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

MIMU gyroscope random drift forecasting method based on ARMA and BPNN combination model

A technology of random drift and combined models, applied in neural learning methods, biological neural network models, measurement devices, etc., can solve problems such as filtering out useful signals, improper selection of wavelet layers, easy leakage of identification noise, etc. Modulo error, the effect of improving prediction performance

Active Publication Date: 2017-11-07
HARBIN INST OF TECH
View PDF15 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In the existing gyroscope random error modeling, common methods to reduce gyroscope random drift are Allan variance method, wavelet analysis method and Kalman filter method. Although Allan variance method is easy to calculate and easy to separate errors, it is easy to leak power and Quantitative expression method is single
The wavelet analysis method can decompose the signal in any detail, and is suitable for analyzing and processing non-stationary signals. However, if the number of wavelet layers is not selected properly, useful signals will be filtered out.
The Kalman filter method can be used for the estimation of time-varying, non-stationary and multidimensional signals, but the noise must be assumed to be a Gaussian process whose statistical properties are known

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
  • MIMU gyroscope random drift forecasting method based on ARMA and BPNN combination model
  • MIMU gyroscope random drift forecasting method based on ARMA and BPNN combination model
  • MIMU gyroscope random drift forecasting method based on ARMA and BPNN combination model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The present invention describes a predictive modeling method for MIMU gyroscope random errors. The invention adopts the predictive fitting algorithm of ARMA and BP neural network combination model. In order to obtain a more accurate gyroscope random drift model, the single ARMA model and BP The neural network cannot fully express the shortcomings of linear and nonlinear relationships. The proposed model prediction method is suitable for MIMU, and can greatly reduce the model prediction error and improve the accuracy of the model prediction. The design scheme of the present invention is as figure 1 As shown, the steps are as follows:

[0023] Step 1: Preprocess the real-time output data of the MIMU gyroscope. The random drift data of the single-axis gyroscope is collected in a static state, the stationarity of the original data sequence is judged, the correlation test is carried out on the test data of the gyroscope, and the order of the ARMA model is preliminarily dete...

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 MIMU gyroscope random drift forecasting method based on an ARMA and BPNN combination model. The method mainly includes the steps that 1, random drift data of a single-axle micro gyroscope is collected in the static state, the stationarity of an original data sequence of a gyroscope is judged by observing graphic characteristics of an autocorrelation parameter ACF and a partial correlation parameter PACF, an ADF unit root is checked, and stationary data is obtained after a trend term of the sequence is removed through differences; 2, the stationary sequence of the gyroscope is subjected to model order determination with the AIC minimum rule method, and an ARMA model of a gyroscope drift stationary sequence is established; 3, a random drift sequence of the gyroscope is modeled through the combination model, a training set and a test set are selected from error data of the ARMA model in the step 2, and a BP neural network forecasting model is established, and the structure of a BP neural network is set; 4, sample data of the established BP neural network is trained, and the forecasting result of gyroscope random drift is preserved.

Description

technical field [0001] The invention relates to the random drift prediction of MIMU (Micro Inertial Measurement Unit) in a deep integrated navigation system, in particular to a gyroscope random drift error prediction and fitting method. Background technique [0002] With the continuous improvement of integrated circuit silicon semiconductor manufacturing technology, micro-machine manufacturing technology has made great progress, and MEMS (Micro-Electro-Mechanical System) inertial sensors have emerged. At the same time, it has the characteristics of small size, light weight, high reliability, impact resistance, easy installation, mass production, and low cost. It is integrated with microelectronic processing circuits to achieve mechatronics. In particular, with the continuous improvement of the precision of MEMS inertial sensors, in the navigation system equipment in the military field, the strapdown inertial navigation system using micro-mechanical inertial instruments as in...

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): G06F17/50G06N3/08G01C25/00
CPCG06N3/084G01C25/005G06F30/20
Inventor 沈锋徐定杰武哲民高伟高畅
Owner HARBIN INST OF 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