带有神经网络干扰观测器的视线角约束制导

doi:10.12305/j.issn.1001-506X.2024.04.26

摘要/Abstract

摘要：

针对具有终端视线(line-of-sight, LOS)角约束的机动目标拦截问题, 提出一种基于径向基函数(radial basis function, RBF)神经网络干扰观测器的LOS角约束制导方法。首先, 考虑目标机动过程中加速度信息无法获取的情况, 给出了一种基于RBF神经网络的干扰观测器, 实现了对目标机动的高精度估计; 其次, 充分考虑终端角度约束, 结合超螺旋算法思想, 通过幂次项的引入设计了一种改进的滑模制导律, 从而有效提升了有限过载情况下的制导精度; 在此基础上, 通过Lyapunov定理对算法的收敛性和稳定性分别进行了证明; 最后, 通过仿真验证对比了3种不同方法在4种拦截场景下的制导性能, 同时针对所提方法进行了蒙特卡罗打靶仿真, 仿真结果表明所给出的LOS角约束制导律对机动目标拦截精度高、鲁棒性强。

关键词: 改进滑模制导律, 视线角约束, 径向基函数神经网络, 干扰观测器

Abstract:

Aiming at the problem of maneuvering target interception with terminal line-of-sight (LOS) angle constraint, a LOS angle constraint guidance method based on radial basis function (RBF) neural network interference observer is proposed. Firstly, considering that the acceleration information cannot be obtained during target maneuvering process, an interference observer based on RBF neural network is presented, which realizes high-precision estimation of target maneuvering. Secondly, an improved sliding mold guidance law is designed by introducing the power term by fully considering the terminal angle constraint and combining the idea of super-twisting algorithm, so as to effectively improve the guidance accuracy under limited overload conditions. On this basis, the convergence and stability of the algorithm are proved by Lyapunov's theorem. Finally, the guidance performance of three different methods in four interception scenarios is compared through simulation verification, and Monte Carlo simulation is given for the proposed method, and the simulation results show that the LOS angle constraint guidance law given in this paper has high accuracy and strong robustness for maneuvering target interception.

Key words: improved sliding mold guidance law, line-of-sight (LOS) angle constraint, radial basis function (RBF) neural networks, interference observers

中图分类号:

V488.133

何通, 卢青, 周军, 郭宗易. 带有神经网络干扰观测器的视线角约束制导[J]. 系统工程与电子技术, 2024, 46(4): 1372-1382.

Tong HE, Qing LU, Jun ZHOU, Zongyi GUO. Line-of-sight angle constraint guidance with neural network interference observer[J]. Systems Engineering and Electronics, 2024, 46(4): 1372-1382.

