Journal of Intelligent and Robotic Systems

, Volume 12, Issue 2, pp 103–125 | Cite as

Learning to monitor a machine tool

  • Mieczyslaw M. Kokar
  • Jerzy Letkowski
  • Thomas F. Callahan


This paper deals with the issue of automatic learning and recognition of various conditions of a machine tool. The ultimate goal of the research discussed in this paper is to develop a comparehensive monitor and control (M&C) system that can substitute for the expert machinist and perform certain critical in-process tasks to assure quality production. The M&C system must reliably recognize and respond to qualitatively different behaviours of the machine tool, learn new behaviors, respond faster than its human counterpart to quality threatening circumstances, and interface with an existing controller. The research considers a series of face-milling anomalies that were subsequently simulated and used as a first step towards establishing the feasibility of employing machine learning as an integral component of the intelligent controller. We address the question of feasibility in two steps. First, it is important to know if the process models (dull tool, broken tool, etc.) can be learned (model learning). And second, if the models are learned, can an algorithm reliably select an appropriate model (distinguish between dull and broken tools) based on input from the model learner and from the sensors (model selection). The results of the simulation-based tests demonstrate that the milling-process anomalies can be learned, and the appropriate model can be reliably selected. Such a model can be subsequently utilized to make compensating in-process machine-tool adjustments. In addition, we observed that the learning curve need not approach the 100% level to be functional.

