基于生成式人工智能的汽车前脸造型设计方法研究

路鹏; 吴凡; 唐建; 宋明亮

doi:10.19554/j.cnki.1001-3563.2026.02.007

PDF(13678 KB)

包装工程（设计栏目） ›› 2026, Vol. 47 ›› Issue (2) : 69-78. DOI: 10.19554/j.cnki.1001-3563.2026.02.007

工业设计

基于生成式人工智能的汽车前脸造型设计方法研究

路鹏¹, 吴凡^2,*, 唐建¹, 宋明亮¹

作者信息 +

Design Methods of Automotive Front-end Forms Based on Generative Artificial Intelligence

LU Peng¹, WU Fan^2,*, TANG Jian¹, SONG Mingliang¹

Author information +

文章历史 +

摘要

目的探究生成式人工智能（Generative Artificial Intelligence, GAI）对传统工业设计流程的革新作用,并提出一种基于GAI的汽车前脸造型设计方法。方法首先,应用GPT-4o归纳分析消费者对汽车前脸造型的感性需求,并提取典型意象需求;其次,利用Midjourney生成符合典型意象需求的汽车前脸造型,以构建造型参考资料库;再次,选取基础造型并设定目标意象,同时结合专家与消费者评价,从资料库中筛选符合目标意象的参考造型;最后,基于基础和参考造型,采用曲线掺合法生成创新的造型曲线,并应用Stable Diffusion将其转化为三维效果的备选方案。结果设计评价结果显示,该方法能够有效生成兼顾汽车品牌特征与消费者感性需求的前脸造型。结论基于GAI的汽车前脸造型设计方法能够提高汽车设计师的效率和创新性,进而启发设计师重新审视传统的工业设计流程。

Abstract

The work aims to explore the transformative impact of Generative Artificial Intelligence (GAI) on traditional industrial design processes and propose a GAI-based method for automotive front-end form design. Firstly, GPT-4o was employed to analyze and summarize consumers' emotional demands for automotive front-end forms and extract typical imagery needs. Next, Midjourney was utilized to generate automotive front-end forms in line with these typical imagery needs, thereby constructing a reference design database. Subsequently, a basic form was selected and a target imagery was assigned, while expert and consumer evaluations were used to filter reference forms from the database that best matched the target imagery. Finally, an innovative form curve was generated through a curve blending method, and Stable Diffusion was applied to transform the design into three-dimensional rendered concepts. Design evaluation results indicated that the proposed method effectively generated the front-end form that balanced brand identity with consumers' emotional demands. The GAI-based design method improves the efficiency and creativity of car designers, inspiring them to reexamine traditional industrial design processes.

导出引用1

路鹏, 吴凡, 唐建, 宋明亮. 基于生成式人工智能的汽车前脸造型设计方法研究[J]. 包装工程. 2026, 47(2): 69-78 https://doi.org/10.19554/j.cnki.1001-3563.2026.02.007

LU Peng, WU Fan, TANG Jian, SONG Mingliang. Design Methods of Automotive Front-end Forms Based on Generative Artificial Intelligence[J]. Packaging Engineering. 2026, 47(2): 69-78 https://doi.org/10.19554/j.cnki.1001-3563.2026.02.007

