目的 针对汽车设计前期方案评价指标筛选科学性不足的问题与行业实践需求,构建量化评价体系,验证核心指标的有效性,并对比AI辅助设计流程与传统设计流程各核心指标的差异,为汽车造型设计领域设计流程的智能化变革与完善提供理论依据。方法 基于文献综述法与访谈法,确立涵盖效率效能、设计质量、用户体验及创新伦理方面的10项初始指标。采用层次分析法（AHP）计算各指标的权重并筛选核心指标,通过质量功能展开（QFD）构建质量屋（HOQ）,实现评价指标与技术特性的精准映射,最终通过对比实验验证AI辅助设计流程与传统设计流程在各核心指标中的差异。结果 AHP分析表明,“情感体验满意度”（权重15.71%）、“伦理合规与数据安全”（权重14.96%）与“设计创新度”（权重13.11%）为排名靠前的三个核心指标;实证对比显示,AI辅助设计流程在“单方案生成周期”与“设计创新度”上显著优于传统设计流程,而传统设计流程在“伦理合规与数据安全”维度的评分更高。结论 研究构建的AHP评价模型可为两种流程下的汽车设计前期方案评价提供科学量化方法,验证了AI辅助设计流程在效率性与创新性上的优势。研究结果可为汽车造型设计流程的智能化优化与行业实践落地提供量化依据与针对性参考。
Abstract
Addressing the inadequacy of scientific rigour in selecting evaluation metrics for preliminary automotive design proposals and meeting industry practicer equirements, the work aims to establish a quantitative evaluation system to validate the effectiveness of core indicators and compare differences between AI-assisted design processes and traditional design processes across core indicators, providing a theoretical basis for the intelligent transformation and improvement of design processes in the field of automotive styling design. Based on literature review and interview methods, 10 initial indicators were established, covering efficiency and effectiveness, design quality, user experience, and innovation ethics. The Analytic Hierarchy Process (AHP) was used to calculate the weights of each indicator and screen core indicators. Through Quality Function Deployment (QFD), a House of Quality (HOQ) was constructed to achieve precise mapping between evaluation indicators and technical characteristics. Finally, comparative experiments were conducted to compare the differences between AI-assisted design processes and traditional design processes in terms of core indicators. AHP analysis indicated that "Emotional Experience Satisfaction" (weight 15.71%), "Ethical Compliance and Data Security" (weight 14.96%), and "Design Innovation" (weight 13.11%) were the top three core indicators. Empirical comparisons showed that the AI-assisted design process significantly outperformed the traditional design process in terms of "single-solution generation cycle" and "design innovation" while the traditional design process scored higher in the "Ethical Compliance and Data Security" dimension. The AHP evaluation system constructed in this study provides a scientific quantitative method for evaluating preliminary design schemes under both processes, validating the advantages of AI-assisted design processes in terms of efficiency and innovation. The research results offer quantitative evidence and targeted references for the intelligent optimization of automotive styling design processes and their practical implementation in the industry.
关键词
生成式人工智能（AIGC） /
汽车外饰设计 /
评价体系 /
工作流程 /
AHP-QFD
Key words
AI-generated Content (AIGC) /
automotive exterior design /
evaluation system /
workflow /
AHP-QFD
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 曾绍庭, 黄帅, 王沛贤. 基于AIGC的汽车内饰形态设计研究[J]. 机械设计, 2025, 42(S1): 208-212.
ZENG S T, HUANG S, WANG P X.Research on Automotive Interior Form Design Based on AIGC[J]. Journal of Machine Design, 2025, 42(S1): 208-212.
[2] 于婉莹. 人工智能对艺术创作的变革性影响分析[J]. 南京艺术学院学报(美术与设计版), 2024(1): 190-194.
YU W Y.Analysis of the Transformative Influence of Artificial Intelligence on Artistic Creation[J]. Journal of Nanjing Arts Institute (Fine Arts & Design), 2024(1): 190-194.
[3] 章彰, 徐义辉, 陆潜慧, 等. 人机协同视域下汽车造型智能设计研究[J]. 机械设计, 2025, 42(7): 219-224.
