Journal of Failure Analysis and Prevention

, Volume 17, Issue 5, pp 1053–1066 | Cite as

Intelligent Health Monitoring of Machine Bearings Based on Feature Extraction

  • Mohammed Chalouli
  • Nasr-eddine Berrached
  • Mouloud Denai
Technical Article---Peer-Reviewed


Finding reliable condition monitoring solutions for large-scale complex systems is currently a major challenge in industrial research. Since fault diagnosis is directly related to the features of a system, there have been many research studies aimed to develop methods for the selection of the relevant features. Moreover, there are no universal features for a particular application domain such as machine diagnosis. For example, in machine bearing fault diagnosis, these features are often selected by an expert or based on previous experience. Thus, for each bearing machine type, the relevant features must be selected. This paper attempts to solve the problem of relevant features identification by building an automatic fault diagnosis process based on relevant feature selection using a data-driven approach. The proposed approach starts with the extraction of the time-domain features from the input signals. Then, a feature reduction algorithm based on cross-correlation filter is applied to reduce the time and cost of the processing. Unsupervised learning mechanism using K-means++ selects the relevant fault features based on the squared Euclidian distance between different health states. Finally, the selected features are used as inputs to a self-organizing map producing our health indicator. The proposed method is tested on roller bearing benchmark datasets.


Failure diagnosis Bearing faults Time-domain features Condition-based maintenance Health indicators Relevant features Fault feature extraction 



The authors wish to thank NSF I/UCR Center for Intelligent Maintenance Systems (IMS) [21] and Case Western Reserve University [40] for providing free access to the bearing vibration experimental data from their Web sites.


