Przegląd algorytmów optymalizacji topologii za pomocą sieci neuronowych o otwartym kodzie

• Autorzy: Kowalski Damian

Identyfikatory

DOI

10.5604/01.3001.0054.8898

Warianty tytułu

EN

Review of open-source topology optimization algorithms with neural networks

• Języki publikacji: PL

Abstrakty

PL

Artykuł prezentuje metody optymalizacji topologii z udziałem sztucznych sieci neuronowych wraz z implementacjami o otwartym kodzie. Algorytmy te skupiają się głównie na optymalizacji konstrukcji, jednak podjęto także próby optymalizacji przewodnictwa cieplnego oraz interakcji płyn-konstrukcja. W pracy przedstawiono porównanie istotnych cech algorytmów oraz podsumowano wyniki przeprowadzonych eksperymentów z ich użyciem. Ponadto nakreślono perspektywy i ograniczenia przy stosowaniu sztucznych sieci neuronowych do zagadnienia optymalizacji.

EN

The article presents methods of topology optimization using artificial neural networks with their open-source implementations. The algorithms are focused mainly on structural optimization, though some attempts of heat transfer and fluid-structure interaction optimizing were made. The paper presents a comparison of essential features of the algorithms and sums up conducted experiments results. Furthermore, perspectives and limitations of using artificial neural networks for optimization task were outlined.

Słowa kluczowe

PL

optymalizacja topologii; sieci neuronowe; algorytm; otwarty kod źródłowy

EN

topology optimization; neural networks; algorithm; open source code

• Wydawca: Fundacja Polskiego Związku Inżynierów i Techników Budownictwa
• Czasopismo: Przegląd Budowlany
• Rocznik: 2024
• Tom: R. 95, nr 7
• Strony: 118--123
• Opis fizyczny: Bibliogr. 32 poz., il., tab.

