基于深度学习的飞行器外形快速生成
收稿日期: 2024-12-04
修回日期: 2024-12-23
录用日期: 2025-03-10
网络出版日期: 2025-03-12
Rapid aircraft shape generation based on deep learning
Received date: 2024-12-04
Revised date: 2024-12-23
Accepted date: 2025-03-10
Online published: 2025-03-12
飞行器气动布局设计技术是发展先进飞行器和实现飞行器性能跨代提升的重要研究方向之一。传统飞行器气动布局设计存在气动构型选型困难、过于依赖设计人员经验的问题。同时，当前的气动外形参数化方法难以突破预设定的气动构型方案，在气动布局优化设计过程中仅能对同一气动构型的外形参数进行优化调整，需设计人员反复开展选型迭代与优化，导致飞行器气动布局设计周期长；且难以获取最优气动外形，制约了短平快的高效方案论证。提出并发展了一种基于图像的飞行器外形生成框架，采用深度行进四面体方法和可微分渲染器，利用神经网络强大的非线性拟合能力实现了飞行器气动外形快速智能生成。飞行器生成外形表面光滑且具有高分辨率，尺寸包络可控，具有工程可用性，无需去噪操作。
王永海 , 李昊歌 , 李嘉鑫 , 段毅 , 田川 , 郭灵犀 , 吴旭生 . 基于深度学习的飞行器外形快速生成[J]. 航空学报, 2025 , 46(10) : 631614 -631614 . DOI: 10.7527/S1000-6893.2025.31614
Aerodynamic configuration design technology for aircraft is one of the critical research directions for developing advanced aircraft and achieving generational leaps in performance. Traditional aerodynamic layout design faces challenges such as difficulties in selecting aerodynamic configurations and over-reliance on designer’s experience. Moreover， current aerodynamic shape parameterization methods struggle to break through pre-defined aerodynamic configuration schemes， limiting optimization to adjusting parameters within the same aerodynamic configuration during the design process. This necessitates repeated iterations and optimizations by designers， leading to prolonged design cycles and difficulties in obtaining optimal aerodynamic shapes， thereby hindering efficient and rapid scheme evaluation. This paper proposes and develops an image-based aircraft shape generation framework， employing deep marching tetrahedra methods and differentiable renderers. Leveraging the powerful nonlinear fitting capabilities of neural networks， this framework achieves rapid and intelligent generation of aerodynamic shapes. The generated aircraft surfaces are smooth， high-resolution， and controllable in dimensional envelope， offering engineering usability without the need for denoising operations.
| 1 | KEDWARD L， ALLEN C B， RENDALL T. Regularisation of high fidelity aerodynamic shape optimisation problems using gradient limits［C］?∥AIAA Aviation 2019 Forum. Reston： AIAA， 2019. |
| 2 | MASTERS D A， TAYLOR N J， RENDALL T C S， et al. Geometric comparison of aerofoil shape parameterization methods［J］. AIAA Journal， 2017， 55（5）： 1575-1589. |
| 3 | SOBIECZKY H. Geometry generator for CFD and applied aerodynamics［M］?∥New Design Concepts for High Speed Air Transport. Vienna： Springer Vienna， 1997： 137-157. |
| 4 | KULFAN B， BUSSOLETTI J. “Fundamental” Parameteric geometry representations for aircraft component shapes?［C］?∥11th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference. Reston： AIAA， 2006. |
| 5 | JAMESON A. Aerodynamic design via control theory［J］. Journal of Scientific Computing， 1988， 3（3）： 233-260. |
| 6 | PICKETT R， RUBINSTEIN M， NELSON R. Automated structural synthesis using a reduced number of design coordinates［C］∥14th Structures， Structural Dynamics， and Materials Conference. Reston： AIAA， 1973. |
| 7 | SEDERBERG T W， PARRY S R. Free-form deformation of solid geometric models?［C］?∥Proceedings of the 13th Annual Conference on Computer Graphics and Interactive Techniques. New York： ACM， 1986： 151-160. |
| 8 | BUHMANN M D. Radial basis functions?［M］. New York： Cambridge University Press， 2003. |
| 9 | MORRIS A M， ALLEN C B， RENDALL T C S. CFD-based optimization of aerofoils using radial basis functions for domain element parameterization and mesh deformation［J］. International Journal for Numerical Methods in Fluids， 2008， 58（8）： 827-860. |
| 10 | SAMAREH J. Aerodynamic shape optimization based on free-form deformation?［C］?∥10th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference. Reston： AIAA， 2004. |
