不依赖剩余飞行时间的数据驱动攻击时间控制导引律

doi:10.12382/bgxb.2022.0324

摘要/Abstract

摘要：

针对导弹的攻击时间控制问题,基于比例导引法和数据驱动方法设计出一种不依赖剩余飞行时间信息的两阶段攻击时间控制导引律。第1阶段为攻击时间控制阶段,在比例导引法框架下仿真构建弹道倾角与导弹飞行状态之间的关系数据集,利用神经网络方法离线训练出相应的映射网络模型,根据该映射网络可在导弹飞行过程中实时解算攻击时间对应的理想弹道倾角,导引指令将控制实际弹道倾角收敛至该理想弹道倾角;第2阶段则直接采用比例导引法,最终实现导弹攻击时间控制。不同条件下的仿真结果验证了该导引律的可行性和有效性,与现有同类导引律相比,所设计导引律对攻击时间的控制精度更高、所需控制能量更少。理论分析表明,该导引律可通过更换映射网络推广至攻击角度控制。

关键词: 数据驱动方法, 比例导引法, 理想弹道倾角, 攻击时间控制, 攻击角度控制

Abstract:

To solve the problem of missile impact time control, a two-stage impact time control guidance law is designed based on proportional navigation guidance and the data-driven method, which is independent of time-to-go information. The first stage is the impact time control stage. The relationship data set between the flight path angle and the flight state of the missile is constructed by simulation under the framework of proportional navigation guidance method, and then the corresponding mapping network model is trained offline by using the neural network method. According to the mapping network, the ideal flight path angle corresponding to the impact time can be calculated in real time during missile flight, and the guidance command will control the actual flight path angle converging to the ideal one. In the second stage, the proportional navigation guidance law is directly applied, and the missile impact time control is finally realized. The simulation results under different conditions verify the feasibility and effectiveness of the proposed guidance law. Compared with the existing similar guidance laws, the proposed one can control the impact time with higher precision and less control energy. In addition, the theoretical analysis shows that the guidance law can be extended to impact angle control by changing the mapping network.

Key words: data-driven method, proportional navigation guidance, ideal flight path angle, impact time control, impact angle control

中图分类号:

TJ765.3

黄嘉, 常思江, 陈琦, 张海洋. 不依赖剩余飞行时间的数据驱动攻击时间控制导引律[J]. 兵工学报, 2023, 44(8): 2299-2309.

HUANG Jia, CHANG Sijiang, CHEN Qi, ZHANG Haiyang. Data-Driven-Based Impact Time Control Guidance Law Independent of Time-to-Go[J]. Acta Armamentarii, 2023, 44(8): 2299-2309.

图/表 11

图1 导弹与目标运动关系

Fig.1 Relationship of missile-target engagement

图2 神经网络结构图

Fig.2 Structure diagram of neural network

图3 训练过程中的误差变化

Fig.3 Error variation during training

图4 不同期望攻击时间仿真结果

Fig.4 Simulation results of different desired impact time

图5 飞行状态变量存在误差的仿真结果

Fig.5 Simulation results of errors in flight state variables

表1 不同期望攻击时间对应的攻击时间误差

Table 1 Errors of impact time corresponding to different desired impact time

序号	R、γ是否存在误差	期望攻击时间/s	实际攻击时间与期望值之差/s
1	否	45	0.013
2	否	50	0.021
3	否	55	0.022
4	否	60	0.012
5	否	65	0.005
6	是	65	0.005

图6 与文献[10]对比仿真结果

Fig.6 Simulation results compared with Ref.[10]

表2 本文导引律和文献[10]导引律的性能对比

Table 2 Comparison of performance between the proposed guidance law and the one in Ref. [10]

序号	导引律	初始前置角/ (°)	攻击时间误差/s	加速度极值绝对值/ (m·s^-2)	总控制能量/ (m²·s^-3)
1	本文	15	0.002	22.59	7.69×10³
2	文献[10]	15	0.039	98.00	1.08×10⁴
3	本文	45	0.005	20.97	5.43×10³
4	文献[10]	45	0.041	42.41	5.72×10³

