基于条件扩散模型的火箭气动外形快速设计方法

李川; 陈建东; 何磊; 程明; 钱炜祺; 蔺佳哲

doi:10.7638/kqdlxxb-2024.0175

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

基于条件扩散模型的火箭气动外形快速设计方法

研究论文 | 更新时间：2026-05-28

- 基于条件扩散模型的火箭气动外形快速设计方法
- Rapid design method of rocket aerodynamic shape based on conditional diffusion model
- 空气动力学学报 2026年44卷第2期页码：22-36
- 作者机构：
  
  1. 四川大学计算机学院,成都,610000
  2. 中国空气动力研究与发展中心计算空气动力研究所,绵阳,621000
  3. 空天飞行空气动力科学与技术全国重点实验室,绵阳,621000
- 作者简介：
  
  李川，副教授，研究方向：强化学习及应用. E-mail：lcharles@scu.edu.cn
  何磊*，副研究员，研究方向：空气动力学. E-mail：helei_email@163.com
- 基金信息：
- DOI：10.7638/kqdlxxb-2024.0175
  中图分类号： V421.1;V221+.3;TP183
- 纸质出版：2026
- 稿件说明：
移动端阅览
李川, 陈建东, 何磊, 等. 基于条件扩散模型的火箭气动外形快速设计方法[J]. 空气动力学学报, 2026, 44(2): 22−36.

Li Chuan, Chen Jiandong, He Lei, et al. Rapid design method of rocket aerodynamic shape based on conditional diffusion model[J]. 2026, 44(2): 22-36.
李川, 陈建东, 何磊, 等. 基于条件扩散模型的火箭气动外形快速设计方法[J]. 空气动力学学报, 2026, 44(2): 22−36. DOI： 10.7638/kqdlxxb-2024.0175

Li Chuan, Chen Jiandong, He Lei, et al. Rapid design method of rocket aerodynamic shape based on conditional diffusion model[J]. 2026, 44(2): 22-36. DOI： 10.7638/kqdlxxb-2024.0175.

摘要

气动设计在火箭设计中扮演着至关重要的角色，为了缩短火箭气动外形设计周期，减少繁琐的迭代优化过程，提出了一种火箭气动外形生成式快速反设计方法。采用图像对火箭气动外形进行几何表征，构建基于条件扩散模型的火箭气动外形生成模型、基于卷积神经网络的火箭气动性能快速预测模型和火箭设计参数判别模型。首先使用气动外形生成模型，以典型工况下轴向力系数

和法向力系数

作为输入，快速生成大量图像化的火箭气动外形方案；然后，再使用气动性能预测模型筛选出满足输入指标的设计方案；最后，通过设计参数判别模型提取优选方案的参数，并对其进行验证，或将其转化为三维外形。本文数据集共包含165 000组气动外形及对应的气动性能。采用典型轴对称布局火箭对气动性能预测模型进行了测试，模型在100个图像化的火箭气动外形预测中耗时约30 s。经验证，优选外形方案轴向力系数

偏差为

0.0827

%，法向力系数

偏差为

0.7124

%，这说明采用本文方法对火箭气动外形进行设计具有可行性，可为相关研究提供新思路。最后本文还分析了交叉注意力机制对模型的影响，发现其并不能对模型精度产生优化效果，此探索研究可为模型后续优化提供参考。

Abstract

Aerodynamic design plays a vital role in rocket design. To expedite the design process of rocket aerodynamic shapes and minimize tedious iterative optimization

this study proposes a generative rapid inverse design metho

d for rocket aerodynamic shapes. This method employs image-based geometric characterization of rocket aerodynamic shapes and integrates three main components: a conditional diffusion model-based rocket aerodynamic shape generation model

a convolutional neural network (CNN)-based rocket aerodynamic performance rapid prediction model

and a rocket design parameter discrimination model. The aerodynamic shape generation model takes the axial force coefficient

and the normal force coefficient

under typical operating conditions as inputs to rapidly generate numerous imaged rocket aerodynamic shape schemes. Subsequently

the performance prediction model screens the designs that meet the specified targets. Finally

the design parameter discrimination model extracts parameters from the selected scheme for validation or converts it into a three-dimensional shape. The dataset used in this study contains

165000

sets of rocket aerodynamic shapes and their corresponding aerodynamic performance. The prediction model was tested on a typical axisymmetric rocket configuration

requiring only about 30 seconds to predict 100 imaged rocket aerodynamic shapes. The optimal design exhibits remarkable accuracy

with deviations of only

0.0827

% and

0.7124

% for the axial and normal force coefficients

respectively. These results demonstrate the feasibility of the proposed method for rocket aerodynamic shape design and offer new insights for related research. Additionally

this paper analyzes the impact of the cross-attention mechanism and finds that it does not optimize model accuracy; this exploratory finding provides a reference for subsequent model optimization.

关键词

Keywords

references

Wang Rong, Zhang Hongjun, Wang Guidong, et al. Multidisciplinary integrated design optimization for an airbreathing air-to-air missile shape[J]. Acta Aeronautica et Astronautica Sinica, 2016, 37(1): 207−215 (in Chinese). doi: 10.7527/S1000-6893.2015.0206

Gao Zhenghong, Wang Chao. Aerodynamic shape design methods for aircraft: status and trends[J]. Acta Aerodynamica Sinica, 2017, 35(4): 516−528,454(in Chinese). doi: 10.7638/kqdlxxb-2017.0058

Xia Lu. Research on integrated optimization design of aerodynamic and stealth of missile shape[D]. Xi'an: Northwestern Polytechnical University, 2001(in Chinese).

