基于自编码网络的导弹攻击区实时计算方法

doi:10.7527/S1000-6893.2019.23571

电子电气工程与控制

本期目录 | 过刊浏览 | 高级检索

前一篇 | 后一篇

基于自编码网络的导弹攻击区实时计算方法

胡东愿, 杨任农, 闫孟达, 岳龙飞, 左家亮, 王瑛

空军工程大学空管领航学院, 西安 710051

收稿日期:2019-10-14 修回日期:2020-01-03 出版日期:2020-04-15 发布日期:2019-12-26
通讯作者: 左家亮 E-mail:jialnzuo@163.com

Real-time calculation of missile launch envelope based on auto-encoder network

HU Dongyuan, YANG Rennong, YAN Mengda, YUE Longfei, ZUO Jialiang, WANG Ying

Air Traffic Control and Navigation College, Air Force Engineering University, Xi'an 710051, China

Received:2019-10-14 Revised:2020-01-03 Online:2020-04-15 Published:2019-12-26

摘要/Abstract

摘要： 针对传统中远距空空导弹三线攻击区无法为飞行员提供丰富的战术决策信息，火控系统计算攻击区实时性差、精度低的问题，提出以攻击机为中心，考虑目标逃逸机动的新型导弹杀伤包线概念。分析经典战例中目标机规避导弹的常见机动方式，将攻击区抽象为导弹的七种杀伤包线，给出准确的计算方法并进行离线仿真。确定8种影响杀伤包线的运动参数，构建样本库。引入深度学习方法，建立降噪自编码网络（AE）模型，采用无监督学习提取样本初级特征，获取表征样本库非线性规律的高维特征量；建立深度网络模型，采用监督学习提取高维特征量中的高级特征并进行拟合。实验表明深度网络的拟合值与六自由度仿真结果以及导弹真实数据相比，误差可控制在15 m之内；网络在线解算只需0.04 s，能够满足实时性需求；新型杀伤包线为飞行员及时掌握敌我态势提供了有效的辅助信息，为机动决策提供理论依据。

关键词: 空空导弹, 攻击区, 杀伤包线, 深度学习, 自编码网络, 实时性

Abstract: Traditional three-line attack area of medium-range air-to-air missile can’t provide effective tactical decision information for the pilot, and it has poor time effectiveness and low precision in calculation using fire control system. To address these problems, a new type of missile launch envelope, under the consideration of the target escape maneuver, is proposed with the attack aircraft as the center. In this paper, common and effective tactical maneuvers, which are used to escape from missiles successfully, are considered and analyzed through many classic examples of battles. The attack area is abstracted into seven killing envelops. the calculated methods are given and the offline simulations are carried out. The sample database is established by identifying eight motion parameters and envelop-values. By introducing deep learning methods, the Auto-Encoder (AE) network model is constructed. By adopting unsupervised learning, the primary features of the sample are extracted, and the high dimensional vectors describing nonlinearity in the sample database are obtained. The deep network model is established with high dimensional vectors to extract advanced features for fitting. Experimental results show that the loss of the deep network can be controlled within 15 m compared with the six-degree-of-freedom simulation results and the actual missile data. The online calculation time is only 0.04 s, which can meet the real-time requirements. The new missile envelope can provide timely and effective information for pilot to understand enemy situation and support maneuvering decision-making.

Key words: air to air missile, attack area, killing envelop, deep learning, auto-encoder network, real time

中图分类号:

V211.1

胡东愿, 杨任农, 闫孟达, 岳龙飞, 左家亮, 王瑛. 基于自编码网络的导弹攻击区实时计算方法[J]. 航空学报, 2020, 41(4): 323571-323571.

HU Dongyuan, YANG Rennong, YAN Mengda, YUE Longfei, ZUO Jialiang, WANG Ying. Real-time calculation of missile launch envelope based on auto-encoder network[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2020, 41(4): 323571-323571.

