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 2504.00510cs.LGcs.AI
收藏

用于偏微分方程求解中几何泛化的人域分解运算学习

Operator Learning with Domain Decomposition for Geometry Generalization in PDE Solving

Corporate Research, Bosch (China) Investment Co., Ltd.(博世(中国)投资有限公司企业研究部)

Jianing Huang, Kaixuan Zhang, Youjia Wu, Ze Cheng

AI总结:

本文提出一种基于域分解的运算学习框架,通过局部到全局的方法解决任意几何上的PDEs,提升几何泛化能力与数据效率。

摘要:

神经运算已成为解决偏微分方程(PDEs)的热门方法,因其在复杂域上函数空间之间捕捉复杂映射的能力卓越。然而,运算学习的数据渴求性不可避免地成为其广泛应用的瓶颈。核心挑战在于神经运算无法转移到新几何上。为解决这一问题,我们提出运算学习与域分解,一种局部到全局的框架来解决任意几何上的PDEs。在此框架下,我们设计了一种迭代方案Schwarz神经推断(SNI)。该方案允许将问题域划分为更小的子域,在这些子域上使用神经运算解决局部问题,并将局部解拼接成全局解。此外,我们还提供了收敛率和误差界理论分析。我们在几种具有不同边界条件的代表性PDEs上进行了广泛实验,并在几何泛化方面取得了比替代方法显著的成果。这些分析和实验展示了所提框架在解决几何泛化和数据效率挑战方面的潜力。

英文摘要:

Neural operators have become increasingly popular in solving \textit{partial differential equations} (PDEs) due to their superior capability to capture intricate mappings between function spaces over complex domains. However, the data-hungry nature of operator learning inevitably poses a bottleneck for their widespread applications. At the core of the challenge lies the absence of transferability of neural operators to new geometries. To tackle this issue, we propose operator learning with domain decomposition, a local-to-global framework to solve PDEs on arbitrary geometries. Under this framework, we devise an iterative scheme \textit{Schwarz Neural Inference} (SNI). This scheme allows for partitioning of the problem domain into smaller subdomains, on which local problems can be solved with neural operators, and stitching local solutions to construct a global solution. Additionally, we provide a theoretical analysis of the convergence rate and error bound. We conduct extensive experiments on several representative PDEs with diverse boundary conditions and achieve remarkable geometry generalization compared to alternative methods. These analysis and experiments demonstrate the proposed framework's potential in addressing challenges related to geometry generalization and data efficiency.

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。

↑