MCRCNet: A Bearing Fault Diagnosis Method for Unknown Faults Based on Transfer Learning

Bearing fault diagnosis in actual working conditions often faces the problem that unknown type faults cannot be identified, which seriously restricts the practical application of fault diagnosis technology. To solve this problem, this paper proposes a bearing fault diagnosis method based on transfer...

Full description

Saved in:
Bibliographic Details
Main Authors: Guangyuan Xu, Ruifeng Guo, Zhenyu Yin, Feiqing Zhang
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/2/921
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832589185019543552
author Guangyuan Xu
Ruifeng Guo
Zhenyu Yin
Feiqing Zhang
author_facet Guangyuan Xu
Ruifeng Guo
Zhenyu Yin
Feiqing Zhang
author_sort Guangyuan Xu
collection DOAJ
description Bearing fault diagnosis in actual working conditions often faces the problem that unknown type faults cannot be identified, which seriously restricts the practical application of fault diagnosis technology. To solve this problem, this paper proposes a bearing fault diagnosis method based on transfer learning. Firstly, this paper designs a feature extraction network, the Multi-scale Convolution-Convolutional Reconstruction Network (MCRCNet), which incorporates a multi-scale feature extraction module to extract bearing fault features at multiple scales, thereby enhancing the extraction ability of key information. Secondly, this paper designs an improved convolutional reconstruction module AcConv (Adaptive Convolution reconstruction), which highlights key feature information and reduces redundant features by reconstructing the feature map. Furthermore, this paper also modifies the loss function to improve the performance in the case of data imbalance, and introduces the Wasserstein distance to optimize the adversarial training process. The proposed method is experimentally verified on Case Western Reserve University, Jiangnan University, and laboratory datasets. The experimental results show that the method has good performance in most tasks and has good generalization ability, which provides a feasible solution for the research of bearing fault diagnosis.
format Article
id doaj-art-5b5b6a41518e43c1a6ebfd1ad8709e9f
institution Kabale University
issn 2076-3417
language English
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-5b5b6a41518e43c1a6ebfd1ad8709e9f2025-01-24T13:21:21ZengMDPI AGApplied Sciences2076-34172025-01-0115292110.3390/app15020921MCRCNet: A Bearing Fault Diagnosis Method for Unknown Faults Based on Transfer LearningGuangyuan Xu0Ruifeng Guo1Zhenyu Yin2Feiqing Zhang3Shenyang Institute of Computing Technology, Chinese Academy of Sciences, Shenyang 110168, ChinaShenyang Institute of Computing Technology, Chinese Academy of Sciences, Shenyang 110168, ChinaShenyang Institute of Computing Technology, Chinese Academy of Sciences, Shenyang 110168, ChinaShenyang Institute of Computing Technology, Chinese Academy of Sciences, Shenyang 110168, ChinaBearing fault diagnosis in actual working conditions often faces the problem that unknown type faults cannot be identified, which seriously restricts the practical application of fault diagnosis technology. To solve this problem, this paper proposes a bearing fault diagnosis method based on transfer learning. Firstly, this paper designs a feature extraction network, the Multi-scale Convolution-Convolutional Reconstruction Network (MCRCNet), which incorporates a multi-scale feature extraction module to extract bearing fault features at multiple scales, thereby enhancing the extraction ability of key information. Secondly, this paper designs an improved convolutional reconstruction module AcConv (Adaptive Convolution reconstruction), which highlights key feature information and reduces redundant features by reconstructing the feature map. Furthermore, this paper also modifies the loss function to improve the performance in the case of data imbalance, and introduces the Wasserstein distance to optimize the adversarial training process. The proposed method is experimentally verified on Case Western Reserve University, Jiangnan University, and laboratory datasets. The experimental results show that the method has good performance in most tasks and has good generalization ability, which provides a feasible solution for the research of bearing fault diagnosis.https://www.mdpi.com/2076-3417/15/2/921fault diagnosistransfer learningconvolutional reconstructionloss functionWasserstein distance
spellingShingle Guangyuan Xu
Ruifeng Guo
Zhenyu Yin
Feiqing Zhang
MCRCNet: A Bearing Fault Diagnosis Method for Unknown Faults Based on Transfer Learning
Applied Sciences
fault diagnosis
transfer learning
convolutional reconstruction
loss function
Wasserstein distance
title MCRCNet: A Bearing Fault Diagnosis Method for Unknown Faults Based on Transfer Learning
title_full MCRCNet: A Bearing Fault Diagnosis Method for Unknown Faults Based on Transfer Learning
title_fullStr MCRCNet: A Bearing Fault Diagnosis Method for Unknown Faults Based on Transfer Learning
title_full_unstemmed MCRCNet: A Bearing Fault Diagnosis Method for Unknown Faults Based on Transfer Learning
title_short MCRCNet: A Bearing Fault Diagnosis Method for Unknown Faults Based on Transfer Learning
title_sort mcrcnet a bearing fault diagnosis method for unknown faults based on transfer learning
topic fault diagnosis
transfer learning
convolutional reconstruction
loss function
Wasserstein distance
url https://www.mdpi.com/2076-3417/15/2/921
work_keys_str_mv AT guangyuanxu mcrcnetabearingfaultdiagnosismethodforunknownfaultsbasedontransferlearning
AT ruifengguo mcrcnetabearingfaultdiagnosismethodforunknownfaultsbasedontransferlearning
AT zhenyuyin mcrcnetabearingfaultdiagnosismethodforunknownfaultsbasedontransferlearning
AT feiqingzhang mcrcnetabearingfaultdiagnosismethodforunknownfaultsbasedontransferlearning