雷达科学与技术2025，Vol.23Issue(1)：109-118,10.DOI:10.3969/j.issn.1672-2337.2025.01.012
小样本条件下LPI雷达信号的双通道识别
Dual-Channel Recognition of LPI Radar Signals Under Small Sample Conditions
摘要
Abstract
Aiming at the problem of low recognition accuracy of radar signals with low probability of intercept(LPI)under small sample conditions and low signal-to-noise ratios(SNRs),this paper proposes a dual-channel feature fusion network model based on local maximum synchrosqueezing transform(LMSST)and smoothed pseudo wigner-ville distribution(SPWVD).LMSST and SPWVD are used to perform time-frequency analysis on the only small sample of LPI radar signal to obtain 2D time-frequency images.It is expanded by using cycle generative adversarial networks(Cyclegan)and sent into a dual-channel network for feature extraction and early fusion of features.The Softmax classifier is used to sort and identify the fused features.The results show that the overall recognition rate of the designed model reaches 93.1%when the signal-to-noise ratio is-8 dB.Compared with the single-channel recognition model,the recogni-tion accuracy under small sample conditions is effectively improved by 6%～7%.This research provides a theoretical basis for the recognition of LPI radar signals with small samples.关键词
小样本信号识别/时频分析/循环对抗生成网络/早特征融合/双通道网络Key words
small-sample signal recognition/time-frequency analysis/Cyclegan/early feature fusion/dual-channel network分类
信息技术与安全科学引用本文复制引用
李辉,秦怡博,王欣然,王伟东,李小磊..小样本条件下LPI雷达信号的双通道识别[J].雷达科学与技术,2025,23(1):109-118,10.基金项目
国家自然科学基金(No.62101176) （No.62101176）
