The transponder deception jamming with DRFM (digital radio frequency memory) is highly coherent with real radar echoes, which makes it difficult for radar to distinguish real radar echoes and jamming. To address this issue, a DRFM-based deception jamming detection method based on Hough transform was proposed. The jamming signal model based on linear frequency modulation was established and the spectrum of the jamming harmonics was analyzed subsequently. Then, the short-time Fourier transform and two-dimensional constant false alarm rate detector were used to extract the features of the jamming signal. The Hough transform was used to complete deception jamming detection. The proposed method is based on the characteristics of DRFM deception jamming itself, and does not depend on prior information and application scenario. Moreover, it has low computational complexity and good detection performance under the condition of low signal-to-noise. The effectiveness of the proposed method is verified through simulations.

Convolutional neural networks currently applied to radiation source identification process the time-series IQ (in-phase and quadrature-phase) signals in two ways: one way transforms them into images, and the other way extracts shallow features of the IQ time-series data. The former way leads to a large computational effort of the algorithm, while the latter way leads to a low accuracy of the recognition rate. To address the above problems, a multi-scale feature extraction and feature selection network was proposed. After inputting the IQ signal, the shallow and multi-scale features of the IQ signal were extracted by the multi-scale feature extraction network. Then the data dimension of multi-scale features was reduced by the feature selection network. Feature enhancement was achieved by the adaptive linear rectification unit, and a single fully connected layer was used to classify the radiation source. Comparison experiments with ORACLE, CNN-DLRF and IQCNet on the FIT/CorteXlab radio frequency fingerprint recognition dataset show that the proposed network improves the recognition accuracy and reduces the computational effort to some extent.