Method for realizing 2ASK signal and AM signal modulation identification in combination with neural network
A neural network and signal modulation technology, which is applied in modulation type identification, modulated carrier system, digital transmission system, etc., can solve the problem of low recognition accuracy, no consideration of amplitude dynamic changes, and cumulative frequency offset affecting code rate and sampling rate loss Signal and other problems, to achieve the effect of resisting noise data interference
Active Publication Date: 2020-04-28
成都华日通讯技术股份有限公司
View PDF9 Cites 6 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0009] The purpose of the present invention is to provide a method for realizing 2ASK signal and AM signal modulation recognition in combination with neural network, which is used to solve the existing problems in AM and 2ASK recognition in the prior art without considering the dynamic change of amplitude, the influence of cumulative frequency offset, the code rate and the Factors such as loss of signal when the sampling rate does not match, and the problem of low recognition accuracy under low signal-to-noise ratio
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0039] combined with figure 1 As shown, a method for realizing 2ASK signal and AM signal modulation recognition combined with neural network, specifically includes:
[0040] 1. Perform IQ demodulation on the modulated signal received by the receiver, and obtain the discrete data sequences of the I channel and the Q channel respectively: specifically, multiply the received carrier signal by the sine function and the cosine function, and perform integral operations respectively , in this example, for the convenience of demonstration and explanation, it is assumed that the IQ data sequence with a length of 2*n is I 1 ,Q 1 , I 2 ,Q 2 , I 3 ,Q 3 …I n ,Q n ;
[0041] 2. Normalize the complex IQ sequence composed of the I road and the Q road, specifically:
[0042] will get I 1 ,Q 1 , I 2 ,Q 2 , I 3 ,Q 3 …I n ,Q n Sequences are combined into complex sequences of length n: I 1 +j*Q 1 , I2 +j*Q 2 , I 3 +j*Q 3 …I n +j*Q n , and normalize the modulus length of eac...
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
Login to View More Abstract
The invention discloses a method for realizing 2ASK signal and AM signal modulation identification in combination with a neural network, and the method comprises the following steps: performing IQ demodulation on a modulation signal to obtain discrete data sequences of an I path and a Q path; normalizing a complex IQ sequence formed by the I path and the Q path; clustering the IQ coordinate pointswith continuous time on the plural planes; rotating the IQ points on the coordinate plane, rotating and moving all the IQ points near the point agglomeration class according to the deviation angle ofeach point agglomeration class relative to the positive semi-axis of the real axis, and counteracting the frequency offset; converting the rotated IQ points into a signal density map; creating a convolutional neural network model as a signal classification and identification model, and classifying and identifying the density maps of an AM signal and a 2ASK signal. According to the invention, the2ASK signal and AM signal modulation mode can be effectively identified under the non-ideal conditions of low signal-to-noise ratio, frequency offset of received signals, incomplete signals and the like.
Description
technical field [0001] The invention relates to the technical field of radio communication, specifically, a method for realizing modulation recognition of 2ASK signals and AM signals in combination with a neural network. Background technique [0002] The identification of communication signal modulation is an important subject of signal processing research, which is widely used in military and civilian fields. With the rapid development of communication technology, the system and modulation styles of communication signals have become more complex and diverse, and the signal environment has become increasingly dense, making it difficult for conventional identification methods and theories to adapt to actual needs and effectively identify communication signals. At present, the commonly used algorithms for identifying AM and 2ASK are: [0003] 1. Decision recognition based on traditional expert features such as signal instantaneous amplitude and decision threshold; [0004] 2...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): H04L27/00
CPCH04L27/0012
Inventor 吕志良唐珂陈曾张笑语
Owner 成都华日通讯技术股份有限公司