English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Although data-driven fault diagnosis methods have been widely applied,massive labeled data are required for model training. However, a difficulty ofimplementing this in real industries hinders the application of these methods.Hence, an effective diagnostic approach that can work well in such situation isurgently needed.In this study, a multi-stage semi-supervised improved deepembedded clustering (MS-SSIDEC) method, which combines semi-supervised learningwith improved deep embedded clustering (IDEC), is proposed to jointly explorescarce labeled data and massive unlabeled data. In the first stage, askip-connection-based convolutional auto-encoder (SCCAE) that can automaticallymap the unlabeled data into a low-dimensional feature space is proposed andpre-trained to be a fault feature extractor. In the second stage, asemi-supervised improved deep embedded clustering (SSIDEC) network is proposedfor clustering. It is first initialized with available labeled data and thenused to simultaneously optimize the clustering label assignment and make thefeature space to be more clustering-friendly. To tackle the phenomenon ofoverfitting, virtual adversarial training (VAT) is introduced as aregularization term in this stage. In the third stage, pseudo labels areobtained by the high-quality results of SSIDEC. The labeled dataset can beaugmented by these pseudo-labeled data and then leveraged to train a bearingfault diagnosis model. Two public datasets of vibration data from rollingbearings are used to evaluate the performance of the proposed method.Experimental results indicate that the proposed method achieves a promisingperformance in both semi-supervised and unsupervised fault diagnosis tasks.This method provides a new approach for fault diagnosis under the situation oflimited labeled samples by effectively exploring unsupervised data.

A multi-stage semi-supervised improved deep embedded clustering method  for bearing fault diagnosis under the situation of insufficient labeled  samples