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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

This paper proposes a new technique called cross-empirical wavelet transform (CEWT) to aid a feature learning network for accurate localization of faults in deep groove bearing of an Induction Motor with varying severities under noisy environment. Vibration signals are acquired for different but similar bearings with faults at different locations using a real-life experimental setup. CEWT spectrum shows the correlation in time-frequency space between such a signal for a certain class of bearing fault and that for a normal bearing. Three different locations and four different severities in terms of fault diameter have been chosen as fault classes for the diagnosis. For classification of the bearing faults, the cross-spectra of corresponding fault conditions are fed to a convolutional neural network (CNN) model. Results show that the proposed method can classify these kinds of localized bearing faults with better accuracy, specificity and sensitivity compared to the existing methods. It was also observed that CEWT has the ability to eliminate the effect of random noises present in the recorded signal upto a certain extent. The performance of the scheme is judged on two different datasets to establish its robustness.

Cross Empirical Wavelet Transform Aided Feature Learning Network for Detection of Localized Faults in Deep Groove Bearings