Fuzzy Logic Data Fusion for Condition Monitoring

Abstract

Metal cutting operations constitute a large percentage of manufacturing activity. One of the most important objectives of metal cutting research is to develop techniques that enable optimal utilisation of machine tools, improved production efficiency, high machining accuracy, reduced machine downtime and tooling costs. To realise this objective, it is necessary to develop integrated, self-adjusting manufacturing systems that are capable of machining various parts automatically without operator supervision. Cutting tool condition monitoring is certainly an important monitoring requirement of unattended machining operations. Using traditional tool change strategies, tools are either replaced after a given number of shifts or the operator would change the tool when he thought it to be no longer capable of performing normally. Generally speaking tools are under-utilised because most estimated tool life data are taken conservatively to ensure machining quality. However, it is also possible for a worn tool to be continuously used in the machining process so the parts produced do not meet the required accuracy standard. It is therefore necessary that an intelligent sensing system be devised to monitor the tool wear state during cutting operations so that worn tools can be replaced at the optimum time [1, 2].