A Generative Deep Learning Approach for Improving the Mechanical Performance of Structural Components
Source abstract
Abstract
This study aimed to improve the mechanical properties of 3D concept designs by combining the design capability of a generative adversarial network with finite element analysis. This approach offers an innovative perspective on the conditioning of generative models while improving design properties and automation. A new design and evaluation framework has been developed for GAN models to generate 3D models with improved mechanical properties. The framework is an iterative process that includes dataset generation, GAN training, and finite element analysis. A “joint” component used in the aerospace industry is considered to demonstrate the proposed method’s effectiveness. Over six iterations, an increase of 20% is recorded in the average safety factor of the designs, and the variety of designs produced is narrowed in the desired direction. These findings suggest that the direct generation of structural components with generative models can expand the potential of deep learning in engineering design. Another innovative aspect of this study is that it provides a new option for the conditioning of data-dependent generative design models.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: 3D Surveying and Cultural Heritage · Manufacturing Process and Optimization · BIM and Construction Integration
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Industrial Design Engineering, Gazi University, 06500 Ankara, Türkiye
Funding
TÜBİTAK
References (54)
Show source-provided references
1. Special Issue: Machine Learning for Engineering Design10.1115/1.4044690 ↗
2. Gatys, L.A., Ecker, A.S., and Bethge, M. (2016, January 27–30). Image Style Transfer Using Convolutional Neural Networks. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.265 ↗
3. Machine Learning-Driven Real-Time Topology Optimization under Moving Morphable Component-Based Framework10.1115/1.4041319 ↗
4. Review of artificial intelligence applications in engineering design perspective10.1016/j.engappai.2022.105697 ↗
5. Emerging artificial intelligence methods in structural engineering10.1016/j.engstruct.2018.05.084 ↗
6. 3D Design Using Generative Adversarial Networks and Physics-Based Validation10.1115/1.4045419 ↗
7. Innovation and Design in the Age of Artificial Intelligence10.1111/jpim.12523 ↗
8. A computational tool for creative idea generation based on analogical reasoning and ontology10.1017/S0890060418000082 ↗
9. Boden, M.A. (2004). The Creative Mind: Myths and Mechanisms, Routledge.10.4324/9780203508527 ↗
10. Attribute-Aware Generative Design With Generative Adversarial Networks10.1109/ACCESS.2020.3032280 ↗
11. Creative idea generation method based on deep learning technology10.1007/s10798-019-09556-y ↗
12. DeepMorpher: Deep learning-based design space dimensionality reduction for shape optimisation10.1080/09544828.2023.2192606 ↗
13. Deep generative models in engineering design: A review10.1115/1.4053859 ↗
14. Zhang, W., Yang, Z., Jiang, H., Nigam, S., Yamakawa, S., Furuhata, T., Shimada, K., and Kara, L.B. (2019, January 18–21). 3D Shape Synthesis for Conceptual Design and Optimization Using Variational Autoencoders. Proceedings of the ASME 2019 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, Anaheim, CA, USA.10.1115/DETC2019-98525 ↗
15. Learning to Design From Humans: Imitating Human Designers Through Deep Learning10.1115/1.4044256 ↗
16. Using Physics-Informed Generative Adversarial Networks to Perform Super-Resolution for Multiphase Fluid Simulations10.1115/1.4053671 ↗
17. Yu, S., Dong, H., Wang, P., Wu, C., and Guo, Y. (2019). Generative Creativity: Adversarial Learning for Bionic Design, Springer.10.1007/978-3-030-30508-6_42 ↗
18. Mirza, M., and Osindero, S. (2014). Conditional generative adversarial nets. arXiv.
19. GAN-DUF: Hierarchical Deep Generative Models for Design under Free-Form Geometric Uncertainty10.1115/1.4055898 ↗
20. Deep Generative Design: Integration of Topology Optimization and Generative Models10.1115/1.4044229 ↗
21. Data-driven design exploration method using conditional variational autoencoder for airfoil design10.1007/s00158-021-02851-0 ↗
22. Nie, Z., Lin, T., Jiang, H., and Kara, L.B. (2020). TopologyGAN: Topology Optimization Using Generative Adversarial Networks Based on Physical Fields Over the Initial Domain. arXiv.10.1115/DETC2020-22675 ↗
23. Predictive GAN-Powered Multi-Objective Optimization for Hybrid Federated Split Learning10.1109/TCOMM.2023.3277878 ↗
24. Integrating deep learning into CAD/CAE system: Generative design and evaluation of 3D conceptual wheel10.1007/s00158-021-02953-9 ↗
25. Synthesizing Designs With Interpart Dependencies Using Hierarchical Generative Adversarial Networks10.1115/1.4044076 ↗
26. Simplification of 3D CAD Model in Voxel Form for Mechanical Parts Using Generative Adversarial Networks10.1016/j.cad.2023.103577 ↗
27. MO-PaDGAN: Reparameterizing Engineering Designs for augmented multi-objective optimization10.1016/j.asoc.2021.107909 ↗
28. Nobari, A.H., Chen, W., and Ahmed, F. (2021, January 14–18). PcDGAN: A Continuous Conditional Diverse Generative Adversarial Network For Inverse Design. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, Virtual Event, Singapore.
