Intelligent Tool Wear Classification of a CNC Drill Bit Using Feature Fusion and a Family of Lazy Classifiers

International Journal of Mechanical Engineering

© 2025 by SSRG - IJME Journal

Volume 12 Issue 11

Year of Publication : 2025

Authors : Amuthakkannan Rajakannu, S.Vishnupriyan, Dinesh Keloth Kaithari, Abubacker KM, K.Baskaran, K.Vijayalakshmi

10.14445/23488360/IJME-V12I11P111

How to Cite?

Amuthakkannan Rajakannu, S.Vishnupriyan, Dinesh Keloth Kaithari, Abubacker KM, K.Baskaran, K.Vijayalakshmi, "Intelligent Tool Wear Classification of a CNC Drill Bit Using Feature Fusion and a Family of Lazy Classifiers," SSRG International Journal of Mechanical Engineering, vol. 12,  no. 11, pp. 113-124, 2025. Crossref, https://doi.org/10.14445/23488360/IJME-V12I11P111

Abstract:

On the shop floor, CNC machining is used for batch production, and it is essential to maintain a trouble-free CNC machine to avoid downtime and increase its practical usage. Among CNC machines, CNC drill maintenance is more complex due to the intricate structure of the drill bits. CNC drilling tool wear affects the accuracy of the system's dimensions, surface finish, and productivity. This paper proposes a method of multidomain feature fusion and a family of lazy classifiers for improved drill bit wear classification. During the controlled drilling processes, Acoustic Emission (AE) signals were recorded for the following wear states: Healthy Tool (HT), Low Wear (LW), Medium Wear (MW), and Severe Wear (SW). The Low, Medium, and Severe wear were created using Electro Chemical Machining (ECM) on the drill bit diameters of 3mm, 3.2mm, 3.4 mm,3.6 mm, and 3.8 mm, and the data acquisition was done using National Instruments (NI) Hardware and LabVIEW software. Features were extracted from the time-domain, frequency-domain, and time–frequency domain, and Wavelet Packet Decomposition (WPD) was used. Lazy classifiers, such as k-Nearest Neighbours (k-NN), Weighted k-NN (WKNN), Locally Weighted Learning (LWL), Instance-Based k (IBk), and LazyBayes, were used after the classifiers were trained on feature vectors describing the previously mentioned signals. Using a 10-fold cross-validation, the best classification rate of 98.7% was attained using WKNN, which outperformed other methods in precision and robustness. The proposed tool wear framework offers high accuracy and low computation for real-time CNC tool wear estimation.

Keywords:

CNC tool wear, Feature fusion, Acoustic emission, Lazy classifiers, k-NN, Wavelet packet decomposition.

References:

[1] Swathi Kotha Amarnath et al., “Combining Sensor Fusion and a Machine Learning Framework for Accurate Tool Wear Prediction During Machining,” Machines, vol. 13, no. 2, pp. 1-15, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Zheng Gong, and Dehong Huo, “Tool Condition Monitoring in Micro Milling of Brittle Materials,” Precision Engineering, vol. 87, pp. 11-22, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Ravi Sekhar et al., “Noise Robust Classification of Carbide Tool Wear in Machining Mild Steel using a Texture-Extraction-Based Transfer Learning Approach for Predictive Maintenance,” Results in Control and Optimization, vol. 17, pp. 1-26, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Changjuan Zhang et al., “Tool Wear Status Monitoring Under Laser-Ultrasonic Compound Cutting based on Acoustic Emission and Deep Learning,” Journal of Mechanical Science and Technology, vol. 38, pp. 2411-2421, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[5] 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]
[6] D. Rajeev 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]
[7] Tanner Jones, and Yang Cao, “Tool Wear Prediction based on Multisensor Data Fusion and Machine Learning,” The International Journal of Advanced Manufacturing Technology, vol. 137, pp. 5213-5225, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Jun-Hong Zhou et al., “Tool Wear Monitoring Using Acoustic Emissions by Dominant-Feature Identification,” IEEE Transactions on Instrumentation and Measurement, vol. 60, no. 2, pp. 547-559, 2011.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Lan Shen Guo et al., “A Mthod of Tools AE Signal Feature Extraction Based on Wavelet Packet Analysis,” Key Engineering Materials, vol. 474-476, pp. 189-194, 2011.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Dongdong Kong et al., “Tool Wear Monitoring Based on Kernel Principal Component Analysis and V-Support Vector Regression,” The International Journal of Advanced Manufacturing Technology, vol. 89, pp. 175-190, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Chenggong Ma et al., “Data-Driven Feature Extraction-Transformer: A Hybrid Fault Diagnosis Scheme Utilizing Acoustic Emission Signals,” Process, vol. 12, no. 10, pp. 1-23, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Zishuo Wang et al., “Identification of Tool-Wear State Using Information Fusion and SSA–BP Neural Network,” Machines, vol. 13, no. 4, pp. 1-17, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Muhammad Umar et al., “Milling Machine Fault Diagnosis Using Acoustic Emission and Hybrid Deep Learning with Feature Optimization,” Applied Sciences, vol. 12, no. 22, pp. 1-22, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Ahmed Abdeltawab et al., “Wavelet-Based Hybrid CNN-BiLSTM Approach in Tool Wear Monitoring,” Digital Signal Processing, vol. 168, part B, 2026.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Yung-Hsiang Hung et al., “Tool Wear Classification Based on Support Vector Machine and Deep Learning Models,” Sensors and Materials, vol. 36, no. 11, pp. 4815-4833, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Xingwei Xu et al., “Deep Learning-Based Tool Wear Prediction and Its Application for Machining Process Using Multi-Scale Feature Fusion and Channel Attention Mechanism,” Measurement, vol. 177, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Dazhong Wu et al., “A Comparative Study on Machine Learning Algorithms for Smart Manufacturing: Tool Wear Prediction Using Random Forests,” Journal of Manufacturing Science and Engineering, vol. 139, no. 7, pp. 1-9, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[18] 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]
[19] N.S. Altman, “An Introduction to Kernel and Nearest-Neighbour Nonparametric Regression,” The American Statistician, vol. 46, no. 3, pp. 175-185, 1992.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Klaus Moeltner et al., “Locally-Weighted Meta-Regression and Benefit Transfer,” Journal of Environmental Economics and Management, vol. 121, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Amandeep Sharma et al., “Bearing Fault Diagnosis using Weighted K-Nearest Neighbours Classifier,” 2018 2nd International Conference on Trends in Electronics and Informatics (ICOEI), Tirunelveli, India, vol. 94, pp. 173-187, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Zrinka Murat et al., “Frequency Domain Analysis of Acoustic Emission Signals in Medical Drill Wear Monitoring,” Proceedings of the 10th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2017), vol. 3, pp. 173-177, 2017.
[Google Scholar] [Publisher Link]
[23] Yaping Zhang et al., “Tool Wear Condition Monitoring Method Based on Deep Learning with Force Signals,” Sensors, vol. 23, no. 10, pp. 1-17, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Zhixiong Li, Rui Liu, and Dazhong Wu, “Data-Driven Smart Manufacturing: Tool Wear Monitoring with Audio Signals and Machine Learning,” Journal of Manufacturing Processes, vol. 48, pp. 66-76, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Dylan Drew et al., “Application of Machine Learning for Tool Condition Monitoring using Sensor Integrated Tooling,” Procedia CIRP, vol. 133, pp. 66-71, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Yung-Hsiang Hung et al., “Tool Wear Classification based on Support Vector Machine and Deep Learning Models,” Sensors and Materials, vol. 36, no. 11, pp. 4815-4833, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Viet Q. Vu, Tien-Ninh Bui, and Minh-Quang Tran, “AI-based Tool Wear Prediction with Feature Selection from Sound Signal Analysis,” Frontiers in Mechanical Engineering, vol. 11, pp. 1-14, 2025.
[CrossRef] [Publisher Link]
[28] Devarajan Kaliyannan et al., “Tool Condition Monitoring in the Milling Process Using Deep Learning and Reinforcement Learning,” Journal of Sensor and Actuator Networks, vol. 13, no. 4, pp. 1-19, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Meiliang Chen et al., “Tool Wear Monitoring based on the Combination of Machine Vision and Acoustic Emission,” The International Journal of Advanced Manufacturing Technology, vol. 125, pp. 3881-3897, 2023.
[CrossRef] [Google Scholar] [Publisher Link]