图7 协同攻击仿真结果

Fig.7 Simulation results of cooperative attack

表3 协同攻击的仿真参数及结果

Table 3 Simulation parameters and results of cooperative attack

仿真对象	位置/m	初始前置角/(°)	攻击时间误差/s
导弹1	(-5000,-7000)	30	0.032
导弹2	(-10000,0)	40	0.012
导弹3	(-10392.3,6000)	20	0.025
目标	(0,0)	0	0

图8 不同期望攻击角度仿真结果

Fig.8 Simulation results of different desired impact angles

参考文献 25

[1]	JEON I S, LEE J I, TAHK M J. Impact-time-control guidance law for anti-ship missiles[J]. IEEE Transactions on Control Systems Technology, 2006, 14(2): 260-266. doi: 10.1109/TCST.2005.863655 URL
[2]	WANG J W, ZHANG R. Terminal guidance for a hypersonic vehicle with impact time control[J]. Journal of Guidance, Control, and Dynamics, 2018, 41(8): 1789-1797.
[3]	LEE S, CHO N, KIM Y. Impact-time-control guidance strategy with a composite structure considering the seeker’s field-of-view constraint[J]. Journal of Guidance, Control, and Dynamics, 2020, 43(8): 1566-1574. doi: 10.2514/1.G005063 URL
[4]	CHO N, KIM Y. Modifiedpure proportional navigation guidance law for impact time control[J]. Journal of Guidance, Control, and Dynamics, 2016, 39(4): 852-872. doi: 10.2514/1.G001618 URL
[5]	JEON I S, LEE J I, TAHK M J. Impact-time-control guidance with generalized proportional navigation based on nonlinear formulation[J]. Journal of Guidance, Control, and Dynamics, 2016, 39(8):1887-1892.
[6]	李斌, 林德福, 何绍溟, 等. 基于最优误差动力学的时间角度控制制导律[J]. 航空学报, 2018, 39(11): 322215. doi: 10.7527/S1000-6893.2018.22215
	LI B, LIN D F, HE S M, et al. Time and angle control guidance law based on optimal error dynamics[J]. Acta Aeronautica et Astronautica Sinica, 2018, 39(11): 322215. (in Chinese) doi: 10.7527/S1000-6893.2018.22215
[7]	CHO D, KIM H J, TAHK M J. Nonsingular sliding mode guidance for impact time control[J]. Journal of Guidance, Control, and Dynamics, 2016, 39(1):61-68. doi: 10.2514/1.G001167 URL
[8]	陈升富, 常思江, 吴放. 带有视场角约束的滑模攻击时间控制制导律[J]. 兵工学报, 2019, 40(4): 777-787. doi: 10.3969/j.issn.1000-1093.2019.04.013
	CHEN S F, CHANG S J, WU F. A sliding mode guidance law for impact time control with field of view constraint[J]. Acta Armamentarii, 2019, 40(4): 777-787. (in Chinese) doi: 10.3969/j.issn.1000-1093.2019.04.013
[9]	TEKIN R, RERE K S, HOLZAPFEL F. Quartic range shaping for impact time control[C]// Proceedings of the 2017 25th Mediterranean Conference on Control and Automation. Valletta, Malta:IEEE, 2017: 1213-1218.
[10]	TEKIN R, RERE K S, HOLZAPFEL F. Impact time control with generalized-polynomial range formulation[J]. Journal of Guidance, Control, and Dynamics, 2018, 41(5): 1188-1193.
[11]	TEKIN R, RERE K S, HOLZAPFEL F. Control of impact time with increased robustness via feedback linearization[J]. Journal of Guidance, Control, and Dynamics, 2016, 39(7): 1678-1685. doi: 10.2514/1.G001513 URL
[12]	TEKIN R, RERE K S, HOLZAPFEL F. Polynomial shaping of the look angle for impact time control[J]. Journal of Guidance, Control, and Dynamics, 2017, 40(10): 2666-2671.
