Satellite amplitude-phase signal identification and demodulation method and device based on a recurrent neural network

Abstract

The invention belongs to the technical field of satellite communication signal processing. The invention particularly relates to a satellite amplitude-phase signal identification and demodulation method and device based on a recurrent neural network. The method comprises the following steps of: constructing a modulation recognition and demodulation network model for a training sample set and a test sample set, training the network model by utilizing the training sample set, checking the convergence degree of the trained network model by utilizing the test sample set, and storing the modulationrecognition and demodulation network model meeting a preset convergence requirement; Receiving a target signal, and preprocessing the target signal to obtain to-be-identified data consistent with theinput signal of the network model; And performing modulation identification on the to-be-identified data by using the stored modulation identification and demodulation network model, and performing signal demodulation by using a modulation identification result to obtain signal bit stream data. The method does not need to estimate the carrier-to-noise ratio of the target signal, overcomes the defects of manual determination of a threshold value and the like in a traditional method, is high in tolerance to signal frequency offset errors and timing errors, and has a very good engineering application prospect.

Description

technical field [0001] The invention belongs to the technical field of satellite communication signal processing, in particular to a method and device for identifying and demodulating satellite amplitude and phase signals based on a cyclic neural network. Background technique [0002] Signal modulation identification refers to the modulation set where the known signal is located, and correctly identifying the modulation type of the target signal is an important research topic in the field of communication reconnaissance and signal blind processing. Signal demodulation, as a means to further obtain deep signal information, has considerable demand in civil and other fields. With the continuous development of communication technology, various new modulation methods continue to appear, and the modulation identification and demodulation technology also needs continuous improvement and development. In the process of satellite communication, due to the non-linearity of the transpo...

AI Technical Summary

Problems solved by technology

But in general, there are few integrated design methods based on signal modulation identification and demodulation, and a large amount of manual intervention is still required to realize the whole process analysis of signals, and there is still a certain distance from the goal of cognitive radio.

Images