Bearing fault classification based on Minimum Volume Ellipsoid feature extraction

This article presents a novel fault classification and diagnosis technique for bearings based on a Minimum Volume Ellipsoid (MVE) method for feature extraction. Data from two accelerometers located at two different sites of the test bed are combined to create a two dimensional representation and the feature extraction stage condenses that information using an ellipsoid description. The proposed features feed a simple non-linear classifier which separates almost perfectly between normal and faulty conditions, with also very high diagnostic accuracy between the faulty classes. The obtained results suggest that this novel representation can be used within a condition monitoring system.