Condition monitoring of carbide and non-carbide coated tool insert using decision tree and random tree – A statistical learning

Abstract

Traditional trial and error methods of tool condition monitoring are time-consuming and not reliable, hence an efficient method for tool condition monitoring is necessary. The following work deals to establish a simple and efficient automatic method to detect and monitor the tool condition. The work includes both the carbide and non-carbide tools used for machining a cylindrical mild steel component. The turning process is carried out under various conditions. Different combinations of speed, feed, and depth of cut are used for turning. A tri-axial accelerometer was used for capturing the vibration signals, which are further used for condition monitoring purposes. A statistical framework has been applied for monitoring the tool insert health condition. The raw vibration signals were processed for extracting the statistical properties. The extracted features were used for applying machine learning. Two machine learning classifiers namely the decision tree and the random tree were used for the classification process. The results were discussed and compared in this study.