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

Preventive maintenance of modern electric rotating machinery (RM) is criticalfor ensuring reliable operation, preventing unpredicted breakdowns and avoidingcostly repairs. Recently many studies investigated machine learning monitoringmethods especially based on Deep Learning networks focusing mostly on detectingbearing faults; however, none of them addressed bearing fault severityclassification for early fault diagnosis with high enough accuracy. 1DConvolutional Neural Networks (CNNs) have indeed achieved good performance fordetecting RM bearing faults from raw vibration and current signals but did notclassify fault severity. Furthermore, recent studies have demonstrated thelimitation in terms of learning capability of conventional CNNs attributed tothe basic underlying linear neuron model. Recently, Operational Neural Networks(ONNs) were proposed to enhance the learning capability of CNN by introducingnon-linear neuron models and further heterogeneity in the networkconfiguration. In this study, we propose 1D Self-organized ONNs (Self-ONNs)with generative neurons for bearing fault severity classification and providingcontinuous condition monitoring. Experimental results over the benchmarkNSF/IMS bearing vibration dataset using both x- and y-axis vibration signalsfor inner race and rolling element faults demonstrate that the proposed 1DSelf-ONNs achieve significant performance gap against the state-of-the-art (1DCNNs) with similar computational complexity.

Early Bearing Fault Diagnosis of Rotating Machinery by 1D Self-Organized Operational Neural Networks