Reversible–Irreversible Coupling, GENERIC [M. Grmela and H.C Oettinger (1997). Phys. Rev. E. 56 (6): 6620–6632], framework so as to guarantee the satisfaction of first principles (particularly, the laws of thermodynamics). We show how the resulting method employs a few degrees of freedom, while it allows for a realistic reconstruction of the fluid dynamics of sloshing processes under severe real-time constraints. The proposed method is shown to run faster than real time in a standard laptop.
KeywordsData-driven fluid simulation Model order reduction GENERIC formalism Real-time simulation
This work has been supported by the Regional Government of Aragon and the European Social Fund, research group T24 17R. The support given by the ESI Group to F. Ch. through the Chair at ENSAM ParisTech, as well as the funding provided to E.C., D.G. and I.A. through the project “Simulated Reality: An intelligence augmentation system based on Hybrid Twins and Augmented Reality” is gratefully acknowledged.
- 2.Bender J, Koschier D (2015) Divergence-free smoothed particle hydrodynamics. In: Proceedings of the 14th ACM SIGGRAPH/eurographics symposium on computer animation, ACM. pp 147–155Google Scholar
- 8.Español P (2004) Statistical mechanics of coarse-graining. Springer, Berlin, pp 69–115Google Scholar
- 14.Ibañez R, Abisset-Chavanne E, Gonzalez D, Duval JL, Cueto E, Chinesta F (2018) Hybrid constitutive modeling: Data-driven learning of corrections to plasticity models. Int J Mater FormGoogle Scholar
- 18.Kaiser E, Nathan KJ, Brunton SL (2018) Discovering conservation laws from data for control. arXiv preprint arXiv:1811.00961
- 20.Kim B, Azevedo VC, Thuerey N, Kim T, Gross MH, Solenthaler B (2018) Deep fluids: a generative network for parameterized fluid simulations. CoRR. arxiv:abs/1806.02071
- 22.Kutz JN, Brunton SL, Brunton BW, Proctor JL (2016) Dynamic mode decomposition: data-driven modeling of complex systems. SIAMGoogle Scholar
- 23.L’ubor L, SoHyeon J, Barbara S, Marc P, Markus G (2015) Data-driven fluid simulations using regression forests. ACM Trans Gr 34(6):199:1–199:9Google Scholar
- 24.Lam RR, Horesh L, Avron H, Willcox KE (2017) Should you derive, or let the data drive? an optimization framework for hybrid first-principles data-driven modeling. arXiv preprint arXiv:1711.04374
- 27.Müller M, Charypar D (2003) Gross Markus particle-based fluid simulation for interactive applications. In: Proceedings of the 2003 ACM SIGGRAPH/eurographics symposium on computer animation, SCA ’03, Aire-la-Ville, Switzerland, Switzerland. Eurographics Association, pp 154–159Google Scholar
- 38.Schenck C, Fox D (2017) Reasoning about liquids via closed-loop simulation. arXiv preprint arXiv:1703.01656
- 40.Schenck C, Fox D (2018) Spnets: differentiable fluid dynamics for deep neural networks. arXiv preprint arXiv:1806.06094