基于EMD-DESN的无人机集群航迹目的地预测

doi:10.12305/j.issn.1001-506X.2024.01.33

摘要/Abstract

摘要：

无人机(unmanned aerial vehicle, UAV)集群作战样式多样、运动模式复杂, 导致集群航迹目的地难以预测。为解决上述问题, 本文提出了一种基于经验模态分解(empirical mode decomposition, EMD)和深度回声状态网络(deep echo state network, DESN)的UAV集群航迹目的地预测算法。为使集群运动模型更真实地模拟UAV集群作战过程, 本文引入航向误差时变方差, 改进了Olfati-Saber集群运动模型的虚拟领导项。为处理因群内的协同作用和集群航向误差导致的运动非平稳性, 引入了EMD, 对UAV航迹序列进行重构。考虑到获知航迹的时序性, 设计了滑窗结构, 采用DESN对重构航迹的不同时段进行目的地预测。仿真实验结果表明, 本文提出的EMD-DESN算法较基本DESN算法能以更高的准确度预测UAV集群航迹目的地, 并能更早地实现稳定的正确预测。

关键词: 无人机集群, 目的地预测, 深度回声状态网络, 经验模态分解, 改进Olfati-Saber模型

Abstract:

The unmanned aerial vehicle (UAV) cluster has various combat styles and complex movement modes, which makes it difficult to predict the cluster trajectory destination. To solve the above problems, we propose a UAV cluster trajectory destination prediction algorithm based on empirical mode decomposition (EMD) and deep echo state network (DESN) in this paper. In order to make the cluster movement model more realistic to simulate the UAV cluster combat process, we introduce the time-varying variance of heading error, and improves the virtual leadership term of Olfati-Saber cluster movement model. In order to deal with the non-stationary motion caused by the coordination within the cluster and the cluster heading error, EMD is introduced to reconstruct the UAV trajectory sequence. Considering the timing of the acquired trajectory, the sliding window structure is designed, and the DESN is used to predict the destination in different periods of the reconstructed trajectory. The simulation results show that the EMD-DESN algorithm proposed in this paper can predict the UAV cluster trajectory destination with higher accuracy than the basic DESN algorithm, and can achieve stable and correct prediction earlier.

Key words: unmanned aerial vehicle (UAV) cluster, destination prediction, deep echo state network (DESN), empirical mode decomposition (EMD), improved Olfati-Saber mode

中图分类号:

TN911.7

薛锡瑞, 黄树彩, 韦道知, 吴建峰. 基于EMD-DESN的无人机集群航迹目的地预测[J]. 系统工程与电子技术, 2023, 46(1): 290-299.

Xirui XUE, Shucai HUANG, Daozhi WEI, Jianfeng WU. Destination prediction of UAV cluster trajectory based on EMD-DESN[J]. Systems Engineering and Electronics, 2023, 46(1): 290-299.

