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

Rotating machines like engines, pumps, or turbines are ubiquitous in modernday societies. Their mechanical parts such as electrical engines, rotors, orbearings are the major components and any failure in them may result in theirtotal shutdown. Anomaly detection in such critical systems is very important tomonitor the system's health. As the requirement to obtain a dataset fromrotating machines where all possible faults are explicitly labeled is difficultto satisfy, we propose a method that focuses on the normal behavior of themachine instead. We propose an autoencoder model-based method for conditionmonitoring of rotating machines by using an anomaly detection approach. Themethod learns the characteristics of a rotating machine using the normalvibration signals to model the healthy state of the machine. A threshold-basedapproach is then applied to the reconstruction error of unseen data, thusenabling the detection of unseen anomalies. The proposed method can directlyextract the salient features from raw vibration signals and eliminate the needfor manually engineered features. We demonstrate the effectiveness of theproposed method by employing two rotating machine datasets and the quality ofthe automatically learned features is compared with a set of handcraftedfeatures by training an Isolation Forest model on either of these two sets.Experimental results on two real-world datasets indicate that our proposedsolution gives promising results, achieving an average F1-score of 99.6%.

Autoencoder-based Condition Monitoring and Anomaly Detection Method for Rotating Machines