Journal
KNOWLEDGE-BASED SYSTEMS
Volume 251, Issue -, Pages -Publisher
ELSEVIER
DOI: 10.1016/j.knosys.2022.109272
Keywords
Fault diagnosis; Transfer learning; Imbalanced data; ResNet; Meta data
Categories
Funding
- National Natural Science Foundation of China [51875436]
- Guangxi Science and Technology Major Project, China [2019YFF0302204]
- National Key Research and Development Program of China [2021AAA0112]
- Scientific research and technology develop-ment in Liuzhou, China [sklms2022005]
- Open Fund of State Key Laboratory [2020GXNSFAA159081]
- Guangxi Natural Science Foundation, China Program [XZY022020007, XZY022021006]
- Fun-damental Research Funds for the Central Universities, China
Ask authors/readers for more resources
In this paper, a transfer residual network augmented with explicit weight self-assignment strategy based on meta data (TRN-EWM) is proposed for cross-domain fault diagnosis. By extracting depth features and conducting class imbalanced cross-domain transfer, this method effectively addresses the diagnosis difficulties in actual working conditions and achieves high diagnosis accuracy.
Intelligent fault diagnosis methods are significant to mitigate the dependency on expert knowledge and the cost. For the limited faulty data and variational working conditions of real scenarios, cross -domain diagnosis using existing diagnosis models is widely discussed. Especially, methods based on cross-domain transfer learning show great potentiality. However, the class imbalanced data of actual working conditions make it difficult to learn the actual fault feature distribution. To this end, a transfer residual network augmented with explicit weight self-assignment strategy based on meta data(TRN-EWM) is proposed. Specifically, we use a domain-shared ResNet to extract depth features of the data, which effectively avoid gradient disappearance and improve classification performance. Then, to lessen diagnosis difficulties in cross-domain and fully mine the actual feature distribution of the samples, a class imbalanced cross-domain transfer method is carried out. Ultimately, we creatively construct an explicit weight self-assignment strategy based on meta data for sample weight rebalancing, which prevents the dominance of major classes and the overfitting of minor classes. Two transfer experiments are conducted, and average cross-domain diagnosis accuracy of 99.60% is achieved by the proposed method, which shows the effectiveness in bearing fault diagnosis. (c) 2022 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available