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/

Zendy Plus

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

Zendy Tools

Zendy Open

Motor bearing fault detection (MBFD) is critical for maintaining thereliability and operational efficiency of industrial machinery. Early detectionof bearing faults can prevent system failures, reduce operational downtime, andlower maintenance costs. In this paper, we propose a robust deep learning-basedsystem for MBFD that incorporates multiple training strategies, includingsupervised, semi-supervised, and unsupervised learning. To enhance thedetection performance, we introduce a novel double loss function. Our approachis evaluated using benchmark datasets from the American Society for MechanicalFailure Prevention Technology (MFPT), Case Western Reserve University BearingCenter (CWRU), and Paderborn University's Condition Monitoring of BearingDamage in Electromechanical Drive Systems (PU). Results demonstrate that deeplearning models outperform traditional machine learning techniques, with ournovel system achieving superior accuracy across all datasets. These findingshighlight the potential of our approach for practical MBFD applications.

A Robust Deep Learning System for Motor Bearing Fault Detection: Leveraging Multiple Learning Strategies and a Novel Double Loss Function