基于Hough变换和优化K均值聚类的反舰导弹编队识别目标选择方法

doi:10.12382/bgxb.2021.0660

摘要/Abstract

摘要：

现有反舰导弹编队识别技术存在侧重于队形识别而非目标选择、对编队末端态势变化考虑不足、实时性偏弱、未考虑队列线检测区间对聚类效果的影响和聚类数优化与聚类迭代过程相互独立等问题。基于Hough变换和优化K均值聚类算法,提出反舰导弹编队识别目标选择流程,构建V形、平行和环形编队目标生成与目标选择模型,旋转、缩放、冲淡式干扰和队型变化等编队目标变化模型。仿真结果表明,聚类数优化代价函数在关键聚类数段区分度明显、聚类数优化准确,移动检测区间检测解决正常检测区间两侧边缘样本点对应机制缺失问题,采用多样本更新聚类与单样本更新聚类结合的聚类迭代、聚类数优化迭代与聚类迭代融合迭代效率高,工程适用性强,对于反舰作战模拟具有重要意义。

关键词: 反舰导弹, Hough变换, 优化K均值聚类, 编队识别, 目标选择

Abstract:

For the formation recognition technology of anti-ship missiles, there are problems of focusing on formation recognition rather than target selection, insufficient consideration of the changes from terminal guidance stage to target indication stage, and relatively weak real-time performance and so on. The formation recognition target selection technology has replaced the single feature recognition target selection technology and become the mainstream of target selection for long-range anti-ship missile weapon systems based on Hough transform and optimized K-means clustering algorithm. A process of formation recognition and target selection for anti-ship missiles is proposed, and models on targets' generation, selection and changes, such as formation rotating, scaling, transforming and dilution jamming, of V-shaped, parallel and ring formations are built up. The simulation results show that: the cost function for optimal clustering number is more effective than the existing methods; the problem for the lack of transforming mechanism for the sample points on both sides of the normal detection interval is solved using the formation line detection on the moving detection interval; the clustering iteration, optimal iteration of clustering number, and fused cluster iteration by combining multi-sample update clustering with single-sample update clustering have higher efficiency and stronger engineering applicability, which is of great significance for anti-ship combat simulation.

Key words: anti-ship missile, Hough transform, optimized K-means clustering, formation recognition, target selection

中图分类号:

TP301.6

黄隽, 吴鹏飞, 李晓宝, 刘玥. 基于Hough变换和优化K均值聚类的反舰导弹编队识别目标选择方法[J]. 兵工学报, 2023, 44(2): 472-483.

HUANG Jun, WU Pengfei, LI Xiaobao, LIU Yue. Formation Recognition and Target Selection of Anti-ship Missile Based on Hough Transform and Optimized K-means Clustering[J]. Acta Armamentarii, 2023, 44(2): 472-483.

图/表 14

图1 V形编队及平行编队示意图

Fig.1 V-shaped and parallel warship formations

图2 环形编队及假目标菱形布阵模式示意图

Fig.2 Ring warship formation and rhombus array of fake targets

图3 目标指示阶段V形编队识别目标预选图

Fig.3 V-shaped formation recognition and target pre-selection in target indication stage

图4 各种聚类数优化方法比较

Fig.4 Comparison of optimal methods for clustering number

图5 末制导阶段V形编队识别目标选择图

Fig.5 V-shaped formation recognition and target confirmation in terminal guidance stage

图6 移动检测区间环形编队目标指示态势聚类参数空间图

Fig.6 Ring formation line detection on the moving detection interval in target indication stage

图7 移动检测区间环形编队目标指示态势识别图

Fig.7 Ring formation recognition and target pre-selection on the moving detection interval in target indication stage

图8 环形编队末制导雷达态势队形识别图

Fig.8 Ring formation recognition and target confirmation in terminal guidance stage

图9 原检测区间环形编队目标指示态势聚类参数空间图

Fig.9 Ring formation line detection on normal detection interval in target indication stage

图10 原检测区间环形编队目标指示态势识别图

Fig.10 Ring formation recognition and target pre-selection on normal detection interval in target indication stage

表1 V形编队位置误差对识别正确率影响

Table 1 Effects of location error of V-shaped formation on recognition rate

情况序号	x轴均方差	z轴均方差	识别正确率/%
1	0.1	0.1	99.9
2	0.1	0.2	99.2
3	0.1	0.3	97.3
4	0.1	0.4	96.1
5	0.2	0.1	91.3
6	0.2	0.2	88.9
7	0.2	0.3	87.6
8	0.3	0.1	84.5
9	0.3	0.2	81.5
10	0.3	0.3	81.0
11	0.4	0.1	80.2
12	0.4	0.2	79.9
13	0.4	0.3	78.1
14	0.4	0.4	77.5

