西安交通大学电子与信息工程学院,西安,710049
网络首发:2016-07-10,
纸质出版:2016
移动端阅览
魏倩, 蔡远利. 一种基于神经网络的中制导改进算法[J]. 西安交通大学学报, 2016,50(7):125-130.
A Modified Algorithm on the Midcourse Guidance Based on BP Neural Network[J]. 2016, 50(7): 125-130.
魏倩, 蔡远利. 一种基于神经网络的中制导改进算法[J]. 西安交通大学学报, 2016,50(7):125-130. DOI: 10.7652/xjtuxb201607019.
A Modified Algorithm on the Midcourse Guidance Based on BP Neural Network[J]. 2016, 50(7): 125-130. DOI: 10.7652/xjtuxb201607019.
针对地球扁率影响下的大气层外导弹中段制导问题
提出了基于BP神经网络的模型预测改进算法
并且创新使用轨道偏差解析解来构造训练样本集。首先
利用极点变换方法把弹体受到的J
2
项摄动引力优化分解为与运动轨迹相关的扰动函数; 然后
采用偏差状态空间的转移矩阵
建立起导弹在J
2
项摄动作用下的轨道偏差公式; 最后
利用偏差公式构造取值广泛的训练样本集并训练BP神经网络
从而建立起关于虚拟目标信息的预测模型
计算出中段制导控制所需的增益速度矢量。该模型的优点是利用极点变换和状态转移矩阵直接求解J
2
项摄动偏差
避免了进行大规模的数值积分运算; 神经网络拥有强大的学习能力
保证了预测模型的全面性及精确性; BP神经网络可以预先离线训练、学习
大大缩短了计算时间。与传统Lambert迭代补偿修正方法相比
改进型BP神经网络补偿算法可以同时满足实时计算速度及计算精度的双重要求
具有较强的实际工程意义。
Aiming at solving the midcourse guidance problem of exo-atmosphere missile under the influence of earth's oblateness perturbation
a prediction model for missile guidance was proposed based on BP neural network. This method provides a new training sample set constructed by the analytical formula of trajectory deviation. First
by using the pole transform method
the missile's J
2
perturbed gravity is decomposed into the disturbing function related to its flight trajectory. Then
with the state space matrix method
the analytic solution of trajectory deviation with the J
2
perturbation is calculated. Finally
using trajectory deviation function to construct a wide range of traini
ng sample set
the BP neural network of prediction model is established. The neural network can forecast the virtual target point information
so as to calculate the vector of gained velocity for midcourse guidance control. Using the modified algorithm
the trajectory deviation of J
2
perturbation can be directly solved by pole transform and state transition matrix
avoiding large-scale numerical calculation. The BP neural network has powerful learning and training ability
ensuring the comprehensiveness and accuracy of the prediction model and saving calculation time by the off-line training and learning before the simulation tests. In comparison with traditional correction method of Lambert guidance
this modified algorithm can satisfy the requirements on both efficiency and accuracy of real-time computation
being of practical engineering significance.
BATTIN R H. Introduction to the mathematics and methods of astrodynamics [M]. Reston, VA, USA: AIAA, 1999: 325-417.
AHN J, lEE S. Lambert algorithm using analytic gradients [J]. Journal of Guidance, Control, and Dynamics, 2013, 36(6): 1751-1761.
AHN J, BANG J, LEE S. Acceleration of zero-revolution Lambert's algorithms using table-based initialization [J]. Journal of Guidance, Control, and Dynamics, 2015, 38(2): 335-342.
ZHANG Gang, CAO Xibin, ZHOU Di. Two-impulse cotangent rendezvous between coplanar elliptic and hyperbolic orbits [J]. Journal of Guidance, Control, and Dynamics, 2014, 37(3): 965-969.
WAILLIEZ S E. On Lambert's problem and the elliptic time of flight equation: a simple semi-analytical inversion method [J]. Advances in Space Research, 2014, 53(5): 890-898.
