Prognostics for drilling process with wavelet packet decomposition

  • Yinhui AoEmail author
  • George Qiao


On-line tool condition monitoring is highly needed in drilling production process. Input current has been employed to monitor the drilling tool wear by many researchers. But few cases can represent the wear status and recognize the breakage simultaneously. The remaining life of tool has not been discussed sufficiently. This paper presents a strategy of on-line tool monitoring system for drilling machine using wavelet packet decomposition of spindle current signature. A moving window technique is used to extract the real drilling parts of data from sampled data sequence. The wavelet packet decomposition is used to extract features from non-stationary current signal. Critical features are selected according to their ability of discriminating the wear progress under Fisher criterion. Logistic regression combined with autoregressive moving average models are used to evaluate the failure possibility and remaining life of the drill bit. Experimental results show good performance of the proposed algorithm.


Tool wear Wavelet packet decomposition Feature selection Prognostics 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Pechloff S (2003) Can you afford to ignore tool monitoring? Production machining. Gardner, CincinnatiGoogle Scholar
  2. 2.
    Goverkar E, Grabec I (1994) Self-organizing neural network application to drill wear classification. J Eng Ind 16(5):233–238CrossRefGoogle Scholar
  3. 3.
    Liu TI, Anantharaman KS (1994) Intelighent classification and measurement of drill wear. J Eng Ind 116(5):233–238Google Scholar
  4. 4.
    Isermann R, Ayoubi M (1993) Model based detection of tool wear and breakage for machine tools. Proceedings of the IEEE International Conference Sys. Man Cyber. IEEE, Piscataway, vol. 3, pp 72–77Google Scholar
  5. 5.
    Rehorn AG, Jin J, Orban PE (2005) State of the art methods and results in tool condition monitoring: a review. Int J Adv Manuf Technol 26:693–710CrossRefGoogle Scholar
  6. 6.
    Jantunen E (2002) A summary of methods applied to tool condition monitoring in drilling. Int J Mach Tools Manuf 42:997–1010CrossRefGoogle Scholar
  7. 7.
    Lin SC, Ting CJ (1995) Tool wear monitoring in drilling using force signals. Wear 180(1–2):53–60CrossRefGoogle Scholar
  8. 8.
    Li X (1999) On-line detection of the breakage of small diameter drills using current signature wavelet transform. Int J Mach Tools Manuf 39(1):157–164CrossRefGoogle Scholar
  9. 9.
    Subramanian K, Cook NH (1977) Sensing of drill wear and prediction of drill life (I). Journal of Engineering for Industry Transactions of the ASME 101:295–301Google Scholar
  10. 10.
    Jantunen E, Jokinen H (1996) Automated on-line diagnosis of cutting tool condition (second version). Int J Flex Autom Integr Manuf 4(3–4):273–287Google Scholar
  11. 11.
    Alfonso LF, Ruiz GH, Vera RP, Troncoso JR, Tafo LW (2006) Sensorless tool failure monitoring system for drilling machines. Int J Mach Tools Manuf 46:381–386CrossRefGoogle Scholar
  12. 12.
    Mallat S (1989) A theory for multi-resolution signal decomposition: the wavelet representation. IEEE Pattern Anal Machine Intell 11(7):674–693zbMATHCrossRefGoogle Scholar
  13. 13.
    Fukunaga K (1992) Introduction to statistical pattern recognition. Academic, New YorkGoogle Scholar
  14. 14.
    Houston WM, Woodruff DJ (1997) Empirical Bayes estimates of parameters from the logistic regression model. ACT Research Report Series, JuneGoogle Scholar
  15. 15.
    Brockwell PJ, Davis RA (1990) Time series: theory and methods. Springer, HeidelbergGoogle Scholar
  16. 16.
    Quadro AL, Branco JRT (1997) Analysis of the acoustic emission during drilling test. Surf Coat Technol 94–95(1–3):691–695CrossRefGoogle Scholar
  17. 17.
    Donoho DL, Johnstone IM (1994) Ideal Spatial adaptation by wavelet shrinkage. Biometrika 81(3):425–455zbMATHCrossRefMathSciNetGoogle Scholar
  18. 18.
    Jin L, Zuo MJ, Fyfe KR (2004) Mechanical fault default detection based on the wavelet de-noising technique. J Vib 106:9–16Google Scholar

Copyright information

© Springer-Verlag London Limited 2010

Authors and Affiliations

  1. 1.School of Mechanical and Electrical EngineeringGuangdong University of TechnologyGuangzhouPeople’s Republic of China
  2. 2.Mechanical Engineering DepartmentUniversity of MichiganAnn ArborUSA

Personalised recommendations