Inter-Pulse Feature Analysis of Radar Emitter Signals Based on Complex Network

In a dense modern electronic warfare environment, Inter-pulse advanced modulation is applied to help the radar reduce range ambiguities and improve the anti-jamming characteristics of radar. This could be hard problems to classify radar emitters one from another through the basic parameters of Pulse Descriptor Words (PDWs). In this paper, we propose a feature extraction method of intercepted radar pulse train for constructing complex networks using Limited penetrable visibility graph (LPVG). In our algorithm, we selected four pulse trains of radar emitter as sample data to analyze the topological characteristics of four networks. Furthermore, the simulation results uncovered the inter-pulse train dynamical patterns which trigger the structure of network changing among PDWs. Meanwhile, the proposed algorithm is effective and feasible in classifying radar emitter signals. In a word, this paper described explored topological characteristics in networks constructed from pulse time series data, which provides a new angle to investigate the radar pulse train and provides a new effective means for feature extraction of radar emitter signals. The experimental results show that the features extracted by the method in this paper have good separability, and the results are visualized after feature extraction and classification of the four radar emitter signals in the experiment, which proves that the method has good results.