Unlock instant, AI-driven research and patent intelligence for your innovation.

Elman neural network assisted tight combination navigation method when GNSS signal is blocked

A neural network and navigation method technology, applied in the field of tight combination navigation, can solve the problem that the neural network structure is difficult to accurately describe the dynamic characteristics of nonlinear systems, etc.

Inactive Publication Date: 2019-11-22
HARBIN ENG UNIV
View PDF5 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These neural network structures are not easy to accurately describe the dynamic characteristics of nonlinear systems

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 assisted tight combination navigation method when GNSS signal is blocked
  • Elman neural network assisted tight combination navigation method when GNSS signal is blocked
  • Elman neural network assisted tight combination navigation method when GNSS signal is blocked

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0085] The specific embodiments of the present invention will be further described below in conjunction with the accompanying drawings.

[0086] The invention proposes an Elman neural network assisted tight combination algorithm when the GNSS signal is blocked, so that the combined navigation system can continue to provide navigation data when the GNSS signal is short-lived. Take the appropriate hidden layer function to construct the Elman neural network model. When the GNSS signal is blocked, the Elman neural network model is used to continue to complete the navigation and positioning of the tight combination.

[0087] The specific steps are as follows:

[0088] Step 1: Construct the Elman neural network model and select the hidden layer transfer function of the Elman neural network.

[0089] Step 2: Design Elman learning algorithm.

[0090] Step 3: Construct a mathematical model of the compact combined Kalman filter.

[0091] Step 4: Bring the tightly combined Kalman fil...

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 assisted tight combination navigation method when a GNSS signal is blocked. On the basis of inertia and a GNSS tight combination navigation system model, aiming at the tight combination navigation problem when the GNSS signal lose lock, a dynamic Elman neural network prediction model is used for learning an error model of inertial navigation and a compensation model of GNSS; when the GNSS signal is lost, the a neural network is utilized to predict an output error of GNSS and compensate for output of inertial navigation, so that the error is not rapidly diverged, and the system continues to perform combination navigation; and finally, a designed tight combination navigation module at low cost is used for carrying out field measurement, and theacquired information is preprocessed to form sample data for training the neural network, so as to train the Elman neural network model. According to the Elman neural network assisted tight combination navigation method, the algorithm can be used for carrying out prediction under the condition that the GNSS signal is lost for 100 s, so that the system can still carry out tight integration navigation.

Description

technical field [0001] The invention relates to a tight combination navigation method, in particular to an Elman neural network assisted tight combination navigation method when GNSS signals are blocked, and belongs to the technical field of navigation. Background technique [0002] The inertial navigation system can fully and autonomously provide navigation information, but under low-cost equipment, the error of the inertial navigation system will continue to accumulate over time. GNSS has a wide positioning range and high precision, but its disadvantage is that it is prone to signal occlusion and interference. Therefore, the characteristics of inertial navigation and GNSS are complementary, and the tight combination of inertial navigation and GNSS can give full play to the advantages of these two systems. Tight combination also improves the accuracy and reliability of the navigation system. But for the tight integrated navigation system, when the satellite signal is unav...

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): G01C21/16G01S19/47
CPCG01C21/165G01S19/47G06N3/084G06N3/044G01C21/188G06N5/046
Inventor 赵琳彭子航丁继成王坤柏亚国张永超王仁龙
Owner HARBIN ENG UNIV