Diagnosing Localized and Distributed Bearing Faults by Bearing Noise Signal Using Machine Learning and Kurstogram

Abstract

Bearings are a common component and crucial to most rotating machinery. Their failures are the causes for more than half of the total machine failures, each with the potential to cause extreme damage, injury, and downtime. Therefore, fault detection through condition monitoring has a significant importance. Since the initial cost of standard condition monitoring techniques such as vibration signature analysis is high and has a long payback period, the condition monitoring via audio signal processing is proposed for both localized faults and distributed/ generalized roughness faults in the rolling bearing. It is not appropriate to analyze bearing faults using Fast Fourier Transform (FFT) of the noise signal of bearing since localized faults are Amplitude Modulated (AM) and mixed up with background noises. Localized faults are processed using Kurstogram technique for finding the appropriate filtering band because localized faulty bearings produce impulsive signals