Twórcy

autor

Kowalski Damian

• Wydział Budownictwa, Politechnika Częstochowska

• https://orcid.org/0000-0002-0257-7642

Bibliografia

• [1] Shin J., Kim C., Bi-directional evolutionary 3D topology optimization with a deep neural network, Journal of Mechanical Science and Technology 36, 2022, str. 3509-3519, https://doi.org/10.1007/s12206-022-0628-2
• [2] Kwok T. H., Improving the diversity of topology-optimized designs by swarm intelligence. Structural and Multidisciplinary Optimization 65, 2022, https://doi.org/10.1007/s00158-022-03295-w
• [3] Xu B., Han Y., Zhao L., Bi-directional evolutionary stress-based topology optimization of material nonlinear structures, Structural and Multidisciplinary Optimization 63, 2021, str. 1287-305, https://doi.org/10.1007/s00158-020-02757-3
• [4] Tajs-Zielińska K., Bochenek B., A heuristic approach to optimization of structural topology including self-weight, AIP Conf Proc, 1922, American Institute of Physics Inc., 2018, https://doi.org/10.1063/1.5019028
• [5] Rozvany G. I. N., A critical review of established methods of structural topology optimization, Structural and Multidisciplinary Optimization 37, 2009, str. 217-237, https://doi.org/10.1007/s00158-007-0217-0
• [6] Sigmund O., Maute K., Topology optimization approaches: A comparative review, Structural and Multidisciplinary Optimization 48, 2013, str. 1031-1055, https://doi.org/10.1007/s00158-013-0978-6
• [7] Ulu E., Zhang R., Kara L. B., A data-driven investigation and estimation of optimal topologies under variable loading configurations, Computer Methods Biomechanics and Biomedical Engineering Imaging and Visualization 4/2016, str. 61-72, https://doi.org/10.1080/21681163.2015.1030775
• [8] Raissi M., Perdikaris P., Karniadakis G. E., Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations. Preprint 2017, https://doi.org/https://doi.org/10.48550/arXiv.1711.10561
• [9] Raissi M., Perdikaris P., Karniadakis G. E., Physics Informed Deep Learning (Part II): Data-driven Discovery of Nonlinear Partial Differential Equations. Preprint 2017, https://doi.org/https://doi.org/10.48550/arXiv.1711.10566
• [10] Joglekar A., Chen H., Kara L. B., DMF-TONN: Direct Mesh-free Topology Optimization using Neural Networks, Engineering with Computers 2023, https://doi.org/https://doi.org/10.1007/s00366-023-01904-w
• [11] Márquez-Neila P., Salzmann M., Fua P., Imposing Hard Constraints on Deep Networks: Promises and Limitations. Preprint, 2017, https://doi.org/https://doi.org/10.48550/arXiv.1706.02025
• [12] Zehnder J., Li Y., Coros S., Thomaszewski B., NTopo: Mesh-free Topology Optimization using Implicit Neural Representations, 35th Conference on Neural Information Processing Systems (NeurIPS 2021), 2021
• [13] Chandrasekhar A., Suresh K., TOuNN: Topology Optimization using Neural Networks. Structural and Multidisciplinary Optimization 63, 2021, str. 1135-1149, https://doi.org/10.1007/s00158-020-02748-4
• [14] Hoyer S., Sohl-Dickstein J., Greydanus S., Neural reparameterization improves structural optimization. Preprint, 2019
• [15] Ulyanov D., Vedaldi A., Lempitsky V., Deep Image Prior, Computer Vision and Pattern Recognition 128, 2020, str. 1867-1888, https://doi.org/10.1007/s11263-020-01303-4
• [16] Sosnovik I., Oseledets I., Neural networks for topology optimization, Russian Journal of Numerical Analysis and Mathematical Modelling 34, 2019, str. 215-23, https://doi.org/10.1515/rnam-2019-0018
• [17] Nie Z., Lin T., Jiang H., Kara L. B., TopologyGAN: Topology Optimization Using Generative Adversarial Networks Based on Physical Fields Over the Initial Domain, Journal of Mechanical Design 143(3)2021, https://doi.org/https://doi.org/10.1115/1.4049533
• [18] He J., Chadha C., Kushwaha S., Koric S., Abueidda D., Jasiuk I., Deep energy method in topology optimization applications, Acta Mech 234, 2023, str. 1365-1379, https://doi.org/10.1007/s00707-022-03449-3
• [19] Bendsoe M. P., Sigmund O., Topology Optimization: Theory, Methods and Applications, 2nd ed. Berlin Heidelberg: Springer, 2003
• [20] Deng C., Wang Y., Qin C., Fu Y., Lu W., Self-directed online machine learning for topology optimization, Nat Commun 13, 2022, https://doi.org/10.1038/s41467-021-27713-7
• [21] Qian C., Ye W., Accelerating gradient-based topology optimization design with dual-model artificial neural networks, Structural and Multidisciplinary Optimization 63, 2021, str. 1687-1707, https://doi.org/10.1007/s00158-020-02770-6
• [22] Wang F., Lazarov B.S., Sigmund O., On projection methods, convergence and robust formulations in topology optimization. Structural and Multidisciplinary Optimization 43, 2011, str. 767-784, https://doi.org/10.1007/s00158-010-0602-y
• [23] Kingma D. P., Ba J., Adam: A Method for Stochastic Optimization, International Conference on Learning Representations, 2014
• [24] Liu D. C., Nocedal J., On the limited memory BFGS method for large scale optimization, Math Program 45, 1989, str. 503-28
• [25] Zhu C., Byrd R. H., Algorithm 778: L-BFGS-B: Fortran Subroutines for Large-Scale Bound-Constrained Optimization, ACM Transactions on Mathematical Software 23, 1997, str. 550-560
• [26] Duchi J., Hazan E., Singer Y., Adaptive Subgradient Methods for Online Learning and Stochastic Optimization, Journal of Machine Learning Research 12, 2011, str. 2121-2159
• [27] Ruder S., An overview of gradient descent optimization algorithms, Vestnik Komp Iuternykh i Informatsionnykh Tekhnologii, 2016, https://doi.org/10.14489/vkit.2019.12.pp.010-017
• [28] Raiaan M. A. K., Sakib S., Fahad N.M., Mamun A. Al., Rahman M.A., Shatabda S. et al., A systematic review of hyperparameter optimization techniques in Convolutional Neural Networks, Decision Analytics Journal 11/2024, https://doi.org/10.1016/j.dajour.2024.100470
• [29] Yu T., Zhu H., Hyper-Parameter Optimization: A Review of Algorithms and Applications. Preprint, 2020
• [30] Pfisterer F., Democratizing Machine Learning Contributions in AutoML and Fairness. Der Ludwig-Maximilians-Universität, 2022
• [31] Mirzaei S. R., Mao H., Al-Nima R. R. O., Woo W. L., Explainable AI Evaluation: A Top-Down Approach for Selecting Optimal Explanations for Black Box Models, Information (Switzerland) 15, 2024, https://doi.org/10.3390/info15010004
• [32] Saeed W., Omlin C., Explainable AI (XAI): A systematic meta-survey of current challenges and future opportunities, Knowledge Based Systems 263, 2023, https://doi.org/10.1016/j.knosys.2023.110273