摘要
针对低信噪比条件下雷达信号识别算法对噪声敏感的问题,提出了一种基于三维特征的雷达信号脉内调制识别算法。该方法通过提取信号的差分近似熵、调和平均分形盒维数和信息维数特征组成三维特征向量,使用遗传算法优化的BP神经网络分类器实现雷达信号的分类识别。仿真结果表明,所提取的三维特征在信噪比为-4~10 dB变化范围内具有较好的类内聚集度和类间分离度,可以实现对不同雷达信号进行识别,证实了该方法的有效性。
For the problem that radar signal recognition algorithm is sensitive to noise under low signal-tonoise ratio( SNR),an intra-pulse modulation recognition algorithm based on three-dimensional features is proposed. The method extracts the difference approximate entropy,average fractal box dimension and information dimension feature of the signal to form three-dimensional features vector,and uses BP neural network classifier optimized by genetic algorithm to realize radar signal classification and recognition. The simulation results show that the proposed three-dimensional features have better intra-class aggregation and inter-class separation within the range of SNR from-4 dB to 10 dB,and can realize the recognition of different radar signals,which proves the effectiveness of the method.
作者
杨洁
弋佳东
YANG Jie;YI Jiadong(School of Communication and Information Engineering,Xi'an University of Posts and Telecommunications,Xi'an 710121,China)
出处
《电讯技术》
北大核心
2020年第3期279-283,共5页
Telecommunication Engineering
关键词
雷达辐射源信号识别
脉内特征提取
BP神经网络
遗传算法
radar emitter signal recognition
intra-pulse feature extraction
BP neural network
genetic algorithm
