Hostname: page-component-cd9895bd7-dk4vv Total loading time: 0 Render date: 2024-12-27T01:33:14.777Z Has data issue: false hasContentIssue false
  • English
  • Français

Generative large language models in engineering design: opportunities and challenges

Published online by Cambridge University Press:  16 May 2024

Filippo Chiarello ,
Simone Barandoni ,
Marija Majda Škec  and
Gualtiero Fantoni
Filippo Chiarello*
Affiliation:
University of Pisa, Italy
Simone Barandoni
Affiliation:
University of Pisa, Italy
Marija Majda Škec
Affiliation:
University of Zagreb Faculty of Mechanical Engineering and Naval Architecture, Croatia
Gualtiero Fantoni
Affiliation:
University of Pisa, Italy
*
filippo.chiarello@unipi.it

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.

Despite the rapid advancement of generative Large Language Models (LLMs), there is still limited understanding of their potential impacts on engineering design (ED). This study fills this gap by collecting the tasks LLMs can perform within ED, using a Natural Language Processing analysis of 15,355 ED research papers. The results lead to a framework of LLM tasks in design, classifying them for different functions of LLMs and ED phases. Our findings illuminate the opportunities and risks of using LLMs for design, offering a foundation for future research and application in this domain.

Keywords

artificial intelligence (AI)design processgenerative AIlarge language model (LLM)natural language processing (NLP)
Type
Artificial Intelligence and Data-Driven Design
Information
Proceedings of the Design Society , Volume 4: DESIGN 2024 , May 2024 , pp. 1959 - 1968
Creative Commons
Creative Common License - CCCreative Common License - BYCreative Common License - NCCreative Common License - ND
This is an Open Access article, distributed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives licence (http://creativecommons.org/licenses/by-nc-nd/4.0/), which permits non-commercial re-use, distribution, and reproduction in any medium, provided the original work is unaltered and is properly cited. The written permission of Cambridge University Press must be obtained for commercial re-use or in order to create a derivative work.
Copyright
The Author(s), 2024.

