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

Fault diagnosis plays an essential role in reducing the maintenance costs ofrotating machinery manufacturing systems. In many real applications of faultdetection and diagnosis, data tend to be imbalanced, meaning that the number ofsamples for some fault classes is much less than the normal data samples. Atthe same time, in an industrial condition, accelerometers encounter high levelsof disruptive signals and the collected samples turn out to be heavily noisy.As a consequence, many traditional Fault Detection and Diagnosis (FDD)frameworks get poor classification performances when dealing with real-worldcircumstances. Three main solutions have been proposed in the literature tocope with this problem: (1) the implementation of generative algorithms toincrease the amount of under-represented input samples, (2) the employment of aclassifier being powerful to learn from imbalanced and noisy data, (3) thedevelopment of an efficient data pre-processing including feature extractionand data augmentation. This paper proposes a hybrid framework which uses thethree aforementioned components to achieve an effective signal-based FDD systemfor imbalanced conditions. Specifically, it first extracts the fault features,using Fourier and wavelet transforms to make full use of the signals. Then, itemploys Wasserstein Generative Adversarial Networks (WGAN) to generatesynthetic samples to populate the rare fault class and enhance the trainingset. Moreover, to achieve a higher performance a novel combination ofConvolutional Long Short-term Memory (CLSTM) and Weighted Extreme LearningMachine (WELM) is proposed. To verify the effectiveness of the developedframework, different datasets settings on different imbalance severities andnoise degrees were used. The comparative results demonstrate that in differentscenarios GAN-CLSTM-ELM outperforms the other state-of-the-art FDD frameworks.

Fault Detection and Diagnosis with Imbalanced and Noisy Data: A Hybrid Framework for Rotating Machinery