Impulsive wavelet based probability sparse coding model for bearing fault diagnosis

•Hyper-Laplacian Sparse Coding model with l0.2-norm was found more suitable for fault diagnosis.•The proposed method successfully extracted early bearing fault features.•The traditional kurtogram method is improved by using the square envelope kurtosis, and the interference of random pulse is remove...

Full description

Saved in:
Bibliographic Details
Published in:Measurement : journal of the International Measurement Confederation Vol. 194; p. 110969
Main Authors: Ma, Huijie, Li, Shunming, Lu, Jiantao, Gong, Siqi, Yu, Tianyi
Format: Journal Article
Language:English
Published: London Elsevier Ltd 15.05.2022
Elsevier Science Ltd
Subjects:
Bearings
Coding
Digital signal processing
Fault diagnosis
Fault tolerance
Feature extraction
Probability
Roller bearings
Signal denoising
Signal processing
Fault diagnosis
Signal denoising
Digital signal processing
ISSN:0263-2241, 1873-412X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•Hyper-Laplacian Sparse Coding model with l0.2-norm was found more suitable for fault diagnosis.•The proposed method successfully extracted early bearing fault features.•The traditional kurtogram method is improved by using the square envelope kurtosis, and the interference of random pulse is removed successfully.•A new model-based impulsive wavelets family is adopted in our method, which can accurately match the repetitive impulses caused by bearing faults. It has become a challenge to accurately extract weak bearing fault features from early fault stage. To solve this problem, a novel fault features extraction method called improved Kurtogram and Hyper-Laplacian Sparse Coding (KurHLSC) based on probability sparse coding is proposed in this paper. The originality of the present article lies in the construction of a sparse coding model considering probability and wavelet dictionary, which can effectively decompose sparse fault features even in strong noise. Moreover, in order to eliminate the interference of random pulse on sparse coding model, the improved kurtogram method successfully achieved filtering. The effectiveness of KurHLSC in rolling bearing fault diagnosis is verified by simulation studies and run-to-failure experiments, and the comparison studies showed that KurHLSC has better estimation results than other existing methods.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0263-2241
1873-412X
DOI:10.1016/j.measurement.2022.110969