IGA-Reuse-NET

A deep-learning-based isogeometric analysis-reuse approach with topology-consistent parameterization[Formula presented]

Journal article (2022)

Authors

Dandan Wang Hangzhou Dianzi University
Jinlan Xu Hangzhou Dianzi University
Fei Gao Hangzhou Dianzi University
C.C. Wang Materials and Manufacturing - IDE , The University of Manchester
Renshu Gu Hangzhou Dianzi University
Fei Lin Hangzhou Dianzi University
Timon Rabczuk Bauhaus University Weimar
Gang Xu Hangzhou Dianzi University
Research Group
Materials and Manufacturing (IDE) (TU Delft)
Copyright: © 2022 Dandan Wang, Jinlan Xu, Fei Gao, C.C. Wang, Renshu Gu, Fei Lin, Timon Rabczuk, Gang Xu
DOI
help_outline
https://doi.org/10.1016/j.cagd.2022.102087
Deep learning Isogeometric analysis Analysis-reuse CAD/CAE integration Topology-consistent model
More Info
expand_more

Published Date

2022

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Industrial Design Engineering

Department

Sustainable Design Engineering

Research Group

Materials and Manufacturing

Abstract

In this paper, a deep learning framework combined with isogeometric analysis (IGA for short) called IGA-Reuse-Net is proposed for efficient reuse of numerical simulation on a set of topology-consistent models. Compared with previous data-driven numerical simulation methods only for simple computational domains, our method can predict high-accuracy PDE solutions over topology-consistent geometries with complex boundaries. UNet3+ architecture with interlaced sparse self-attention (ISSA) module is used to enhance the performance of the network. In addition, we propose a new loss function that combines a coefficients loss and a numerical solution loss. Several training datasets with topology-consistent models are constructed for the proposed framework. To verify the effectiveness of our approach, two different types of Poisson equations with different source functions are solved on three datasets with different topologies. Our framework can achieve a good trade-off between accuracy and efficiency. It outperforms the physics-informed neural network (PINN for short) model and yields promising results of prediction.