OFDM channel estimation and signal detection method based on deep learning

A channel estimation and signal detection technology, which is applied in the field of OFDM channel estimation and signal detection based on deep learning, and can solve the problems of higher diversity of channel sample data and complex mechanism.

Active Publication Date: 2020-07-10
BEIHANG UNIV
View PDF6 Cites 43 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for the UAV data link OFDM channel estimation and signal detection problems in complex environments, the mechanism of multipath effects is more complex than that of general scenarios, and the diversity of channel sample data is required to be higher

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
  • OFDM channel estimation and signal detection method based on deep learning
  • OFDM channel estimation and signal detection method based on deep learning
  • OFDM channel estimation and signal detection method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] The specific implementation method of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0056] The present invention is an OFDM channel estimation and signal detection method based on deep learning, which uses a deep neural network to realize OFDM multipath channel estimation and original signal detection, and can quickly and accurately restore the original signal.

[0057] like figure 2 As shown, it specifically includes the following steps:

[0058] Step 1, generate a sample database of the OFDM multipath channel model matrix in a complex environment based on the existing Non-WSSUS channel model;

[0059] The present invention performs multi-path channel modeling in a complex environment based on a Non-Wide-Sense Stationary Uncorrelated Scattering (Non-WSSUS) channel model, and generates channel matrix sample data accordingly. The Non-WSSUS channel model is based on the time-frequency transformation function, w...

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 an OFDM channel estimation and signal detection method based on deep learning, and belongs to the field of unmanned aerial vehicle measurement and control communication. The method comprises the following steps: firstly, generating a sample database of an OFDM multipath channel model matrix in a complex environment based on an existing No-WSSUS channel model; then, constructing a neural network comprising a channel estimation sub-network and a signal detection sub-network, and training the neural network by utilizing the data sample of the multipath channel model matrix; finally, applying the trained neural network to the OFDM data link system of the unmanned aerial vehicle in a complex environment in an off-line mode, and detecting signals while a channel is estimated. According to the method, a large-data-volume channel sample set capable of reflecting OFDM channel characteristics in a complex environment is generated, so that the whole network can effectivelyreflect nonlinear characteristics of a wireless channel and a transmission signal.

Description

technical field [0001] The invention belongs to the field of unmanned aerial vehicle measurement and control communication, and specifically refers to an OFDM channel estimation and signal detection method based on deep learning. Background technique [0002] The UAV data link is an important part of the UAV system, which realizes functions such as remote control telemetry and reconnaissance information return to the UAV platform. When the UAV performs tasks in a complex geographical terrain environment, the data link system is often affected by the "Multipath Effect (Multipath Effect)", that is, the data link receiver not only receives the direct wave from the transmitter, but also receives From different reflection surfaces in the environment (diffuse reflection or specular reflection) reflected waves with different amplitudes and phases, and then generate inter-symbol interference (Inter-Symbol-Interference, ISI), the width of the received signal is extended due to multip...

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): H04L25/02H04L25/03G06N3/04G06N3/08
CPCH04L25/0212H04L25/0242H04L25/03006G06N3/08G06N3/045
Inventor 刘春辉王美琳丁文锐
Owner BEIHANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap