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 2602.21590cs.CE
收藏

基于有限差分法的物理信息神经网络

Physics Informed Neural Network using Finite Difference Method

Kart Leong Lim, Rahul Dutta, Mihai Rotaru

AI总结:

本文提出基于有限差分法的PINN方法,用于高效求解偏微分方程,实现成本低且性能优异。

摘要:

在最近的深度学习工程应用中,物理信息神经网络(PINN)作为一种新发展,能够利用工程系统的底层物理。PINN的创新之处在于将偏微分方程(PDE)用于损失函数。大多数PINN是通过自动微分(AD)来训练PDE损失函数的。较少为人所知的是,使用有限差分法(FDM)作为替代方法。与基于AD的PINN不同,使用基于FDM的PINN的即时好处是实现成本低。在本文中,我们提出使用有限差分法来估计PINN中的PDE损失函数。我们的工作受到电磁系统计算分析的启发,传统上使用逐次加速松弛法求解拉普拉斯方程。在拉普拉斯方程的情况下,我们的PINN方法可以被视为将神经网络输出的拉普拉斯滤波响应作为损失函数。因此,PINN的实现可以非常简单。在我们的实验中,我们测试了PINN在拉普拉斯方程和伯格方程上的表现。我们展示了使用FDM,PINN在非PINN深度学习方法上表现一致。当与基于AD的PINN比较时,我们展示了我们的方法计算更快,且在误差减少方面也相当。

英文摘要:

In recent engineering applications using deep learning, physics-informed neural network (PINN) is a new development as it can exploit the underlying physics of engineering systems. The novelty of PINN lies in the use of partial differential equations (PDE) for the loss function. Most PINNs are implemented using automatic differentiation (AD) for training the PDE loss functions. A lesser well-known study is the use of finite difference method (FDM) as an alternative. Unlike an AD based PINN, an immediate benefit of using a FDM based PINN is low implementation cost. In this paper, we propose the use of finite difference method for estimating the PDE loss functions in PINN. Our work is inspired by computational analysis in electromagnetic systems that traditionally solve Laplace's equation using successive over-relaxation. In the case of Laplace's equation, our PINN approach can be seen as taking the Laplacian filter response of the neural network output as the loss function. Thus, the implementation of PINN can be very simple. In our experiments, we tested PINN on Laplace's equation and Burger's equation. We showed that using FDM, PINN consistently outperforms non-PINN based deep learning. When comparing to AD based PINNs, we showed that our method is faster to compute as well as on par in terms of error reduction.

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。

↑