基于迁移学习的角度约束时间最短制导算法

doi:10.7527/S1000-6893.2022.28400

Abstract

Abstract:

The aerodynamic environment and other external conditions of the missile are complex and changeable. The deep supervised learning guidance algorithm with excellent performance in the specific aerodynamic environment cannot be directly applied to the new environment, which brings great challenges to the accurate prediction of guidance instructions. To solve the above problem, this paper proposes a Transfer-learning-based Impact-angel Constraint with Time-minimum Guidance algorithm (TICTG) for missile guidance, which minimizes the impact time under impact angle constraints. The proposed algorithm can quickly adapt the guidance law to different aerodynamic conditions with very little new data. Firstly, we extract key features insensitive to aerodynamic changes from ballistic data in different aerodynamic environments by training the feature extractor and domain discriminator against the domain ground. Secondly, we design a bias acceleration predictor adapted to different aerodynamic conditions, so as to achieve accurate guidance of the missile. A large number of numerical simulation results show that the method proposed can achieve accurate prediction of guidance instructions in the new aerodynamic environment.

Key words: computational guidance, deep learning, transfer learning, impact angle constraint, bais proportion navigation

CLC Number:

V249

Haowen LUO, Shaoming HE, Tianyu JIN, Zichao LIU. Impact-angle-constrained with time-minimum guidance algorithm based on transfer learning[J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(19): 328400-328400.

Figures/Tables 23

Fig.1

Table 1

Aerodynamic coefficients of source region

马赫数	$C D 0$	$C D α 2$	$C L α$
0.1	0.451 29	22.041	24.538
0.2	0.421 05	22.424	24.496
0.3	0.416 64	22.731	24.572
0.4	0.421 47	23.056	24.551
0.5	0.421 68	23.190	24.678
0.6	0.430 61	23.592	24.994
0.7	0.444 04	24.158	25.263

Table 1

Fig.2

Fig.3

Table 2

Aerodynamic coefficients of target region

马赫数	$C D 0$	$C D α 2$	$C L α$
0.1	0.541 55	26.449	29.446
0.2	0.505 26	26.909	29.395
0.3	0.499 97	27.276	29.487
0.4	0.505 76	27.667	29.461
0.5	0.506 02	27.828	29.613
0.6	0.516 73	28.311	29.993
0.7	0.532 85	28.988	30.316

Table 2

Fig.4

Fig.5

Table 3

Initial state and impact angle constraint

参数	取值
导弹x方向初始位 $x 0 / m$	0
导弹y方向初始位 $y 0 / k m$	5
目标x方向位置 $x f / k m$	［20， 21］
目标y方向位置 $y f / m$	2
导弹初始速度 $v 0 / (m ⋅ s - 1)$	300
初始弹道倾角 $θ 0 / ∘$	［0，10］
终端攻击角度 $θ f / ∘$	-90

Table 3

Table 4

Fig.6

Fig.7

Table 5

Mean， maximum， median and standard deviation of bias acceleration prediction error

参数	均值	最大值	中位数	标准差
与实际偏置加速度的误差/（ $m ⋅ s - 2$ ）	0.153 3	22.42	0.009 1	2.072

Table 5

Fig.8

Fig.9

Fig.10

Table 6

Error statistics of TICTG

误差	均值	最大值	中位数	标准差
水平脱靶量 $Δ x / 10 - 3 m$	2.4	3.6	2.11	1.1
铅锤脱靶量 $Δ y / m$	0.578 2	0.987 6	0.437 6	0.223 2
速度误差 $Δ v / (m ⋅ s - 1)$	0.080 3	0.542	0.072 2	0.031 91
攻击角度误差 $Δ θ / (°)$	0.208 8	0.266 4	0.151 93	0.052 8
飞行时间误差 $Δ t / 10 - 3 s$	9.07	43.39	12.5	3.8

