航空学报 > 2026, Vol. 47 Issue (6): 132518-132518   doi: 10.7527/S1000-6893.2025.32518

基于生成对抗网络的通航飞行器气动布局设计方法

余囿铮1,2,3, 寇家庆1,2,3(), 张伟伟1,2,3   

  1. 1.西北工业大学 航空学院,西安 710072
    2.西北工业大学 流体力学智能化国际联合研究所,西安 710072
    3.飞行器基础布局全国重点实验室,西安 710072
  • 收稿日期:2025-07-07 修回日期:2025-07-28 接受日期:2025-10-24 出版日期:2025-11-10 发布日期:2025-11-03
  • 通讯作者: 寇家庆 E-mail:jqkou@nwpu.edu.cn
  • 基金资助:
    国家重点研发计划(2024YFB3310401);飞行器基础布局全国重点实验室开放基金(JBGS-202504);陕西省自然科学基础研究计划资助项目(2025JC-YBQN-087);中央高校基本科研业务费专项资金(G2024KY05101)

A generative adversarial network based method for aerodynamic configuration design of general aviation aircraft

Youzheng YU1,2,3, Jiaqing KOU1,2,3(), Weiwei ZHANG1,2,3   

  1. 1.School of Aeronautics,Northwestern Polytechnical University,Xi’an 710072,China
    2.International Joint Institute of Artificial Intelligence on Fluid Mechanics,Northwestern Polytechnical University,Xi’an 710072,China
    3.National Key Laboratory of Aircraft Configuration Design,Xi’an 710072,China
  • Received:2025-07-07 Revised:2025-07-28 Accepted:2025-10-24 Online:2025-11-10 Published:2025-11-03
  • Contact: Jiaqing KOU E-mail:jqkou@nwpu.edu.cn
  • Supported by:
    National Key Research and Development Program of China(2024YFB3310401);Open Foundation of National Key Laboratory of Aircraft Configuration Design(JBGS-202504);Natural Science Basic Research Program of Shaanxi(2025JC-YBQN-087);Fundamental Research Funds for the Central Universities(G2024KY05101)

摘要:

近年来,生成式人工智能为飞行器布局设计提供了全新解决思路。本研究提出了基于生成对抗网络(GAN)的气动布局概念设计方法,以小型通航飞行器为研究对象,开展了气动布局生成式设计研究。首先,基于标准生成对抗网络及其改进模型,建立了面向飞行器气动布局设计的条件Wasserstein生成对抗网络(CWGAN-GP),能实现给定气动性能下的布局方案快速生成。其次,面向低速巡航状态(马赫数0.2、2° 迎角)的机翼设计,分析了不同生成式模型对参数空间的表征能力和给定条件下的布局生成能力,展示出CWGAN-GP在生成式设计方面的优势。最后,面向常规巡航状态(马赫数0.6、2° 迎角)的通航飞行器气动布局生成式设计,以升力系数和升阻比2种关键气动参数为条件,生成了符合条件的多样性气动布局方案。通过突破条件参数采样范围,提出的方法能生成给定气动参数以外的不同气动外形,具有较强的泛化能力与外推性能。研究成果为下一代飞行器生成式气动设计提供了新方法。

关键词: 生成式模型, 飞行器设计, 气动布局设计, 生成对抗网络, 空气动力学

Abstract:

Mainstream aerodynamic optimization approaches typically commence with the refinement of initial design stages, concentrating on local optimization within predefined configurations, rather than exploring the diversity of aerodynamic layout alternatives during the conceptual design phase. Recently, generative artificial intelligence has offered a novel solution paradigm for aircraft configuration design. This study presents a generative aerodynamic configuration design methodology based on Generative Adversarial Network (GAN), with application to a small general aviation aircraft. First, the GAN and its variants are evaluated for their capability in representing parametric space and generating aerodynamic configurations. Based on this analysis, a Conditional Wasserstein GAN with Gradient Penalty (CWGAN-GP) is established for efficient generation of aerodynamic configurations. Second, for wing design under low-speed cruise conditions (Mach number 0.2, angle of attack of 2°), the representation capability of different generative models in the parameter space and their ability to generate configurations under given conditions are analyzed, demonstrating the advantages of CWGAN-GP in generative design. Finally, for the conceptual aerodynamic configuration design of a general aviation aircraft under typical cruise conditions (Mach number 0.6, angle of attack of 2°), the CWGAN-GP model successfully generates a variety of aerodynamic configurations using the lift coefficient and lift-to-drag ratio as conditional parameters. By extending beyond the training parameter ranges, the proposed method exhibits strong generalization and extrapolation capabilities, capable of producing different aerodynamic shapes outside the original condition space. These results indicate that the generative design methodology presented offers a promising new paradigm for next-generation aircraft aerodynamic configuration exploration and innovation.

Key words: generative models, aircraft design, aerodynamic configuration design, generative adversarial network, aerodynamics

中图分类号: