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
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
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...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


