Fault Diagnosis of Single Point Cutting Tool through Vibration Signal 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 increases machining quality as well as surface finish of machined components, reduces wear and tear of the machine and its components and hence increases machining efficiency. Vibration analysis of mechanical systems can be used to identify the tool condition to distinguish good and worn tool. This paper uses the vibration signals acquired using the accelerometer in a lathe with fresh and simulated worn tool for the fault diagnosis using machine learning techniques for online tool condition monitoring. Statistical features are obtained from vibration signal. Significant features were chosen from J48 algorithm, which is used as a classifier too. The significant features were given as input for the classifier and the accuracies of classification were examined. Results of (J48) algorithm were used to classify the condition of tool, also found its accuracy as of 89.38%.