Fuzzy logic approach for multi-sensor process monitoring in machining

A new strategy for process monitoring in machining is proposed in this paper. The proposed strategy combines a decision-tree approach with the fuzzy set theory to develop a decision-making procedure valid for a reasonable range of cutting conditions. Several sensors are used for monitoring, which include force, vibration, and cutting power sensors. The process and tool conditions considered include three states of tool wear, tool breakage, and machining chatter. The partial least squares method is used to integrate the information from the several sensors. The proposed strategy is verified experimentally using cutting tests performed under a range of cutting conditions. The results indicate an overall 98% success rate of the decision-making system within the ranges of cutting conditions considered in this study.