Radar radiation source signal identification method based on one-dimensional convolutional neural network

Abstract

The invention belongs to the radiation source signal identification technology field and particularly relates to a radar radiation source signal identification method based on the one-dimensional convolutional neural network. The method comprises steps that (1), a radar radiation source signal data set is generated; (2), data pre-processing is carried out; (3), the convolutional neural network is constructed; (4), parameters are set, and the convolutional neural network is trained; (5), prediction classification is carried out; (6), precision calculation is carried out; and (7), the result is outputted. The method is advantaged in that 1, a network structure of the convolutional neural network is utilized to carry out characteristic extraction of signals, and a manual characteristic design process in a traditional algorithm can be avoided; 2, signals with a signal to noise ratio lower than -10dB can be accurately identified; and 3, the method can be simply realized.

Description

technical field [0001] The invention belongs to the technical field of radiation source signal identification, and in particular relates to a radar radiation source signal identification method based on a one-dimensional convolutional neural network. Background technique [0002] Radar emitter signal identification is an important link in electronic countermeasures, and plays a key role in electronic intelligence reconnaissance, electronic support reconnaissance and threat warning systems. [0003] With the rapid development of electronic information technology, the confrontation in the modern electronic battlefield is becoming more and more fierce, and the new complex system radar is gradually occupying a dominant position. The electromagnetic environment is increasingly complex and dense, and the traditional pulse descriptors (carrier frequency, pulse arrival time, pulse arrival angle, pulse amplitude, pulse width) are no longer suitable for radar radiation source signals ...

AI Technical Summary

Problems solved by technology

However, these methods have many shortcomings. On the one hand, many methods have a general effect on the recognition of signals under low signal-to-noise conditions. On the other hand, these methods often spend a lot of time on signal feature extraction, and some features extracted are not It is not universal, and if you want to use combined features, you may have to face the disaster of dimensionality or the difficulty of feature selection

Images