Abstract
Simulations are crucial for validating the design of engineering systems and their components. However, before simulations can be performed, the geometry of the component must undergo meshing, which involves dividing it into small elements to solve the Partial Differential Equations that describe the phenomenon being simulated. This process can be computationally expensive, so we propose a meshing algorithm that uses Generator Neural Networks to generate refined meshes. Our algorithm is based on a generator used in a Conditional Generative Adversarial Network, which was trained on reference meshes generated by conventional meshing codes. The proposed scheme generated mesh nodal coordinates for both 2D and 3D geometries, and the difference between the element quality of our meshes and the reference meshes used as training data was only 1%. Our algorithm was also 75% faster than the algorithm used to generate the training data meshes. We demonstrate that refined meshes can be generated without relying on computationally expensive solvers.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Arahira T, Todo M, Myoui A (2021) Fracture analysis of porous bioceramics by finite element method. ICIC Express Lett, Part B: Appl 12(07):619
Zienkiewicz OC, Taylor RL, Zhu JZ (2005) The finite element method: its basis and fundamentals. Elsevier
Ainsworth M, Oden JT (1997) A posteriori error estimation in finite element analysis. Comput Methods Appl Mech Eng 142(1–2):1–88
Chang-Hoi A, Sang-Soo L, Hyuek-Jae L, Soo-Young L (1991) A self-organizing neural network approach for automatic mesh generation. IEEE Trans Magn 27(5):4201–4204
Chedid R, Najjar N (1996) Automatic finite-element mesh generation using artificial neural networks-part i: prediction of mesh density. IEEE Trans Magn 32(5):5173–5178
Manevitz L, Yousef M, Givoli D (1997) Finite-element mesh generation using self-organizing neural networks. Comput-Aided Civil Infrastruct Eng 12(4):233–250
Nechaeva O (2006) Composite algorithm for adaptive mesh construction based on self-organizing maps. In: International conference on artificial neural networks, pp. 445–454 . Springer
Alfonzetti S, Coco S, Cavalieri S, Malgeri M (1996) Automatic mesh generation by the let-it-grow neural network. IEEE Trans Magn 32(3):1349–1352
Triantafyllidis DG, Labridis DP (2002) A finite-element mesh generator based on growing neural networks. IEEE Trans Neural Netw 13(6):1482–1496
Martinetz T, Schulten K (1994) Topology representing networks. Neural Netw 7(3):507–522
Fritzke B (1995) A growing neural gas network learns topologies. Adv Neural Inf Process Syst 7:625–632
Álvarez R, Noguera J, Tortosa L, Zamora A (2006) Gng3d-a software tool for mesh optimization based on neural networks. In: The 2006 IEEE international joint conference on neural network proceedings, pp. 4005–4012 . IEEE
Vinyals O, Fortunato M, Jaitly N (2015) Pointer networks. arXiv preprint arXiv:1506.03134
Sutskever I, Vinyals O, Le QV (2014) Sequence to sequence learning with neural networks. In: Advances in neural information processing systems, pp. 3104–3112
Kim J, Choi J, Kang W (2020) A data-driven approach for simultaneous mesh untangling and smoothing using pointer networks. IEEE Access 8:70329–70342
Zhang Z, Wang Y, Jimack PK, Wang H (2020) Meshingnet: a new mesh generation method based on deep learning. In: International conference on computational science, pp. 186–198 . Springer
Papagiannopoulos A, Clausen P, Avellan F (2021) How to teach neural networks to mesh: application on 2-d simplicial contours. Neural Netw 136:152–179
Chen X, Li T, Wan Q, He X, Gong C, Pang Y, Liu J (2022) Mgnet: a novel differential mesh generation method based on unsupervised neural networks. Eng Comput 38(5):4409–4421
Chen X, Liu J, Yan J, Wang Z, Gong C (2022) An improved structured mesh generation method based on physics-informed neural networks. arXiv preprint arXiv:2210.09546
Mehendale N, Soman S (2021) Finite element (fe) mesh generation for 2d shapes using multiple long short-term memory networks. Available at SSRN 3968782
Goodfellow I, Bengio Y, Courville A (2016) Deep learning. MIT press
Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2(5):359–366
Goodfellow IJ, Shlens J, Szegedy C (2014) Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572
Kushida J-I, Hara A, Takahama T (2020) Generation of adversarial examples using adaptive differential evolution. Int J Innov Comput, Inform Control 16(5):405–414
Radford A, Metz L, Chintala S (2015) Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434
Persson P-O, Strang G (2004) A simple mesh generator in matlab. SIAM Rev 46(2):329–345
Strang G (2007) Computational science and engineering. Wellesley-Cambridge Press . https://books.google.co.in/books?id=GQ9pQgAACAAJ
Field DA (2000) Qualitative measures for initial meshes. Int J Numer Meth Eng 47(4):887–906
Acknowledgements
The authors express their gratitude to Rutwik Patel, Vrushali Sule, Dr. Devayani Soman, and Swanand Soman for their review and assistance in formatting the manuscript. The authors are thankful for their valuable feedback and insightful suggestions.
Funding
No funding was involved in the present work.
Author information
Authors and Affiliations
Contributions
Conceptualization was done by S. Soman (SS) and N. Mehendale (NM). All the literature reading and data gathering were performed by SS. All the experiments and coding were performed by SS. The formal analysis was performed by SS. Manuscript writing—original draft preparation was done by SS. Review and editing were done by NM. Visualization work was carried out by SS and NM.
Corresponding author
Ethics declarations
Conflicts of interest
Authors S. Soman and N. Mehendale declare that there has been no conflict of interest.
Code availability
All the codes have been made available in the supplementary material.
Ethics approval
All authors consciously assure that the manuscript fulfills the following statements: (1) This material is the authors’ own original work, which has not been previously published elsewhere. (2) The paper is not currently being considered for publication elsewhere. (3) The paper reflects the authors’ own research and analysis in a truthful and complete manner. (4) The paper properly credits the meaningful contributions of co-authors and co-researchers. (5) The results are appropriately placed in the context of prior and existing research.
Consent to participate
Informed consent was not required as there were no human participants. All the necessary permissions were obtained from Institute’s Ethical committee and concerned authorities.
Consent for publication
Authors have taken all the necessary consents for publication from participants wherever required.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Supplementary file1 (MP4 759 KB)
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Soman, S., Mehendale, N. Faster and efficient tetrahedral mesh generation using generator neural networks for 2D and 3D geometries. Neural Comput & Applic 36, 1805–1813 (2024). https://doi.org/10.1007/s00521-023-09119-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-023-09119-2