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

Communication interference method based on generative adversarial network

A communication interference and network technology, applied in the field of communication interference, can solve problems such as unusability, achieve good interference effects, solve signal interference of unknown signals and dynamic changes in parameters, and reduce the effect of manual decision-making process

Pending Publication Date: 2021-01-05
NAT UNIV OF DEFENSE TECH
View PDF4 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method cannot be used when the interfering party cannot obtain feedback information from the target system

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
  • Communication interference method based on generative adversarial network
  • Communication interference method based on generative adversarial network
  • Communication interference method based on generative adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0077]Example 1 Learning rate optimization experiment

[0078]At present, GAN is mostly used in the field of computer vision to process two-dimensional picture data with complex features, while the present invention requires GAN to process one-dimensional time series data with simpler features than two-dimensional pictures. Changes in data dimensions and characteristics make the required learning rate different. Therefore, first, taking BPSK signal as an example, an optimization experiment of learning rate is carried out, and a suitable learning rate is selected to realize the generation of communication signals.

[0079]Set the learning rate to 0.0001 and 0.001 to experiment, and the number of training is from 1000 to 90000. The loss function curve is as followsFigure 4 (a) ~ (b) shown. FromFigure 4 It can be seen that, because the two networks are fighting each other, regardless of the overall trend, the loss functions of the two networks are in violent fluctuations. When the learning r...

Embodiment 2

[0082]Example 2 Network application generalization experiment

[0083]The traditional interference method is based on the detected target signal characteristics to select the appropriate interference waveform to implement the interference. The GAN-based communication interference waveform generation technology proposed in the present invention directly uses GAN to learn the collected target signal time-domain waveform , Obtain its potential characteristics, and generate waveforms with similar characteristics as interference waveforms, without prior knowledge about target characteristics, and have stronger generalization than traditional interference methods. The following is an experimental investigation on the application effect of GAN on different target communication signals to verify its generalization.

[0084]In experiment 1, the time-domain waveform of the BPSK signal was sampled to make a data set, and the network was trained. In order to show that GAN has a good effect on other t...

Embodiment 3

[0086]Example 3 Interference effect comparison experiment

[0087]The ultimate goal of communication interference waveform generation is to achieve effective interference. In order to illustrate the effectiveness of the interference waveform generation method of the present invention and the superiority of the traditional method, the interference effect comparison test was carried out between the method of the present invention and the best interference and Gaussian noise interference.

[0088]In the experiment, in order to fully observe the interference effect, taking the length of 10,000 symbols as an example, the interference waveform, the best interference waveform and Gaussian noise generated after training 80,000 times are used to interfere with the target communication system. The comparison is repeated 100 times, the average bit error rate is taken, and the interference effect comparison chart is drawn. For BPSK and QPSK communication systems, the best interference is the communic...

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 discloses a communication interference method based on a generative adversarial network. The method comprises the following steps: constructing a GAN network model; collecting a target signal time domain waveform of a target communication system, and making a training set; training the GAN network model by using the training set of the target signal, changing the learning rate, training for multiple times, observing the change trend and the generated waveform of the loss function under different learning rates, and when the network loss function tends to be stable within the settraining times and the generated waveform with the same time domain and frequency domain characteristics as the signal in the training set can be generated, fixing the learning rate; training the network under the determined learning rate to generate an interference waveform with the same time domain and frequency domain characteristics as the signals in the training set; and applying interferenceto the target communication system by using the generated interference waveform. Characteristics of the target signal can be autonomously extracted, the interference waveform is generated to implement interference, and application generalization is achieved while good interference effect is achieved.

Description

Technical field[0001]The invention relates to the technical field of communication interference, in particular to a communication interference method based on a generation countermeasure network.Background technique[0002]Communication jamming is an important research direction in the field of communication countermeasures. On the basis of obtaining the prior information of the target signal through communication reconnaissance methods, the communication jamming system suppresses the communication process of the target signal by generating an interference signal associated with the target signal And destruction, and ultimately achieve the purpose of weakening or even blocking the communication capabilities of the other party.[0003]In general, the existing communication interference methods rely more on communication reconnaissance methods. It is necessary to select from a fixed interference strategy library or formulate an interference strategy based on user experience on the basis o...

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 Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/048G06N3/045G06F2218/10G06F2218/04G06F18/214
Inventor 金虎赵凡钱锋冯辉蔡晓霞陈红徐云姜丽
Owner NAT UNIV OF DEFENSE TECH
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com