Two-dimensional finite element network analysis: Formulation and static analysis of structural assemblies
Two-dimensional finite element network analysis: Formulation and static analysis of structural assemblies
复制标题
二维有限元网络分析：结构组件的公式化和静态分析
DOI：
10.1016/j.compstruc.2022.106784
复制
发表时间：
2022
影响因子：
4.7
通讯作者：
Semperlotti, Fabio
中科院分区：
文献类型：
--
作者：
Jokar, Mehdi;Semperlotti, Fabio
有限元网络分析（FENA）是一种基于物理信息的、基于深度学习的框架，用于模拟物理系统。FENA将经典有限元方法的概念灵活性与预训练神经网络的计算能力相结合。FENA的一个显着特点是能够通过连接预先训练的网络作为物理系统类的模型来模拟物理元素的集合。这一特点的地方FENA在一个新的类别的基于网络的计算平台，因为，与其他技术，它不需要训练的具体问题conditions.The本研究显着扩展FENA的概念和功能，包括一维细长梁和二维薄板，并进一步扩展其串联功能。串联，这是一个关键的属性，创建多组件组件，而不需要训练，重新制定以下的能量为基础的变分方法，显着提高精度和收敛速度。该方法的数值验证对不同配置的结构组件，负载和边界条件的有限元解。虽然在一维和二维结构的背景下，本框架是非常普遍的，并提供了一个基础，潜在地模拟广泛的物理系统。
Finite element network analysis (FENA) is a physics-informed, deep-learning-based framework for the simulation of physical systems. FENA combines the conceptual flexibility of classical finite element methods with the computational power of pre-trained neural networks. A remarkable characteristic of FENA is the ability to simulate assemblies of physical elements by concatenating pre-trained networks serving as models of classes of physical systems. This characteristic places FENA in a new category of network-based computational platforms because, unlike other techniques, it does not requiread hoctraining for problem-specific conditions.The present study significantly expands the concept and functionalities of FENA by including 1D slender beams and 2D thin plates and by further extending its concatenation functionality. Concatenation, which is a key property to create multicomponent assemblies without requiring training, is reformulated following an energy-based variational approach that significantly enhances accuracy and speed of convergence. The approach is numerically validated against finite element solutions for different configurations of structural assemblies, loads, and boundary conditions. Although presented in the context of one- and two-dimensional structures, the present framework is extremely general and provides a foundation to potentially simulate a broad range of physical systems.
登录
查看更多内容
DOI：
10.1016/j.cma.2020.112913
发表时间：
2020-05-01
影响因子：
7.2
作者：
Liu, Zeliang
通讯作者：
Liu, Zeliang
影响因子：
4.1
作者：
Raissi, M.;Perdikaris, P.;Karniadakis, G. E.
通讯作者：
Karniadakis, G. E.
使用高通量分子动力学模拟和机器学习预测硅酸盐玻璃的杨氏模量
影响因子：
4.6
作者：
Yang, Kai;Xu, Xinyi;Yang, Benjamin;Cook, Brian;Ramos, Herbert;Krishnan, N. M.;Smedskjaer, Morten M.;Hoover, Christian;Bauchy, Mathieu
通讯作者：
Bauchy, Mathieu
影响因子：
16.6
作者：
Schubert, Philipp J.;Dorkenwald, Sven;Kornfeld, Joergen
通讯作者：
Kornfeld, Joergen