Research on bearing fault feature transfer diagnosis based on balanced distribution adaptation under feature fusion

In practical industrial applications, the operating conditions of bearings frequently change, posing significant challenges for reliable fault diagnosis. Traditional machine learning methods, which rely on the assumption of independent and identically distributed samples, often experience a signific...

Full description

Saved in:
Bibliographic Details
Main Authors: Lulu Wang, Yongqi Li, Chunyi Zhang, Ralph Gerard Sangalang
Format: Article
Language:English
Published: SAGE Publishing 2025-06-01
Series:Advances in Mechanical Engineering
Online Access:https://doi.org/10.1177/16878132251348366
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849422040360026112
author Lulu Wang
Yongqi Li
Chunyi Zhang
Ralph Gerard Sangalang
author_facet Lulu Wang
Yongqi Li
Chunyi Zhang
Ralph Gerard Sangalang
author_sort Lulu Wang
collection DOAJ
description In practical industrial applications, the operating conditions of bearings frequently change, posing significant challenges for reliable fault diagnosis. Traditional machine learning methods, which rely on the assumption of independent and identically distributed samples, often experience a significant decline in diagnostic accuracy under such variable conditions. To address this issue, this paper proposes a bearing fault transfer diagnosis method that combines the Balanced Distribution Adaptation (BDA) algorithm with a Back Propagation neural network (BPNN) classification algorithm. Firstly, time-domain features of the bearing signals are extracted to comprehensively reflect the operational state of the bearings. Principal Component Analysis (PCA) is then utilized to reduce the dimensionality of the high-dimensional features, preserving the main information while reducing computational complexity. Subsequently, the BDA algorithm is employed to align the features of the source and target domains, balancing distribution differences and achieving effective feature space transfer. Finally, the BP neural network classification algorithm is used to classify the transferred features, thereby diagnosing bearing faults. Experimental results demonstrate that, compared to traditional fault diagnosis methods, the proposed approach achieves higher diagnostic accuracy and robustness under different working conditions. This method not only addresses the challenges posed by changing operating conditions but also holds significant practical value, providing a robust and efficient solution for real-world industrial applications such as predictive maintenance and condition monitoring in critical engineering systems.
format Article
id doaj-art-b30aa63c2f954682bcca7f895d71655c
institution Kabale University
issn 1687-8140
language English
publishDate 2025-06-01
publisher SAGE Publishing
record_format Article
series Advances in Mechanical Engineering
spelling doaj-art-b30aa63c2f954682bcca7f895d71655c2025-08-20T03:31:15ZengSAGE PublishingAdvances in Mechanical Engineering1687-81402025-06-011710.1177/16878132251348366Research on bearing fault feature transfer diagnosis based on balanced distribution adaptation under feature fusionLulu Wang0Yongqi Li1Chunyi Zhang2Ralph Gerard Sangalang3Guangdong University of Science and Technology, Dongguan, ChinaChina Copper Southeast Copper Co., Ltd, Ningde, Fujian, ChinaGuangdong University of Science and Technology, Dongguan, ChinaBatangas State University, PhilippinesIn practical industrial applications, the operating conditions of bearings frequently change, posing significant challenges for reliable fault diagnosis. Traditional machine learning methods, which rely on the assumption of independent and identically distributed samples, often experience a significant decline in diagnostic accuracy under such variable conditions. To address this issue, this paper proposes a bearing fault transfer diagnosis method that combines the Balanced Distribution Adaptation (BDA) algorithm with a Back Propagation neural network (BPNN) classification algorithm. Firstly, time-domain features of the bearing signals are extracted to comprehensively reflect the operational state of the bearings. Principal Component Analysis (PCA) is then utilized to reduce the dimensionality of the high-dimensional features, preserving the main information while reducing computational complexity. Subsequently, the BDA algorithm is employed to align the features of the source and target domains, balancing distribution differences and achieving effective feature space transfer. Finally, the BP neural network classification algorithm is used to classify the transferred features, thereby diagnosing bearing faults. Experimental results demonstrate that, compared to traditional fault diagnosis methods, the proposed approach achieves higher diagnostic accuracy and robustness under different working conditions. This method not only addresses the challenges posed by changing operating conditions but also holds significant practical value, providing a robust and efficient solution for real-world industrial applications such as predictive maintenance and condition monitoring in critical engineering systems.https://doi.org/10.1177/16878132251348366
spellingShingle Lulu Wang
Yongqi Li
Chunyi Zhang
Ralph Gerard Sangalang
Research on bearing fault feature transfer diagnosis based on balanced distribution adaptation under feature fusion
Advances in Mechanical Engineering
title Research on bearing fault feature transfer diagnosis based on balanced distribution adaptation under feature fusion
title_full Research on bearing fault feature transfer diagnosis based on balanced distribution adaptation under feature fusion
title_fullStr Research on bearing fault feature transfer diagnosis based on balanced distribution adaptation under feature fusion
title_full_unstemmed Research on bearing fault feature transfer diagnosis based on balanced distribution adaptation under feature fusion
title_short Research on bearing fault feature transfer diagnosis based on balanced distribution adaptation under feature fusion
title_sort research on bearing fault feature transfer diagnosis based on balanced distribution adaptation under feature fusion
url https://doi.org/10.1177/16878132251348366
work_keys_str_mv AT luluwang researchonbearingfaultfeaturetransferdiagnosisbasedonbalanceddistributionadaptationunderfeaturefusion
AT yongqili researchonbearingfaultfeaturetransferdiagnosisbasedonbalanceddistributionadaptationunderfeaturefusion
AT chunyizhang researchonbearingfaultfeaturetransferdiagnosisbasedonbalanceddistributionadaptationunderfeaturefusion
AT ralphgerardsangalang researchonbearingfaultfeaturetransferdiagnosisbasedonbalanceddistributionadaptationunderfeaturefusion