Radar Signal Classification System Based on BP Neural Network

Abstract

This paper introduces a method of recognition and classification of radar echo signals. We introduce the method of radar signal preprocessing, including the construction of complex echo signals of radar and the normalization of spectrums. Besides, we calculate the power spectral density (PSD) and extract the features. Then we construct the back propagation (BP) neural network as the classifier. Finally, we conduct the simulation experiment and analyze the experimental results. From the experimental results, it can be seen that this method is better than the traditional single-layer neural network recognition method. In addition, our method can not only maintain a better classification accuracy of radar signals despite the low signal-to-noise ratio, but also reduce the classification gap between different radar signals, with good stability and robustness.