Multiple Working Condition Bearing Fault Diagnosis Method Based on Channel Segmentation Improved Residual Network

To address the problems of poor model diagnosis and poor noise immunity caused by inconsistent distribution of bearing fault features and difficulty in feature extraction in multi-condition environments, a multi-condition bearing fault diagnosis method based on a channel segmentation improved residu...

Full description

Bibliographic Details
Main Authors: Yuanyuan Jiang, Jinyang Xie, Linghui Meng, Hanguang Jia
Format: Article
Language:English
Published: MDPI AG 2022-12-01
Series:Electronics
Subjects:
Online Access:https://www.mdpi.com/2079-9292/12/1/145
_version_ 1797625954504278016
author Yuanyuan Jiang
Jinyang Xie
Linghui Meng
Hanguang Jia
author_facet Yuanyuan Jiang
Jinyang Xie
Linghui Meng
Hanguang Jia
author_sort Yuanyuan Jiang
collection DOAJ
description To address the problems of poor model diagnosis and poor noise immunity caused by inconsistent distribution of bearing fault features and difficulty in feature extraction in multi-condition environments, a multi-condition bearing fault diagnosis method based on a channel segmentation improved residual network is proposed. A channel segmentation mechanism is designed for channel information highlighting, by selecting one channel of the three-channel feature image as the main operation channel, stacking it with the secondary operation channel after convolution, and then inputting the stacked feature map into the convolutional neural network to realize the extraction and classification of bearing fault features. Four different network models were selected to verify the diagnostic performance of the channel segmentation mechanism on the Case Western Reserve University bearing dataset and the Jiangnan University bearing dataset, and noise immunity experiments were conducted on the Jiangnan University bearing dataset. The experiments show that the proposed diagnostic model on the Case Western Reserve bearing dataset has a minimum improvement of 6.8% compared to the comparison method for multi-case bearing fault diagnosis experiments. In terms of noise immunity, the diagnostic accuracy of the fault diagnosis model with the addition of the channel cut-off mechanism improves the diagnostic accuracy of the noisy data by an average of 4.3% compared to that without the addition. The proposed model still has excellent diagnostic performance when diagnosing variable speed bearing faults.
first_indexed 2024-03-11T10:03:48Z
format Article
id doaj.art-4b960e7a4f384a7982b8e30c9dab2f05
institution Directory Open Access Journal
issn 2079-9292
language English
last_indexed 2024-03-11T10:03:48Z
publishDate 2022-12-01
publisher MDPI AG
record_format Article
series Electronics
spelling doaj.art-4b960e7a4f384a7982b8e30c9dab2f052023-11-16T15:11:43ZengMDPI AGElectronics2079-92922022-12-0112114510.3390/electronics12010145Multiple Working Condition Bearing Fault Diagnosis Method Based on Channel Segmentation Improved Residual NetworkYuanyuan Jiang0Jinyang Xie1Linghui Meng2Hanguang Jia3School of Electrical and Information Engineering, Anhui University of Science and Technology, Huainan 232000, ChinaSchool of Institute of Artificial Intelligence, Anhui University of Science and Technology, Huainan 232000, ChinaChina Electronic Product Reliability and Environmental Testing Research Institute, Guangzhou 510610, ChinaChina Electronic Product Reliability and Environmental Testing Research Institute, Guangzhou 510610, ChinaTo address the problems of poor model diagnosis and poor noise immunity caused by inconsistent distribution of bearing fault features and difficulty in feature extraction in multi-condition environments, a multi-condition bearing fault diagnosis method based on a channel segmentation improved residual network is proposed. A channel segmentation mechanism is designed for channel information highlighting, by selecting one channel of the three-channel feature image as the main operation channel, stacking it with the secondary operation channel after convolution, and then inputting the stacked feature map into the convolutional neural network to realize the extraction and classification of bearing fault features. Four different network models were selected to verify the diagnostic performance of the channel segmentation mechanism on the Case Western Reserve University bearing dataset and the Jiangnan University bearing dataset, and noise immunity experiments were conducted on the Jiangnan University bearing dataset. The experiments show that the proposed diagnostic model on the Case Western Reserve bearing dataset has a minimum improvement of 6.8% compared to the comparison method for multi-case bearing fault diagnosis experiments. In terms of noise immunity, the diagnostic accuracy of the fault diagnosis model with the addition of the channel cut-off mechanism improves the diagnostic accuracy of the noisy data by an average of 4.3% compared to that without the addition. The proposed model still has excellent diagnostic performance when diagnosing variable speed bearing faults.https://www.mdpi.com/2079-9292/12/1/145multiple working conditionsbearing fault diagnosischannel segmentation mechanismconvolutional neural network
spellingShingle Yuanyuan Jiang
Jinyang Xie
Linghui Meng
Hanguang Jia
Multiple Working Condition Bearing Fault Diagnosis Method Based on Channel Segmentation Improved Residual Network
Electronics
multiple working conditions
bearing fault diagnosis
channel segmentation mechanism
convolutional neural network
title Multiple Working Condition Bearing Fault Diagnosis Method Based on Channel Segmentation Improved Residual Network
title_full Multiple Working Condition Bearing Fault Diagnosis Method Based on Channel Segmentation Improved Residual Network
title_fullStr Multiple Working Condition Bearing Fault Diagnosis Method Based on Channel Segmentation Improved Residual Network
title_full_unstemmed Multiple Working Condition Bearing Fault Diagnosis Method Based on Channel Segmentation Improved Residual Network
title_short Multiple Working Condition Bearing Fault Diagnosis Method Based on Channel Segmentation Improved Residual Network
title_sort multiple working condition bearing fault diagnosis method based on channel segmentation improved residual network
topic multiple working conditions
bearing fault diagnosis
channel segmentation mechanism
convolutional neural network
url https://www.mdpi.com/2079-9292/12/1/145
work_keys_str_mv AT yuanyuanjiang multipleworkingconditionbearingfaultdiagnosismethodbasedonchannelsegmentationimprovedresidualnetwork
AT jinyangxie multipleworkingconditionbearingfaultdiagnosismethodbasedonchannelsegmentationimprovedresidualnetwork
AT linghuimeng multipleworkingconditionbearingfaultdiagnosismethodbasedonchannelsegmentationimprovedresidualnetwork
AT hanguangjia multipleworkingconditionbearingfaultdiagnosismethodbasedonchannelsegmentationimprovedresidualnetwork