A fault diagnosis method for rolling bearing based on gram matrix and multiscale convolutional neural network

Abstract The safety and reliability of rotating machinery hinge significantly on the proper functioning of rolling bearings. In the last few years, there have been significant advances in the algorithms for intelligent fault diagnosis of bearings. However, the vibration signals collected by machines...

Full description

Saved in:
Bibliographic Details
Main Authors: Xinyan Zhang, Shaobin Cai, Wanchen Cai, Yuchang Mo, Liansuo Wei
Format: Article
Language:English
Published: Nature Portfolio 2024-12-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-024-83315-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850150424993071104
author Xinyan Zhang
Shaobin Cai
Wanchen Cai
Yuchang Mo
Liansuo Wei
author_facet Xinyan Zhang
Shaobin Cai
Wanchen Cai
Yuchang Mo
Liansuo Wei
author_sort Xinyan Zhang
collection DOAJ
description Abstract The safety and reliability of rotating machinery hinge significantly on the proper functioning of rolling bearings. In the last few years, there have been significant advances in the algorithms for intelligent fault diagnosis of bearings. However, the vibration signals collected by machines are inevitably affected by irrelevant noise because of the complex working environments of bearings. So, an end-to-end bearing fault diagnosis method: GMSCNN, a bearing fault diagnosis method based on Gram Matrix (GM) and Multi scale Convolutional Neural Network (MSCNN), is proposed in this paper. In this method, first, GM is used to reduce the noise of the collected vibration signals; Secondly, MSCNN is used for feature extraction, and the characteristics of vibration signals at different frequencies and time scales can be captured by the convolutional kernels of different scales; thirdly, two feature enhancement branches are added, utilizing the undenoised vibration signal as input, to enrich and diversify features while enhancing the model’s expressive and generalization capabilities; Finally, the experimental analysis was conducted on two bearing datasets to indicates that the noise robustness of GMSCNN is strong.
format Article
id doaj-art-382db02e2fcc4338a0ab5f461e87d351
institution OA Journals
issn 2045-2322
language English
publishDate 2024-12-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-382db02e2fcc4338a0ab5f461e87d3512025-08-20T02:26:33ZengNature PortfolioScientific Reports2045-23222024-12-0114111710.1038/s41598-024-83315-5A fault diagnosis method for rolling bearing based on gram matrix and multiscale convolutional neural networkXinyan Zhang0Shaobin Cai1Wanchen Cai2Yuchang Mo3Liansuo Wei4College of Information Engineering, Huzhou UniversityCollege of Information Engineering, Huzhou UniversityCollege of Management, National Taiwan UniversityCollege of Mathematics, Huaqiao UniversityCollege of Information Engineering, SuQian UniversityAbstract The safety and reliability of rotating machinery hinge significantly on the proper functioning of rolling bearings. In the last few years, there have been significant advances in the algorithms for intelligent fault diagnosis of bearings. However, the vibration signals collected by machines are inevitably affected by irrelevant noise because of the complex working environments of bearings. So, an end-to-end bearing fault diagnosis method: GMSCNN, a bearing fault diagnosis method based on Gram Matrix (GM) and Multi scale Convolutional Neural Network (MSCNN), is proposed in this paper. In this method, first, GM is used to reduce the noise of the collected vibration signals; Secondly, MSCNN is used for feature extraction, and the characteristics of vibration signals at different frequencies and time scales can be captured by the convolutional kernels of different scales; thirdly, two feature enhancement branches are added, utilizing the undenoised vibration signal as input, to enrich and diversify features while enhancing the model’s expressive and generalization capabilities; Finally, the experimental analysis was conducted on two bearing datasets to indicates that the noise robustness of GMSCNN is strong.https://doi.org/10.1038/s41598-024-83315-5Gram matrixMultiscale convolutional neural networkDenoisingRolling bearingFault diagnosis
spellingShingle Xinyan Zhang
Shaobin Cai
Wanchen Cai
Yuchang Mo
Liansuo Wei
A fault diagnosis method for rolling bearing based on gram matrix and multiscale convolutional neural network
Scientific Reports
Gram matrix
Multiscale convolutional neural network
Denoising
Rolling bearing
Fault diagnosis
title A fault diagnosis method for rolling bearing based on gram matrix and multiscale convolutional neural network
title_full A fault diagnosis method for rolling bearing based on gram matrix and multiscale convolutional neural network
title_fullStr A fault diagnosis method for rolling bearing based on gram matrix and multiscale convolutional neural network
title_full_unstemmed A fault diagnosis method for rolling bearing based on gram matrix and multiscale convolutional neural network
title_short A fault diagnosis method for rolling bearing based on gram matrix and multiscale convolutional neural network
title_sort fault diagnosis method for rolling bearing based on gram matrix and multiscale convolutional neural network
topic Gram matrix
Multiscale convolutional neural network
Denoising
Rolling bearing
Fault diagnosis
url https://doi.org/10.1038/s41598-024-83315-5
work_keys_str_mv AT xinyanzhang afaultdiagnosismethodforrollingbearingbasedongrammatrixandmultiscaleconvolutionalneuralnetwork
AT shaobincai afaultdiagnosismethodforrollingbearingbasedongrammatrixandmultiscaleconvolutionalneuralnetwork
AT wanchencai afaultdiagnosismethodforrollingbearingbasedongrammatrixandmultiscaleconvolutionalneuralnetwork
AT yuchangmo afaultdiagnosismethodforrollingbearingbasedongrammatrixandmultiscaleconvolutionalneuralnetwork
AT liansuowei afaultdiagnosismethodforrollingbearingbasedongrammatrixandmultiscaleconvolutionalneuralnetwork
AT xinyanzhang faultdiagnosismethodforrollingbearingbasedongrammatrixandmultiscaleconvolutionalneuralnetwork
AT shaobincai faultdiagnosismethodforrollingbearingbasedongrammatrixandmultiscaleconvolutionalneuralnetwork
AT wanchencai faultdiagnosismethodforrollingbearingbasedongrammatrixandmultiscaleconvolutionalneuralnetwork
AT yuchangmo faultdiagnosismethodforrollingbearingbasedongrammatrixandmultiscaleconvolutionalneuralnetwork
AT liansuowei faultdiagnosismethodforrollingbearingbasedongrammatrixandmultiscaleconvolutionalneuralnetwork