使用物理感知卷积神经网络学习二维不可压缩Navier-Stokes方程的解算子
Learning the solution operator of two-dimensional incompressible Navier-Stokes equations using physics-aware convolutional neural networks
AI总结:
提出一种结合U-Net型CNN与有限差分法的物理感知技术,无需参数化即可学习不同几何形状下稳态Navier-Stokes方程的近似解,并与数据驱动方法进行了对比和融合验证。
摘要:
近年来,将物理引入机器学习的概念已变得非常流行。然而,大多数包含物理的机器学习技术仍然局限于单一几何形状或一组可参数化的几何形状。因此,即使新几何形状仅被略微修改,也仍需为其训练新模型。在本工作中,我们引入了一种技术,无需参数化即可学习不同几何形状下稳态Navier-Stokes方程的近似解。该技术基于类似U-Net的CNN与有限差分法领域中成熟的离散化方法的结合。我们将物理感知CNN的结果与最先进的数据驱动方法进行了比较。此外,我们还展示了该方法与数据驱动方法相结合时的性能表现。
英文摘要:
In recent years, the concept of introducing physics to machine learning has become widely popular. Most physics-inclusive ML-techniques however are still limited to a single geometry or a set of parametrizable geometries. Thus, there remains the need to train a new model for a new geometry, even if it is only slightly modified. With this work we introduce a technique with which it is possible to learn approximate solutions to the steady-state Navier--Stokes equations in varying geometries without the need of parametrization. This technique is based on a combination of a U-Net-like CNN and well established discretization methods from the field of the finite difference method.The results of our physics-aware CNN are compared to a state-of-the-art data-based approach. Additionally, it is also shown how our approach performs when combined with the data-based approach.
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。