Unlock instant, AI-driven research and patent intelligence for your innovation.

Bearing fault diagnosis method based on deep kernel processing

A fault diagnosis and nuclear processing technology, applied in the field of signal processing, can solve problems such as failure and effectiveness reduction, achieve high precision, suppress Gaussian noise and non-Gaussian noise interference, and improve robustness

Active Publication Date: 2022-03-29
TIANJIN UNIV OF TECH & EDUCATION TEACHER DEV CENT OF CHINA VOCATIONAL TRAINING & GUIDANCE
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when dealing with strong Gaussian noise interference signals, the effectiveness of the traditional spectral correlation density method will be significantly reduced; and the traditional spectral correlation density method will even fail when dealing with non-Gaussian noise interference signals

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 based on deep kernel processing
  • Bearing fault diagnosis method based on deep kernel processing
  • Bearing fault diagnosis method based on deep kernel processing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] Such as figure 1 As shown, the present invention discloses a bearing fault diagnosis method based on deep kernel processing, comprising the following steps:

[0030] Step S1, collect the vibration signal x, such as figure 2 shown. Suppose x is a column vector of length n, let y=x T , where x T For the transpose of signal x, compute the correlation kernel R of signal x xy = x y;

[0031] x 1 ,x 2 ...,x n are the elements in the given one-dimensional signal x of length n respectively, signal x=[x 1 ,x 2 ,x 3 ,...,x n ] T ,[·] T is the transpose operator.

[0032] Step S2, using the Gaussian kernel function to calculate the correlation kernel R xy Gaussian kernel κ σ (x,y), , where σ is the kernel length of the Gaussian kernel, e (·) is a natural exponential function.

[0033] Step S3, calculate the depth kernel D(x,y) of the vibration signal x in the Hilbert space Where E[ ] is the mathematical expectation; the depth kernel D(x,y) is the nonlinear t...

Embodiment 2

[0036] This embodiment is a verification of the method in Embodiment 1. In this embodiment, a vibration sensor is used to obtain the fault vibration signal of the outer ring of the bearing. The model of the experimental rolling bearing in this embodiment is 208 deep groove bearing. The rated speed of the shaft where the faulty bearing is located is 1500r / min, and the sampling frequency is f s =6kHz, sampling time T=0.5s, signal x(t) length n=3000. The geometric dimension data of 208 rolling bearings are: bearing major diameter D=97.5mm; ball diameter d=18.33mm; number of balls z=10; pressure Angle α=0°. according to Calculate the fault characteristic frequency f of the rolling bearing outer ring outer = 101.5Hz, f r is the rotational frequency of the shaft.

[0037] The time-domain waveform of the vibration signal x(t) of embodiment 2, such as figure 2 Shown; The frequency-domain waveform of embodiment vibration signal x (t), as image 3 shown. Calculate the depth nu...

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 bearing fault diagnosis method based on deep kernel processing, which relates to the problem of identifying the bearing fault characteristic frequency in the bearing fault vibration signal under the condition of joint interference of Gaussian noise and non-Gaussian pulse noise. The method comprises the following steps: collecting a vibration signal x, calculating the correlation kernel of the signal x; using a Gaussian kernel function, calculating the correlation kernel R xy Gaussian kernel κ σ (x,y); Calculate the depth kernel D(x,y) of the vibration signal x in the Hilbert space; Calculate the spectral correlation density S of the depth kernel D(x,y) D (α, f), draw a two-dimensional contour map and a three-dimensional stereogram, and the characteristic frequency of the bearing fault in the vibration signal of the bearing fault can be identified by the peak of the spectrum. The invention can improve the robustness to Gaussian noise and non-Gaussian pulse noise, and can effectively identify the bearing fault characteristic frequency in the bearing fault vibration signal.

Description

technical field [0001] The invention relates to the technical field of signal processing, in particular to a bearing fault diagnosis method based on deep kernel processing. Background technique [0002] The traditional spectral correlation density method based on second-order statistics has been widely used in the field of signal processing. It can well characterize the cyclostationary characteristics of the signal and effectively extract the cyclic period components in the signal. However, when dealing with strong Gaussian noise interference signals, the effectiveness of the traditional spectral correlation density method will be significantly reduced; and the traditional spectral correlation density method will even fail when dealing with non-Gaussian noise interference signals. Contents of the invention [0003] The purpose of the present invention is to provide a method for diagnosing bearing faults based on deep kernel processing in view of the technical defects in th...

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
IPC IPC(8): G01M13/045
CPCG01M13/045
Inventor 李辉张宇平
Owner TIANJIN UNIV OF TECH & EDUCATION TEACHER DEV CENT OF CHINA VOCATIONAL TRAINING & GUIDANCE