Journal
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
Volume 67, Issue 8, Pages 6785-6794Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIE.2019.2935987
Keywords
Sensors; Training; Testing; Machinery; Fault diagnosis; Task analysis; Vibrations; Deep learning; fault diagnosis; rotating machines; transfer learning
Categories
Funding
- Fundamental Research Funds for the Central Universities [N170503012, N170308028, N180708009, N180703018]
- National Natural Science Foundation of China [61871107]
Ask authors/readers for more resources
In the recent years, data-driven machinery fault diagnostic methods have been successfully developed, and the tasks where the training and testing data are from the same distribution have been well addressed. However, due to sensor malfunctions, the training and testing data can be collected at different places of machines, resulting in the feature space with significant distribution discrepancy. This challenging issue has received less attention in the current literature, and the existing approaches generally fail in such scenarios. This article proposes a domain adaptation method for machinery fault diagnostics based on deep learning. Adversarial training is introduced for marginal domain fusion, and unsupervised parallel data are explored to achieve conditional distribution alignments with respect to different machine health conditions. Experiments on two rotating machinery datasets are carried out for validations. The results suggest the proposed method is promising to address the fault diagnostic tasks with data from different places of machines, further enhancing applicability of data-driven methods in real industries.
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