Rolling Bearing Fault Diagnosis Based on Optimized VMD and SSAE

The monitoring and fault diagnosis of axle-box bearings in high-speed trains is crucial for ensuring safe train operations. The vibration signals of these bearings exhibit non-stationary and non-linear characteristics. To further enhance the accuracy of identifying rolling bearing faults, a fault di...

Full description

Saved in:
Bibliographic Details
Main Authors: Baoxian Chang, Xing Zhao, Dawei Guo, Siyu Zhao, Jiyou Fei
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10494842/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850263513937739776
author Baoxian Chang
Xing Zhao
Dawei Guo
Siyu Zhao
Jiyou Fei
author_facet Baoxian Chang
Xing Zhao
Dawei Guo
Siyu Zhao
Jiyou Fei
author_sort Baoxian Chang
collection DOAJ
description The monitoring and fault diagnosis of axle-box bearings in high-speed trains is crucial for ensuring safe train operations. The vibration signals of these bearings exhibit non-stationary and non-linear characteristics. To further enhance the accuracy of identifying rolling bearing faults, a fault diagnosis method is proposed. This method is based on the improved Dung Beetle Optimization (DBO) algorithm for optimizing Variational Mode Decomposition (VMD) combined with Stacked Sparse Autoencoder (SSAE). Firstly, the DBO algorithm is enhanced to improve its optimization precision and global optimization capability. It is then utilized for the adaptive selection of two parameters: the number of decomposition modes and the penalty factor in VMD. These improvements address issues such as mode mixing, signal loss, and excessive decomposition, which arise from poor parameter selection in the traditional VMD method. Subsequently, components of Intrinsic Mode Functions (IMFs) that are highly correlated with the original signal are selected. The time-domain and frequency-domain features of these IMF components are used to construct the dataset. The feature set is then inputted into the deep machine learning model SSAE for training and testing. Through diagnostic experiments on various types and levels of rolling bearing faults, the model demonstrates a higher rate of fault diagnosis recognition.
format Article
id doaj-art-32acbd6ea9174f9b9521e2a0a6dffde3
institution OA Journals
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-32acbd6ea9174f9b9521e2a0a6dffde32025-08-20T01:54:57ZengIEEEIEEE Access2169-35362024-01-011213074613076210.1109/ACCESS.2024.338683510494842Rolling Bearing Fault Diagnosis Based on Optimized VMD and SSAEBaoxian Chang0https://orcid.org/0009-0005-0430-5201Xing Zhao1https://orcid.org/0000-0002-3654-7134Dawei Guo2Siyu Zhao3Jiyou Fei4https://orcid.org/0000-0003-2547-8783College of Locomotive and Rolling Stock Engineering, Dalian Jiaotong University, Dalian, ChinaCollege of Locomotive and Rolling Stock Engineering, Dalian Jiaotong University, Dalian, ChinaCollege of Locomotive and Rolling Stock Engineering, Dalian Jiaotong University, Dalian, ChinaCollege of Locomotive and Rolling Stock Engineering, Dalian Jiaotong University, Dalian, ChinaCollege of Locomotive and Rolling Stock Engineering, Dalian Jiaotong University, Dalian, ChinaThe monitoring and fault diagnosis of axle-box bearings in high-speed trains is crucial for ensuring safe train operations. The vibration signals of these bearings exhibit non-stationary and non-linear characteristics. To further enhance the accuracy of identifying rolling bearing faults, a fault diagnosis method is proposed. This method is based on the improved Dung Beetle Optimization (DBO) algorithm for optimizing Variational Mode Decomposition (VMD) combined with Stacked Sparse Autoencoder (SSAE). Firstly, the DBO algorithm is enhanced to improve its optimization precision and global optimization capability. It is then utilized for the adaptive selection of two parameters: the number of decomposition modes and the penalty factor in VMD. These improvements address issues such as mode mixing, signal loss, and excessive decomposition, which arise from poor parameter selection in the traditional VMD method. Subsequently, components of Intrinsic Mode Functions (IMFs) that are highly correlated with the original signal are selected. The time-domain and frequency-domain features of these IMF components are used to construct the dataset. The feature set is then inputted into the deep machine learning model SSAE for training and testing. Through diagnostic experiments on various types and levels of rolling bearing faults, the model demonstrates a higher rate of fault diagnosis recognition.https://ieeexplore.ieee.org/document/10494842/Bearing fault diagnosisdung beetle optimization algorithmvariational modal decompositionstacked sparse autoencoders
spellingShingle Baoxian Chang
Xing Zhao
Dawei Guo
Siyu Zhao
Jiyou Fei
Rolling Bearing Fault Diagnosis Based on Optimized VMD and SSAE
IEEE Access
Bearing fault diagnosis
dung beetle optimization algorithm
variational modal decomposition
stacked sparse autoencoders
title Rolling Bearing Fault Diagnosis Based on Optimized VMD and SSAE
title_full Rolling Bearing Fault Diagnosis Based on Optimized VMD and SSAE
title_fullStr Rolling Bearing Fault Diagnosis Based on Optimized VMD and SSAE
title_full_unstemmed Rolling Bearing Fault Diagnosis Based on Optimized VMD and SSAE
title_short Rolling Bearing Fault Diagnosis Based on Optimized VMD and SSAE
title_sort rolling bearing fault diagnosis based on optimized vmd and ssae
topic Bearing fault diagnosis
dung beetle optimization algorithm
variational modal decomposition
stacked sparse autoencoders
url https://ieeexplore.ieee.org/document/10494842/
work_keys_str_mv AT baoxianchang rollingbearingfaultdiagnosisbasedonoptimizedvmdandssae
AT xingzhao rollingbearingfaultdiagnosisbasedonoptimizedvmdandssae
AT daweiguo rollingbearingfaultdiagnosisbasedonoptimizedvmdandssae
AT siyuzhao rollingbearingfaultdiagnosisbasedonoptimizedvmdandssae
AT jiyoufei rollingbearingfaultdiagnosisbasedonoptimizedvmdandssae