Dynamic Interference Detection and Suppression in Electronic Countermeasures Systems Based on Machine Learning

In order to understand the dynamic interference detection and suppression in machine learning electronic countermeasures systems, a machine learning based study on dynamic interference detection and suppression in electronic countermeasures systems is proposed. Firstly, a mathematical analysis is conducted on the operation process of speed and distance combined deception interference in electronic communication systems, and a signal tracking model based on the coordinate system filtering of the towed head is proposed to enable preliminary detection of composite interference signals. Secondly, conventional time-domain feature extraction methods are used to further identify the composite interference signal, but the discrimination precision is not sufficient. By adding and recognizing process branching through the rule library again, each sub process has corresponding features and rule libraries, thus directly identifying composite interference signals. Finally, empirical testing was conducted, and the results showed that the proposed method has high efficiency and good performance in terms of stability and robustness.