Skip to main content
Log in

Enhancing Clustering Algorithm with Initial Centroids in Tool Wear Region Recognition

  • Regular Paper
  • Published:
International Journal of Precision Engineering and Manufacturing Aims and scope Submit manuscript

Abstract

Autonomous manufacturing allows the system to distinguish between a mild, normal and total failure in tool condition. K-means clustering has become the most applied algorithm in discovering classes in an unsupervised scenario. Nevertheless, the algorithm is sensitive to the initial centroids giving various solution every time the system updating. Regular unsupervised K-means is refocused as semi-supervised Fixum K-means. It is embedded with a new tactic to recapture the K value and new initial seedings computation to kick off the system until it converges. Force components of cutting force \({F}_{c}\), thrust force \({F}_{t}\) and perpendicular cutting force \({F}_{cn}\) were extracted from Neo-MoMac cutting force measurement device. The analysis threshold represents a natural-sorted input vector as Z-rot coefficient (RZ) corresponds to the number of cutting accomplish a strong correlation (R2 = 0.8511) over wear evolution. The clustering system adopted a new calculation of initial centroids has successfully determined the three regions for only a single assignment and achieving the optimal distance squared through eight given data sets. It is conflicting with the standard K-means that return different clustering structure in each run, while K-means +  + replicates several times to achieve minimum objective function. During the course, F-Km delivered robust and consistence clustering results of 85% accuracy over standard K-means and four times converges faster than K-means +  + . The silhouette value average score is 0.8504 (highest score is 0.9207) of how well-distributed the resulting clusters. The clustering system has identified the tool to stop cutting at approximate VB = 0.213 mm before the tool condition enters the failure region of abnormal phase (VB < 0.250 mm).s The proposed system functioned effectively in clustering the data obtained from cutting tests performed within a reasonable range of wear stages. Precision and robustness analysis have proved F-km to score 100% attainment for clustering assignment output and replicability. In contrast, K-means scored 76.3% for precision and ranging from 5 to 33% for robustness. Whereas, K-means +  + scored 33% for robustness and a higher chance of time complexity compared to F-km. F-Km is found to be more accurate, time savvy and robust than standard K-means and K-means +  + . Therefore, the method can be reliably used for observing tool wear state recognition without training and equivocate traditional direct tool wear.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16

Similar content being viewed by others

Abbreviations

Asgmt :

Assignment

CS :

Clustering structure

D i :

Delta Total of Sum Distance

\(\overline{D}\) :

Average difference of Total of Sum Distance

Exp :

Experiment

F-km :

Fixum K-means

F c :

Main cutting force

F cn :

Perpendicular cutting force

F t :

Thrust force

h :

Cluster / partition number

K :

Number of clusters

K r :

Kurtosis

M 1,h :

Initial Centroids set 1

M 2,h :

Initial Centroids set 2

R 2 :

Coefficient of determination

R Z :

Z-rot coefficient

STP :

Second transition point

SV :

Silhouette value

TCM :

Tool condition monitoring

Temp :

Temperature

TSD :

Total of Sum Distance

VB :

Flank wear measurement

\({\stackrel{-}{x}}_{1, h}^{(0)}\) :

Initial centroid for particular cluster of set 1

\({\stackrel{-}{x}}_{2, h}^{(0)}\) :

Initial centroid for particular cluster of set 2

X h :

Cluster number h

Z-rot :

Tracking method

σ :

Standard deviation

References

  1. Painuli, S., Elangovan, M., & Sugumaran, V. (2014). Tool condition monitoring using K-star algorithm. Expert Systems with Applications, 41(6), 2638–2643. https://doi.org/10.1016/j.eswa.2013.11.005.

    Article  Google Scholar 

  2. Yang, X. (2010). Wear state recognition of drills based on K-means cluster and radial basis function neural network. International Journal of Automation and Computing, 7(3), 271–276. https://doi.org/10.1007/s11633-010-0502-z.

    Article  Google Scholar 

  3. Torabi, A. J., Er, M. J., Li, X., Lim, B. S., & Peen, G. O. (2016). Application of clustering methods for online tool condition monitoring and fault diagnosis in high-speed milling processes. IEEE Systems Journal, 10(2), 721–732. https://doi.org/10.1109/JSYST.2015.2425793.