Table 6

Table 7

Different aerodynamic perturbations

气动环境摄动	$C D 0$ /%	$C D α 2$ /%	$C L α$ /%
1	5	5	5
2	10	10	10
3	20	20	20

Table 7

Fig.11

Table 8

Error statistics of TICTG and DICTG in Perturbed environment 1

误差种类	TICTG				DICTG
误差种类	均值	最大值	中位数	标准差	均值	最大值	中位数	标准差
水平脱靶量 $Δ x / 10 - 3 m$	4.7	9.1	6.41	1.8	43.2	92.6	43.2	17.6
铅锤脱靶量 $Δ y / m$	0.573 2	0.994 2	0.529 3	0.206 7	0.589 2	0.997 7	0.601	0.216 8
速度误差 $Δ v / (m ⋅ s - 1)$	1.932	2.240	2.123	0.412	2.507 1	2.847 9	2.201	0.357 8
攻击角度误差 $Δ θ / (°)$	0.481 9	0.698 2	0.474 7	0.090 3	4.248	6.252	4.331	0.917
飞行时间误差 $Δ t / s$	0.415 5	0.470 6	0.409 7	0.022 3	1.106	1.516	1.224	0.191

Table 8

Table 9

Error statistics of TICTG and DICTG in Perturbed environment 2

误差种类	TICTG				DICTG
误差种类	均值	最大值	中位数	标准差	均值	最大值	中位数	标准差
水平脱靶量 $Δ x / 10 - 3 m$	13.6	26.9	13.4	5.1	103.2	220.0	103.8	46.2
铅锤脱靶量 $Δ y / m$	0.623 6	0.999 9	0.634 1	0.211 8	0.634 5	0.995 6	0.633	0.223
速度误差 $Δ v / (m ⋅ s - 1)$	3.867 5	4.218 5	4.022 6	0.367 8	4.238	4.739	4.367	0.310
攻击角度误差 $Δ θ / (°)$	1.263 6	1.784 8	1.274 7	0.216 2	9.160	13.110	9.56	2.256
飞行时间误差 $Δ t / s$	0.812 6	0.946 1	0.811 7	0.054 7	2.359 1	3.233	2.398	0.499 2

Table 9

Table 10

Error statistics of TICTG and DICTG in Perturbed environment 3

误差	TICTG				DICTG
误差	均值	最大值	中位数	标准差	均值	最大值	中位数	标准差
水平脱靶量 $Δ x / 10 - 3 m$	25.1	50.8	6.35	10.0	239.4	555.6	205.4	102.2
铅锤脱靶量 $Δ y / m$	0.588	0.992	0.567	0.214 8	0.654 8	0.9996	0.632 2	0.195 1
速度误差 $Δ v / (m ⋅ s - 1)$	7.502	7.767	7.184 3	0.258 4	8.165 6	9.0946	8.214 8	0.395 8
攻击角度误差 $Δ θ / (°)$	2.451	3.087	2.711 9	0.329	19.815	30.238	18.785 4	5.212 3
飞行时间误差 $Δ t / s$	1.493	1.676	0.437 2	0.084 9	5.160 4	7.8024	4.887 5	1.278 4

Table 10

Fig.12

Table 11

Introduction of error statistics of thrust perturbation in aerodynamic Perturbed environment 1

误差	均值	最大值	中位数	标准差
水平脱靶量 $Δ x / 10 - 3 m$	2.7	9.5	2.5	2.2
铅锤脱靶量 $Δ y / m$	0.618 1	0.996 1	0.618 1	0.218 9
速度误差 $Δ v / (m ⋅ s - 1)$	2.465 4	3.272	2.541	0.491 1
攻击角度误差 $Δ θ / (°)$	0.541 6	0.764 9	0.673 2	0.173 9
飞行时间误差 $Δ t / s$	0.394 6	0.463 8	0.393 4	0.015 2

