逆轨拦截的目标命中点分支预测智能制导算法

doi:10.7527/S1000-6893.2024.30873

Abstract

Abstract:

To achieve the maximum interception terminal velocity when intercepting maneuvering targets in the contra-orbit， this paper constructs a target maneuvering ballistic branch prediction model based on the sequence-to-sequence method， and constructs a deep reinforcement learning intelligent guidance law based on the deep Q-learning algorithm and the bias guidance law. To address the sparse reward problem caused by the training process of the smart guidance law， the prediction-correction method is used to introduce the guidance ratio of the terminal guidance to construct the terminal reward， and the process reward is constructed by combining the physical process and performance indexes. The process reward and terminal reward are combined to improve the training effect. Simulation shows that the target maneuvering ballistic branch prediction model improves the average prediction accuracy of the maneuvering ballistic in the sub-direction by at least 67% compared with the ballistic extrapolation method， and the intelligent guidance law improves the relative interception speed by 67% compared with the baseline guidance law on the premise of meeting the requirements of shift performance and low overload.

Key words: maneuvering target, head-on interception, trajectory prediction, predicted hit point, intelligent guidance law

CLC Number:

Qingcheng WAN, Meng YU, Yubao LI, Yin WANG. Intelligent guidance algorithm for target hit point branch prediction for head-on interception[J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(S1): 730873.