图/表 31

图1

图2

图3

表1

表2

图4

图5

图6

图7

图8

图9

图10

图11

图12

图13

图14

图15

图16

图17

图18

图19

表3

表4

图20

图21

图22

图23

图24

图25

表5

图26

参考文献 37

1	黄诘, 张友安, 赵育良, 等.基于终端落角和加速度约束的末制导律设计[J].飞行力学,2020,38(3):52-56, 62.
	HUANG J , ZHANG Y A , ZHAO Y L , et al.Design of terminal guidance law based on terminal impact angle and acceleration constraints[J].Flight Dynamics,2020,38(3):52-56, 62.
2	LYU S , ZHU Z H , TANG S , et al.Prescribed performance slide mode guidance law with terminal line-of-sight angle constraint against maneuvering targets[J].Nonlinear Dynamics,2017,88(3):2101-2110. doi: 10.1007/s11071-017-3365-9
3	XIONG S F , WANG W , LIU X , et al.Guidance law against maneuvering targets with intercept angle constraint[J].ISA Transactions,2014,53(4):1332-1342. doi: 10.1016/j.isatra.2014.03.007
4	蔡洪, 胡正东, 曹渊.具有终端角度约束的导引律综述[J].宇航学报,2010,31(2):315-323.
	CAI H , HU Z D , CAO Y .A survey of guidance law with terminal impact angle constraints[J].Journal of Astronautics,2010,31(2):315-323.
5	KIM M , GRIDER K V .Terminal guidance for impact attitude angle constrained flight trajectories[J].IEEE Trans.on Aerospace and Electronic Systems,1973,AES-9(6):852-859. doi: 10.1109/TAES.1973.309659
6	KIM B S , LEE J G , HAN H S .Biased PNG law for impact with angular constraint[J].IEEE Trans.on Aerospace and Electronic Systems,1998,34(1):277-288. doi: 10.1109/7.640285
7	ZHOU D , QU P P , SUN S .A guidance law with terminal impact angle constraint accounting for missile autopilot[J].Journal of Dynamic Systems, Measurement, and Control,2013,135(5):051009. doi: 10.1115/1.4024202
8	PARK B G , KIM T H , TAHK M J .Range-to-go weighted optimal guidance with impact angle constraint and seeker's look angle limits[J].IEEE Trans.on Aerospace and Electronic Systems,2016,52(3):1241-1256. doi: 10.1109/TAES.2016.150415
9	LEE Y I, RYOO C K, KIM E. Optimal guidance with constraints on impact angle and terminal acceleration[C]//Proc. of the AIAA Guidance, Navigation, and Control Conference and Exhibit, 2003: 5795.
10	LEE J I, JEON I S, TAHK M J. Guidance law to control impact time and angle[J]//IEEE Trans. on Aerospace and Electronic Systems, 2007, 43(1): 301-310.
11	HONG D , KIM M , PARK S .Study on reinforcement learning- based missile guidance law[J].Applied Sciences,2020,10(18):6567. doi: 10.3390/app10186567
12	GAUDET B , FURFARO R , LINARES R .Reinforcement learning for angle-only intercept guidance of maneuvering targets[J].Aerospace Science and Technology,2020,99,1-10.
13	GAUDET B , LINARES R , FURFARO R .Adaptive guidance and integrated navigation with reinforcement meta-learning[J].Acta Astronautica,2020,169,180-190. doi: 10.1016/j.actaastro.2020.01.007
14	LIANG C , WANG W H , LIU Z H , et al.Range-aware impact angle guidance law with deep reinforcement meta-learning[J].IEEE Access,2020,8,152093-152104. doi: 10.1109/ACCESS.2020.3017480
15	HARL N , BALAKRISHNAN S N .Impact time and angle guidance with sliding mode control[J].IEEE Trans.on Control Systems Technology,2012,20(6):1436-1449. doi: 10.1109/TCST.2011.2169795
16	WANG P Y, GU Y, GUO Y N, et al. Shrinking horizon MPC strategy for impact time and angle guidance[C]//Proc. of the 40th Chinese Control Conference, 2021: 3667-3672.
17	赵斌, 梁乐成, 蒋瑞民, 等.终端角度约束制导及制导控制一体化方法综述[J].宇航学报,2022,43(5):563-579.
	ZHAO B , LIANG L C , JIANG R M , et al.Review of guidance and integrated guidance and control methods under terminal angle constraints[J].Journal of Astronautics,2022,43(5):563-579.
18	SONG J H , SONG S M , ZHOU H B .Adaptive nonsingular fast terminal sliding mode guidance law with impact angle constraints[J].International Journal of Control, Automation and Systems,2016,14(1):99-114. doi: 10.1007/s12555-014-0155-8
19	张明洋, 晁涛, 杨明.带有攻击角约束的机动目标协同拦截制导律[J].战术导弹技术,2022,(4):78-89.
	ZHANG M Y , CHAO T , YANG M .Cooperative interception guidance law for maneuvering target with impact angle constraint[J].Tactical Missile Technology,2022,(4):78-89.
20	OHNISHI K .A new servo method in mechatronics[J].Japanese Society of Electrical Engineering,1987,177,83-86.
21	ZHANG X G , SUN L Z , ZHAO K , et al.Nonlinear speed control for PMSM system using sliding-mode control and disturbance compensation techniques[J].IEEE Trans.on Power Electronics,2013,28(3):1358-1365. doi: 10.1109/TPEL.2012.2206610
22	宋俊红, 宋申民, 徐胜利.带有攻击角约束的多导弹协同制导律[J].中国惯性技术学报,2016,24(4):554-560.
	SONG J H , SONG S M , XU S L .Cooperative guidance law for multiple missiles with impact angle constraints[J].Journal of Chinese Inertial Technology,2016,24(4):554-560.
23	LIN S Y , CAI Y Z , YANG B , et al.Electrical line-shafting control for motor speed synchronisation using sliding mode controller and disturbance observer[J].IET Control Theory & Applications,2017,11(2):205-212.
24	ZHANG X G , HOU B S , MEI Y .Deadbeat predictive current control of permanent-magnet synchronous motors with stator current and disturbance observer[J].IEEE Trans.on Power Electronics,2017,32(5):3818-3834. doi: 10.1109/TPEL.2016.2592534
25	JIANG Y J , XU W , MU C X , et al.Improved deadbeat predictive current control combined sliding mode strategy for PMSM drive system[J].IEEE Trans.on Vehicular Technology,2018,67(1):251-263. doi: 10.1109/TVT.2017.2752778
26	WANG B , LUO C , YU Y , et al.Antidisturbance speed control for induction machine drives using high-order fast terminal sliding-mode load torque observer[J].IEEE Trans.on Power Electronics,2018,33(9):7927-7937. doi: 10.1109/TPEL.2017.2765522
27	UTKIN V, SHI J X. Integral sliding mode in systems operating under uncertainty conditions[C]//Proc. of the IEEE 35th Conference on Decision and Control, 1996, 4: 4591-4596.
28	HUO J H, MENG T, JIN Z H. Adaptive attitude control using neural network observer disturbance compensation technique[C]//Proc. of the IEEE 9th International Conference on Recent Advances in Space Technologies, 2019: 697-701.
29	岳晓奎, 吕佰梁, 刘闯, 等.基于神经网络干扰观测器的柔性航天器姿态稳定控制[J].上海航天,2022,39(4):58-65.
	YUE X K , LYU B L , LIU C , et al.Neural network disturbance observer-based attitude control for flexible spacecrafts[J].Aerospace Shanghai,2022,39(4):58-65.
30	DONG W , WANG C Y , WANG J N , et al.Fixed-time terminal angle-constrained cooperative guidance law against maneuvering target[J].IEEE Trans.on Aerospace and Electronic Systems,2022,58(2):1352-1366. doi: 10.1109/TAES.2021.3113292
31	YU H , DAI K R , LI H J , et al.Three-dimensional adaptive fixed-time cooperative guidance law with impact time and angle constraints[J].Aerospace Science and Technology,2022,123,107450. doi: 10.1016/j.ast.2022.107450
32	LIN M , DING X J , WANG C Y , et al.Three-dimensional fixed-time cooperative guidance law with impact angle constraint and prespecified impact time[J].IEEE Access,2021,9,29755-29763. doi: 10.1109/ACCESS.2021.3057428
33	刘金琨.滑模变结构控制Matlab仿真基本理论与设计方法[M].北京: 清华大学出版社,2022.
	LIU J K .Sliding mode control design and Matlab simulation the basic theory and design method[M].Beijing: Tsinghua University Press,2022.
34	LEVANT A .Sliding order and sliding accuracy in sliding mode control[J].International Journal of Control,1993,58(6):1247-1263. doi: 10.1080/00207179308923053
35	LEVANT A .Robust exact differentiation via sliding mode technique[J].Automatica,1998,34(3):379-384. doi: 10.1016/S0005-1098(97)00209-4
36	MORENO J A, OSORIO M. A Lyapunov approach to second-order sliding mode controllers and observers[C]//Proc. of the IEEE 47th Conference on Decision and Control, 2008: 2856-2861.
37	DAVILA A, MORENO J A, FRIDMAN L. Optimal Lyapunov function selection for reaching time estimation of super twisting algorithm[C]//Proc. of the IEEE 48h Conference on Decision and Control Held Jointly with the 28th Chinese Control Confe-rence, 2009: 8405-8410.

