Classification and detection of cavitation, particle contamination and oil starvation in journal bearing through machine learning approach using acoustic emission signals

Abstract

The ability to classify condition-monitoring data and make a decision can be imparted to a computer through the machine learning approach. In this article, the acoustic emission signals emerging from journal bearings under normal operating conditions and faulty states, namely cavitation, particle contamination and oil starvation, have been classified to develop fault-prediction model using the machine learning approach. Furthermore, an application has been developed that takes acoustic emission data as input and diagnoses the category of faults besides triggering an alarm under faulty states.

Topics & Concepts