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 2205.12419physics.flu-dyncs.LGnlin.PS
收藏

物理引导的变分多尺度降阶建模机器学习

Physics Guided Machine Learning for Variational Multiscale Reduced Order Modeling

Oklahoma State University(俄克拉荷马州立大学);Norwegian University of Science and Technology(挪威科技大学);SINTEF Digital(SINTEF数字研究院);Virginia Tech(弗吉尼亚理工大学);Emory University(埃默里大学)

Shady E. Ahmed, Omer San, Adil Rasheed, Traian Iliescu, Alessandro Veneziani

摘要:

我们提出了一个新的物理引导的机器学习(PGML)范式,利用变分多尺度(VMS)框架和可用的数据,以显着提高降阶模型(ROM)的准确性在一个适度的计算成本。ROM基础和VMS框架的分层结构使得能够自然分离已解决和未解决的ROM空间尺度。现代PGML算法被用来构建新的模型之间的相互作用的解决和未解决的ROM规模。具体来说,新的框架建立ROM运营商是最接近真正的相互作用条款的VMS框架。最后,使用机器学习来减少投影误差并进一步提高ROM精度。我们的二维涡输运问题的数值实验表明,新的PGML-VMS-ROM范式保持了当前ROM的低计算成本,同时显着提高ROM的精度。

英文摘要:

We propose a new physics guided machine learning (PGML) paradigm that leverages the variational multiscale (VMS) framework and available data to dramatically increase the accuracy of reduced order models (ROMs) at a modest computational cost. The hierarchical structure of the ROM basis and the VMS framework enable a natural separation of the resolved and unresolved ROM spatial scales. Modern PGML algorithms are used to construct novel models for the interaction among the resolved and unresolved ROM scales. Specifically, the new framework builds ROM operators that are closest to the true interaction terms in the VMS framework. Finally, machine learning is used to reduce the projection error and further increase the ROM accuracy. Our numerical experiments for a two-dimensional vorticity transport problem show that the novel PGML-VMS-ROM paradigm maintains the low computational cost of current ROMs, while significantly increasing the ROM accuracy.

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。

↑