表2 平行横队位置误差对识别正确率影响

Table 2 Effects of location error ofparallel formation on recognition rate

情况序号	x轴均方差	z轴均方差	识别正确率/%
1	0.1	0.1	80.4
2	0.1	0.2	76.8
3	0.1	0.3	87.0
4	0.1	0.4	90.8
5	0.2	0.1	77.1
6	0.2	0.2	78.4
7	0.2	0.3	87.5
8	0.3	0.1	79.1
9	0.3	0.2	77.1
10	0.3	0.3	83.1
11	0.4	0.1	76.7
12	0.4	0.2	75.1
13	0.4	0.3	76.0
14	0.4	0.4	71.2

表3 环形编队位置误差对识别正确率影响

Table 3 Effects of location error ofring formation on recognition rate

情况序号	x轴均方差	z轴均方差	识别正确率/%
1	0.1	0.1	96.0
2	0.1	0.2	81.2
3	0.1	0.3	74.6
4	0.2	0.1	77.4
5	0.2	0.2	70.6
6	0.3	0.1	61.8

表4 队型变化和位置误差对识别正确率影响

Table 4 Effects of formation transforming and location error on recognition rate

情况序号	X轴均方差	Z轴均方差	识别正确率/%
1	0.1	0.1	98.7
2	0.1	0.2	92.0
3	0.1	0.3	80.8
4	0.2	0.1	90.4
5	0.2	0.2	83.9
6	0.2	0.3	68.0
7	0.3	0.1	82.5
8	0.3	0.2	78.4
9	0.3	0.3	67.2

