Convolution Hierarchical Deep-learning Neural Networks (C-HiDeNN): finite elements, isogeometric analysis, tensor decomposition, and beyond

• Published in: Computational mechanics 2023-08, Vol.72 (2), p.333-362
• Main Authors: Lu, Ye, Li, Hengyang, Zhang, Lei, Park, Chanwook, Mojumder, Satyajit, Knapik, Stefan, Sang, Zhongsheng, Tang, Shaoqiang, Apley, Daniel W., Wagner, Gregory J., Liu, Wing Kam
• Format: Article
• Language: English
• Subjects: Analysis; Approximation; Classical and Continuum Physics; Computational Science and Engineering; Convergence; Convolution; Decomposition; Deep learning; Differential equations; Engineering; Finite element method; Interpolation; Neural networks; Original Paper; Parameters; Partial differential equations; Polynomials; Reduced order models; Shape functions; Smoothness; Tensors; Theoretical and Applied Mechanics; Topology optimization; Transient heat transfer
• ISSN: 0178-7675; 1432-0924
• DOI: 10.1007/s00466-023-02336-5

This paper presents a general Convolution Hierarchical Deep-learning Neural Networks (C-HiDeNN) computational framework for solving partial differential equations. This is the first paper of a series of papers devoted to C-HiDeNN. We focus on the theoretical foundation and formulation of the method. The C-HiDeNN framework provides a flexible way to construct high-order C n approximation with arbitrary convergence rates and automatic mesh adaptivity. By constraining the C-HiDeNN to build certain functions, it can be degenerated to a specification, the so-called convolution finite element method (C-FEM). The C-FEM will be presented in detail and used to study the numerical performance of the convolution approximation. The C-FEM combines the standard C 0 FE shape function and the meshfree-type radial basis interpolation. It has been demonstrated that the C-FEM can achieve arbitrary orders of smoothness and convergence rates by adjusting the different controlling parameters, such as the patch function dilation parameter and polynomial order, without increasing the degrees of freedom of the discretized systems, compared to FEM. We will also present the convolution tensor decomposition method under the reduced-order modeling setup. The proposed methods are expected to provide highly efficient solutions for extra-large scale problems while maintaining superior accuracy. The applications to transient heat transfer problems in additive manufacturing, topology optimization, GPU-based parallelization, and convolution isogeometric analysis have been discussed.