arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2212.06124physics.comp-ph
收藏

学习格子玻尔兹曼碰撞算符

Towards learning Lattice Boltzmann collision operators

Alessandro Corbetta, Alessandro Gabbana, Vitaliy Gyrya, Daniel Livescu, Joost Prins, Federico Toschi

摘要:

在这项工作中,我们探讨了使用深度学习方法从格子玻尔兹曼方法的数据碰撞算子中学习的可能性。我们比较层次的神经网络(NN)碰撞算子的设计和评估所产生的LBM方法在再现时间动态的几个规范流的性能。在目前的研究中,作为第一次尝试解决学习问题,数据是由一个单一的弛豫时间BGK算子。我们证明,香草NN架构具有非常有限的准确性。另一方面,通过嵌入物理特性,如守恒定律和对称性,可以将精度大幅提高几个数量级,并正确再现标准流体流动的短期和长期动态。

英文摘要:

In this work we explore the possibility of learning from data collision operators for the Lattice Boltzmann Method using a deep learning approach. We compare a hierarchy of designs of the neural network (NN) collision operator and evaluate the performance of the resulting LBM method in reproducing time dynamics of several canonical flows. In the current study, as a first attempt to address the learning problem, the data was generated by a single relaxation time BGK operator. We demonstrate that vanilla NN architecture has very limited accuracy. On the other hand, by embedding physical properties, such as conservation laws and symmetries, it is possible to dramatically increase the accuracy by several orders of magnitude and correctly reproduce the short and long time dynamics of standard fluid flows.

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。

↑