References

Agyemang, M., Andreae, D. A., & McComb, C. (2023), “Uncovering potential bias in engineering design research”, Design Science, 9. https://doi.org/10.1017/dsj.2023.17CrossRefGoogle Scholar
Ahmed, S., & Štorga, M. (2009). Merged ontology for engineering design: Contrasting empirical and theoretical approaches to develop engineering ontologies. AI EDAM, 23(4), 391-407. https://doi.org/10.1017/S0890060409000146CrossRefGoogle Scholar
Andersson, T. (2020), “Design judgement processes in mature Swedish manufacturing companies”, Journal of Design Research, Vol. 18 No. 5-6, pp. 410-433. https://doi.org/10.1504/JDR.2020.118668CrossRefGoogle Scholar
Barandoni, S., Giordano, V., Fantoni, G., & Chiarello, F. (2023), “The ChatGPT Tweets Dataset [Data set]”, Kaggle, https://doi.org/10.34740/KAGGLE/DSV/6241027CrossRefGoogle Scholar
Buonamici, F., Carfagni, M., Furferi, R., Volpe, Y., Governi, L., 2020, “Generative Design: An Explorative Study”, Computer-Aided Design and Applications, Vol. 18, pp. 144–155. https://doi.org/10.14733/cadaps.2021.144-155CrossRefGoogle Scholar
Brown, D. R., & Hwang, K. Y. (1993), “Solving fixed configuration problems with genetic search”, Research in Engineering Design, Vol. 5, pp. 80-87. https://doi.org/10.1007/BF02032577CrossRefGoogle Scholar
Cheligeer, C., Huang, J., Wu, G., Bhuiyan, N., Xu, Y., & Zeng, Y. (2022), “Machine learning in requirements elicitation: A literature review”, AI EDAM, Vol. 36. https://doi.org/10.1017/S0890060422000166Google Scholar
Chiarello, F., Belingheri, P., & Fantoni, G. (2021), “Data science for engineering design: State of the art and future directions”, Computers in Industry, Vol. 129, 103447. https://doi.org/10.1016/j.compind.2021.103447CrossRefGoogle Scholar
Chiarello, F., Bonaccorsi, A., & Fantoni, G. (2020), “Technical sentiment analysis, Measuring advantages and drawbacks of new products using social media”, Computers in Industry, Vol. 123, 103299. https://doi.org/10.1016/j.compind.2020.103299CrossRefGoogle Scholar
Cummings, M., & Teal, G. (2023), “Healing fabulations: a dialogic methodology for digital codesign in health research”, CoDesign, Vol. 19 No. 1, pp. 74-90, https://doi.org/10.1080/15710882.2022.2157837CrossRefGoogle Scholar
Fantoni, G., Apreda, R., Dell'Orletta, Felice., & Monge, Maurizio (2013), “Automatic extraction of function–behaviour–state information from patents”, Advanced Engineering Informatics, Vol. 27 No. 3, pp. 317-334. https://doi.org/10.1016/j.aei.2013.04.004CrossRefGoogle Scholar
Franceschini, F., & Rossetto, S. (1995), “QFD: the problem of comparing technical/engineering design requirements”, Research in Engineering design, Vol. 7, pp. 270-278. https://doi.org/10.1007/BF01580463CrossRefGoogle Scholar
Gunaratnam, D. J., & Gero, J. S. (1994), “Effect of representation on the performance of neural networks in structural engineering applications”. Computer-Aided Civil and Infrastructure Engineering, Vol. 9 No. 2, pp. 97-108.CrossRefGoogle Scholar
Han, J., Sarica, S., Shi, F., & Luo, J. (2022). Semantic networks for engineering design: state of the art and future directions. Journal of Mechanical Design, 144(2), 020802. https://doi.org/10.1115/1.4052148.Google Scholar
Han, J., Shi, F., Chen, L., & Childs, P. R. (2018), “The Combinator–a computer-based tool for creative idea generation based on a simulation approach”, Design Science, Vol. 4, No. 11. https://doi.org/10.1017/dsj.2018.7CrossRefGoogle Scholar
Honnibal, M., and Montani, I. (2017), “spaCy 2: Natural language understanding with Bloom embeddings, convolutional neural networks and incremental parsing”.Google Scholar
Huang, F., Kwak, H., An, J., (2023), “Is ChatGPT Better than Human Annotators? Potential and Limitations of ChatGPT in Explaining Implicit Hate Speech”, arXiv Preprint ArXiv:2302.07736. https://doi.org/10.48550/arXiv.2302.07736Google Scholar
Hwang, A. H. C. (2022, April), “Too late to be creative? AI-empowered tools in creative processes”, CHI Conference on Human Factors in Computing Systems Extended Abstracts, pp. 1-9. https://doi.org/10.1145/3491101.3503549CrossRefGoogle Scholar
