Comparative study of machine learning and ensemble learning approach on tool wear classification

Abstract

This study investigates the application of machine learning algorithms for predicting tool wear in machining operations, aiming to enhance production efficiency and reduce costs associated with tool maintenance. We implemented five distinct algorithms: K-Nearest Neighbors (KNN), Decision Trees, Random Forests, LightGBM, and XGBoost. The results reveal that these models can accurately classify tool conditions as "worn" or "unworn," with LightGBM and XGBoost showing solid performance. Notably, an ensemble approach using a soft voting classifier combining KNN, Random Forest, and LightGBM achieved an accuracy of 0.9968 and a ROC AUC of 0.9998. This research underscores the potential of machine learning to transform traditional tool management practices, enabling proactive maintenance strategies that can significantly improve machining efficiency and product quality. Future work may explore integrating real-time data for further enhancements in predictive accuracy.

Keywords

• tool wear prediction
• machine tools
• classification
• machine learning
• ensemble learning

References

1. REFERENCES
2. [1] Ni, J., Liu, X., Meng, Z., & Cui, Y. (2023). Identification of tool wear based on infographics and a double-attention network. Machines, 11(10), Article 927. [CrossRef]
3. [2] Mahardika, M., Taha, Z., Suharto, D., Mitsui, K., & Aoyama, H. (2006). Sensor fusion strategy in the monitoring of cutting tool wear. Key Engineering Materials, 306, 727–732. [CrossRef]
4. [3] Kadhim, K. J., Abbas, A. A., & Hussein, M. A. H. (2018). Effect Ti/AlTiN multilayer coating on the crater wear process of cutting tool and tribological properties. Al-Khwarizmi Engineering Journal, 13(4), 58–68. [CrossRef]
5. [4] Kothuru, A., Nooka, S. P., & Liu, R. (2017). Cutting process monitoring system using audible sound signals and machine learning techniques: An application to end milling. In Proceedings of the International Manufacturing Science and Engineering Conference, 3, V003T04A050. [CrossRef]
6. [5] Terrazas, G., Martínez-Arellano, G., Benardos, P., & Ratchev, S. (2018). Online tool wear classification during dry machining using real time cutting force measurements and a CNN approach. Journal of Manufacturing and Materials Processing, 2(4), Article 72. [CrossRef]
7. [6] Kumar, A. S., Agarwal, A., Jansari, V. G., Desai, K. A., Chattopadhyay, C., & Mears, L. (2023). Vision-based tool wear classification during end-milling of Inconel 718 using a pre-trained convolutional neural network. In ASME International Mechanical Engineering Congress and Exposition, 3, V003T03A016. [CrossRef]
8. [7] Sun, S. (2018). CNC mill tool wear. Available at: https://www.kaggle.com/datasets/shasun/tool-wear- detection-in-cnc-mill Accessed on Oct 3, 2025.

9. [8] Cover, T., & Hart, P. (1967). Nearest neighbor pattern classification. IEEE Transactions on Information Theory, 13(1), 21–27. [CrossRef]
10. [9] Quinlan, J. R. (1986). Induction of decision trees. Machine Learning, 1(1), 81–106.
11. [10] Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. [CrossRef]
12. [11] Ke, T. Y., Meng, G., Finley, T., Wang, T., Chen, W., Ma, W., ... & Liu. (2017). LightGBM: A highly efficient gradient boosting decision tree. Advances in Neural Information Processing Systems, 20.
13. [12] Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794. [CrossRef]
14. [13] Peterson, L. E. (2009). K-nearest neighbor. Scholarpedia, 4(2), 1883. [CrossRef]
15. [14] Safavian, S. R., & Landgrebe, D. (1991). A survey of decision tree classifier methodology. IEEE Transactions on Systems, Man, and Cybernetics, 21(3), 660–674. [CrossRef]
16. [15] Liaw, A., & Wiener, M. (2001). Classification and regression by RandomForest. Forest, 23.
17. [16] Dietterich, T. G. (2000). Ensemble methods in machine learning. In Multiple Classifier Systems (pp. 1–15). Springer Berlin Heidelberg. [CrossRef]
18. [17] Zhou, Z.-H. (2012). Ensemble methods: Foundations and algorithms (Vol. 14). [CrossRef]
19. [18] Rokach, L. (2010). Ensemble-based classifiers. Artificial Intelligence Review, 33(1), 1–39. [CrossRef]
20. [19] Polikar, R. (2006). Ensemble based systems in decision making. IEEE Circuits and Systems Magazine, 6(3), 21– 45. [CrossRef]
21. [20] Kuncheva, L. (2014). Combining pattern classifiers: Methods and algorithms: Second edition (Vol. 47). [CrossRef]
22. [21] Opitz, D., & Maclin, R. (1999). Popular ensemble methods: An empirical study. Journal of Artificial Intelligence Research, 11, 169–198. [CrossRef]
23. [22] Hastie, T., Tibshirani, R., & Friedman, J. (2009). The elements of statistical learning: Data mining, inference, and prediction (2nd ed.). Springer. [CrossRef]
24. [23] Aykanat, M. A., & Kurban, R. CNC-tool-wear-detection. Available at: https://github.com/MAAykanat/CNC-Tool-Wear-Detection Accessed on Oct 03, 2025.