Radar radiation source sorting method based on deep clustering

Abstract

The invention relates to a radar radiation source sorting method based on deep clustering, comprising the following steps: data preprocessing; constructing a convolutional self-encoder network; constructing a fully connected self-encoder network; network pre-training; feature fusion; clustering Number estimation; data clustering; network fine-tuning; sorting result output. The neural network is used to automatically extract the intrapulse features of the radar radiation source signal, which avoids artificial design and calculation of the intrapulse features, and improves the intelligence and adaptive ability. At the same time, the density peak clustering algorithm is used to estimate the number of clusters, which solves the problem that k-means clustering needs to preset the number of clusters, reduces the prior knowledge required by the present invention, and can realize the sorting of unknown radar radiation sources. In addition, the present invention fuses the intra-pulse and inter-pulse features of the radar radiation source to form a joint feature, so that the combined feature used for sorting contains both the intra-pulse and inter-pulse information of the radar radiation source, thereby improving the sorting efficiency of the radar radiation source. Correct rate.

Description

technical field [0001] The invention belongs to the field of signal processing, and further relates to a radar radiation source sorting method based on depth clustering in the technical field of radar radiation source sorting. The invention can be used for sorting received radar radiation source signals in electronic intelligence reconnaissance, electronic support and threat warning systems. Background technique [0002] Radar radiation source sorting refers to separating the signals of various radars from the intercepted densely overlapping pulse streams, which is an important part of radar reconnaissance. The primary task of the radar reconnaissance system is to sort out each radar signal from the interlaced pulse stream and identify it to obtain the model information of different radiation sources, and then analyze the working mode and threat level of each radar radiation source according to the identification results. The accuracy of radar radiation source sorting direc...

AI Technical Summary

Problems solved by technology

[0007] In order to avoid the deficiencies of the prior art, the present invention proposes a radar radiation source sorting method based on depth clustering to solve the problems that the existing radar radiation source sorting method needs to manually extract features and the correct rate of sorting is not high.

Images