Deceptive Jamming Recognition Based on Wavelet Entropy And RBF Neural Network

Abstract

The development of digital radio frequency memory has made the technology of deceptive jamming get a qualitative leap. The real-time and immersiveness are greatly improved, which makes it difficult to manually judge the type of deceptive jamming. Aiming at the problem of automatic identification of deceptive jamming, a method based on wavelet entropy for deceptive jamming is studied. Firstly, three mathematical models of deceptive jamming patterns are combed, then wavelet analysis is performed on the signal and wavelet entropy is extracted, and then sent to the radial basis function (RBF) neural network for automatic classification. The simulation results show that the proposed method has a high recognition rate for deceptive jamming patterns, which relatively less affected by the Jamming-to-Noise Ratio (JNR), and has a faster calculation velocity and better real-time performance.