Radar signal recognition based on triplet convolutional neural network

Lutao Liu,Xinyu Li

doi:10.1186/s13634-021-00821-8

Abstract

Recently, due to the wide application of low probability of intercept (LPI) radar, lots of recognition approaches about LPI radar signal modulations have been proposed. However, facing the increasingly complex electromagnetic environment, most existing methods have poor performance to identify different modulation types in low signal-to-noise ratio (SNR). This paper proposes an automatic recognition method for different LPI radar signal modulations. Firstly, time-domain signals are converted to time-frequency images (TFIs) by smooth pseudo-Wigner–Ville distribution. Then, these TFIs are fed into a designed triplet convolutional neural network (TCNN) to obtain high-dimensional feature vectors. In essence, TCNN is a CNN network that triplet loss is adopted to optimize parameters of the network in the training process. The participation of triplet loss can ensure that the distance between samples in different classes is greater than that between samples with the same label, improving the discriminability of TCNN. Eventually, a fully connected neural network is employed as the classifier to recognize different modulation types. Simulation shows that the overall recognition success rate can achieve 94% at − 10 dB, which proves the proposed method has a strong discriminating capability for the recognition of different LPI radar signal modulations, even under low SNR.

Highlights

low probability of intercept (LPI) radar prevents the non-cooperative receiver from intercepting and detecting its signals by transmitting a special waveform[1, 2]
It has already been proved that compared with other models of deep learning (DL), such as Stacked AutoEncoder (SAE) [16, 17] and Deep Belief Network (DBN) [18, 19], CNN has a better performance in many areas such as time series prediction [20], target detection [21], and object identification [22, 23]
This paper proposes a triplet convolutional neural network (TCNN)-Fully connected neural network (FCNN) structure to address the problem of LPI radar signal modulations recognition in low signal-to-noise ratio (SNR)

Summary

Introduction

LPI radar prevents the non-cooperative receiver from intercepting and detecting its signals by transmitting a special waveform[1, 2]. Due to the properties of low power, high resolution, large bandwidth, frequency changing, and so on [3, 4], it is tough for traditional electronic reconnaissance methods to estimate parameters of received signals exactly, which means different modulation types of LPI radar signals cannot be recognized accurately. It has already been proved that compared with other models of DL, such as Stacked AutoEncoder (SAE) [16, 17] and Deep Belief Network (DBN) [18, 19], CNN has a better performance in many areas such as time series prediction [20], target detection [21], and object identification [22, 23]. Employing CNN as the encoder module means that manual intervention will not be needed anymore, which makes the recognition process more reasonable and reliable

Methods

Results

Conclusion