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

Detection method of UAV micro-movement feature signal based on weight-agnostic neural network

A neural network and feature signal technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve the problem of difficult observation of micro-motion feature signals, and achieve good sparse characteristics, good anti-interference, and low computational cost. Effect

Active Publication Date: 2022-03-18
GUILIN UNIV OF ELECTRONIC TECH
View PDF18 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problem that the micro-motion characteristic signal is difficult to observe, and to provide a method for detecting the micro-motion signal of the UAV based on the weight-agnostic neural network

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
  • Detection method of UAV micro-movement feature signal based on weight-agnostic neural network
  • Detection method of UAV micro-movement feature signal based on weight-agnostic neural network
  • Detection method of UAV micro-movement feature signal based on weight-agnostic neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0037] refer to figure 1 , a UAV micro-movement feature signal detection method based on a weight-agnostic neural network, including the following steps:

[0038] 1) Calculate the cyclic spectrum of the signal: such as figure 2 As shown, taking the FM frequency modulation signal x(t) as an example, the signal is a generalized cyclostationary process, and its autocorrelation function is:

[0039] R x (t,τ)=E[x(t)x * (t-τ)] (1),

[0040] due to R x (t,τ) is a periodic function with time T as the period, so for R x (t,τ) is expanded by Fourier series, and the following formula is obtained:

[0041]

[0042] In the formula: α=m / T, which is called the cyclic frequency of the signal x(t), 1 / T is the basis of the cyclic frequency, and the coefficient of its Fourier series is:

[0043]

[0044] In the formula: is the cyclic autocorrelation function of the signal x(t), which is also a function of the cyclic frequency α and the time interval τ, and the cyclic autocorrela...

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 method for detecting the micro-motion characteristic signal of an unmanned aerial vehicle based on a weight-agnostic neural network, which is characterized in that it comprises the following steps: 1) calculating the cyclic spectrum of the signal; 2) obtaining the contour map of the cyclic spectrum through MATLAB processing , and select the observation area; 3) Train the weight-agnostic neural network; 4) Use the trained weight-agnostic neural network for micro-motion feature recognition. This method has good anti-interference, the structure of the neural network is simpler, the amount of calculation is smaller, and the accuracy of the recognition of the micro-movement characteristic signal of the UAV is higher.

Description

technical field [0001] The invention relates to the field of UAV signal detection, in particular to a method for detecting UAV micro-motion characteristic signals based on a weight-agnostic neural network. Background technique [0002] Although the widespread popularity of drones has led to the development and transformation of related industries, due to the inadequacy of the legal system and market system, as well as other factors, incidents of drones disrupting navigation and threatening public safety have also occurred frequently, resulting in relatively Therefore, effective supervision and regulation of drones is urgent. The rotation of the UAV's rotor will micro-modulate the scattered electromagnetic wave signal, but the UAV is a "low, slow and small" target. observed. [0003] In recent years, neural networks have made breakthroughs in the field of feature recognition, and some scholars have applied neural networks to modulation recognition of communication signals. ...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V10/431G06N3/045G06F2218/02G06F2218/08G06F2218/12G06F18/241
Inventor 谢跃雷刘信蒋平易国顺许强邓涵方肖潇蒋俊正欧阳缮廖桂生
Owner GUILIN UNIV OF ELECTRONIC 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