飞行仿真气动力数据机器学习建模方法

王超; 王贵东; 白鹏

doi:10.7638/kqdlxxb-2019.0024

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 >

飞行仿真气动力数据机器学习建模方法

专栏——智能空气动力学研究探索 | 更新时间：2026-05-28

- 飞行仿真气动力数据机器学习建模方法
- Machine learning method for aerodynamic modeling based on flight simulation data
- 空气动力学学报 2019年37卷第3期页码：488-497
- 作者机构：
  
  中国航天空气动力技术研究院,北京,100074
- 作者简介：
  
  王超(1986-), 男, 山东菏泽人, 博士, 工程师, 研究方向:空气动力学与飞行控制.E-mail:caawangchao@163.com
  王贵东(1976-), 男, 河南鹿邑人, 博士, 高级工程师, 研究方向:飞行器气动参数辨识.E-mail:wgdbj@sina.com
- 基金信息：
  
  国家重点研发计划（2018YFA070211）;装备预研基金（61402060202）
- DOI：10.7638/kqdlxxb-2019.0024
  中图分类号： TP181;V211
- 纸质出版：2019
- 稿件说明：
移动端阅览
王超, 王贵东, 白鹏. 飞行仿真气动力数据机器学习建模方法[J]. 空气动力学学报, 2019, 37(3): 488-497.

WANG Chao, WANG Guidong, BAI Peng. Machine learning method for aerodynamic modeling based on flight simulation data[J]. 2019, 37(3): 488-497.
王超, 王贵东, 白鹏. 飞行仿真气动力数据机器学习建模方法[J]. 空气动力学学报, 2019, 37(3): 488-497. DOI： 10.7638/kqdlxxb-2019.0024.

WANG Chao, WANG Guidong, BAI Peng. Machine learning method for aerodynamic modeling based on flight simulation data[J]. 2019, 37(3): 488-497. DOI： 10.7638/kqdlxxb-2019.0024.

摘要

基于机器学习思想，提出了一种大空域、宽速域的气动力建模方法。该方法利用飞行仿真弹道数据辨识的气动力数据，采用人工神经网络技术，实现了对高度、速度、姿态和舵偏角等多维度强非线性特性的全弹道气动力数据的高精度逼近。首先，分析了神经网络层数、隐含层神经元个数等对建模误差的影响，通过对典型弹道气动数据的神经网络建模计算，确定了较合适的神经网络层数和较优的隐层神经元个数。进而，利用飞行仿真的弹道数据辨识出沿弹道的气动力，采用神经网络建立了包含多个弹道融合的气动力模型，输出量分别为三轴气动力系数和力矩系数。最后通过气动模型输出量与原样本数据的对比，以及4条未参与训练弹道气动数据的预测，验证了该气动力建模方法具有较高的精度。建模结果表明：采用神经网络方法建立的飞行器气动力模型，对拟合多源耦合输入全弹道非线性气动力是可行的和有效的，在样本覆盖的高度、速度、姿态和控制舵偏角范围内，气动力拟合能力较强，并具有一定的外推性。该项研究可以为基于飞行试验数据的气动建模提供新的方法，并且能为飞行器气动力数据挖掘、飞行仿真和总体性能分析提供参考。

Abstract

An aerodynamic modeling method based on machine learning theory applying to large airspace and wide speed range is proposed. This method utilizes aerodynamic parameter identification results from flight trajectory simulation data and adopts neural network technology

so the aerodynamic model has a high precision fitting ability for the aerodynamic data with high nonlinear characteristics

regarding variable height

velocity

attitude angle and control rudder angle conditions. Firstly

the effects of the number of neural network and hidden neural unit number on model accuracy are discussed. The proper neural network layer numbers and hidden neural units are obtained through several neural network modeling calculations. Then we use the flight trajectory simulation data to get the whole aerodynamic parameters by identification method. By using BP neural networks

six aerodynamic models including three aerodynamic force coefficients and three aerodynamic moment coefficients are obtained. The models have high precision according to the comparison between model output results and origin data

as well as the aerodynamic prediction of four trajectories which are not applied to the modeling. The results show that the aerodynamic modeling method based on machine learning is feasible and effective. The aerodynamic models have a great fitting ability and some extrapolations in the ranges of data samples including height

Mach number

attack angle

sideslip angle

angular rate

and control surface angle. This study provides a new method on flight test experiment aerodynamic modeling and a good feasibility of the usage in the field of aerodynamic data mining

flight simulation

and aircraft flight evaluation.