    Article  Google Scholar 

  4. Li, Z., Wang, G., & He, G. (2017). Milling tool wear state recognition based on partitioning around medoids (PAM) clustering. International Journal of Advanced Manufacturing Technology, 88(5), 1203–1213. https://doi.org/10.1007/s00170-016-8848-1.

    Article  Google Scholar 

  5. Nazeer, K. A. & Sebastian, M. (2009) “Improving the accuracy and efficiency of the k-means clustering algorithm,” Proceedings of The World Congress on Engineering 2009, pp. 308–312.

  6. Nazeer, K. A., Kumar, S. M., & Sebastian, M. (2011) “Enhancing the K-means Clustering Algorithm by Using a O (n logn) Heuristic Method for Finding Better Initial Centroids,” in Emerging applications of information technology, international conference on (EAIT), vol. 00, pp. 261–264, doi: https://doi.org/10.1109/EAIT.2011.57.

  7. Mahmud, M. S., Rahman. M. M., & Akhtar. M. N., (2012) “Improvement of K-means clustering algorithm with better initial centroids based on weighted average,” in 7th International Conference on Electrical and Computer Engineering, 2012, pp. 647–650, doi: https://doi.org/10.1109/ICECE.2012.6471633.

  8. Xie, J., & Jiang, S. (2010) “A Simple and Fast Algorithm for Global K-means Clustering,” in 2010 Second International Workshop on Education Technology and Computer Science, vol. 2, pp. 36–40, doi: https://doi.org/10.1109/ETCS.2010.347.

  9. Min, Z., & Kai-fei, D. (2015). “Improved Research to K-means Initial Cluster Centers”, in. Ninth International Conference on Frontier of Computer Science and Technology, 2015, 349–353. https://doi.org/10.1109/FCST.2015.61.

    Article  Google Scholar 

  10. R. Dash, De. Mishra, A. K. Rath, and M. Acharya, “A hybridized K-means clustering approach for high dimensional dataset,” International Journal of Engineering Science Technology, vol. 2, pp. 59–66, 2010.

  11. Ismail, M. A., & Kamel, M. S. (1989). Multidimensional data clustering utilizing hybrid search strategies. Pattern Recognition, 22(1), 75–89. https://doi.org/10.1016/0031-3203(89)90040-X.

    Article  MathSciNet  MATH  Google Scholar 

  12. Park, J.-K., Kwon, B.-K., Park, J.-H., & Kang, D.-J. (2016). Machine learning-based imaging system for surface defect inspection. International Journal Precise Engineering Manufacturing Technology, 3(3), 303–310. https://doi.org/10.1007/s40684-016-0039-x.

    Article  Google Scholar 

  13. Kasim, N. A., Nuawi, M., Ghani, J., Rizal, M., Ahmad, M. A. F., & Haron, C. (2019). Cutting tool wear progression index via signal element variance. Journal Mechanical Engineering Science, 13, 4596–4612. https://doi.org/10.15282/jmes.13.1.2019.17.0387_rfseq1.

    Article  Google Scholar 

  14. Nuawi, Z. M., Lamin, F., Nor, M. J. M., Jamaluddin, N., Abdullah, S., & Nizwan, C. K. E. (2007). Integration of I-kaz coefficient and taylor tool life curve for tool wear progression monitoring in machining process. Internaional Journal of Mechanics, 1(4), 44–50.

    Google Scholar 

  15. Choi, E., & Kim, J. (2020). Deep learning based defect inspection using the intersection over minimum between search and abnormal regions. International Journal of Precision Engineering and Manufacuring, 21(4), 747–758. https://doi.org/10.1007/s12541-019-00269-9.

    Article  Google Scholar 

  16. Chadha, A., & Kumar, S. (2014). “An improved K-Means clustering algorithm: A step forward for removal of dependency on K”, in. International Conference on Reliability Optimization and Information Technology (ICROIT), 2014, 136–140. https://doi.org/10.1109/ICROIT.2014.6798312.

