Vibration Images-Driven Fault Diagnosis Based on CNN and Transfer Learning of Rolling Bearing under Strong Noise

Deep learning-based fault diagnosis of rolling bearings is a hot research topic, and a rapid and accurate diagnosis is important. In this paper, aiming at the vibration image samples of rolling bearing affected by strong noise, the convolutional neural network- (CNN-) and transfer learning- (TL-) ba...

Full description

Saved in:
Bibliographic Details
Main Authors: Hongwei Fan, Ceyi Xue, Xuhui Zhang, Xiangang Cao, Shuoqi Gao, Sijie Shao
Format: Article
Language:English
Published: Wiley 2021-01-01
Series:Shock and Vibration
Online Access:http://dx.doi.org/10.1155/2021/6616592
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832554027470028800
author Hongwei Fan
Ceyi Xue
Xuhui Zhang
Xiangang Cao
Shuoqi Gao
Sijie Shao
author_facet Hongwei Fan
Ceyi Xue
Xuhui Zhang
Xiangang Cao
Shuoqi Gao
Sijie Shao
author_sort Hongwei Fan
collection DOAJ
description Deep learning-based fault diagnosis of rolling bearings is a hot research topic, and a rapid and accurate diagnosis is important. In this paper, aiming at the vibration image samples of rolling bearing affected by strong noise, the convolutional neural network- (CNN-) and transfer learning- (TL-) based fault diagnosis method is proposed. Firstly, four kinds of vibration image generation method with different characteristics are put forward, and the corresponding pure vibration image samples are obtained according to the original data. Secondly, using CNN as the adaptive feature extraction and recognition model, the influences of main sensitive parameters of CNN on the network recognition effect are studied, such as learning rate, optimizer, and L1 regularization, and the best model is determined. In order to obtain the pretraining parameters, the training and fault classification test for different image samples are carried out, respectively. Thirdly, the Gaussian white noise with different levels is added to the original signals, and four kinds of noised vibration image samples are obtained. The previous pretrained model parameters are shared for the TL. Each kind of sample research compares the impact of thirteen data sharing schemes on the TL accuracy and efficiency, and finally, the test accuracy and time index are introduced to evaluate the model. The results show that, among the four kinds of image generation method, the classification performance of data obtained by empirical mode decomposition-pseudo-Wigner–Ville distribution (EP) is the best; when the signal to noise ratio (SNR) is 10 dB, the model test accuracy obtained by TL is 96.67% and the training time is 170.46 s.
format Article
id doaj-art-9426051590a74bdcaa5bbd4fb2483430
institution Kabale University
issn 1070-9622
1875-9203
language English
publishDate 2021-01-01
publisher Wiley
record_format Article
series Shock and Vibration
spelling doaj-art-9426051590a74bdcaa5bbd4fb24834302025-02-03T05:52:30ZengWileyShock and Vibration1070-96221875-92032021-01-01202110.1155/2021/66165926616592Vibration Images-Driven Fault Diagnosis Based on CNN and Transfer Learning of Rolling Bearing under Strong NoiseHongwei Fan0Ceyi Xue1Xuhui Zhang2Xiangang Cao3Shuoqi Gao4Sijie Shao5School of Mechanical Engineering, Xi’an University of Science and Technology, Xi’an 710054, ChinaSchool of Mechanical Engineering, Xi’an University of Science and Technology, Xi’an 710054, ChinaSchool of Mechanical Engineering, Xi’an University of Science and Technology, Xi’an 710054, ChinaSchool of Mechanical Engineering, Xi’an University of Science and Technology, Xi’an 710054, ChinaSchool of Mechanical Engineering, Xi’an University of Science and Technology, Xi’an 710054, ChinaSchool of Mechanical Engineering, Xi’an University of Science and Technology, Xi’an 710054, ChinaDeep learning-based fault diagnosis of rolling bearings is a hot research topic, and a rapid and accurate diagnosis is important. In this paper, aiming at the vibration image samples of rolling bearing affected by strong noise, the convolutional neural network- (CNN-) and transfer learning- (TL-) based fault diagnosis method is proposed. Firstly, four kinds of vibration image generation method with different characteristics are put forward, and the corresponding pure vibration image samples are obtained according to the original data. Secondly, using CNN as the adaptive feature extraction and recognition model, the influences of main sensitive parameters of CNN on the network recognition effect are studied, such as learning rate, optimizer, and L1 regularization, and the best model is determined. In order to obtain the pretraining parameters, the training and fault classification test for different image samples are carried out, respectively. Thirdly, the Gaussian white noise with different levels is added to the original signals, and four kinds of noised vibration image samples are obtained. The previous pretrained model parameters are shared for the TL. Each kind of sample research compares the impact of thirteen data sharing schemes on the TL accuracy and efficiency, and finally, the test accuracy and time index are introduced to evaluate the model. The results show that, among the four kinds of image generation method, the classification performance of data obtained by empirical mode decomposition-pseudo-Wigner–Ville distribution (EP) is the best; when the signal to noise ratio (SNR) is 10 dB, the model test accuracy obtained by TL is 96.67% and the training time is 170.46 s.http://dx.doi.org/10.1155/2021/6616592
spellingShingle Hongwei Fan
Ceyi Xue
Xuhui Zhang
Xiangang Cao
Shuoqi Gao
Sijie Shao
Vibration Images-Driven Fault Diagnosis Based on CNN and Transfer Learning of Rolling Bearing under Strong Noise
Shock and Vibration
title Vibration Images-Driven Fault Diagnosis Based on CNN and Transfer Learning of Rolling Bearing under Strong Noise
title_full Vibration Images-Driven Fault Diagnosis Based on CNN and Transfer Learning of Rolling Bearing under Strong Noise
title_fullStr Vibration Images-Driven Fault Diagnosis Based on CNN and Transfer Learning of Rolling Bearing under Strong Noise
title_full_unstemmed Vibration Images-Driven Fault Diagnosis Based on CNN and Transfer Learning of Rolling Bearing under Strong Noise
title_short Vibration Images-Driven Fault Diagnosis Based on CNN and Transfer Learning of Rolling Bearing under Strong Noise
title_sort vibration images driven fault diagnosis based on cnn and transfer learning of rolling bearing under strong noise
url http://dx.doi.org/10.1155/2021/6616592
work_keys_str_mv AT hongweifan vibrationimagesdrivenfaultdiagnosisbasedoncnnandtransferlearningofrollingbearingunderstrongnoise
AT ceyixue vibrationimagesdrivenfaultdiagnosisbasedoncnnandtransferlearningofrollingbearingunderstrongnoise
AT xuhuizhang vibrationimagesdrivenfaultdiagnosisbasedoncnnandtransferlearningofrollingbearingunderstrongnoise
AT xiangangcao vibrationimagesdrivenfaultdiagnosisbasedoncnnandtransferlearningofrollingbearingunderstrongnoise
AT shuoqigao vibrationimagesdrivenfaultdiagnosisbasedoncnnandtransferlearningofrollingbearingunderstrongnoise
AT sijieshao vibrationimagesdrivenfaultdiagnosisbasedoncnnandtransferlearningofrollingbearingunderstrongnoise