Hilbert Marginal Spectrum for Failure Mode Diagnosis of Rotating Machines

Mechanical bearings are a core component for rotating machines. These critical elements suffer from degradation which can be gradual or abrupt which typically results in premature failure modes occurring. In recent years, bearing faults have been reported to be the cause of up to 75% of low voltage motor/generator breakdowns and up to 41% of all rotating machine failures. Abrupt equipment failure in many critical applications such as aircraft, automotive and energy converters is often extremely costly, untimely and catastrophic, as well presenting serious health and safety implications. The paper investigates a unique approach for bearing fault mode diagnosis through incorporating novel Hilbert Marginal Spectrum derived features that are utilised in Machine Learning (ML) classification algorithms, specifically that of Support Vector Machines (SVM) and k-Nearest Neighbour (k-NN). The techniques and methods proposed are tested and validated on real vibration signals achieving 93.8% classification accuracy.