Support vector regression to correct motor current of machine tool drives

  • Max SchwenzerEmail author
  • Thomas Auerbach
  • Kazumasa Miura
  • Benjamin Döbbeler
  • Thomas Bergs


Nonlinear friction is the limiting factor in using motor current signals to estimate the load of machine tools. The inertia of the axis and the positional dependency of the friction add another degree of complexity. The work focuses on industrial machining centers with ball-screw driven stages as they are used in metal cutting. The approach uses Internal low-frequency signals from the NC controller to keep the barriers for an industrial application at a minimum. The contribution of this study is twofold: First, it extends conventional analytic friction models so that they incorporate positional dependency of friction, as well as the contribution of the inertia of the axis. Second, it proposes how to model the both effects jointly through support vector regression. This data-driven model outperforms the extended Stribeck and the generalized Maxwell-slip friction models, which serve as a representative benchmark for static and dynamic friction models respectively. However, this comes with the need for a careful selection of the data, on which the support vector machine is trained, in order to obtain an accurate and general model.


Friction model Machine tool drive Support vector regression Cutting technology 



The authors would like to thank the German Research Foundation DFG for the kind support within the Cluster of Excellence “Internet of Production”.


  1. Al-Bender, F., Lampaert, V., & Swevers, J. (2005). The generalized Maxwell-slip model: A novel model for friction Simulation and compensation. IEEE Transactions on Automatic Control, 50(11), 1883–1887. Scholar
  2. Altintas, Y. (1992). Prediction of cutting forces and tool breakage in milling from feed drive current measurements. Journal of Engineering for Industry, 114(4), 386–392.CrossRefGoogle Scholar
  3. Auchet, S., Chevrier, P., Lacour, M., & Lipinski, P. (2004). A new method of cutting force measurement based on command voltages of active electro-magnetic bearings. International Journal of Machine Tools and Manufacture, 44(14), 1441–1449. Scholar
  4. Boser, B. E., Guyon, I. M., & Vapnik, V. N. (1992). A training algorithm for optimal margin classifiers. In Proceedings of the fifth annual workshop on computational learning theory, ACM, New York, NY, USA, COLT ’92, pp. 144–152.
  5. Bui, B. D., Uchiyama, N., & Sano, S. (2015). Nonlinear friction modeling and compensation for precision control of a mechanical feed-drive system. Sensors and Materials, 27(10), 971–983. Scholar
  6. Canudas de Wit, C., Olsson, H., Astrom, K. J., & Lischinsky, P. (1995). A new model for control of systems with friction. IEEE Transactions on Automatic Control, 40(3), 419–425.CrossRefGoogle Scholar
  7. Chang, C. C., & Lin, C. J. (2011). LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology 2:27:1–27:27, software available at
  8. Cherkassky, V., & Ma, Y. (2004). Practical selection of SVM parameters and noise estimation for SVM regression. Neural Networks, 17(1), 113–126. Scholar
  9. Denkena, B., & Hackelöer, F. L. (2010). Multi-sensor disturbance force measurement for compliant mechanical structures. IEEE, pp 2518–2524.
  10. Hong, Y. C., Ha, S. J., & Cho, M. W. (2012). Predicting of cutting forces in a micromilling process based on frequency analysis of sensor signals and modified polynomial neural network algorithm. International Journal of Precision Engineering and Manufacturing, 13(1), 17–23. Scholar
  11. Kim, T. Y., Woo, J., Shin, D., & Kim, J. (1999). Indirect cutting force measurement in multi-axis simultaneous NC milling processes. International Journal of Machine Tools and Manufacture, 39(11), 1717–1731. Scholar
  12. Kurihara, D., Kakinuma, Y., & Katsura, S. (2010). Cutting force control applying sensorless cutting force monitoring method. Journal of Advanced Mechanical Design, Systems, and Manufacturing, 4(5), 955–965. Scholar
  13. Lampaert, V., Swevers, J., & Al-Bender, F. (2002). Modification of the Leuven integrated friction model structure. IEEE Transactions on Automatic Control, 47(4), 683–687. Scholar
