Deep Learning Algorithms for Bearing Fault Diagnostics—A Comprehensive Review
In this survey paper, we systematically summarize existing literature on bearing fault diagnostics with deep learning (DL) algorithms. While conventional machine learning (ML) methods, including artificial neural network, principal component analysis, support vector machines, etc., have been success...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8988271/ |
id |
doaj-6349c42932af4e3dbc7e2acbe7d46ccc |
---|---|
record_format |
Article |
spelling |
doaj-6349c42932af4e3dbc7e2acbe7d46ccc2021-03-30T02:09:58ZengIEEEIEEE Access2169-35362020-01-018298572988110.1109/ACCESS.2020.29728598988271Deep Learning Algorithms for Bearing Fault Diagnostics—A Comprehensive ReviewShen Zhang0https://orcid.org/0000-0002-1245-0565Shibo Zhang1https://orcid.org/0000-0003-3054-9590Bingnan Wang2https://orcid.org/0000-0002-8710-2813Thomas G. Habetler3https://orcid.org/0000-0001-6598-2429Mitsubishi Electric Research Laboratories, Cambridge, MA, USADepartment of Computer Science, Northwestern University, Evanston, IL, USAMitsubishi Electric Research Laboratories, Cambridge, MA, USASchool of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USAIn this survey paper, we systematically summarize existing literature on bearing fault diagnostics with deep learning (DL) algorithms. While conventional machine learning (ML) methods, including artificial neural network, principal component analysis, support vector machines, etc., have been successfully applied to the detection and categorization of bearing faults for decades, recent developments in DL algorithms in the last five years have sparked renewed interest in both industry and academia for intelligent machine health monitoring. In this paper, we first provide a brief review of conventional ML methods, before taking a deep dive into the state-of-the-art DL algorithms for bearing fault applications. Specifically, the superiority of DL based methods are analyzed in terms of fault feature extraction and classification performances; many new functionalities enabled by DL techniques are also summarized. In addition, to obtain a more intuitive insight, a comparative study is conducted on the classification accuracy of different algorithms utilizing the open source Case Western Reserve University (CWRU) bearing dataset. Finally, to facilitate the transition on applying various DL algorithms to bearing fault diagnostics, detailed recommendations and suggestions are provided for specific application conditions. Future research directions to further enhance the performance of DL algorithms on health monitoring are also discussed.https://ieeexplore.ieee.org/document/8988271/Bearing faultdeep learningdiagnosticsfeature extractionmachine learning |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Shen Zhang Shibo Zhang Bingnan Wang Thomas G. Habetler |
spellingShingle |
Shen Zhang Shibo Zhang Bingnan Wang Thomas G. Habetler Deep Learning Algorithms for Bearing Fault Diagnostics—A Comprehensive Review IEEE Access Bearing fault deep learning diagnostics feature extraction machine learning |
author_facet |
Shen Zhang Shibo Zhang Bingnan Wang Thomas G. Habetler |
author_sort |
Shen Zhang |
title |
Deep Learning Algorithms for Bearing Fault Diagnostics—A Comprehensive Review |
title_short |
Deep Learning Algorithms for Bearing Fault Diagnostics—A Comprehensive Review |
title_full |
Deep Learning Algorithms for Bearing Fault Diagnostics—A Comprehensive Review |
title_fullStr |
Deep Learning Algorithms for Bearing Fault Diagnostics—A Comprehensive Review |
title_full_unstemmed |
Deep Learning Algorithms for Bearing Fault Diagnostics—A Comprehensive Review |
title_sort |
deep learning algorithms for bearing fault diagnostics—a comprehensive review |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
In this survey paper, we systematically summarize existing literature on bearing fault diagnostics with deep learning (DL) algorithms. While conventional machine learning (ML) methods, including artificial neural network, principal component analysis, support vector machines, etc., have been successfully applied to the detection and categorization of bearing faults for decades, recent developments in DL algorithms in the last five years have sparked renewed interest in both industry and academia for intelligent machine health monitoring. In this paper, we first provide a brief review of conventional ML methods, before taking a deep dive into the state-of-the-art DL algorithms for bearing fault applications. Specifically, the superiority of DL based methods are analyzed in terms of fault feature extraction and classification performances; many new functionalities enabled by DL techniques are also summarized. In addition, to obtain a more intuitive insight, a comparative study is conducted on the classification accuracy of different algorithms utilizing the open source Case Western Reserve University (CWRU) bearing dataset. Finally, to facilitate the transition on applying various DL algorithms to bearing fault diagnostics, detailed recommendations and suggestions are provided for specific application conditions. Future research directions to further enhance the performance of DL algorithms on health monitoring are also discussed. |
topic |
Bearing fault deep learning diagnostics feature extraction machine learning |
url |
https://ieeexplore.ieee.org/document/8988271/ |
work_keys_str_mv |
AT shenzhang deeplearningalgorithmsforbearingfaultdiagnosticsx2014acomprehensivereview AT shibozhang deeplearningalgorithmsforbearingfaultdiagnosticsx2014acomprehensivereview AT bingnanwang deeplearningalgorithmsforbearingfaultdiagnosticsx2014acomprehensivereview AT thomasghabetler deeplearningalgorithmsforbearingfaultdiagnosticsx2014acomprehensivereview |
_version_ |
1724185631486115840 |