arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.04104physics.flu-dynphysics.comp-ph
收藏

基于物理信息的神经网络在表面张力驱动液膜流动中的应用

Physics-informed neural network applied to surface-tension-driven liquid film flows

Yo Nakamura, Suguru Shiratori, Ryota Takagi, Michihiro Sutoh, Iori Sugihara, Hideaki Nagano, Kenjiro Shimano

摘要:

物理信息神经网络(PINN)最近由Raissi等人提出[J. Comp. Phys. 378,pp. 686-707(2019)],应用于液膜流动的偏微分方程(PDE)。所考虑的偏微分方程是由拉普拉斯压力引起的厚度分布$h(x,t)$随时间的演化,其中包含四阶空间导数和四阶非线性项。即使对于这样的偏微分方程,它被证实,PINN可以预测的解决方案具有足够的精度。然而,在训练收敛性和解的准确性方面需要改进。浮点数的精度是目前PDE的一个关键问题。当使用单精度浮点数执行计算时,由于丢失有效位数,优化将终止。自动微分(AD)的计算支配训练所需的计算时间,并且随着导数阶数的增加而呈指数增长。通过将原来的四阶单变量偏微分方程分解为二阶双变量偏微分方程,大大减少了每次训练迭代的计算时间。训练数据的采样密度也显著影响训练收敛性。对于本研究中考虑的问题,通过允许训练数据的采样密度在较早的时间范围内更大,从而获得改进的收敛性,在较早的时间范围内发生厚度的快速平坦化。

英文摘要:

A physics-informed neural network (PINN), which has been recently proposed by Raissi et al [J. Comp. Phys. 378, pp. 686-707 (2019)], is applied to the partial differential equation (PDE) of liquid film flows. The PDE considered is the time evolution of the thickness distribution $h(x,t)$ owing to the Laplace pressure, which involves 4th-order spatial derivative and 4th-order nonlinear term. Even for such a PDE, it is confirmed that the PINN can predict the solutions with sufficient accuracy. Nevertheless, some improvements are needed in training convergence and accuracy of the solutions. The precision of floating-point numbers is a critical issue for the present PDE. When the calculation is executed with a single precision floating-point number, the optimization is terminated due to the loss of significant digits. Calculation of the automatic differentiation (AD) dominates the computational time required for training, and becomes exponentially longer with increasing order of derivatives. By splitting the original 4th-order one-variable PDE into 2nd-order two-variable PDEs, the computational time for each training iteration is greatly reduced. The sampling density of training data also significantly affects training convergence. For the problem considered in this study, mproved convergence was obtained by allowing the sampling density of training data to be greater in earlier time ranges, where the rapid flattening of the thickness occurs.

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。

↑