ZHANG Z, XU Y H, LU Q H, et al.Research on Intelligent Design of Automobile Styling from the Perspective of Man-Machine Collaboration[J]. Journal of Machine Design, 2025, 42(7): 219-224.
[4] 路鹏, 吴凡, 唐建, 等. 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, 2025: 1-13.
LU P, WU F, TANG J, SONG M L.Research on Car Front Form Design Method Based on Generative Artificial Intelligence[J]. Packaging Engineering, 2025: 1-13.
[5] 刘鸿恩, 张列平. 质量功能展开(QFD)理论与方法——研究进展综述[J]. 系统工程, 2000, 18(2): 1-6.
LIU H E, ZHANG L P.Quality Function Deployment Theories and Methods—Review on Research Progress[J]. Systems Engineering, 2000, 18(2): 1-6.
[6] 许娜. 人工智能辅助汽车造型设计方法综述[J]. 包装工程, 2021, 42(18): 35-41.
XU N.Review of Artificial Intelligence Aided Vehicle Styling Design Methods[J]. Packaging Engineering, 2021, 42(18): 35-41.
[7] CHEN X Y, MA Z R, JIANG X H, et al.Lumos: AI-Driven Prompt Optimisation Tool for Assisting Conceptual Design[J]. Journal of Engineering Design, 2024, 35(12): 1597-1623.
[8] 赵婧, 尹欢. 体验设计在汽车内饰设计中的发展及展望[J]. 包装工程, 2014, 35(6): 77-81.
ZHAO J, YIN H.Development and Prospect of Experience Design in Automotive Interior Design[J]. Packaging Engineering, 2014, 35(6): 77-81.
[9] 王钰雯. 社会创新设计的设计伦理视角下设计学学科化思辨[J]. 美术研究, 2024(4): 114-117.
WANG Y W.Disciplined Thinking of Design Science from the Perspective of Design Ethics of Social Innovative Design[J]. Art Research, 2024(4): 114-117.
[10] 韩利, 梅强, 陆玉梅, 等. AHP-模糊综合评价方法的分析与研究[J]. 中国安全科学学报, 2004, 14(7): 86-89.
HAN L, MEI Q, LU Y M, et al.Analysis and Study on AHP-Fuzzy Comprehensive Evaluation[J]. China Safety Science Journal, 2004, 14(7): 86-89.
[11] 王利民, 于丹丹, 马莘梓. 数智时代下对设计教育的审视与探讨[J]. 艺术设计研究, 2025(3): 128-134.
WANG L M, YU D D, MA X Z.Examining and Exploring Design Education in the Digital Intelligence Era[J]. Art & Design Research, 2025(3): 128-134.
[12] 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): 18-33.
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): 18-33.
[13] ZENG S T, CAI Y F, ZHANG R S, et al.Research on Human-Machine Collaborative Aesthetic Decision-Making and Evaluation Methods in Automotive Body Design: Based on DCGAN and ANN Models[J]. IEEE Access, 2024, 12: 91575-91589.
[14] 左文, 王南轶, 张宗登. 基于感性工学的明式座椅造型意象设计[J]. 林业工程学报, 2023, 8(3): 190-197.
ZUO W, WANG N Y, ZHANG Z D.Study on the Design of Imagery of Ming-Style Chair Shape Based on Kansei Engineering[J]. Journal of Forestry Engineering, 2023, 8(3): 190-197.
[15] 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.
[16] 万力勇, 杜静, 熊若欣. 人机共创:基于AIGC的数字化教育资源开发新范式[J]. 现代远程教育研究, 2023, 35(5): 12-21.
WAN L Y, DU J, XIONG R X.Human-Machine Co-Creation: A New Paradigm for the Development of Digital Educational Resources Based on AIGC[J]. Modern Distance Education Research, 2023, 35(5): 12-21.
基金
辽宁省教育厅2025年度基本科研项目（LJ112510178002）
PDF(2766 KB)
渝公网安备 50010702501717号