Acoustic emission (AE) signals are thought to contain crucial information for identifying defects and monitoring processes. It is crucial to have a comprehensive understanding of how AE signal parameters behave under different experimental conditions. However, based on current research, there appears to be a lack of knowledge on the impact of machining parameters, especially in milling operations, where complex chip formation patterns, interaction effects, and directional pressures and forces are present. To bridge this informational void, analyzing how various cutting conditions impact the AE signal characteristics derived from milling operations is crucial. This research predominantly focuses on the impact of cutting conditions, material attributes, insert coatings, and nose radius on AE signal attributes in the time domain. The proposed innovative method suggests segmenting acquired AE signals correlated with the cutting tool's trajectory through the material into three distinct phases: entry, active cutting, and exit, each marked by a particular signal timeframe for effective signal processing and characteristic derivation. Furthermore, advanced signal processing techniques and statistical analysis are utilized to determine which AE parameters are sensitive to changes in cutting parameters. This research identifies cutting speed and feed rate as the primary variables affecting AE signal characteristics. The study's outcomes can enhance sophisticated classifications and AI techniques for monitoring machining operations.
