Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Demodulation method of dqpsk modulated signal based on cnn and lstm

A technology for modulating signals and demodulation methods, applied in modulation carrier system, phase modulation carrier system, digital transmission system, etc., can solve the problem of high bit error rate, simplify demodulation system, increase versatility and flexibility, improve Effect of demodulation rate

Active Publication Date: 2020-11-24
XIDIAN UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0011] The purpose of the present invention is to overcome the deficiencies in the above-mentioned prior art, and provides a method for demodulating DQPSK modulated signals based on CNN and LSTM, which is used to solve the high bit error rate existing in the existing DQPSK modulated signal demodulation method technical issues

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Demodulation method of dqpsk modulated signal based on cnn and lstm
  • Demodulation method of dqpsk modulated signal based on cnn and lstm
  • Demodulation method of dqpsk modulated signal based on cnn and lstm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments.

[0040] refer to figure 1 , a kind of DQPSK modulated signal demodulation method based on CNN and LSTM, comprises the steps:

[0041] Step 1) Obtain DQPSK modulation signal E 1 The sampling sequence s 1 and token sequence m:

[0042] Step 1a) Simulation generates a symbol sequence O comprising 1000 double-bit symbols, and carries out Gray differential encoding on the double-bit symbol sequence O to obtain an encoded double-bit symbol sequence comprising 1001 double-bit symbols o 1 , for the encoded double-bit symbol sequence O 1 Carry out QPSK modulation and add additive Gaussian white noise to obtain a signal-to-noise ratio of 20dB and a symbol period of 10 -6 s, the carrier period is 2.5×10 -7 The DQPSK modulated signal E of s 1 ;

[0043] Step 2a) DQPSK modulated signal E with a sampling rate of 32Msps 1 Sampling to obtain...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a CNN (Convolutional Neural Network) and LSTM (Long Short Term Memory)-based DQPSK (Differential Quadrature Phase Shift Keying) modulating signal demodulating method, and solvesthe technical problem of high demodulating error rate in an existing DQPSK signal demodulating method. The method comprises the following realizing steps: acquiring a sampling sequence and a symbol sequence of a DQPSK modulating signal; constructing a CNN and training the CNN; constructing an LSTM and training the LSTM; acquiring an output sequence of the trained CNN; determining sampling data corresponding to each code element period of the DQPSK modulating signal in the sampling sequence; and acquiring a demodulating result of the to-be-demodulated DQPSK modulating signal. According to theCNN and LSTM-based DQPSK modulating signal demodulating method, a boundary of a code element of the DQPSK modulating signal is judged through the CNN, and the problems of Doppler frequency shift, a sampling clock error and the like can be solved; acquisition of demodulating data of the DQPSK modulating signal is directly completed by using the LSTM; and the problem of high demodulating error ratecaused by an uncertain boundary of the code element of the modulating signal is solved.

Description

technical field [0001] The invention belongs to the technical field of digital communication, relates to a DQPSK modulation signal demodulation method, in particular to a DQPSK modulation signal demodulation method based on CNN and LSTM, which can be used for satellite communication and deep space communication. Background technique [0002] In order to transmit a digital signal in a bandpass channel, the carrier must be modulated with a digital baseband signal to match the signal to the characteristics of the channel. This process of controlling the carrier with a digital baseband signal and converting the digital baseband signal into a digital bandpass signal is called digital modulation, and the process of restoring the bandpass signal to a digital baseband signal through a demodulator at the receiving end is called digital demodulation. Digital modulation includes phase shift keying (Phase Shift Keying, referred to as PSK), amplitude shift keying (Amplitude Shift Keying,...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): H04L27/22H04L27/233
CPCH04L27/22H04L27/2338
Inventor 王海刘宗延俞忠伟张敏秦红波
Owner XIDIAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products