[1]李金晟,常思江,陈升富.基于神经网络算法的弹丸阻力系数辨识[J].弹道学报,2018,(04):38.[doi:10.12115/j.issn.1004-499X(2018)04-007]
 LI Jinsheng,CHANG Sijiang,CHEN Shengfu.Identification of Projectile Drag Coefficient Based onNeural Network Algorithm[J].Journal Of Ballistics,2018,(04):38.[doi:10.12115/j.issn.1004-499X(2018)04-007]
点击复制

基于神经网络算法的弹丸阻力系数辨识()
分享到:

《弹道学报》[ISSN:1004-499x/CN:32-1343/TJ]

卷:
期数:
2018年04期
页码:
38
栏目:
出版日期:
2018-12-31

文章信息/Info

Title:
Identification of Projectile Drag Coefficient Based onNeural Network Algorithm
文章编号:
1004-499X(2018)04-0038-06
作者:
李金晟12常思江2陈升富2
1.北京航天长征飞行器研究所,北京 100076; 2.南京理工大学 能源与动力工程学院,江苏 南京 210094
Author(s):
LI Jinsheng12CHANG Sijiang2CHEN Shengfu2
1.Beijing Institute of Space Long March Vehicle,Beijing 100076,China; 2.School of Energy and Power Engineering,Nanjing University of Science and Technology,Nanjing 210094,China
关键词:
无控炮弹 阻力系数辨识 BP神经网络 极大似然准则
Keywords:
uncontrolled projectile drag coefficient identification BP neural network maximum likelihood criterion
分类号:
TJ012.3
DOI:
10.12115/j.issn.1004-499X(2018)04-007
文献标志码:
A
摘要:
为了解决传统辨识方法在应用于弹丸气动参数辨识时所存在的建模误差问题,基于极大似然准则,采用神经网络-牛顿法,对无控旋转弹丸的飞行状态数据进行处理,提取出其零升阻力系数。仿真结果表明,该算法具有较高的辨识精度和可靠性。基于实测数据,采用该算法和应用已成熟的扩展卡尔曼滤波算法进行辨识。结果表明,神经网络算法的前期辨识精度较高,但中期误差较大,而扩展卡尔曼滤波的前期精度较差,故可结合二者的优点有效地解决工程实际问题。
Abstract:
In order to solve the modeling error of the traditional identification method applied to the identification of the aerodynamic parameters of projectile,the neural network Newton method was used to deal with the flight state data of uncontrolled spinning projectile based on the maximum likelihood criterion,and the zero lift drag coefficient was extracted. Simulation results show that the algorithm has high identification accuracy and reliability. Based on the measured data,this algorithm and the mature extended Kalman filter algorithm were used for identification. The results show that the accuracy of the neural network algorithm is higher in the early stage,but the mid-term error is larger,while the extended Calman filter has poor accuracy in the earlier stage. The engineering problems can be solved effectively by combining the advantages of both.

参考文献/References:

[1] 曾仕伦,李迎九. 关于Chapman-Kirk法的理论研究[J]. 弹道学报,1996,8(1):82-86.
ZENG Shilun,LI Yingjiu. A theoretical study of the Chapman-Kirk method[J]. Journal of Ballistics,1996,8(1):82-86.(in Chinese)
[2]管军,易文俊,刘海,等. 基于遗传-最大似然方法高速旋转弹丸阻力系数辨识[J]. 弹道学报,2016,28(4):1-6.
GUAN Jun,YI Wenjun,LIU Hai,et al. Drag coefficient identification of spinning projectile using GA-MSE[J]. Journal of Ballistics,2016,28(4):1-6.(in Chinese)
[3]史金光,刘猛,曹成壮,等. 弹道修正弹落点预报方法研究[J]. 弹道学报,2014,26(2):29-33.
SHI Jinguang,LIU Meng,CAO Chengzhuang,et al. Research on method of falling point prediction for trajectory correction projectile[J]. Journal of Ballistics,2014,26(2):29-33.(in Chinese)
[4]JATEGAONKAR R V. Flight vehicle system identification:a time-domain methodology[M]. Reston:American Institute of Aeronautics and Astronautics,2006.
[5]ANNASWAMY A M,YU S H. Theta-adaptive neural networks:a new approach to parameter estimation[J]. IEEE Transactions on Neural Networks,1996,7(4):907-918.
[6]SINGH S,GHOSH A K. Parameter estimation from flight data of a missile using maximum likelihood and neural network method[C]//AIAA Atmospheric Flight Mechanics Conference and Exhibit. USA:AIAA,2006:20-24.
[7]PEYADA N K,GHOSH A K. Aircraft parameter estimation using neural network based algorithm[C]//AIAA Atmospheric Flight Mechanics Conference. Chicago:AIAA,2009:1-13.
[8]王小川. MATLAB神经网络43个案例分析[M]. 北京:北京航空航天大学出版社,2013.
WANG Xiaochuan. Analysis of 43 cases of MATLAB neural network[M]. Beijing:Beijing University of Aeronautics and Astronautics Press,2013.(in Chinese)
[9]焦李成. 神经网络系统理论[M]. 西安:西北工业大学出版社,1990.
JIAO Licheng. Neural network system theory[M]. Xi’an:Northwestern Polytechnical University Press,1990.(in Chinese)

备注/Memo

备注/Memo:
收稿日期:2018-06-14基金项目:国家自然科学基金项目(11402117); 中国博士后科学基金项目(2013M541676)作者简介:李金晟(1994- ),男,硕士研究生,研究方向为弹箭飞行制导与控制。E-mail:ljs0906@foxmail.com。
更新日期/Last Update: 2018-12-30