Cargando…

Gearbox Fault Diagnosis Method Based on Multidomain Information Fusion

Traditional methods of gearbox fault diagnosis rely heavily on manual experience. To address this problem, our study proposes a gearbox fault diagnosis method based on multidomain information fusion. An experimental platform consisting of a JZQ250 fixed-axis gearbox was built. An acceleration sensor...

Descripción completa

Detalles Bibliográficos
Autores principales: Xie, Fengyun, Wang, Gan, Shang, Jiandong, Liu, Hui, Xiao, Qian, Xie, Sanmao
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10223782/
https://www.ncbi.nlm.nih.gov/pubmed/37430835
http://dx.doi.org/10.3390/s23104921
_version_ 1785050023905460224
author Xie, Fengyun
Wang, Gan
Shang, Jiandong
Liu, Hui
Xiao, Qian
Xie, Sanmao
author_facet Xie, Fengyun
Wang, Gan
Shang, Jiandong
Liu, Hui
Xiao, Qian
Xie, Sanmao
author_sort Xie, Fengyun
collection PubMed
description Traditional methods of gearbox fault diagnosis rely heavily on manual experience. To address this problem, our study proposes a gearbox fault diagnosis method based on multidomain information fusion. An experimental platform consisting of a JZQ250 fixed-axis gearbox was built. An acceleration sensor was used to obtain the vibration signal of the gearbox. Singular value decomposition (SVD) was used to preprocess the signal in order to reduce noise, and the processed vibration signal was subjected to short-time Fourier transform to obtain a two-dimensional time–frequency map. A multidomain information fusion convolutional neural network (CNN) model was constructed. Channel 1 was a one-dimensional convolutional neural network (1DCNN) model that input a one-dimensional vibration signal, and channel 2 was a two-dimensional convolutional neural network (2DCNN) model that input short-time Fourier transform (STFT) time–frequency images. The feature vectors extracted using the two channels were then fused into feature vectors for input into the classification model. Finally, support vector machines (SVM) were used to identify and classify the fault types. The model training performance used multiple methods: training set, verification set, loss curve, accuracy curve and t-SNE visualization (t-SNE). Through experimental verification, the method proposed in this paper was compared with FFT-2DCNN, 1DCNN-SVM and 2DCNN-SVM in terms of gearbox fault recognition performance. The model proposed in this paper had the highest fault recognition accuracy (98.08%).
format Online
Article
Text
id pubmed-10223782
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-102237822023-05-28 Gearbox Fault Diagnosis Method Based on Multidomain Information Fusion Xie, Fengyun Wang, Gan Shang, Jiandong Liu, Hui Xiao, Qian Xie, Sanmao Sensors (Basel) Article Traditional methods of gearbox fault diagnosis rely heavily on manual experience. To address this problem, our study proposes a gearbox fault diagnosis method based on multidomain information fusion. An experimental platform consisting of a JZQ250 fixed-axis gearbox was built. An acceleration sensor was used to obtain the vibration signal of the gearbox. Singular value decomposition (SVD) was used to preprocess the signal in order to reduce noise, and the processed vibration signal was subjected to short-time Fourier transform to obtain a two-dimensional time–frequency map. A multidomain information fusion convolutional neural network (CNN) model was constructed. Channel 1 was a one-dimensional convolutional neural network (1DCNN) model that input a one-dimensional vibration signal, and channel 2 was a two-dimensional convolutional neural network (2DCNN) model that input short-time Fourier transform (STFT) time–frequency images. The feature vectors extracted using the two channels were then fused into feature vectors for input into the classification model. Finally, support vector machines (SVM) were used to identify and classify the fault types. The model training performance used multiple methods: training set, verification set, loss curve, accuracy curve and t-SNE visualization (t-SNE). Through experimental verification, the method proposed in this paper was compared with FFT-2DCNN, 1DCNN-SVM and 2DCNN-SVM in terms of gearbox fault recognition performance. The model proposed in this paper had the highest fault recognition accuracy (98.08%). MDPI 2023-05-19 /pmc/articles/PMC10223782/ /pubmed/37430835 http://dx.doi.org/10.3390/s23104921 Text en © 2023 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
Xie, Fengyun
Wang, Gan
Shang, Jiandong
Liu, Hui
Xiao, Qian
Xie, Sanmao
Gearbox Fault Diagnosis Method Based on Multidomain Information Fusion
title Gearbox Fault Diagnosis Method Based on Multidomain Information Fusion
title_full Gearbox Fault Diagnosis Method Based on Multidomain Information Fusion
title_fullStr Gearbox Fault Diagnosis Method Based on Multidomain Information Fusion
title_full_unstemmed Gearbox Fault Diagnosis Method Based on Multidomain Information Fusion
title_short Gearbox Fault Diagnosis Method Based on Multidomain Information Fusion
title_sort gearbox fault diagnosis method based on multidomain information fusion
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10223782/
https://www.ncbi.nlm.nih.gov/pubmed/37430835
http://dx.doi.org/10.3390/s23104921
work_keys_str_mv AT xiefengyun gearboxfaultdiagnosismethodbasedonmultidomaininformationfusion
AT wanggan gearboxfaultdiagnosismethodbasedonmultidomaininformationfusion
AT shangjiandong gearboxfaultdiagnosismethodbasedonmultidomaininformationfusion
AT liuhui gearboxfaultdiagnosismethodbasedonmultidomaininformationfusion
AT xiaoqian gearboxfaultdiagnosismethodbasedonmultidomaininformationfusion
AT xiesanmao gearboxfaultdiagnosismethodbasedonmultidomaininformationfusion