This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Application of Adversarial Networks for 3D Structural Topology Optimization
Technical Paper
2019-01-0829
ISSN: 0148-7191, e-ISSN: 2688-3627
Annotation ability available
Sector:
Language:
English
Abstract
Topology optimization is a branch of structural optimization which solves an optimal material distribution problem. The resulting structural topology, for a given set of boundary conditions and constraints, has an optimal performance (e.g. minimum compliance). Conventional 3D topology optimization algorithms achieve quality optimized results; however, it is an extremely computationally intensive task which is, in general, impractical and computationally unachievable for real-world structural optimal design processes. Therefore, the current development of rapid topology optimization technology is experiencing a major drawback. To address the issues, a new approach is presented to utilize the powerful abilities of large deep learning models to replicate this design process for 3D structures. Adversarial models, primarily Wasserstein Generative Adversarial Networks (WGAN), are constructed which consist of 2 deep convolutional neural networks (CNN) namely, a discriminator and a generator. A minimax game is conducted between the generator and the discriminator as part of training where the discriminator maximizes the loss function whereas the generator tries to minimize the loss function of the model. Once trained, the generator from GAN can produce 3D structures in a computationally inexpensive process instantaneously. The corresponding input variables of the new generated structures are evaluated using a trained convolutional neural network. The dataset needed for training is generated using the traditional 3D topology optimization algorithms. Results from the GANs are validated by comparing these optimal structures against the 3D structures generated from the traditional algorithms with the same design settings. The potential issues and future extension of this work are discussed in detail in the article. As illustrated, introducing deep learning into the field of design will remarkably reduce the work time of an iterative design process.
Recommended Content
Citation
Rawat, S. and Shen, M., "Application of Adversarial Networks for 3D Structural Topology Optimization," SAE Technical Paper 2019-01-0829, 2019, https://doi.org/10.4271/2019-01-0829.Also In
References
- Joseph , V. , Hung , Y. , Sudijianto , A. , and Kriging , B. A New Method for Developing Metamodels ASME Journal of Mechanical Design 130 3 031102 031102-8 2008 10.1115/1.2829873
- Cauchy , A. M’ethode g’en’erale pour la r’esolution des syst’emes d’´equations simultan’ees C. R. Acad. Sci. Paris 25 536 538 1847
- Deb , K. , Pratap , A. , Agarwal , S. et al. A Fast and Elitist Multiobjective Genetic Algorithm: NSGA-II IEEE Trans. Evol. Comput. 6 2 182 197 2002
- Kennedy , J and Eberhat , R Particle Swarm Optimization Proceedings of the 1995 IEEE International Conference on Neural Networks (Perth. Australia): IEEE Service Center Piscataway, NJ IV 1942 1948
- Bendsøe , M.P. Optimal Shape Design as a Material Distribution Problem Structural and Multidisciplinary Optimization 1 4 193 202 1989
- Bendsøe , M.P. , Philip , M. , and Sigmund , O. Topology Optimization Theory, Methods, and Applications Springer 2004 9783662050866
- Bendsøe , M.P. and Philip , M. Optimization of Structural Topology, Shape, and Material New York Springer 1995 9783662031155
- Fleury C. Shape Optimal Design by the Convex Linearization Method Bennett J.A. , Botkin M.E. The Optimum Shape General Motors Research Laboratories Symposia Series. Springer Boston, MA 1986
- Bremicker , M. , Chirehdast , M. , Kikuchi , N. , and Papalambros , P.Y. Integrated Topology and Shape Optimization in Structural Design Mechanics of Structures and Machines 19 4 551 587 1991 10.1080/08905459108905156
- Olhoff , N. , Bendsøe , M.P. , and Rasmussen , J. On CAD-Integrated Structural Topology and Design Optimization Comp. Meths. Appl. Mech. Eng. 89 259 279 1992
- Bendsøe , M.P. , Lund , E. , Olhoff , N. , and Sigmund , O. Topology Optimization-Broadening the Areas of Application Control and Cybernetics 34 7 35 2005
- Kim , Y.Y. and Yoon , G.H. Multi-Resolution Multi-Scale Topology Optimization - A New Paradigm International Journal of Solids and Structures 37 5529 5559 2000 10.1016/S0020-7683(99)00251-6
- Kim , S.Y. , Kim , I.Y. , and Mechefske , C.K. A New Efficient Convergence Criterion for Reducing Computational Expense in Topology Optimization: Reducible Design Variable Method International Journal of Numerical Methods in Engineering 90 752 783 2012 10.1002/nme.3343
- Liu , K , Tovar , A , Nutwell , E , and Detwiler , D Towards Nonlinear Multimaterial Topology Optimization Using Unsupervised Machine Learning and Metamodel-Based Optimization 41st Design Automation Conference 2015 2B 10.1115/DETC2015-46534
- Sosnovik , I. and Oseledets , I. 2017
- Goodfellow , I.J. , Pouget-Abadie , J , Mirza , M , Xu , B et al. 2014
- Yu , Y , Hur , T , and Jung , J
- Yu , Y , Hur , T , Jung , J , and Jang , I.G 2018
- Li , Y , Wang , H , Mo , H , and Zeng , T 2018
- Rawat , S. and Shen , M.-H. 2018
- Bendsøe , M.P. Optimal Shape Design as a Material Distribution Problem Structural and Multidisciplinary Optimization 1 4 193 202 1989
- Sigmund , O. A 99line Code Topology Optimization Code Written in MATLAB Structural and Multidisciplinary Optimization 21 120 127 2001
- Andreassen , E. , Clausen , A. , Schevenels , M. , Lazarov , S.B. et al. Efficient Topology Optimization in MATLAB Using 88 Lines of Code Structural and Multidisciplinary Optimization 43 1 2011 16 2011 10.1007/s00158-010-0594-7
- Salimans , T , Goodfellow , I , Zaremba , W , Cheung V et al. 2015
- Arjovsky , M , Chintala , S , and Bottou , L 2017
- LeCun , Y. , Boser , B. , Denker , J.S. , Henderson , D. et al. Backpropagation Applied to Handwritten Zip Code Recognition Neural Computation 1 541 551 1989 10.1162/neco.1989.1.4.541
- Kingma D. and Ba J. Adam: A Method for Stochastic Optimization International Conference on Learning Representations (ICLR) 2015
- Radford , A , Metz , L , and Chintala , S 2016