Machine learning method in elastic plate topology optimization problems

Author details
  • Peter the Great Saint Petersburg Polytechnic University, Saint-Petersburg, Russian Federation
  • Peter the Great Saint Petersburg Polytechnic University, Saint-Petersburg, Russian Federation
  • Peter the Great Saint Petersburg Polytechnic University, Saint-Petersburg, Russian Federation

Abstract

In this article, as an alternative to traditional methods of topology optimization of deformable solids, an approach to topology optimization based on machine learning methods is proposed. The proposed approach significantly reduces the time spent on obtaining the optimal solution and allows to avoid the use of time-consuming finite element calculations at the stage of obtaining the optimal solution. All of time-consuming calculations are performed at the network training stage. A review of the world literature on the application of machine learning methods in the problem of topology optimization of an elastic deformable solid is given. Further, as an example, a square elastic plate is considered, fixed on one side and loaded with a force on the other. For a given plate, a series of topology optimization problems (maximizing stiffness under volume constraints) are solved using the method of moving asymptotes to build a training data set. A comparative study of a neural network with one custom nonlinear layer, based on the nature of the optimal topology, and a three-layer neural network built using the standard PyTorch library features is carried out. The input parameter of the neural network is the force application point, the output parameter is the optimal topology of the plate. The network is trained using the backpropagation method. The quadratic norm of the predicted design variable values deviations compared to the true values form last optimization is minimized during neural network learning. The considered example shows the possibility of applying the approach to other problems that differ in geometry, boundary conditions, etc. The results and unsolved problems of the method are also discussed.

Keywords

machine learningneural networksstructural optimizationtopological optimizationadaptive materialsPyTorchmoving asymptotesSIMP.

Bibliography

  1. 1.Sosnovik I, Oseledets I. Neural networks for topology optimization. Russian Journal of Numerical Analysis and Mathematical Modelling, 2019, 34(4): 215-223. Scholar
  2. 2.Saurabh Banga, Harsh Gehani, Sanket Bhilare, Sagar Patel, and Levent Kara. 3D Topology Optimization using Convolutional Neural Networks. Preprint, 8 2018. Scholar
  3. 3.Kai, R.; Chao, T.; Michael, Q.; Wenjing, W. An efficient data generation method for ANN—Based surrogate models. Struct Multidiscip. Optim. 2022, 65, 90. https://doi.org/10.1007/s00158- 022- 03180- 6 Scholar
  4. 4.Kallioras, N. A., Kazakis, G., & Lagaros, N. D. (2020). Accelerated topology optimization by means of deep learning. Structural and Multidisciplinary Optimization, 62(3), 1185-1212 Scholar
  5. 5.Hong-Ling Ye, Ji-Cheng Li, Bo-Shuai Yuan, Nan Wei, and Yun-Kang Sui. Acceleration Design for Continuum Topology Optimization by Using Pix2pix Neural Network. International Journal of Applied Mechanics, 13(04):2150042, 5 2021. ISSN 1758-8251. doi: 10.1142/S1758825121500423. Scholar
  6. 6.Younghwan Joo, Yonggyun Yu, and In Gwon Jang. Unit Module-Based Convergence Acceleration for Topology Optimization Using the Spatiotemporal Deep Neural Network. IEEE Access, 9:149766-149779, 2021. ISSN 2169-3536. doi: 10.1109/ACCESS.2021.3125014 Scholar
  7. 7.Lee, S., Kim, H., Lieu, Q. X., & Lee, J. (2020). CNN-based image recognition for topology optimization. Knowledge-Based Systems, 198, 105887 Scholar
  8. 8.Kim, C., Lee, J., & Yoo, J. (2021). Machine learning-combined topology optimization for functionary graded composite structure design. Computer Methods in Applied Mechanics and Engineering, 387, 114158. Scholar
  9. 9.White, D. A., Arrighi, W. J., Kudo, J., & Watts, S. E. (2019). Multiscale topology optimization using neural network surrogate models. Computer Methods in Applied Mechanics and Engineering, 346, 1118-1135 Scholar
  10. 10.Takahashi, Y., Suzuki, Y., & Todoroki, A. (2019). Convolutional neural network-based topology optimization (cnn-to) by estimating sensitivity of compliance from material distribution. arXiv preprint arXiv:2001.00635. Scholar
Download PDF

Article information

Published
3 July 2023
Issue date
3 July 2023
Issue
No. 3 (2023)
Share