An evaluation of the potential offered by a relevance vector classifier in machinery fault diagnosis

The increasing complexity of modern machinery systems demands an effective fault diagnosis strategy with low cost, high efficiency and reliability. This paper reports work which attempts to explore the potential offered by a Relevance Vector Machine (RVM) in machinery fault diagnosis. This work starts with a full investigation into the demands of modern fault diagnosis and the characteristics of the RVM method, and then provides an insight into the model of a relevance vector machine for classification. Finally, a case study of the multi-class classification of bearing faults further demonstrates the application potential of the method. Besides, it is proved that the proposed method is most suitable for real-time applications due to its high computational speed, low memory requirement and high accuracy.