Unknown Radar Signals Deinterleaving Based on TCN Network

Abstract

Radar signals deinterleaving plays a critical role in electronic reconnaissance. Nevertheless, due to the extremely high density of intercepted signal trains and the unknown number of emitters, along with the low probability of interception (LPI), high loss rate, and high spurious rate, the deinterleaving task is becoming more challenging. In this paper, we propose a temporal convolutional network (TCN)-based method for deinterleaving radar signal pulse trains, using only the time of arrival (TOA) parameter without knowing how many emitters there are. Simulation results indicate that the proposed method can still achieve high accuracy in situations with high pulse loss and spurious rates.