AdaBoost-PSO-LSTM网络实时预测机动轨迹

doi:10.12305/j.issn.1001-506X.2021.06.23

摘要/Abstract

摘要：

针对自主空战中轨迹预测难以同时保持高预测精度和短预测时间的问题, 提出一种自适应增强的粒子群优化长短期记忆网络预测方法。首先，建立三自由度无人机动力学模型, 解决机动轨迹的数据来源问题。其次，分析长短期记忆网络, 并引入在线预测的滑动模块输入矩阵, 利用粒子群优化算法代替传统基于时间的反向传播算法进行网络内部权值更新; 同时为解决优化算法非定向性问题, 提出数据共享方法。然后，为进一步提高预测精度, 采用自适应增强算法搭建外框架, 通过控制弱预测器的数量平衡预测精度与预测时间。最后, 在一段变化较为频繁的轨迹进行预测, 与5种神经网络预测方法进行比较, 结果表明所提方法能够较好地满足精度和时间要求。

关键词: 轨迹预测, 粒子群优化长短期记忆网络, 动力学模型, 无人机

Abstract:

To solve the problem that trajectory prediction is difficult to maintain high prediction accuracy and short prediction time in autonomous air combat, an AdaBoost particle swarm optimization for long and short term memory network prediction method is proposed. Firstly, the dynamic model of unmanned aerial vehicle with three degrees of freedom is established to solve the problem of data source of maneuver trajectory. Secondly, the long and short term memory network is analyzed, and the sliding module input matrix of online prediction is introduced. Particle swarm optimization algorithm is used to replace the traditional back propagation algorithm through time to update the internal weights of the network. Meanwhile, in order to solve the problem of non-orientation of the optimization algorithm, a data sharing method is proposed. Then, in order to further improve the prediction accuracy, AdaBoost algorithm is used to build the outer framework, and the prediction accuracy and prediction time are balanced by controlling the number of weak predictors. Finally, compared with five neural network prediction methods in a period of more frequent changes in the trajectory prediction, the results show that the proposed method can meet the requirements of accuracy and time.

Key words: trajectory prediction, particle swarm optimization for long and short term memory network, dynamic model, unmanned aerial vehicle

中图分类号:

V247.5

谢磊, 丁达理, 魏政磊, 汤安迪, 张鹏. AdaBoost-PSO-LSTM网络实时预测机动轨迹[J]. 系统工程与电子技术, 2021, 43(6): 1651-1658.

Lei XIE, Dali DING, Zhenglei WEI, Andi TANG, Peng ZHANG. Real time prediction of maneuver trajectory for AdaBoost-PSO-LSTM network[J]. Systems Engineering and Electronics, 2021, 43(6): 1651-1658.

