Journal of Failure Analysis and Prevention

, Volume 17, Issue 3, pp 602–619 | Cite as

An Optimized Clustering Approach Using Simulated Annealing Algorithm with HMM Coordination for Rolling Elements Bearings’ Diagnosis

  • Yinqiang Gao
  • Nan Xie
  • Kai Hu
  • Ying Zhu
  • Liang Wang
Technical Article---Peer-Reviewed


Nowadays applying condition-based maintenance technology for detecting the states of machines or components could be anticipated, when the diagnostic and prognostic algorithms are successfully introduced. In particular, for those enduring components like rolling bearings with relative long service life and complex states of development, such like sudden collapse caused by pitting, the diagnosis process is essential for identifying damages and by that way reducing unnecessary costs in many fields of manufacturing industry. This paper presents an improved approach to clarify the defect states of rolling bearings by using optimized clustering method. The simulated annealing k-means algorithm is proposed, which is used to remove isolated noising data points from the main distribution. In addition, of acquiring optimized assignments, and to predict the degradation by setting up hidden Markov model that carries out the diagnosis characteristics. Experiment reveals the correlation between the defect periods and the area of corrosion pits The results are presented to verify the efficiency and effectivity of the approach.


Diagnosis Clustering approach Simulated annealing k-means algorithm (SA-k-means) Degradation 



This work is partly supported by Natural Science Foundation of China (Grant No. 71471139) and Zhejiang Natural Science Foundation, China (Grant No. LY14E050020).


  1. 1.
    K. Javed, R. Gouriveau, N. Zerhouni, Enabling health monitoring approach based on vibration data for accurate prognostics. IEEE Trans. Ind. Electron. 61(1), 647–656 (2015)CrossRefGoogle Scholar
  2. 2.
    O. Ondel, E. Boutleux, E. Blanco, Coupling pattern recognition with state estimation using Kalman filter for fault diagnosis. IEEE Trans. Ind. Electron. 59(11), 4293–4300 (2012)CrossRefGoogle Scholar
  3. 3.
    P. Baruah, R.B. Chinnam, HMMs for diagnostics and prognostics in machining processes. Int. J. Prod. Res. 6(43), 1275–1293 (2004)Google Scholar
  4. 4.
    T. Ueda, K. Ueda, N. Mitamura, Unique fatigue failure of spherical roller bearings and life-enhancing measures, in Proceedings of WTC2005, World Tribology Congress III, 2015(9)Google Scholar
  5. 5.
    T. Ueda, N. Mitamura, Mechanism of dent initiated flaking and bearing life enhancement technology under contaminated lubrication condition. Part II: effect of rolling element surface roughness on flaking resulting from dents, and life enhancement technology of rolling bearings under contaminated lubrication condition. Tribol. Int. 12, 1832–1837 (2009)CrossRefGoogle Scholar
  6. 6.
    W.T. Becker, R.J. Shipley, ASM Handbook Volume 11: Failure Analysis and Prevention (ASM International, Ohio, 2002)Google Scholar
  7. 7.
    P.J. Blau, O. Ridge, ASM Handbook Volume 18: Friction, Lubrication, and Wear Technology (ASM International, Ohio, 1992)Google Scholar
  8. 8.
    Idriss El-Thalji, Erkki Jantunen, A descriptive model of wear evolution in rolling bearings. Eng. Fail. Anal. 10(45), 204–224 (2014)CrossRefGoogle Scholar
  9. 9.
    W. Guo, H. Cao, Z. He, L. Yang, Fatigue life analysis of rolling bearings based on quasistatic modeling. Shock Vib. 8 (2015). Article ID 982350Google Scholar
  10. 10.
    A.M. Khorasani, G. Littlefair, M. Goldberg, Time domain vibration signal processing on milling process for chattar detection. J. Mach. Form. Technol. 6, 45–64 (2014)Google Scholar
  11. 11.
    S.N. Sulaiman, N.A.M. Isa, Adaptive fuzzy-K-means clustering algorithm for image segmentation. IEEE Trans. Consum. Electron. 19(1), 2661–2668 (2010)CrossRefGoogle Scholar
  12. 12.
    B.S. Everitt, S. Landau, M. Leese, Cluster Analysis, 5th edn. (Wiley, New York, 2010)Google Scholar
  13. 13.
    T.J. Amin, E.M. Joo, X. Li, B.S. Lim, Sequential fuzzy clustering based dynamic fuzzy neural network for fault diagnosis and prognosis. Neurocomputing 196(6), 31–41 (2016)Google Scholar
  14. 14.
    Y. Ding, X. Fu, Kernel-based fuzzy c-means clustering algorithm based on genetic algorithm. Neurocomputing 5(188), 233–238 (2015)Google Scholar
  15. 15.
    A. Soualhi, H. Razik, G. Clerc, D.D. Doan, Prognosis of bearing failures using hidden Markov models and the adaptive neuro-fuzzy inference system. IEEE Trans. Ind. Electron. 61(6), 2864–2874 (2014)CrossRefGoogle Scholar
  16. 16.
    M. Yuwono, Y. Qin, J. Zhou, Y. Guo, B.G. Celler, S.W. Su, Automatic bearing fault diagnosis using particle swarm clustering and Hidden Markov Model. Eng. Appl. Artif. Intell. 47(1), 88–100 (2015)Google Scholar
  17. 17.
    S. Ntalampiras, Y. Soupionis, G. Giannopoulos, A fault diagnosis system for interdependent critical infrastructures based on HMMs. Reliab. Eng. Syst. Saf. 6(138), 73–81 (2015)CrossRefGoogle Scholar
  18. 18.
    H.M. Ertunc, K.A. Loparo, H. Ocak, Tool wear condition monitoring in drilling operations using hidden Markov models (HMMs). Int. J. Mach. Tools Manuf 9(41), 1363–1384 (2001)CrossRefGoogle Scholar
  19. 19.
    Q. Li, T. Zhao, L. Zhang, Mechanical fault diagnostics of onload tap changer within power transformers based on Hidden Markov Model. IEEE Trans. Power Deliv. 4(27), 596–601 (2012)CrossRefGoogle Scholar
  20. 20.
    S. Mahmoodpour, M. Masihi, An improved simulated annealing algorithm in fracture network modeling. J. Nat. Gas Sci. Eng. 7(33), 538–550 (2016)CrossRefGoogle Scholar
  21. 21.
    N.G. Nikolaou, I.A. Antoniadis, Rolling element bearing fault diagnosis using wavelet packets. NDT&E Int. 4(35), 197–205 (2002)CrossRefGoogle Scholar
  22. 22.
    F. Zhou, J. Park, Y. Liu, Differential feature based hierarchical PCA fault detection method for dynamic fault. Neurocomputing 8(202), 27–35 (2016)CrossRefGoogle Scholar

Copyright information

© ASM International 2017

Authors and Affiliations

  • Yinqiang Gao
    • 1
  • Nan Xie
    • 1
  • Kai Hu
    • 1
  • Ying Zhu
    • 1
  • Liang Wang
    • 1
  1. 1.Sino-German College of Applied ScienceTongji UniversityShanghaiChina

Personalised recommendations