基于IFOA-SA-BP神经网络的雷达信号识别

doi:10.3969/j.issn.1001-506X.2020.12.08

摘要/Abstract

摘要：

为提高雷达信号的识别率,提出一种改进的果蝇优化算法(improved fruit fly optimization algorithm, IFOA)和模拟退火(simulated annealing, SA)算法相融合并用于优化反向传播(back propagation, BP)神经网络的雷达信号识别算法。首先,该算法提取雷达信号的调和平均盒维数、信息维数和差分近似熵特征作为信号识别的三维特征。然后,改进果蝇优化算法的寻优步长并添加逃脱系数以修改适应度函数,同时引入三维空间的搜索概念扩大果蝇的搜索范围,再对果蝇算法所求解的接受机制通过SA算法进行修正。最后,将融合后的算法IFOA-SA用于优化BP神经网络得到网络最优的初始权值和阈值,并用此网络进行雷达信号的分类识别。通过与BP和FOA-BP进行对比,结果表明IFOA-SA-BP能够提高雷达信号的识别率,证实了该算法的有效性。

关键词: 雷达信号识别, 特征提取, 反向传播神经网络, 果蝇优化算法, 模拟退火算法

Abstract:

In order to improve the recognition rate of radar signal, an improved fruit fly optimization algorithm (IFOA) and simulated annealing (SA) algorithm are combined to optimize the radar signal recognition algorithm of the back propagation (BP) neural network. Firsty, the algorithm extracts the harmonic average fractal box dimension, information dimension and differential approximate entropy feature of radar signal as the three-dimensional features of signal recognition. Then, the optimization step length of fruit fly optimization algorithm (FOA) is improved and the jump coefficient is added to modify the fitness function. At the same time, the three-dimensional search concept is introduced to expand the search range of the fruit fly. And then the acceptance mechanism of solution by the FOA is modified by the SA algorithm. Finally, the fusion algorithm of the IFOA-SA is used to optimize the BP neural network for acquirig the best initial weight and threshold value, and the network is used for radar signal classification and recognition. Compared with the BP and the FOA-BP, the results show that the IFOA-SA-BP can improve the recognition rate of radar signal, which proves the effectiveness of the algorithm.

Key words: radar signal recognition, feature extraction, back propagation (BP) neural network, fruit fly optimization algorithm (FOA), simulated annealing (SA) algorithm

中图分类号:

TN957.51

弋佳东, 杨洁. 基于IFOA-SA-BP神经网络的雷达信号识别[J]. 系统工程与电子技术, 2020, 42(12): 2735-2741.

Jiadong YI, Jie YANG. Radar signal recognition based on IFOA-SA-BP neural network[J]. Systems Engineering and Electronics, 2020, 42(12): 2735-2741.

