arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.08569cs.LGphysics.comp-ph
收藏

一种用于偏微分方程描述的物理过程模拟的物理驱动GraphSAGE方法

A Physics-driven GraphSAGE Method for Physical Process Simulations Described by Partial Differential Equations

Xiamen University(厦门大学);Peking University(北京大学)

Hang Hu, Sidi Wu, Guoxiong Cai, Na Liu

AI总结:

本文提出物理驱动的PD-GraphSAGE方法,结合Galerkin法与图表示求解不规则偏微分方程并构建参数化代理模型,在保证精度的同时显著提升计算速度。

摘要:

物理信息神经网络(PINNs)已成功解决了基于偏微分方程(PDEs)的各种计算物理问题。然而,在处理与奇异性和振荡等不规则性相关的问题时,训练得到的解通常精度较低。此外,目前大多数工作仅针对预先确定的输入参数提供训练解。如果输入参数发生任何变化,就需要进行迁移学习或重新训练,而传统数值方法也需要进行独立的模拟。本文提出了一种基于Galerkin方法和分片多项式节点基函数的物理驱动GraphSAGE方法(PD-GraphSAGE),用于求解由不规则偏微分方程控制的计算问题,并建立参数化PDE代理模型。该方法采用物理域的图表示,从而通过局部细化降低了对评估点数量的需求。针对奇异性和振荡情形,分别设计了距离相关的边特征和特征映射策略,以帮助训练和收敛。通过若干算例验证了所提方法的优点。此外,成功建立了以高斯随机场源为参数的热传导问题的鲁棒PDE代理模型,该模型不仅能准确提供解,而且在我们的实验中比有限元方法快数倍。

英文摘要:

Physics-informed neural networks (PINNs) have successfully addressed various computational physics problems based on partial differential equations (PDEs). However, while tackling issues related to irregularities like singularities and oscillations, trained solutions usually suffer low accuracy. In addition, most current works only offer the trained solution for predetermined input parameters. If any change occurs in input parameters, transfer learning or retraining is required, and traditional numerical techniques also need an independent simulation. In this work, a physics-driven GraphSAGE approach (PD-GraphSAGE) based on the Galerkin method and piecewise polynomial nodal basis functions is presented to solve computational problems governed by irregular PDEs and to develop parametric PDE surrogate models. This approach employs graph representations of physical domains, thereby reducing the demands for evaluated points due to local refinement. A distance-related edge feature and a feature mapping strategy are devised to help training and convergence for singularity and oscillation situations, respectively. The merits of the proposed method are demonstrated through a couple of cases. Moreover, the robust PDE surrogate model for heat conduction problems parameterized by the Gaussian random field source is successfully established, which not only provides the solution accurately but is several times faster than the finite element method in our experiments.

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。

↑