Feature selection and a method to improve the performance of tool condition monitoring

  • Zhengyou Xie
  • Jianguang Li
  • Yong LuEmail author


Tool condition monitoring (TCM) is especially important in the modern machining process. In order to distinguish different tool wear states accurately and reduce the computation cost, it is of great significance to extract and select appropriate features that can reflect changes in tool wear states but are insensitive to cutting parameters. In this work, Fisher’s discriminant ratio (FDR) is adopted as the criterion for feature selection by evaluates every feature’s classification ability. However, it is found that the continuous hidden Markov models (CHMM) trained based on the features selected by the conventional method could recognize some tool state well, but have poor ability to classify other wear states. The reasons for this phenomenon have been analyzed, then a simple and effective method that used two feature sets for TCM has been proposed to improve the recognition performance. Four tests with different cutting parameters are carried out, and the new method has been implemented and verified its usefulness and validity.


Feature selection Fisher’s discriminant ratio Hidden Markov model Tool condition monitoring Cutting force Tool wear 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


Funding information

This work was supported by the National High Technology Research and Development Program of China (863 Program) under Grant No. 2013AA041107.


  1. 1.
    Teti R, Jemielniak K, O’Donnell G, Dornfeld D (2010) Advanced monitoring of machining operations. CIRP Ann Manuf Technol 59(2):717–739CrossRefGoogle Scholar
  2. 2.
    Kong D, Chen Y, Li N (2018) Gaussian process regression for tool wear prediction. Mech Syst Signal Process 104:556–574CrossRefGoogle Scholar
  3. 3.
    Liao Z, Gao D, Lu Y, Lv Z (2016) Multi-scale hybrid HMM for tool wear condition monitoring. Int J Adv Manuf Technol 84(9–12):2437–2448CrossRefGoogle Scholar
  4. 4.
    Sevilla-Camacho PY, Robles-Ocampo JB, Muñiz-Soria J, Lee-Orantes F (2015) Tool failure detection method for high-speed milling using vibration signal and reconfigurable bandpass digital filtering. Int J Adv Manuf Technol 81(5–8):1187–1194CrossRefGoogle Scholar
  5. 5.
    Wu H, Yu Z, Wang Y (2016) Real-time FDM machine condition monitoring and diagnosis based on acoustic emission and hidden semi-Markov model. Int J Adv Manuf Technol 1–10Google Scholar
  6. 6.
    Sevilla-Camacho PY, Herrera-Ruiz G, Robles-Ocampo JB, Jáuregui-Correa JC (2011) Tool breakage detection in CNC high-speed milling based in feed-motor current signals. Int J Adv Manuf Technol 53(9–12):1141–1148CrossRefGoogle Scholar
  7. 7.
    Yu J, Liang S, Tang D, Liu H (2016) A weighted hidden Markov model approach for continuous-state tool wear monitoring and tool life prediction. Int J Adv Manuf Technol 91(1–4):1–11Google Scholar
  8. 8.
    Zhang C, Yao X, Zhang J, Jin H (2016) Tool condition monitoring and remaining useful life prognostic based on a wireless sensor in dry milling operations. Sensors 16(6):795CrossRefGoogle Scholar
  9. 9.
    Scheffer C, Heyns PS (2004) An industrial tool wear monitoring system for interrupted turning. Mech Syst Signal Process 18(5):1219–1242CrossRefGoogle Scholar
  10. 10.
    Zhu KP, Hong GS, Wong YS (2008) A comparative study of feature selection for hidden Markov model-based micro-milling tool wear monitoring. Mach Sci Technol 12(3):348–369CrossRefGoogle Scholar
  11. 11.
    Geramifard O, Xu JX, Zhou JH, Li X (2012) Feature selection for tool wear monitoring: a comparative study. In: Industrial electronics and applications. p 1230–1235Google Scholar
  12. 12.
    Bhat NN, Dutta S, Pal SK, Pal S (2016) Tool condition classification in turning process using hidden Markov model based on texture analysis of machined surface images. Measurement 90:500–509CrossRefGoogle Scholar
  13. 13.
    Geramifard O, Xu JX, Zhou JH, Li X (2012) A physically segmented hidden Markov model approach for continuous tool condition monitoring: diagnostics and prognostics. IEEE Trans Ind Inf 8(4):964–973CrossRefGoogle Scholar
  14. 14.
    Zhu K, Hong GS, San WY (2011) Multiscale singularity analysis of cutting forces for micromilling tool-wear monitoring. IEEE Trans Ind Electron 58(6):2512–2521CrossRefGoogle Scholar
  15. 15.
    Xie Z, Lu Y, Li J (2017) Development and testing of an integrated smart tool holder for four-component cutting force measurement. Mech Syst Signal Process 93:225–240CrossRefGoogle Scholar
  16. 16.
    Organization IS (1989) Tool life testing in milling—Part 2: End milling. ISO 8688-2: 1989Google Scholar
  17. 17.
    Zhu K, Wong YS, Hong GS (2009) Wavelet analysis of sensor signals for tool condition monitoring: a review and some new results. Int J Mach Tool Manu 49(7):537–553CrossRefGoogle Scholar
  18. 18.
    Wang M, Wang J (2012) CHMM for tool condition monitoring and remaining useful life prediction. Int J Adv Manuf Technol 59(5–8):463–471CrossRefGoogle Scholar
  19. 19.
    Zhu K, Wong YS, Hong GS (2009) Multi-category micro-milling tool wear monitoring with continuous hidden Markov models. Mech Syst Signal Process 23(2):547–560CrossRefGoogle Scholar
  20. 20.
    Xie Z, Li J, Lu Y (2018) An integrated wireless vibration sensing tool holder for milling tool condition monitoring. Int J Adv Manuf Technol 95(5–8):2885–2896CrossRefGoogle Scholar
  21. 21.
    Rabiner LR (1990) A tutorial on hidden Markov models and selected applications in speech recognition, readings in speech recognition. Morgan Kaufmann, San Francisco, pp 267–296Google Scholar
  22. 22.
    Gao D, Liao Z, Lv Z, Lu Y (2015) Multi-scale statistical signal processing of cutting force in cutting tool condition monitoring. Int J Adv Manuf Technol 80(9–12):1843–1853CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2018

Authors and Affiliations

  1. 1.School of Mechatronics EngineeringHarbin Institute of TechnologyHarbinChina

Personalised recommendations