Johannesson, P., & Perjons, E. (2014), “An introduction to design science”, Vol. 10, pp. 978-3, Cham: Springer. https://doi.org/10.1007/978-3-319-10632-8CrossRefGoogle Scholar
Kicinger, R., Arciszewski, T., & DeJong, K. (2005), “Evolutionary design of steel structures in tall buildings”, Journal of Computing in Civil Engineering, Vol. 19 No. 3, pp. 223-238.CrossRefGoogle Scholar
Lee, J. W., Daly, S. R., Vadakumcherry, V., & Rodrigues, D. (2023), “Idea generation, development and selection: a study of mechanical engineering students’ natural approaches and the impact of hybrid learning blocks”, Design Science, Vol. 9. https://doi.org/10.1017/dsj.2023.26CrossRefGoogle Scholar
Moses, N. D., Wojciechowski, L. R., Daly, S. R., & Sienko, K. H. (2023), “Front-end design prototyping strategies during remote stakeholder engagement”, Design Science, Vol. 9, e24. https://doi.org/10.1017/dsj.2023.23CrossRefGoogle Scholar
Mugge, R., Schoormans, J. P., & Schifferstein, H. N. (2009), “Emotional bonding with personalised products”, Journal of Engineering Design, Vol. 20 No. 5, pp. 467-476. https://doi.org/10.1080/09544820802698550CrossRefGoogle Scholar
Nie, Z., Lin, T., Jiang, H., & Kara, L. B. (2021), “Topologygan: Topology optimisation using generative adversarial networks based on physical fields over the initial domain”, Journal of Mechanical Design, Vol. 143 No. 3, 031715. https://doi.org/10.1115/1.4049533CrossRefGoogle Scholar
Nobari, A. H., Rashad, M. F., & Ahmed, F. (2021), “Creativegan: Editing generative adversarial networks for creative design synthesis”. arXiv preprint arXiv:2103.06242.Google Scholar
Puccetti, G., Giordano, V., Spada, I., Chiarello, F., & Fantoni, G. (2023), “Technology identification from patent texts: A novel named entity recognition method”, Technological Forecasting and Social Change, Vol. 186, 122160. https://doi.org/10.1016/j.techfore.2022.122160CrossRefGoogle Scholar
Regenwetter, L., Nobari, A. H., & Ahmed, F. (2022), “Deep generative models in engineering design: A review”, Journal of Mechanical Design, Vol. 144 No. 7, 071704. https://doi.org/10.1115/1.4053859CrossRefGoogle Scholar
Sarica, S., Song, B., Low, E., Luo, J., (2019), “Engineering knowledge graph for keyword discovery in patent search”, Proceedings of the International Conference on Engineering Design, Cambridge University Press, pp. 2249–2258. https://doi.org/10.1017/dsi.2019.231Google Scholar
Shafqat, A., Oehmen, J., Welo, T., & Willumsen, P. (2019), “The cost of learning from failures and mistakes in new product development projects: An exploratory framework”, Proceedings of the International Conference on Engineering Design, ICED, Vol. 1, pp. 1791-1800. https://doi.org/10.1017/dsi.2019.171Google Scholar
Bhattacharjee, Shankar, Kumar Singh, K., & Ray, H., T. (2016), “Multi-objective optimisation with multiple spatially distributed surrogates”, Journal of Mechanical Design, Vol. 138 No. 9, 091401. https://doi.org/10.1115/1.4034035CrossRefGoogle Scholar
She, J., Belanger, E., Bartels, C., & Reeling, H. (2022), “Improve Syntax Correctness and Breadth of Design Space Exploration in Functional Analysis”, Journal of Mechanical Design, Vol. 144 No. 11, https://doi.org/10.1115/1.4054875CrossRefGoogle Scholar
Siddharth, L., Blessing, L., & Luo, J. (2022), “Natural language processing in-and-for design research”, Design Science, Vol. 8, e21. https://doi.org/10.1017/dsj.2022.16CrossRefGoogle Scholar
Stevenson, P. D., & Mattson, C. A. (2019), “The personification of big data”, Proceedings of the International Conference on Engineering Design (ICED ), pp. 4019-4028. https://doi.org/10.1017/dsi.2019.409CrossRefGoogle Scholar
Stevenson, P. D., Mattson, C. A., Dahlin, E. C., & Salmon, J. L. (2023), “Creating predictive social impact models of engineered products using synthetic populations”, Research in Engineering Design, Vol. 34 No. 4, pp. 461-476. https://doi.org/10.1007/s00163-023-00424-4CrossRefGoogle Scholar
Thoring, K., Huettemann, S., & Mueller, R. M. (2023), “The Augmented Designer: a Research Agenda for Generative AI-Enable Design”, Proceedings of the Design Society, Vol. 3, pp. 3345-3354. https://doi.org/10.1017/pds.2023.335CrossRefGoogle Scholar