Model-based monitoring of diamond turning process using cross entropy

This paper discusses the model-based monitoring as one of key steps toward building an inprocess diagnostic tool for the supervisory level control in diamond turning. In particular, estimation of surface profile from a nonlinear force model and model-based monitoring of tool chipping are demonstrated. Classification rule is based on the minimization of information-theoretic measure called the cross entropy. The experimental results indicate that monitoring strategy based on the minimum cross entropy guarantees the consistent and optimum classification results in the presence of varying cutting conditions. In addition, the cross entropy as a criterion for indicating the dynamic quality of machine-tool is explained.