Bearing fault diagnosis method and system device based on improved empirical wavelet transform

An empirical wavelet and fault diagnosis technology, applied in the field of signal analysis, can solve the problems of inaccurate mode decomposition and inconspicuous fault characteristics, and achieve the effect of improving the unreasonable spectral division, avoiding mode aliasing, and improving accuracy.

Inactive Publication Date: 2018-08-07
WUHAN UNIV OF SCI & TECH
View PDF10 Cites 40 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to provide a new spectrum segmentation method, aiming to solve the problem that the mode decomposition caused by noise is inaccurate and the fault characteristics are not obvious

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
  • Bearing fault diagnosis method and system device based on improved empirical wavelet transform
  • Bearing fault diagnosis method and system device based on improved empirical wavelet transform
  • Bearing fault diagnosis method and system device based on improved empirical wavelet transform

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0060] Embodiment 1: A bearing fault diagnosis method based on improved empirical wavelet transform, using the collected bearing signal as an analysis signal, and using sequential statistical filtering to convert the frequency peak into a corresponding flat top to form an upper envelope. Then filter out the highest flat-top in the frequency domain according to three criteria, remove the flat-top caused by noise and meaningless, and keep the main frequency. Next, the minimum value between adjacent flat tops is selected as the boundary of spectrum segmentation. Finally, a suitable empirical wavelet filter bank is established for each frequency band, the signal is decomposed into N mode components, and the corresponding frequency domain transformation is performed to extract the characteristic frequency. Such as figure 1 As shown, the method steps are as follows:

[0061] (1) The diagnostic module obtains the fault signal, and the diagnostic module respectively performs Fourier...

Embodiment 2

[0116] Such as Figure 14 As shown, based on the above method, the present invention also provides a bearing fault diagnosis system based on improved empirical wavelet transform, and the system includes:

[0117] The monitoring module is used to obtain different faulty bearing signals as analysis signals, convert the time-domain waveform to the frequency domain; draw the upper envelope of the spectrum, and convert the frequency peaks with tight supports into flat tops; filter the flat tops in the frequency domain with criteria , remove meaningless flat-tops, and retain the main frequency; use the minimum value between adjacent flat-tops as the boundary of spectrum segmentation; separate the separated spectrum to establish wavelet filters to decompose the signal into N mode components; The relationship coefficient calculates the similarity between the mode component and the original signal, and selects the component with the highest similarity; takes samples from the fault, and...

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 provides a bearing fault diagnosis method and system device based on improved empirical wavelet transform. The method comprises: step one, collecting different fault bearing signals as analysis signals and converting a time domain waveform into a frequency domain waveform; step two, drawing an upper envelope of a frequency spectrum and transforming a frequency peak with a tight support into a flat top; step three, screening flat tops in the frequency domain based on criteria, removing meaningless flat tops, and keeping a main frequency; step four, using a minimum value between adjacent flat tops as the boundary of spectrum segmentation; step five, establishing wavelet filters respectively for segmented frequency spectrums and decomposing the signals into N mode components; step six, calculating similarity values between mode components and the original signals by using a cross-correlation coefficient and selecting a component with the highest similarity value; and step seven, taking a fault sample, calculating an IMF component with the largest correlation coefficient of the sample, calculating a multi-scale entropy of the IMF component, and drawing the multi-scale entropy curve of the sample to realize fault classification.

Description

technical field [0001] The method of the invention belongs to the field of signal analysis. Due to the unreasonable spectrum segmentation method of traditional empirical wavelet transform, mode aliasing and meaningless components appear in the decomposition results. The present invention provides a bearing fault diagnosis method based on Improved Empirical Wavelet Transform (IEWT), aiming at increasing the accuracy of decomposition modes, thereby improving the accuracy of fault classification. Background technique [0002] Bearings are important supporting components in mechanical transmission systems. Affected by harsh working conditions, frequent failures often seriously affect the normal production and operation of enterprises. In order to ensure the normal operation of equipment, bearing fault diagnosis is very important. Empirical Wavelet Transform (EWT), which combines the theory of wavelet analysis and the adaptability of Empirical Mode Decomposition (EMD), has both ...

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): G01M13/04G06K9/00G06K9/62
CPCG01M13/045G06F2218/06G06F18/24
Inventor 吕勇郝爽易灿灿
Owner WUHAN UNIV OF SCI & TECH
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