Citation :

Abubacker KM, Amuthakkannan Rajakannu, Jacob Wekalao, Maamar Al Tobi, S Vishnupriyan, "Non-Stationary Airborne Acoustic Emission Analysis for CNC Drill Wear Classification Using Synchrosqueezed Wavelet Representation and Vision Transformer," International Journal of Engineering Trends and Technology (IJETT), vol. 74, no. 6, pp. 231-243, 2026. Crossref, https://doi.org/10.14445/22315381/IJETT-V74I6P117

Abstract

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 is 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 utilizes 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 generalization, 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.

Keywords

CNC Tool Wear, Synchrosqueezed Wavelet Transform, Acoustic Emission, Vision Transformer.

References

[1] Mu Xiqing, and Xu Chuangwen, “Tool Wear Monitoring of Acoustic Emission Signals from Milling Processes,” 2009 First International Workshop on Education Technology and Computer Science, Wuhan, China, pp. 431-435, 2009.
[CrossRef] [Google Scholar] [Publisher Link]

[2] K. Vijayalakshmi, “Reliability Improvement in a Component-Based Software Development Environment,” International Journal of Information Systems and Change Management, vol. 5, no. 2, pp.  99-123, 2011.
[CrossRef] [Google Scholar] [Publisher Link]

[3] Mohsina Kamarudeen, and K. Vijayalakshmi, “A Machine Learning-Based Financial Management Mobile Application to Enhance College Students' Financial Literacy,” Proceedings of International Conference on Research in Education and Science, Cappadocia, Turkey, pp. 1237-1253, 2023.
[Google Scholar] [Publisher Link]

[4] Rajeev D et al., “Cutting-Edge Tool Wear Monitoring in AISI4140 Steel Hard Turning using Least-Square Support Vector Machine,” Journal of the Chinese Institute of Engineers, vol. 47, no. 5, pp. 492-507, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[5] Muhammad Farooq Siddique et al., “Advanced Fault Diagnosis in Milling Cutting Tools using Vision Transformers with Semi-Supervised Learning and Uncertainty Quantification,” Scientific Reports, vol. 15, pp. 1-23, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[6] Paweł Twardowski et al., “Identification of Tool Wear using Acoustic Emission Signal and Machine Learning Methods,” Precision Engineering, vol. 72, pp. 738-744, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[7] Sohan Nagaraj, and Nancy Diaz-Elsayed, “Tool Condition Monitoring in the Milling of Low- to High-Yield-Strength Materials,” Machines, vol. 13, no. 4, pp. 1-25, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[8] Luís Henrique Andrade Maia et al., “Enhancing Machining Efficiency: Real-Time Monitoring of Tool Wear with Acoustic Emission and STFT Techniques,” Lubricants, vol. 12, no. 11, pp. 1-23, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[9] Yingjie Liu et al., “Acoustic-Force Fusion with Stacking Ensemble Learning for Wear Recognition of Pyramid Abrasive Belts under Variable Grinding Conditions,” Mechanical Systems and Signal Processing, vol. 250, 2026.
[CrossRef] [Google Scholar] [Publisher Link]

[10] MingAng Guo et al., “Time-Frequency Analysis-Based Impulse Feature Extraction Method for Quantitative Evaluation of Milling Tool Wear,” Structural Health Monitoring, vol. 23, no. 3, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[11] Chao Peng et al., “Tool Wear Feature Extraction in BTA Deep Hole Drilling Process Based on Maximum Probability Multi-Synchrosqueezing Transform of Spindle Current Signal,” Measurement, vol. 241, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[12] Jun Shi et al., “Synchrosqueezed Fractional Wavelet Transform: A New High-Resolution Time-Frequency Representation,” IEEE Transactions on Signal Processing, vol. 71, pp. 264-278, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[13] Ahmed Abdeltawab et al., “Wavelet-based Hybrid CNN-BiLSTM Approach in Tool Wear Monitoring,” Digital Signal Processing, vol. 168, 2026.
[CrossRef] [Google Scholar] [Publisher Link]

[14] Priyadharshini Rengasamy, and R. Rajesh, “Explainable Artificial Intelligence Framework for Wind Turbine Fault Detection using Random Forest–Extreme Gradient Boosting Hybrid Model,” Results in Engineering, vol. 28, pp. 1-14, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[15] David W. Aha, Dennis Kibler, and Marc K. Albert, “Instance-based Learning Algorithms,” Machine Learning, vol. 6, pp. 37-66, 1991.
[CrossRef] [Google Scholar] [Publisher Link]

