Vibration-based Feature Analysis and Intelligent Tool Wear Prediction for CNC Machines: An Industry 4.0 Approach

This study comprises two main parts. The first part analyzes vibration data from turning operations performed at three different depths of cut to identify the most effective features for distinguishing between the resulting signals. Using a machine and deep learning-based classification approach, a thorough feature importance analysis was conducted to identify the most influential signal characteristics. Building on these findings, the second part of the study focuses on utilizing the most important feature identified in the first phase for near real-time tool wear monitoring. By tracking changes in this specific feature during machining, the system can detect wear progression through vibration signals, enabling more accurate and timely intervention. This two-step approach not only enhances the understanding of how vibrational features vary with cutting conditions but also offers a practical method for near real-time tool condition monitoring. It is important to note that the most influential feature is initially identified based on its sensitivity to controlled changes in cutting conditions and is subsequently tested as a tool wear indicator in the second part. Furthermore, this study demonstrates an offline trend analysis on recorded data rather than a deployed online monitoring system.