STATE-OF-THE-ART IN METHODS APPLIED TO TOOL CONDITION MONITORING (TCM) IN UNMANNED MACHINING OPERATIONS: A REVIEW

The main scope of this paper is to present a summary of the monitoring methods, signal analysis and diagnostic techniques for tool wear and failure monitoring that have been proposed, tested or reported in literature up today. Initially, the necessity for planned tool condition monitoring in modern manufacturing is being discussed. Then, there is a discussion about the difference between soft and hard faults and the reason that they are used for prediction and diagnosis respectively. The paper, then, lists the basic parameters that are correlated with each type of fault. Both direct methods, such as computer vision, and indirect methods, such as vibration, that have been used to monitor the aforementioned parameters, are presented. Moreover, the paper summarizes the signal processing techniques that have been applied to each monitoring method, including e.g. statistical parameters and Wavelet Transform. Following this, a number of diagnostic tools, which have been developed for diagnosis of tool condition, are presented. The paper concludes that the area of condition monitoring and fault diagnosis is of increasing importance, stressing the fact that only few implementations have been achieved, as a consequence that all available techniques present drawbacks and limitations.