论文标题
学习通过图神经网络模拟看不见的物理系统
Learning to Simulate Unseen Physical Systems with Graph Neural Networks
论文作者
论文摘要
物理系统动力学的模拟对于科学和工程的发展至关重要。最近，学习使用神经网络模拟物理系统的动力学越来越兴趣。但是，现有的方法无法推广到训练集中的物理物质，例如具有不同粘度的液体或具有不同弹性的弹性体。在这里，我们提出了一种嵌入物理先验和材料参数的机器学习方法，我们将其称为“基于图形的物理引擎”（GPE），以有效地在多种情况下对不同物质的物理动力学进行建模。我们证明，GPE可以推广到在训练集中看不到的不同属性的材料，并且从单步预测到多步推出仿真。此外，在模型中引入动量保护定律可显着提高学习的效率和稳定性，从而通过更少的训练步骤来融合到更好的模型。
Simulation of the dynamics of physical systems is essential to the development of both science and engineering. Recently there is an increasing interest in learning to simulate the dynamics of physical systems using neural networks. However, existing approaches fail to generalize to physical substances not in the training set, such as liquids with different viscosities or elastomers with different elasticities. Here we present a machine learning method embedded with physical priors and material parameters, which we term as "Graph-based Physics Engine" (GPE), to efficiently model the physical dynamics of different substances in a wide variety of scenarios. We demonstrate that GPE can generalize to materials with different properties not seen in the training set and perform well from single-step predictions to multi-step roll-out simulations. In addition, introducing the law of momentum conservation in the model significantly improves the efficiency and stability of learning, allowing convergence to better models with fewer training steps.