参考文献 33

[1]	黄睿,刘小方,郑祥.某型导弹性能质量评估系统设计与实现[J].火炮发射与控制学报, 2019, 40(2):88-92. HUANG R, LIU X F, ZHENG X. Design and implementation of a missile performance quality evaluation system[J]. Journal of Gun Launch&Control, 2019, 40(2):88-92(in Chinese).
[2]	史振庆,梁晓龙,张佳强,等.基于导弹攻击区的空战态势评估[J].火力与指挥控制, 2018, 43(9):89-93. SHI Z Q, LIANG X L, ZHANG J Q, et al. Situation assessment for air combat based on missile attack zone[J]. Fire Control&Command Control, 2018, 43(9):89-93(in Chinese).
[3]	付昭旺,于雷,李战武,等.战斗机隐蔽接敌轨迹优化方法[J].国防科技大学学报, 2013, 35(5):52-58. FU Z W, YU L, LI Z W, et al. The trajectory optimization method for fighter stealthy approach[J]. Journal of National University of Defense Technology, 2013, 35(5):52-58(in Chinese).
[4]	董海霞,邹杰,王永庭.基于协同攻击区模型的多机最优攻击占位决策[J].火力与指挥控制, 2018, 43(12):11-15. DONG H X, ZOU J, WANG Y T. Collaborative attack area model for multi-aircrafts of optimal attack occupancy decision[J]. Fire Control&Command Control, 2018, 43(12):11-15(in Chinese).
[5]	WANG H, LEI H, YE J, et al. A novel capture region of retro proportional navigation guidance law for intercepting high-speed nonmaneuvering targets[J]. Proceedings of the Institution of Mechanical Engineers, Part G:Journal of Aerospace Engineering, 2018, 232(6):86-98.
[6]	方学毅,刘俊贤,周德云.基于背景插值的空空导弹攻击区在线模拟方法[J].系统工程与电子技术, 2019, 41(6):1286-1293. FANG X Y, LIU J X, ZHOU D Y. Back ground interpolation for on-line simulation of capture zone of air-to-air missiles[J]. Systems Engineering and Electronics, 2019, 41(6):1286-1293(in Chinese).
[7]	周须峰,易华,谢永强.近距格斗空空导弹三自由度弹道仿真建模[J].四川兵工学报, 2014, 35(2):9-12. ZHOU X F, YI H, XIE Y Q. Modeling on 3DOF trajectory simulation of short range dogfight air-to-air missile[J]. Journal of Sichuan Ordnance, 2014, 35(2):9-12(in Chinese).
[8]	黄威,任洋.基于自适应步长的空空导弹攻击区解算方法[J].电光与控制, 2019, 26(5):55-58. HUANG W, REN Y. Adaptive step-size based calculation of air-to-air missile launch envelopes[J]. Electronics Optics&Control, 2019, 26(5):55-58(in Chinese).
[9]	高胜灵,胡松启.基于Matlab/Simulink的导弹六自由度弹道仿真系统设计[J].科学技术与工程, 2011, 11(1):29-34. GAO S L, HU S Q. Six-degree-of-freedom simulation modelling for missile trajectory based on Matlab/Simulink[J]. Science Technology and Engineering, 2011, 11(1):29-34(in Chinese).
[10]	程翔,李苑青,王丽华.基于OpenGL的六自由度三维弹道仿真技术研究[J].电子科技, 2017, 30(6):16-20. CHENG X, LI Y Q, WANG L H. Research on six degree of freedom 3d trajectory simulation based on opengl[J]. Electronic Science and Technology, 2017, 30(6):16-20(in Chinese).
[11]	俞吉,周德云,周灿辉.基于云模型空空导弹攻击区的拟合方法[J].火力与指挥控制, 2013, 38(7):32-35. YU J, ZHOU D Y, ZHOU C H. A method for approximating allowable attack area for air-to-air missile based on cloud model[J]. Fire Control&Command Control, 2013, 38(7):32-35(in Chinese).
[12]	邓健,王星,曾艳丽,等.基于数据建模的空空导弹攻击区仿真[J].弹箭与制导学报, 2016, 36(4):33-35. DENG J, WANG X, ZENG Y L, et al. Simulation of attack area for air-to-air missile based on data modeling[J]. Journal of Projectiles, Rockets, Missiles and Guidance, 2016, 36(4):33-35(in Chinese).
[13]	张列航,雷蕾,杨长启.中程空空导弹攻击区仿真与拟合[J].航空科学技术, 2010(4):25-27. ZHANG L H, LEI L, YANG C Q. Attack area calculating and data fitting for medium air-to-air missile[J]. Aeronautical Science&Technology, 2010(4):25-27(in Chinese).
[14]	史振庆,梁晓龙,张佳强,等.基于GWO-BP神经网络的攻击区解算方法[J].飞行力学, 2019, 37(3):64-67,92. SHI Z Q, LIANG X L, ZHANG J Q, et al. Solution of attack zone based on GWO-BP neural network[J]. Flight Dynamics, 2019, 37(3):64-67,92(in Chinese).
[15]	孟博.基于BP神经网络的空空导弹攻击大机动目标攻击区仿真研究[J].弹箭与制导学报, 2017, 37(4):43-46,50. MENG B. Research on launch envelopes simulation of air-to-air missile attacking high maneuvering targets based on bp neural network[J]. Journal of Projectiles, Rockets, Missiles and Guidance, 2017, 37(4):43-46,50(in Chinese).
[16]	苗涛,杨毅,南英.导弹动态可攻击区实时在线算法研究[J].飞行力学, 2018, 36(2):39-43. MIAO T, YANG Y, NAN Y. Research on real-time online algorithm of missile dynamic attack zone[J]. Flight Dynamics, 2018, 36(2):39-43(in Chinese).