高海燕, 蔡远利. 高超声速飞行器的滑模预测控制方法 [J]. 西安交通大学学报, 2014, 48(1): 67-72.
GAO Haiyan, CAI Yuanli. Sliding mode predictive control for hypersonic vehicle [J]. Journal of Xi'an Jiaotong University, 2014, 48(1): 67-72.
徐明, 谭田, 李志武, 等. Lambert转移中途修正的全局概率最优策略 [J]. 北京航空航天大学学报, 2012, 38(5): 574-578.
XU Ming, TAN Tian, LI Zhiwu, et al. Optimal correction strategy during Lambert transfer from view of probability [J]. Journal of Beijing University of Aeronautics and Astronautics, 2012, 38(5): 574-578.
胡正东, 郭才发, 曹渊, 等. 轨道轰炸飞行器过渡段轨道设计与制导 [J]. 固体火箭技术, 2009, 32(5): 473-479.
HU Zhengdong, GUO Caifa, CAO Yuan, et al. Transition trajectory planning and guidance for orbital bombing vehicle [J]. Journal of Solid Rocket Technology, 2009, 32(5): 473-479.
柴华, 仲明, 梁彦刚. 采用状态转移矩阵的拦截中段制导方法 [J]. 国防科技大学学报, 2015, 37(4): 137-142.
CHAI Hua, ZHONG Ming, LIANG Yangang. Midcourse guidance of interception using state transition matrix [J]. Journal of National University of Defense Technology, 2015, 37(4): 137-142.
郑伟, 汤国建. 扰动引力场中弹道导弹飞行力学 [M]. 北京: 国防工业出版社, 2009: 32-45.
YAMADA K, KIMURA M. New state transition matrix for formation flying in J2-perturbed elliptic orbits [J]. Journal of Guidance, Control, and Dynamics, 2012, 35(2): 536-547.
邓一兵, 胡伟, 高峰, 等. 遗传神经网络在载人飞船环控决策系统中的应用研究 [J]. 西安交通大学学报, 2010, 44(7): 64-69.
DENG Yibing, HU Wei, GAO Feng, et al. Application of genetic neural network to decision support system for environmental control and life support system [J]. Journal of Xi'an Jiaotong University, 2010, 44(7): 64-69.
张小栋,郭晋,李睿,等.表情驱动下脑电信号的建模仿真及分类识别.2016,50(6):1-8.[doi:10.7652/xjtuxb201606001]
姜涛,黄伟,王安麟.多路阀阀芯节流槽拓扑结构组合的神经网络模型.2016,50(6):36-41.[doi:10.7652/xjtuxb201606 006]
宋青松,田正鑫,孙文磊,等.用于孤立数字语音识别的一种组合降维方法.2016,50(6):42-46.[doi:10.7652/xjtuxb2016 06007]
陈江城,张小栋.人体下肢行走关节连续运动表面肌电解码方法.2016,50(6):61-67.[doi:10.7652/xjtuxb201606010]
陈斌,胡平舸,屈丹.子空间域相关特征变换与融合的语音识别方法.2016,50(4):60-67.[doi:10.7652/xjtuxb201604010]
王安麟,孟庆华,曹岩,等.液力变矩器的叶片数神经网络模型.2015,49(7):11-16.[doi:10.7652/xjtuxb201507003]
马忠丽,文杰,梁秀梅,等.无人艇视觉系统多类水面目标特征提取与识别.2014,48(8):60-66.[doi:10.7652/xjtuxb2014 08011]
侯雨伸,王秀丽.气象过程信息挖掘与输电线路覆冰预测.2014,48(6):43-49.[doi:10.7652/xjtuxb201406008]
王万召,王杰.采用限定记忆极限学习机的过热汽温逆建模研究.2014,48(2):32-37.[doi:10.7652/xjtuxb201402006]
冯斌,梅雪松,杨军,等.数控机床摩擦误差自适应补偿方法研究.2013,47(11):65-69.[doi:10.7652/xjtuxb201311012]
0
浏览量
4
下载量
3
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621