An finite element analysis surrogate model with boundary oriented graph embedding approach for rapid design

Fu, Xingyu; Zhou, Fengfeng; Peddireddy, Dheeraj; Kang, Zhengyang; Jun, Martin Byung-Guk; Aggarwal, Vaneet

doi:10.1093/jcde/qwad025

Title: An finite element analysis surrogate model with boundary oriented graph embedding approach for rapid design

Journal Article · 24 March 2023 · Journal of Computational Design and Engineering (Online)

DOI: https://doi.org/10.1093/jcde/qwad025 · OSTI ID:1973285

; Zhou, Fengfeng; Peddireddy, Dheeraj; Kang, Zhengyang;

; Aggarwal, Vaneet

Abstract In this work, we present a boundary oriented graph embedding (BOGE) approach for the graph neural network to assist in rapid design and digital prototyping. The cantilever beam problem has been solved as an example to validate its potential of providing physical field results and optimized designs using only 10 ms. Providing shortcuts for both boundary elements and local neighbor elements, the BOGE approach can embed unstructured mesh elements into the graph and performs an efficient regression on large-scale triangular-mesh-based finite element analysis (FEA) results, which cannot be realized by other machine-learning-based surrogate methods. It has the potential to serve as a surrogate model for other boundary value problems. Focusing on the cantilever beam problem, the BOGE approach with 3-layer DeepGCN model achieves the regression with mean square error (MSE) of 0.011 706 (2.41% mean absolute percentage error) for stress field prediction and 0.002 735 MSE (with 1.58% elements having error larger than 0.01) for topological optimization. The overall concept of the BOGE approach paves the way for a general and efficient deep-learning-based FEA simulator that will benefit both industry and Computer Aided Design (CAD) design-related areas.

View Journal Article

Cite

Export

Save

Research Organization:: Univ. of California, Los Angeles, CA (United States)

Sponsoring Organization:: USDOE; USDOE Office of Energy Efficiency and Renewable Energy (EERE)

Grant/Contract Number:: EE0007613

OSTI ID:: 1973285

Journal Information:: Journal of Computational Design and Engineering (Online), Journal Name: Journal of Computational Design and Engineering (Online) Journal Issue: 3 Vol. 10; ISSN 2288-5048

Publisher:: Oxford University PressCopyright Statement

Country of Publication:: Korea, Republic of

Language:: English

References (22)