王旭刚, 蔡昱, 杜涛. 基于标准遗传算法的巡航导弹造型/气功/隐身一体化设计[C]//大型飞机关键技术高层论坛暨中国航空学会2007年年会, 深圳, 2007.

Zhang Peng, Gu Liangxian, Gong Chunlin. Shape optimization of morphing wing based on the bi-level optimization strategy[J]. Aeronautical Manufacturing Technology, 2010, 53(8): 82−85 (in Chinese). doi: 10.3969/j.issn.1671-833X.2010.08.016

Liu Jimin, Hou Zhiqiang, Song Guibao, et al. Optimization design and aerodynamic characteristic analysis of waverider based hypersonic cruise missile configuration[J]. Acta Aerodynamica Sinica, 2011, 29(1): 118−123(in Chinese). doi: 10.3969/j.issn.0258-1825.2011.01.020

Liu Mengqi. Research on maneuvering characteristics of micro missile and optimal design of steering gear[D]. Xi'an: Xi'an Technological University, 2022(in Chinese).

Zuo Yingtao, Su Wei, Gao Zhenghong, et al. Aerodynamic configuration optimization design of hypersonic missile based on discrete adjoint method[J]. Chinese Journal of Computational Mechanics, 2012, 29(2): 284−289(in Chinese). doi: 10.7511/jslx20122023

Qiu Linya. Aerodynamic shape optimization design of cruise missile based on discrete conjugate method[D]. Changsha: National University of Defense Technology, 2016(in Chinese).

Song Chao, Liu Hongyang, Zhou Zhu, et al. Inverse design of aerodynamic configuration using generative topographic mapping[J]. Journal of Northwestern Polytechnical University, 2022, 40(4): 837−844 (in Chinese). doi: 10.1051/jnwpu/20224040837

Li Chunna, Jia Xuyi, Gong Chunlin. Airfoil inverse design method based on two-layer POD and BPNN[J]. Advances in Aeronautical Science and Engineering, 2021, 12(2): 30−37(in Chinese). doi: 10.16615/j.cnki.1674-8190.2021.02.04

Tyan M, Choi C K, Nguyen T A, et al. Rapid airfoil inverse design method with a deep neural network and hyperparameter selection[J]. International Journal of Aeronautical and Space Sciences, 2023, 24(1): 33−46. doi: 10.1007/s42405-022-00507-x

Su J, Sun G, Tao J. A novel inverse design method for morphing airfoil based on deep reinforcement learning[J]. Aerospace Science and Technology, 2024, 145: 108895. doi: 10.1016/j.ast.2024.108895

He Lei, Qian Weiqi, Liu Tao, et al. Inverse design method of airfoil based on deep learning[J]. Journal of Aerospace Power, 2020, 35(9): 1909−1917(in Chinese). doi: 10.13224/j.cnki.jasp.2020.09.013

Yan Ruopeng, Huang Diangui. Method of aerodynamic inverse design for airfoils based on the deeply reduced-order model[J]. Journal of Engineering for Thermal Energy and Power, 2021, 36(1): 17−23(in Chinese). doi: 10.16146/j.cnki.rndlgc.2021.01.003

Wang Chaojie, He Lei, Li Chuan, et al. Airfoil reverse design method based on self-attention mechanism[J]. Journal of Aerospace Power, 2025, 40(1): 292−299(in Chinese). doi: 10.13224/j.cnki.jasp.20230106

Yilmaz E, German B. Conditional generative adversarial network framework for airfoil inverse design[C]// AIAA AVIATION 2020 FORUM, VIRTUAL EVENT. Reston, Virginia: AIAA, 2020: 3185. doi: 10.2514/6.2020-3185

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. doi: 10.1016/j.cja.2021.03.006

Wu Mingyu, Chen Zhihua, Qiu Zhiming, et al. An inverse design method of airfoil using conditional generative adversarial network[J]. Journal of Astronautics, 2023, 44(10): 1512−1521(in Chinese). doi: 10.3873/j.issn.1000-1328.2023.10.004

Yonekura K, Tomori Y, Suzuki K. Airfoil shape generation and feature extraction using the conditional VAE-WGAN-gp[J]. Ai, 2024, 5(4): 2092−2103. doi: 10.3390/ai5040102

Ho J, Jain A N, Abbeel P. Denoising diffusion probabilistic models[C]// Advances in neural information processing systems, 2020, 33.

Nichol A, Dhariwal P, Ramesh A, et al. GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models[C]// 39th International Conference on Machine Learning, Baltimore: PMLR, 2022.

Kawar B, Zada S, Lang O, et al. Imagic: Text-based real image editing with diffusion models[C]// 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada. IEEE, 2023: 6007-6017. doi: 10.1109/CVPR52729.2023.00582

Huang Wanxin X, Ren Yingjie, Lu Tianliang, el al. Multimodal face generation method for diffusion large models[J]. Journal of Frontiers of Computer Science and Technology, 2025, 19(10): 2815−2828(in Chinese). doi: 10.3778/j.issn.1673-9418.240906

Lou Jinhua, Chen Rongqian, Liu Jiaqi, et al. Research on aircraft aerodynamic performance prediction and inverse design based on a gated diffusion model[J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(10): 631183(in Chinese). doi: 10.7527/S1000-6893.2024.31183

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

机器学习方法在气动特性建模中的应用

基于U-Net的磁浮飞行风洞气动力干扰剥离算法

定常来流下钝体二维组合断面气动特性与流场的智能预测方法

基于物理约束深度学习的大跨柔性光伏阵列绕流场重构

基于机器学习的极端风场短时预测研究进展与思考