Fault Diagnosis of Rotating Machinery Based on One-Dimensional Deep Residual Shrinkage Network with a Wide Convolution Layer

In actual engineering applications, inevitable noise seriously affects the accuracy of fault diagnosis for rotating machinery. To effectively identify the fault classes of rotating machinery under noise interference, an efficient fault diagnosis method without additional denoising procedures is prop...

Full description

Bibliographic Details
Main Authors:	Jingli Yang, Tianyu Gao, Shouda Jiang, Shijie Li, Qing Tang
Format:	Article
Language:	English
Published:	Hindawi Limited 2020-01-01
Series:	Shock and Vibration
Online Access:	http://dx.doi.org/10.1155/2020/8880960

id	doaj-b4c03a51b8814b70b472df2f11dc017f
record_format	Article
spelling	doaj-b4c03a51b8814b70b472df2f11dc017f2020-12-21T11:41:26ZengHindawi LimitedShock and Vibration1070-96221875-92032020-01-01202010.1155/2020/88809608880960Fault Diagnosis of Rotating Machinery Based on One-Dimensional Deep Residual Shrinkage Network with a Wide Convolution LayerJingli Yang0Tianyu Gao1Shouda Jiang2Shijie Li3Qing Tang4Department of Automatic Test and Control, Harbin Institute of Technology, Harbin 150001, ChinaDepartment of Automatic Test and Control, Harbin Institute of Technology, Harbin 150001, ChinaDepartment of Automatic Test and Control, Harbin Institute of Technology, Harbin 150001, ChinaChina Tobacco Henan Industrial Co., Ltd., Zhengzhou 450000, ChinaChina Institute of Marine Technology and Economy, Beijing 10001, ChinaIn actual engineering applications, inevitable noise seriously affects the accuracy of fault diagnosis for rotating machinery. To effectively identify the fault classes of rotating machinery under noise interference, an efficient fault diagnosis method without additional denoising procedures is proposed. First, a one-dimensional deep residual shrinkage network, which directly takes the raw vibration signals contaminated by noise as input, is developed to realize end-to-end fault diagnosis. Then, to further enhance the noise immunity of the diagnosis model, the first layer of the model is set to a wide convolution layer to extract short time features. Moreover, an adaptive batch normalization algorithm (AdaBN) is introduced into the diagnosis model to enhance the adaptability to noise. Experimental results illustrate that the fault diagnosis model for rotating machinery based on one-dimensional deep residual shrinkage network with a wide convolution layer (1D-WDRSN) can accurately identify the fault classes even under noise interference.http://dx.doi.org/10.1155/2020/8880960
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Jingli Yang Tianyu Gao Shouda Jiang Shijie Li Qing Tang
spellingShingle	Jingli Yang Tianyu Gao Shouda Jiang Shijie Li Qing Tang Fault Diagnosis of Rotating Machinery Based on One-Dimensional Deep Residual Shrinkage Network with a Wide Convolution Layer Shock and Vibration
author_facet	Jingli Yang Tianyu Gao Shouda Jiang Shijie Li Qing Tang
author_sort	Jingli Yang
title	Fault Diagnosis of Rotating Machinery Based on One-Dimensional Deep Residual Shrinkage Network with a Wide Convolution Layer
title_short	Fault Diagnosis of Rotating Machinery Based on One-Dimensional Deep Residual Shrinkage Network with a Wide Convolution Layer
title_full	Fault Diagnosis of Rotating Machinery Based on One-Dimensional Deep Residual Shrinkage Network with a Wide Convolution Layer
title_fullStr	Fault Diagnosis of Rotating Machinery Based on One-Dimensional Deep Residual Shrinkage Network with a Wide Convolution Layer
title_full_unstemmed	Fault Diagnosis of Rotating Machinery Based on One-Dimensional Deep Residual Shrinkage Network with a Wide Convolution Layer
title_sort	fault diagnosis of rotating machinery based on one-dimensional deep residual shrinkage network with a wide convolution layer
publisher	Hindawi Limited
series	Shock and Vibration
issn	1070-9622 1875-9203
publishDate	2020-01-01
description	In actual engineering applications, inevitable noise seriously affects the accuracy of fault diagnosis for rotating machinery. To effectively identify the fault classes of rotating machinery under noise interference, an efficient fault diagnosis method without additional denoising procedures is proposed. First, a one-dimensional deep residual shrinkage network, which directly takes the raw vibration signals contaminated by noise as input, is developed to realize end-to-end fault diagnosis. Then, to further enhance the noise immunity of the diagnosis model, the first layer of the model is set to a wide convolution layer to extract short time features. Moreover, an adaptive batch normalization algorithm (AdaBN) is introduced into the diagnosis model to enhance the adaptability to noise. Experimental results illustrate that the fault diagnosis model for rotating machinery based on one-dimensional deep residual shrinkage network with a wide convolution layer (1D-WDRSN) can accurately identify the fault classes even under noise interference.
url	http://dx.doi.org/10.1155/2020/8880960
work_keys_str_mv	AT jingliyang faultdiagnosisofrotatingmachinerybasedononedimensionaldeepresidualshrinkagenetworkwithawideconvolutionlayer AT tianyugao faultdiagnosisofrotatingmachinerybasedononedimensionaldeepresidualshrinkagenetworkwithawideconvolutionlayer AT shoudajiang faultdiagnosisofrotatingmachinerybasedononedimensionaldeepresidualshrinkagenetworkwithawideconvolutionlayer AT shijieli faultdiagnosisofrotatingmachinerybasedononedimensionaldeepresidualshrinkagenetworkwithawideconvolutionlayer AT qingtang faultdiagnosisofrotatingmachinerybasedononedimensionaldeepresidualshrinkagenetworkwithawideconvolutionlayer
_version_	1714988526332805120

Fault Diagnosis of Rotating Machinery Based on One-Dimensional Deep Residual Shrinkage Network with a Wide Convolution Layer

Similar Items