| 11 | EYI S N， HANQUIST K M， BOYD I D. Shape optimization of reentry vehicles to minimize heat loading［J］. Journal of Thermophysics and Heat Transfer， 2019， 33（3）： 785-796. |
| 12 | 吴义忠， 曹庆伟. 基于知识的飞行器外形设计系统研究［J］. 计算机工程与应用， 2006， 42（1）： 202-204. |
| WU Y Z， CAO Q W. Research on aerocraft shape design system with knowledge based engineering［J］. Computer Engineering and Applications， 2006， 42（1）： 202-204 （in Chinese）. | |
| 13 | 李润泽， 张宇飞， 陈海昕. 针对超临界翼型气动修型策略的强化学习［J］. 航空学报， 2021， 42（4）： 269-282. |
| LI R Z， ZHANG Y F， CHEN H X. Reinforcement learning method for supercritical airfoil aerodynamic design［J］. Acta Aeronautica et Astronautica Sinica， 2021， 42（4）： 269-282 （in Chinese）. | |
| 14 | KAR A， TULSIANI S， CARREIRA J， et al. Category-specific object reconstruction from a single image［C］∥2015 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Piscataway： IEEE Press， 2015： 1966-1974. |
| 15 | FAN H Q， SU H， GUIBAS L. A point set generation network for 3D object reconstruction from a single image［C］?∥2017 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Piscataway： IEEE Press， 2017： 2463-2471. |
| 16 | WU J J， WANG Y F， XUE T F， et al. MarrNet： 3D shape reconstruction via 2.5D sketches［EB/OL］. （2017-11-08） ［2024-12-04］. . |
| 17 | GADELHA M， MAJI S， WANG R. 3D shape induction from 2D views of multiple objects［C］?∥2017 International Conference on 3D Vision （3DV）. Piscataway： IEEE Press， 2017： 402-411. |
| 18 | HAN X G， GAO C， YU Y Z. DeepSketch2Face［J］. ACM Transactions on Graphics， 2017， 36（4）： 1-12. |
| 19 | WANG N Y， ZHANG Y D， LI Z W， et al. Pixel2Mesh： generating 3D mesh models from single RGB images?［C］?∥Computer Vision-ECCV 2018. Cham： Springer International Publishing， 2018： 55-71. |
| 20 | 张伟伟， 寇家庆， 刘溢浪. 智能赋能流体力学展望［J］. 航空学报， 2021， 42（4）： 524689. |
| ZHANG W W， KOU J Q， LIU Y L. Prospect of artificial intelligence empowered fluid mechanics?［J］. Acta Aeronautica et Astronautica Sinica， 2021， 42（4）： 524689 （in Chinese）. | |
| 21 | 田洁华， 孙迪， 屈峰， 等. 基于CST-GAN的翼型参数化方法［J］. 航空学报， 2023， 44（18）： 128280. |
| TIAN J H， SUN D， QU F， et al. Airfoil parameterization method based on CST-GAN［J］. Acta Aeronautica et Astronautica Sinica， 2023， 44（18）： 128280 （in Chinese）. | |
| 22 | WANG J， LI R Z， HE C， et al. An inverse design method for supercritical airfoil based on conditional generative models?［J］. Chinese Journal of Aeronautics， 2022， 35（3）： 62-74. |
| 23 | LI R Z， ZHANG Y F， CHEN H X. Physically interpretable feature learning of supercritical airfoils based on variational autoencoders?［J］. AIAA Journal， 2022， 60（11）： 6168-6182. |
| 24 | KOU J Q， BOTERO-BOLíVAR L， BALLANO R， et al. Aeroacoustic airfoil shape optimization enhanced by autoencoders?［J］. Expert Systems with Applications， 2023， 217： 119513. |
| 25 | DENG Z W， WANG J， LIU H S， et al. Prediction of transonic flow over supercritical airfoils using geometric-encoding and deep-learning strategies［J］. Physics of Fluids， 2023， 35（7）： 075146. |
| 26 | 赵钟， 何磊， 何先耀. 风雷（PHengLEI）通用CFD软件设计［J］. 计算机工程与科学， 2020， 42（2）： 210-219. |
| ZHAO Z， HE L， HE X Y. Design of general CFD software PHengLEI［J］. Computer Engineering & Science， 2020， 42（2）： 210-219 （in Chinese）. | |
| 27 | 唐志共， 钱炜祺， 何磊， 等. 空气动力学领域大模型研究思考与展望［J］. 空气动力学学报， 2024， 42（12）： 1-11. |
| TANG Z G， QIAN W Q， HE L， et al. Thoughts and prospects on large model research in aerodynamics?［J］. Acta Aerodynamica Sinica， 2024， 42（12）： 1-11. | |
| 28 | 林杰， 唐志共， 钱炜祺， 等. 飞行器生成式气动设计研究进展与展望［J］. 航空学报， 2025， 46（10）： 631679. |
| LIN J， TANG Z G， QIAN W Q， et al. Research progress and prospect of aircraft generative aerodynamic design［J］. Acta Aeronautica et Astronautica Sinica， 2025， 46（10）： 631679 （in Chinese）. | |