29. Nobari, A.H., Chen, W., and Ahmed, F. (2021). Range-Constrained Generative Adversarial Network: Design Synthesis Under Constraints Using Conditional Generative Adversarial Networks. J. Mech. Des., 144.
30. Giannone, G., Regenwetter, L., Srivastava, A., Gutfreund, D., and Ahmed, F. (2023). Learning from Invalid Data: On Constraint Satisfaction in Generative Models. arXiv.
31. Deep learning for determining a near-optimal topological design without any iteration10.1007/s00158-018-2101-5 ↗
32. ShipHullGAN: A generic parametric modeller for ship hull design using deep convolutional generative model10.1016/j.cma.2023.116051 ↗
33. Real-Time Topology Optimization in 3D via Deep Transfer Learning10.1016/j.cad.2021.103014 ↗
34. Rawat, S., and Shen, M.H. (2019). Application of Adversarial Networks for 3D Structural Topology Optimization, SAE International.10.4271/2019-01-0829 ↗
35. Product Design Award Prediction Modeling: Design Visual Aesthetic Quality Assessment via DCNNs10.1109/ACCESS.2020.3039715 ↗
36. Achlioptas, P., Diamanti, O., Mitliagkas, I., and Guibas, L.J. (, 2017). Learning Representations and Generative Models for 3D Point Clouds. Proceedings of the International Conference on Machine Learning, Kyoto, Japan. Available online: https://arxiv.org/abs/1707.02392.
37. Li, C.-L., Zaheer, M., Zhang, Y., Poczos, B., and Salakhutdinov, R. (2018). Point cloud gan. arXiv.
38. 3D convolutional neural network for object recognition: A review10.1007/s11042-018-6912-6 ↗
39. Wu, Z., Song, S., Khosla, A., Yu, F., Zhang, L., Tang, X., and Xiao, J. (2015, January 7–12). 3d shapenets: A deep representation for volumetric shapes. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.
40. Computational design in architecture: Defining parametric, generative, and algorithmic design10.1016/j.foar.2019.12.008 ↗
41. Ahlquist, S., and Menges, A. (2011). Computational Design Thinking, Wiley.
42. Voronoi diagrams with overlapping regions10.1007/s00291-012-0292-5 ↗
43. Laaroussi, F.-E., Nouh, B., and Bakkali, M. (2020). Intelligent Environments 2020, IOS Press.
44. Generative adversarial networks10.1145/3422622 ↗
45. Wu, J., Zhang, C., Xue, T., Freeman, W.T., and Tenenbaum, J.B. (2016, January 5–10). Learning a probabilistic latent space of object shapes via 3d generative-adversarial modeling. Proceedings of the 30th International Conference on Neural Information Processing Systems, Barcelona, Spain.
46. A GAN-Based Surrogate Model for Instantaneous Urban Wind Flow Prediction10.1016/j.buildenv.2023.110384 ↗
47. Rahman, R. (2020). Computer Games Technology, Abertay University.
48. Bendale, S. (2020). A Study of 3D-GANs and their Implementation Challenges. Int. Res. J. Eng. Technol., 194.
49. Generative adversarial network in medical imaging: A review10.1016/j.media.2019.101552 ↗
50. Application of python-based Abaqus preprocess and postprocess technique in analysis of gearbox vibration and noise reduction10.1007/s11465-011-0128-z ↗
51. Additive manufacturing methods and modelling approaches: A critical review10.1007/s00170-015-7576-2 ↗
52. Ian Gibson, I.G. (2015). Additive Manufacturing Technologies 3D Printing, Rapid Prototyping, and Direct Digital Manufacturing, Springer.10.1007/978-1-4939-2113-3 ↗
53. Recent developments in fused deposition modeling-based 3D printing of polymers and their composites10.1080/15583724.2019.1597883 ↗
54. Metal additive manufacturing: A review10.1007/s11665-014-0958-z ↗