图/表 10

图1

图2

图3

图4

图5

图6

表1

图7

图8

图9

参考文献 31

1	SLATTERY R , ZHAO Y . Trajectory synthesis for air traffic automation[J]. Journal of Guidance, Control, and Dynamics, 1997, 20 (2): 232- 238. doi: 10.2514/2.4056
2	LYMPEROPOULOS I, LYGEROS J. Adaptive aircraft trajectory prediction using particle filters[C]//Proc. of the AIAA Guidance, Navigation & Control Conference & Exhibit, 2008.
3	ZHAO K G , WANG C X , XIAO G Q , et al. Research for nonlinear model predictive controls to laterally control unmanned vehicle trajectory tracking[J]. Applied sciences, 2020, 10, 6034. doi: 10.3390/app10176034
4	WANG X , JINAG X W , WU Y . A second-order HMM trajectory prediction method based on the spark platform[J]. Journal of Information Hiding and Multimedia Signal Processing, 2019, 10 (2): 346- 358.
5	MATHEW W, RAPOSO R, MARTINS B. Predicting future locations with hidden Markov models[C]//Proc. of the ACM Conference on Ubiquitous Computing, 2012: 911-918.
6	ZHANG K , XIONG J J , LI F . Bayesian trajectory prediction for a hypersonic gliding reentry vehicle based on intent inference[J]. Journal of Astronautics, 2018, 39, 1262- 1265.
7	王新, 杨任农, 左家亮. 基于HPSO-TPFENN的目标机轨迹预测[J]. 西北工业大学学报, 2019, 37 (3): 612- 619. doi: 10.3969/j.issn.1000-2758.2019.03.025
	WANG X , YANG R N , ZUO J L . Trajectory prediction of target aircraft based on HPSO-TPFENN neural network[J]. Journal of Northwestern Polytechnical University, 2019, 37 (3): 612- 619. doi: 10.3969/j.issn.1000-2758.2019.03.025
8	PAN T L , SUMALEE A , ZHONG R X , et al. Short-term traffic state prediction based on temporal-spatial correlation[J]. IEEE Trans.on Intelligent Transportation Systems, 2013, 14 (3): 1242- 254. doi: 10.1109/TITS.2013.2258916
9	乔少杰, 金琨, 韩楠. 一种基于高斯混合模型的轨迹预测算法[J]. 软件学报, 2015, 26 (5): 1048- 1063.
	QIAO S J , JIN K , HAN N . Trajectory prediction algorithm based on Gaussian mixture model[J]. Journal of Software, 2015, 26 (5): 1048- 1063.
10	WANG Q Y , ZHANG Z L , WANG Z Y , et al. The trajectory prediction of spacecraft by grey method[J]. Measurement Science and Technology, 2016, 27 (8): 085011- 085021. doi: 10.1088/0957-0233/27/8/085011
11	QIAO S J , SHEN D Y , WANG X T , et al. A self-adaptive parameter selection trajectory prediction approach via hidden markova models[J]. IEEE Trans.on Intelligent Transportation Systems, 2015, 16 (1): 284- 296. doi: 10.1109/TITS.2014.2331758
12	MA L , TIAN S . A hybrid CNN-LSTM model for aircraft 4D trajectory prediction[J]. IEEE Access, 2020, 8, 134668- 134680. doi: 10.1109/ACCESS.2020.3010963
13	WEI L Z , ZHI B Q , ZHAO Z Y . A deep learning approach for aircraft trajectory prediction in terminal airspace[J]. IEEE Access, 2020, 8, 151250- 151266. doi: 10.1109/ACCESS.2020.3016289
14	李明晓, 张恒才, 仇培元, 等. 一种基于模糊长短期神经网络的移动对象轨迹预测算法[J]. 测绘学报, 2018, 47 (12): 1660- 1669. doi: 10.11947/j.AGCS.2018.20170268
	LI M X , ZHANG H C , QIU P Y , et al. Predicting future locations with deep fuzzy-lstm network[J]. Acta Geodaetica et Cartographica Sinca, 2018, 47 (12): 1660- 1669. doi: 10.11947/j.AGCS.2018.20170268
15	VIRTANEN K , RAIVIO T . Modeling pilot's sequential maneuvering decisions by a multistage influence diagram[J]. Journal of Guidance, Control, and Dynamics, 2004, 27 (4): 665- 677. doi: 10.2514/1.11167
16	LECUN Y , BENGIO Y , HINTON G . Deeplearning[J]. Nature, 2015, 521, 436- 444. doi: 10.1038/nature14539
17	TONG Y , LIU Y L , WANG J , et al. Text steganography on RNN-generated lyrics[J]. Mathematical Bioences and Engineering, 2019, 16 (5): 5451- 5463.
18	YANG Y , ZHOU M Y , FANG Q W , et al. AnnoFly: annotating Drosophila embryonic images based on an attention-enhanced RNN model[J]. Bioinformatics, 2019, 35 (16): 2834- 2842. doi: 10.1093/bioinformatics/bty1064
19	SON G , KWON S , PARK N . Gender classification based on the non-lexical cues of emergency calls with recurrent neural networks (RNN)[J]. Symmetry, 2019, 11 (4): 525- 539. doi: 10.3390/sym11040525
20	杨丽, 吴雨茜, 王俊丽. 循环神经网络研究综述[J]. 计算机应用, 2018, 38 (S2): 1- 6, 26.
	YANG L , WU Y X , WANG J L . Research on recurrent neural network[J]. Journal of Computer Applications, 2018, 38 (S2): 1- 6, 26.
21	KUANG J W , YANG H Z , LIU J J , et al. Dynamic prediction of cardiovascular disease using improved LSTM[J]. International Journal of Crowd Science, 2019, 3 (1): 14- 25. doi: 10.1108/IJCS-01-2019-0002
22	WANG P X , WANG H E , ZHANG H C , et al. A hybrid Markov and LSTM model for indoor location prediction[J]. IEEE Access, 2019, 7, 185928- 185940. doi: 10.1109/ACCESS.2019.2961559
23	JIANG Q, TANG C L, CHEN C, et al. Stock price forecast based on lstm neural network[C]//Proc. of the 12th International Conference on Management Science and Engineering Management, 2019: 393-408.
24	GU L L , LIU Y , ZHEN J Q . Optimization of PSO algorithm based on adaptive inertia weight and escape strategy[J]. Journal of Physics: Conference Series, 2020, 1486 (3): 032033- 032039.
25	李牧东, 赵辉, 翁兴伟. 基于最优高斯随机游走和个体筛选策略的差分进化算法[J]. 控制与决策, 2016, 31 (8): 1379- 1386.
	LI M D , ZHAO H , WENG X W . Differential evolution based on optimal Gaussian random walk and individual selection strategies[J]. Control and Decision, 2016, 31 (8): 1379- 1386.
26	SUN S L , WEI Y J , WANG S Y . AdaBoost-LSTM ensemble learning for financial time series forecasting[J]. Computational Science-ICCS, 2018, 10862, 590- 597.
27	ZHANG Y Y , JIA Y X , WU W Y , et al. A diagnosis method for the compound fault of gearboxes based on multi-feature and BP-AdaBoost[J]. Symmetry, 2020, 12 (3): 461- 480. doi: 10.3390/sym12030461
28	TAHERKHANIA A , COSMAB G , MCGINNITYCD T M . AdaBoost-CNN: an adaptive boosting algorithm for convolutional neural networks to classify multi-class imbalanced datasets using transfer learning[J]. Neurocomputing, 2020, 404, 351- 366. doi: 10.1016/j.neucom.2020.03.064
29	SUI X J , LI M Y , YING Y L , et al. Aerolysin nanopore identification of single nucleotides using the adaboost model[J]. Journal of Analysis & Testing, 2019, 3, 134- 139. doi: 10.1007/s41664-019-00088-x
30	毛景慧. 基于LSTM深度神经网络的股市时间序列预测精度的影响因素研究[D]. 广州: 暨南大学.
	MAO J H. Research on influencing factors of stock market time series prediction accuracy based on lstm deep neural network[D]. Guangzhou: Jinan University.
31	BIAU G , CADRE B , ROUVIÈRE L . Accelerated gradient boosting[J]. Machine Learning, 2019, 108 (6): 971- 992. doi: 10.1007/s10994-019-05787-1

