arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.04244math.NAcs.LGcs.NAphysics.comp-phphysics.flu-dyn
收藏

NPLIC:一种构造分段线性界面的机器学习方法

NPLIC: A Machine Learning Approach to Piecewise Linear Interface Construction

Vector Institute(向量研究所);University of Toronto(多伦多大学);Autodesk, Inc.(欧特克公司)

Mohammadmehdi Ataei, Markus Bussmann, Vahid Shaayegan, Franco Costa, Sejin Han, Chul B. Park

摘要:

流体体积(VOF)方法广泛用于数值模拟中的流体界面跟踪,许多VOF算法需要对界面进行几何重构。为此目的,分段线性接口构造(PLIC)技术是最常用的,由于几何复杂性的原因,它可能是缓慢的,难以实现。在这里,我们提出了一种替代的基于神经网络的方法称为NPLIC执行PLIC计算。该模型是在正方形、立方体、三角形和四面体网格的PLIC解决方案的大型合成数据集上训练的。我们表明,这种数据驱动的方法,在通常的计算成本的一小部分,在准确的计算结果,和一个单一的神经网络系统可以用于不同的网格类型的接口重建。

英文摘要:

Volume of fluid (VOF) methods are extensively used to track fluid interfaces in numerical simulations, and many VOF algorithms require that the interface be reconstructed geometrically. For this purpose, the Piecewise Linear Interface Construction (PLIC) technique is most frequently used, which for reasons of geometric complexity can be slow and difficult to implement. Here, we propose an alternative neural network based method called NPLIC to perform PLIC calculations. The model is trained on a large synthetic dataset of PLIC solutions for square, cubic, triangular, and tetrahedral meshes. We show that this data-driven approach results in accurate calculations at a fraction of the usual computational cost, and a single neural network system can be used for interface reconstruction of different mesh types.

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。

↑