An identification method, device, equipment and medium for communication signal modulation mode

Abstract

The invention discloses a method for identifying a modulation mode of a communication signal, which includes: obtaining the characteristic value of the signal, and the characteristic value is a plurality of characteristic values ​​respectively extracted from the signal from the perspective of statistical characteristics and high-order cumulants; obtaining and A decision threshold corresponding to each eigenvalue; using the decision threshold to compare multiple eigenvalues ​​of the signal, and identify the modulation mode of the signal according to the comparison result. It can be seen that when identifying the modulation mode of communication signals in this application, it is necessary to extract eigenvalues ​​from the two perspectives of statistical characteristics and high-order cumulants, and compare the extracted eigenvalues ​​with the corresponding set judgment thresholds, and then identify them according to the comparison results. The modulation method of the signal not only improves the recognition rate, but also increases the recognizable modulation types. The invention also discloses an identification device, equipment and storage medium for the communication signal modulation mode, which can also achieve the above-mentioned technical effect.

Description

technical field [0001] The present invention relates to the technical field of communications, and more specifically, to a method, device, equipment and medium for identifying modulation modes of communications signals. Background technique [0002] At present, modulated signal recognition is an important step between signal detection and signal demodulation. Its purpose is to judge the modulation mode of the signal through processing the received signal without other prior knowledge, and estimate the corresponding modulation parameters. It is mainly applied in two aspects: one is the software radio system, which ensures the intercommunication and interconnection between communication systems of different systems; the other is the electronic warfare system, which provides the basis for intercepting information and selecting the best interference pattern. Modulation mode is an important feature to distinguish communication signals of different natures. For the received sign...

AI Technical Summary

Problems solved by technology

[0003] In the past few years, many identification algorithms for analog and digital signals can be summarized as follows: Nandi and Azzouz proposed three modulation identification algorithms, mainly for amplitude modulation AM, frequency modulation FM, double sideband modulation DSB, lower sideband modulation LSB, upper sideband modulation USB with modulation, vestigial sideband modulation VSB, combined (AM-FM), binary amplitude keying 2ASK, quaternary amplitude keying 4ASK, binary phase shift keying 2PSK, quaternary phase shift keying 4PSK, binary digital frequency Modulation 2FSK and quaternary digital frequency modulation 4FSK, when the signal-to-noise ratio is 15dB, the average recognition probability reaches 94%; some scholars such as Sun use deep learning based on the VGG convolution neural network model (VGG convolution neural network model) The method realizes the recognition of 6 common digital modulation signals, and the recognition rate reaches 98% when the signal-to-noise ratio is -2dB; Talieh uses four kinds of features as the input of the support vector machine, and proposes a fuzzy multi-class classification method For the recognition of 3 different types of digitally modulated signals, the recognition accuracy reaches 77% when the signal-to-noise ratio is 10dB, and its performance is not satisfactory

Images