Advertisement

Milling tool wear state recognition based on partitioning around medoids (PAM) clustering

  • Zhimeng Li
  • Guofeng WangEmail author
  • Gaiyun He
ORIGINAL ARTICLE

Abstract

This paper presents a partitioning around medoid (PAM)-based novel method to realize the recognition of the tool wear state in milling. In PAM, the representative objects called medoids are used to define clusters and average dissimilarities are applied to assess the medoids, which make PAM robust to outliers and therefore improve the clustering performance. Meanwhile, locality preserving projections (LPP) method is utilized to further increase the clustering accuracy by dimension reduction. To show the effectiveness of the proposed method, end milling experiment of Ti-6Al-4V alloy were carried out and the commonly used k-means and fuzzy c-means (FCM) algorithm are introduced to make a comparison with PAM algorithm by using five clustering evaluation indicators. The results show that PAM performs higher accuracy and robustness than the other two clustering algorithm.

Keywords

Partitioning around medoids Locality preserving projections Tool wear state recognition Clustering diagnosis 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Li XL (2002) A brief review: acoustic emission method for tool wear monitoring during turning. Int J Mach Tool Manuf 42(2):157–165CrossRefGoogle Scholar
  2. 2.
    Siddhpura A, Paurobally R (2013) A review of flank wear prediction methods for tool condition monitoring in a turning process. Int J Adv Manuf Technol 65:371–393CrossRefGoogle Scholar
  3. 3.
    Sick B (2002) On-line and indirect tool wear monitoring in turning with artificial neural networks: a review of more than a decade of research. Mech Syst Signal Process 16(4):487–546CrossRefGoogle Scholar
  4. 4.
    Dimla E Dimla Snr (2000) Sensor signals for tool-wear monitoring in metal cutting operations—a review of methods. Int J Mach Tool Manuf 40(8):1073–1098Google Scholar
  5. 5.
    Rehorn AG, Jiang J, Orban PE (2005) State-of-the-art methods and results in tool condition monitoring: a review. Int J Adv Manuf Tech 26(7):693–710CrossRefGoogle Scholar
  6. 6.
    Zhu KP, Wong YS, Hong GS (2009) Wavelet analysis of sensor signals for tool condition monitoring: a review and some new results. Int J Mach Tool Manuf 49(7–8):537–553CrossRefGoogle Scholar
  7. 7.
    Gaja H, Liou F (2016) Automatic detection of depth of cut during end milling operation using acoustic emission sensor. Int J Adv Manuf Technol. doi: 10.1007/s00170-016-8395-9 Google Scholar
  8. 8.
    Godfrey CO, Petr B, Frank L (2008) Modeling tool wear in end-milling using enhanced GMDH learning networks. Int J Adv Manuf Technol 39:1080–1092CrossRefGoogle Scholar
  9. 9.
    García-Nieto PJ, García-Gonzalo E, Vilán Vilán JA, Segade Robleda A (2015) A new predictive model based on the PSO-optimized support vector machine approach for predicting the milling tool wear from milling runs experimental data. Int J Adv Manuf Technol. doi: 10.1007/s00170-015-8148-1 zbMATHGoogle Scholar
  10. 10.
    Cho S, Binsaeid S, Asfour S (2010) Design of multisensor fusion-based tool condition monitoring system in end milling. Int J Adv Manuf Technol 46:681–694CrossRefGoogle Scholar
  11. 11.
    Wang GF, Liu C, Cui YH (2012) Clustering diagnosis of rolling element bearing fault based on integrated autoregressive/autoregressive conditional heteroscedasticity model. J Sound Vib 331:4379–4387CrossRefGoogle Scholar
  12. 12.
    Hu D, Sarosh A, Dong YF (2012) A novel KFCM based fault diagnosis method for unknown faults in satellite reaction wheels. ISA Trans 51:309–316CrossRefGoogle Scholar
  13. 13.
    Yuwono M, Qin Y, Zhou J, Guo Y, Celler BG, Su SW (2015) Automatic bearing fault diagnosis using particle swarm clustering and Hidden Markov Model. Eng Appl Artif Intell. doi: 10.1016/j.engappai.2015.03.007 Google Scholar
  14. 14.
