JERAJournal of Electronic Research and Application2208-35022208-3510Bio-Byword Scientific Publishing Pty. Ltd.10.26689/jera.v10i3.14306ArticleAn Intelligent Recognition Method for Radar Comb Spectrum Jamming Based on Dual-Channel Deep Convolutional Networkhttps://artdesignp.com/journal/JERA/10/3/10.26689/jera.v10i3.14306WangKuo,WeiYunyu,GaoSizhe,YinZiming20261032026-03-26This paper presents a deep learning method to recognize comb spectrum jamming in radar systems. Unlike traditional methods requiring manual feature extraction, our approach learns features directly from signal data. We built a dataset of radar echoes with four comb jamming types and five non-comb interference types. A dual-channel method creates 2D images preserving both magnitude and phase information from the signal spectrum. A CNN classifier with convolutional blocks, batch normalization, and dropout achieves 99.75% accuracy with 1.5% false alarm rate after only 7 training epochs.

Xu C, Yu L, Wei Y, 2019, Research on Active Jamming Recognition in Complex Electromagnetic Environment. 2019 IEEE International Conference on Signal, Information and Data Processing (ICSIDP), Signal, Information and Data Processing (ICSIDP), 2019 IEEE International Conference On, 1–5.

Sun P, Yu J, Hao W, 2021, Research on Radar Active Jamming Recognition Based on 2-D Time-Frequency Features. 2021 3rd International Academic Exchange Conference on Science and Technology Innovation (IAECST), Science and Technology Innovation (IAECST), 2021 3rd International Academic Exchange Conference On, 777–781.

Wang J, Dong W, Fu Q, et al., 2021, Radar Jamming Classification and Recognition Technology Based on Deep Learning. Proceedings of SPIE: The International Society for Optical Engineering, 11848(1): 118480T-1–118480T-7

Dong X, Guo S, Fang W, et al., 2024, Radar Active Composite Jamming Recognition Based on Characteristic Parameters, 415–420