Adaptability of a tool wear monitoring system under changing cutting conditions

The process of metal cutting is a complex phenomenon that has been researched for many years but the aim of practical cutting tool condition monitoring has yet to be achieved. Previous work by the current authors using two neural networks (to classify acquired data) moderated by an Expert System (based on Taylor's tool life equation) has shown that it is possible to accurately monitor tool wear with a single machine/tool/material/cutting condition combination and to identify any inconsistencies between the predictions of the neural networks and engineering practice. This paper investigates the effects that minor inconsistencies in cutting conditions might have on such a system by determining the 'zone of influence' of this working system by systematically varying the cutting conditions whilst keeping all other variables fixed. The investigation has found that the zone of influence is small but usable, and an approach to the utilisation of the system in a machine shop is suggested.