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 2306.05486math.NAcs.NA
收藏

基于多级领域分解的物理信息神经网络架构

Multilevel domain decomposition-based architectures for physics-informed neural networks

Victorita Dolean, Alexander Heinlein, Siddhartha Mishra, Ben Moseley

AI总结:

针对PINNs难以求解高频多尺度问题的不足,受经典多级Schwarz领域分解方法启发,提出多级FBPINNs架构,实验证明其在多类问题中精度显著优于PINNs和常规FBPINNs。

摘要:

物理信息神经网络(PINNs)是求解涉及微分方程问题的一种强大方法,但在求解具有高频和/或多尺度解的问题时往往存在困难。有限基物理信息神经网络(FBPINNs)通过将PINNs与重叠领域分解方法相结合,提升了PINNs在这类场景下的性能。在本研究中,受经典多级Schwarz领域分解方法(DDMs)的启发,我们通过在FBPINNs的解 ansatz 中加入多级领域分解,对FBPINNs进行了扩展。与经典DDMs的典型测试类似,我们通过开展强缩放和弱缩放测试,评估了PINNs、FBPINNs和多级FBPINNs的精度随计算量和解复杂度的变化情况。我们的数值结果表明,在一系列具有高频和多尺度解的问题中,所提出的多级FBPINNs始终显著优于PINNs。此外,正如经典DDMs中所预期的那样,我们证明了多级FBPINNs在使用大量子域时,可通过促进子域间的全局通信来提升FBPINNs的精度。

英文摘要:

Physics-informed neural networks (PINNs) are a powerful approach for solving problems involving differential equations, yet they often struggle to solve problems with high frequency and/or multi-scale solutions. Finite basis physics-informed neural networks (FBPINNs) improve the performance of PINNs in this regime by combining them with an overlapping domain decomposition approach. In this work, FBPINNs are extended by adding multiple levels of domain decompositions to their solution ansatz, inspired by classical multilevel Schwarz domain decomposition methods (DDMs). Analogous to typical tests for classical DDMs, we assess how the accuracy of PINNs, FBPINNs and multilevel FBPINNs scale with respect to computational effort and solution complexity by carrying out strong and weak scaling tests. Our numerical results show that the proposed multilevel FBPINNs consistently and significantly outperform PINNs across a range of problems with high frequency and multi-scale solutions. Furthermore, as expected in classical DDMs, we show that multilevel FBPINNs improve the accuracy of FBPINNs when using large numbers of subdomains by aiding global communication between subdomains.

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。

↑