[17]	王志刚,张宁,李伟.一种空空导弹攻击区的快速解算方法[J].固体火箭技术, 2014, 37(4):448-452. WANG Z G, ZHANG N, LI W. A fast solving method for attacking area of air-to-air missile[J]. Journal of Solid Rocket Technology, 2014, 37(4):448-452(in Chinese).
[18]	李枭扬,周德云,冯琦,等.基于遗传规划的空空导弹攻击区拟合[J].弹箭与制导学报, 2015, 35(3):16-18,22. LI X Y, ZHOU D Y, FENG Q, et al. Air-to-air missile launch envelops fitting based on genetic programming[J]. Journal of Projectiles,Rockets,Missiles and Guidance, 2015, 35(3):16-18,22(in Chinese).
[19]	徐国训,梁晓龙,张佳强,等.双机空空导弹协同攻击区仿真研究[J].火力与指挥控制, 2019, 44(1):34-39. XU G X, LIANG X L, ZHANG J Q. Simulation research on air-to-air missile cooperating weapon engagement zone of two aircrafts[J]. Fire Control&Command Control, 2019, 44(1):34-39(in Chinese).
[20]	高劲松,赵华超,田省民.空空导弹的两种全向攻击方式的关系[J].电光与控制, 2018, 25(12):16-20. GAO J S, ZHAO H C, TIAN X M. On relationship between two modes of aam's all-aspect attack[J]. Electronics Optics&Control, 2018, 25(12):16-20(in Chinese).
[21]	左家亮,杨任农,张滢,等.分布式半实物环境实时弹道仿真步长自适应研究[J].兵工学报, 2015, 36(4):653-659. ZUO J L, YANG R N, ZHANG Y, et al. Research on the step size of real-time self-adaptation trajector[J]. Acta Armamentar, 2015, 36(4):653-659(in Chinese).
[22]	张彬超,寇雅楠,邬蒙,等.基于深度置信网络的近距空战态势评估[J].北京航空航天大学学报, 2017, 43(7):1450-1459. ZHANG B C, KOU Y N, WU M, et al. Close-range air combat situation assessment using deep belief network[J]. Journal of Beijing University of Aeronautics and Astronautics, 2017, 43(7):1450-1459(in Chinese).
[23]	焦珂,皮亦鸣,陆继珍.空空导弹发射包线的快速计算方法[J].火力与指挥控制, 2010, 35(6):100-102,106. JIAO K, PI Y M, LU J Z. A fast calculation method of launch envelope of air-to-air missile[J]. Fire Control&Command Control, 2010, 35(6):100-102,106(in Chinese).
[24]	刘瑛,李敏强,张瑞峰.复杂机动动作最优航迹控制模型及操纵特性分析[J].控制理论与应用, 2014, 31(5):566-576. LIU Y, LI M Q, ZHANG R F. The optimal trajectory control model of the aircraft maneuver and its operation characteristics[J]. Control Theory&Applications, 2014, 31(5):566-576(in Chinese).
[25]	HUI Y, NAN Y, CHEN S, et al. Dynamic attack zone of air-to-air missile after being launched in random wind field[J]. Chinese Journal of Aeronautics, 2015, 28(5):1519-1528.
[26]	FANG J, ZHANG L, WEI F, et al. Approximate dynamic programming for CGF air combat maneuvering decision[C]//Proceedings of the 20162nd IEEE International Conference on Computer and Communications (ICCC). Piscataway, NJ:IEEE Press, 2016.
[27]	贾镇泽,樊晓光,薛明浩,等.基于机动动作元的敌机战术机动在线识别方法[J].北京理工大学学报, 2018, 38(8):820-827. JIA Z Z, FAN X G, XUE M H, et al. Online identification method for tactical maneuver of target based on air combat maneuver element[J]. Transactions of Beijing Institute of Technology, 2018, 38(8):820-827(in Chinese).
[28]	FANG J, ZHANG L, WEI F, et al. Approximate dynamic programming for CGF air combat maneuvering decision[C]//IEEE International Conference on Computer&Communications. Piscataway, NJ:IEEE Press, 2017.
[29]	杨新,王小虎,申功璋,等.飞机六自由度模型及仿真研究[J].系统仿真学报, 2000(3):36-39. YANG X, WANG X H, SHEN G Z, et al. Modeling and simulation research of six-degree-of-freedom fighter[J]. Journal of System Simulation,2000(3):36-39(in Chinese).
[30]	方振平.航空飞行器飞行动力学[M].北京:北京航空航天大学出版社,2005. FANG Z P. Aviation vehicle flight dynamics[M]. Beijing:Beihang Universtity Press,2005(in Chinese).
[31]	董肖杰,余敏建,宋帅.空战机动动作库及控制算法设计研究[C]//第五届中国指挥控制大会, 2017. DONG X J, YU M J, SONG S. Research on the design of air combat maneuver library and control arithmetic of movements[C]//Proceedings of the 5th China Command and Control Conference,2017(in Chinese).
[32]	林德福,王辉,王江,等.战术导弹自动驾驶仪设计与制导律分析[M].北京:北京理工大学出版社,2012. LIN D F, WANG H, WANG J, et al. Autopilot design and guidance law analysis for tactical missile[M]. Beijing:Beijing Institute of Technology Press, 2012(in Chinese).
[33]	潘广源,柴伟,乔俊飞. DBN网络的深度确定方法[J].控制与决策, 2015, 30(2):256-260. PAN G Y, CHAI W, QIAO J F. Calculation for depth of deep belief network[J]. Control and Decision, 2015, 30(2):256-260(in Chinese).

