Data-Driven Prediction of Remaining Useful Life for Milling Tools Using Machine Learning Models
Từ khóa
DOI:
https://doi.org/10.31817/vjas.2026.9.3.05Tóm tắt
In the context of precision machining, predicting the remaining useful life (RUL) of cutting tools plays a critical role in optimizing production processes and reducing maintenance costs. This study proposed and developed four machine learning models for predicting tool RUL in milling operations, namely exponential Gaussian process regression (GPR), fine tree, linear regression, and quadratic support vector machine (SVM). The input dataset was constructed from sensor signals and key process parameters, including three-axis vibrations (vibration_x, vibration_y, vibration_z), acoustic emission signals, spindle load, cutting speed, feed rate, material hardness, and tool wear. The models were trained and evaluated using standard performance metrics, namely the coefficient of determination (R²), root mean square error (RMSE), and mean absolute error (MAE). Experimental results indicated that the linear regression model outperformed the other models, achieving an R² value of 1 and extremely low prediction errors (RMSE = 4.1 × 10⁻⁸; MAE = 3.2 × 10⁻⁸). The findings suggest that the proposed framework is both effective and highly applicable for tool condition monitoring, while also supporting the optimization of cutting parameters in milling processes.Lượt tải
Tài liệu tham khảo
Refaie A., Atrash M. & Lepkova N. (2025). Prediction of the remaining useful life of a milling machine using machine learning. Methods X. 14: 103195. DOI: 10.1016/j.mex.2025.103195.
Bareth R., Kochar M. & Yadav A. (2023). Comparative Analysis of different Machine learning Models for Load Forecasting. 2023 IEEE IAS Global Conference on Renewable Energy and Hydrogen Technologies (GlobConHT). 1-5. DOI: 10.1109/GlobConHT56829.2023.10087406.
Chen Z., Wu M., Zhao R., Guretno F., Yan R. & Li X. (2021). Machine Remaining Useful Life Prediction via an Attention-Based Deep Learning Approach. IEEE Transactions on Industrial Electronics. 68(3): 2521-2531. DOI: 10.1109/TIE.2020.2972443.
Li X., Liu X., Yue C., Wang L. & Liang S. Y. (2024). Data-model linkage prediction of tool remaining useful life based on deep feature fusion and Wiener process. Journal of Manufacturing Systems. 73: 19-38. DOI: 10.1016/j.jmsy.2024.01.008.
Li Y., Xiang Y., Pan B. & Shi L. (2022). A hybrid remaining useful life prediction method for cutting tool considering the wear state. The International Journal of Advanced Manufacturing Technology. 121(5): 3583-3596. DOI: 10.1007/s00170-022-09417-4.
Liu W., Yang W. A. & You Y. (2022). Three-Stage Wiener-Process-Based Model for Remaining Useful Life Prediction of a Cutting Tool in High-Speed Milling. Sensors. 22(13). DOI: 10.3390/s22134763.
Kaggle (2025). Milling Tool Wear and RUL Dataset. Retrieved from https://www.kaggle.com/datasets/programmer3/milling-tool-wear-and-rul-dataset on April 28, 2026.
Montgomery D. C,, Peck E. A. & Vining G. G. (2021). Introduction to Linear Regression Analysis, (6th ed). Wiley. Hoboken, New Jersey.
Nguyen H. P., Nguyen D. T. & Kim J. M. (2026). Gaussian process regression with physics-guided pseudo-sample augmentation for wear prediction under sparse measurements in milling. Scientific Reports. 16(1): 7231. DOI: 10.1038/s41598-026-38067-9.
Nguyen T. M. & Le T. T. (2026). Development of machine-learning models to determine the power of natural gas/hydrogen spark ignition engines. Proceedings of the Institution of Mechanical Engineers, Part A: Journal of Power and Energy: 1-12. DOI: 10.1177/09576509261443391.
Qin X., Huang W., Wang X., Tang Z. & Liu Z. (2022). Real-Time Remaining Useful Life Prediction of Cutting Tools Using Sparse Augmented Lagrangian Analysis and Gaussian Process Regression. Sensors. 23(1). DOI: 10.3390/s23010413.
Sayyad S., Kumar S., Bongale A., Kamat P., Patil S. & Kotecha K. (2021). Data-Driven Remaining Useful Life Estimation for Milling Process: Sensors, Algorithms, Datasets, and Future Directions. IEEE Access. 9: 110255-110286. DOI: 10.1109/ACCESS.2021.3101284.
Sayyad S., Kumar S., Bongale A., Kotecha K. & Abraham A. (2023). Remaining Useful-Life Prediction of the Milling Cutting Tool Using Time-Frequency-Based Features and Deep Learning Models. Sensors. 23(12). DOI: 10.3390/s23125659.
Smola A. J. & Schölkopf B. (2004). A tutorial on support vector regression. Statistics and Computing. 14(3): 199-222. DOI: 10.1023/B:STCO.0000035301.49549.88.
Wang B., Lei Y., Yan T., Li N. & Guo L. (2020). Recurrent convolutional neural network: A new framework for remaining useful life prediction of machinery. Neurocomputing. 379: 117-129. DOI: 10.1016/j.neucom.2019.10.064.
Wang S., Yu Z., Xu G. & Zhao F. (2023). Research on Tool Remaining Life Prediction Method Based on CNN-LSTM-PSO. IEEE Access. 11: 80448-80464. DOI: 10.1109/ACCESS.2023.3299849.
Yadav A., Bareth R., Kochar M., Pazoki M. & Sehiemy R. A .E. (2024). Gaussian process regression-based load forecasting model. IET Generation, Transmission & Distribution. 18(5): 899-910. DOI: 10.1049/gtd2.12926.
Yang L., Liu S., Tsoka S. & Papageorgiou L. G. (2017). A regression tree approach using mathematical programming. Expert Systems with Applications. 78: 347-357. DOI: 10.1016/j.eswa.2017.02.013.
Zhang H., Jiang S., Gao D., Sun Y. & Bai, W. (2024). A
Review of Physics-Based, Data-Driven, and Hybrid
Models for Tool Wear Monitoring. Machines. 12(12). DOI: 10.3390/machines12120833.
Zhou J., Yang J., Qian Q. & Qin Y. (2024). A comprehensive survey of machine remaining useful life prediction approaches based on pattern recognition: Taxonomy and challenges. Measurement Science and Technology. 35(6): 062001. DOI: 10.1088/1361-6501/ad2bcc.
Wang Y., Li D., Nie C., Gong P., Yang J., Hu Z., Li B. & Ma M. (2023). Research Progress on the Wear Resistance of Key Components in Agricultural Machinery. Materials. 16(24): 7646. DOI: 10.3390/ma16247646.
Lee K., Lanning D., Lin L., Cakmak E., Keiser J. R. & Qu J. (2021). Wear Mechanism Analysis of a New Rotary Shear Biomass Comminution System. ACS Sustainable Chemistry and Engineering. 9(35). DOI: 10.1021/acssuschemeng. 1c02542.
.
