雷达辐射源信号识别的效能综合评估方法

doi:10.19665/j.issn1001-2400.2019.06.001

摘要/Abstract

摘要：

针对现有评估方法存在指标权重设置不科学、评估方法不合理等问题,提出了一种雷达辐射源信号识别的效能综合评估方法。该方法首先根据雷达辐射源信号识别的效果,建立效能评估指标体系;然后在评估准则下,采用直觉模糊网络分析法对具有关联性特点的指标进行分析,并求解其指标权重;最后在区间犹豫模糊思想的基础上,结合消去与选择转换法和逼近理想排序法建立级别优先关系,从而实现雷达辐射源信号识别的效能综合评估。仿真结果表明,该方法可以得出合理的雷达辐射源信号识别方法效能的评估顺序。与现有方法相比,所提方法可以有效地解决指标相互关联的问题,并且可避免因评估方法的缺陷造成的错误评估。

关键词: 雷达信号识别, 效能评估, 直觉模糊网络分析法, 消去与选择转换法, 逼近理想排序法

Abstract:

Aiming at the problems of the existing evaluation methods, such as unscientific index weight setting and unreasonable evaluation method, a method for comprehensive evaluation of the radar radiation source signal identification efficiency is proposed. The performance evaluation index system based on the effect of radar radiation source signal recognition is first established. And then, under the evaluation criteria, an intuitionistic fuzzy network analysis method is used to analyze the indexes with the characteristics of relevance to solve the index weight. Finally, on the basis of the interval-valued hesitant fuzzy idea, the ranking priority relation is established by combining the elimination and selection conversion method and approximate ideal ranking method to realize the comprehensive evaluation of the effectiveness of radar radiation source signal identification. Simulation results show that the method proposed can obtain a reasonable evaluation order of the effectiveness of the radar source signal identification method. Compared with the existing methods, the proposed method can reasonably and effectively solve the problem of index correlation, and avoid the error evaluation caused by the defects of the evaluation method.

Key words: radar signal recognition, effectiveness evaluation, intuitionistic fuzzy network analysis, elimination and selection conversion, method, approximate ideal ranking method

中图分类号:

TN974

刘明骞,孟燕,张卫东. 雷达辐射源信号识别的效能综合评估方法[J]. 西安电子科技大学学报, 2019, 46(6): 1-8.

LIU Mingqian,MENG Yan,ZHANG Weidong. Method for comprehensive evaluation of effectiveness of radar emitter signals recognition[J]. Journal of Xidian University, 2019, 46(6): 1-8.

