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

SVR antifriction bearing performance degradation prediction method based on krill-herd algorithm

A technology of rolling bearing and prediction method, which is used in mechanical bearing testing, mechanical component testing, and machine/structural component testing. , the number of iterations is reduced, the effect of good clustering effect

Inactive Publication Date: 2017-08-11
HARBIN UNIV OF SCI & TECH
View PDF6 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, multi-characteristic parameters have the disadvantages of large amount of information and poor sensitivity, and cannot comprehensively evaluate bearing degradation.

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
  • SVR antifriction bearing performance degradation prediction method based on krill-herd algorithm
  • SVR antifriction bearing performance degradation prediction method based on krill-herd algorithm
  • SVR antifriction bearing performance degradation prediction method based on krill-herd algorithm

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0036] Specific implementation mode one: as figure 1 As shown, the SVR rolling bearing performance degradation prediction method based on the krill swarm algorithm of the present embodiment, the method includes the following steps:

[0037]Step 1: Based on CEEMD (Complete Overall Empirical Mode Decomposition: Similar to EEMD, the form of adding positive and negative pairs of Gaussian white noise has a good effect on eliminating the residual auxiliary noise in the reconstructed signal, thereby reducing the reconstruction error. Improve calculation speed) and feature extraction of wavelet packet threshold noise reduction;

[0038] Analyze the time domain, frequency domain, and time-frequency domain characteristic indicators, reflect the fault diagnosis ability of rolling bearings, and propose a new theoretical algorithm combining CEEMD with wavelet packet semi-soft threshold;

[0039] Step 2: Rolling bearing dimensionality reduction based on C-LLE (establish fuzzy C clustering ...

specific Embodiment approach 2

[0043] Specific implementation mode 2: This implementation mode is a further description of specific implementation mode 1;

[0044] Step 1 (firstly, analyze the vibration signal of the rolling bearing. When the noise signal in the rolling bearing is large enough to cover the useful information, directly using the wavelet packet threshold for noise reduction will remove the noise signal while also removing the useful signal submerged in the noise. The use of CEEMD to directly discard the high-frequency components for denoising will cause the loss of high-frequency effective signals, so the specific steps of using the method of combining CEEMD and wavelet packets) are as follows:

[0045] Step 11: Set the sampling time and frequency for the acceleration sensor installed on the rolling bearing seat, then determine the number of acceleration sensor channels, and collect the vibration signals of the rolling bearing in different damage states, and then preprocess the obtained fault ...

specific Embodiment approach 3

[0048] Specific implementation mode three: this implementation mode is a further description of specific implementation mode one;

[0049] Step 2 (Because a single characteristic parameter cannot well reflect the changes in the normal operation of the rolling bearing, and multi-characteristic parameters often have the problems of irrelevance and information redundancy, the method of feature dimensionality reduction is used to reduce the Space matrix is ​​used for dimensionality reduction, and the rolling bearing feature dimensionality reduction method based on C-LLE is used. During the entire monitoring process of rolling bearings, not only can different damage degrees of bearings be distinguished, but also the degradation trend of rolling bearings can be predicted and classified. The normal vibration signal of rolling bearings and the final failure fault signal as training data to establish a fuzzy C clustering model. First, fault feature extraction: extract the time domain, f...

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

An SVR antifriction bearing performance degradation prediction method based on a krill-herd algorithm belongs to the field of functional approximation rotating machinery prediction methods. The method comprises the following steps: firstly analyzing time domain, frequency domain and time-frequency domain feature indexes, and proposing a feature extraction method based on combination of CEEMD and wavelet packet half-soft threshold noise reduction to perform fault diagnosis of an antifriction bearing; performing comprehensive evaluation of the fault degradation feature of the antifriction bearing for multiple feature parameters, and proposing a method of combining the LLE nonlinear feature dimension reduction method with the fuzzy C mean value; and finally, introducing the basic theory of the support vector regression machine, and proposing the prediction model of multivariable support vector regression machine based on the krill herd algorithm, optimizing parameters of the SVR, and selecting the optimal C, [sigma] parameters. The method is advantaged by high prediction precision, short calculation time, and good feature value prediction effect after clustering. The degradation process of the antifriction bearing can be precisely predicted through the abovementioned three steps.

Description

technical field [0001] The invention belongs to the field of rotating machinery prediction methods of functional approximation, and specifically relates to a method for feature extraction based on the combination of CEEMD and wavelet packet transform, and a method for dimensionality reduction processing of nonlinear signals by using multi-feature fusion technology. Background technique [0002] With the breakthroughs and leaps in science and technology, the diagnosis and prediction of rotating machinery equipment faults have attracted widespread attention, and large-scale rotating machinery equipment has become more and more automated, sophisticated, and complex with the development of the times. The requirements are also getting stricter. Equipment will gradually enter a stage of high incidence of wear and tear over time. The entire production line in the factory may be paralyzed due to the failure of individual components, which will not only cause economic crisis to the ...

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): G01M13/04G06N3/00
CPCG01M13/045G06N3/006
Inventor 王亚萍马华鑫许迪葛江华匡宇麒赵强付岩
Owner HARBIN UNIV OF SCI & 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