Rolling bearing fault diagnosis method based on vibration signal analysis

A vibration signal, rolling bearing technology, applied in the testing of mechanical components, testing of machine/structural components, measuring devices, etc., can solve the problems of low fault recognition rate and difficulty in extracting fault features of rolling bearings, and achieve the effect of good fault recognition ability.

Inactive Publication Date: 2019-07-23
KUNMING UNIV OF SCI & TECH
View PDF7 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem solved by the present invention is: the present invention provides a rolling bearing fault diagnosis method based on...

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
  • Rolling bearing fault diagnosis method based on vibration signal analysis
  • Rolling bearing fault diagnosis method based on vibration signal analysis
  • Rolling bearing fault diagnosis method based on vibration signal analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0033] Embodiment 1: as figure 1 As shown, a rolling bearing fault diagnosis method based on vibration signals, the specific steps are as follows:

[0034] Step1: Acquire the vibration signals of the rolling bearing in four working states: normal, inner ring fault, outer ring fault and rolling element fault;

[0035] Step2: Differential Empirical Mode Decomposition (DEMD) decomposition is performed on the vibration signal in each working state and several IMF components with physical meaning are obtained;

[0036] Step3: Calculate the correlation coefficient between the IMF component and the original vibration signal;

[0037] Step4: Select the IMF component with a large correlation coefficient, because the IMF component with a large correlation coefficient is the principal component containing fault characteristic information;

[0038] Step5: Calculate the multi-scale entropy of each IMF component after screening;

[0039] Step6: Constitute the obtained multi-scale entropy...

Embodiment 2

[0040] Embodiment 2: In this embodiment, the fault of the rolling bearing is diagnosed by the method described in the following engineering test, and the specific experiment is as follows:

[0041] Step 1. The experimental data comes from the data of the Electrical Engineering Laboratory of Case Western Reserve University in the United States. The bearing model is 6205-2RS JEM SKF, the load is 2.237kW, and the rotation frequency is 1730r·min -1, the sampling frequency is 12kHz. In order to simulate bearing damage and failure, cracks are artificially added on the inner and outer rings of the bearing and on the rolling body respectively. The crack diameter is 0.1778mm and the crack depth is 0.2794mm.

[0042] Step 2. Collect 4 different types of vibration signals of rolling bearings (normal, rolling element fault, inner ring fault, outer ring fault) at a fixed sampling frequency. The length of the data is 2400, and 50 sets of data are collected for each state as a total sample ...

Embodiment 3

[0053] Embodiment 3: In order to study the influence of different training sample numbers on the rolling bearing fault identification results, select the above-mentioned Case Western Reserve University rolling bearing vibration number under the four states of a total of 50 * 4 groups, in normal state, inner ring fault, outer ring fault 10, 20, 30, and 40 sets of data are randomly selected from the rolling element fault sample data as training sample data, and the remaining sample data are used as test samples. Table 2 shows when the classification is correct under different numbers of training samples. From the table we can see that when the training data is 30 groups, the diagnostic accuracy of the proposed method can reach 96.25%. When the number of training samples increases, the established classification model is more accurate and the recognition degree is higher, but after a certain number of samples are increased, the correct rate of fault identification will be reduced...

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

PropertyMeasurementUnit
Crack depthaaaaaaaaaa
Login to view more

Abstract

The invention relates to a rolling bearing fault diagnosis method based on vibration signal analysis, and belongs to the field of mechanical fault diagnosis and signal processing. According to the rolling bearing fault diagnosis method based on the vibration signal analysis, firstly, empirical mode decomposition (DEMD) is carried out on vibration signals of a bearing, and a plurality of intrinsicmode function (IMF) components with physical significance are obtained through the decomposition; then the correlation coefficient between component signals and the original vibration signals is calculated, the components containing fault characteristic information are selected through the correlation coefficient, and the multi-scale entropy of the selected components is calculated to form an eigenvalue vector; and at last, the eigenvalue vector is input into a support vector machine (SVM) to complete the recognition of the working state of a rolling bearing. According to the rolling bearing fault diagnosis method based on the vibration signal analysis, low-energy high-frequency signals are decomposed through DEMD, the multi-scale entropy is calculated to be an characteristic, the SVM is utilized to classify, the accuracy of bearing fault recognition is improved, and the practicability is comparatively high.

Description

technical field [0001] The invention relates to a rolling bearing fault diagnosis method based on vibration signal analysis, which belongs to the field of mechanical fault diagnosis and signal processing. Background technique [0002] Rolling bearings are one of the most important components of rotating machinery and other machinery, and they are easily damaged due to their high-frequency operation. In industrial practical applications, its operating status plays a decisive role in the operation of the overall equipment, and most mechanical equipment failures are closely related to it. According to relevant data, 30% of rotating machinery failures are caused by rolling bearing failures. In gearbox failures, bearings cause more than 20% of the failures, second only to gear failures, especially in motor failures. The faults accounted for 80% of the total faults. It can be seen that the research on rolling bearing fault diagnosis technology has important practical significanc...

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 黄国勇潘震吴建德王晓东叶波范玉刚邹金慧冯早
Owner KUNMING UNIV OF SCI & TECH
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