Research on Bearing Fault Diagnosis Based on GMNR and ResNet-CABA-MAGRU

Focusing on the problem that it is difficult to maintain a high diagnostic accuracy rate, short running time, and robust generalization capability in the face of a strong-noise environment in rolling bearing fault diagnosis, a bearing fault diagnosis model (GMNR-CABA-MAGRU) founded upon a new attent...

Full description

Saved in:
Bibliographic Details
Main Authors: Longfa Chen, Na Meng, Wenzheng Sun, Sen Yang, Shuo Tian, Yuguo Li
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/11/3458
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849721833839919104
author Longfa Chen
Na Meng
Wenzheng Sun
Sen Yang
Shuo Tian
Yuguo Li
author_facet Longfa Chen
Na Meng
Wenzheng Sun
Sen Yang
Shuo Tian
Yuguo Li
author_sort Longfa Chen
collection DOAJ
description Focusing on the problem that it is difficult to maintain a high diagnostic accuracy rate, short running time, and robust generalization capability in the face of a strong-noise environment in rolling bearing fault diagnosis, a bearing fault diagnosis model (GMNR-CABA-MAGRU) founded upon a new attention-mechanism-improved residual network (ResNet-CABA) and a Gram denoising module (GMNR) is proposed, and the CWRU bearing dataset is used for verification. Under the 0-load condition in a noise-free environment, the diagnostic accuracy of this model reached 99.66%, and the running time was only 52.74 s. Then, a bearing dataset with added Gaussian noise from −4 db to 4 db was verified, and this model was still able to maintain a diagnostic accuracy of 90.32% under the strong-noise environment of −4 db SNR. And migration experiments were carried out under different load conditions, and this model was also able to maintain a very high accuracy rate. Moreover, in all the above experiments, this model performed better than various comparative models. The developed framework demonstrated superior diagnostic precision, enhanced robustness, and improved generalization capability.
format Article
id doaj-art-c13611f08bf14e888fbc91b3f3fd6b62
institution DOAJ
issn 1424-8220
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-c13611f08bf14e888fbc91b3f3fd6b622025-08-20T03:11:32ZengMDPI AGSensors1424-82202025-05-012511345810.3390/s25113458Research on Bearing Fault Diagnosis Based on GMNR and ResNet-CABA-MAGRULongfa Chen0Na Meng1Wenzheng Sun2Sen Yang3Shuo Tian4Yuguo Li5School of Intelligent Equipment, Shandong University of Science and Technology, Tai’an 271019, ChinaSchool of Intelligent Equipment, Shandong University of Science and Technology, Tai’an 271019, ChinaSchool of Intelligent Equipment, Shandong University of Science and Technology, Tai’an 271019, ChinaSchool of Intelligent Equipment, Shandong University of Science and Technology, Tai’an 271019, ChinaSchool of Intelligent Equipment, Shandong University of Science and Technology, Tai’an 271019, ChinaSchool of Intelligent Equipment, Shandong University of Science and Technology, Tai’an 271019, ChinaFocusing on the problem that it is difficult to maintain a high diagnostic accuracy rate, short running time, and robust generalization capability in the face of a strong-noise environment in rolling bearing fault diagnosis, a bearing fault diagnosis model (GMNR-CABA-MAGRU) founded upon a new attention-mechanism-improved residual network (ResNet-CABA) and a Gram denoising module (GMNR) is proposed, and the CWRU bearing dataset is used for verification. Under the 0-load condition in a noise-free environment, the diagnostic accuracy of this model reached 99.66%, and the running time was only 52.74 s. Then, a bearing dataset with added Gaussian noise from −4 db to 4 db was verified, and this model was still able to maintain a diagnostic accuracy of 90.32% under the strong-noise environment of −4 db SNR. And migration experiments were carried out under different load conditions, and this model was also able to maintain a very high accuracy rate. Moreover, in all the above experiments, this model performed better than various comparative models. The developed framework demonstrated superior diagnostic precision, enhanced robustness, and improved generalization capability.https://www.mdpi.com/1424-8220/25/11/3458deep learningfault diagnosisattention mechanismGram denoising module (GMNR)
spellingShingle Longfa Chen
Na Meng
Wenzheng Sun
Sen Yang
Shuo Tian
Yuguo Li
Research on Bearing Fault Diagnosis Based on GMNR and ResNet-CABA-MAGRU
Sensors
deep learning
fault diagnosis
attention mechanism
Gram denoising module (GMNR)
title Research on Bearing Fault Diagnosis Based on GMNR and ResNet-CABA-MAGRU
title_full Research on Bearing Fault Diagnosis Based on GMNR and ResNet-CABA-MAGRU
title_fullStr Research on Bearing Fault Diagnosis Based on GMNR and ResNet-CABA-MAGRU
title_full_unstemmed Research on Bearing Fault Diagnosis Based on GMNR and ResNet-CABA-MAGRU
title_short Research on Bearing Fault Diagnosis Based on GMNR and ResNet-CABA-MAGRU
title_sort research on bearing fault diagnosis based on gmnr and resnet caba magru
topic deep learning
fault diagnosis
attention mechanism
Gram denoising module (GMNR)
url https://www.mdpi.com/1424-8220/25/11/3458
work_keys_str_mv AT longfachen researchonbearingfaultdiagnosisbasedongmnrandresnetcabamagru
AT nameng researchonbearingfaultdiagnosisbasedongmnrandresnetcabamagru
AT wenzhengsun researchonbearingfaultdiagnosisbasedongmnrandresnetcabamagru
AT senyang researchonbearingfaultdiagnosisbasedongmnrandresnetcabamagru
AT shuotian researchonbearingfaultdiagnosisbasedongmnrandresnetcabamagru
AT yuguoli researchonbearingfaultdiagnosisbasedongmnrandresnetcabamagru