Fault detection and diagnosis in low speed rolling element bearings Part II: The use of nearest neighbour classification

Abstract

An effective procedure for automatic fault diagnosis in low speed (⩽100 RPM) rolling element bearings is described. The procedure involves the calculation of a statistical distance measure between vibration signals. The distance measure is then automatically used to distinguish between different fault conditions. A new trending index, based on the statistical distance measure, which may be used for fault detection, is also described.