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

An Improved Fault Diagnosis Method of Limit Learning Machine Based on Information Reconstruction

A technology of extreme learning machine and fault diagnosis, which is applied in computer parts, instruments, character and pattern recognition, etc.

Inactive Publication Date: 2019-02-01
LIAONING UNIVERSITY
View PDF5 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] There are many deficiencies that cannot be avoided in the training process of the model in the prior art

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
  • An Improved Fault Diagnosis Method of Limit Learning Machine Based on Information Reconstruction
  • An Improved Fault Diagnosis Method of Limit Learning Machine Based on Information Reconstruction
  • An Improved Fault Diagnosis Method of Limit Learning Machine Based on Information Reconstruction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The improved extreme learning machine fault diagnosis method for information reconstruction is characterized in that the steps are as follows:

[0045] 1) Acquisition signal: collect bearing data, according to the inner ring, outer ring, ball and normal state (not very smooth, the meaning expression is not clear, and needs to be modified).

[0046] 2) Signal processing: Decompose the signal through the empirical mode decomposition method to decompose multiple intrinsic mode components, and each mode component is detected by the proposed weighted permutation entropy to filter out noise and reconstruct the original Some single-frequency signal sequences;

[0047] The calculation method of weighted permutation entropy is as follows:

[0048] The formula for weighted permutation entropy is as follows:

[0049]

[0050] In the formula: m ij Indicates the evaluation value of item i under the j index, and this formula calculates the weight of the entropy value i under th...

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 relates to an improved fault diagnosis method of a limit learning machine based on information reconstruction, which comprises the following steps: 1) collecting signals; 2) signal processing; 3) feature extraction; 4) division of fault diagnosis; the invention is based on the permutation entropy (PE) thought, and proposes the weighted permutation entropy (WPE) thought. By weightingthe entropy characteristic of the common permutation entropy, the characteristic information becomes more sensitive, the change of the characteristic information can be well presented, and the foundation for the characteristic selection is provided. In addition, a new method based on Filter-Wrapper (filter-package) method discriminates the features effectively, minimizes the error by constantly adjusting the output weight of the network, minimizes the error of the output result of the limit learning machine, and compares the result with the result of the traditional limit learning machine, thereby verifying the effectiveness of the invention.

Description

technical field [0001] The invention relates to an improved extreme learning machine fault diagnosis method for information reconstruction, which belongs to the technical field of rolling bearing fault diagnosis and prevention. Background technique [0002] Bearings have always been a vital component in large mechanical equipment, and their operating status has a huge impact on the entire mechanical equipment. Moreover, the failure of rolling bearings often occurs in the failure of rotating machinery equipment. According to incomplete statistics, about 30% of all large-scale mechanical accidents and disasters are caused by mechanical failures. Among them, nearly 60% to 70% are caused by a series of various equipment damages due to bearing failure. The reason is that mechanical equipment is often affected by harsh working conditions, and mechanical equipment often has to undertake high-load work, so fault diagnosis for rolling bearings has always been a research hotspot in f...

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): G06K9/62
CPCG06F18/214G06F18/24
Inventor 张利郭炜儒张皓博高欣邱存月周佳宁王军
Owner LIAONING UNIVERSITY
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