A Novel Intelligent Fault Diagnosis Method for Rolling Bearings Based on Compressed Sensing and Stacked Multi-Granularity Convolution Denoising Auto-Encoder

This paper investigates the unsupervised automatic feature extraction method with a large amount of unlabeled data for the fault diagnosis of rolling bearings in automobile production line, where the fault information is hard to identify due to the low-level features of a single category and the mas...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Chuang Liang, Changzheng Chen, Ye Liu, Xinying Jia
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Bearing fault intelligent diagnosis feature extraction compressive sensing stacked auto-encoder Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/5bbc5421dfed4c67898e0a2af66bb1f1
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:5bbc5421dfed4c67898e0a2af66bb1f1
record_format	dspace
spelling	oai:doaj.org-article:5bbc5421dfed4c67898e0a2af66bb1f12021-11-25T00:00:57ZA Novel Intelligent Fault Diagnosis Method for Rolling Bearings Based on Compressed Sensing and Stacked Multi-Granularity Convolution Denoising Auto-Encoder2169-353610.1109/ACCESS.2021.3129061https://doaj.org/article/5bbc5421dfed4c67898e0a2af66bb1f12021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9618940/https://doaj.org/toc/2169-3536This paper investigates the unsupervised automatic feature extraction method with a large amount of unlabeled data for the fault diagnosis of rolling bearings in automobile production line, where the fault information is hard to identify due to the low-level features of a single category and the massive fault data is difficult to process. Different from the existing methods, which only combine the compressive sensing with single category of low-level features, or extract features from raw data, a novel intelligent fault diagnosis method for rolling bearings based on the compressive sensing and a stacked multi-granularity convolution denoise auto-encoder network is proposed, which utilizes the nonlinear projection to achieve the compressed acquisition and resolves issues with character unicity by extracting a diverse category of high-level features. Moreover, a regularization method called ‘dropout’ is used to prevent overfitting during the training process. The amount of measured data that contained all the information of faults is reduced and the classification accuracy is improved by extracting more robust features based on the proposed method. Finally, the effectiveness of the proposed method is validated using data sets from rolling bearings in an automotive production line and the analysis result show that it is superior to the existing methods and is able to obtain high diagnostic accuracies.Chuang LiangChangzheng ChenYe LiuXinying JiaIEEEarticleBearing faultintelligent diagnosisfeature extractioncompressive sensingstacked auto-encoderElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 154777-154787 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Bearing fault intelligent diagnosis feature extraction compressive sensing stacked auto-encoder Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Bearing fault intelligent diagnosis feature extraction compressive sensing stacked auto-encoder Electrical engineering. Electronics. Nuclear engineering TK1-9971 Chuang Liang Changzheng Chen Ye Liu Xinying Jia A Novel Intelligent Fault Diagnosis Method for Rolling Bearings Based on Compressed Sensing and Stacked Multi-Granularity Convolution Denoising Auto-Encoder
description	This paper investigates the unsupervised automatic feature extraction method with a large amount of unlabeled data for the fault diagnosis of rolling bearings in automobile production line, where the fault information is hard to identify due to the low-level features of a single category and the massive fault data is difficult to process. Different from the existing methods, which only combine the compressive sensing with single category of low-level features, or extract features from raw data, a novel intelligent fault diagnosis method for rolling bearings based on the compressive sensing and a stacked multi-granularity convolution denoise auto-encoder network is proposed, which utilizes the nonlinear projection to achieve the compressed acquisition and resolves issues with character unicity by extracting a diverse category of high-level features. Moreover, a regularization method called ‘dropout’ is used to prevent overfitting during the training process. The amount of measured data that contained all the information of faults is reduced and the classification accuracy is improved by extracting more robust features based on the proposed method. Finally, the effectiveness of the proposed method is validated using data sets from rolling bearings in an automotive production line and the analysis result show that it is superior to the existing methods and is able to obtain high diagnostic accuracies.
format	article
author	Chuang Liang Changzheng Chen Ye Liu Xinying Jia
author_facet	Chuang Liang Changzheng Chen Ye Liu Xinying Jia
author_sort	Chuang Liang
title	A Novel Intelligent Fault Diagnosis Method for Rolling Bearings Based on Compressed Sensing and Stacked Multi-Granularity Convolution Denoising Auto-Encoder
title_short	A Novel Intelligent Fault Diagnosis Method for Rolling Bearings Based on Compressed Sensing and Stacked Multi-Granularity Convolution Denoising Auto-Encoder
title_full	A Novel Intelligent Fault Diagnosis Method for Rolling Bearings Based on Compressed Sensing and Stacked Multi-Granularity Convolution Denoising Auto-Encoder
title_fullStr	A Novel Intelligent Fault Diagnosis Method for Rolling Bearings Based on Compressed Sensing and Stacked Multi-Granularity Convolution Denoising Auto-Encoder
title_full_unstemmed	A Novel Intelligent Fault Diagnosis Method for Rolling Bearings Based on Compressed Sensing and Stacked Multi-Granularity Convolution Denoising Auto-Encoder
title_sort	novel intelligent fault diagnosis method for rolling bearings based on compressed sensing and stacked multi-granularity convolution denoising auto-encoder
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/5bbc5421dfed4c67898e0a2af66bb1f1
work_keys_str_mv	AT chuangliang anovelintelligentfaultdiagnosismethodforrollingbearingsbasedoncompressedsensingandstackedmultigranularityconvolutiondenoisingautoencoder AT changzhengchen anovelintelligentfaultdiagnosismethodforrollingbearingsbasedoncompressedsensingandstackedmultigranularityconvolutiondenoisingautoencoder AT yeliu anovelintelligentfaultdiagnosismethodforrollingbearingsbasedoncompressedsensingandstackedmultigranularityconvolutiondenoisingautoencoder AT xinyingjia anovelintelligentfaultdiagnosismethodforrollingbearingsbasedoncompressedsensingandstackedmultigranularityconvolutiondenoisingautoencoder AT chuangliang novelintelligentfaultdiagnosismethodforrollingbearingsbasedoncompressedsensingandstackedmultigranularityconvolutiondenoisingautoencoder AT changzhengchen novelintelligentfaultdiagnosismethodforrollingbearingsbasedoncompressedsensingandstackedmultigranularityconvolutiondenoisingautoencoder AT yeliu novelintelligentfaultdiagnosismethodforrollingbearingsbasedoncompressedsensingandstackedmultigranularityconvolutiondenoisingautoencoder AT xinyingjia novelintelligentfaultdiagnosismethodforrollingbearingsbasedoncompressedsensingandstackedmultigranularityconvolutiondenoisingautoencoder
_version_	1718414695471251456

A Novel Intelligent Fault Diagnosis Method for Rolling Bearings Based on Compressed Sensing and Stacked Multi-Granularity Convolution Denoising Auto-Encoder

Ejemplares similares