基于优化VMD与斜率熵的目标辐射噪声特征提取方法  

Feature Extraction Method for Target Radiated Noise Based on Optimized VMD and Slope Entropy

作　　者：周照翔 占春连 ZHOU Zhao-xiang;ZHAN Chun-lian(School of Optics and Electronic Technology,China Jiliang University,Hangzhou 310018,China)

机构地区：[1]中国计量大学光学与电子科技学院,杭州310018

出　　处：《科学技术与工程》2024年第28期12188-12199,共12页Science Technology and Engineering

摘　　要：为了在复杂多变的环境中有效提取目标辐射噪声的特征信息,提出一种基于优化变分模态分解(variational mode decomposition,VMD)和斜率熵的目标辐射噪声特征提取方法。采用蝴蝶优化算法(butterfly optimization algorithm,BOA),提出基于BOA的参数优化VMD算法(BOA-VMD),实现VMD最佳参数组合的自适应选取,从而对四类辐射噪声信号进行分解,得到一定数量的固有模态函数(intrinsic mode functions,IMF)。计算各IMF分量的斜率熵作为特征值,通过仿真实验和实际噪声信号进行实验分析,并与散布熵、波动散布熵和排列熵3种特征相比较。结果表明:所提出的基于BOA-VMD与斜率熵的特征提取方法可以实现不同种类目标的分类识别,并且在单特征和多特征条件下均具有最高识别率,而且随着提取的特征数量的增加,最高识别率也会随之增加。In order to effectively extract feature information of target radiated noise in complex and ever-changing environments,a target radiated noise feature extraction method based on optimized variational mode decomposition(VMD)and slope entropy(SlEn)was proposed.Firstly,a parameter optimization VMD algorithm(BOA-VMD)based on BOA was proposed to achieve adaptive selection of the optimal parameter combination for VMD.Then,the four types of target radiation noises were decomposed to obtain a certain number of IMF.The SlEn of each IMF component was calculated as the feature value,and was compared with three types of features:dispersion entropy,fluctuation dispersion entropy,and permutation entropy to demonstrate the effectiveness of SlEn through experiment.The results show that the proposed feature extraction method based on BOA-VMD and SlEn can achieve classification and recognition of different types of targets,and has the highest recognition rate under single and multiple feature conditions.Additionally,as the number of extracted features increases,the highest recognition rate will also increase accordingly.

关 键 词：目标辐射噪声 特征提取 变分模态分解 蝴蝶优化算法 斜率熵 

分 类 号：TN911.72[电子电信—通信与信息系统]