基于时频循环平稳特征的通信辐射源个体识别

打开文本图片集

中图分类号：TN911 文献标志码：A DOI： 10.12305/j.issn.1001-506X.2026.03.33

Abstract：Addressng the issue of signal featureextraction being affected by noise interference in the individual identificationofcommunicationemiters，amathematical modelformeasuring signalsisconstructed，andresearchis conductedontheemitersignalsoftheautomatic identification systemforships.Firstly，the time-frequency energyspectrum ofthesignal'scyclostationaryfeatures is derivedusingtheshort-timeFourier transform，andtherelationship betweenits statistical quantities and cyclostationary features is analyzed. Secondly，a method for constructing a deep learming training dataset is proposed，through field measurements，the diferences and stabilityof the time-frequency energy spectrum of cyclostationaryfeatures，aswellasitsefectiveness insuppressingnoiseinterferenceareverified.Finally，comparative experimentsareconductedonthe trainingand testsamples byusing diferent networksand time-frequency features，which validates that the cumulative time-frequency energy spectrum method based on cyclostationary features can improve the acuracyofcommunication emiterindividualidentification.Forautomaticidentificationsystemsignals forships，theaverage Top-1 identification accuracy across 10 typical network models reaches 75.92% ，which is approximately a 25% performance improvement compared to traditional non-cumulative identification methods.The method can effectively suppress noise interference invarious spatiotemporal scenarios，providinga novel solution forcommunication emiter identification under non-cooperative conditions.

Keywords：emitterindividual identification； time-frequencyspectrum； short-timeFouriertransform; cyclostationary

0 引言

通信辐射源个体识别，又称通信射频指纹识别，旨在通过提取通信发射机发射的无线电磁波信号细微特征差异来识别发射平台，其中特征提取是关键和基础[1]。（剩余17463字）