Rolling Bearing Fault Diagnosis Based on Optimized VMD Combining Signal Features and Improved CNN

Aiming at the problem that the vibration signals of rolling bearings in high-speed rail traction motors are often affected by noise when they are in a fault state, which makes it very difficult to extract the fault features during fault diagnosis and causes obstruction in fault classification. The a...

Full description

Saved in:
Bibliographic Details
Main Authors: Yingyong Zou, Xingkui Zhang, Wenzhuo Zhao, Tao Liu
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:World Electric Vehicle Journal
Subjects:
Online Access:https://www.mdpi.com/2032-6653/15/12/544
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846102339645079552
author Yingyong Zou
Xingkui Zhang
Wenzhuo Zhao
Tao Liu
author_facet Yingyong Zou
Xingkui Zhang
Wenzhuo Zhao
Tao Liu
author_sort Yingyong Zou
collection DOAJ
description Aiming at the problem that the vibration signals of rolling bearings in high-speed rail traction motors are often affected by noise when they are in a fault state, which makes it very difficult to extract the fault features during fault diagnosis and causes obstruction in fault classification. The article proposes a rolling bearing fault diagnosis based on optimized variational mode decomposition (VMD) combined with signal features and an improved convolutional neural network (CNN). The golden jackal optimization (GJO) algorithm is employed to optimize the key parameters of the VMD, enabling effective signal decomposition. The decomposed signals are then filtered and reconstructed using criteria based on kurtosis and interrelationship measures. The time-domain features of the reconstructed signals are computed, and the feature vectors are constructed, which are used as inputs to the deep learning network; the CNN combined with the support vector machine (SVM) network model is used for the extraction of the features and the classification of the faults. The experimental results show that the method can effectively extract fault features in noise-covered signals, and the accuracy is also significantly improved compared with traditional methods.
format Article
id doaj-art-409211bd979b4243b56bdadcd5b93a4e
institution Kabale University
issn 2032-6653
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series World Electric Vehicle Journal
spelling doaj-art-409211bd979b4243b56bdadcd5b93a4e2024-12-27T14:59:31ZengMDPI AGWorld Electric Vehicle Journal2032-66532024-11-01151254410.3390/wevj15120544Rolling Bearing Fault Diagnosis Based on Optimized VMD Combining Signal Features and Improved CNNYingyong Zou0Xingkui Zhang1Wenzhuo Zhao2Tao Liu3College of Mechanical and Vehicular Engineering, Changchun University, Changchun 130022, ChinaCollege of Mechanical and Vehicular Engineering, Changchun University, Changchun 130022, ChinaCollege of Mechanical and Vehicular Engineering, Changchun University, Changchun 130022, ChinaCollege of Mechanical and Vehicular Engineering, Changchun University, Changchun 130022, ChinaAiming at the problem that the vibration signals of rolling bearings in high-speed rail traction motors are often affected by noise when they are in a fault state, which makes it very difficult to extract the fault features during fault diagnosis and causes obstruction in fault classification. The article proposes a rolling bearing fault diagnosis based on optimized variational mode decomposition (VMD) combined with signal features and an improved convolutional neural network (CNN). The golden jackal optimization (GJO) algorithm is employed to optimize the key parameters of the VMD, enabling effective signal decomposition. The decomposed signals are then filtered and reconstructed using criteria based on kurtosis and interrelationship measures. The time-domain features of the reconstructed signals are computed, and the feature vectors are constructed, which are used as inputs to the deep learning network; the CNN combined with the support vector machine (SVM) network model is used for the extraction of the features and the classification of the faults. The experimental results show that the method can effectively extract fault features in noise-covered signals, and the accuracy is also significantly improved compared with traditional methods.https://www.mdpi.com/2032-6653/15/12/544bearing fault diagnosisgolden jackal optimization algorithmvariational mode decompositionconvolutional neural networksupport vector machine
spellingShingle Yingyong Zou
Xingkui Zhang
Wenzhuo Zhao
Tao Liu
Rolling Bearing Fault Diagnosis Based on Optimized VMD Combining Signal Features and Improved CNN
World Electric Vehicle Journal
bearing fault diagnosis
golden jackal optimization algorithm
variational mode decomposition
convolutional neural network
support vector machine
title Rolling Bearing Fault Diagnosis Based on Optimized VMD Combining Signal Features and Improved CNN
title_full Rolling Bearing Fault Diagnosis Based on Optimized VMD Combining Signal Features and Improved CNN
title_fullStr Rolling Bearing Fault Diagnosis Based on Optimized VMD Combining Signal Features and Improved CNN
title_full_unstemmed Rolling Bearing Fault Diagnosis Based on Optimized VMD Combining Signal Features and Improved CNN
title_short Rolling Bearing Fault Diagnosis Based on Optimized VMD Combining Signal Features and Improved CNN
title_sort rolling bearing fault diagnosis based on optimized vmd combining signal features and improved cnn
topic bearing fault diagnosis
golden jackal optimization algorithm
variational mode decomposition
convolutional neural network
support vector machine
url https://www.mdpi.com/2032-6653/15/12/544
work_keys_str_mv AT yingyongzou rollingbearingfaultdiagnosisbasedonoptimizedvmdcombiningsignalfeaturesandimprovedcnn
AT xingkuizhang rollingbearingfaultdiagnosisbasedonoptimizedvmdcombiningsignalfeaturesandimprovedcnn
AT wenzhuozhao rollingbearingfaultdiagnosisbasedonoptimizedvmdcombiningsignalfeaturesandimprovedcnn
AT taoliu rollingbearingfaultdiagnosisbasedonoptimizedvmdcombiningsignalfeaturesandimprovedcnn