摘要
为了快速准确地分析稳定敌方航向并判断其攻击目标,提出了基于蚁狮优化算法(ALO)的自组织竞争(SOM)神经网络的航迹稳定分析方法。首先探究了航迹稳定分析的具体流程;然后提出并采用ALO-SOM神经网络提取航迹特征;最后,为了提高复杂线段拟合的准确性,采用分段线性拟合对特征进行处理,进而获取稳定的航向。仿真结果表明,ALO-SOM神经网络可以快速准确地提取航迹特征,SOM神经网络训练正常,分段线性拟合方法准确地获得了目标的稳定航向。
In order to fast and accurately analyze the steady course and judge the attack target of the enemy, an analysis model of trajectory stability based on antlion algorithm optimized(ALO) self organizing map(SOM) model is put forward. Firstly, the specific progress of steady course analysis is explored. Then, features of the track are extracted with ALO-SOM. Finally, the features are processed by piecewise linear fitting to improve the accuracy of complex line segment fitting, and then steady course can be reached. Experimental results show that ALO-SOM neural network can extract features of the track rapidly but accurately. Values of CV prove that SOM network operates well, method of piecewise linear fitting achieves the steady course soundly.
引文
[1] 王涛波,黄宝军.改进模糊聚类算法在航迹分析中的应用[J].中国安全科学学报,2014,24(2):23-27.
[2] Santanu D,Matthews B L,Robert L.Fleet level anomaly detection of aviation safety data[C]//2011 IEEE Conference Prognostics and Health Management.Montreal,QC,Canada:IEEE,2011:1-10.
[3] Gariel M,Srivastava A N,Feron E.Trajectory clustering and an application to airspace monitoring[J].IEEE Transactions on Intelligent Transportation Systems,2011,12(4):1511-1524.
[4] Wang C,Han Z H.Trajectory clustering method research and application[C]//Proceedings of 2011 International Conference on Transportation,Mechanical,and Electrical Engineering(TEMM).Changchun:IEEE,2012:97-100.
[5] Leiden K,Atkins S.Trajectory clustering for metroplex operations[R].AIAA-2011-7066,2011.
[6] Kohonen T.Self-organizing maps[J].Springer Series in Information Science,1995,30(4):266-270.
[7] Tomé A R,Miranda P M.Piecewise linear fitting and trend changing points of climate parameters[J].Geophysical Research Letters,2004,10(21):2207-2210.
[8] Mirjalili S.The ant lion optimizer[J].Advances in Engineering Software,2015,83(C):80-98.
[9] Kingma D P,Ba J.Adam:a method for stochastic optimization[C]//3rd International Conference for Learning Representations.San Diego,2015.