Use of generative artificial intelligence in solving technical engineering tasks in design
DOI:
https://doi.org/10.33271/crpnmu/86.330Keywords:
generative design, product shape, topological optimizationAbstract
Purpose. To investigate generative artificial intelligence tools for the design of engineering products, enabling the automated synthesis of a rational form under specified boundary conditions and strength and efficiency criteria.
The methods. The potential of interactive modeling of product shape search is explored through engineering research: a conceptual approach to a fixed shape is considered, which acts as a visualization of interacting forces, and a manufacturing technology model is further proposed based on existing constraints. The implications of modeling based on the analysis of the state of production development for future directions of product evolution are considered.
Findings. Using the generative capabilities of automation tools powered by artificial intelligence frees the developer to create more meaningful designs that add value to the final product. It is shown that the integration of generative artificial intelligence with FEM verification provides a nonlinear increase in engineering efficiency (up to 2.7 times compared to the basic parametric approach), i.e. a change in topology has a proportionally greater impact on strength than on mass. It is proven that generative design can perform not only the function of automatic form construction, but is a tool for identifying and formalizing design dependencies of the type in the system of configuration processes, topology, mass-dimensional characteristics and safety factor. This allows us to move from empirical selection of options to controlled synthesis of optimal configurations with a predictable increase in efficiency.
The originality. For the first time, a quantitative relationship between the geometric parameters of the generated topology, the mass of the structure and the safety factor has been established for the design problem of a bicycle frame, which allowed analytically assessing the effectiveness of the obtained solutions in the form of the ratio of the safety factor to the mass.
Practical implementation. Using the capabilities of generative artificial intelligence, you can significantly speed up the design process, increase the efficiency and accuracy of calculations, and allow developers of engineering products to focus more on ideas.
References
1. Lomas, J. D., & Xue, H. (2022). Harmony in design: A synthesis of literature from classical philosophy, the sciences, economics, and design. She Ji: The Journal of Design, Economics, and Innovation, 8(1), 5–64. https://doi.org/10.1016/j.sheji.2022.01.001
2. Attar, R., Aish, R., Stam, J., Brinsmead, D., Tessier, A., Glueck, M., & Khan, A. (2009). Physics-based generative design. In Joining languages, cultures and visions: CAAD Futures 2009 (pp. 231–244). Les Presses de l’Université de Montréal.
3. Hatchuel, A., Le Masson, P., Thomas, M., & Weil, B. (2021). What is generative in generative design tools? Uncovering topological generativity with a C-K model of evolutionary algorithms. Proceedings of the Design Society, 1, 3419–3430. https://doi.org/10.1017/pds.2021.603
4. Byrne, J., Cardiff, P., Brabazon, A., & O’Neill, M. (2014). Evolving parametric aircraft models for design exploration and optimisation. Neurocomputing, 142, 39–47. https://doi.org/10.1016/j.neucom.2014.04.004
5. Nagy, D., Lau, D., Locke, J., Stoddart, J., Villaggi, L., Wang, R., Zhao, D., & Benjamin, D. (2017). Project discover: An application of generative design for architectural space planning. In Proceedings of the Symposium on Simulation for Architecture and Urban Design (SimAUD 2017) (pp. 1–8). Society for Modeling & Simulation International. https://doi.org/10.22360/SimAUD.2017.SimAUD.007
6. Chen, X. A., Tao, Y., Wang, G., Kang, R., Grossman, T., Coros, S., & Hudson, S. E. (2018). Forte: User-driven generative design. In Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems (pp. 1–12). Association for Computing Machinery. https://doi.org/10.1145/3173574.3174070
7. Wünsch, A., Schabacker, M., & Vajna, S. (2012). Designing a gearbox for a novel independently controllable transmission using the autogenetic design theory. In Proceedings of the 9th International Workshop on Integrated Product Development. Magdeburg, Germany.
8. Pismenkova, T., & Ziborov, K. (2021). Development of design thinking—A modern view on the training of masters of technical specialties on the experience of Dnipro University of Technology. International Scientific Journal of Universities and Leadership, 2(12), 22–34. https://doi.org/10.31874/2520-6702-2021-12-2-22-34
9. Burnap, A., Liu, Y., Pan, Y., Lee, H., Gonzalez, R., & Papalambros, P. Y. (2016). Estimating and exploring the product form design space using deep generative models. In Proceedings of the ASME 2016 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference: Volume 2A, 42nd Design Automation Conference. ASME. https://doi.org/10.1115/DETC2016-60091
Downloads
Published
Issue
Section
License
All articles are published under the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Authors retain copyright and grant the journal right of first publication.
Authors are permitted and encouraged to deposit the final published version of their article, or the Author's Accepted Manuscript (AAM), in institutional or subject-specific open-access repositories (including the university's own institutional repository, CORE, Zenodo, or Figshare), ensuring maximum visibility, accessibility, and impact of the publication.
