Feature Extraction-Oriented Analysis of Drilling Tool Wear Evolution in Composite Materials

The 4.0 industry has allowed an increase in process quality through Tool Condition Monitoring (TCM) techniques, as they enable the identification of anomalous behaviors caused by tool wear, for instance, by analysing extracted features from real-time signals collected during machining processes. Thus, increasing understanding of the tool wear process is relevant to maintaining process quality and reducing machining downtime and catastrophic failure occurrences. This work analyzes the tool wear of five different hard metal tools through feature-extraction techniques such as Root Mean Square (RMS), Fast Fourier Transform (FFT), Short-Time Fourier Transform (STFT), Hilbert-Huang Transform (HHT), along with other signal metrics like the Root Mean Squared Deviation (RMSD), the Correlation Coefficient Deviation Metric (CCDM), the Rank-based Entropy (RBE), the Fractal Geometry Indicator (FGI), and the Chaos Quantifier (CQ). The features were extracted from Acoustic Emission (AE) signals collected during an experimental drilling process of a Carbon Fiber Reinforced Polymer (CFRP) plate. Although some works have already employed quantitative approaches based on these techniques to gain insight into tool wear characteristics, this research innovates by combining and comparing techniques from time, frequency, and time-frequency domains, and other feature metrics to obtain a fuller comprehension of the signal attributes that help to differentiate tool wear states. It also presents results from features that have only been recently employed in AE feature extraction, such as RBE, FGI, and CQ. Results indicate that the extracted characteristics, when analysed together, allow for a clearer visual differentiation of early-life, middle-life, and worn tool states. Therefore, this work contributes to knowledge acquisition on tool wear in CFRP drilling operations.