图/表 16

图1

图2

图3

图4

表1

图5

图6

图7

表2

图8

图9

图10

图11

表3

表4

图12

参考文献 38

1	BORDEAUX J. Self-organized air tasking: examining a non-hierarchical model for joint air operations[R]. Fairfax: SRA International Inc., 2004.
2	党爱国, 王坤, 王延密, 等. 无人机集群作战概念发展对未来战场攻防影响[J]. 战术导弹技术, 2019, 193 (1): 37- 41.
	DANG A G , WANG K , WANG Y M , et al. The impact of UAVs swarming fighting concept development on attack and defense in future battlefield[J]. Tactical Missile Technology, 2019, 193 (1): 37- 41.
3	葛顺, 夏学知. 用于战术意图识别的动态序列贝叶斯网络[J]. 系统工程与电子技术, 2014, 36 (1): 76- 83.
	GE S , XIA X Z . DSBN used for recognition of tactical intention[J]. Systems Engineering and Electronics, 2014, 36 (1): 76- 83.
4	GUO L , CHEN F , GAO C , et al. Performance measurement model of multi-source data fusion based on network situation awareness[J]. Przegląd Elektrotechniczny, 2012, 88 (7): 315- 319.
5	熊伟, 何友. 信息融合系统中的态势预测技术[J]. 火力与指挥控制, 2001, 26 (4): 47- 50. doi: 10.3969/j.issn.1002-0640.2001.04.012
	XIONG W , HE Y . Research situation prediction in data fusion system[J]. Fire Control & Command Control, 2001, 26 (4): 47- 50. doi: 10.3969/j.issn.1002-0640.2001.04.012
6	XUE X R , HUANG S C , XIE J H , et al. Resolvable cluster target tracking based on the DBSCAN clustering algorithm and labeled RFS[J]. IEEE Access, 2021, 9, 43364- 43377. doi: 10.1109/ACCESS.2021.3066629
7	REYNOLDS C W. Flocks, herds and schools: a distributed behavioral model[C]//Proc. of the 14th Annual Conference on Computer Graphics and Interactive Techniques, 1987: 25-34.
8	VICSEK T , CZIROK A , BEN-JACOB E , et al. Novel type of phase transition in a system of self-driven particles[J]. Physical Review Letters, 1995, 75, 1226- 1229. doi: 10.1103/PhysRevLett.75.1226
9	COUZIN I , KRAUSE J , FRANKS N , et al. Effective leadership and decision-making in animal groups on the move[J]. Nature, 2005, 433 (7025): 513- 516. doi: 10.1038/nature03236
10	DENG C , WEN C Y , HUANG J S , et al. Distributed observer- based cooperative control approach for uncertain nonlinear MASs under event-triggered communication[J]. IEEE Trans. on Automatic Control, 2022, 67 (5): 2669- 2676. doi: 10.1109/TAC.2021.3090739
11	YU J L , DONG X W , LI Q D , et al. Fully adaptive practical time-varying output formation tracking for high-order nonlinear stochastic multiagent system with multiple leaders[J]. IEEE Trans. on Cybernetics, 2021, 51 (4): 2265- 2277. doi: 10.1109/TCYB.2019.2956316
12	WANG Y W , LIU X K , XIAO J W , et al. Output formation- containment of interacted heterogeneous linear systems by distributed hybrid active control[J]. Automatica, 2018, 93, 26- 32. doi: 10.1016/j.automatica.2018.03.020
13	LI W H , ZHANG H G , GAO Z Y , et al. Fully distributed event/self-triggered bipartite output formation-containment tracking control for heterogeneous multiagent systems[J]. IEEE Trans. on Neural Networks and Learning Systems, 2023, 34 (10): 7851- 7860. doi: 10.1109/TNNLS.2022.3146814
14	OLFATI-SABER R . Flocking for multi-agent dynamic systems: algorithms and theory[J]. IEEE Trans. on Automatic Control, 2006, 51 (3): 401- 420. doi: 10.1109/TAC.2005.864190
15	SORIA E, SCHIANO F, FLOREANO D. SwarmLab: a MATLAB drone swarm simulator[C]//Proc. of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2020: 8005-8011.
16	FU Q , LIANG X , ZHANG J , et al. Intent inference based trajectory prediction and smooth for UAS in low-altitude airspace with geofence[J]. Computers, Materials and Continua, 2020, 62 (3): 417- 444. doi: 10.32604/cmc.2020.07044
17	郭小宾, 王壮, 胡卫东. 基于贝叶斯网络的目标融合识别方法研究[J]. 系统仿真学报, 2005, 17 (11): 144- 147.
	GUO X B , WANG Z , HU W D . Information fusion with Bayesian networks for target recognition[J]. Journal of System Simulation, 2005, 17 (11): 144- 147.
18	薛锡瑞, 黄树彩, 韦道知. 基于桥接分布的无人机集群作战意图推断[J]. 北京航空航天大学学报, 2023, 49.
	XUE X R , HUANG S C , WEI D Z . Operational intention inference of UAV cluster based on bridging distributions[J]. Journal of Beijing University of Aeronautics and Astronautics, 2023, 49 (10): 2679- 2688.
