Full connection neural network-based classification method of low interception radar signals

Abstract

The invention provides a full connection neural network-based classification method of low interception radar signals and mainly solves the problem of a low correctness classification rate of the lowinterception radar signals with low signal-to-noise ratios in the prior art. The classification method includes the following steps of: 1) obtaining the low interception radar signals with different signal-to-noise ratios; 2) calculating bi-spectrum features of the low interception radar signals, and preprocessing and grouping bi-spectrum feature signals to obtain a data set; 3) designing a modelof a full connection neural network, and training the full connection neural network by utilizing the data set to obtain a well-trained full connection neural network; and 4) preprocessing unclassified low interception radar signals, inputting the unclassified low interception radar signals in the well-trained full connection neural network, and obtaining a classification of the unclassified low interception radar signals through network output. Simulation results show that according to the classification method of the invention, the classification correctness rate of the low interception radar signals with the low signal-to-noise ratios is much higher than that of conventional technology, and the classification method can be used to identify different types of radar signal sources.

Description

technical field [0001] The invention belongs to the technical field of radar signal processing, in particular to a low intercept probability radar signal classification method, which can be used to identify different types of radar signal sources. Background technique [0002] With the rapid development of radar technology, the electromagnetic environment faced by electronic countermeasures is becoming more and more complex. The traditional one-dimensional radar signal parameters and other pulse-to-pulse features can no longer meet the sorting requirements of modern radar signals. One needs to achieve signal sorting by calculating the relevant changes of the signal in the pulse time and frequency, that is, the intrapulse characteristics. However, since different signals have different characterization capabilities on different characteristic parameters, in order to realize the complementary advantages and disadvantages of each recognition parameter, a common practice is to e...

AI Technical Summary

Problems solved by technology

[0004] However, due to the richer and more diverse modulation modes of modern radar signals, which are very different from traditional signals, and the increasingly complex electromagnetic environment also puts forward higher resolution requirements for the classification of radar signals with low SNR values. Signals can not be classified well by using deep learning network directly

[0005] Wang Xing and others proposed "Low intercept probability radar signal recognition based on deep belief network and bispectral The DBN model of the Ertzmann machine performs layer-by-layer unsupervised greedy learning on the BDS data of low-intercepted radar signals. Although in the case of no noise, this method can achieve a classification accuracy of 98.3% for the four low-intercepted signals, but After adding Gaussian white noise, the classification accuracy rate of these four signals is only 64.8% when the signal-to-noise ratio is 0dB, which cannot meet the resolution requirements of low-interception radar signal classification

Images