场景编号	目标加速度	终端角度约束
1	a_tx=0 a_ty=1.5cos(0.1t)+Δa_ty a_tz=1.5cos(0.1t)+Δa_tz	q_εf=20° q_βf=－45°
2	a_tx=0 a_ty=1.5cos(0.1t)+Δa_ty a_tz=1.5cos(0.1t)+Δa_tz	q_εf=15° q_βf=30°
3	a_tx=0 a_ty=0+Δa_ty a_tz=0+Δa_tz	q_εf=20° q_βf=－45°
4	a_tx=0 a_ty=0+Δa_ty a_tz=0+Δa_tz	q_εf=15° q_βf=30°

场景编号	关键参数	方法1	方法2	方法3
1	T/s	38.848 0	34.278 0	37.355 0
	Δq_ε/(°)	0.048 0	10.115 3	0.002 1
	Δq_β/(°)	26.809 8	32.415 1	1.804 8
2	T/s	37.811 0	34.434 0	38.901 0
	Δq_ε/(°)	0.018 3	6.087 82	0.004 9
	Δq_β/(°)	23.769 5	28.142 6	0.134 5
3	T/s	34.650 0	32.323 0	36.342 0
	Δq_ε/(°)	1.021 9	10.455 8	0.012 5
	Δq_β/(°)	11.141 6	33.160 0	1.115 6
4	T/s	33.686 0	32.211 0	34.714 0
	Δq_ε/(°)	0.362 5	6.381 86	0.011 0
	Δq_β/(°)	12.480 9	28.833 9	1.876 5

参数	方法
参数	RBF	SMO
T_m/s	0.611 0	3.959 0
err₁	0.021 3	0.022 2

参数	方法
参数	RBF	SMO
T_n/s	1.159 0	4.097 0
err₂	0.003 2	0.010 1

参数	方法
参数	方法1	方法2	方法3
平均脱靶量/m	1.302 49	1.068 32	1.026 01
平均纵向角误差/(°)	0.395 95	9.140 70	0.161 16
平均侧向角误差/(°)	20.222 20	32.714 50	7.592 64