K值	误差/m					误差均值/m	时间均值/s
K值	1	2	3	4	5	误差均值/m	时间均值/s
1	66.7	42.9	50.7	57.9	47.7	53.2	0.038
2	30.3	23.4	35.9	30.8	30.5	30.2	0.049
3	14.9	31.6	30.7	27.0	15.3	23.9	0.063
4	17.6	20.4	25.9	18.8	19.4	20.4	0.075
5	14.3	15.3	16.2	16.7	15.6	15.6	0.087
6	13.3	13.1	14.9	13.3	12.8	13.5	0.102

[1]	孙田野, 孙伟, 吴建军. 改进Quatre算法的无人机编队快速集结方法[J]. 系统工程与电子技术, 2022, 44(9): 2840-2848.
[2]	余婧, 雍恩米, 陈汉洋, 郝东, 张显才. 面向多无人机协同对地攻击的双层任务规划方法[J]. 系统工程与电子技术, 2022, 44(9): 2849-2857.
[3]	徐星光, 王晓峰, 姚璐, 任章. 固定翼无人机编队构型与通信拓扑优化[J]. 系统工程与电子技术, 2022, 44(9): 2936-2946.
[4]	杨建峰, 肖和业, 李亮, 白俊强, 董维浩. 基于模糊聚类和专家评分机制的无人机多层次模块划分方法[J]. 系统工程与电子技术, 2022, 44(8): 2530-2539.
[5]	卢元杰, 刘志敏, 孙智孝, 阚东. 基于模型的无人机系统架构综合评估方法[J]. 系统工程与电子技术, 2022, 44(4): 1239-1245.
[6]	李洪瑶, 李小强, 韩心中, 谢学立, 席建祥. 基于决策融合的多无人机协同目标检测识别算法[J]. 系统工程与电子技术, 2022, 44(3): 746-754.
[7]	张源原, 高阳, 朱鹏, 刘锦涛, 谷树山. 基于着色Petri网的无人机侦察战术规划[J]. 系统工程与电子技术, 2022, 44(3): 900-907.
[8]	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.
[9]	余雪勇, 朱烨, 邱礼翔, 朱洪波. 基于无人机辅助边缘计算系统的节能卸载策略[J]. 系统工程与电子技术, 2022, 44(3): 1022-1029.
[10]	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.
[11]	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.
[12]	陈都, 孟秀云. 基于自适应郊狼算法的无人机离线航迹规划[J]. 系统工程与电子技术, 2022, 44(2): 603-611.
[13]	刘步花, 丁丹, 杨柳, 薛乃阳, 刘仲谦. 基于DNN的无人机数据OFDM传输技术[J]. 系统工程与电子技术, 2022, 44(2): 696-702.
[14]	吴志鹏, 张平, 李震, 黄磊, 刘畅, 高硕. 基于轻小型无人机雷达的植被高度反演方法[J]. 系统工程与电子技术, 2022, 44(12): 3667-3675.
[15]	王玉佳, 方伟, 徐涛, 余应福, 邓博元. 基于遗传模糊树的海空对抗无人机智能决策模型[J]. 系统工程与电子技术, 2022, 44(12): 3756-3765.