Journal
IEEE-ASME TRANSACTIONS ON MECHATRONICS
Volume 27, Issue 1, Pages 430-439Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMECH.2021.3065522
Keywords
Feature extraction; Data models; Transfer learning; Fault diagnosis; Data privacy; Training; Testing; Data privacy; deep learning; fault diagnosis; federated learning; rotating machines
Categories
Funding
- National Natural Science Foundation of China [52005086, 11902202]
- Fundamental Research Funds for the Central Universities [N2005010, N180708009]
- Liaoning Provincial Department of Science and Technology [2020-BS-048, 2019-BS-184]
- Key Laboratory of Vibration, and Control of Aero-Propulsion System Ministry of Education Northeastern University [VCAME201906]
Ask authors/readers for more resources
This article proposes a federated transfer learning method for fault diagnosis, which enhances data privacy by using different models among different users, and addresses the domain shift and data privacy issues through federated initialization, federated communication, and prediction consistency scheme.
Intelligent data-driven machinery fault diagnosis methods have been popularly developed in the past years. While fairly high diagnosis accuracies have been obtained, large amounts of labeled training data are mostly required, which are difficult to collect in practice. The promising collaborative model training solution with multiple users poses high demands on data privacy due to conflict of interests. Furthermore, in the real industries, the data from different users can be usually collected from different machine operating conditions. The domain shift phenomenon and data privacy concern make the joint model training scheme quite challenging. To address this issue, a federated transfer learning method for fault diagnosis is proposed in this article. Different models can be used by different users to enhance data privacy. A federal initialization stage is introduced to keep similar data structures in distributed feature extractions, and a federated communication stage is further implemented using deep adversarial learning. A prediction consistency scheme is also adopted to increase model robustness. Experiments on two real-world datasets suggest the proposed federated transfer learning method is promising for real industrial applications.
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