    Article  Google Scholar 

  17. Rizal, M., Ghani, J. A., Nuawi, M. Z., & Haron, C. H. C. (2018). An embedded multi-sensor system on the rotating dynamometer for real-time condition monitoring in milling. International Journal of Advanced Manufacturing Technology, 95(1), 811–823. https://doi.org/10.1007/s00170-017-1251-8.

    Article  Google Scholar 

  18. Stoić, A., Kopač, J., & Cukor, G. (2005). Testing of machinability of mould steel 40CrMnMo7 using genetic algorithm. Journal of Materials Processing Technology, 164, 1624–1630. https://doi.org/10.1016/j.jmatprotec.2005.01.013.

    Article  Google Scholar 

  19. Rizal, M., Ghani, J. A., Nuawi, M. Z., & Cheharon, C. H. (2015). Development and testing of an integrated rotating dynamometer on tool holder for milling process. Mechanical Systems and Signal Processing, 52–53, 559–576. https://doi.org/10.1016/j.ymssp.2014.07.017.

    Article  Google Scholar 

  20. Rizal, M., Ghani, J. A., Nuawi, M. Z., & Haron, C. H. C. (2017). Cutting tool wear classification and detection using multi-sensor signals and Mahalanobis-Taguchi system. Wear, 376–377, 1759–1765. https://doi.org/10.1016/j.wear.2017.02.017.

    Article  Google Scholar 

  21. Tiwari, K., Shaik, A., & Arunachalam, N. (2018). Tool wear prediction in end milling of Ti-6Al-4V through Kalman filter based fusion of texture features and cutting forces. Procedia Manufacturing, 26, 1459–1470. https://doi.org/10.1016/j.promfg.2018.07.095.

    Article  Google Scholar 

  22. Kapoor, A., & Singhal, A. (2017) “A comparative study of K-Means, K-Means++ and Fuzzy C-Means clustering algorithms,” in 3rd International conference on computational intelligence communication technology (CICT), 2017, pp. 1–6, doi: https://doi.org/10.1109/CIACT.2017.7977272.

  23. Kaufman, L., & Rousseeuw, P. J. (2009). Finding Groups in Data: An Introduction to Cluster Analysis. New Jersey: John Wiley & Sons.

    MATH  Google Scholar 

  24. Scheffer, C., & Heyns, P. S. (2004). An industrial tool wear monitoring system for interrupted turning. Mechanical Systems and Signal Processing, 18(5), 1219–1242. https://doi.org/10.1016/j.ymssp.2003.09.001.

    Article  Google Scholar 

  25. Zhu, K., Wong, Y. S., & Hong, G. S. (2009). Multi-category micro-milling tool wear monitoring with continuous hidden Markov models. Mechanical Systems and Signal Processing, 23(2), 547–560. https://doi.org/10.1016/j.ymssp.2008.04.010.

    Article  Google Scholar 

  26. Wang, G., Qian, L., & Guo, Z. (2013). Continuous tool wear prediction based on Gaussian mixture regression model. International Journal of Advanced Manufacturing Technology, 66(9), 1921–1929. https://doi.org/10.1007/s00170-012-4470-z.

    Article  Google Scholar 

  27. Cho, S., Binsaeid, S., & Asfour, S. (2010). Design of multisensor fusion-based tool condition monitoring system in end milling. International Journal of Advanced Manufacturing Technology, 46(5), 681–694. https://doi.org/10.1007/s00170-009-2110-z.

    Article  Google Scholar 

  28. Ji, W., Shi, J., Liu, X., Wang, L., & Liang, S. Y. (2017). A novel approach of tool wear evaluation. Journal Manufacturing Science and Engineering. https://doi.org/10.1115/14037231.

    Article  Google Scholar 

  29. Taga, Ö., Kiral, Z., & Yaman, K. (2016). Determination of cutting parameters in end milling operation based on the optical surface roughness measurement. International Journal of Precision Engineering Manufacturing, 17(5), 579–589. https://doi.org/10.1007/s12541-016-0070-4.