中图分类号： TB472

参考文献

[1] SMITH R P, MORROW J A.Product Development Process Modeling[J]. Design Studies, 1999, 20(3): 237-261.
[2] 陈林, 李彦, 李文强, 等. 计算机辅助产品创新设计系统开发[J]. 计算机集成制造系统, 2013, 19(2): 319-329.
CHEN L, LI Y, LI W Q, et al.Development of a Computer-Aided Product Innovation and Design System— CAIP[J]. Computer Integrated Manufacturing Systems, 2013, 19(2): 319-329.
[3] SHIVEGOWDA M D, BOONYASOPON P, RANGAPPA S M, et al.A Review on Computer-Aided Design and Manufacturing Processes in Design and Architecture[J]. Archives of Computational Methods in Engineering, 2022, 29(6): 3973-3980.
[4] 李白杨, 白云, 詹希旎, 等. 人工智能生成内容(AIGC)的技术特征与形态演进[J]. 图书情报知识, 2023, 40(1): 66-74.
LI B Y, BAI Y, ZHAN X N, et al.The Technical Features and Aromorphosis of Artificial Intelligence Generated Content(AIGC)[J]. Document, Informaiton & Knowledge, 2023, 40(1): 66-74.
[5] HUNT K M R. Could Artificial Intelligence Win the Next Weather Photographer of the Year Competition?[J]. Weather, 2023, 78(4): 108-112.
[6] WU F, HSIAO S W, LU P.An AIGC-Empowered Methodology to Product Color Matching Design[J]. Displays, 2024, 81: 102623.
[7] 刘泽润, 尹宇飞, 薛文灏, 等. 基于扩散模型的条件引导图像生成综述[J]. 浙江大学学报(理学版), 2023, 50(6): 651-667.
LIU Z R, YIN Y F, XUE W H, et al.A Review of Conditional Image Generation Based on Diffusion Models[J]. Journal of Zhejiang University (Science Edition), 2023, 50(6): 651-667.
[8] 赵文强, 臧欣慈. 皮尔斯符号学视域下AIGC对文创产品的设计探索[J]. 包装工程, 2024, 45(10): 116-126.
ZHAO W Q, ZANG X C.Design of Cultural and Creative Products Based on the Combination of Pierce Semiotics and AIGC[J]. Packaging Engineering, 2024, 45(10): 116-126.
[9] 李源枫, 王丽, 唐彩云, 等. 基于AIGC辅助技术的智慧交通公共设施设计研究[J]. 包装工程, 2024, 45(6): 479-488.
LI Y F, WANG L, TANG C Y, et al.Design of Smart Public Transportation Facilities Aided by AIGC Technology[J]. Packaging Engineering, 2024, 45(6): 479-488.
[10] 路鹏, 吴凡, 唐建. 基于人工智能生成内容的产品造型设计与评价方法[J]. 图学学报, 2024, 45(6): 1277-1288.
LU P, WU F, TANG J.Product Design and Evaluation Methods Based on AI-Generated Content[J]. Journal of Graphics, 2024, 45(6): 1277-1288.
[11] DU Y J, LIU X X, CAI M B, et al.A Product’s Kansei Appearance Design Method Based on Conditional- Controlled AI Image Generation[J]. Sustainability, 2024, 16(20): 8837.
[12] WANG C L, ZHANG J, LIU D S, et al.An AI-Powered Product Identity Form Design Method Based on Shape Grammar and Kansei Engineering: Integrating Midjourney and Grey-AHP-QFD[J]. Applied Sciences, 2024, 14(17): 7444.
[13] 于水, 范德志. 新一代人工智能(ChatGPT)的主要特征、社会风险及其治理路径[J]. 大连理工大学学报(社会科学版), 2023, 44(5): 28-34.
YU S, FAN D Z. The Main Characteristics, Social Risks and Governance Paths of the New Generation of Artificial Intelligence(ChatGPT)[J]. Journal of Dalian University of Technology (Social Sciences), 2023, 44(5): 28-34.
[14] 卢兆麟, 宋新衡, 金昱成. AIGC技术趋势下智能设计的现状与发展[J]. 包装工程, 2023, 44(24): 10-11.
LU Z L, SONG X H, JIN Y C.State of Arts and Development of Intelligent Design Methods under the AIGC Trend[J]. Packaging Engineering, 2023, 44(24): 10-11.
[15] EDITORIALS N.Tools such as ChatGPT Threaten Transparent Science; Here Are Our Ground Rules for Their Use[J]. Nature, 2023, 613(7945): 612.
[16] 李彦宏. 10年后全世界50%的工作会是提示词工程[J]. 中国商人, 2023(11): 68-69.
LI Y H. In 10 Years' Time, 50% of the World’s Work Will Be Prompt Project[J]. Chinese Businessman2023(11): 68-69.
[17] 刘挺. 从ChatGPT谈大语言模型及其应用[J]. 语言战略研究, 2023, 8(5): 14-18.
LIU T.A Look into Large Language Models and Its Applications from the Perspective of ChatGPT[J]. Chinese Journal of Language Policy and Planning, 2023, 8(5): 14-18.
[18] ALıŞıK E. "all Compressed and Rendered with a Pathetic Delicacy that Astounds the Eye": Midjourney Renders Ambergris as Constantinople[J]. CyberOrient, 2022, 16(2): 76-88.
[19] 杨莉莉. AI图像生成: 终结艺术契约[J]. 艺术当代, 2023, 22(3): 54-57.
YANG L L.AI Image Generation: Ending the Art Contract[J]. The Leading Contemporary Art Magazine in China, 2023, 22(3): 54-57.
[20] 冯玉泉. AIGC在工业设计上的应用与思考[J]. 包装工程, 2024, 45(8): 337-345.
FENG Y Q.Application and Thinking of AIGC in Industrial Design[J]. Packaging Engineering, 2024, 45(8): 337-345.
[21] 赵永涛, 高经纬. 新一代人工智能技术在平面设计中的应用[J]. 包装工程, 2024, 45(4): 226-234.
ZHAO Y T, GAO J W.Application of New Generation Artificial Intelligence Technology in Graphic Design[J]. Packaging Engineering, 2024, 45(4): 226-234.
[22] YANG W J, SU J N, ZHANG S T, et al.Research on the Intelligent Design of the Multidimensional Form of a Product under a Brand Cobweb Constraint[J]. International Journal of Arts and Technology, 2020, 12(4): 352.
[23] 赵卫辉, 赵江洪. 汽车前脸造型的表情设计[J]. 包装工程, 2015, 36(24): 100-104.
ZHAO W H, ZHAO J H.Expression Design of Car Front Face Modeling[J]. Packaging Engineering, 2015, 36(24): 100-104.
[24] 李津臣, 李然. 聚焦民族品牌汽车SUV的设计理念研究[J]. 包装工程, 2021, 42(8): 175-183.
LI J C, LI R.Design Ideas Focusing on National Brand Auto SUV[J]. Packaging Engineering, 2021, 42(8): 175-183.
[25] LU P, HSIAO S W, TANG J, et al.A Generative- AI-Based Design Methodology for Car Frontal Forms Design[J]. Advanced Engineering Informatics, 2024, 62: 102835.
[26] HSIAO S W, LEE C H, CHEN R Q, et al.A Methodology for Brand Feature Establishment Based on the Decomposition and Reconstruction of a Feature Curve[J]. Advanced Engineering Informatics, 2018, 38: 14-26.
[27] HSIAO S W, CHUANG J C.A Reverse Engineering Based Approach for Product Form Design[J]. Design Studies, 2003, 24(2): 155-171.