Table 11

References 25

1	高峰，唐胜景，师娇，等. 一种基于落角约束的偏置比例导引律［J］. 北京理工大学学报， 2014， 34（3）： 277-282.
	GAO F， TANG S J， SHI J， et al. A bias proportional navigation guidance law based on terminal impact angle constraint［J］. Transactions of Beijing Institute of Technology， 2014， 34（3）： 277-282 （in Chinese）.
2	KIM B S， LEE J G， HAN H S. Biased PNG law for impact with angular constraint［J］. IEEE Transactions on Aerospace and Electronic Systems， 1998， 34（1）： 277-288.
3	张友根，于德海，张友安. 基于时间最优的攻击角度控制研究［J］. 飞行力学， 2010， 28（2）： 46-50.
	ZHANG Y G， YU D H， ZHANG Y A. Study on time-optimal impact angle control［J］. Flight Dynamics， 2010， 28（2）： 46-50 （in Chinese）.
4	黄汉桥，周军，郭建国. 具有角度和时间约束的导弹最优全弹道设计［J］. 西北工业大学学报， 2010， 28（2）： 165-170.
	HUANG H Q， ZHOU J， GUO J G. Design and simulation of an optimal missile trajectory with constraints of impact time and impact angle［J］. Journal of Northwestern Polytechnical University， 2010， 28（2）： 165-170 （in Chinese）.
5	KIM T H， LEE C H， TAHK M J， et al. Biased PNG law for impact-time control［J］. Transactions of the Japan Society for Aeronautical and Space Sciences， 2013， 56（4）： 205-214.
6	KIM T H， LEE C H， JEON I S， et al. Augmented polynomial guidance with impact time and angle constraints［J］. IEEE Transactions on Aerospace and Electronic Systems， 2013， 49（4）： 2806-2817.
7	ARITA S， UENO S. Optimal feedback guidance for nonlinear missile model with impact time and angle constraints： AIAA-2013-4785［R］. Reston： AIAA， 2013.
8	LU P. Introducing computational guidance and control［J］. Journal of Guidance， Control， and Dynamics， 2017， 40（2）： 193.
9	WANG X Y， QUAN Z Y， ZHANG J J. Optimal 3-dimension trajectory-tracking guidance for reusable launch vehicle based on back-stepping adaptive dynamic programming［J］. Neural Computing and Applications， 2023， 35（7）： 5319-5334.
10	WAN S Z， CHANG X F， LI Q C， et al. Suboptimal midcourse guidance with terminal-angle constraint for hypersonic target interception［J］. International Journal of Aerospace Engineering， 2019， 2019： 1-13.
11	周聪，闫晓东，唐硕，等. 大气层内模型预测静态规划拦截中制导［J］. 航空学报， 2021， 42（11）： 524912.
	ZHOU C， YAN X D， TANG S， et al. Midcourse guidance for endo-atmospheric interception based on model predictive static programming［J］. Acta Aeronautica et Astronautica Sinica， 2021， 42（11）： 524912 （in Chinese）.
12	PAN B F， MA Y Y， YAN R. Newton-type methods in computational guidance［J］. Journal of Guidance， Control， and Dynamics， 2019， 42（2）： 377-383.
13	SHI W， JING Z L， YANG Y S， et al. A pseudospectral approach to ascent trajectory optimization for hypersonic air-breathing vehicles［C］∥ 2013 9th Asian Control Conference （ASCC）. Piscataway： IEEE Press， 2013： 1-6.
14	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.
15	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， 2022， 43（8）： 325433.
	LIU Z C， WANG J， HE S M， et al. A computational guidance algorithm for impact angle control based on predictor-corrector concept［J］. Acta Aeronautica et Astronautica Sinica， 2022， 43（8）： 325433 （in Chinese）.
16	PAN S J， YANG Q. A survey on transfer learning［J］. IEEE Transactions on Knowledge and Data Engineering， 2010， 22（10）： 1345-1359.
17	王育鹏，吕帅帅，杨宇，等. 基于域自适应的复合材料结构损伤识别方法［J］. 航空学报， 2022， 43（6）： 526752.
	WANG Y P， LYU S S， YANG Y， et al. Damage recognition of composite structures based on domain adaptive model［J］. Acta Aeronautica et Astronautica Sinica， 2022， 43（6）： 526752 （in Chinese）.
18	O’CONNELL M， SHI G Y， SHI X C， et al. Neural-fly enables rapid learning for agile flight in strong winds［J］. Science Robotics， 2022， 7（66）： eabm6597.
19	YE C C， YANG J X， DING H. High-accuracy prediction and compensation of industrial robot stiffness deformation［J］. International Journal of Mechanical Sciences， 2022， 233： 107638.
20	LIU C Y， GRYLLIAS K. Simulation-driven domain adaptation for rolling element bearing fault diagnosis［J］. IEEE Transactions on Industrial Informatics， 2022， 18（9）： 5760-5770.
21	ROSS I M， FAHROO F. A perspective on methods for trajectory optimization： AIAA-2002-4727［R］. Reston： AIAA， 2002.
22	FAHROO F， ROSS I M. Direct trajectory optimization by a Chebyshev pseudospectral method［J］. Journal of Guidance， Control， and Dynamics， 2002， 25（1）： 160-166.
23	SHI Y， WANG Z B. A deep learning-based approach to real-time trajectory optimization for hypersonic vehicles： AIAA-2020-0023［R］. Reston： AIAA， 2020.
24	MA Y C， ZHANG Z， YANG H L， et al. An adaptive adversarial domain adaptation approach for corn yield prediction［J］. Computers and Electronics in Agriculture， 2021， 187： 106314.
25	SILVESTRINI S， LAVAGNA M. Deep learning and artificial neural networks for spacecraft dynamics， navigation and control［J］. Drones， 2022， 6（10）： 270.

