Multi-scale extreme learning machine training method for fiber optic gyroscope temperature drift based on emd

An extreme learning machine, temperature drift technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve the problems of complex modeling process, limited ability to approximate complex nonlinearity, etc.

Active Publication Date: 2017-08-25
SOUTHEAST UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Non-stationary modeling methods based on time series analysis, such as the autoregressive differential moving average (ARIMA) model, the modeling process is complex, and the ability to approximate complex nonlinearities is limited

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
  • Multi-scale extreme learning machine training method for fiber optic gyroscope temperature drift based on emd
  • Multi-scale extreme learning machine training method for fiber optic gyroscope temperature drift based on emd
  • Multi-scale extreme learning machine training method for fiber optic gyroscope temperature drift based on emd

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] This embodiment mainly includes the following steps:

[0039] Step 1: Use the BEEMD method to adaptively decompose the temperature drift data into a series of intrinsic mode functions (IMF), set the temperature drift data as x(t), and the order of noise assistance as M=m-1, add Gaussian white noise w j The degree of (t) is I, and the noise variance is where k is the current decomposed IMF order, which is initially 1, and j represents the count of noise-assisted realization, and the decomposition process is:

[0040] Initialize variable j=0,

[0041] add random white noise to which is Update j=j+1, where E v (χ) represents the operation operator for taking the vth order IMF of the sequence χ, in particular, v=1 represents the original χ sequence;

[0042] find out All extremums of , use the cubic spline difference to construct the upper and lower envelopes of the sequence, calculate the envelope mean value m(t), and update

[0043] judge Whether the I...

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 EMD-based multi-scale extreme learning machine training method for fiber optic gyroscope temperature drift. EEMD) method is decomposed into a series of intrinsic mode functions; 2) using the sample entropy (SE) measurement theory to calculate the SE value of the intrinsic mode function (IMF) in 1); 3) according to the fluctuation trend of the SE value and Determine the size of the noise-dominated IMF set and the IMF set with different self-similar features; 4) superimpose the IMFs determined in step 3) with similar self-similar features as the ELM model training input, and use the temperature variable speed corresponding to the set of output data The temperature gradient under the rate is used as another input training ELM model, similarly, different self-similarity IMF superposition and corresponding temperature gradient training generate different ELM models; Integrate multiscale models.

Description

technical field [0001] The invention relates to an EMD-based multi-scale extreme learning machine training method for fiber optic gyroscope temperature drift, which belongs to the field of modeling compensation of inertial devices, and can also be used for modeling other error signals with non-stationary characteristics. Background technique [0002] The interferometric fiber optic gyroscope (IFOG) is greatly affected by the ambient temperature, and its constantly changing temperature field inside the fiber ring leads to constant changes in the thermal expansion coefficient and refractive index of the fiber material, and these changes are anisotropic at different positions of the fiber ring , resulting in thermally induced non-reciprocal phase shift errors. It is very difficult to improve the accuracy of medium and high-precision fiber optic gyroscopes in terms of mechanism. In engineering, methods such as improving fiber winding technology, adding temperature control equipm...

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 Patents(China)
IPC IPC(8): G06F17/50
Inventor 陈熙源崔冰波宋锐何昆鹏方琳
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

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