Fault detection and diagnosis in low speed rolling element bearings using inductive inference classification

Abstract

An effective procedure for the early detection and objective diagnosis of faults in rolling element bearings is described. The procedure involves the use of an inductive inference theory based classification program called ‘Snob’. The program objectively divides frequency spectra into classes representing different bearing conditions. The estimated description length of each spectrum, which is used for classification, can also be used to detect the early stages of bearing deterioration. The procedure was tested using parametric frequency spectra representing various low speed (60 rpm) rolling element bearing fault conditions. It is shown that the inductive inference theory based spectra classification procedure works well at objectively diagnosing faults in low speed rolling element bearings and allowing early detection of bearing deterioration.