基于功率谱熵的无线电引信目标与干扰信号分类方法  

Classification method of radio fuze target and interference signal based on power spectrum entropy

作　　者：刘冰[1] 郝新红[1] 蔡鑫 LIU Bing;HAO Xinhong;CAI Xin(Science and Technology on Electromechanical Dynamic Control Laboratory,Beijing Institute of Technology,Beijing 100081,China)

机构地区：[1]北京理工大学机电动态控制重点实验室,北京100081

出　　处：《北京航空航天大学学报》2024年第3期913-919,共7页Journal of Beijing University of Aeronautics and Astronautics

基　　金：国家自然科学基金(61871414)。

摘　　要：无线电调频引信在战场环境容易受到干扰信号的干扰导致早炸,丧失打击能力。为提升无线电调频引信抗干扰能力,准确识别引信目标与干扰信号,提出一种基于功率谱熵特征的无线电调频引信目标与干扰信号分类识别方法。利用实测采集的无线电引信检波端输出信号,通过提取目标和干扰信号的功率谱指数熵和Renyi熵特征构成特征向量,作为K邻近(KNN)分类器的输入进行目标和干扰信号分类识别,并利用5-折交叉检验方法对其进行验证。结果表明:目标和干扰信号的功率指数熵和Renyi熵具有显著差异性,使用KNN分类器对其进行分类识别时,最高的识别准确率可达99.47%。Radio frequency modulation fuze is easy to be disturbed by jamming signals in a battlefield environment,which lead to explosion early and loss of attack ability.In a combat setting,jamming signals can easily disrupt radio frequency modulation fuses,resulting in an early explosion and a loss of assault capability.In order to identify target and jamming signals accurately,a classification method based on signal power spectrum entropy is proposed.Using the measured output signals of radio fuze,the power spectrum exponential entropy and Renyi entropy of the target and jamming signals are extracted to form feature vectors,which is used as the input of KNN classifier to classify target and jamming signals,and verified by 5-fold cross validation method.The target and jamming signals'power spectrum exponential entropy and Renyi entropy are extracted from the radio fuze's measured output signals to create feature vectors.These vectors are then fed into a K-nearest neighbor(KNN)classifier to classify the target and jamming signals,and their classification is confirmed through the use of the 5-fold cross validation method.The results show that there is a significant difference between the power spectrum exponential entropy and Renyi entropy of the target and jamming signals,and the highest classification accuracy reaches 99.47%when the KNN classifier is used to classify the target and jamming signals.

关 键 词：无线电调频引信 抗干扰 功率谱熵特征 目标分类 KNN算法 

分 类 号：TJ434.1[兵器科学与技术—火炮、自动武器与弹药工程]