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 2411.02411physics.comp-ph
收藏

SK-PINN:通过平滑核梯度加速物理信息深度学习

SK-PINN: Accelerated physics-informed deep learning by smoothing kernel gradients

Cunliang Pan, Chengxuan Li, Yu Liu, Yonggang Zheng, Hongfei Ye

AI总结:

本文提出SK-PINN,利用SPH平滑核离散化替代自动微分加速物理信息神经网络训练,在大配点集和高阶问题上速度提升数十倍,且收敛速率与原始PINN一致,适用于复杂域计算力学正逆问题。

摘要:

原始物理信息神经网络(PINNs)中的自动微分(AD)是高效分析的计算瓶颈。光滑粒子流体动力学(SPH)中的导数离散化概念可为PINNs提供一种加速训练方法。本文建立了平滑核物理信息神经网络(SK-PINNs),利用平滑核离散化求解微分方程。它是一个稳健的框架,能够解决复杂域计算力学中的问题。当配点数逐渐增加时,SK-PINNs的训练速度显著超过原始PINNs。在涉及大配点集或高阶问题的情况下,SK-PINN训练可比原始PINN快数十倍。此外,使用神经正切核(NTK)理论的分析表明,SK-PINNs的收敛速率与原始PINNs一致。SK-PINNs的优越性能通过多个示例得到展示,包括规则和复杂域,以及流体动力学和固体力学中的正问题和逆问题。

英文摘要:

The automatic differentiation (AD) in the vanilla physics-informed neural networks (PINNs) is the computational bottleneck for the high-efficiency analysis. The concept of derivative discretization in smoothed particle hydrodynamics (SPH) can provide an accelerated training method for PINNs. In this paper, smoothing kernel physics-informed neural networks (SK-PINNs) are established, which solve differential equations using smoothing kernel discretization. It is a robust framework capable of solving problems in the computational mechanics of complex domains. When the number of collocation points gradually increases, the training speed of SK-PINNs significantly surpasses that of vanilla PINNs. In cases involving large collocation point sets or higher-order problems, SK-PINN training can be up to tens of times faster than vanilla PINN. Additionally, analysis using neural tangent kernel (NTK) theory shows that the convergence rates of SK-PINNs are consistent with those of vanilla PINNs. The superior performance of SK-PINNs is demonstrated through various examples, including regular and complex domains, as well as forward and inverse problems in fluid dynamics and solid mechanics.

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。

↑