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 2010.03409cs.LGcs.CE
收藏

基于图网络的学习网格仿真

Learning Mesh-Based Simulation with Graph Networks

Deepmind(深度思维)

Tobias Pfaff, Meire Fortunato, Alvaro Sanchez-Gonzalez, Peter W. Battaglia

摘要:

基于网格的模拟是科学和工程领域许多学科中复杂物理系统建模的核心。网格表示支持强大的数值积分方法,并且可以调整其分辨率以在精度和效率之间取得有利的平衡。然而,高维科学模拟运行起来非常昂贵,并且求解器和参数必须经常针对所研究的每个系统进行单独调整。在这里,我们介绍MeshGraphNets,这是一个使用图神经网络学习基于网格的模拟的框架。我们的模型可以被训练为在网格图上传递消息,并在正向模拟过程中适应网格离散化。我们的研究结果表明,它可以准确地预测各种物理系统的动态,包括空气动力学,结构力学和布料。该模型的自适应性支持学习与分辨率无关的动态,并可以在测试时扩展到更复杂的状态空间。我们的方法也非常高效,比训练它的模拟快1-2个数量级。我们的方法拓宽了神经网络模拟器可以操作的问题范围,并有望提高复杂科学建模任务的效率。

英文摘要:

Mesh-based simulations are central to modeling complex physical systems in many disciplines across science and engineering. Mesh representations support powerful numerical integration methods and their resolution can be adapted to strike favorable trade-offs between accuracy and efficiency. However, high-dimensional scientific simulations are very expensive to run, and solvers and parameters must often be tuned individually to each system studied. Here we introduce MeshGraphNets, a framework for learning mesh-based simulations using graph neural networks. Our model can be trained to pass messages on a mesh graph and to adapt the mesh discretization during forward simulation. Our results show it can accurately predict the dynamics of a wide range of physical systems, including aerodynamics, structural mechanics, and cloth. The model's adaptivity supports learning resolution-independent dynamics and can scale to more complex state spaces at test time. Our method is also highly efficient, running 1-2 orders of magnitude faster than the simulation on which it is trained. Our approach broadens the range of problems on which neural network simulators can operate and promises to improve the efficiency of complex, scientific modeling tasks.

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。

↑