基于ConvNeXt模型的雷达辐射源信号识别

Radar Emitter Signal Recognition Based on ConvNeXt Model

针对雷达辐射源信号识别问题,提出一种基于ConvNeXt模型的识别算法。首先,由于不同调制方式的信号在时频域中具有不同的特征,因此将雷达辐射源信号的时频变换结果视为图像,并利用计算机视觉技术进行识别。其次,通过Choi-Williams分布(CWD)变换获得不同调制类型雷达信号的时频图像,对图像进行预处理。最后,使用ConvNeXt模型提取时频特征并识别雷达信号,解决低信噪比和有限样本条件下识别准确率不高的问题。实验表明,ConvNeXt模型具有更强的特征学习表征能力,有效提高16类信号的整体识别率,且对时频特性相近的6类信号(Frank、LFM、P1、P2、P3、P4)的识别精度更高。此外,该算法对小样本具有很好的鲁棒性。

Aiming at the problem of radar radiation source signal recognition,an algorithm based on ConvNeXt model is proposed.Firstly,because the signals with different modulation modes have differ⁃ent characteristics in the time-frequency domain,the time-frequency conversion results of radar radia⁃tion source signal are regarded as images,and computer vision technology is used to recognize them.Secondly,the time-frequency images of radar signals of different modulation types are obtained by the Choi-Williams distribution(CWD)transformation,and the images are preprocessed.Thirdly,the timefrequency features are extracted and the radar signals are identified using ConvNeXt model,which solves the problem of low recognition accuracy under the condition of low SNR and limited samples.The experimental results show that ConvNext model has a stronger feature learning ability and im⁃proves the overall recognition rate of 16 kinds of signals effectively.The recognition accuracy of 6 types of signals with similar time-frequency characteristics(Frank,LFM,P1,P2,P3,P4)is higher.In addition,the algorithm is robust to small samples.