Material-adaptive kurtosis thresholding for real-time multi-parameter condition monitoring in CNC milling
DOI:
https://doi.org/10.15282/ijame.23.1.2026.6.1004Keywords:
Advanced manufacturing , Condition monitoring, Statistical analysis, Vibration measurement, Tool wear detectionAbstract
Tool wear remains a major contributor to dimensional defects and unplanned downtime in Computer Numerical Control (CNC) machining. Most existing monitoring strategies employ fixed vibration thresholds that cannot accommodate the distinct dynamic responses of different workpiece materials. Thresholds calibrated for hard materials such as cast iron often fail to detect early wear, whereas the same settings applied to softer polymers lead to excessive false alarms. This limitation highlights the need for material-dependent condition assessment rather than universal thresholding. This study proposes a material-adaptive monitoring framework based on kurtosis thresholds that automatically adjust when the machined material changes. Experimental validation was conducted on three materials representing a wide hardness range: cast iron (220 to 260), aluminum (95 to 100), and polyvinyl chloride (PVC) (80 to 85). A full factorial design comprising 81 milling trials of 27 per material was performed using spindle speeds of 1,500 to 3,500 rev/min, feed rates of 125 to 250 mm/min, and axial depths of cut between 0.2 and 0.7 mm. Vibration signals were acquired using accelerometers mounted on both the spindle and workpiece, and material-specific kurtosis thresholds were derived by correlating statistical features with measured tool wear. The current method achieved classification accuracies of 95.2% for cast iron, 97.8% for aluminum, and 96.7% for PVC, representing improvements of 6-11% over conventional fixed-threshold approaches. The monitoring system was further implemented on an Internet of Things platform to enable real-time remote diagnostics and automated alerts. Pilot deployment indicated a 25-30% reduction in maintenance costs compared with the existing practice. These results demonstrate that material-adaptive thresholding substantially improves the reliability and practicality of vibration-based tool condition monitoring in CNC milling environments.
References
[1] A. Jimenez-Cortadi, I. Irigoien, F. Boto, B. Sierra, G. Rodriguez, “Predictive maintenance on the machining process and machine tool,” Applied Science, vol. 10, no. 1, p. 342, 2020.
[2] I.U. Hassan, K. Panduru, J. Walsh, “An in-depth study of vibration sensors for condition monitoring,” Sensors, vol. 24, no. 3, p. 892, 2024.
[3] G. Wszołek, P. Czop, J. Słoniewski, H. Dogrusoz, “Vibration monitoring of CNC machinery using MEMS sensors,” Journal of Vibroengineering, vol. 22, no. 4, pp. 735–750, Jun. 2020.
[4] D. Neupane, M.R. Bouadjenek, R. Dazeley, S. Aryal, “Data-driven machinery fault detection: A comprehensive review,” IEEE Transactions on Industrial Informatics, vol. 20, no. 4, pp. 5235–5248, 2024.
[5] M. Rahman, S. Ali, K. Ahmed, “Deep learning approaches for predictive maintenance in manufacturing: A comprehensive review,” Journal of Intelligent Manufacturing, vol. 33, no. 6, pp. 1651–1677, 2022.
[6] M. Jamil, A.M. Khan, H. Hegab, L. Gong, M. Mia, M.K. Gupta et al., “Recent advances in tool condition monitoring in machining operations: A comprehensive review,” IEEE Access, vol. 9, pp. 28171–28196, 2021.
[7] T. Li, C. Sun, R. Yan, X. Chen, “Advanced statistical feature extraction for mechanical fault detection using unsupervised learning techniques,” IEEE Transactions on Industrial Electronics, vol. 70, no. 4, pp. 4215–4225, 2023.
[8] J. Antoni, “The spectral kurtosis: a useful tool for characterising non-stationary signals,” Mechanical Systems and Signal Processing, vol. 20, no. 2, pp. 282–307, 2006.
[9] T. Li, C. Sun, R. Yan, X. Chen, “A novel unsupervised graph wavelet autoencoder for mechanical system fault detection,” IEEE Transactions on Industrial Informatics, vol. 17, no. 10, pp. 6999–7008, 2021.
[10] P. Bangalore, L.B. Tjernberg, “An artificial neural network approach for early fault detection of gearbox bearings,” IEEE Transactions on Smart Grid, vol. 6, no. 2, pp. 980–987, 2015.
[11] S. Kumar, A. Sharma, R. Singh, “Machine learning approaches for vibration-based fault detection in manufacturing systems,” Journal of Manufacturing Science and Engineering, vol. 144, no. 8, p. 081005, 2022.
[12] X. Wang, Y. Liu, Z. Chen, “Cloud-based monitoring platforms for industrial equipment condition assessment,” IEEE Internet of Things Journal, vol. 10, no. 12, pp. 10543–10557, 2023.
[13] L. Chen, H. Wang, M. Zhang, “Multi-sensor fusion techniques for enhanced condition monitoring in manufacturing systems,” International Journal of Advanced Manufacturing Technology, vol. 131, no. 5–6, pp. 2587–2601, 2024.
[14] C.R. Farrar, K. Worden, “An introduction to structural health monitoring,” Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, vol. 365, no. 1851, pp. 303–315, 2007.
[15] M.S.H. Bhuiyan, I.A. Choudhury, M. Dahari, “Monitoring the tool wear, surface roughness and chip formation occurrences using multiple sensors in turning,” Journal of Manufacturing Systems, vol. 33, no. 4, pp. 476–487, 2014.
[16] M.C. Shaw, Metal cutting principles, 2nd ed. Oxford, U.K.: Oxford University Press, 2005.
[17] M.E. Merchant, “Mechanics of the metal cutting process,” Journal of Applied Physics, vol. 16, no. 5, pp. 267–275, 1945.
[18] D.J. Whitehouse, surfaces and their measurement. London, U.K.: Hermes Penton Science, 2004.
[19] Y. Bai, Z. Zhao, X. Chen, “Surface roughness prediction model in machining based on vibration signals and deep learning,” Journal of Manufacturing Processes, vol. 91, pp. 1–12, 2023.
[20] Y. Altintas, Manufacturing Automation: Metal Cutting Mechanics, Machine Tool Vibrations, and CNC Design, 2nd ed. Cambridge, U.K.: Cambridge University Press, 2012.
[21] P. Bangalore, L.B. Tjernberg, “An artificial neural network approach for early fault detection of gearbox bearings,” IEEE Transactions on Smart Grid, vol. 6, no. 2, pp. 980–987, 2015.
[22] M.M. Maru, R.S. Castillo, L.R. Padovese, “Study of solid contamination in ball bearings through vibration and wear analyses,” Tribology International, vol. 40, no. 3, pp. 433–440, 2007.
[23] J.S. Bendat, A.G. Piersol, Random Data: Analysis and Measurement Procedures, 4th ed. New York, NY, USA: Wiley, 2010.
[24] W.T. Thomson, M.D. Dahleh, Theory of Vibration with Applications, 5th ed. Upper Saddle River, NJ, USA: Prentice Hall, 1998.
[25] Y. Zhou, K. Guo, J. Sun, “An integrated wireless vibration sensing tool holder for milling tool condition monitoring with singularity analysis,” Measurement, vol. 174, p. 109038, 2021.
[26] V. Hariharan, P. S. S. Srinivasan, “Vibration analysis of misaligned shaft-ball bearing system,” Indian Journal of Science and Technology, vol. 2, no. 9, pp. 45–50, 2009.
[27] A. Papoulis, S.U. Pillai, Probability, random variables and stochastic processes, 4th ed. New York, NY, USA: McGraw-Hill, 2002.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 The Author(s)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