| 29 | WANG Z R. 3D representation methods： a survey［DB/OL］. arXiv preprint： 2410. 06475， 2024. |
| 30 | ACHLIOPTAS P， DIAMANTI O， MITLIAGKAS I， et al. Learning representations and generative models for 3D point clouds?［EB/OL］. （2018-06-12）［2024-12-04］. . |
| 31 | MESCHEDER L， OECHSLE M， NIEMEYER M， et al. Occupancy networks： learning 3D reconstruction in function space?［C］?∥2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Piscataway： IEEE， 2019： 4460-4470. |
| 32 | MESCHEDER L， OECHSLE M， NIEMEYER M， et al. Occupancy networks： learning 3D reconstruction in function space?［C］?∥2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Piscataway： IEEE， 2019： 4460-4470. |
| 33 | PAVLLO D， SPINKS G， HOFMANN T， et al. Convolutional generation of textured 3D meshes?［EB/OL］. （2020-10-23） ?［2024-12-04］. ?. |
| 34 | GROUEIX T， FISHER M， KIM V G， et al. A papier-Mache approach to learning 3D surface generation［C］?∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE Press， 2018： 216-224. |
| 35 | WU J J， ZHANG C K， XUE T F， et al. Learning a probabilistic latent space of object shapes via 3D generative-adversarial modeling［EB/OL］. （2017-01-04）（2024-12-04）. . |
| 36 | CHEN Z Q， KIM V G， FISHER M， et al. DECOR-GAN： 3D shape detailization by conditional refinement［C］?∥2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Piscataway： IEEE Press， 2021： 15740-15749. |
| 37 | RIEGLER G， ULUSOY A O， GEIGER A. OctNet： learning deep 3D representations at high resolutions［C］∥2017 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Piscataway： IEEE Press， 2017： 6620-6629. |
| 38 | KARRAS T， AITTALA M， LAINE S， et al. Alias-free generative adversarial networks［C］?∥Proceedings of the 35th International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2021： 852-863. |
| 39 | KARRAS T， LAINE S， AILA T M. A style-based generator architecture for generative adversarial networks［C］?∥2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Piscataway： IEEE Press， 2019： 4396-4405. |
| 40 | KARRAS T， LAINE S， AITTALA M， et al. Analyzing and improving the image quality of StyleGAN［C］?∥2020 Piscataway： IEEE， Press/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Piscataway： IEEE Press， 2020： 8110-8119. |
| 41 | SHEN T C， GAO J， YIN K， et al. Deep marching tetrahedra： a hybrid representation for high-resolution 3D shape synthesis?［C］?∥Proceedings of the 35th International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2021： 6087-6101. |
| 42 | GAO J， CHEN W Z， XIANG T， et al. Learning deformable tetrahedral meshes for 3D reconstruction［C］?∥Proceedings of the 34th International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2020： 9936-9947. |
| 43 | GAO J， WANG Z A， XUAN J C， et al. Beyond fixed grid： learning geometric image representation with a deformable grid?［C］?∥Computer Vision-ECCV 2020. Cham： Springer International Publishing， 2020： 108-125. |
| 44 | DOI A， KOIDE A. An efficient method of triangulating equi-valued surfaces by using tetrahedral cells［J］. IEICE Transactions on Information and Systems， 1991， 74： 214-224. |
| 45 | MUNKBERG J， CHEN W Z， HASSELGREN J， et al. Extracting triangular 3D models， materials， and lighting from images［C］∥2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Piscataway： IEEE Press， 2022： 8270-8280. |
| 46 | LAINE S， HELLSTEN J， KARRAS T， et al. Modular primitives for high-performance differentiable rendering［J］. ACM Transactions on Graphics， 2020， 39（6）： 1-14. |
| 47 | MESCHEDER L， NOWOZIN S， GEIGER A. Which training methods for GANs do actually converge？?［J］. JMLR， 2018， 80： 3481-3490. |
| 48 | POOLE D J， ALLEN C B， RENDALL T. Control point-based aerodynamic shape optimization applied to AIAA ADODG test cases［C］?∥53rd AIAA Aerospace Sciences Meeting. Reston： AIAA， 2015. |
/
| 〈 |
|
〉 |
CJA