E-mail：hkxb@buaa.edu.cn

关于我们

期刊社服务

专业学科

封面文章

友情链接

主管单位：中国科学技术协会主办单位：中国航空学会北京航空航天大学

基于自编码网络的导弹攻击区实时计算方法

Real-time calculation of missile launch envelope based on auto-encoder network

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献 33

相关文章 15

编辑推荐

Metrics

本文评价

[1]	柳家齐, 陈荣钱, 楼锦华, 韩旭, 吴昊, 尤延铖. 基于深度学习的高速直升机旋翼翼型气动优化设计[J]. 航空学报, 2024, 45(9): 529828-529828.
[2]	罗旭东, 吴一全, 陈金林. 无人机航拍影像目标检测与语义分割的深度学习方法研究进展[J]. 航空学报, 2024, 45(6): 28822-028822.
[3]	刘海桥, 刘萌, 龚子超, 董晶. 基于深度学习的图像匹配方法综述[J]. 航空学报, 2024, 45(3): 28796-028796.
[4]	苏鑫, 管润程, 王桥, 苑伟政, 吕湘连, 何洋. 基于深度学习的结冰区域和厚度检测方法[J]. 航空学报, 2023, 44(S2): 729283-729283.
[5]	陈立群, 邹旭, 张磊, 朱颖盼, 王港, 陈金勇. 基于国产商用器件的星载智能目标检测技术[J]. 航空学报, 2023, 44(S2): 728860-728860.
[6]	刘鹏宇, 朱雪耀. 基于深度学习的融合空域空管指令语义解析技术[J]. 航空学报, 2023, 44(S1): 727592-727592.
[7]	李政, 于剑桥, 赵新运. 空空导弹敏捷转弯固定时间收敛滑模控制[J]. 航空学报, 2023, 44(8): 327262-327262.
[8]	何磊, 钱炜祺, 董康生, 易贤, 柴聪聪. 基于卷积神经网络的结冰翼型气动特性建模[J]. 航空学报, 2023, 44(5): 126434-126434.
[9]	丁鹏, 宋亚飞. 代价敏感的空中目标意图识别方法[J]. 航空学报, 2023, 44(24): 328551-328551.
[10]	李晓航, 周建江. 基于自适应记忆长度的多尺度模态融合网络[J]. 航空学报, 2023, 44(22): 628977-628977.
[11]	罗皓文, 何绍溟, 金天宇, 刘子超. 基于迁移学习的角度约束时间最短制导算法[J]. 航空学报, 2023, 44(19): 328400-328400.
[12]	赵鋆赫, 王生楠. 基于深度学习的权函数法应力强度因子求解[J]. 航空学报, 2023, 44(19): 228367-228367.
[13]	高一凡, 何锋, 于思凡. 基于发布订阅架构的在线时间触发调度方法[J]. 航空学报, 2023, 44(18): 328125-328125.
[14]	高树一, 林德福, 郑多, 胡馨予. 针对集群攻击的飞行器智能协同拦截策略[J]. 航空学报, 2023, 44(18): 328301-328301.
[15]	苑玉彬, 吴一全, 赵朗月, 陈金林, 赵其昌. 基于深度学习的无人机航拍视频多目标检测与跟踪研究进展[J]. 航空学报, 2023, 44(18): 28334-028334.