IJAT Vol.18 No.1 pp. 26-38
doi: 10.20965/ijat.2024.p0026

Research Paper:

Machine-Learning-Based Model Parameter Identification for Cutting Force Estimation

Junichi Kouguchi*,† ORCID Icon, Shingo Tajima** ORCID Icon, and Hayato Yoshioka*** ORCID Icon

*Beckhoff Automation K.K.
Nisseki Yokohama Building 18F, 1-1-8 Sakuragi-cho, Naka-ku, Yokohama, Kanagawa 231-0062, Japan

Corresponding author

**Tokyo Institute of Technology
Yokohama, Japan

***The University of Tokyo
Tokyo, Japan

June 30, 2023
November 27, 2023
January 5, 2024
milling, cutting force, machine learning, model-based monitoring, in-process monitoring

Recently, there has been an increased demand for precise monitoring of the milling process using machine tools through a simple and cost-effective method. Accurate estimation of cutting forces is highly effective for this monitoring, and one approach is the modeling of tool spindles and tables of a machine tool. To model machine structures, well-known methods involving the use of impulse hammer response or structural analysis exist. However, the complex modeling is hard to achieve when using the impulse response. Moreover, it is often considerably difficult to achieve the modeling with structural analysis because the preparation of the accurate model and highly complicated calculations are required. Therefore, in this study, we propose a new monitoring method to identify model parameters of the machine structure and estimate cutting forces. First, a simplified assumed structure is prepared based on locations where sensors can be mounted. Next, measurement data during actual milling process are collected through the acceleration sensors mounted on the tool spindle and the dynamometer for the cutting force attached to the table. Subsequently, model parameters are identified from these data using machine learning. A 3-axis NC milling machine was used to evaluate the application range of the model parameters by changing cutting conditions, milling direction, cutting tools, and materials. The model parameters identified using the proposed method were equivalent to those using the impulse response. Furthermore, even in cases where the impulse response was difficult to identify, suitable model parameters were identified using machine learning. Finally, we confirmed that the proposed method can accurately achieve in-process monitoring of cutting forces in the X, Y, and Z directions.

