基于时频图像和神经网络的LPI雷达信号调制识别

熊坤来; 罗景青; 吴世龙

doi:10.15892/j.cnki.djzdxb.2011.05.020

2011 , Vol. 31 >Issue 5: 230 - 233

DOI: https://doi.org/10.15892/j.cnki.djzdxb.2011.05.020

摘要

针对LPI雷达信号调制识别问题,提出一种基于时频分析、图像处理和神经网络的LPI雷达信号识别新方法。该方法先对LPI雷达信号进行时频分析,获得时频分布图像,然后利用图像处理的方法对时频图像作预处理,最后再用RBF神经网络对处理后的图像进行识别分类。仿真实验表明,该方法在信噪比高于3dB时,平均正确识别率达到了92%。

关键词： LPI雷达信号; 自动识别; 时频分析; 图像处理; 神经网络

本文引用格式

熊坤来 , 罗景青 , 吴世龙 . 基于时频图像和神经网络的LPI雷达信号调制识别[J]. 弹箭与制导学报, 2011 , 31(5) : 230 -233 . DOI: 10.15892/j.cnki.djzdxb.2011.05.020

Abstract

To correctly classify low probability of intercept (LPI) radar signals, a novel method was presented based on time frequency analysis, image processing and neural network. First, LPI radar signals were analyzed in time frequency domain and their time frequency images were obtained. Then, the time frequency images were pre-processed by image processing method. Finally, the images were used to train a RBF neural network for automatic identification and classification of the LPI radar signals. The experiments show that the correct identification rate of the method comes to 92% when the signal-to-noise ration (SNR) is above 3dB.

Key words： LPI radar signal; automatic identification; time frequency analysis; image processing; neural network

[an error occurred while processing this directive]

参考文献

[1]	张锡熊. 低截获概率(LPI)雷达的发展[J]. 现代雷达, 2003, 25(12): 1-4.
[2]	Pace P E. Detecting and classifying low probability of intercept radar [M]. Norwood, MA: Artech House, 2004: 113-166.
[3]	袁伟明, 王敏, 吴顺君. 低截获概率雷达信号的调制识别研究[J]. 信号处理, 2006, 22(2): 153-155.
[4]	邓振淼, 刘渝. 多相码雷达信号的识别与参数估计[J]. 电子与信息学报, 2009, 31(4): 781-785.
[5]	L Anjaneyulu, N S Murthy, N V S N Sarma. Identification of LPI radar signals by higher order spectra and neural network techniques [C] // International Conference on Electronic Design, 2008.
[6]	高平安, 卜冠英, 罗铸楷. 关于Costas 阵列[J]. 计算机与自动化, 2000, 19(3): 10-14.
[7]	张贤达. 现代信号处理[M].2版. 北京: 清华大学出版社, 2002: 480-481.
[8]	张德丰. 数字图像处理[M]. 北京: 人民邮电出版社, 2009: 6-84,226-228.
[9]	Fredric M Ham, Ivic Kostcmic. 神经计算原理[M]. 叶世伟, 王海娟,译. 北京: 机械工业出版社, 2007: 101-106.
[10]	孙志强, 葛哲学. 神经网络理论与 MATLAB 7实现[M]. 北京: 电子工业出版社, 2005: 79-81.

Options

文章导航