arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.04750physics.flu-dyncs.LG
收藏

JAX-SPH:一个可微分的平滑粒子流体动力学框架

JAX-SPH: A Differentiable Smoothed Particle Hydrodynamics Framework

NXAI GmbH(NXAI 有限公司);Munich Institute of Integrated Materials, Energy and Process Engineering, TUM(慕尼黑工业大学集成材料、能源与过程工程研究所);ELLIS Unit Linz(ELLIS 林茨单元);LIT AI Lab(LIT 人工智能实验室);Institute for Machine Learning(机器学习研究所)

Artur P. Toshev, Harish Ramachandran, Jonas A. Erbesdobler, Gianluca Galletti, Johannes Brandstetter, Nikolaus A. Adams

AI总结:

本文提出JAX-SPH,一个基于JAX实现的可微分平滑粒子流体动力学框架,通过集成关键SPH算法、重构为Python包、验证梯度并展示其在反问题与Solver-in-the-Loop中的应用,实现了与深度学习框架兼容的拉格朗日流体模拟。

摘要:

基于粒子的流体模拟已成为求解纳维-斯托克斯方程的有力工具,尤其是在涉及复杂物理和自由表面的情况下。近年来,机器学习方法被引入求解此类问题的工具箱,正在推动此类数值模拟在质量与速度权衡上的边界。在这项工作中,我们率先开发了与深度学习框架兼容的拉格朗日流体模拟器,并提出了JAX-SPH——一个在JAX中实现的平滑粒子流体动力学(SPH)框架。JAX-SPH建立在LagrangeBench项目(Toshev et al., 2023)的数据集生成代码之上,并从多个方面对该代码进行了扩展:(a)集成了更多关键的SPH算法,(b)将代码重构为Python包,(c)验证了通过求解器的梯度,(d)展示了梯度在求解反问题以及Solver-in-the-Loop应用中的实用性。我们的代码可在https://github.com/tumaer/jax-sph获取。

英文摘要:

Particle-based fluid simulations have emerged as a powerful tool for solving the Navier-Stokes equations, especially in cases that include intricate physics and free surfaces. The recent addition of machine learning methods to the toolbox for solving such problems is pushing the boundary of the quality vs. speed tradeoff of such numerical simulations. In this work, we lead the way to Lagrangian fluid simulators compatible with deep learning frameworks, and propose JAX-SPH - a Smoothed Particle Hydrodynamics (SPH) framework implemented in JAX. JAX-SPH builds on the code for dataset generation from the LagrangeBench project (Toshev et al., 2023) and extends this code in multiple ways: (a) integration of further key SPH algorithms, (b) restructuring the code toward a Python package, (c) verification of the gradients through the solver, and (d) demonstration of the utility of the gradients for solving inverse problems as well as a Solver-in-the-Loop application. Our code is available at https://github.com/tumaer/jax-sph.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