Bearings are among the most widely used machine elements and are critical to almost all forms of rotating machines. In order to prevent unexpected bearing failure, defects that can occur in bearings should be detected as early as possible. It is widely recognised that Acoustic Emission (AE) is gaining ground as a monitoring method for health diagnosis on rotating machinery. The advantage of AE monitoring over vibration monitoring is that the AE monitoring can detect the growth of subsurface cracks whereas the vibration monitoring can detect defects only when they appear on the surface. The present work involves studying the variation of AE signals obtained from spindle bearing housing of a lathe for various cutting conditions. Simple functional relationships between the parameters were plotted to arrive at possible information on bearing condition. But these simpler methods of analysis did not provide any information about the status of the bearing. Thus, there is a requirement for more sophisticated methods that are capable of integrating information from multiple sensors. Hence, methods like multiple regression analysis and GMDH have been applied for the estimation of AE Counts and AE Energy. From the Experimental data it was observed that as the cutting condition increases there is an increase in the signal level of AE parameters. This is due to increase in load acting on the bearing at higher cutting conditions. Estimates from multiple regression and GMDH were compared and it was observed that, GMDH with regularity criterion gives better results.

This content is only available via PDF.
You do not currently have access to this content.