Research on Intelligent Fault Diagnosis of Rolling Bearing Based on Improved Deep Residual Network

Rolling bearings are the most fault-prone parts in rotating machinery. In order to find faults in time and reduce losses, this paper presents an intelligent diagnosis method for rolling bearings. At present, the deep residual network (RESNET) is the most widely used convolutional neural network (CNN...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Xinyu Hao, Yuan Zheng, Li Lu, Hong Pan
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	fault diagnosis improved deep residual network deep learning GAP Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/3ac15ed7254c4b569b5b9452548dfccf
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:3ac15ed7254c4b569b5b9452548dfccf
record_format	dspace
spelling	oai:doaj.org-article:3ac15ed7254c4b569b5b9452548dfccf2021-11-25T16:39:54ZResearch on Intelligent Fault Diagnosis of Rolling Bearing Based on Improved Deep Residual Network10.3390/app1122108892076-3417https://doaj.org/article/3ac15ed7254c4b569b5b9452548dfccf2021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/22/10889https://doaj.org/toc/2076-3417Rolling bearings are the most fault-prone parts in rotating machinery. In order to find faults in time and reduce losses, this paper presents an intelligent diagnosis method for rolling bearings. At present, the deep residual network (RESNET) is the most widely used convolutional neural network (CNN) and has become one of the hotspots in fault diagnosis. However, the fully connected layer of the deep residual network has the disadvantage of too many training parameters, which makes the model training and testing time longer. So, we proposed a new network structure which the global average pooling (GAP) technology replaces the fully connected layer part of the traditional RESNET. It effectively solves the problem of too many parameters of the traditional RESNET model, and uses data enhancement, dropout, and other deep learning training techniques to prevent the model from overfitting. Experiments show that the accuracy of fault diagnosis of the improved algorithm reaches 99.83%, training time has been shortened. Also, the whole process of rolling bearing fault detection does not need any manually extract features, and this “end-to-end” algorithm has good versatility and operability.Xinyu HaoYuan ZhengLi LuHong PanMDPI AGarticlefault diagnosisimproved deep residual networkdeep learningGAPTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10889, p 10889 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	fault diagnosis improved deep residual network deep learning GAP Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	fault diagnosis improved deep residual network deep learning GAP Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Xinyu Hao Yuan Zheng Li Lu Hong Pan Research on Intelligent Fault Diagnosis of Rolling Bearing Based on Improved Deep Residual Network
description	Rolling bearings are the most fault-prone parts in rotating machinery. In order to find faults in time and reduce losses, this paper presents an intelligent diagnosis method for rolling bearings. At present, the deep residual network (RESNET) is the most widely used convolutional neural network (CNN) and has become one of the hotspots in fault diagnosis. However, the fully connected layer of the deep residual network has the disadvantage of too many training parameters, which makes the model training and testing time longer. So, we proposed a new network structure which the global average pooling (GAP) technology replaces the fully connected layer part of the traditional RESNET. It effectively solves the problem of too many parameters of the traditional RESNET model, and uses data enhancement, dropout, and other deep learning training techniques to prevent the model from overfitting. Experiments show that the accuracy of fault diagnosis of the improved algorithm reaches 99.83%, training time has been shortened. Also, the whole process of rolling bearing fault detection does not need any manually extract features, and this “end-to-end” algorithm has good versatility and operability.
format	article
author	Xinyu Hao Yuan Zheng Li Lu Hong Pan
author_facet	Xinyu Hao Yuan Zheng Li Lu Hong Pan
author_sort	Xinyu Hao
title	Research on Intelligent Fault Diagnosis of Rolling Bearing Based on Improved Deep Residual Network
title_short	Research on Intelligent Fault Diagnosis of Rolling Bearing Based on Improved Deep Residual Network
title_full	Research on Intelligent Fault Diagnosis of Rolling Bearing Based on Improved Deep Residual Network
title_fullStr	Research on Intelligent Fault Diagnosis of Rolling Bearing Based on Improved Deep Residual Network
title_full_unstemmed	Research on Intelligent Fault Diagnosis of Rolling Bearing Based on Improved Deep Residual Network
title_sort	research on intelligent fault diagnosis of rolling bearing based on improved deep residual network
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/3ac15ed7254c4b569b5b9452548dfccf
work_keys_str_mv	AT xinyuhao researchonintelligentfaultdiagnosisofrollingbearingbasedonimproveddeepresidualnetwork AT yuanzheng researchonintelligentfaultdiagnosisofrollingbearingbasedonimproveddeepresidualnetwork AT lilu researchonintelligentfaultdiagnosisofrollingbearingbasedonimproveddeepresidualnetwork AT hongpan researchonintelligentfaultdiagnosisofrollingbearingbasedonimproveddeepresidualnetwork
_version_	1718413070568521728

Research on Intelligent Fault Diagnosis of Rolling Bearing Based on Improved Deep Residual Network

Ejemplares similares