Condition Monitoring of Single Point Cutting Tool through Vibration Signals using Decision Tree Algorithm

Tool condition monitoring in machining plays a crucial role in modern manufacturing systems, finding tool wear state in early with the help of monitoring system will reduce downtime and excessive power drawing while machining. It also increases machining quality as well as surface finish of machined components. Vibration analysis of mechanical systems can be used to identify the tool condition to distinguish good and worn tool. This paper deals with the vibration signals acquired using the accelerometer in a lathe with fresh and worn tool for the fault diagnosis through machine learning approach for online tool condition monitoring. The statistical features were extracted from the vibration signals. Significantly important features were selected using J48 decision tree algorithm and it is used as a classifier too. The selected features were given as inputs for the classifier and their classification accuracies were compared. Results of (J48) algorithm were used to learn and classify the condition of tool and also found its accuracy as of 95%. Hence, the results of the decision tree model can be practically used for diagnosing the condition of the tool wear.