  1. 1.
    K. Medjaher, D. Tobon-mejia, N. Zerhouni, Remaining useful life estimation of critical components with application to bearings. IEEE Trans. Reliab. 61(2), 292–302 (2012)CrossRefGoogle Scholar
  2. 2.
    K. Medjaher, F. Camci, N. Zerhouni, Feature extraction and evaluation for Health Assessment and Failure prognostics, in First European Conference of the Prognostics and Health Management Society, (2012) pp. 1–6Google Scholar
  3. 3.
    J. Hu, L. Zhang, W. Liang, Degradation Assessment of Bearing Fault using SOM Network, 2011, pp. 561–565Google Scholar
  4. 4.
    L. Wang, R.X. Gao, Condition Monitoring and Control for Intelligent Manufacturing (Springer, Berlin, 2006)CrossRefGoogle Scholar
  5. 5.
    H. Kenneth, A. Adam, A. Aitor, J. Erkki, M. Julien, M. Samir, E-maintenance (Springer, Berlin, 2010)Google Scholar
  6. 6.
    R.K. Singleton, E.G. Strangas, S. Aviyente, Discovering the hidden health states in bearing vibration signals for fault prognosis, in Proceedings of the 40th Annual Conference of the IEEE Industrial Electronics Society, IECON, 2014, pp. 3438–3444Google Scholar
  7. 7.
    C. Nataraj, K. Kappaganthu, Vibration-based diagnostics of rolling element bearings: state of the art and challenges, in 13th World Congress in Mechanism and Machine Science, 2011, pp. 1–10Google Scholar
  8. 8.
    D.A. Tobon-Mejia, K. Medjaher, N. Zerhouni, G. Tripot, A mixture of Gaussians hidden Markov model for failure diagnostic and prognostic. IEEE Int. Conf. Autom. Sci. Eng. CASE 2010, 338–343 (2010)Google Scholar
  9. 9.
    S. Patidar, P.K. Soni, An overview on vibration analysis techniques for the diagnosis of rolling element bearing faults. Int. J. Eng. 4(May), 1804–1809 (2013)Google Scholar
  10. 10.
    A. Boudiaf, A. Moussaoui, A. Dahane, A comparative study of various methods of bearing faults diagnosis using the case Western Reserve University data. J. Fail. Anal. Prev. 16(2), 271–284 (2016)CrossRefGoogle Scholar
  11. 11.
    P. Lakshmi Pratyusha, V. Shanmukha Priya, V.P.S. Naidu, Bearing health condition monitoring: time domain analysis. Int. J. Adv. Res. Electr. Electr. Instrum. Eng. 3(5), 75–82 (2014)Google Scholar
  12. 12.
    L. Batista, B. Badri, R. Sabourin, M. Thomas, A classifier fusion system for bearing fault diagnosis. Expert Syst. Appl. 40(17), 6788–6797 (2013)CrossRefGoogle Scholar
  13. 13.
    S. Sassi, B. Badri, M. Thomas, TALAF and THIKAT as innovative time domain indicators for tracking BALL bearings, in Proceedings of the 14th Seminar on Machinery Vibration, 2(1), 24–27 (2006)Google Scholar
  14. 14.
    V. Sugumaran, K.I. Ramachandran, Effect of number of features on classification of roller bearing faults using SVM and PSVM. Expert Syst. Appl. 38(4), 4088–4096 (2011)CrossRefGoogle Scholar
  15. 15.
    A. Mosallam, K. Medjaher, N. Zerhouni, Time series trending for condition assessment and prognostics. J. Manuf. Technol. Manag. 25(4), 550–567 (2014)CrossRefGoogle Scholar
  16. 16.
    G. Jia, S. Yuan, C. Tang, Fault Diagnosis of Roller Bearing Based on PCA and Multi-class Support Vector Machine (Springer, Berlin, 2011), pp. 198–205Google Scholar
  17. 17.
    D. Galar, U. Kumar, Y. Fuqing, RUL prediction using moving trajectories between SVM hyper planes, in Proceedings of the Annual Reliability and Maintainability Symposium, 2012, pp. 1–6Google Scholar
  18. 18.
    M.M. Ettefagh, M. Ghaemi, M.Y. Asr, Bearing fault diagnosis using hybrid genetic algorithm K-means clustering, in Innovations in Intelligent Systems and Applications (INISTA) Proceedings, 2014 IEEE International Symposium on, 2014Google Scholar
  19. 19.
    W. Lu, X. Wang, C. Yang, and T. Zhang, A novel feature extraction method using deep neural network for rolling bearing fault diagnosis, 2015, pp. 2427–2431Google Scholar
  20. 20.
    Y. Wang, J. Xiang, R. Markert, M. Liang, Spectral kurtosis for fault detection, diagnosis and prognostics of rotating machines: a review with applications. Mech. Syst. Signal Process. 66–67, 679–698 (2016)CrossRefGoogle Scholar
  21. 21.
    H. Qiu, J. Lee, J. Lin, G. Yu, IMS Bearing Data The, 2006Google Scholar
  22. 22.
    S. Hong, Z. Zhou, Remaining useful life prognosis of bearing based on Gauss process regression, in 5th International Conference on Biomedical Engineering and Informatics (BMEI), 2012, pp. 1575–1579Google Scholar
  23. 23.
    M.E. Boukhobza, Z. Derouiche, Z.A. Foitih, Location and evaluation of bearings defects by vibration analysis and neural networks. Mechanika 19(4), 459–465 (2013)CrossRefGoogle Scholar
  24. 24.
    M. Zhu, Feature Extraction and Dimension Reduction with Applications to Classification and the Analysis of Co-occurrence Data, Doctoral Dissertation, Stanford University, 2001Google Scholar
  25. 25.
    A. Soualhi, K. Medjaher, N. Zerhouni, Bearing health monitoring based on hilbert-huang transform, support vector machine, and regression. IEEE Trans. Instrum. Meas. 64(1), 52–62 (2015)CrossRefGoogle Scholar
  26. 26.
    P. Berkhin, Survey of clustering data mining techniques, 2010, pp. 1–56Google Scholar
  27. 27.
    D. Arthur, S. Vassilvitskii, K-means++: the advantages of careful seeding, in Proceedings of 18th Annual ACM-SIAM Symposium Discrete algorithms, 8, 1027–1035 (2007)Google Scholar
  28. 28.
    Y. Dogan, D. Birant, A. Kut, SOM++: integration of self-organizing map and K-means++ Algorithms, in Mldm, 2013, pp. 246–259Google Scholar
  29. 29.
    M. Agarwal, R. Jaiswal, A. Pal, K-means++ under approximation stability. Theor. Comput. Sci. 588, 37–51 (2015)CrossRefGoogle Scholar
  30. 30.
    M.M. Öztürk, U. Cavusoglu, A. Zengin, A novel defect prediction method for web pages using K-means++. Expert Syst. Appl. 42, 6496–6506 (2015)CrossRefGoogle Scholar
  31. 31.
    H. Qiu, J. Lee, M. Kantardzic, O. Nasraoui, M. Milanova, Feature fusion and degradation detection using self-organizing map, in Proceedings of the 2004 International Conference on Machine Learning Application, 2004, pp. 107–114Google Scholar
  32. 32.
    J. Vesanto, J. Himberg, E. Alhoniemi, J. Parhankangas, Self-organizing map in Matlab: the SOM Toolbox, in Proceedings of the MATLAB DSP Conference, 1999, pp. 35–40Google Scholar
  33. 33.
    S. Shi, L. Zhang, W. Liang, Condition monitoring and fault diagnosis of rolling element bearings based on wavelet energy entropy and SOM, in International Conference on Quality, Reliability, Risk, Maintenance, and Safety Engineering, 2012, pp. 651–655Google Scholar
  34. 34.
    P. Jun, L. Jiaquan, L. Xiangjiang, Self-organizing map-based fault dictionary application research on rolling bearing faults, in Proceedings of the 4th International Conference Natural Computing ICNC, 3, 311–315 (2008)Google Scholar
  35. 35.
    Z. Xia, S. Xia, L. Wan, S. Cai, Spectral regression based fault feature extraction for bearing accelerometer sensor signals. Sensors (Switzerland) 12(10), 13694–13719 (2012)CrossRefGoogle Scholar
  36. 36.
    A. Boulenger, C. Pachaud, Aide-mémoire Surveillance des Machines par Analyse des Vibrations (2009)Google Scholar
  37. 37.
    R. Chaib, Contribution a L’optimisation de la Maintenance Conditionelle par L’analyse Vibratoire (2007)Google Scholar
  38. 38.
    O. Djebili, Contribution à la maintenance prédictive par analyse vibratoire des composants mécaniques tournants. Application aux butées à billes soumises à la fatigue de contact de roulement, 2013Google Scholar
  39. 39.
    J. Lee, J. Ni, D. Djurdjanovic, H. Qiu, H. Liao, Intelligent prognostics tools and e-maintenance. Comput. Ind. 57(6), 476–489 (2006)CrossRefGoogle Scholar
  40. 40.
    Bearing Data Center|Personal web site of Bearing Data Center (Online). Accessed: 15 Jan 2017
  41. 41.
    K. Medjaher, J.-Y. Moya, N. Zerhouni, Failure prognostic by using dynamic Bayesian networks. Dependable Control Discret. Syst. 2(1), 257–262 (2009)Google Scholar

Copyright information

© ASM International 2017

Authors and Affiliations

  1. 1.Intelligent Systems Research Laboratory (LARESI)USTO-MB UniversityOranAlgeria
  2. 2.School of Engineering and TechnologyUniversity of HertfordshireHatfieldUK

Personalised recommendations