Rolling bearing fault diagnosis based on parameter optimized VMD and improved GoogLeNet

ObjectiveThe application of deep learning methods in the field of rolling bearing fault diagnosis is very effective, but traditional neural networks cannot extract features at multiple scales due to the use of a single scale convolution kernel, and do not consider the importance of different feature...

Full description

Saved in:
Bibliographic Details
Main Authors: LI Haoran, LIU Deping
Format: Article
Language:zho
Published: Editorial Office of Journal of Mechanical Transmission 2025-01-01
Series:Jixie chuandong
Subjects:
Online Access:http://www.jxcd.net.cn/thesisDetails#10.16578/j.issn.1004.2539.2025.01.020
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832586340344004608
author LI Haoran
LIU Deping
author_facet LI Haoran
LIU Deping
author_sort LI Haoran
collection DOAJ
description ObjectiveThe application of deep learning methods in the field of rolling bearing fault diagnosis is very effective, but traditional neural networks cannot extract features at multiple scales due to the use of a single scale convolution kernel, and do not consider the importance of different features in fault diagnosis. Therefore, it is difficult to extract fault features of rolling bearing signals under noise interference. A rolling bearing fault diagnosis method based on parameter-optimized variational mode decomposition (VMD) noise reduction and GoogLeNet network with improved attention mechanism was proposed.MethodsThe local minimal envelope entropy was used as the fitness function, and the sparrow search algorithm (SSA) was used to optimize the VMD parameter combination; the optimized VMD algorithm was used to decompose the bearing vibration signals to obtain several modal components, and the signals were reconstructed by filtering the modal components with rich fault features according to the envelope entropy and kurtosis; the reconstructed signals were used to construct the feature matrix and input into the improved GoogLeNet network to complete the diagnosis.ResultsThe test results show that the diagnostic accuracy of the method is 95.5% to 99.8% under different noise backgrounds, which is better than other methods in terms of noise robustness.
format Article
id doaj-art-6c7f94b563a54e8794d0a0143a7d095a
institution Kabale University
issn 1004-2539
language zho
publishDate 2025-01-01
publisher Editorial Office of Journal of Mechanical Transmission
record_format Article
series Jixie chuandong
spelling doaj-art-6c7f94b563a54e8794d0a0143a7d095a2025-01-25T19:01:08ZzhoEditorial Office of Journal of Mechanical TransmissionJixie chuandong1004-25392025-01-014916317081411124Rolling bearing fault diagnosis based on parameter optimized VMD and improved GoogLeNetLI HaoranLIU DepingObjectiveThe application of deep learning methods in the field of rolling bearing fault diagnosis is very effective, but traditional neural networks cannot extract features at multiple scales due to the use of a single scale convolution kernel, and do not consider the importance of different features in fault diagnosis. Therefore, it is difficult to extract fault features of rolling bearing signals under noise interference. A rolling bearing fault diagnosis method based on parameter-optimized variational mode decomposition (VMD) noise reduction and GoogLeNet network with improved attention mechanism was proposed.MethodsThe local minimal envelope entropy was used as the fitness function, and the sparrow search algorithm (SSA) was used to optimize the VMD parameter combination; the optimized VMD algorithm was used to decompose the bearing vibration signals to obtain several modal components, and the signals were reconstructed by filtering the modal components with rich fault features according to the envelope entropy and kurtosis; the reconstructed signals were used to construct the feature matrix and input into the improved GoogLeNet network to complete the diagnosis.ResultsThe test results show that the diagnostic accuracy of the method is 95.5% to 99.8% under different noise backgrounds, which is better than other methods in terms of noise robustness.http://www.jxcd.net.cn/thesisDetails#10.16578/j.issn.1004.2539.2025.01.020Rolling bearingVariational mode decompositionSparrow search algorithmConvolutional neural networkFault diagnosisAttention mechanism
spellingShingle LI Haoran
LIU Deping
Rolling bearing fault diagnosis based on parameter optimized VMD and improved GoogLeNet
Jixie chuandong
Rolling bearing
Variational mode decomposition
Sparrow search algorithm
Convolutional neural network
Fault diagnosis
Attention mechanism
title Rolling bearing fault diagnosis based on parameter optimized VMD and improved GoogLeNet
title_full Rolling bearing fault diagnosis based on parameter optimized VMD and improved GoogLeNet
title_fullStr Rolling bearing fault diagnosis based on parameter optimized VMD and improved GoogLeNet
title_full_unstemmed Rolling bearing fault diagnosis based on parameter optimized VMD and improved GoogLeNet
title_short Rolling bearing fault diagnosis based on parameter optimized VMD and improved GoogLeNet
title_sort rolling bearing fault diagnosis based on parameter optimized vmd and improved googlenet
topic Rolling bearing
Variational mode decomposition
Sparrow search algorithm
Convolutional neural network
Fault diagnosis
Attention mechanism
url http://www.jxcd.net.cn/thesisDetails#10.16578/j.issn.1004.2539.2025.01.020
work_keys_str_mv AT lihaoran rollingbearingfaultdiagnosisbasedonparameteroptimizedvmdandimprovedgooglenet
AT liudeping rollingbearingfaultdiagnosisbasedonparameteroptimizedvmdandimprovedgooglenet