2022
DOI: 10.1109/tmech.2022.3177174
|View full text |Cite
|
Sign up to set email alerts
|

Novel Joint Transfer Network for Unsupervised Bearing Fault Diagnosis From Simulation Domain to Experimental Domain

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
5

Citation Types

0
73
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
7
3

Relationship

0
10

Authors

Journals

citations
Cited by 211 publications
(73 citation statements)
references
References 37 publications
0
73
0
Order By: Relevance
“…Roller bearing condition monitoring using DNN with two branches—one branch accounting for feature engineering (pattern recognition and extraction) and the other branch taking care of the final fault classification [ 15 ]—was performed by Guo et al The convolutional long short-term memory (C-LSTM) approach was employed by Zhao et al to monitor the condition of a tool [ 16 ]. Xiao et al performed a study into the adoption of a novel joint transfer network for unsupervised bearing fault diagnosis from the simulation domain to the experimental domain [ 17 ]. Cai et al examined a data-driven methodology for fault diagnosis in a permanent magnet synchronous motor using Bayesian networks [ 18 ].…”
Section: Introductionmentioning
confidence: 99%
“…Roller bearing condition monitoring using DNN with two branches—one branch accounting for feature engineering (pattern recognition and extraction) and the other branch taking care of the final fault classification [ 15 ]—was performed by Guo et al The convolutional long short-term memory (C-LSTM) approach was employed by Zhao et al to monitor the condition of a tool [ 16 ]. Xiao et al performed a study into the adoption of a novel joint transfer network for unsupervised bearing fault diagnosis from the simulation domain to the experimental domain [ 17 ]. Cai et al examined a data-driven methodology for fault diagnosis in a permanent magnet synchronous motor using Bayesian networks [ 18 ].…”
Section: Introductionmentioning
confidence: 99%
“…This approach is appropriate for modern electrical machines, especially under nonstationary conditions [10]. Xiao et al firstly took cross-domain case from simulation domain to experimental domain into consideration, and developed promising joint adaptation network, which contributes to unsupervised transfer fault diagnosis [11]. Wang et al exploited a novel convolutional deep belief network, which is applicable to fault diagnosis [12].…”
Section: Introductionmentioning
confidence: 99%
“…The transfer learning (TL) 11 , including domain adaptation 12 and deep transfer learning 13 can leverage present knowledge from the source domain to achieve target domain tasks 14 . And domain adaptation is the critical technology to minimise the distribution discrepancy between the source and target domain by exploring domain-invariant features to address the domain shift problem.…”
Section: Introductionmentioning
confidence: 99%