Geomagnetic model online approximation method based on Legendre polynomial and BP neural network

A BP neural network, BP network technology, applied in the field of online approximation of the geomagnetic model of the BP neural network, can solve the problems of insufficient reference field accuracy and so on

Active Publication Date: 2019-06-07
SOUTHEAST UNIV
View PDF10 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Purpose of the invention: Aiming at the problems existing in the prior art, the present invention provides a geomagnetic model online approximation method based on Legendre polynomials and BP neural network, which overcomes the problem of insufficient accuracy of the reference field and is suitable for regional geomagnetic-assisted inertial navigation The measurement modeling of the system can realize the online approximation of the geomagnetic model, improve the accuracy of the geomagnetic model, and then improve the positioning accuracy of the integrated navigation 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
  • Geomagnetic model online approximation method based on Legendre polynomial and BP neural network
  • Geomagnetic model online approximation method based on Legendre polynomial and BP neural network
  • Geomagnetic model online approximation method based on Legendre polynomial and BP neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] In order to make the object, technical solution and advantages of the present invention clearer, the specific implementation cases of the present invention will be described below in conjunction with the accompanying drawings.

[0051] The invention discloses a

[0052] The geomagnetic model online approximation method based on Legendre polynomial and BP neural network comprises the following steps:

[0053] Step 1. Read the position information pos indicated by the k integrated navigation system at the current moment k =[L k lambda k h k ] T and aircraft navigation error where λ k is the longitude, L k is the latitude, h k is the elevation value, is the error of the j-axis of the platform misalignment angle of the integrated navigation system in the geographic coordinate system, is the error of the speed of the integrated navigation system on the j-axis, δλ k is the longitude error, δL k is the latitude error; j∈{E,N,U}; the longitude range of the deter...

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 geomagnetic model online approximation method based on a Legendre polynomial and a BP neural network. The method includes the following steps that: 1, position information and aircraft navigation error which are indicated by a current integrated navigation system, and the measured value of a geomagnetic sensor are read; 2, a Legendre polynomial model is established according to a priori geomagnetic map; 3, a BP neural network is constructed, with the position information and aircraft navigation error adopted as input, the difference value of the measured value of thegeomagnetic sensor and the read value of the Legendre polynomial adopted as output, the constructed BP neural network is trained, so that the expression of input and output can be obtained, and geomagnetic model error at the current moment is obtained according to the read position information and aircraft navigation error; and 4, the geomagnetic value of the geomagnetic model at the current position at the current moment is corrected. The method is applicable to the measurement modeling of a regional geomagnetic assisted inertial navigation system and can realize the online approximationof the geomagnetic model, improve the accuracy of the geomagnetic model, and improve the positioning accuracy of the integrated navigation system.

Description

technical field [0001] The invention belongs to the technical field of geomagnetic-assisted inertial navigation, and in particular relates to an online approximation method of a geomagnetic model of a BP neural network. Background technique [0002] The passive navigation method of underwater vehicles mainly relies on inertial navigation. The inertial navigation system (INS) uses accelerometers and gyroscopes to perform dead reckoning and attitude calculations, but its navigation errors will diverge over time, which limits the dive time of the aircraft, making it difficult to achieve long-term navigation accuracy. ensure. The geomagnetic field is the inherent field of the earth. Theoretically, the geomagnetic information under each geographic coordinate is unique and can be used as a natural navigation coordinate system. Therefore, underwater inertial / geomagnetic integrated navigation is a hot spot in underwater vehicle navigation research. [0003] Geomagnetism-assisted ...

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): G01C21/20G01C21/16
Inventor 王立辉刘庆雅
Owner SOUTHEAST 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