A domain generalization network for imbalanced machinery fault diagnosis
Abstract Traditional models for Imbalanced Fault Diagnosis (IFD) face challenges in practical applications due to domain shifts caused by varying working conditions and machinery. Domain Generalization (DG) models provide an advantage over traditional approaches by learning class-discriminative and...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-10-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-75088-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850204279582752768 |
|---|---|
| author | Yu Guo Guangshuo Ju Jundong Zhang |
| author_facet | Yu Guo Guangshuo Ju Jundong Zhang |
| author_sort | Yu Guo |
| collection | DOAJ |
| description | Abstract Traditional models for Imbalanced Fault Diagnosis (IFD) face challenges in practical applications due to domain shifts caused by varying working conditions and machinery. Domain Generalization (DG) models provide an advantage over traditional approaches by learning class-discriminative and domain-invariant feature representations, allowing them to generalize to unseen target data. However, the scarcity of fault samples relative to healthy ones limits their application in real-world industrial scenarios. In this paper, we propose a Domain Mixed-Enhanced Domain Generalization Network (DEMDGN) that enhances IFD performance by utilizing mixup-based data augmentation and domain-based discrepancy metrics to align feature distributions across multiple heterogeneous source domains. By creating domain-invariant features, DEMDGN allows robust fault diagnosis under varying conditions. Extensive experiments on one marine machinery dataset and two bearing datasets demonstrate that the proposed method effectively addresses class imbalance and domain shift problems, achieving superior diagnostic performance. |
| format | Article |
| id | doaj-art-de57028481e849a28bdecf2144c51c7d |
| institution | OA Journals |
| issn | 2045-2322 |
| language | English |
| publishDate | 2024-10-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-de57028481e849a28bdecf2144c51c7d2025-08-20T02:11:18ZengNature PortfolioScientific Reports2045-23222024-10-0114112310.1038/s41598-024-75088-8A domain generalization network for imbalanced machinery fault diagnosisYu Guo0Guangshuo Ju1Jundong Zhang2Marine Engineering College, Dalian Maritime UniversityFaculty of Natural, Mathematical and Engineering Sciences, King’s College LondonMarine Engineering College, Dalian Maritime UniversityAbstract Traditional models for Imbalanced Fault Diagnosis (IFD) face challenges in practical applications due to domain shifts caused by varying working conditions and machinery. Domain Generalization (DG) models provide an advantage over traditional approaches by learning class-discriminative and domain-invariant feature representations, allowing them to generalize to unseen target data. However, the scarcity of fault samples relative to healthy ones limits their application in real-world industrial scenarios. In this paper, we propose a Domain Mixed-Enhanced Domain Generalization Network (DEMDGN) that enhances IFD performance by utilizing mixup-based data augmentation and domain-based discrepancy metrics to align feature distributions across multiple heterogeneous source domains. By creating domain-invariant features, DEMDGN allows robust fault diagnosis under varying conditions. Extensive experiments on one marine machinery dataset and two bearing datasets demonstrate that the proposed method effectively addresses class imbalance and domain shift problems, achieving superior diagnostic performance.https://doi.org/10.1038/s41598-024-75088-8Marine machineryFault diagnosisDomain generalizationData imbalance |
| spellingShingle | Yu Guo Guangshuo Ju Jundong Zhang A domain generalization network for imbalanced machinery fault diagnosis Scientific Reports Marine machinery Fault diagnosis Domain generalization Data imbalance |
| title | A domain generalization network for imbalanced machinery fault diagnosis |
| title_full | A domain generalization network for imbalanced machinery fault diagnosis |
| title_fullStr | A domain generalization network for imbalanced machinery fault diagnosis |
| title_full_unstemmed | A domain generalization network for imbalanced machinery fault diagnosis |
| title_short | A domain generalization network for imbalanced machinery fault diagnosis |
| title_sort | domain generalization network for imbalanced machinery fault diagnosis |
| topic | Marine machinery Fault diagnosis Domain generalization Data imbalance |
| url | https://doi.org/10.1038/s41598-024-75088-8 |
| work_keys_str_mv | AT yuguo adomaingeneralizationnetworkforimbalancedmachineryfaultdiagnosis AT guangshuoju adomaingeneralizationnetworkforimbalancedmachineryfaultdiagnosis AT jundongzhang adomaingeneralizationnetworkforimbalancedmachineryfaultdiagnosis AT yuguo domaingeneralizationnetworkforimbalancedmachineryfaultdiagnosis AT guangshuoju domaingeneralizationnetworkforimbalancedmachineryfaultdiagnosis AT jundongzhang domaingeneralizationnetworkforimbalancedmachineryfaultdiagnosis |