Cite this article as:
J. Kouguchi, S. Tajima, and H. Yoshioka, “Machine-Learning-Based Model Parameter Identification for Cutting Force Estimation,” Int. J. Automation Technol., Vol.18 No.1, pp. 26-38, 2024.
Data files:
  1. [1] L. Monostori, B. Kádár, T. Bauernhansl, S. Kondoh, S. Kumara, G. Reinhart, O. Sauer, G. Schuh, W. Sihn, and K. Ueda, “Cyber-Physical Systems in Manufacturing,” Annals of the CIRP, Vol.65, No.2, pp. 621-641, 2016.
  2. [2] H.-C. Möhring, P. Wiederkehr, K. Erkorkmaz, and Y. Kakinuma, “Self-optimizing machining systems,” Annals of the CIRP, Vol.69, No.2, pp. 740-763, 2020.
  3. [3] H. Shinno, H. Yoshioka, and H. Sawano, “A Framework for Systematizing Machine Tool Engineering,” Int. J. Automation Technol., Vol.7, No.6, pp. 760-768, 2013.
  4. [4] I. Nishida, R. Tsuyama, K. Shirase, M. Onishi, and K. Koarashi, “Development of Innovative Intelligent Machine Tool Based on CAM-CNC Integration Concept – Adaptive Control Based on Predicted Cutting Force –,” Int. J. Automation Technol., Vol.13, No.3, pp. 373-381, 2019.
  5. [5] H. K. Tönshoff, J. P. Wulfsberg, H. J. J. Kals, W. Konig, and C. A. van Luttervelt, “Development and trends in monitoring and control of machining process,” Annals of the CIRP, Vol.37, No.2, pp. 611-622, 1988.
  6. [6] A. Matsubara and S. Ibaraki, “Monitoring and Control of Cutting Forces in Machining Processes: A Review,” Int. J. Automation Technol., Vol.3, No.4, pp. 445-456, 2009.
  7. [7] R. Teti, K. Jemielniak, G. O’Donnell, and D. Dornfeld, “Advanced Monitoring of Machining Operations,” Annals of the CIRP, Vol.59, No.2, pp. 717-739, 2010.
  8. [8] T. Matsumura, M. Shimada, and K. Teramoto, “Predictive Cutting Force Model and Cutting Force Chart for Milling with Cutter Axis Inclination,” Int. J. Automation Technol., Vol.7, No.1, pp. 30-38, 2013.
  9. [9] Y. Altintas and S. S. Park, “Dynamic Compensation of Spindle-Integrated Force Sensors,” Annals of the CIRP, Vol.53, No.1, pp. 305-308, 2004.
  10. [10] C. Andersson, M. Andersson, and J.-E. Ståhl, “Experimental studies of cutting force variation in face milling,” Int. J. of Machine Tools and Manufacture, Vol.51, No.1, pp. 67-76, 2011.
  11. [11] M. Takei, D. Kurihara, S. Katsura, and Y. Kakinuma, “Hybrid Control for Machine Tool Table Applying Sensorless Cutting Force Monitoring,” Int. J. Automation Technol., Vol.5, No.4, pp. 587-593, 2011.
  12. [12] T. Hida, T. Asano, C. Higashino, M. Kanamaru, J. Kaneko, and Y. Takeuchi, “Development of Cutting Force Prediction Method Using Motion Information from CNC Controller,” Int. J. Automation Technol., Vol.10, No.2, pp. 253-261, 2016.
  13. [13] A. Albrecht, S. S. Park, Y. Altintas, and G. Pritschow, “High Frequency Bandwidth Cutting Force Measurement in Milling Using Capacitance Displacement Sensors,” Int. J. of Machine Tools and Manufacture, Vol.45, No.9, pp. 993-1008, 2005.
  14. [14] P. Albertelli, M. Goletti, M. Torta, M. Salehi, and M. Monno, “Model-based broadband estimation of cutting forces and tool vibration in milling through in-process indirect multiple-sensors measurements,” Int. J. of Advanced Manufacturing Technology, Vol.82, pp. 779-796, 2016.
  15. [15] C. Wang, X. Zhang, B. Qiao, X. Chen, and H. Cao, “Milling force identification from acceleration signals using regularization method based on TSVD in peripheral milling,” Procedia CIRP, Vol.77, pp. 18-21, 2018.
  16. [16] M. Salehi, P. Albertelli, M. Goletti, F. Ripamonti, G. Tomasini, and M. Monno, “Indirect model based estimation of cutting force and tool tip vibrational behavior in milling machines by sensor fusion,” Procedia CIRP, Vol.33, pp. 239-244, 2015.
  17. [17] M. Postel, D. Aslan, K. Wegener, and Y. Altintas, “Monitoring of vibrations and cutting forces with spindle mounted vibration sensors,” Annals of the CIRP, Vol.68, No.1. pp. 413-416, 2019.
  18. [18] J. Zhou, X. Mao, H. Liu, B. Li, and Y. Peng, “Prediction of cutting force in milling process using vibration signals of machine tool,” Int. J. of Advanced Manufacturing Technology, Vol.99, pp. 965-984, 2018.
  19. [19] D. Kono, S. Weikert, A. Matsubara, and K. Yamazaki, “Estimation of Dynamic Mechanical Error for Evaluation of Machine Tool Structures,” Int. J. Automation Technol., Vol.6, No.2, pp. 147-153, 2012.
  20. [20] B. Liu, K. T. Miura, and S. Usuki, “Structure Analysis with 3D Hexahedral Meshes Generated by a Label-Driven Subdivision,” Int. J. Automation Technol., Vol.12, No.1, pp. 113-122, 2018.
  21. [21] N. Lanz, D. Spescha, S. Weikert, and K. Wegener, “Efficient Static and Dynamic Modelling of Machine Structures with Large Linear Motions,” Int. J. Automation Technol., Vol.12, No.5, pp. 622-630, 2018.
  22. [22] A. Saadallaha, F. Finkeldeyb, K. Morika, and P. Wiederkehrb, “Stability prediction in milling processes using a simulation-based machine learning approach,” Procedia CIRP, Vol.72, pp. 1493-1498, 2018.
  23. [23] P. Charalampous, “Prediction of Cutting Forces in Milling Using Machine Learning Algorithms and Finite Element Analysis,” J. of Materials Engineering and Performance, Vol.30, pp. 2002-2013, 2021.
  24. [24] K. Mizuhara, D. Nakamichi, W. Yanagihara, and Y. Kakinuma, “Machine Learning-Based Shape Error Estimation Using the Servomotor Current Generated During Micro-Milling of a Micro-Lens Mold,” Int. J. Automation Technol., Vol.17, No.2, pp. 92-102, 2023.
  25. [25] N. Komura, K. Matsumoto, S. Igari, T. Ogawa, S. Fujita, and K. Nakamoto, “Computer Aided Process Planning for Rough Machining Based on Machine Learning with Certainty Evaluation of Inferred Results,” Int. J. Automation Technol., Vol.17, No.2, pp. 120-127, 2023.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Feb. 19, 2024