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

A dimensionless parameter rolling bearing long-related fault trend prediction method

A dimensionless parameter, rolling bearing technology, used in mechanical bearing testing, measuring devices, testing of mechanical components, etc., to ensure accurate reliability, simple prediction methods, and easy implementation.

Active Publication Date: 2019-01-15
SHANGHAI UNIV OF ENG SCI
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The two basic problems of fault prediction are: the extraction method of mechanical operating state and fault trend feature quantity; the trend prediction method based on the fault feature sequence characteristics

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 dimensionless parameter rolling bearing long-related fault trend prediction method
  • A dimensionless parameter rolling bearing long-related fault trend prediction method
  • A dimensionless parameter rolling bearing long-related fault trend prediction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0032] Such as figure 1 As shown, a dimensionless parameter rolling bearing long-term correlation fault trend prediction method, the method includes the following steps:

[0033] (1) Collect the original vibration signal of the rolling bearing;

[0034] (2) Establish the MIX-ARMA model;

[0035] (3) Using the MIX-ARMA model to smooth the original vibration signal to obtain a smooth vibration signal;

[0036] (4) obtain the Hurst parameter of smooth vibration signal;

[0037] (5) Determine whether the rolling bearing fails according to the Hurst parameter.

[0038] The MIX-ARMA model combines the short correlation time series model ARIMA and the long correlation time series model FARIMA. The MIX-ARMA model is specifically:

[0039] Φ(z -1 )(1-z -1 ) d x t =Θ(z -1 )ε t ,

[0040]

[0041] Among them, ε t is the original vibration signal, x t is the smooth vibration signal, d is the differential order, p is the autoregressive order, q is the moving average order, ...

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 relates to a dimensionless parameter rolling bearing long-related fault trend prediction method. The method comprises the following steps: (1) collecting original vibration signal of rolling bearing; (2) establishing MIX-ARMA model; (3) using MIX-ARMA model to smooth the original vibration signal to obtain the smooth vibration signal. (4) acquiring the Hurst parameter of the smooth vibration signal; (5) whether the rolling bearing is faulty or not is determined according to the Hurst parameter. Compared with the prior art, the method of the invention is simple, and the predictionresult is accurate and reliable.

Description

technical field [0001] The invention relates to a rolling bearing fault prediction method, in particular to a dimensionless parameter rolling bearing long-term correlation fault trend prediction method. Background technique [0002] Fault trend prediction is of great significance for realizing early warning and forecasting of mechanical equipment faults, ensuring long-term safe operation, reducing maintenance costs and improving utilization rates. The two basic issues of fault prediction are: the method of extracting mechanical operating state and fault trend feature quantity; the trend prediction method based on the fault feature sequence characteristics. [0003] In recent years, more and more attention has been paid to dimensionless amplitude domain parameters, such as waveform index, peak index, margin index, and kurtosis index. They are not very sensitive to changes in amplitude capability and have little to do with machine operating conditions, but are sensitive enoug...

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): G06F17/50G01M13/04
CPCG01M13/045G06F30/20
Inventor 李宇飞宋万清金暠
Owner SHANGHAI UNIV OF ENG SCI