A novel Brownian correlation metric prototypical network for rotating machinery fault diagnosis with few and zero shot learners. (October 2022)

• Record Type: Journal Article
• Authors: Yang, Jingli; Wang, Changdong; Wei, Chang'an
• Is Part Of: Advanced engineering informatics. Volume 54(2022)
• Publication Date: 2022-10
• Subjects: Rotating machinery -- Fault diagnosis -- Prototypical network -- Multi-scale mask -- Brownian distance covariance; Computer-aided engineering -- Periodicals; Engineering -- Data processing -- Periodicals; 620.00285
• DOI: 10.1016/j.aei.2022.101815
• Languages: English
• ISSNs: 1474-0346

Abstract

Abstract: Due to the variability of working conditions and the scarcity of fault samples, the existing diagnosis models still have a big gap under the condition of covering more practical application scenarios. Therefore, it is of great significance to study an intelligent diagnosis scheme that takes few samples in the training source domain and zero samples in the test target domain (FST-ZST) into account. A Brownian correlation metric prototypical network (BCMPN) algorithm based on a multi-scale mask preprocessing mechanism is proposed for the above problem. First, this paper constructs a multi-scale mask preprocessing mechanism (MMP) to improve the optimization starting point. Second, the multi-scale feature embedding is realized through the dilation convolution module and the effective light channel attention (ELCA) module. Third, based on the Brownian distance similarity measurement, we learn the feature representation by measuring the difference between the joint feature function and the edge product in the field of diagnosis. Finally, based on the gear data set of the Connecticut university (UConn) and the data collected in the laboratory, it is proved that the BCMPN has better performance in the problem of FST-ZST.