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 2606.26013physics.flu-dyn
收藏

G-PINNs: 基于高斯空间加权公式的PINNs:一维低粘性Burgers方程

A Gaussian-based spatially weighted loss formulation for Physics-Informed Neural Networks with Shocks

University Salhi Ahmed(Salhi Ahmed大学);University Mohamed Khider Biskra(Mohamed Khider Biskra大学);Universidad Politécnica de Madrid(马德里理工大学);University Center of El Bayadh Nour El Bachir(El Bayadh Nour El Bachir大学中心)

Kheir-eddine Otmani, Abdelhalim Azzouz, Nourelhouda Groun, Esteban Ferrer

AI总结:

提出基于高斯空间加权的损失框架G-PINNs,通过动态优先高梯度区域配点,无需先验知识即可自主检测和跟踪移动间断,在一维低粘性Burgers问题中显著降低L2相对误差。

摘要:

我们引入了一种基于高斯空间加权的损失框架(G-PINNs),用于物理信息神经网络(PINNs),以提高对尖锐间断和激波的分辨率。所提出的方法在优化过程中动态优先处理高梯度区域的配点。无需先验知道激波位置或轨迹,该框架可以直接从PDE残差景观中自主检测和跟踪移动间断,使其广泛适用于激波或间断位置未知的问题。该方法通过一维准无粘Burgers问题进行了验证,该问题同时表现出静止和移动激波。对于低粘度 regime $(\nu = 0.0005)$,所提出的方法在静止和移动激波情况下分别实现了约$13\%$和$14\%$的$L_2$相对误差,而使用标准PINNs时分别为$45\%$和$33\%$。

英文摘要:

Physics-informed neural networks (PINNs) often struggle to resolve shocks because smooth neural representations and globally averaged residual losses tend to underemphasize localized high-gradient regions. We introduce a residual-tracked Gaussian weighting strategy that represents the spatial distribution of the PDE-residual loss through a small number of learnable parameters, without resampling the collocation points or prescribing the shock location. The Gaussian center and width are updated from the evolving PDE residual, allowing the weighting field to follow stationary and moving shocks during training without prior knowledge of their positions or trajectories. The method is assessed using one-dimensional low-viscosity Burgers problems and a two-dimensional Euler Riemann problem with four interacting shocks. For $ν=5\times10^{-4}$, the relative $L_2$ error decreases from approximately $45\%$ to $13\%$ for the stationary shock and from $33\%$ to $14\%$ for the moving shock, compared with a standard PINN. In the two-dimensional problem, the maximum absolute density error decreases from $1.08$ to $0.62$. These results show that a compact, dynamically localized residual weighting can substantially improve PINN resolution of shock-dominated solutions while retaining the original collocation set and avoiding prescribed shock trajectories.

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。

↑