Non-Stationary Airborne Acoustic Emission Analysis for CNC Drill Wear Classification Using Synchrosqueezed Wavelet Representation and Vision Transformer

Drill bits can be one of the toughest components to maintain when working with CNC systems because of their unique geometries and slow wear of the tools themselves. When measuring wear on drill bits, it’s important to consider the impact tool wear can have on the drill's accuracy, the smoothness of the surfaces created, and the overall efficiency of the machining process. The wear of drill bits is a common occurrence and a normal part of the machining process. This paper seeks to address these challenges by implementing a classification framework for tool wear in CNC drill bits that utilises the Synchrosqueezed Wavelet Transform (SSWT) and the Vision Transformer (ViT). During controlled drilling experiments, Acoustic Emission (AE) signals were captured for each of the following tool conditions: Healthy Tool (HT), Low Wear (LW), Medium Wear (MW), and Severe Wear (SW). In this study, the wear of drill bits was measured and created artificially, with Electrochemical Machining (ECM) for drill bits of sizes 3.0 mm, 3.2 mm, 3.4 mm, 3.6 mm, and 3.8 mm. A system by National Instruments (NI) was used for data acquisition, and LabVIEW was used to acquire a set of data with high resolution and time-frequency representation developed with the SSWT method, which is designed for drill bit wear measurement. These features were captured in the SSWT time-frequency maps, which were used as input to a Vision Transformer that enables efficient capture of global relationships in the time–frequency domain. Unlike traditional convolution-based methods, the proposed transformer-based framework allows for automated multi-domain fusion and feature learning. During experiments with 10-fold cross-validation, the proposed SSWT-ViT framework demonstrated reliable generalisation, strong robustness, and high classification accuracy across varying wear states. Thus, the proposed method is appropriate for intelligent real-time monitoring of CNC drill bit conditions in an industrial setting.