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 2408.15753cs.LG
收藏

一种用于粒子模拟的神经物质点方法

A Neural Material Point Method for Particle-based Emulation

University of Liège(列日大学)

Omer Rochman Sharabi, Sacha Lewin, Gilles Louppe

AI总结:

针对粒子模拟计算昂贵的问题,受物质点方法启发提出NeuralMPM框架,利用网格插值和图像到图像神经网络加速模拟,训练时间从数天降至数小时,精度相当或更优。

摘要:

无网格拉格朗日方法因其能够处理大变形和拓扑变化,被广泛用于模拟流体、固体及其复杂相互作用。然而,这些物理模拟器在进行精确模拟时需要大量的计算资源。为了解决这些问题,深度学习模拟器有望实现更快、可扩展的模拟,但它们通常仍然昂贵且难以训练,限制了其实际应用。受物质点方法(MPM)的启发,我们提出了NeuralMPM,一种用于粒子模拟的神经模拟框架。NeuralMPM将拉格朗日粒子插值到固定大小的网格上,使用图像到图像的神经网络在网格节点上计算更新,并将结果插值回粒子。与MPM类似,NeuralMPM受益于规则的体素化表示,以简化状态动力学的计算,同时避免了基于网格的欧拉方法的缺点。我们在多个数据集上展示了NeuralMPM的优势,包括流体动力学和流体-固体相互作用。与现有方法相比,NeuralMPM将训练时间从数天减少到数小时,同时实现相当或更优的长期精度,使其成为实际正问题和逆问题的一种有前景的方法。项目页面可在https://neuralmpm.isach.be获取。

英文摘要:

Mesh-free Lagrangian methods are widely used for simulating fluids, solids, and their complex interactions due to their ability to handle large deformations and topological changes. These physics simulators, however, require substantial computational resources for accurate simulations. To address these issues, deep learning emulators promise faster and scalable simulations, yet they often remain expensive and difficult to train, limiting their practical use. Inspired by the Material Point Method (MPM), we present NeuralMPM, a neural emulation framework for particle-based simulations. NeuralMPM interpolates Lagrangian particles onto a fixed-size grid, computes updates on grid nodes using image-to-image neural networks, and interpolates back to the particles. Similarly to MPM, NeuralMPM benefits from the regular voxelized representation to simplify the computation of the state dynamics, while avoiding the drawbacks of mesh-based Eulerian methods. We demonstrate the advantages of NeuralMPM on several datasets, including fluid dynamics and fluid-solid interactions. Compared to existing methods, NeuralMPM reduces training times from days to hours, while achieving comparable or superior long-term accuracy, making it a promising approach for practical forward and inverse problems. A project page is available at https://neuralmpm.isach.be

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。

↑