Machine learning induction of a model for online parameter selection in EDM rough machining

  • Joško Valentinčič
  • Bogdan Filipič
  • Mihael Junkar
ORIGINAL ARTICLE

Abstract

In electrical discharge machining (EDM), appropriate average current in the gap has to be selected for the given machining surface in order to obtain the highest material removal rate at low electrode wear. Thus, rough machining parameters have to be selected according to the machining surface. In the case of sculptured features, the machining surface varies with the depth of machining. Hence, the machining parameters have to be selected on-line to obtain appropriate current density in the gap. In this paper, inductive machine learning is used to derive a model based on the voltage and current in the gap. The sufficient inputs to the model are only two discharge attributes extracted from the voltage signal in the gap. The model successfully selects between two machining parameter settings that obtain different average surface current in the gap. It requires only voltage signal acquisition during the machining process and a simple algorithm that is easy to implement on industrial machines.

Keywords

Electrical discharge machining EDM Rough machining Parameter selection Process attributes Artificial intelligence 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Albinski M, Liebeskind A (1980) Characteristics of the process of electrical discharge machining. In: Proceedings of the 6th international symposium for electromachining (ISEM 6), Krakow, Poland, pp 88–96Google Scholar
  2. 2.
    Assadi HA, Wong SV, Hamouda A, Ahmad MM (2004) Development of machine learning strategy for acquiring on-line machining skills during turning process. J Mater Process Technol 155–156:2087–2092CrossRefGoogle Scholar
  3. 3.
    Canz T, Jagdale S (1995) Decision support for manufacturing using artificial neural-networks. J Mater Process Technol 52(1):9–26CrossRefGoogle Scholar
  4. 4.
    Cho S, Asfour S, Onar A, Kaundinya N (2005) Tool breakage detection using support vector machine learning in a milling process. Int J Mach Tools Manuf 45(3):241–249CrossRefGoogle Scholar
  5. 5.
    Dauw D (1983) Advanced pulse discriminating system for EDM process analysis and control. Ann CIRP 32(1):541–539Google Scholar
  6. 6.
    Dehmer J (1992) Prozeßführung beim funkenerosiven Senken durch adaptive Spaltweitenregelung und Steuerung der Erosionsimpulse. In: Fortscritt–Berichte VDI Reihe 2, no. 224 in WZL Produktionstechnik, VDI Verlag, DüsseldorfGoogle Scholar
  7. 7.
    DiBitonto D, Eubank P, Patel M, Barrufet M (1989) Theoretical models of the electrical discharge machining process. I. A simple cathode erosion model. J Appl Phys 66(9):4095–4103CrossRefGoogle Scholar
  8. 8.
    Filipič B, Junkar M (2000) Using inductive machine learning to support decision-making in machining processes. Comput Ind 43(1):31–41CrossRefGoogle Scholar
  9. 9.
    Garbajs V (1985) Statistical model for an adaptive control of EDM–process. Ann CIRP 34(1):499–502Google Scholar
  10. 10.
    IH Witten EF, Kaufmann M (2000) Data mining: practical machine learning tools with Java implementations. San FranciscoGoogle Scholar
  11. 11.
    Itoh T (1994) EDM apparatus current efficiency technique. US Patent 5,276,302Google Scholar
  12. 12.
    Itoh T (1994) Method and apparatus for sink-type electrical discharge machining with control of pyrographite bildup. US Patent 3,369,239Google Scholar
  13. 13.
    Junkar M, Filipič B, Bratko I (1991) Identifying the grinding process by means of inductive machine learning. Comput Ind 17(2/3):147–153CrossRefGoogle Scholar
  14. 14.
    Junkar M, Valentinčič J, Lebar A (1996) Enotni dogodek kot osnovni element obdelane povrine. Mednarodna konferenca o tribologiji SLOTRIB’96, Slovensko drutvo za tribologijo, LjubljanaGoogle Scholar
