arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2208.09145math.NAcs.LGcs.NA
收藏

奇摄动边值问题的半解析PINN方法

Semi-analytic PINN methods for singularly perturbed boundary value problems

University of Louisville(路易斯维尔大学);Sungkyunkwan University(成均馆大学);Ulsan National Institute of Science and Technology(蔚山国立科学技术院)

Gung-Min Gie, Youngjoon Hong, Chang-Yeol Jung

摘要:

提出了一种新的半解析物理信息神经网络(PINN)来求解奇摄动边值问题。PINN是一个科学的机器学习框架,为寻找偏微分方程的数值解提供了一个有前途的前景。PINN在求解各种微分方程方面表现出令人印象深刻的性能,包括涉及复杂几何形状的域中的时间相关和多维方程。然而,当考虑刚性微分方程时,由于谱偏差,神经网络通常无法捕获解的急剧转变。为了解决这个问题,在这里,我们开发的半解析PINN方法,丰富了使用所谓的校正功能从边界层分析。我们的新的丰富PINN准确地预测数值解的奇异扰动问题。数值实验包括各种类型的奇摄动线性和非线性微分方程。

英文摘要:

We propose a new semi-analytic physics informed neural network (PINN) to solve singularly perturbed boundary value problems. The PINN is a scientific machine learning framework that offers a promising perspective for finding numerical solutions to partial differential equations. The PINNs have shown impressive performance in solving various differential equations including time-dependent and multi-dimensional equations involved in a complex geometry of the domain. However, when considering stiff differential equations, neural networks in general fail to capture the sharp transition of solutions, due to the spectral bias. To resolve this issue, here we develop the semi-analytic PINN methods, enriched by using the so-called corrector functions obtained from the boundary layer analysis. Our new enriched PINNs accurately predict numerical solutions to the singular perturbation problems. Numerical experiments include various types of singularly perturbed linear and nonlinear differential equations.

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。

↑