参考文献 21

[1]	SURYA V V S, LEONARD P. Multi-UAS formation recognition in dynamic environments[J]. Procedia Computer Science, 2020, 168:241-248. doi: 10.1016/j.procs.2020.02.260 URL
[2]	张昌芳, 杨宏文, 胡卫东, 等. 一种通用的阵群目标队形识别方法[J]. 系统工程与电子技术, 2010, 32(8):1703-1705.
	ZHANG C F, YANG H W, HU W D, et al. General formation recognition method for group targets[J]. Systems Engineering and Electronics, 2010, 32(8):1703-1705. (in Chinese)
[3]	沈建锋. 舰艇队形识别目标选择算法[J]. 火力与指挥控制, 2010, 35(9):98-100.
	SHEN J F. A target selection algorithm using naval ships formation identification[J]. Fire Control& Command Control, 2010, 35(9):98-100. (in Chinese)
[4]	宁云晖, 范晓虹, 李欣. 选择编队指定目标的一种新方法[J]. 火力与指挥控制, 2012, 37(11):85-89.
	NING Y H, FAN X H, LI X. Method of choosing assigned target in formatted ships[J]. Fire Control & Command Control, 2012, 37(11):85-89. (in Chinese)
[5]	董受全, 宋伟. 基于空间方向相似性的编队队形识别算法[J]. 火力与指挥控制, 2010, 35(11):167-169.
	DONG S Q, SONG W. Identification algorithm of combat warship formation based on similarity between spatial directions[J]. Fire Control & Command Control, 2010, 35(11):167-169. (in Chinese)
[6]	乔冰, 肖滨. 基于模板匹配的战斗舰艇队形自动识别研究[J]. 计算机仿真, 2006, 23(9):4-6.
	QIAO B, XIAO B. Identification of combat warship formation based on template matching[J]. Computer Simulation, 2006, 23(9):4-6. (in Chinese)
[7]	冷画屏, 关庆云, 吴晓锋. 基于领域知识的海上编队线型队形识别[J]. 舰船科学技术, 2013, 35(2):103-106.
	LENG H P, GUAN Q Y, WU X F. Recognition of naval fleet line type formation based on domain knowledge[J]. Ship Science and Technology, 2013, 35(2):103-106. (in Chinese)
[8]	饶佳人, 孙世庆, 李婷婷. 基于规则的空中作战编队识别[J]. 指挥信息系统与技术, 2021, 12(3):19-22.
	RAO J R, SUN S Q, LI T T. Rule-based formation identification of air combat[J]. Command Information System and Technology, 2021, 12(3):19-22. (in Chinese)
[9]	郑志国. 基于编队提取的SAR图像群目标识别方法研究[J]. 舰船电子工程, 2021, 41(3):30-32.
	ZHENG Z G. Research of group target recognition based on formation extraction for SAR image[J]. Ship Electronic Engineering, 2021, 41(3):30-32. (in Chinese)
[10]	CARLOTTO M J. MTI data clustering and formation recognition[J]. IEEE Transactions on Aerospace and Electronic Systems, 2001, 37(2):524-537. doi: 10.1109/7.937466 URL
[11]	蔡益朝, 张维明, 贺玲, 等. 一种基于Hough变换的线型群体队型识别方法[J]. 国防科技大学学报, 2006, 28(2):124-130.
	CAI Y C, ZHANG W M, HE L, et al. Formation recognition based on Hough transform[J]. Journal of National University of Defense Technology, 2006, 28(2):124-130. (in Chinese)
[12]	张翼飞, 董受全, 毕开波. 基于Hough变换和聚类的舰艇编队队形识别算法[J]. 兵工学报, 2016, 37(4):648-655. doi: 10.3969/j.issn.1000-1093.2016.04.011
	ZHANG Y F, DONG S Q, BI K B. Warship formation recognition algorithm based on Hough transform and clustering[J]. Acta Armamentarii, 2016, 37(4):648-655. (in Chinese)
[13]	刘文一, 孙伟, 朱良明, 等. 舰载飞行器打击水面舰艇编队队形识别和目标选择方法[J]. 兵器装备工程学报, 2020, 41(2):85-89.
	LIU W Y, SUN W, ZHU L M, et al. Study on formation recognition and target selection method of shipborne aircraft against warship formation[J]. Journal of Ordnance Equipment Engineering, 2020, 41(2):85-89. (in Chinese)
[14]	杨善林, 李永森, 胡笑旋, 等. K_MEANS算法中的k值优化问题研究[J]. 系统工程理论与实践, 2006, 26(2):97-101. doi: 10.12011/1000-6788(2006)2-97
	YANG S L, LI Y S, HU X X, et al. Optimization study on k value of K-means algorithm[J]. Systems Engineering-Theory & Practice, 2006, 26(2):97-101. (in Chinese)
[15]	于剑, 程乾生. 模糊聚类方法中的最佳聚类数的搜索范围[J]. 中国科学(E辑), 2002, 32(2):274-280.
	YU J, CHENG Q S. The range of optimal class number of fuzzy cluster[J]. Science of China (Series E), 2002, 32(2):274-280. (in Chinese)
[16]	姜苗苗, 史国友, 许栓梅, 等. 基于自适应K均值聚类和霍夫变换的船舶干舷视觉检测[J]. 上海海事大学学报, 2021, 42(2):34-39.
	JIANG M M, SHI G Y, XU S M, et al. Ship freeboard visual detection based on adaptive K-means clustering and Hough transform[J]. Journal of Shanghai Maritime University, 2021, 42(2):34-39. (in Chinese)
[17]	田立业, 刘剑, 鲍凯. 队形识别智能化方法定量分析[J]. 指挥控制与仿真, 2019, 41(6):18-23. doi: 10.3969/j.issn.1673-3819.2019.06.004
	TIAN L Y, LIU J, BAO K. Quantitatively analysis on formation identification intelligent method[J]. Command Control & Simulation, 2019, 41(6):18-23. (in Chinese)
[18]	孟光磊, 周铭哲, 朴海音, 等. 基于协同战术识别的双机编队威胁评估方法[J]. 系统工程与电子技术, 2020, 42(10):2285-2293.
	MENG G L, ZHOU M Z, PIAO H Y, et al. Threat assessment method of dual-aircraft formation based on cooperative tactical recognition[J]. Systems Engineering and Electronics, 2021, 42(2): 2285-2293. (in Chinese)
[19]	WANG W T, TANG Z Y, XIANG J T, et al. A sorties recognition algorithm of formation targets for wide-band radar[C]// Proceedings of the 2019 International Conference on Control,Automation and Information Sciences.Chengdu, China:IEEE, 2019:1-4.
[20]	LIN Z C, ZHANG X R, HAO N, et al. An LSTM-based fleet formation recognition algorithm[C]// Proceedings of the 2021 40th Chinese Control Conference. Shanghai, China:IEEE, 2021:8565-8569.
[21]	HUANG J, WU P F, LI X B. Research on dynamically corrective hit probability model of anti-air missile integrated in war game system[J]. Engineering Letters, 2022, 30(2):757-763.