    Baraldi P, Maio FD, Rigamonti M, Zio E, Seraoui R (2015) Clustering for unsupervised fault diagnosis in nuclear turbine shut-down transients. Mech Syst Signal Process 58–59:160–178CrossRefGoogle Scholar
  15. 15.
    Wang G, Yin S (2014) Data-driven fault diagnosis for an automobile suspension system by using a clustering based method. J Franklin Inst 351:3231–3244MathSciNetCrossRefzbMATHGoogle Scholar
  16. 16.
    Liu WY, Wang ZF, Han JG, Wang GF (2013) Wind turbine fault diagnosis method based on diagonal spectrum and clustering binary tree SVM. Renew Energy 50:1–6CrossRefGoogle Scholar
  17. 17.
    Zhou JH, Pang CK, Zhong ZW, Lewis FL (2011) Tool wear monitoring using acoustic emissions by dominant-feature identification. IEEE Trans Instrum Meas 60(2):547–559CrossRefGoogle Scholar
  18. 18.
    Jipkate BR, Gohokar VV (2012) A comparative analysis of fuzzy C-means clustering and K means clustering algorithms. IJCER 2(3):737–739Google Scholar
  19. 19.
    Li XL, Yuan ZJ (1998) Tool wear monitoring with wavelet packet transform-fuzzy clustering method. Wear 219(2):145–154CrossRefGoogle Scholar
  20. 20.
    Fu P, Yi WL, Guo L (2011) Fuzzy clustering and visualization analysis of tool wear status recognition. PEEA 23:479–486Google Scholar
  21. 21.
    Li WL, Fu P, Zhang EQ (2013) Application of fractal dimensions and fuzzy clustering to tool wear monitoring. TELKOMNIKA 11(1):187–194Google Scholar
  22. 22.
    Simeone A, Woolley EB, Rahimifard S (2015) Tool state assessment for reduction of life cycle environmental impacts of aluminium machining processes via infrared temperature monitoring. Procedia CIRP 29:526–531CrossRefGoogle Scholar
  23. 23.
    Kaufman L, Rousseeuw PJ (1990) Finding groups in data: an introduction to cluster analysis. Wiley-Interscience, AmericaCrossRefzbMATHGoogle Scholar
  24. 24.
    Bhattacharyya P, Sengupta D, Mukhopadhyay S (2007) Cutting force-based real-time estimation of tool wear in face milling using a combination of signal processing techniques. Mech Syst Signal Process 21:2665–2683CrossRefGoogle Scholar
  25. 25.
    Aknouche H, Outahyon A, Nouveau C, Marchal R, Zerizer A, Butaud JC (2009) Tool wear effect on cutting forces: in routing process of Aleppo pine wood. J Mater Process Technol 209:2918–2922CrossRefGoogle Scholar
  26. 26.
    Rizala M, Ghania JA, Nuawia M, Che Haron CH (2013) The application of I-kazTM-based method for tool wear monitoring using cutting force signal. MITC2013 68:461–468Google Scholar
  27. 27.
    Abu-Mahfouz I, Banerjee A (2014) Drill wear feature identification under varying cutting conditions using vibration and cutting force signals and data mining techniques. Procedia Comput Sci 36:556–563CrossRefGoogle Scholar
  28. 28.
    He XF, Niyogi P (2003) Locality preserving projections. In: Thrun S, Saul LK, Schölkopf B (ed) Advances in Neural Information Processing Systems 16 (NIPS 2003). VancouverGoogle Scholar
  29. 29.
    Song MJ, Zhang L (2008) Comparison of cluster representations from partial second—to full fourth-order cross moments for data stream clustering, data mining. 2008 ICDM ‘08 143:560–569Google Scholar
  30. 30.
    Strehl A, Ghosh J (2002) Cluster ensembles—a knowledge reuse framework for combining multiple partitions. J Mach Learn Res 3:583–617MathSciNetzbMATHGoogle Scholar
  31. 31.
    Wu M, Schölkopf B, (2007) A local learning approach for clustering. In: Schölkopf B, Platt J, Hofmann T (ed) Advances in Neural Information Processing Systems 19 (NIPS 2006). VancouverGoogle Scholar
  32. 32.
    Aghabozorgi S, Shirkhorshidi AS, Wah TY (2015) Time-series clustering—a decade review. Inf Syst 53:16–38CrossRefGoogle Scholar
  33. 33.
    Liao TW (2005) Clustering of time series data—a survey. Pattern Recogn 38:1857–1874CrossRefzbMATHGoogle Scholar

Copyright information

© Springer-Verlag London 2016

Authors and Affiliations

  1. 1.Tianjin Key Laboratory of Equipment Design and Manufacturing TechnologyTianjin UniversityNankai DistrictChina

Personalised recommendations