Figures/Tables 14

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Fig.7

Fig.8

Fig.9

Table 1

Fig.10

Table 2

Fig.11

Table 3

References 21

1	蔡远利，邓逸凡，苏悦华.高超声速飞行器LSTM弹道分类与预报方法［C］∥第21届中国系统仿真技术及其应用学术年会论文集. 北京：中国自动化协会， 2020： 303-307.
	CAI Y L， DENG Y F， SU Y H， LSTM based trajectory classification and prediction for hypersonic vehicle［C］‍∥ CCSSTA 21st. Beijing： CAA， 2020： 303-307 （in Chinese）.
2	吉瑞萍，张程祎，梁彦，等. 基于LSTM的弹道导弹主动段轨迹预报［J］. 系统工程与电子技术， 2022， 44（6）： 1968-1976.
	JI R P， ZHANG C Y， LIANG Y， et al. Trajectory prediction of boost-phase ballistic missile based on LSTM［J］. Systems Engineering and Electronics， 2022， 44（6）： 1968-1976 （in Chinese）.
3	宋波涛，许广亮. 基于 LSTM 与1DCNN 的导弹轨迹预测方法［J］.系统工程与电子技术， 2023，45（2）：504-512.
	SONG B T， XU G L.Missile trajectory prediction method based on LSTM and 1DCNN［J］. Systems Engineering and Electronics， 2023， 45（2）： 504-512.
4	周昶丰，范世鹏. 考虑终端多约束条件的多项式最优制导律［J］. 弹箭与制导学报， 2024， 44（ 2）： 97-104.
	ZHOU C F， FAN S P. Polynomial optimal guidance law with terminal multi-constraints［J］. Journal of Projectiles， Rockets， Missiles and Guidance， 2024， 44（ 2）： 97-104.
5	姚怀瑾，林德福，臧路尧，等. 变结构经典比例导引制导性能对比研究［J］. 计算机仿真， 2014， 31（7）： 31-35.
	YAO H J， LIN D F， ZANG L Y， et al. Performance comparison of variable structure/classic proportional navigation guidance laws［J］. Computer Simulation， 2014， 31（7）： 31-35 （in Chinese）.
6	雷文贵，周浩，陈万春. 基于 Guass伪谱法的空空导弹中制导方法研究［J/OL］. 飞行力学. （2024-04-07）［2024-06-26］. .
	LEI W G， ZHOU H， CHEN W C. Midcourse guidance method in air-to-air missiles based on Gauss pseudospectral method［J/OL］. （2024-04-07）［2024-6-26］. （in Chinese）.
7	马雪飞，王智，宋清华，等. 基于终端角度约束的鱼雷滑模制导律［J］.惯性技术学报， 2023，31（10）：1044-1052+1060.
	MA X F， WANG Z， SONG Q H， et al. Torpedo sliding mode guidance law based on terminal angle constraint［J］. Journal of Chinese Inertial Technology， 2023， 31（10）：1044-1052+1060.
8	李晨迪，王江，李斌，等. 过虚拟交班点的能量最优制导律［J］. 航空学报， 2019， 40（12）： 323249.
	LI C D， WANG J， LI B， et al. Energy-optimal guidance law with virtual hand-over point［J］. Acta Aeronautica et Astronautica Sinica， 2019， 40（12）： 323249 （in Chinese）.
9	吴紫怡，何绍溟，王亚东，等. 针对运动目标的可观性增强非线性最优制导律［J］.航空学报，2023，44（S2）：729750.
	WU Z Y， HE S M， WANG Y D， et al. Nonlinear observability-enhancement optimal guidance law for moving targets［J］. Acta Aeronautica et Astronautica Sinica， 2019，40（S2）： 729750 （in Chinese）.
10	司玉洁，熊华，宋勋，等. 三维自适应终端滑模协同制导律［J］.航空学报，2020，41（S1）：723759.
	SI Y J， XIONG H， SONG X， et al. Three dimensional guidance law for cooperative operation based on adaptive terminal sliding mode ［J］. Acta Aeronautica et Astronautica Sinica， 2020， 41（S1）： 723759 （in Chinese）.
11	郑成辰，李辉，陶伟，等. 基于深度强化学习的导弹末端约束角制导律［J］. 战术导弹技术， 2022 （6）： 93-102.
	ZHENG C C， LI H， TAO W，et al. Navigation guidance law with impact angle constraint based on deep reinforcement learning［J］.Tactical Missile Technology，2022（6）： 93-102 （in Chinese）.
12	康冰冰，姜涛，曹建，等. 基于强化学习的带落角约束的制导律研究［J］. 航空兵器， 2023， 30（6）： 44-49.
	KANG B B， JIANG T， CAO J， et al. Research on guidance law with constraint attack angle based on reinforcement learning［J］. Aero Weaponry， 2023， 30（6）： 44-49 （in Chinese）.
13	张豪，朱建文，李小平，等. 针对高机动目标的深度强化学习智能拦截制导［J/OL］. 北京航空航天大学学报.（2023-09-27）［2024-06-26］. .
	ZHANG H， ZHU J W， LI X P， et al. Deep reinforcement learing intelligent guidance for intercepting high maneuvering targets［J］. Journal of Beijing University of Aeronautics and Astronautics. （2023-09-27）［2024-6-26］. .
14	陈文钰，邵雷，谭诗利，等. 基于虚拟拦截点的预测制导算法设计［J］.飞行力学， 2020， 38（03）： 70-76.
	CHEN W Y， SHAO L， TAN S L， et al. Design of predictive guidance algorithm based on virtual intercepting points［J］. FLIGHT DYNAMICS，2020， 38（03）： 70-76 （in Chinese）.
15	舒健生，孟少飞，张士熊. 基于虚拟目标的KKV逆轨拦截导引方法［J］. 四川兵工学报， 2014， 35（4）： 5-8.
	SHU J S， MENG S F， ZHANG S X. KKV guidance law for exoatmospheric head-on interception based on virtual target［J］. Journal of Ordnance Equipment Engineering， 2014， 35（4）： 5-8 （in Chinese）.
16	CHO K， VAN MERRIENBOER B， GULCEHRE C， et al. Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation［C］∥ Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing （EMNLP）. Stroudsburg： Association for Computational Linguistics， 2014： 1724-1734.
17	BENGIO S， VINYALS O， JAITLY N， et al. Scheduled sampling for sequence prediction with recurrent neural networks［J］. Advances in Neural Information Processing Systems， 2015， 2015-January： 1171-1179.
18	SUTSKEVER I， VINYALS O， LE Q V. Sequence to sequence learning with neural networks［J］. Advances in Neural Information Processing Systems， 2014， 4（January）： 3104-3112.
19	MNIH V， KAVUKCUOGLU K， SILVER D， et al. Playing atari with deep reinforcement learning［DB/OL］. arXiv Preprint： 1312.5602； 2013.
20	SCHAUL T， QUAN J， ANTONOGLOU I， et al. Prioritized experience replay［DB/OL］. arXiv Preprint： 1511.05952； 2015.
21	董朝阳，周雨. 一种交班时刻性能最优的中制导律设计与仿真［J］. 系统仿真学报， 2009， 21（24）： 7873-7877， 7882.
	DONG C Y， ZHOU Y. Design and simulation of handover performance optimal midcourse guidance law［J］. Journal of System Simulation， 2009， 21（24）： 7873-7877， 7882 （in Chinese）.

