A vibration signal denoising method and system based on independence

A vibration signal and independent technology, which is applied to the recognition of patterns in signals, instruments, characters and patterns, etc., can solve the problems of amplitude uncertainty, unsatisfactory separation results, and influence on separation effects, etc., to achieve feature extraction, Solve the problem of algorithm failure and accurately determine the effect

Active Publication Date: 2019-01-25
YANSHAN UNIV
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, during the separation process, there is a certain phase difference in the data collected by different sensors. If the independent component analysis is performed without considering the phase difference, the separation effect will be seriously affected.
A commonly used solution is to perform blind deconvolution on the signal, transform the sampled signal to the frequency domain, and perform complex independent component analysis on the signal in the frequency domain, but complex independent component analysis has amplitude uncertainty and order uncertainty. problem, the process of solving the sorting problem is complicated, and the separation result is not ideal

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
  • A vibration signal denoising method and system based on independence
  • A vibration signal denoising method and system based on independence
  • A vibration signal denoising method and system based on independence

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment 1

[0099] The fault data s of the inner ring of the rolling bearing collected by the acceleration sensor, such as figure 2 shown. Add 15dB noise to s to generate six noisy signals as simulation signals, such as image 3 As shown, these six signals are denoised.

[0100] Step 1: Take one of the six signals as the reference signal X 0 , the other five signals are comparison signals X1={X 1 ,X 2 ,...,X 5}, take 5000 points for each signal;

[0101] Step 2: Set the parameters, select the position of the 1000th point as the starting point of the phase mark τ 0 , the mark length parameter m=200, respectively at the starting point τ of the phase mark 0 Take 200 points on the left side and 200 points on the right side.

[0102] Step 3: According to the reference signal X 0 Create the reference data S, a total of 1000 points of data in S, and create a phase-shifting data set X2 according to the signals of different phase starting points:

[0103]

[0104] There are 1000 poin...

specific Embodiment 2

[0113] The acceleration sensor is used to collect the fault signal s of the inner ring of the rolling bearing, but there are other signals that interfere with the measured value. This interference signal is s’. The two signals are as follows: Figure 7 shown. Due to the different sensor positions, the two signals are mixed in the following mixing matrix:

[0114]

[0115] According to the formula X=H×(s, s’)’, the two-way mixed signal X={X 1 ,X 2},Such as Figure 8 shown. For a more accurate analog sampling signal, arrange a certain phase difference for the mixed signal X to obtain the simulated signal S={S 1 ,S 2}.

[0116] Step 1: S is the sensor sampling data obtained by simulation, where S is selected 1 As the benchmark data, select S 2 For data comparison, 5000 points are taken for each signal.

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 vibration signal denoising method and system based on independence. The method comprises the following steps: obtaining a phase mark starting point position and a mark lengthparameter of the signal; According to the reference signal, creating the reference data at the starting point position of the phase mark; A phase shifting data set is created according to the phase mark starting point position and the mark length parameters of the comparison signal. Independent component analysis (ICA) was used to process the datum and phase-shifted dataset to obtain the processseparation signal. Acquiring a phase marker factor matrix of the process separation signal; Determining the phase information according to the outlier information of the phase marker factor matrix; Adjusting the phase of the comparison signal according to the phase information, and constructing an adjustment data set together with the reference signal; The adjusted data set is processed by independent component analysis, and the final separated signal is obtained. The denoised signal is determined according to the time-frequency characteristics of the final separated signal. The invention caneffectively remove the noise of the vibration signal and realize the feature extraction of the vibration signal.

Description

technical field [0001] The invention relates to the field of vibration signal analysis, in particular to an independence-based vibration signal denoising method and system. Background technique [0002] Vibration signal monitoring is one of the main technologies of mechanical equipment condition monitoring and fault diagnosis. The basic method is to analyze and process the vibration signal by measuring the vibration signal of some special parts on the machine equipment, and extract the characteristic information reflecting the fault from it. The characteristic information makes a diagnosis on the fault type, location, degree and its development trend. Extracting the characteristics of the vibration signal requires analyzing and processing the signal, and removing noise signals that are not related to the characteristic signal is one of the most critical steps. [0003] Independent component analysis is a signal processing method that uses the statistical independence of sou...

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): G06K9/62G06K9/00
CPCG06F2218/04G06F2218/08G06F18/2134
Inventor 孟宗李晶殷娜潘作舟樊凤杰
Owner YANSHAN 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