当前位置: X-MOL 学术Comput. Methods Appl. Mech. Eng. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Multi-patch Isogeometric convolution hierarchical deep-learning neural network
Computer Methods in Applied Mechanics and Engineering ( IF 6.9 ) Pub Date : 2024-11-30 , DOI: 10.1016/j.cma.2024.117582
Lei Zhang, Chanwook Park, Thomas J.R. Hughes, Wing Kam Liu

A seamless integration of neural networks with Isogeometric Analysis (IGA) was first introduced in [1] under the name of Hierarchical Deep-learning Neural Network (HiDeNN) and has systematically evolved into Isogeometric Convolution HiDeNN (in short, C-IGA) [2]. C-IGA achieves higher order approximations without increasing the degree of freedom. Due to the Kronecker delta property of C-IGA shape functions, one can refine the mesh in the physical domain like standard finite element method (FEM) while maintaining the exact geometrical mapping of IGA. In this article, C-IGA theory is generalized for multi-CAD-patch systems with a mathematical investigation of the compatibility conditions at patch interfaces and convergence of error estimates. Two compatibility conditions (nodal compatibility and G0 (i.e., global C0) compatibility) are presented and validated through numerical examples.

中文翻译:


多面片等几何卷积分层深度学习神经网络



神经网络与等几何分析 (IGA) 的无缝集成在 [1] 中首次以分层深度学习神经网络 (HiDeNN) 的名义引入,并已系统地演变为等几何卷积 HiDeNN(简称 C-IGA)[2]。C-IGA 在不增加自由度的情况下实现更高阶的近似。由于 C-IGA 形状函数的 Kronecker delta 特性,可以像标准有限元法 (FEM) 一样在物理域中细化网格,同时保持 IGA 的精确几何映射。在本文中,C-IGA 理论被推广到多 CAD 贴片系统中,对贴片界面的兼容性条件和误差估计的收敛进行了数学研究。通过数值示例提出并验证了两个相容性条件 (节点相容性和 G0 (即全局 C0) 相容性)。
更新日期:2024-11-30
down
wechat
bug