图/表 7

图1

图2

表1

图3

图4

图5

表2

参考文献 29

1	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.
	HUANG Y K , JIN W D , GE P , et al. Radar emitter signal recognition based on multi-scale information entropy[J]. Journal of Electronics & Information Technology, 2019, 41 (5): 1084- 1091.
2	PENG C , CHEN H Q , LENAN W , et al. Estimation of extended targets based on compressed sensing in cognitive radar system[J]. IEEE Trans.on Vehicular Technology, 2017, 66 (2): 941- 951. doi: 10.1109/TVT.2016.2565518
3	ZHANG W X , SUN F L , WANG B . Radar signal intra-pulse feature extraction based on improved wavelet transform algorithm[J]. International Journal of Communications, 2017, 10 (8): 118- 127.
4	ZHANG Y , LIU B , JI X , et a1 . Classification of EEG signals based on autoregressive model and wavelet packet decomposition[J]. Neural Processing Letter, 2017, 45 (2): 365- 378. doi: 10.1007/s11063-016-9530-1
5	CIUONZO D , ROSSI P S . Noncolocated time-reversal MUSIC: High-SNR distribution of null spectrum[J]. IEEE Signal Processing Letters, 2017, 24 (4): 397- 401.
6	KISHORE T R , RAO K D . Automatic intra-pulse modulation classification of advanced LPI radar waveforms[J]. IEEE Trans.on Signal Process, 2017, 53 (2): 901- 914.
7	XIE J S. Robust intra-pulse modulation recognition via sparse representation[C]//Proc.of the CIE International Conference on Radar, 2017.
8	LIN J , KEOGH E , WEI L , et al. Experiencing SAX: a novel symbolic representation of time series[J]. Data Mining and Knowledge Discovery, 2007, 15 (2): 107- 144.
9	SONG W , WANG Z G , ZHANG F , et al. Empirical study of symbolic aggregate approximation for time series classification[J]. Intelligent Data Analysis, 2017, 21 (1): 135- 150. doi: 10.3233/IDA-150351
10	ZHANF X Y , WAN J , ZHAO Y N , et al. Recognition of radar emitter signals based on SVD and AF mainridge slice[J]. Journal of Communication & Networks, 2015, 17 (5): 491- 498.
11	TAVAKOLI E T , FALAHATI A . Radar signal recognition by CWD picture features[J]. International Journal of Communications Network & System Sciences, 2012, 5 (4): 238- 242.
12	ZHU J D , ZHAO Y J , TANG J , et al. Automatic recognition of radar signals based on time-frequency image character[J]. Defence Science Journal, 2013, 63 (3): 1- 6.
13	MENDIS G J, WEI J, MADANAYAKE A. Deep learning based automated modulation classification for cognitive radio[C]//Proc.of the IEEE International Conference on Communication Systems, 2016.
14	BOUCHOU M, WANG H, EL HADI L. Automatic digital modulation recognition based on stacked sparse autoencoder[C]//Proc.of the IEEE 17th International Conference on Communication Technology, 2017: 28-32.
15	KONG S H , KIM M J , HOANG L M , et a1 . Automatic LPI radar waveform recognition using CNN[J]. IEEE Access, 2018, 6, 4207- 4219. doi: 10.1109/ACCESS.2017.2788942
16	曲志昱, 毛校洁, 侯长波. 基于奇异值熵和分形维数的雷达信号识别[J]. 系统工程与电子技术, 2018, 40 (2): 303- 307.
	QU Z Y , MAO X J , HOU C B . Radar signal recognition based on singular value entropy and fractal dimension[J]. Systems Engineering and Electronics, 2018, 40 (2): 303- 307.
17	LIN Y , XU X C , PANG J F . The improved recognition method of radiation signal under the condition of unstable SNR[J]. International Journal of Signal Processing Image Processing & Pattern Recognition, 2014, 7 (2): 339- 344.
18	CHEN C X , HE M H , XU J , et al. A new method for sorting unknown radar emitter signal[J]. Chinese Journal of Electro-nics, 2014, 23 (3): 499- 502.
19	吕铁军, 郭双冰, 肖先赐. 调制信号的分形特征研究[J]. 中国科学E辑, 2001, 31 (6): 508- 513.
	LYU T J , GUO S B , XIAO X C . Study on fractal characteristics of modulation signal[J]. Science in China (Series E), 2001, 31 (6): 508- 513.
20	龙晓红, 张洪欣, 张明明. 基于调和平均分形盒维数的无线通信信号调制识别算法[J]. 江苏大学学报(自然科学版), 2017, 38 (3): 308- 312.
	LONG X H , ZHANG H X , ZHANG M M . Modulation recognition algorithm of wireless communication signal based on harmonic average fractal box dimension[J]. Journal of Jiangsu University (Natural Science Edition), 2017, 38 (3): 308- 312.
21	谢阳.通信信号指纹特征提取与个体识别技术研究[D].长沙:国防科技大学, 2016.
	XIE Y. Research on fingerprint feature extraction and individual identification technology of communication signal[D]. Changsha: National University of Defense Technology, 2016.
22	TANG Y , YUAN S Q , QIU Z P , et al. Optimization of impulse water turbine based on GA-BP neural network arithmetic[J]. Journal of Mechanical Science and Technology, 2019, 33 (1): 241- 253. doi: 10.1007/s12206-018-1224-3
23	ZANDIEH M , TAVANA M , ALIKAR N , et al. A tuned hybrid intelligent fruit fly optimization algorithm for fuzzy rule generation and classification[J]. Neural Computing & applications, 2019, 31 (3): 873- 885.
24	SATTAR S , ADIL B , EHSAN Z B , et al. A simulated annealing-based maximum margin clustering algorithm[J]. Computational Intelligence, 2019, 35 (1): 23- 41. doi: 10.1111/coin.12187
25	吕昌民, 欧阳缮, 李贝贝, 等. 基于SA算法反演层状介质介电常数的算法[J]. 现代雷达, 2017, 39 (5): 54- 58.
	LYU C M , OUYANG J , LI B B , et al. Inversion algorithm of permittivity of layered media based on SA algorithm[J]. Modern Radar, 2017, 39 (5): 54- 58.
26	ISCAN H, MESUT G. A survey on fruit fly optimization algorithm[C]//Proc.of the IEEE International Conference on Signal-Image Technology & Internet-Based Systems, 2015: 520-527.
27	韩俊英, 刘成忠. 自适应混沌果蝇优化算[J]. 计算机应用, 2013, 33 (5): 1313- 1316.
	HAN J Y , LIU C Z . Adaptive chaos fruit fly optimization algorithm[J]. Journal of Computer Applications, 2013, 33 (5): 1313- 1316.
28	LIANG H D , HAN J H . Sorting radar signal based on wavelet characteristics of Wigner-Ville distribution[J]. Journal of Electronics, 2013, 30 (5): 454- 462.
29	GUO Q, NAN P L, WAN J. Radar signal recognition based on ambiguity function features and cloud model similarity[C]//Proc.of the IEEE International Conference on Ultrawideband & Ultrashort Impulse Signals, 2016.