19	HOSSEINI S , IVANOV D . Bayesian networks for supply chain risk, resilience and ripple effect analysis: a literature review[J]. Expert Systems with Applications, 2020, 161, 113649. doi: 10.1016/j.eswa.2020.113649
20	FAN S , ZHANG J , BLANCO-DAVIS E , et al. Maritime accident prevention strategy formulation from a human factor perspective using Bayesian networks and TOPSIS[J]. Ocean Engineering, 2020, 210, 107544. doi: 10.1016/j.oceaneng.2020.107544
21	乔殿峰, 梁彦, 马超雄, 等. 多域作战下的群目标意图识别与预测[J]. 系统工程与电子技术, 2022, 44 (11): 3403- 3412. doi: 10.12305/j.issn.1001-506X.2022.11.15
	QIAO D F , LIANG Y , MA C X , et al. Recognition and prediction of group target intention in multi-domain operations[J]. Systems Engineering and Electronics, 2022, 44 (11): 3403- 3412. doi: 10.12305/j.issn.1001-506X.2022.11.15
22	那晓栋, 王嘉宁, 刘墨燃, 等. 基于层次化可塑性回声状态网络的混沌时间序列预测[J]. 控制与决策, 2023, 38 (1): 133- 142.
	NA X D , WANG J N , LIU M R , et al. Hierarchical plasticity echo state network for chaotic time series prediction[J]. Control and Decision, 2023, 38 (1): 133- 142.
23	CLAUDIO G , ALESSIO M , LUCA P . Design of deep echo state networks[J]. Neural Networks, 2018, 108, 33- 47. doi: 10.1016/j.neunet.2018.08.002
24	KIM T , KING B R . Time series prediction using deep echo state networks[J]. Neural Computing and Applications, 2020, 32, 3- 4.
25	SONG Z , WU K , SHAO J . Destination prediction using deep echo state network[J]. Neurocomputing, 2020, 406, 343- 353. doi: 10.1016/j.neucom.2019.09.115
26	WU Z , LI Q , XIA X H . Multi-timescale forecast of solar irradiance based on multi-task learning and echo state network approaches[J]. IEEE Trans. on Industrial Informatics, 2020, 17 (1): 300- 310.
27	LONG J Y , ZHANG S H , LI C . Evolving deep echo state networks for intelligent fault diagnosis[J]. IEEE Trans. on Industrial Informatics, 2019, 16 (7): 4928- 4937.
28	HUANG N E , SHEN Z , LONG S R , et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences, 1998, 454 (1971): 903- 995. doi: 10.1098/rspa.1998.0193
29	XI X G , WU H , LUO Z Z . De-noising method of the SEMG based on EMD autocorrelation[J]. Chinese Journal of Scientific Instrument, 2014, 35 (11): 2494- 2500.
30	SUN Z Y , XI X G , YUAN C M , et al. Surface electromyography signal denoising via EEMD and improved wavelet thresholds[J]. Mathematical Biosciences and Engineering, 2020, 17 (6): 6945- 6962. doi: 10.3934/mbe.2020359
31	马愈昭, 刘逵, 张岩峰, 等. CEEMD结合改进小波阈值的激光雷达信号去噪算法[J]. 系统工程与电子技术, 2023, 45 (1): 93- 100.
	MA Y Z , LIU K , ZHANG Y F , et al. Laser radar signal denoising algorithm based on CEEMD combined with improved wavelet threshold[J]. Systems Engineering and Electronics, 2023, 45 (1): 93- 100.
32	王粟, 江鑫, 曾亮, 等. 基于VMD-DESN-MSGP模型的超短期光伏功率预测[J]. 电网技术, 2020, 44 (3): 917- 926.
	WANG S , JIANG X , ZENG L , et al. Ultra-short-term photovoltaic power prediction based on VMD-DESN-MSGP model[J]. Power System Technology, 2020, 44 (3): 917- 926.
33	STRANDBURG-PESHKIN A , TWOMEY C R , BODE N W F , et al. Visual sensory networks and effective information transfer in animal groups[J]. Current Biology, 2013, 23 (17): 709- 711. doi: 10.1016/j.cub.2013.07.059
34	BALLERINI M , CABIBBO N , CANDELIER R , et al. Interaction ruling animal collective behavior depends on topological rather than metric distance: evidence from a field study[J]. Proceedings of the National Academy of Sciences, 2007, 105 (4): 1232- 1237.
35	OLFATI-SABER R, MURRAY R M. Flocking with obstacle avoidance: cooperation with limited communication in mobile networks[C]//Proc. of the IEEE 42nd Conference Decision and Control, 2003: 2022-2028.
36	GALLICCHIO C , MICHELI A , PEDRELLI L . Deep reservoir computing: a critical experimental analysis[J]. Neurocomputing, 2017, 268, 87- 99. doi: 10.1016/j.neucom.2016.12.089
37	CHEW J Y , KURABAYASHI D , NAKAMURA Y . Echo state networks with Tikhonov regularization: optimization using integral gain[J]. Advanced Robotics, 2015, 29 (12): 801- 814. doi: 10.1080/01691864.2015.1010576
38	NEVITT J , HANCOCK G R . Improving the root mean square error of approximation for nonnormal conditions in structural equation modeling[J]. The Journal of Experimental Education, 2000, 68 (3): 251- 268. doi: 10.1080/00220970009600095

