Intra-Pulse Modulation Recognition of Dual-Component Radar Signals Based on Deep Convolutional Neural Network

Abstract

In an ever-increasingly complicated electromagnetic environment with explosive radar signals density, accurate and fast recognition of dual-component radar signals has become an urgent problem in the current radar reconnaissance system. This letter proposes a novel multi-class learning framework based on deep convolutional neural network (DCNN) for recognizing eight types of randomly overlapping dual-component radar signals. The framework mainly includes dual-component radar signals preprocessing, DCNN model that aimed to extract more effective dual-component radar signals features, and multi-class classification. The results shown that the average classification accuracy of dual-component radar signals can be up to 96.17% when the signal-to-noise ratio (SNR) is −8 dB, which demonstrates the superior performance over others. The proposed model possesses the larger improvement for 4FSK, BPSK, EQFM, and FRANK, especially at the lower SNR. This work provides a sound guidance for further improving multi-component radar signals recognition.