Deep Learning Method for Bearing Fault Diagnosis

In recent years, deep learning technology has shown great potential in bearing fault diagnosis based on vibration signals.However, in the fault diagnosis method based on deep learning, the traditional single network topology feature extraction has weak discrimination and low noise robustness, and th...

Full description

Saved in:
Bibliographic Details
Main Authors: LIU Xiu, MA Shan-tao, XIE Yi-ning, HE Yong-jun
Format: Article
Language:zho
Published: Harbin University of Science and Technology Publications 2022-08-01
Series:Journal of Harbin University of Science and Technology
Subjects:
Online Access:https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2124
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849713322002219008
author LIU Xiu
MA Shan-tao
XIE Yi-ning
HE Yong-jun
author_facet LIU Xiu
MA Shan-tao
XIE Yi-ning
HE Yong-jun
author_sort LIU Xiu
collection DOAJ
description In recent years, deep learning technology has shown great potential in bearing fault diagnosis based on vibration signals.However, in the fault diagnosis method based on deep learning, the traditional single network topology feature extraction has weak discrimination and low noise robustness, and the accuracy of fault diagnosis is not high.In addition, most of the current research methods have a low fault recognition rate in a variable load environment.In response to the above problems, this paper proposes an improved neural network end-to-end fault diagnosis model.The model combines convolutional neural networks (CNN) and the attention long short-term memory (ALSTM) based on the attention mechanism, and uses ALSTM to capture long-distance correlations in time series data , Effectively suppress the high frequency noise in the input signal.At the same time, a multi-scale and attention mechanism is introduced to broaden the range of the convolution kernel to capture high and low frequency features, and highlight the key features of the fault. After testing on multiple data sets, and comparing with existing methods, experiments show that the method in this paper has significant performance in accuracy, noise robustness, and fault recognition rate under variable load conditions.
format Article
id doaj-art-ccc44ee1d96944c8acec94b8a5e4aac4
institution DOAJ
issn 1007-2683
language zho
publishDate 2022-08-01
publisher Harbin University of Science and Technology Publications
record_format Article
series Journal of Harbin University of Science and Technology
spelling doaj-art-ccc44ee1d96944c8acec94b8a5e4aac42025-08-20T03:13:59ZzhoHarbin University of Science and Technology PublicationsJournal of Harbin University of Science and Technology1007-26832022-08-01270411812410.15938/j.jhust.2022.04.015Deep Learning Method for Bearing Fault DiagnosisLIU Xiu0MA Shan-tao1XIE Yi-ning2HE Yong-jun3School of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, ChinaSchool of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, ChinaCollege of Mechanical and Electrical Engineering, The Northeast Forestry University, Harbin 150080, ChinaSchool of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, ChinaIn recent years, deep learning technology has shown great potential in bearing fault diagnosis based on vibration signals.However, in the fault diagnosis method based on deep learning, the traditional single network topology feature extraction has weak discrimination and low noise robustness, and the accuracy of fault diagnosis is not high.In addition, most of the current research methods have a low fault recognition rate in a variable load environment.In response to the above problems, this paper proposes an improved neural network end-to-end fault diagnosis model.The model combines convolutional neural networks (CNN) and the attention long short-term memory (ALSTM) based on the attention mechanism, and uses ALSTM to capture long-distance correlations in time series data , Effectively suppress the high frequency noise in the input signal.At the same time, a multi-scale and attention mechanism is introduced to broaden the range of the convolution kernel to capture high and low frequency features, and highlight the key features of the fault. After testing on multiple data sets, and comparing with existing methods, experiments show that the method in this paper has significant performance in accuracy, noise robustness, and fault recognition rate under variable load conditions.https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2124fault diagnosisconvolutional neural networklong and short-term memory networkmulti-scale feature extractionattention mechanism
spellingShingle LIU Xiu
MA Shan-tao
XIE Yi-ning
HE Yong-jun
Deep Learning Method for Bearing Fault Diagnosis
Journal of Harbin University of Science and Technology
fault diagnosis
convolutional neural network
long and short-term memory network
multi-scale feature extraction
attention mechanism
title Deep Learning Method for Bearing Fault Diagnosis
title_full Deep Learning Method for Bearing Fault Diagnosis
title_fullStr Deep Learning Method for Bearing Fault Diagnosis
title_full_unstemmed Deep Learning Method for Bearing Fault Diagnosis
title_short Deep Learning Method for Bearing Fault Diagnosis
title_sort deep learning method for bearing fault diagnosis
topic fault diagnosis
convolutional neural network
long and short-term memory network
multi-scale feature extraction
attention mechanism
url https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2124
work_keys_str_mv AT liuxiu deeplearningmethodforbearingfaultdiagnosis
AT mashantao deeplearningmethodforbearingfaultdiagnosis
AT xieyining deeplearningmethodforbearingfaultdiagnosis
AT heyongjun deeplearningmethodforbearingfaultdiagnosis