Deep learning–based stress prediction for bottom-up SLA 3D printing process Khadilkar, Aditya; Wang, Jun; Rai, Rahul The International Journal of Advanced Manufacturing Technology, Vol. 102, Issue 5-8 https://doi.org/10.1007/s00170-019-03363-4	journal	February 2019
A Bayesian multiscale CNN framework to predict local stress fields in structures with microscale features Krokos, Vasilis; Bui Xuan, Viet; Bordas, Stéphane P. A. Computational Mechanics, Vol. 69, Issue 3 https://doi.org/10.1007/s00466-021-02112-3	journal	November 2021
Multilayer feedforward networks are universal approximators Hornik, Kurt; Stinchcombe, Maxwell; White, Halbert Neural Networks, Vol. 2, Issue 5 https://doi.org/10.1016/0893-6080(89)90020-8	journal	January 1989
FeatureNet: Machining feature recognition based on 3D Convolution Neural Network Zhang, Zhibo; Jaiswal, Prakhar; Rai, Rahul Computer-Aided Design, Vol. 101 https://doi.org/10.1016/j.cad.2018.03.006	journal	August 2018
Smart finite elements: A novel machine learning application Capuano, German; Rimoli, Julian J. Computer Methods in Applied Mechanics and Engineering, Vol. 345 https://doi.org/10.1016/j.cma.2018.10.046	journal	March 2019
An intelligent nonlinear meta element for elastoplastic continua: deep learning using a new Time-distributed Residual U-Net architecture Koeppe, Arnd; Bamer, Franz; Markert, Bernd Computer Methods in Applied Mechanics and Engineering, Vol. 366 https://doi.org/10.1016/j.cma.2020.113088	journal	July 2020
Data-driven inverse modelling through neural network (deep learning) and computational heat transfer Tamaddon-Jahromi, Hamid Reza; Chakshu, Neeraj Kavan; Sazonov, Igor Computer Methods in Applied Mechanics and Engineering, Vol. 369 https://doi.org/10.1016/j.cma.2020.113217	journal	September 2020
A semi-supervised approach to architected materials design using graph neural networks Guo, Kai; Buehler, Markus J. Extreme Mechanics Letters, Vol. 41 https://doi.org/10.1016/j.eml.2020.101029	journal	November 2020
The state of framework development for implementing reasoning mechanisms in smart cyber-physical systems: A literature review Tepjit, Sirasak; Horváth, Imre; Rusák, Zoltán Journal of Computational Design and Engineering, Vol. 6, Issue 4 https://doi.org/10.1016/j.jcde.2019.04.002	journal	April 2019
Identifying manufacturability and machining processes using deep 3D convolutional networks Peddireddy, Dheeraj; Fu, Xingyu; Shankar, Anirudh Journal of Manufacturing Processes, Vol. 64 https://doi.org/10.1016/j.jmapro.2021.02.034	journal	April 2021
CNN-based image recognition for topology optimization Lee, Seunghye; Kim, Hyunjoo; Lieu, Qui X. Knowledge-Based Systems, Vol. 198 https://doi.org/10.1016/j.knosys.2020.105887	journal	June 2020
Design of an interpretable Convolutional Neural Network for stress concentration prediction in rough surfaces Kantzos, Christopher; Lao, Jacky; Rollett, Anthony Materials Characterization, Vol. 158 https://doi.org/10.1016/j.matchar.2019.109961	journal	December 2019
Real-time simulation of contact and cutting of heterogeneous soft-tissues Courtecuisse, Hadrien; Allard, Jérémie; Kerfriden, Pierre Medical Image Analysis, Vol. 18, Issue 2 https://doi.org/10.1016/j.media.2013.11.001	journal	February 2014
Deep learning in fluid dynamics Kutz, J. Nathan Journal of Fluid Mechanics, Vol. 814 https://doi.org/10.1017/jfm.2016.803	journal	January 2017
Finite element compatible matrix interpolation for parametric model order reduction of electrothermal microgripper Roy, Ananya; Nabi, M.; Rahman, Najmur Journal of Computational Design and Engineering, Vol. 8, Issue 6 https://doi.org/10.1093/jcde/qwab066	journal	December 2021
Dataset and method for deep learning-based reconstruction of 3D CAD models containing machining features for mechanical parts Lee, Hyunoh; Lee, Jinwon; Kim, Hyungki Journal of Computational Design and Engineering, Vol. 9, Issue 1 https://doi.org/10.1093/jcde/qwab072	journal	December 2021
Improved Dexel Representation: A 3-D CNN Geometry Descriptor for Manufacturing CAD Fu, Xingyu; Peddireddy, Dheeraj; Aggarwal, Vaneet IEEE Transactions on Industrial Informatics, Vol. 18, Issue 9 https://doi.org/10.1109/TII.2021.3136167	journal	September 2022
Stress Field Prediction in Cantilevered Structures Using Convolutional Neural Networks Nie, Zhenguo; Jiang, Haoliang; Kara, Levent Burak Journal of Computing and Information Science in Engineering, Vol. 20, Issue 1 https://doi.org/10.1115/1.4044097	journal	September 2019
TopologyGAN: Topology Optimization Using Generative Adversarial Networks Based on Physical Fields Over the Initial Domain Nie, Zhenguo; Lin, Tong; Jiang, Haoliang Journal of Mechanical Design, Vol. 143, Issue 3 https://doi.org/10.1115/1.4049533	journal	February 2021
Convolutional Neural Networks for Steady Flow Approximation Guo, Xiaoxiao; Li, Wei; Iorio, Francesco KDD '16: The 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining https://doi.org/10.1145/2939672.2939738	conference	August 2016
Kalibre Wang, Ruihang; Zhou, Xin; Dong, Linsen Proceedings of the 7th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation https://doi.org/10.1145/3408308.3427982	conference	November 2020
Application of Convolutional Neural Network to Predict Airfoil Lift Coefficient Zhang, Yao; Sung, Woong Je; Mavris, Dimitri N. 2018 AIAA/ASCE/AHS/ASC Structures, Structural Dynamics, and Materials Conference https://doi.org/10.2514/6.2018-1903	conference	January 2018

Similar Records

Towards Generalizable and Efficient Circuit Topology Design: A Graph-Transformer-based Surrogate Model with Curriculum Learning

Journal Article · 2026 · ACM Transactions on Design Automation of Electronic Systems · OSTI ID:3023663

Lu, Haoshu; Fan, Shaoze; Zhang, Shun; +3 more

Parameter uncertainties for imperfect surrogate models in the low-noise regime

Journal Article · 2025 · Machine Learning: Science and Technology · OSTI ID:2499832

Swinburne, Thomas D.; Perez, Danny

Efficient Surrogate Model Development: Impact of Sample Size and Underlying Model Dimensions

Journal Article · 2018 · Computer Aided Chemical Engineering · OSTI ID:1642420

Davis, Sarah E.; Cremaschi, Selen; Eden, Mario R.

Related Subjects

42 ENGINEERING
97 MATHEMATICS AND COMPUTING
Computer Science
Engineering
Graph neural network
Machine learning
Solid mechanics
Stress field
Topology optimization

Title: An finite element analysis surrogate model with boundary oriented graph embedding approach for rapid design

Citation Formats

References (22)

Similar Records

Related Subjects