    Article  Google Scholar 

  30. Yang, Y., et al. (2020). A Novel Tool (Single-Flute) Condition Monitoring Method for End Milling Process Based on Intelligent Processing of Milling Force Data by Machine Learning Algorithms. International Journal of Precision Engineering Manufacturing, 21(11), 2159–2171. https://doi.org/10.1007/s12541-020-00388-8.

    Article  Google Scholar 

  31. Schulze, V., Becke, C., Weidenmann, K., & Dietrich, S. (2011). Machining strategies for hole making in composites with minimal workpiece damage by directing the process forces inwards. Journal of Materials Processing Technology, 211(3), 329–338. https://doi.org/10.1016/j.jmatprotec.2010.10.004.

    Article  Google Scholar 

  32. Kuljanic, E., & Sortino, M. (2005). TWEM, a method based on cutting forces—monitoring tool wear in face milling. International Journal of Machine Tools and Manufacture, 45(1), 29–34. https://doi.org/10.1016/j.ijmachtools.2004.06.016.

    Article  Google Scholar 

  33. Subramanian, M., Sakthivel, M., Sooryaprakash, K., & Sudhakaran, R. (2013). Optimization of end mill tool geometry parameters for Al7075-T6 machining operations based on vibration amplitude by response surface methodology. Measurement, 46(10), 4005–4022. https://doi.org/10.1016/j.measurement.2013.08.015.

    Article  Google Scholar 

  34. Lauro, C. H., Brandão, L. C., Baldo, D., Reis, R. A., & Davim, J. P. (2014). Monitoring and processing signal applied in machining processes-A review. Measurement, 58, 73–86. https://doi.org/10.1016/j.measurement.2014.08.035.

    Article  Google Scholar 

  35. Wang, G., Yang, Y., Xie, Q., & Zhang, Y. (2014). Force based tool wear monitoring system for milling process based on relevance vector machine. Advances in Engineering Software, 71, 46–51. https://doi.org/10.1016/j.advengsoft.2014.02.002.

    Article  Google Scholar 

  36. Segreto, T., Simeone, A., & Teti, R. (2014). Principal component analysis for feature extraction and NN pattern recognition in sensor monitoring of chip form during turning. CIRP Journal Manufacturing Science Technology, 7(3), 202–209. https://doi.org/10.1016/j.cirpj.2014.04.005.

    Article  Google Scholar 

  37. Kasim, M. S., Che Haron, C. H., Ghani, J. A., Sulaiman, M. A., & Yazid, M. Z. A. (2013). Wear mechanism and notch wear location prediction model in ball nose end milling of Inconel 718. Wear, 302(1), 1171–1179. https://doi.org/10.1016/j.wear.2012.12.040.

    Article  Google Scholar 

  38. Ambhore, N., Kamble, D., Chinchanikar, S., & Wayal, V. (2015). Tool Condition Monitoring System: A Review. Material Today Proceeding, 2(4–5), 3419–3428. https://doi.org/10.1016/j.matpr.2015.07.317.

    Article  Google Scholar 

  39. Chuangwen, X., Jianming, D., Yuzhen, C., Huaiyuan, L., Zhicheng, S., & Jing, X. (2018). The relationships between cutting parameters, tool wear, cutting force and vibration. Advance Mechanical Engineering, 10(1), 1–14. https://doi.org/10.1177/1687814017750434.

    Article  Google Scholar 

  40. Fan, H., Keer, L. M., Cheng, W., & Cheng, H. S. (1993). Competition Between Fatigue Crack Propagation and Wear. Journal of Tribology, 115(1), 141–147.

    Article  Google Scholar 

  41. Nelwamondo, F., Marwala, T., & Mahola, U. (2006). Early classifications of bearing faults using hidden Markov models, Gaussian mixture models, Mel-frequency cepstral coefficients and fractals. International Journal of Innovation Computer Information Control, 2, 1281–1299.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to N. A. Kasim.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kasim, N.A., Nuawi, M.Z., Ghani, J.A. et al. Enhancing Clustering Algorithm with Initial Centroids in Tool Wear Region Recognition. Int. J. Precis. Eng. Manuf. 22, 843–863 (2021). https://doi.org/10.1007/s12541-020-00450-5

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12541-020-00450-5

Keywords

Navigation