MODEL-BASED MONITORING OF DIAMOND TURNING PROCESS USING CROSS-ENTROPY

This paper discusses the model-based monitoring as one of key steps to ward building an in -process diagnostic tool for the supervisory level control in diamond turning. In particular, estimation of surface prof ile from a nonlinear force model and model-based monitoring of tool ch ipping are demonstrated. Classification rule is based on the minimizat ion of information -theoretic measure called the cross entropy. The ex perimental results indicate that monitoring strategy based on the mini mum cross entropy guarantees the consistent and optimum classification results in the presence of varying cutting conditions. In addition, t he cross entropy as a criterion for indicating the dynamic quality of machine-tool is explained.