FCDG: A Central Dogma-Inspired Approach for Cross-Domain Fault Diagnosis
- 23 December 2024
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (3) , 5192-5199
Abstract
Although deep learning-based detection technology has significantly improved the efficiency and accuracy of fault diagnosis, its development is limited by the differences in sample distribution caused by operating condition changes. To address the challenge, a feature codon intelligent bearing fault diagnosis method FCDG with wide-area generalization capability is proposed. FCDG introduces the concepts of feature codons and feature anticodons and proposes a new fault diagnosis method based on non-probabilistic modeling of feature codons. That is, feature anticodons and feature codons are extracted from the source domain and target domain, respectively, and the feature anticodons and feature codons are matched and translated into the corresponding fault category. The paradigm effectively integrates the distribution of feature codons in the source domain to infer the class affiliation of samples in the target domain and expands the theoretical framework of domain generalization fault diagnosis by introducing the matching of feature codons and feature anticodons. The classification method of feature codon matching replaces the traditional classification, avoiding the influence of classification boundary failure caused by domain shift. A large number of experimental results demonstrate the effectiveness of the proposed FCDG under various variable operating conditions.Keywords
Funding Information
- Industrialization Cultivation Project of the Department of Education of Jilin Province (JJKH20240149CY)
This publication has 36 references indexed in Scilit:
- Like draws to like: A Multi-granularity Ball-Intra Fusion approach for fault diagnosis models to resists misleading by noisy labelsAdvanced Engineering Informatics, 2024
- Multi-source information fusion: Progress and futureChinese Journal of Aeronautics, 2023
- Empowering intelligent manufacturing with edge computing: A portable diagnosis and distance localization approach for bearing faultsAdvanced Engineering Informatics, 2023
- Single domain generalizable and physically interpretable bearing fault diagnosis for unseen working conditionsExpert Systems with Applications, 2023
- LiConvFormer: A lightweight fault diagnosis framework using separable multiscale convolution and broadcast self-attentionExpert Systems with Applications, 2023
- Deep discriminative causal domain generalizationInformation Sciences, 2023
- Detection of wire breaks in prestressed concrete bridges by Acoustic Emission analysisDevelopments in the Built Environment, 2023
- Domain adaptation network base on contrastive learning for bearings fault diagnosis under variable working conditionsExpert Systems with Applications, 2022
- Deep transfer multi-wavelet auto-encoder for intelligent fault diagnosis of gearbox with few target training samplesKnowledge-Based Systems, 2020
- Deep CORAL: Correlation Alignment for Deep Domain Adaptation2016