函数	算法名称	平均值	方差
f₁(x)	FOA	8.175×10^-5	3.168×10^-11
f₁(x)	IFOA-SA	8.561×10^-6	1.610×10^-12
f₂(x)	FOA	1.236×10^-2	1.179×10^-6
f₂(x)	IFOA-SA	1.652×10^-3	7.743×10^-8

识别方法	时间/s
小波特征	78.65
模糊函数	63.31
本文方法	54.27

[1]	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.
[2]	马泽煊, 李进, 路艳丽, 陈晨. 融合WaveNet和BiGRU的网络入侵检测方法[J]. 系统工程与电子技术, 2022, 44(8): 2652-2660.
[3]	李郝亮, 陈思伟, 王雪松. 海面角反射器的极化旋转域特性研究[J]. 系统工程与电子技术, 2022, 44(7): 2065-2073.
[4]	张彦, 叶春茂, 李璋峰, 鲁耀兵. 多种转发干扰下的脉内脉间波形综合优化设计[J]. 系统工程与电子技术, 2022, 44(5): 1495-1501.
[5]	曹鹏宇, 杨承志, 石礼盟, 吴宏超. 基于PSO-DBSCAN和SCGAN的未知雷达信号处理方法[J]. 系统工程与电子技术, 2022, 44(4): 1158-1165.
[6]	石宸睿, 田露, 徐湛, 职如昕, 陈晋辉. 基于PSO-BP的应急通信感知装备效能评价方法[J]. 系统工程与电子技术, 2022, 44(11): 3455-3462.
[7]	朱峰, 蒋倩倩, 林川, 杨啸. 基于支持向量机的典型宽带电磁干扰源识别[J]. 系统工程与电子技术, 2021, 43(9): 2400-2406.
[8]	苏瑜, 荆文芳, 卢晓春, 张阳. 基于BP-PID控制的载波频率准确度提高算法[J]. 系统工程与电子技术, 2021, 43(7): 1894-1903.
[9]	谢存祥, 张立民, 钟兆根. 基于时频特征提取和残差神经网络的雷达信号识别[J]. 系统工程与电子技术, 2021, 43(4): 917-926.
[10]	王力, 刘子奇. WPA-IGA-BP神经网络的模拟电路故障诊断[J]. 系统工程与电子技术, 2021, 43(4): 1133-1143.
[11]	陈浩, 杨俊安, 刘辉. 基于深度残差适配网络的通信辐射源个体识别[J]. 系统工程与电子技术, 2021, 43(3): 603-609.
[12]	张国令, 吴崇明, 李睿, 来杰, 向前. 基于一维堆叠池化融合卷积自编码器的HRRP目标识别方法[J]. 系统工程与电子技术, 2021, 43(12): 3533-3541.
[13]	赵若辰, 王敬东, 林思玉, 顾东泽. 基于卷积神经网络的小型建筑物检测算法[J]. 系统工程与电子技术, 2021, 43(11): 3098-3106.
[14]	张天骐, 范聪聪, 喻盛琪, 赵健根. 基于JADE与特征提取的正交/非正交空时分组码盲识别[J]. 系统工程与电子技术, 2020, 42(4): 933-939.
[15]	张怡霄, 郭文普, 康凯, 姚云龙, 王攀. 基于聚类和时序相关的重点雷达信号快速识别[J]. 系统工程与电子技术, 2020, 42(3): 597-602.