图/表 4

图1

图2

表1

表2

参考文献 16

[1]	MANTUSZEWSKI J. Radar Signal Identification Using a Neural Network and Pattern Recognition Methods[C]//Proceedings of the 2018 14th International Conference on Advanced Trends in Radio-electronics, Telecommunications and Computer Engineering. Piscataway: IEEE, 2018: 79-83.
[2]	CHEN X J, LI D, YANG X B , et al. Radar Emitter Signals Identification with a Optimal Recurrent Type 2 Wavelet Fuzzy Neural Network[J]. International Journal of Aeronautical and Space Sciences, 2018,9(3):685-693.
[3]	黄颖坤, 金炜东, 葛鹏 , 等. 基于多尺度信息熵的雷达辐射源信号识别[J]. 电子与信息学报, 2019,41(5):1084-1091. doi: 10.1021/acsnano.9b07956 pmid: 31869204
	HUANG Yingkun, JIN Weidong, GE Peng , et al. Radar Emitter Signal Identification Based on Multi-scale Information Entropy[J]. Journal of Electronics & Information Technology, 2019,41(5):1084-1091. doi: 10.1021/acsnano.9b07956 pmid: 31869204
[4]	金秋, 王宏艳, 延淼 . 基于深度卷积网络的雷达辐射源信号识别[J]. 现代防御技术, 2019,47(2):154-160.
	JIN Qiu, WANG Hongyan, YAN Miao . RadarEmitter Signal Recognition Based on Deep Convolutional Network[J]. Modern Defence Technology, 2019,47(2):154-160.
[5]	徐璟, 何明浩, 陈昌孝 , 等. 雷达辐射源信号识别结果评估方法研究[J]. 电波科学学报, 2014,29(2):300-304.
	XU Jing, HE Minghao, CHEN Changxiao , et al. Performance Evaluation Method for Radar Emitter Signals Recognition[J]. Chinese Journal of Radio Science, 2014,29(2):300-304.
[6]	徐璟, 何明浩, 韩俊 . 基于AIT方法的雷达辐射源信号识别效能评估[J]. 空军预警学院学报, 2014,28(4):243-245.
	XU Jing, HE Minghao, HAN Jun . Effectiveness Assessment of Radar Emitter Signal Recognition Based on AHP-interval-TOPSIS[J]. Journal of Air Force Early Warning Academy, 2014,28(4):243-245.
[7]	徐璟, 何明浩, 陈昌孝 , 等. 基于理想排序的雷达信号识别效能评估方法[J]. 电波科学学报, 2015,30(3):554-559.
	XU Jing, HE Minghao, CHEN Changxiao , et al. Effectiveness Evaluation of Signal Recognition Based on AHP-12TOPSIS[J]. Chinese Journal of Radio Science, 2015,30(3):554-559.
[8]	杨朝, 何明浩, 韩俊 , 等. 基于RE-ELECTRE的雷达辐射源信号识别效能评估[J]. 空军预警学院学报, 2017,31(2):85-88.
	YANG Zhao, HE Minghao, HAN Jun , et al. Effectiveness Evaluation of Radar Emitter Signal Recognition Based on RE-ELECTRE[J]. Journal of Air Force Early Warning Academy, 2017,31(2):85-88.
[9]	WANG H, HE M H, XU J, et al. Performance Evaluation for Radar Signal Recognition Based on AHP[C]//Communications in Computer and Information Science:346. Heidelberg: Springer Verlag, 2012: 554-561.
[10]	HAN J, PAN Y C, CHENG B L , et al. Recognition Effect Evaluation of Radar Signals Based on Fuzzy Comprehensive Evaluation[C]//Proceedings of the 2016 International Conference on Electrical, Mechanical and Industrial Engineering. Paris: Atlantis Press, 2016: 108-112.
[11]	张强, 王红卫, 陈游 . 改进的雷达信号识别效能评估方法[J]. 现代雷达, 2016,38(11):1-6.
	ZHANG Qiang, WANG Hongwei, CHEN You . AnImproved Effectiveness Evaluation Method of Radar Signal Recognition[J]. Modern Radar, 2016,38(11):1-6.
[12]	WEI G W, ZHAO X F . Induced Hesitant Interval-valued Fuzzy Einstein Aggregation Operators and Their Application to Multiple Attribute Decision Making[J]. Journal of Intelligent and Fuzzy Systems, 2013,24(4):789-803. doi: 10.3233/IFS-2012-0598
[13]	LIAO H C, MI X M, XU Z S , et al. Intuitionistic Fuzzy Analytic Network Process[J]. IEEE Transactions on Fuzzy Systems, 2018,26(5):2578-2590. doi: 10.1109/TFUZZ.91
[14]	LIAO H C, XU Z S . Priorities of Intuitionistic Fuzzy Preference Relation Based on Multiplicative Consistency[J]. IEEE Transactions on Fuzzy Systems, 2014,22(6):1669-1681. doi: 10.1109/TFUZZ.2014.2302495
[15]	于倩, 侯福均, 翟玉冰 , 等. 区间犹豫模糊ELECTRE多属性决策方法及应用[J]. 运筹与管理, 2015,24(6):16-24.
	YU Qian, HOU Fujun, ZHAI Yubing , et al. ELECTRE-basedMeasure for Multi-attribute Decision Making Using Interval-valued Hesitant Fuzzy Set[J]. Operations Research and Management Science, 2015,24(6):16-24.
[16]	高志方, 赖雨晴, 彭定洪 . 云计算安全评估的区间犹豫模糊灰色妥协关联分析方法[J]. 计算机应用, 2017,37(10):2847-2853.
	GAO Zhifang, LAI Yuqing, PENG Dinghong . Interval-valuedHesitant Fuzzy Gray Compromise Relation Analysis Method for Security of Cloud Computing Evaluation[J]. Journal of Computer Applications, 2017,37(10):2847-2853.

识别方法	C₁₁/%	C₁₂/%	C₂₁	C₂₂	C₃	C₄₁/KB	C₄₂/s
PNN	[86.08,87.12]	86.61	0.1807	[0.838 3,2.577 0]	0.969 5	65	[0.18,0.20]
SVM	[88.63,89.03]	88.81	0.413 7	[0.255 8,0.557 7]	0.808 2	81	[0.12,0.14]
GA-SVM	[91.80,91.94]	91.88	0.460 0	[0.047 1,0.143 9]	0.776 3	85	[0.35,0.44]
PSO-SVM	[91.95,92.02]	91.99	0.693 7	[0.002 0,0.026 2]	0.793 5	86	[0.37,0.45]

识别方法	C₁₁/%	C₁₂/%	C₂₁	C₂₂	C₃	C₄₁/KB	C₄₂/s
PNN	[0.480 1,0.483 7]	[0.481 9,0.482 1]	[0.190 7,0.190 9]	[0.955 1,0.975 5]	[0.576 7,0.576 9]	[0.470 7,0.470 9]	[0.325 3,0.296 3]
SVM	[0.494 3,0.494 3]	[0.494 1,0.494 3]	[0.436 8,0.437 0]	[0.291 4,0.212 8]	[0.480 7,0.480 9]	[0.508 1,0.508 3]	[0.216 9,0.207 4]
GA-SVM	[0.512 0,0.511 3]	[0.511 2,0.511 4]	[0.485 7,0.485 9]	[0.053 7,0.054 9]	[0.461 7,0.461 9]	[0.533 2,0.533 4]	[0.632 5,0.651 8]
PSO-SVM	[0.512 8,0.510 9]	[0.511 8,0.512 0]	[0.732 5,0.732 7]	[0.002 3,0.010 0]	[0.472 0,0.472 2]	[0.539 4,0.539 6]	[0.668 7,0.666 6]