Bearing Fault Diagnosis via Improved One-Dimensional Multi-Scale Dilated CNN

Bearings are the key and important components of rotating machinery. Effective bearing fault diagnosis can ensure operation safety and reduce maintenance costs. This paper aims to develop a novel bearing fault diagnosis method via an improved multi-scale convolutional neural network (IMSCNN). In tra...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jiajun He, Ping Wu, Yizhi Tong, Xujie Zhang, Meizhen Lei, Jinfeng Gao
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	multi-scale CNN dilated convolutional fault diagnosis Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/a1bb9b617351474eb2e88df4e15baac4
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a1bb9b617351474eb2e88df4e15baac4
record_format	dspace
spelling	oai:doaj.org-article:a1bb9b617351474eb2e88df4e15baac42021-11-11T19:16:33ZBearing Fault Diagnosis via Improved One-Dimensional Multi-Scale Dilated CNN10.3390/s212173191424-8220https://doaj.org/article/a1bb9b617351474eb2e88df4e15baac42021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7319https://doaj.org/toc/1424-8220Bearings are the key and important components of rotating machinery. Effective bearing fault diagnosis can ensure operation safety and reduce maintenance costs. This paper aims to develop a novel bearing fault diagnosis method via an improved multi-scale convolutional neural network (IMSCNN). In traditional convolutional neural network (CNN), a fixed convolutional kernel is often employed in the convolutional layer. Thus, informative features can not be fully extracted for fault diagnosis. In the proposed IMSCNN, a 1D dimensional convolutional layer is used to mitigate the effect of noise contained in vibration signals. Then, four dilated convolutional kernels with different dilation rates are integrated to extract multi-scale features through the inception structure. Experimental results from the popular CWRU and PU datasets show the superiority of the proposed method by comparison with other related methods.Jiajun HePing WuYizhi TongXujie ZhangMeizhen LeiJinfeng GaoMDPI AGarticlemulti-scaleCNNdilated convolutionalfault diagnosisChemical technologyTP1-1185ENSensors, Vol 21, Iss 7319, p 7319 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	multi-scale CNN dilated convolutional fault diagnosis Chemical technology TP1-1185
spellingShingle	multi-scale CNN dilated convolutional fault diagnosis Chemical technology TP1-1185 Jiajun He Ping Wu Yizhi Tong Xujie Zhang Meizhen Lei Jinfeng Gao Bearing Fault Diagnosis via Improved One-Dimensional Multi-Scale Dilated CNN
description	Bearings are the key and important components of rotating machinery. Effective bearing fault diagnosis can ensure operation safety and reduce maintenance costs. This paper aims to develop a novel bearing fault diagnosis method via an improved multi-scale convolutional neural network (IMSCNN). In traditional convolutional neural network (CNN), a fixed convolutional kernel is often employed in the convolutional layer. Thus, informative features can not be fully extracted for fault diagnosis. In the proposed IMSCNN, a 1D dimensional convolutional layer is used to mitigate the effect of noise contained in vibration signals. Then, four dilated convolutional kernels with different dilation rates are integrated to extract multi-scale features through the inception structure. Experimental results from the popular CWRU and PU datasets show the superiority of the proposed method by comparison with other related methods.
format	article
author	Jiajun He Ping Wu Yizhi Tong Xujie Zhang Meizhen Lei Jinfeng Gao
author_facet	Jiajun He Ping Wu Yizhi Tong Xujie Zhang Meizhen Lei Jinfeng Gao
author_sort	Jiajun He
title	Bearing Fault Diagnosis via Improved One-Dimensional Multi-Scale Dilated CNN
title_short	Bearing Fault Diagnosis via Improved One-Dimensional Multi-Scale Dilated CNN
title_full	Bearing Fault Diagnosis via Improved One-Dimensional Multi-Scale Dilated CNN
title_fullStr	Bearing Fault Diagnosis via Improved One-Dimensional Multi-Scale Dilated CNN
title_full_unstemmed	Bearing Fault Diagnosis via Improved One-Dimensional Multi-Scale Dilated CNN
title_sort	bearing fault diagnosis via improved one-dimensional multi-scale dilated cnn
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/a1bb9b617351474eb2e88df4e15baac4
work_keys_str_mv	AT jiajunhe bearingfaultdiagnosisviaimprovedonedimensionalmultiscaledilatedcnn AT pingwu bearingfaultdiagnosisviaimprovedonedimensionalmultiscaledilatedcnn AT yizhitong bearingfaultdiagnosisviaimprovedonedimensionalmultiscaledilatedcnn AT xujiezhang bearingfaultdiagnosisviaimprovedonedimensionalmultiscaledilatedcnn AT meizhenlei bearingfaultdiagnosisviaimprovedonedimensionalmultiscaledilatedcnn AT jinfenggao bearingfaultdiagnosisviaimprovedonedimensionalmultiscaledilatedcnn
_version_	1718431601461821440

Bearing Fault Diagnosis via Improved One-Dimensional Multi-Scale Dilated CNN

Ejemplares similares