目的地	坐标(x, y)/m
D₁	(1 400, 2 040)
D₂	(1 960, 2 500)
D₃	(2 560, 3 360)
D₄	(2 880, 2 940)
D₅	(3 440, 2 680)

模态	v_x中心频率	v_y中心频率
IMF1	2.56	2.81
IMF2	1.06	1.04
IMF3	0.34	0.67
IMF4	0.19	0.31
IMF5	0.14	0.20
IMF6	0.14	0.14

算法	时刻/s
算法	20	40	60	80	100
DESN	276.3	423.3	216.9	209.0	88.3
EMD-ESN	288.3	432.0	306.0	329.0	70.6
EMD-DESN	235.6	392.9	162.3	180.6	83.5
EMD效果/%	14.7	7.2	25.2	13.6	5.4

算法	第1次	第2次
DESN	14.3	56.2
EMD-ESN	-	83.2
EMD-DESN	7.5	55.7

[1]	齐小刚, 周雨桐, 刘立芳. 无人机集群对地作战任务可靠性评估[J]. 系统工程与电子技术, 2023, 45(9): 2971-2978.
[2]	张书衡, 翟茹萍, 刘永凯. 基于通信域和雷达域融合特征的无人机集群类型识别算法[J]. 系统工程与电子技术, 2023, 45(12): 3734-3742.
[3]	罗瑞宁, 黄树彩, 赵岩, 张振. 子母导弹反无人机集群制导策略[J]. 系统工程与电子技术, 2023, 45(10): 3249-3258.
[4]	吴宗收, 汪立新, 沈强, 李灿, 李文华. 基于CEEMD半球谐振陀螺输出预测方法[J]. 系统工程与电子技术, 2023, 45(10): 3259-3264.
[5]	翟茹萍, 张书衡, 平嘉蓉. 复杂多径环境下的无人机集群通信波形识别[J]. 系统工程与电子技术, 2023, 45(10): 3312-3320.
[6]	马愈昭, 刘逵, 张岩峰, 冯帅, 熊兴隆. CEEMD结合改进小波阈值的激光雷达信号去噪算法[J]. 系统工程与电子技术, 2023, 45(1): 93-100.
[7]	谷旭平, 唐大全. 基于联邦滤波算法的无人机集群分层协同导航[J]. 系统工程与电子技术, 2022, 44(3): 967-976.
[8]	杨兴家, 段克清, 李想, 祁炜. 无人机集群协同探测距离解模糊方法[J]. 系统工程与电子技术, 2022, 44(2): 480-489.
[9]	符小卫, 潘静. 无人机集群规避动态障碍物的分布式队形控制[J]. 系统工程与电子技术, 2022, 44(2): 529-537.
[10]	时艳玲, 刘子鹏, 张学良, 顾为亮. 基于EMD能量占比的海面漂浮小目标特征检测[J]. 系统工程与电子技术, 2021, 43(2): 300-310.
[11]	彭正红, 杨德贵, 王行, 王浩, 朱政亮. 基于趋势估计的微多普勒分离与特征提取算法[J]. 系统工程与电子技术, 2021, 43(12): 3452-3461.
[12]	管灵, 朱晨曦, 董纯柱, 殷红成. 基于模式/区域分解的无人机集群电磁特性快速分析[J]. 系统工程与电子技术, 2021, 43(10): 2697-2705.
[13]	贾高伟, 王建峰. 无人机集群任务规划方法研究综述[J]. 系统工程与电子技术, 2021, 43(1): 99-111.
[14]	顾凌枫, 何明, 陈国友, 季敏惠, 刘锦涛. 无人机集群系统弹性研究[J]. 系统工程与电子技术, 2021, 43(1): 156-162.
[15]	张丹娜, 钱锋, 冯辉, 闻年成. Walsh码软扩频信号降噪算法[J]. 系统工程与电子技术, 2020, 42(4): 773-780.