… Second, multiple bootstrap samples are generated to … ensemble to get the optimized fault
diagnosis result, a correlation-… in machinery fault diagnosis, which are the focus of this paper. …

… fault diagnosis of rotating machinery. Specifically, the overall flowchart of the intelligent …
extremely-limited sample condition as using no more than 10 labeled training samples each class…

… In order to improve the safety of equipment operation and avoid disasters and accidents, it
… machinery, and fault diagnosis is a key link in the health management of rotating machinery. …

… health, which can effectively overcome the effects of noise and condition variance issues
in sampling signals. The effectiveness and the merits of the proposed TFM feature are …

… is proposed for the gearbox fault diagnosis with limited labeled samples. The GSSL is used
to annotate the unlabeled samples to increase the labeled samples for the RF construction, …

… fault diagnosis method based on attention residual prototypical network (ARPN) under the
limited sample… implicit classification information under fewer samples, frequency slice wavelet …

… problem [12]. In this case, deep learning models are … -sample fault diagnosis methods cannot
only realize the accurate identification of equipment health status under limited training data…

… domain labeled sample scarcity to the few-shot diagnosis problem and achieved promising
… A novel FD-DAML is proposed in this study for few-shot cross- domain fault diagnosis with …

… During experiments, we use different ratios (100%, 60%, and 30%) of training samples to
train each fault diagnosis algorithm and test them on the test set. The results are shown in …

… In this paper, a MAMN is designed for the problem of fault diagnosis with few samples across
different working conditions and different equipment datasets. The approach of this paper …