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

Elman neural network and Kalman fusion filtering algorithm based on wavelet threshold method

A wavelet threshold method and neural network technology, applied in the field of navigation, guidance and control, can solve the problems of poor practicality and achieve the effect of improving accuracy and reliability

Pending Publication Date: 2022-07-01
BEIJING AEROSPACE ERA LASER NAVIGATION TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem solved by the present invention is: aiming at the problem that in the current prior art, using the residual error of the correlator to update the navigation parameters and using the updated navigation parameters to predict the signal to track the loop parameters is not practical in engineering application, and proposes A Fusion Filter Algorithm of Elman Neural Network and Kalman Based on Wavelet Threshold Method

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
  • Elman neural network and Kalman fusion filtering algorithm based on wavelet threshold method
  • Elman neural network and Kalman fusion filtering algorithm based on wavelet threshold method
  • Elman neural network and Kalman fusion filtering algorithm based on wavelet threshold method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0080] An Elman neural network and Kalman fusion filtering algorithm based on wavelet threshold method, in the case of short-term GPS failure, to predict and estimate the position and attitude of the carrier, and the specific process of the positioning method is as follows:

[0081] (1) Filter the sensor data, and use the wavelet threshold method to determine the triaxial angular rate ω output by the inertial navigation system. 3 Perform noise reduction processing to obtain the triaxial angular velocity w after noise reduction processing 3 ;

[0082] (2) Through the neural network module of inertial navigation, use GPS and the inertial navigation data after wavelet threshold noise reduction obtained in step (1) for training, the analyzed three-axis velocity v 3 , the angular velocity w after noise reduction 3 and comparison information f 3 Increment with GPS position Relationship;

[0083] (3) The GPS data and INS data are fused by the loose combination Kalman filter met...

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 Elman neural network and Kalman fusion filtering algorithm based on a wavelet threshold method, and aims to solve the problem of GPS interruption and enhance the traditional GPS / INS integrated navigation performance. When the GPS signal is available, the neural network module can be trained by using the GPS and the inertial navigation data subjected to wavelet threshold noise reduction, and the relationship between the speed, angular speed and specific force information of the inertial navigation system and the GPS position increment is analyzed. And when the GPS signal is interrupted, the trained neural network module can output an estimated GPS position by using the previously trained error model and inertial navigation real-time data, and corrects an inertial navigation output result by using a Kalman filtering algorithm.

Description

technical field [0001] The invention relates to an Elman neural network and Kalman fusion filtering algorithm based on a wavelet threshold method, belonging to the fields of navigation, guidance and control. Background technique [0002] Global Positioning System GPS and Inertial Navigation System are two common positioning systems. GPS can maintain good stability in the long-term navigation range, but its multipath effect will cause signal blocking and loss in some environments, resulting in the degradation of navigation performance; inertial navigation system is composed of inertial measurement unit (IMU) The independent system formed can provide dynamic measurement data through high-frequency update, but the error of its sensor will accumulate with the increase of time, resulting in the continuous decline of positioning accuracy. In order to absorb the advantages of these two systems and make up for their respective shortcomings, the INS / GPS integrated navigation system ...

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): G01S19/37G01C21/16G01S19/49G06K9/00G06K9/62G06N3/04G06N3/08
CPCG01S19/37G01C21/188G01S19/49G01C21/165G06N3/08G06N3/045G06F2218/06G06F18/251G06F18/214
Inventor 李晶李长春李丹华
Owner BEIJING AEROSPACE ERA LASER NAVIGATION TECH CO LTD
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