现代雷达2025，Vol.47Issue(10)：50-59,10.DOI:10.16592/j.cnki.1004-7859.2025063001
基于自监督联合预训练的雷达辐射源识别方法
Radar Emitter Recognition Method Based on Self-supervised Joint Pre-training
摘要
Abstract
A self-supervised joint pre-training multi-scale dual attention network method is proposed to address the issue of insuffi-cient recognition robustness caused by missing,distorted,and interfering radar pulse signals in non-cooperative electromagnetic en-vironments.The pulse sequence is modeled as natural language,and the model is driven to learn deep semantic correlations and temporal patterns within the signals through the collaborative optimization of sequence semantic contrast and sequence ordering tasks.During the data pre-processing stage,word embedding and positional encoding techniques are employed to transform discrete pulse parameters into high-dimensional dynamic features incorporating temporal dependencies.Feature representation flexibility is enhanced by the multi-scale convolutional module through the decoupling of temporal and channel dimensions.Implicit temporal features are mined during the pre-training phase utilizing sequence semantic contrast tasks and sequence ordering tasks.The per-formance of the self-supervised training is validated on a downstream task involving the recognition of radar emitters from a total of 6 categories.Experiments demonstrate that under a 50%pulse missing rate,the recognition accuracy of the proposed method rea-ches 82.0%,outperforming RNN,CNN,and Transformer by 37.3%,24.9%,and 35.7%in accuracy,respectively.At a 20%erroneous pulse rate,the proposed method maintains a recognition accuracy of 91.3%,representing improvements of 8.3%,14.3%,and 14.2%over the aforementioned comparative methods.Ablation studies confirm that the self-supervised joint pre-train-ing elevates the recognition accuracy to 96.9%,showing a significant improvement compared to without self-supervised training.关键词
雷达信号识别/自监督联合预训练/错漏脉冲/时序特征学习/多尺度双重注意力网络Key words
radar signal recognition/self-supervised joint pre-training/missing and wrong pulses/sequence feature learning/multi-scale dual attention network分类
电子信息工程引用本文复制引用
邓开,张振熙,徐逸飞,张霖润,石晓然,周峰..基于自监督联合预训练的雷达辐射源识别方法[J].现代雷达,2025,47(10):50-59,10.基金项目
国家自然科学基金资助项目(62401429,62501437,62401445,62531020) （62401429,62501437,62401445,62531020）
中国博士后科学基金资助项目(GZC20241332,2025M771739) （GZC20241332,2025M771739）