  15. 15.
    Kohavi R (1995) A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Proceedings of the 14th international joint conference on artificial intelligence, Montreal, Canada, p 1137Google Scholar
  16. 16.
    Kruth J, Lauwers B, Clappaert W (1992) A study of EDM pocketing. In: Proceedings of the 10th international symposium for electromachining (ISEM 10), Magdeburg, pp 121–135Google Scholar
  17. 17.
    Kyoshi I (1982) Feeder for electrical discharge machining. Patent JP 57138544 AGoogle Scholar
  18. 18.
    Liao Y, Yan M, Chang C (2002) A neural network approach for the on-line estimation of workpiece height in WEDM. J Mater Process Technol 121(2–3):252–258CrossRefGoogle Scholar
  19. 19.
    Patel M, Barrufet M, Eubank P, DiBitonto D (1989) Theoretical models of the electrical discharge machining process. II. A simple anode erosion model. J Appl Phys 66(9):4104–4111CrossRefGoogle Scholar
  20. 20.
    Pham D, Dimov S, Bigot S, Ivanov A, Popov K (2004) Micro EDM: recent developments and research issues. In: Proceedings of the 14th CIRP international symposium for electromachining (ISEM 14), Edinburgh, UK, pp 50–57Google Scholar
  21. 21.
    Rajurkar K, Wang W, McGeough J (1994) WEDM identification and adaptive control for variable height components. Ann CIRP 43(1):199–202Google Scholar
  22. 22.
    Rajurkar K, Wang W, Zhao W (1997) WEDM adaptive control with a multiple input model for identification of workpiece height. Ann CIRP 46(1):147–150Google Scholar
  23. 23.
    Schulze H, Wollenberg G, Steinmetz G (1998) Stability of the EDM-sinking process. In: Proceedings of the 12th international symposium for electromachining (ISEM 12), VDI-Verlag, Düsseldorf, pp 215–223Google Scholar
  24. 24.
    Schulze H, Wollenberg G, Luter M (2000) Face measuring systems for parameter control of electrical discharge machining. In: Proceedings of the 2nd international conference on machining and measurement of sculptured surfaces, Krakow, pp 295–304Google Scholar
  25. 25.
    Tarng Y, Tseng C, Chung L (1997) A fuzzy pulse discriminating system for electrical discharge machining. Int J Mach Tools Manuf 37(4):511–522CrossRefGoogle Scholar
  26. 26.
    Valentinčič J (2003) A model of EDM process parameter selection upon the size of eroding surface. PhD thesis, University of Ljubljana, Faculty of Mechanical Engineering (in Slovene)Google Scholar
  27. 27.
    Valentinčič J, Junkar M (2004) A model for detection of the eroding surface based on discharge parameters. Int J Mach Tools Manuf 44(2–3):175–181CrossRefGoogle Scholar
  28. 28.
    Valentinčič J, Junkar M (2004) On-line selection of rough machining parameters. J Mater Process Technol 149(1/3):256–262CrossRefGoogle Scholar
  29. 29.
    Valentinčič J, Junkar M (2006) Detection of the eroding surface in the EDM process based on the current signal in the gap. Int J Adv Manuf Technol 26(3–4):294–301CrossRefGoogle Scholar
  30. 30.
    Valentinčič J, Kušer D, Smrkolj S, Blatnik O, Junkar M (2007) Machining parameters selection for varying surface in EDM. Int J Mater Prod Technol 29(1,2,3,4)Google Scholar
  31. 31.
    Weck M, Dehmer J (1992) Analysis and adaptive control of EDM sinking process using the ignition delay time and fall time as parameter. Ann CIRP 41(1):243–246Google Scholar
  32. 32.
    Wollenberg G, Schulze H, Grisch A (1996) On–line determination of the working area on sinking EDM. In: EDM technology, EDM technology transfer, pp 7–13Google Scholar

Copyright information

© Springer-Verlag London Limited 2008

Authors and Affiliations

  • Joško Valentinčič
    • 1
  • Bogdan Filipič
    • 2
  • Mihael Junkar
    • 1
  1. 1.Faculty of Mechanical EngineeringUniversity of LjubljanaLjubljanaSlovenia
  2. 2.Department of Intelligent SystemsJožef Stefan InstituteLjubljanaSlovenia

Personalised recommendations