Intelligent identification of turning process based on pattern recognition of cutting states

A method has been developed to monitor and identify the cutting states for CNC turning by utilizing the dynamic cutting forces based on proposed pattern recognition technique. The method proposed introduces three parameters, which are calculated and obtained by taking the ratio of the average variances of the dynamic cutting forces, to classify the cutting states of continuous chip formation, broken chip formation, and chatter. The broken chip formation is required for the stable and reliable machining process. The algorithm was developed to calculate the values of three parameters during the process in order to obtain the reference feature spaces and determine the proper threshold values for classification of the cutting states. It is proved by series of cutting experiments that the states of cutting are well identified by the method developed and proposed here even though the cutting conditions are changed. The algorithm is proposed to obtain the broken chips by changing the cutting conditions during the process.