Diagnosis and prognosis of slow speed bearing behavior under grease starvation condition
The monitoring and diagnosis of rolling element bearings with acoustic emission and vibration measurements has evolved as one of the much used techniques for condition monitoring and diagnosis of rotating machinery. Furthermore, recent developments indicate the drive toward integration of diagnosis and prognosis algorithms in future integrated machine health management systems. With this in mind, this article is an experimental study of slow speed bearings in a starved lubricated contact. It investigates the influence of grease starvation conditions on detection and monitoring natural defect initiation and propagation using acoustic emission approach. The experiments are also aimed at a comparison of results acquired by acoustic emission and vibration diagnosis on full-scale axial bearing. In addition to this, the article concentrates on the estimation of the remaining useful life for bearings while in operation. To implement this, a multilayer artificial neural network model has been proposed to correlate the selected acoustic emission features with corresponding bearing wear throughout laboratory experiments. Experiments confirm that the obtained results were promising and selecting this appropriate signal processing technique can significantly affect the defect identification.