关键词

Keywords

references

CAI J S. System identification for flight vehicles[M]. China Astronautic Publishing House, 1995. (in Chinese)

WU C, YAO H, PENG X Z, et al. Application of support vector regression for aerodynamic modeling[J]. Computer Simulation, 2013, 30(10):128-132. (in Chinese)

LIU L J, ZHOU Y, GAO Z X. Aerodynamic force calculation and inverse design for airfoil based on neural network[J]. Physics of Gas, 2018, 3(5):41-47. (in Chinese)

ALI P, PIETER A. Deep learning helicopter dynamic models[C]//IEEE International Conference on Robotics and Automation. Washington, USA: 2015: 3223-3230.

WANG Q, QIAN W Q, DING D. A review of unsteady aerodynamic modeling of aircraft at high angles of attack[J]. Acta Aeronautica et Astronautica Sinica, 2016, 37(8):2331-2347. (in Chinese)

ZHANG R M, ZHANG S Y, ZHAO J B. The research of neural network in modeling of unsready aerodynamics[J]. Computer Simulation, 2017, 34(2):106-110. (in Chinese)

GONG Z, SHEN H L. Structure self-adapting ANN method in modeling of unsteady aerodynamics[J]. Flight Dynamics, 2007, 25(4):13-16. (in Chinese)

SHI Z W, WANG Z H, LI J C. The research of RBFNN in modeling of nonlinear unsteady aerodynamics[J]. Acta Aerodynamica Sinica, 2012, 30(1):108-119. (in Chinese)

FU J Q, SHI Z W, CHEN K, et al. Applications of real-time recurrent neural network based on extended Kalman filter in unsteady aerodynamics modeling[J]. Acta Aerodynamica Sinica, 2018, 36(4):658-663. (in Chinese)

WANG B B, ZHANG W W, YE Z Y. Unsteady nonlinear aerodynamics indentification based on neural network model[J]. Acta Aeronautica et Astronautica Sinica, 2010, 31(7):1379-1388. (in Chinese)

WANG W Z, ZHENG K P, CHEN G, et al. Application research of data-mining method to flight test data analysis and aerodynamic parameter identification[J]. Acta Aerodynamica Sinica, 2016, 34(6):778-782. (in Chinese)

ZHU L, GAO Z H. Aerodynamic optimization design of aerfoi based on neural networks[J]. Aeronautica Computing Technique, 2007, 37(3):33-36. (in Chinese)

CHEN H, QIAN W Q, HE L. Aerodynamic coefficient prediction of airfoils based on deep learning[J]. Acta Aerodynamica Sinica, 2018, 36(2):294-299. (in Chinese)

CHEN G Q, WANG G D, CHEN B Y, et al. Study of flush air data system algorithms for hypersonic vehicle[J]. Aircraft Design, 2015, 35(6):1-7. (in Chinese)

LI F, YANG W B, WANG Q, et al. Status of ground test for hypersonic aerodynamics and its new challenge[J]. Physics of Gases, 2016, 1(2):1-9.

LEVENBERG K. A method for the solution of certain nonlinear problems in least squares[J]. Quarterly of Applied Mathematics, 1944, (2):164-168.

MARQUARDT D. An algorithm for least-squares estimation of nonlinear parameters[J]. SIAM Journal on Applied Mathematics, 1963, 11(2):431-441.

LIU J K. Intelligent control[M]. BeiJing:Publishing House of Electronics Industry, 2009. (in Chinese)

WANG G D. Study on aerodynamic parameter identification for aerospace vehicle[D]. China Academy of Aerospace Aerodynamics, 2010. (in Chinese)

WANG G D, CUI E J, CHEN Z X. Study on aerodynamic parameter identification method for aircraft with jet thruster control[J]. Acta Aerodynamica Sinica, 2011, 29(4):433-438. (in Chinese)

KIRKPATRICK K, Jr MAY J, VALASEKZ J. Aircraft system identification using artificial neural networks[R]. AIAA 2013-0878.

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

基于多支微射流的超声速射流主动控制

无人机气动/风能获取一体化设计

基于稀疏神经核的多保真度代理模型

基于柔性智能蒙皮的翼型流场预测和重建方法

数据驱动的升力体飞行器表面热流快速预测