基于嵌入式神经网络数据预测的多体分离安全评估平台

吴岸平; 林敬周; 王岩; 邹东阳; 解福田

doi:10.7638/kqdlxxb-2024.0076

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 >

基于嵌入式神经网络数据预测的多体分离安全评估平台

研究论文 | 更新时间：2026-05-28

- 基于嵌入式神经网络数据预测的多体分离安全评估平台
- Separation trajectory safety evaluation platform based on embedded neural network data prediction
- 空气动力学学报 2025年43卷第3期页码：42-50
- 作者机构：
  
  1. 中国空气动力研究与发展中心超高速空气动力研究所,绵阳,621000
  2. 飞行器流体物理全国重点实验室,绵阳,621000
  3. 南京航空航天大学航空学院,南京,210016
- 作者简介：
  
  吴岸平（1990—），男，博士，工程师，研究方向：风洞试验技术. E-mail：wuanpingtech@163.com
  林敬周*，研究员，研究方向：多体分离技术. E-mail：Scmy-xxb@163.com
- 基金信息：
  
  国家重点研发计划项目（2020YFA0405700）
- DOI：10.7638/kqdlxxb-2024.0076
  中图分类号： V211.3
- 纸质出版：2025
- 稿件说明：
移动端阅览
吴岸平, 林敬周, 王岩, 等. 基于嵌入式神经网络数据预测的多体分离安全评估平台[J]. 空气动力学学报, 2025, 43(3): 42−50.

WU Anping, LIN Jingzhou, WANG Yan, et al. Separation trajectory safety evaluation platform based on embedded neural network data prediction[J]. 2025, 43(3): 42-50.
吴岸平, 林敬周, 王岩, 等. 基于嵌入式神经网络数据预测的多体分离安全评估平台[J]. 空气动力学学报, 2025, 43(3): 42−50. DOI： 10.7638/kqdlxxb-2024.0076

WU Anping, LIN Jingzhou, WANG Yan, et al. Separation trajectory safety evaluation platform based on embedded neural network data prediction[J]. 2025, 43(3): 42-50. DOI： 10.7638/kqdlxxb-2024.0076.

摘要

针对高速飞行器头罩分离等高动态多体分离问题，开展气动特性智能预测与分离轨迹仿真模拟研究，为分离系统设计、分离窗口选择、分离方案优化与评估提供技术支撑。选取典型状态点进行数值模拟计算和网格测力风洞试验，建立气动数据库。采用融合高、低保真度数据的嵌入式神经网络进行学习训练，并结合遗传算法对神经网络结构进行优化，得到的气动力系数预测结果相较网格测力试验结果误差小于5%。在此基础上，采用四阶龙格-库塔法求解飞行器六自由度运动方程，建立了基于神经网络训练结果的分离轨迹仿真模拟方法。通过在不同初始分离条件下开展蒙特卡罗分析和灵敏度分析，评估了影响分离安全的主要因素。研究结果表明，与风洞CTS模拟轨迹结果相比，平台分离轨迹预测可靠，成本代价较低，可快速提升轨迹模拟能力，为分离方案设计提供有力支撑。

Abstract

Aiming at the high dynamic multi-body separation problem of hypersonic vehicle

intelligent prediction of aerodynamic characteristics and simulations of separation trajectory were carried out

which provided technical support for separation system design

separation window selection

separation scheme optimization and evaluation. Typical states were selected to carry out numerical simulations and grid force measurement in wind tunnel tests

thus an aerodynamic database was established. Embedded neural network with high and low fidelity data was used for the learning and training processes

and the structure of neural network was optimized by the genetic algorithm

leading to the error between the predicted aerodynamic coefficients and those of the grid force measurement less than 5%. The fourth-order Runge-Kutta method was used to solve the six-degree-of-freedom motion equation of aircraft

and the separation trajectory simulation method based on neural network training results was established. The Monte Carlo analysis and sensitivity analysis were carried out under different initial separation conditions to evaluate the main factors affecting separation safety. Compared with the capture trajectory system (CTS) simulation results in wind tunnel

the platform is reliable in separation trajectory prediction

and the cost is low

which can quickly improve the trajectory simulation ability and better support the separation scheme design.

关键词

Keywords

references

LIN J Z, WANG X, ZHONG J, et al . Investigation and application of high Mach number multi-body separation test technique[J ] . Journal of Propulsion Technology, 2020 , 41 ( 4 ): 925 − 933 (in Chinese).

BERNOT P T. Abort separation study of a shuttle orbiter and external tank at hypersonic speeds: NASA-TM-3212. [R] 1975.

ZHANG Y J, SUN Q . Reliability analysis on separation trajectory of integral nose cap[J ] . Journal of Projectiles, Rockets, Missi les and Guidance, 2011 , 31 ( 1 ): 19 − 22 (in Chinese).

ZHANG Y D, JI C Q . The numerical simulation of submution separation processes from dispenser[J ] . Acta Aerodynamica Sinica, 2003 , 21 ( 1 ): 47 − 52 (in Chinese).

