Signal demodulation method based on end-to-end cascade generative adversarial network

Abstract

The invention discloses a signal demodulation method based on an end-to-end cascade generative adversarial network. The method comprises the following steps: 1, carrying out dimension transformation on modulation information and demodulation information through data preprocessing to serve as a data set of a generative adversarial network; 2, mapping from modulation information to demodulation information is realized based on a demodulation model of the GAN network, so that signal demodulation is realized; 3, compensating the received information based on a channel estimation compensation model of the CGAN network, and then mapping to obtain stable modulation information; and 4, cascading the channel estimation compensation model based on the CGAN network and the demodulation model of the GAN network to form an end-to-end cascading generative adversarial network demodulation model. According to the method, the demodulation capability of the whole system is improved by utilizing the advantage that the target function of the GAN network is more constraint. In addition, a good coping strategy is still provided for a Gaussian channel and a Rayleigh fading channel.

Description

technical field [0001] The invention mainly aims at the modulation signal transmitted under the Gaussian channel and the Rayleigh fading channel, and mainly relates to an end-to-end cascaded generation confrontation network signal demodulation method. Background technique [0002] Traditional wireless communication is a complete system including multiple communication processing modules based on a signal transmitter and a signal receiver. Although the traditional wireless communication system technology is becoming more and more mature, and the technology between each communication module is also tending to be perfect, but with the gradual complexity of the communication environment, low signal-to-noise ratio transmission, dense signal transmission, and multi-interference transmission appear, making the current The communication capabilities of some communication modules are challenged, and even cannot meet the communication conditions in some relatively harsh situations. C...

AI Technical Summary

Problems solved by technology

[0003] So far, digital signal demodulators based on CNN networks have made breakthroughs compared with traditional coherent demodulation algorithms, but are limited by the problems of traditional CNN structure and objective functions, resulting in model learning and mapping capabilities that cannot reach the ideal level. Therefore, in The signal demodulation performance is average when faced with a complex transmission environment or a high-noise transmission environment

Images