[16] N. S. Altman, “An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression,” The American Statistician, vol. 46, no. 3, pp. 175-185, 1992.
[Google Scholar] [Publisher Link]

[17] Shengming Dong et al., “Tool Wear State Recognition Study based on an MTF and a Vision Transformer with a Kolmogorov–Arnold Network,” Mechanical Systems and Signal Processing, vol. 228, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[18] Jianwen Qiu et al., “Tool Wear Prediction based on an LSTM-Transformer Model,” Proceedings of the 2025 International Conference on Artificial Intelligence and Computational Intelligence, pp. 29-33, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[19] Sumei Si, Deqiang Mu, and Zekai Si, “Intelligent Tool Wear Prediction based on Deep Learning PSD-CVT Model,” Scientific Reports, vol. 14, pp. 1-10, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[20] Shuhang Li, Meiqiu Li, and Yingning Gao, “Deep Learning Tool Wear State Identification Method Based on Cutting Force Signal,” Sensors, vol. 25, no. 3, pp. 1-19, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[21] Ningning Han, Yongzhen Pei, and Zhanjie Song, “Signal Separation Operator Based on Wavelet Transform for Non-Stationary Signal Decomposition,” Sensors, vol. 24, no. 18, pp. 1-14, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[22] K. Vijayalakshmi et al., Secure and Private Federated Learning through Encrypted Parameter Aggregation, Handbook on Federated Learning, CRC Press, pp. 80-105, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[23] Tam T. Truong et al., “Data-Driven Prediction of Tool Wear Using Bayesian-Regularised Artificial Neural Networks,” Measurement, vol. 238, pp. 1-15, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[24] F. Gougam et al., “Computer Numerical Control Machine Tool Wear Monitoring Through a Data-Driven Approach,” Advances in Mechanical Engineering, vol. 16, no. 2, pp. 1471-1485, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[25] Satish Kumar et al., “Performance Evaluation for Tool Wear Prediction Based on Bi-Directional, Encoder-Decoder, and Hybrid Long Short-Term Memory models,” International Journal of Quality & Reliability Management, vol. 39, no. 7, pp. 1551-1576, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[26] Deniz Bilgili et al., “Tool Flank Wear Prediction using High-Frequency Machine Data from an Industrial Edge Device,” Procedia CIRP, vol. 118, pp. 483-488, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[27] Song Zhang et al., “GNSS Signal Extraction Using CEEMDAN–WPD for Deformation Monitoring of Ropeway Pillars,” Remote Sensing, vol. 17, no. 2, pp. pp. 1-22, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[28] Dung Tien Hoang et al., “Combined Analysis of Acoustic Emission and Vibration Signals in Monitoring Tool wear, Surface Quality and Chip Formation when Turning SCM440 Steel using MQL,” EUREKA: Physics and Engineering, vol. 2023, no. 1, pp. 86-101, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[29] Muhammad Umar et al., “Milling Machine Fault Diagnosis Using Acoustic Emission and Hybrid Deep Learning with Feature Optimization,” Applied Sciences, vol. 14, no. 22, pp. 1-22, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[30] Thafseela Koya Poolakkachalil et al., “Comparative Analysis of Lossless Compression Techniques in an Efficient DCT-based Image Compression System based on Laplacian Transparent Composite Model and An Innovative Lossless Compression Method for Discrete-Color Images,” 2016 3^rd MEC International Conference on Big Data and Smart City (ICBDSC), Muscat, Oman, pp. 1-6, 2016.
[CrossRef] [Google Scholar] [Publisher Link]

[31] Pimolkan Piankitrungreang et al., “Acoustic-Based Machine Main State Monitoring for High-Speed CNC Drilling,” Machines, vol. 13, no. 5, pp. 1-25, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[32] Jagannathan Jayachandran et al., “Machine Learning-Enhanced MXene–Copper–Graphene THz Sensor for Accurate Salinity Sensing in Environmental Applications,” Plasmonics, vol. 20, pp. 11349-11359, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[33] Zhaohua Wu, and Norden E. Huang, “Ensemble Empirical Mode Decomposition: A Noise-Assisted Data Analysis Method,” Advances in Adaptive Data Analysis, vol. 1, no. 1, pp. 1-41, 2009.
[CrossRef] [Google Scholar] [Publisher Link]

[34] Ahmat Orhan et al., “A Comparative Study of Time–Frequency Representations for Bearing and Rotating Fault Diagnosis Using Vision Transformer,” Machines, vol. 13, no. 8, pp. 1-21, 2025.
[CrossRef] [Google Scholar] [Publisher Link]