Fractional Dimensionless Indicator with Random Forest for Bearing Fault Diagnosis under Variable Speed Conditions

Fault diagnosis of rolling bearings under variable speed is a common issue in engineering practice, but it lacks an effective diagnosis algorithm, while approaches developed for steady speed cannot be directly applied. Therefore, for effectively identifying bearing faults under variable speed, this...

Full description

Saved in:
Bibliographic Details
Published in:Shock and vibration 2022-10, Vol.2022, p.1-14
Main Authors: Huang, Yujing, Xu, Zhi, Cao, Liang, Hu, Hao, Tang, Gang
Format: Article
Language:English
Subjects:
Algorithms
Aviation
Case studies
Classification
Discriminant analysis
Fault detection
Fault diagnosis
Feature selection
Fourier series
Fourier transforms
Machine learning
Methods
Neural networks
Optimization
Roller bearings
Support vector machines
Wavelet transforms
Working conditions
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Fault diagnosis of rolling bearings under variable speed is a common issue in engineering practice, but it lacks an effective diagnosis algorithm, while approaches developed for steady speed cannot be directly applied. Therefore, for effectively identifying bearing faults under variable speed, this paper proposed a multiscale fractional dimensionless indicator (MSFDI) and put forward a fault diagnosis method with random forest (RF). It can overcome the feature space aliasing problem of traditional dimensionless indicators, which will lead to increased diagnosis uncertainty. The multiorder fractional Fourier transform is carried out on bearing signals to get a series of fractional Fourier domain components, which will be used to construct the original MSFDI feature set. Moreover, reliefF selects the sensitive MSFDIs as the input of the RF algorithm to determine the health condition. The effectiveness of the proposed method is verified by experiments and case studies.
ISSN:1070-9622
1875-9203
DOI:10.1155/2022/1781340