Key words

Machine learning reinforcement learning intelligent control machine tool tool monitoring metal cutting manufacturing 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Machining Data Handbook, Metcut Research Associates, Inc., Cincinnati, OH, 1980.Google Scholar
  2. 2.
    Workshop on Information Technology for Manufacturing and Concurrent Engineering, DARPA, Stanford University, Palo Alto, CA, 1992.Google Scholar
  3. 3.
    Altintas, Y. and Yellowley, I.: In-process detection of tool failure in milling using cutting force models,J. Eng. Industry 111 (1989) 149–157.Google Scholar
  4. 4.
    Antsaklis, P. J. and Passino, K. M.: Introduction to intelligent control systems with high degrees of autonomy, in K. M. Passino and P. J. Antsaklis, (eds),Introduction to Intelligent and Autonomous Control., Kluwer Academic Publishers, Dordrecht, 1992.Google Scholar
  5. 5.
    Diei, E. N. and Dornfeld, D. A.: Acoustic emission from the face milling process — the effets of process variables,J. Eng. Industry 109 (1987) 92–99.Google Scholar
  6. 6.
    Diei, E. N. and Dornfeld, D. A.: Acoustic emission sensing of tool wear in face milling,J. Eng. Industry 109 (1987) 234–240.Google Scholar
  7. 7.
    Fu, H. J., DeVor, R. E. and Kapoor, S. G.: Model for the prediction of the force system in face milling operations,J. Eng. Industry 106 (1984) 81–88.Google Scholar
  8. 8.
    Gamache, R. W. and McCabe, J. T.: A critical review of options for tool and workpiece sensing, Technical Report SE-89-01, Mechanical Technology, Inc., 1990.Google Scholar
  9. 9.
    Garcia, H. E., Ray, A. and Edwards, R. M.: Reconfigurable control of power plants using learning automata,IEEE Control Systems Magazine 11(1) (1991) 85–92.Google Scholar
  10. 10.
    Kaelbling, L. P.: Learning in embedded systems, Technical Report TR-90-04, Teleos Research, CA, 1990.Google Scholar
  11. 11.
    Koenigsberger, F.:Design Principles of Metal-Cutting Machine Tools, Macmillan, New York, 1964.Google Scholar
  12. 12.
    Kokar, M. M., Keshav, S. N., Gopalraman, S. and Lirov, Y.: Learning in semantic control, inProc. 27th Conf. Decision and Control, IEEE, 1988, pp. 1812–1817.Google Scholar
  13. 13.
    Kokar, M. M. and Reeves, J. J.: Qualitative monitoring of time-variant physical systems, inProc. 29th Conf. Decision and Control, IEEE, 1990, pp. 1504–1508.Google Scholar
  14. 14.
    Kokar, M. M. and Reveliotis, S. A.: Integrating qualitative and quantitative methods for model validation and monitoring, inProc. 1991 IEEE Int. Symp. Intelligent Control, 1991.Google Scholar
  15. 15.
    Kokar, M. M. and Reveliotis, S. A.: Learning to select a model in a changing world, inProc. 8th Int. Workshop Machine Learning, 1991, pp. 313–317.Google Scholar
  16. 16.
    Kokar, M. M. and Reveliotis, S. A.: Reinforcement learning: Architectures and algorithms,Int. J. Intelligent Systems (1992), pp. 875–894.Google Scholar
  17. 17.
    Kolarits, F. M. and DeVries, W. R.: Model of end milling for process controller simulation,J. Eng. Industry 113 (1991) 176–183.Google Scholar
  18. 18.
    Kuipers, B. J.: Qualitative simulation,Artificial Intelligence J. 29 (1986) 289–338.Google Scholar
  19. 19.
    Lauderbaugh, L. K. and Ulsoy, A. G.: Dynamic modeling for control of the milling process,J. Eng. Industry 110 (1988) 367–375.Google Scholar
  20. 20.
    Lauderbaugh, L. K. and Ulsoy, A. G.: Model reference adaptive force control in milling,J. Eng. Industry 111 (1989) 13–21.Google Scholar
  21. 21.
    Meystel, A.: Intelligent control, inEncyclopedia of Physical Science and Technology, 1989 Yearbook, pp. 343–359, Academic Press, New York, 1989.Google Scholar
  22. 22.
    Montgomery, D. and Altintas, Y.: Mechanism of cutting force and surface generation in dynamic milling,J. Eng. Industry 113 (1991) 160–168.Google Scholar
  23. 23.
    Moriwaki, T. and Tobito, M.: A new approach to automatic detection of life of coated tool based on acoustic emission measurements,J. Eng. Industry 112 (1990) 212–218.Google Scholar
  24. 24.
    Narendra, K. S. and Thathachar, M. A. L.:Learning Automata: An Introduction, Prentice-Hall, 1989.Google Scholar
  25. 25.
    Osuri, R. H., Chatterjee, S. and Chandrashekhar, S.: On-line condition monitoring of tool wear in end using acoustic emission,Int. J. Production Res. 29 (1991) 1339–1353.Google Scholar
  26. 26.
    Rangwala, S. and Dornfeld, D.: Sensor integration using neural networks for intelligent tool condition monitoring,J. Eng. Industry 112 (1990) 219–228.Google Scholar
  27. 27.
    Smith, S. and Tlusty, J.: An overview of modeling and simulation of the milling process,J. Eng. Industry 113 (1991) 169–175.Google Scholar
  28. 28.
    Saridis, G. N.: Intelligent robotic control,IEEE Trans. Automatic Control AC-28(5) (1983) 547–557.Google Scholar
  29. 29.
    Stephanou, H. E., Meystel, A. and Luh, J. Y. S.: Intelligent control: From perception to action, inProc. IEEE Int. Symp. Intelligent Control, 1988.Google Scholar
  30. 30.
    Tlusty, J. and Andrews, G. C.: A critical review of sensors for unmanned machining,Ann. CIRP,32(2) (1983) 563–572.Google Scholar
  31. 31.
    Wright, P. K. and Bourne, D. A.,Manufacturing Intelligence, Addison-Wesley, Reading, MA, 1988.Google Scholar
  32. 32.
    Wright, P. K. and Greenfeld, I.: Open-architecture manufacturing — the impact of open systems, Technical Report, NYU, Courant Institute of Mathematical Sciences, NYC, NY, 1989.Google Scholar

Copyright information

© Kluwer Academic Publishers 1995

Authors and Affiliations

  • Mieczyslaw M. Kokar
    • 1
  • Jerzy Letkowski
    • 2
  • Thomas F. Callahan
    • 3
  1. 1.Department of Industrial EngineeringNortheastern UniversityBostonUSA
  2. 2.Western New England CollegeUSA
  3. 3.University Research Engineers and AssociatesUSA

Personalised recommendations