TANG Z G, LI B, ZHENG M, et al . Store separation simulation using overset unstructured grid[J ] . Acta Aerodynamica Sinica, 2009 , 27 ( 5 ): 592 − 596 (in Chinese).

LIN J Z, XIE F T, ZHONG J, et al . Dual-body synchronous captive trajectory test technique in hypersonic wind tunnel[J ] . Acta Aerodynamica Sinica, 2023 , 41 ( 5 ): 77 − 86 (in Chinese).

QIAN F X, GUO P, GAO P, et al . Stage separation trajectory simulation test technique in high speed wind tunnel[J ] . Journal of Experiments in Fluid Mechanics, 2021 , 35 ( 5 ): 90 − 98 (in Chinese).

WU A P, FAN X H, GUO L T, et al . Flow quality anslysis and improvement of hypersonic nozzle[J ] . Acta Aerodynamic Sinica, 2024 , 42 ( 5 ): 38 − 44 (in Chinese).

REUBUSH D. Hyper-X stage separation – background and status[C]// 9th International Space Planes and Hypersonic Systems and Technologies Conference, 1999.

REUBUSH D E, MARTIN J G, ROBINSON J S. Hyper-X stage separation – simulation development and results[C] // 10th AIAA/NAL-NASDA-ISAS International Space Planes and Hypersonic Systems and Technologies Conference, Kyoto, Janpan. AIAA, 2001:1802.

TARTABINI P V, BOSE D M, McMINN J D. Hyper-X stage separation trajectory validation studies[C]// AIAA Modeling and Simulation Technologies Conference and Exhibit, Texas, USA. AIAA, 2003:5819.

XIE F T, ZOU D Y, ZHONG J, et al . Multi-body separation trajectory prediction based on grid force measurement data[J ] . Journal of Propulsion Technology, 2022 , 43 ( 8 ): 149 − 159 (in Chinese).

CHEN B, LIU G, XIAO H S, et al . Application of Monte Carlo simulation for th e boundary of separation trajectories of a missile[J ] . Acta Aerodynamica Sinica, 2012 , 30 ( 4 ): 508 − 513,523 (in Chinese).

LYU F K, HE W L. Attitude and trajectory simulation for separated rocket booster[J]. Missiles and Space Vehicles, 2015(1): 13−16 (in Chinese).

TANG Z G, YUAN X X, QIAN W Q, et al. Research progress on the fusion of data obtained by high-speed wind tunnels, CFD and model flight[J]. Acta Aerodynamica, 2023, 41(8): 44−59 (in Chinese).

WANG L, HE G Y, WANG N, et al . Engineering method for computing the aerodynamics performance of hypersonic vehicle[J ] . Journal of Nanchang Hangkong University (Natural Sciences), 2020 , 34 ( 1 ): 1 − 6 (in Chinese).

FADGYAS M C, PRICOP M V, NICULESCU M L, et al. Semi-empirical relations for pressure distributions in hypersonic regime[C]// AIP Conference Proceedings, Thessaloniki, Greece: AIP Publishing, 2018.

WARE G M, CRUZ C I . Aerodynamic characteristics of the HL-20[J ] . Journal of Spacecraft and Rockets, 1993 , 30 ( 5 ): 529 − 536 .

PEHERSTORFER B, WILLCOX K, GUNZBURGER M . Survey of multifidelity methods in uncertainty propagation, inference, and optimization[J ] . SIAM Review, 2018 , 60 ( 3 ): 550 − 591 .

FISCHER C C, GRANDHI R V, BERAN P S . Bayesian-enhanced low-fidelity correction approach to multifidelity aerospace design[J ] . AIAA Journal, 2018 , 56 ( 8 ): 3295 − 3306 .

LI K L, SHI Z W, FU J Q, et al. Comparative analysis of three machine learning methods for unsteady aerodynamic modeling[J]. Flight Dynamics. 2023, 41(3): 33−39 (in Chinese).

ZHANG W W, PENG X H, KOU J Q, et al . Heterogeneous data-driven aerodynamic modeling based on physical feature embedding[J ] . Chinese Journal of Aeronautics, 2024 , 37 ( 3 ): 1 − 6 .

NING C J, ZHANG W W . MHA-Net: Multi-source heterogeneous aerodynamic data fusion neural network embedding reduced-dimension features[J ] . Aerospace Science and Technolog y, 2024 , 145 : 108908 .

WEN X, LI X, ZHANG X W, et al. The application of MATLAB neural network[M]. Beijing: National Defense Industry Press, 2015 (in Chinese).

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

一种用于TSTO级间分离CFD计算的网格动态优化技术

高超声速风洞双体同步分离捕获轨迹试验技术

基于离散优化的飞行试验点优化设计方法

基于熵产理论设计方法的多目标翼型优化

基于复合弯掠技术的轴流风机叶轮优化