Cargando…

Rolling Bearing Fault Diagnosis Using Multi-Sensor Data Fusion Based on 1D-CNN Model

To satisfy the requirements of the end-to-end fault diagnosis of rolling bearings, a hybrid model, based on optimal SWD and 1D-CNN, with the layer of multi-sensor data fusion, is proposed in this paper. Firstly, the BAS optimal algorithm is adopted to obtain the optimal parameters of SWD. After that...

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Hongwei, Sun, Wenlei, He, Li, Zhou, Jianxing
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9141983/
https://www.ncbi.nlm.nih.gov/pubmed/35626458
http://dx.doi.org/10.3390/e24050573
_version_ 1784715476167819264
author Wang, Hongwei
Sun, Wenlei
He, Li
Zhou, Jianxing
author_facet Wang, Hongwei
Sun, Wenlei
He, Li
Zhou, Jianxing
author_sort Wang, Hongwei
collection PubMed
description To satisfy the requirements of the end-to-end fault diagnosis of rolling bearings, a hybrid model, based on optimal SWD and 1D-CNN, with the layer of multi-sensor data fusion, is proposed in this paper. Firstly, the BAS optimal algorithm is adopted to obtain the optimal parameters of SWD. After that, the raw signals from different channels of sensors are segmented and preprocessed by the optimal SWD, whose name is BAS-SWD. By which, the sensitive OCs with higher values of spectrum kurtosis are extracted from the raw signals. Subsequently, the improved 1D-CNN model based on VGG-16 is constructed, and the decomposed signals from different channels are fed into the independent convolutional blocks in the model; then, the features extracted from the input signals are fused in the fusion layer. Finally, the fused features are processed by the fully connected layers, and the probability of classification is calculated by the cross-entropy loss function. The result of comparative experiments, based on different datasets, indicates that the proposed model is accurate, effective, and has a good generalization ability.
format Online
Article
Text
id pubmed-9141983
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-91419832022-05-28 Rolling Bearing Fault Diagnosis Using Multi-Sensor Data Fusion Based on 1D-CNN Model Wang, Hongwei Sun, Wenlei He, Li Zhou, Jianxing Entropy (Basel) Article To satisfy the requirements of the end-to-end fault diagnosis of rolling bearings, a hybrid model, based on optimal SWD and 1D-CNN, with the layer of multi-sensor data fusion, is proposed in this paper. Firstly, the BAS optimal algorithm is adopted to obtain the optimal parameters of SWD. After that, the raw signals from different channels of sensors are segmented and preprocessed by the optimal SWD, whose name is BAS-SWD. By which, the sensitive OCs with higher values of spectrum kurtosis are extracted from the raw signals. Subsequently, the improved 1D-CNN model based on VGG-16 is constructed, and the decomposed signals from different channels are fed into the independent convolutional blocks in the model; then, the features extracted from the input signals are fused in the fusion layer. Finally, the fused features are processed by the fully connected layers, and the probability of classification is calculated by the cross-entropy loss function. The result of comparative experiments, based on different datasets, indicates that the proposed model is accurate, effective, and has a good generalization ability. MDPI 2022-04-19 /pmc/articles/PMC9141983/ /pubmed/35626458 http://dx.doi.org/10.3390/e24050573 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Wang, Hongwei
Sun, Wenlei
He, Li
Zhou, Jianxing
Rolling Bearing Fault Diagnosis Using Multi-Sensor Data Fusion Based on 1D-CNN Model
title Rolling Bearing Fault Diagnosis Using Multi-Sensor Data Fusion Based on 1D-CNN Model
title_full Rolling Bearing Fault Diagnosis Using Multi-Sensor Data Fusion Based on 1D-CNN Model
title_fullStr Rolling Bearing Fault Diagnosis Using Multi-Sensor Data Fusion Based on 1D-CNN Model
title_full_unstemmed Rolling Bearing Fault Diagnosis Using Multi-Sensor Data Fusion Based on 1D-CNN Model
title_short Rolling Bearing Fault Diagnosis Using Multi-Sensor Data Fusion Based on 1D-CNN Model
title_sort rolling bearing fault diagnosis using multi-sensor data fusion based on 1d-cnn model
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9141983/
https://www.ncbi.nlm.nih.gov/pubmed/35626458
http://dx.doi.org/10.3390/e24050573
work_keys_str_mv AT wanghongwei rollingbearingfaultdiagnosisusingmultisensordatafusionbasedon1dcnnmodel
AT sunwenlei rollingbearingfaultdiagnosisusingmultisensordatafusionbasedon1dcnnmodel
AT heli rollingbearingfaultdiagnosisusingmultisensordatafusionbasedon1dcnnmodel
AT zhoujianxing rollingbearingfaultdiagnosisusingmultisensordatafusionbasedon1dcnnmodel