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 1908.10407stat.MLcs.LGmath.AP
收藏

基于机器学习的计算力学中偏微分方程求解的能量方法:概念、实现和应用

An Energy Approach to the Solution of Partial Differential Equations in Computational Mechanics via Machine Learning: Concepts, Implementation and Applications

Universidad de Cuenca(昆卡大学);Bauhaus-Universität Weimar(魏玛包豪斯大学);Leibniz Universität Hannover(汉诺威莱布尼茨大学);School of Engineering and Departamento de Recursos Hídricos y Ciencias Ambientales, Universidad de Cuenca(昆卡大学工程学院和水资源与环境科学系)

Esteban Samaniego, Cosmin Anitescu, Somdatta Goswami, Vien Minh Nguyen-Thanh, Hongwei Guo, Khader Hamdia, Timon Rabczuk, Xiaoying Zhuang

摘要:

偏微分方程(PDE)是对科学和工程中的各种现象进行数学建模的基础。解决这些问题是精确了解自然和工程系统行为的关键一步。一般来说,为了解决代表真实系统的偏微分方程,以可接受的程度,分析方法通常是不够的。人们不得不求助于离散化方法。对于工程问题,可能最知名的选择是有限元法(FEM)。然而,强大的替代方法,如无网格方法和等几何分析(IGA)也是可用的。其基本思想是通过专门构建的具有某些理想性质的函数来近似PDE的解。在这篇文章中,我们探索了深度神经网络(DNN)作为近似的一种选择。他们在视觉识别等领域取得了令人印象深刻的成果。DNN在这里被视为函数逼近机。有很大的灵活性来定义它们的结构和重要的进步,在架构和算法的效率,以实现它们使DNN一个非常有趣的替代近似PDE的解决方案。我们专注于对计算力学感兴趣的应用程序。大多数决定探索这种可能性的文章都采用了搭配策略。在这方面的贡献,我们集中在力学问题和分析充满活力的格式的偏微分方程。机械系统的能量似乎是机器学习方法处理机械问题的自然损失函数。作为概念的证明,我们处理几个问题,并探讨该方法在工程中的应用能力。

英文摘要:

Partial Differential Equations (PDE) are fundamental to model different phenomena in science and engineering mathematically. Solving them is a crucial step towards a precise knowledge of the behaviour of natural and engineered systems. In general, in order to solve PDEs that represent real systems to an acceptable degree, analytical methods are usually not enough. One has to resort to discretization methods. For engineering problems, probably the best known option is the finite element method (FEM). However, powerful alternatives such as mesh-free methods and Isogeometric Analysis (IGA) are also available. The fundamental idea is to approximate the solution of the PDE by means of functions specifically built to have some desirable properties. In this contribution, we explore Deep Neural Networks (DNNs) as an option for approximation. They have shown impressive results in areas such as visual recognition. DNNs are regarded here as function approximation machines. There is great flexibility to define their structure and important advances in the architecture and the efficiency of the algorithms to implement them make DNNs a very interesting alternative to approximate the solution of a PDE. We concentrate in applications that have an interest for Computational Mechanics. Most contributions that have decided to explore this possibility have adopted a collocation strategy. In this contribution, we concentrate in mechanical problems and analyze the energetic format of the PDE. The energy of a mechanical system seems to be the natural loss function for a machine learning method to approach a mechanical problem. As proofs of concept, we deal with several problems and explore the capabilities of the method for applications in engineering.

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。

↑