参数名称	参数值
神经网络隐含层数	2
状态维度	6
动作维度	15
动作网络学习率	0.05
评价网络学习率	0.05
样本批次大小	128
折扣因子	0.99
探索率	0.7
初始目标点/km	（60，30）
初始目标角度/（°）	60
目标变动时弹目距离/km	10
目标变动范围/km	x∈［60，64］y∈［26，30］
变动目标角度/（°）	70
中末交班时弹目距离/km	7
制导过载上限/g	20
交班速度交会角约束/（°）	［50，90］

参数名称	PNG	OCPNG	DLRG（数据过滤）	DLRG
相对拦截速度/（m·s^-1）	614	1 037	1 739	1 070
最大过载比a/g（无量纲）	8.86	24.85	20	20
交班速度交会角/（°）	16.9	33	51.4	22.5

命中点变动方向	制导律种类	相对拦截速度/（m·s^-1）	速度交会角/（°）
左上方	DRLG	1 784	67.0
x∈［56，60］ km	OCPNG	1 203	72.2
y∈［30，34］ km	PNG	1 120	40.5
左下方	DRLG	1 870	56.0
x∈［56，60］ km	OCPNG	1 163	49.6
y∈［26，30］ km	PNG	753	30.2
右上方	DRLG	1 916	60.2
x∈［60，64］ km	OCPNG	1 208	31.5
y∈［30，34］ km	PNG	987	26.7

[1]	Shusheng CHEN, Muliang JIA, Jiahao LIN, Shiyi JIN, Zhenghong GAO, Yueqing WANG, Zhiqiang MA, Zheng LI, Chenlong DUAN, Jiawei LI. Empowering aircraft technology applications with generative models: Research progress and prospects [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(10): 631194-631194.
[2]	Jian WANG, Lihui ZHOU, Jiafu CHEN, Xinqi LI, Linyang GUO, Zihao HE, Hao ZHOU. Time-varying smooth variable structure filter based on interactive multi-model [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(21): 330167-330167.
[3]	Qian ZHANG, Guanwei YAN, Qin NIE, Ruihai CHEN, Jianing LIU. Aircraft-missile cooperative guidance method based on trajectory numerical optimization of long-range air-to-air missiles [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(17): 530138-530138.
[4]	Baichuan ZHANG, Wenhao BI, An ZHANG, Zeming MAO, Mi YANG. Transformer-based error compensation method for air combat aircraft trajectory prediction [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(9): 327413-327413.
[5]	Yiting TAN, Wuxing JING, Changsheng GAO, Ruoming AN. Multiple constrained analytical capture region for hypersonic maneuvering target interception [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(22): 328436-328436.
[6]	Bing WANG, Runyuan ZOU, Zhening CHANG. Aircraft takeoff mass estimation method based on improved simulated annealing algorithm [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(16): 328090-328090.
[7]	Wenxue CHEN, Changsheng GAO, Wuxing JING. Trust region policy optimization guidance algorithm for intercepting maneuvering target [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(11): 327596-327596.
[8]	YU Jianglong, DONG Xiwang, LI Qingdong, LYU Jinhu, REN Zhang. Distributed cooperative encirclement hunting guidance method for intercepting maneuvering target [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(9): 325817-325817.
[9]	XIONG Wei, ZHU Hongfeng, CUI Yaqi. Recurrent adaptive maneuvering target tracking algorithm based on online learning [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(5): 325250-325250.
[10]	WANG Yaning, WANG Hui, LIN Defu, YUAN Yifang. Guidance method for maneuvering target interception based on virtual look angle constraint [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(1): 324799-324799.
[11]	QIAO Dianfeng, LIANG Yan, ZHANG Huixia, ZHAO Pengjiao. Automatic backtracking-based refined segment recognition of maneuvering target track [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2021, 42(4): 524744-524744.
[12]	XIAO Wei, YU Jianglong, DONG Xiwang, LI Qingdong, REN Zhang. Cooperative interception against highly maneuvering target with acceleration constraints [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2020, 41(S1): 723777-723777.
[13]	DONG Xiaofei, REN Zhang, CHI Qingxi, LI Qingdong. Distributed cooperative guidance for maneuvering targets with directed conmunication topologies [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2020, 41(S1): 723762-723762.
[14]	BAI Zhihui, LI Kebo, SU Wenshan, CHEN Lei. Capture region of RTPN guidance law against arbitrarily maneuvering targets [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2020, 41(8): 323947-323947.
[15]	ZHANG Feng. A new method for double IRST cooperative passive detection and positioning for maneuvering target [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2020, 41(2): 322988-322988.

Intelligent guidance algorithm for target hit point branch prediction for head-on interception

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 14

References 21

Related Articles 15

Recommended Articles

Metrics

Comments