Radar interference detection and identification method based on convolutional neural network

Abstract

The invention discloses a radar interference detection and identification method based on a convolutional neural network. The method comprises the following steps: preprocessing radar signals; performing time domain transformation on the preprocessed signal by adopting short-time Fourier transform; performing constant false alarm detection and interference measurement on the time-frequency image ain sequence to obtain a time parameter and a frequency parameter of an interference signal; extracting an interference signal in the radar signal according to the time parameter; filtering the extracted interference signal by adopting a band-pass filter according to the frequency parameter; carrying out time domain transformation on the filtered signal by adopting short-time Fourier transform toobtain a time-frequency image b, and carrying out normalization processing; smoothing the normalized time-frequency image b by adopting a Wiener filtering algorithm, and then performing adaptive clipping on a smoothing result; scaling the adaptively clipped image by adopting a bicubic interpolation algorithm to obtain identification data; and inputting the identification data into a pre-trained CNN model for identification to obtain the type of the interference signal.

Description

technical field [0001] The invention relates to the identification of interference signal types, in particular to a radar interference detection and identification method based on a convolutional neural network. Background technique [0002] With the emergence and rapid application of digital radio frequency storage (DFRM) technology, the fidelity of radar active interference in modern electronic warfare is higher, and the forms are complex and diverse, which poses a serious threat to the normal operation and survival of radar. Therefore, how to effectively counteract Jamming is an increasingly urgent need for modern radars. The premise of anti-interference is the correct identification of the interference. The traditional method is the interference classification based on feature extraction, but this kind of method requires manual selection of features and the generalization ability is weak. In recent years, many radar jamming identification algorithms have emerged, but th...

AI Technical Summary

Problems solved by technology

[0003] In view of the above-mentioned deficiencies in the prior art, the radar interference detection and recognition method based on the convolutional neural network provided by the present invention solves the problem that the prior art needs to manually select features and has weak generalization ability when performing radar recognition

Images