Legendre Multiwavelet Transform and Its Application in Bearing Fault Detection

Bearing failures often result from compound faults, where the characteristics of these compound faults span across multiple domains. To tackle the challenge of extracting features from compound faults, this paper proposes a novel fault detection method based on the Legendre multiwavelet transform (L...

Full description

Saved in:
Bibliographic Details
Published in:Applied sciences 2024-01, Vol.14 (1), p.219
Main Authors: Zheng, Xiaoyang, Lei, Zijian, Feng, Zhixia, Chen, Lei
Format: Article
Language:English
Subjects:
Accuracy
Bearings
Deep learning
envelope spectrum analysis
Fault diagnosis
Fourier transforms
Legendre multiwavelet decomposition
Methods
Neural networks
rolling bearings
Signal processing
spectral segmentation
Wavelet transforms
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:Bearing failures often result from compound faults, where the characteristics of these compound faults span across multiple domains. To tackle the challenge of extracting features from compound faults, this paper proposes a novel fault detection method based on the Legendre multiwavelet transform (LMWT) combined with envelope spectrum analysis. Additionally, to address the issue of identifying suitable wavelet decomposition coefficients, this paper introduces the concept of relative energy ratio. This ratio assists in identifying the most sensitive wavelet coefficients associated with fault frequency bands. To assess the performance of the proposed method, the results obtained from the LMWT method are compared with those derived from the empirical wavelet transform (EWT) method using different datasets. Experimental findings demonstrate that the proposed method exhibits more effective frequency spectrum segmentation and superior detection performance across various experimental conditions.
ISSN:2076-3417
2076-3417
DOI:10.3390/app14010219