Highly Contaminated Work Mode Identification of Phased Array Radar Using Deep Learning Method

Different work modes of phased array radar have different threat levels. Therefore, it is of great significance to distinguish the work mode of the phased array radar by the intercepted information. However, as the phased array radar signals are non-cooperative signals, it is difficult to identify them in terms of in-pulse information. Traditional methods do not have enough analysis on the radar signals and heavily rely on machine learning algorithms to identify the work mode, so the accuracy is low. By utilizing the smoothness differences, backlight information and pulse repeat frequency variation rule, in this paper, we use the deep learning method to identify seven common work modes of airborne phased array radar. The simulation results show that the method has a high identification accuracy for the work mode of phased array radar.