数据	数据大小	弹道条数
源域数据	718 318	5 500
目标域数据a	9 201	121
目标域数据b	5 087	55
目标域数据c	4 197	44
目标域数据d	3 375	33

[1]	Jiaqi LIU, Rongqian CHEN, Jinhua LOU, Xu HAN, Hao WU, Yancheng YOU. Aerodynamic shape optimization of high-speed helicopter rotor airfoil based on deep learning [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(9): 529828-529828.
[2]	Xudong LUO, Yiquan WU, Jinlin CHEN. Research progress on deep learning methods for object detection and semantic segmentation in UAV aerial images [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(6): 28822-028822.
[3]	Haiqiao LIU, Meng LIU, Zichao GONG, Jing DONG. A review of image matching methods based on deep learning [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(3): 28796-028796.
[4]	Xin SU, Runcheng GUAN, Qiao WANG, Weizheng YUAN, Xianglian LYU, Yang HE. Ice area and thickness detection method based on deep learning [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(S2): 729283-729283.
[5]	Liqun CHEN, Xu ZOU, Lei ZHANG, Yingpan ZHU, Gang WANG, Jinyong CHEN. On⁃board intelligent target detection technology based on domestic commercial components [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(S2): 728860-728860.
[6]	Pengyu LIU, Xueyao ZHU. Semantic parsing technology of air traffic control instruction in fusion airspace based on deep learning [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(S1): 727592-727592.
[7]	Lei HE, Weiqi QIAN, Kangsheng DONG, Xian YI, Congcong CHAI. Aerodynamic characteristics modeling of iced airfoil based on convolution neural networks [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(5): 126434-126434.
[8]	Peng DING, Yafei SONG. A cost-sensitive method for aerial target intention recognition [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(24): 328551-328551.
[9]	Xiaohang LI, Jianjiang ZHOU. Multi⁃scale modality fusion network based on adaptive memory length [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(22): 628977-628977.
[10]	Gongye YU, Weidong CAI, Minghui HU, Wencai LIU, Bo MA. Intelligent migration diagnosis of mechanical faults driven by hybrid fault mechanism and domain adaptation [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(2): 426800-426800.
[11]	Yunhe ZHAO, Shengnan WANG. Solution to stress intensity factor by weight function method based on deep learning [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(19): 228367-228367.
[12]	Shuyi GAO, Defu LIN, Duo ZHENG, Xinyu HU. Intelligent cooperative interception strategy of aircraft against cluster attack [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(18): 328301-328301.
[13]	Yubin YUAN, Yiquan WU, Langyue ZHAO, Jinlin CHEN, Qichang ZHAO. Research progress of UAV aerial video multi⁃object detection and tracking based on deep learning [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(18): 28334-028334.
[14]	Lianzi WANG, Ling WANG, Daiyin ZHU. An ISAR autofocus imaging algorithm based on FCN and transfer learing [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(17): 328172-328172.
[15]	Rongsheng ZHANG, Yansheng WU, Xudong QIN, Puzhuo ZHANG. A real⁃time in⁃flight wind estimation and prediction method based on deep learning [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(13): 327860-327860.

Impact-angle-constrained with time-minimum guidance algorithm based on transfer learning

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 23

References 25

Related Articles 15

Recommended Articles

Metrics

Comments