Research on the Design Method of High-Speed Rail Seat Shape Driven by Generative Artificial Intelligence
DOI:
https://doi.org/10.54097/ketcv708Keywords:
High-speed Rail Seats, Generative Artificial Intelligence, Industrial Design Process, Quantitative EvaluationAbstract
Moving beyond conventional paradigms, this study investigates the transformative integration of Generative Artificial Intelligence (GAI) within industrial design, proposing a novel framework specifically tailored for high-speed rail seat styling. The methodology commences with the extraction of consumer perceptual imagery regarding seating via user interviews and GPT-4o analysis. Subsequently, Midjourney is leveraged to translate these insights into a visual corpus of design alternatives. By defining target imagery and anchoring foundational geometries, candidate solutions are rigorously screened through a dual-track evaluation system. Furthermore, employing Rhino for geometric deconstruction and Stable Diffusion for rendering, the study executes a concrete recombination of design curves to yield innovative 3D prototypes. Empirical results substantiate that this GAI-augmented workflow not only reconciles aesthetic appeal with user perceptual expectations but also significantly catalyzes design efficiency and innovation, offering profound implications for the optimization of traditional design ecosystems.
Downloads
References
[1] Smith, R. P., & Morrow, J. A. (1999). Product development process modeling. Design Studies, 20(3), 237–261. https://doi. org/ 10.1016/S0142-694X (98)00032-1.
[2] Shivegowda, M. D., Boonyasonpon, P., & Rangappa, S. M. (2022). A review on computer-aided design and manufacturing processes in design and architecture. Archives of Computational Methods in Engineering, 29(6), 3973–3980. https:// doi.org/10.1007/s11831-022-09731-2.
[3] Li, B. Y., Bai, Y., & Zhan, X. N., et al. (2023). Technical characteristics and morphological evolution of artificial intelligence-generated content (AIGC). Library and Information Science Knowledge, 40(1), 66–74.
[4] Liu, Z. R., Yin, Y. F., Xue, W. H., et al. (2023). A review of condition-guided image generation based on diffusion models. Journal of Zhejiang University (Science Edition), 50(6), 651–667.
[5] Lu, P., Wu, F., & Tang, J. (2024). Product styling design and evaluation methods for AI-generated content. Journal of Graph Theory, 45(6), 1277–1288.
[6] Yu, S., & Fan, D. Z. (2023). Key characteristics, social risks, and governance approaches of the new generation of artificial intelligence (ChatGPT). Journal of Dalian University of Technology (Social Sciences Edition), 44(5), 28–34.
[7] Liu, T. (2023). On large language models and their applications from the perspective of ChatGPT. Language Strategy Research, 8(5), 14–18.
[8] Yang, L. L. (2023). AI image generation: Ending the art contract. Art Contemporary, 22(3), 54–57.
[9] Zhao, Y. T., & Gao, J. W. (2024). Application of next-generation artificial intelligence technologies in graphic design. Packaging Engineering, 45(4), 226–234.
[10] Zhao, W. H., & Zhao, J. H. (2015). Expression design of automotive front fascia styling. Packaging Engineering, 36(24), 100–104.
[11] Li, J. C., & Li, R. (2021). Research on the design philosophy of national-brand automotive SUVs. Packaging Engineering, 42(8), 175–183.
[12] Lu, Z. L., Song, X. H., & Jin, Y. C. (2023). The current state and development of intelligent design under AIGC technology trends. Packaging Engineering, 44(24), 18–33+13.
[13] Du, Y., Liu, X., Cai, M., & Park, K. (2024). A product’s Kansei appearance design method based on conditional-controlled AI image generation. Sustainability, 16(20), 8837. https://doi. org/10. 3390/su16208837.
[14] Editorials, N. (2023). Tools such as ChatGPT threaten transparent science; here are our ground rules for their use. Nature, 613(7945), 612. https://doi.org/10.1038/d41586-023-00001-5.
[15] Alışık, E. (2022). "All compressed and rendered with a pathetic delicacy that astounds the eye": Midjourney renders ambergris as constantinople. CyberOrient, 16(2), 76–88. https://doi. org/ 10. 34911/CO.2022.16.2.5.
[16] Lu, P., Hsiao, S. W., Tang, J., & Wu, F. (2024). A generative-AI-based design methodology for car frontal forms design. Advanced Engineering Informatics, 62, 102835. https://doi.org /10. 1016/j.aei.2024.102835.
[17] Hsiao, S. W., & Chuang, J. C. (2003). A reverse engineering based approach for product form design. Design Studies, 24(2), 155–171. https://doi.org/10.1016/S0142-694X(02)00041-3.
[18] Feng, Y. Q. (2024). Applications and reflections on AIGC in industrial design. Packaging Engineering, 45(8), 337–345.
[19] Lu, Z. L., Song, X. H., & Jin, Y. C. (2023). The current state and development of intelligent design under AIGC technology trends. Packaging Engineering, 44(24), 18–33+13.
[20] Li, Y. F., Wang, L., Tang, C. Y., et al. (2024). Research on the design of public facilities for smart transportation based on AIGC-assisted technology. Packaging Engineering, 45(6), 479–488.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Highlights in Art and Design
This work is licensed under a Creative Commons Attribution 4.0 International License.