[13]	JEON I S, LEE J I. Impact-time-control guidance law with constraints on seeker look angle[J]. IEEE Transactions on Aerospace and Electronic Systems, 2017, 53(5): 2621-2627. doi: 10.1109/TAES.2017.2698837 URL
[14]	TEKIN R, RERE K S, HOLZAPFEL F. Adaptive impact time control via look-angle shaping under varying velocity[J]. Journal of Guidance, Control, and Dynamics, 2017, 40(12): 3247-3255. doi: 10.2514/1.G002981 URL
[15]	CHEN X T, WANG J Z. Nonsingular sliding-mode control for field-of-view constrained impact time guidance[J]. Journal of Guidance, Control, and Dynamics, 2018, 41(5): 1210-1218.
[16]	吴放, 常思江, 陈升富. 基于终端滑模理论的攻击时间控制制导律[J]. 系统工程与电子技术, 2019, 41(10): 2335-2342.
	WU F, CHANG S J, CHEN S F. Impact time control guidance law based on terminal sliding mode theory[J]. Systems Engineering and Electronics, 2019, 41(10): 2335-2342. (in Chinese)
[17]	HU Q L, HAN T, XIN M. Sliding-mode impact time guidance law design for various target motions[J]. Journal of Guidance, Control, and Dynamics, 2019, 42(1): 136-148.
[18]	CHANG S J, CHEN S F. Nonsingular PNG-based impact time control guidance with lower dependence on time-to-go estimate[J]. International Journal of Aerospace Engineering, 2019: 5031245.
[19]	GUO Y H, LI X, ZHANG H J, et al. Data-driven method for impact time control based on proportional navigation guidance[J]. Journal of Guidance, Control, and Dynamics, 2020, 43(5): 955-966. doi: 10.2514/1.G004669 URL
[20]	刘子超, 王江, 何绍溟, 等. 基于预测校正的落角约束计算制导方法[J]. 航空学报, 2021, 42:325433.
	LIU Z C, WANG J, HE S M, et al. A computational guidance algorithm for impact angle control based on the predictor-corrector concept[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42:325433. (in Chinese)
[21]	HE S M, SHIN H S, TSOURDOS A. Computational missile guidance: a deep reinforcement learning approach[J]. Journal of Aerospace Information Systems, 2021, 18(8): 571-582. doi: 10.2514/1.I010970 URL
[22]	方科, 张庆振, 倪昆, 等. 飞行时间约束下的再入制导律[J]. 哈尔滨工业大学学报, 2019, 51(10): 90-97.
	FANG K, ZHANG Q Z, NI K, et al. Reentry guidance law with flight time constraint[J]. Journal of Harbin Institute of Technology, 2019, 51(10): 90-97. (in Chinese)
[23]	张晚晴, 余文斌, 李静琳, 等. 基于纵程解析解的飞行器智能横程机动再入协同制导[J]. 兵工学报, 2021, 42(7):1410-1411.
	ZHANG W Q, YU W B, LI J L, et al. Cooperative reentry guidance for intelligent lateral maneuver of hypersonic vehicle based on downrange analytical solution[J]. Acta Armamentarii, 2021, 42(7):1410-1411. (in Chinese)
[24]	余跃, 王宏伦. 基于深度学习的高超声速飞行器再入预测校正容错制导[J]. 兵工学报, 2020, 41(4):656-669. doi: 10.3969/j.issn.1000-1093.2020.04.005
	YU Y, WANG H L. Deep learning-based reentry predictor-corrector fault-tolerant guidance for hypersonic vehicles[J]. Acta Armamentarii, 2020, 41(4): 656-669. (in Chinese) doi: 10.3969/j.issn.1000-1093.2020.04.005
[25]	CHENG L, JIANG F H, WANG Z B, et al. Multiconstrained real-time entry guidance using deep neural networks[J]. IEEE Transactions on Aerospace and Electronic Systems, 2021, 57(1): 325-340. doi: 10.1109/TAES.7 URL