  14. Lee, W., Lee, C. Y., Jeong, Y. H., & Min, B. K. (2015). Friction compensation controller for load varying machine tool feed drive. International Journal of Machine Tools and Manufacture, 96, 47–54. Scholar
  15. Rafan, N., Jamaludin, Z., Chiew, T., Abdullah, L., & Maslan, M. (2015). Contour error analysis of precise positioning for ball screw driven stage using friction model feedforward. Procedia CIRP, 26, 712–717. Scholar
  16. Rebelein, C., & Zaeh, M. F. (2016). Friction in feed drives of machine tools: Investigation, modeling and validation. Production Engineering, 10(4–5), 497–507. Scholar
  17. Ruderman, M., & Bertram, T. (2011). Modified Maxwell-slip model of presliding friction. IFAC Proceedings Volumes, 44(1), 10764–10769. Scholar
  18. Sato, R., Shirase, K., & Hayashi, A. (2017). Energy consumption of feed drive systems based on workpiece setting position in five-axis machining center. Journal of Manufacturing Science and Engineering, 140(2), 021008. Scholar
  19. Shinno, H., Hashizume, H., & Yoshioka, H. (2003). Sensor-less monitoring of cutting force during ultraprecision machining. CIRP Annals, 52(1), 303–306. Scholar
  20. Smola, A. J., & Schölkopf, B. (2004). A tutorial on support vector regression. Statistics and Computing, 14(3), 199–222. Scholar
  21. Stein, J., Colvin, D., Clever, G., & Wang, C. (1986). Evaluation of DC servo machine-tool feed drives as force sensors. Journal of Dynamic Systems Measurement and Control-Transactions of the ASME, 108(4), 279–288.CrossRefGoogle Scholar
  22. Stemmler, S., Abel, D., Schwenzer, M., Adams, O., & Klocke, F. (2017). Model predictive control for force control in milling. IFAC-Papers OnLine, 50(1), 15871–15876. Scholar
  23. Swevers, J., Al-Bender, F., Ganseman, C., & Projogo, T. (2000). An integrated friction model structure with improved presliding behavior for accurate friction compensation. IEEE Transactions on Automatic Control, 45(4), 675–686. Scholar
  24. Tjahjowidodo, T., Al-Bender, F., & Van Brussel, H. (2005). Friction identification and compensation in a DC motor. IFAC Proceedings Volumes, 38(1), 554–559. Scholar
  25. Tjahjowidodo, T., Al-Bender, F., Van Brussel, H., & Symens, W. (2007). Friction characterization and compensation in electro-mechanical systems. Journal of Sound and Vibration, 308(3–5), 632–646. Scholar
  26. Tsirikoglou, P., Abraham, S., Contino, F., Lacor, C., & Ghorbaniasl, G. (2017). A hyperparameters selection technique for support vector regression models. Applied Soft Computing, 61, 139–148. Scholar
  27. Vapnik, V., Golowich, S. E., & Smola, A. J. (1996). Support vector method for function approximation, regression estimation and signal processing. In NIPS.Google Scholar
  28. Villegas, F. J., Hecker, R. L., Peña, M. E., Vicente, D. A., & Flores, G. M. (2014). Modeling of a linear motor feed drive including pre-rolling friction and aperiodic cogging and ripple. The International Journal of Advanced Manufacturing Technology, 73(1–4), 267–277. Scholar
  29. Wu, X., Kumar, V., Ross Quinlan, J., Ghosh, J., Yang, Q., Motoda, H., et al. (2008). Top 10 algorithms in data mining. Knowledge and Information Systems, 14(1), 1–37. Scholar
  30. Yamada, Y., Kakinuma, Y., Ito, T., Fujita, J., & Matsuzaki, H. (2016). Sensorless monitoring of cutting force variation with fractured tool under heavy cutting condition. In ASME, p V003T08A025.
  31. Yamada, Y., & Kakinuma, Y. (2016a). Mode decoupled cutting force monitoring by applying multi encoder based disturbance observer. Procedia CIRP, 57, 643–648. Scholar
  32. Yamada, Y., & Kakinuma, Y. (2016b). Sensorless cutting force estimation for full-closed controlled ball-screw-driven stage. The International Journal of Advanced Manufacturing Technology, 87(9), 3337–3348. Scholar
  33. Yamada, Y., Yamato, S., & Kakinuma, Y. (2017). Mode decoupled and sensorless cutting force monitoring based on multi-encoder. The International Journal of Advanced Manufacturing Technology, 92(9–12), 4081–4093. Scholar
  34. Yang, M., Yang, J., & Ding, H. (2018). A two-stage friction model and its application in tracking error pre-compensation of CNC machine tools. Precision Engineering, 51, 426–436. Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Laboratory for Machine Tools and Production Engineering (WZL)RWTH Aachen UniversityAachenGermany

Personalised recommendations