access icon free Sparse component analysis-based under-determined blind source separation for bearing fault feature extraction in wind turbine gearbox

The signal processing-based bearing fault diagnosis in wind turbine gearbox is considered challenging as the vibration signals collected from acceleration transducers are, in general, a mixture of signals originating from an unknown number of sources. Even worse, the source number is often larger than the number of installed sensors, and hence the fault characterisation is effectively an under-determined blind source separation problem. In this study, a novel sparse component analysis-based algorithmic solution is proposed to address this technical challenge from two aspects: source number estimation and source signal recovery, to enable accurate and efficient bearing fault diagnosis. The source number estimation is implemented based on the empirical mode decomposition and singular value decomposition joint approach. The observed signals are transformed to the time–frequency domain using short-time Fourier transform to obtain the sparse representation of the signals. The fuzzy C-means clustering and l 1 norm decomposition methods are used to estimate the mixing matrix and recover the source signals, respectively. The proposed solution is assessed through simulation experiments for scenarios of linearly and non-linearly mixed bearing vibration signals, and the numerical result confirms the effectiveness of the proposed algorithmic solution

Inspec keywords: transducers; fault diagnosis; feature extraction; blind source separation; signal representation; wind turbines; Fourier transforms; singular value decomposition; gears; time-frequency analysis; fuzzy systems

Other keywords: bearing fault feature extraction; sparse signal representation; source number estimation; short-time Fourier transform; under-determined blind source separation; fuzzy C-means clustering; signal processing-based bearing fault diagnosis; sparse component analysis; signal feature characterisation; time–frequency domain; acceleration transducers; empirical mode decomposition; singular value decomposition; nonlinearly mixed bearing vibration signals; wind turbine gearbox; source signal recovery; l1 norm decomposition; source estimation

Subjects: Numerical analysis; Linear algebra (numerical analysis); Mathematical analysis; Wind power plants; Integral transforms in numerical analysis; Signal processing and detection

References

    1. 1)
      • 3. Cichocki, A., Amari, S.I.: ‘Analysis of sparse representation and blind source separation’, Neural Comput., 2004, 16, pp. 11931234.
    2. 2)
      • 7. Zeng, T.J., Feng, Q.Y., Yuan, X.H., et al: ‘The multi-component signal model and learning algorithm of blind source separation’. Proc. of Progress in Electromagnetics Research Symp., Taipei, March 2013, pp. 2528.
    3. 3)
      • 22. Bofill, P., Zibulevsky, M.: ‘Underdetermined blind source separation using sparse representations’, Signal Process., 2001, 81, pp. 23532362.
    4. 4)
      • 6. Zhou, W., Chelidze, D.: ‘Blind source separation based vibration mode identification’, Mech. Syst. Signal Process., 2007, 21, pp. 30723087.
    5. 5)
      • 8. Cheng, W., Lee, S., Zhang, Z., et al: ‘Independent component analysis based source number estimation and its comparison for mechanical systems’, J. Sound Vib., 2012, 331, (23), pp. 51535167.
    6. 6)
      • 25. ‘Bearing Information’. Available at http://www.csegroups.case.edu/bearingdatacenter/pages/bearing-information, accessed on 2 March 2016.
    7. 7)
      • 21. Yilmaz, O., Rickard, S.: ‘Blind separation of speech mixtures via time-frequency masking’, IEEE Trans. Signal Process., 2004, 52, pp. 18301847.
    8. 8)
      • 10. Yang, Y., Nagarajaiah, S.: ‘Output-only modal identification with limited sensors using sparse component analysis’, J. Sound Vib., 2013, 332, (19), pp. 47414765.
    9. 9)
      • 17. Gong, M., Liang, Y., Shi, J., et al: ‘Fuzzy c-means clustering with local information and kernel metric for image segmentation’, IEEE Trans. Image Process., 2013, 22, (2), pp. 573584.
    10. 10)
      • 20. Keller, B.M., Nathan, D.L., Wang, Y., et al: ‘Estimation of breast percent density in raw and processed full field digital mammography images via adaptive fuzzy c-means clustering and support vector machine segmentation’, Med. Phys., 2012, 39, (8), pp. 49034917.
    11. 11)
      • 9. Nadler, B.: ‘Nonparametric detection of signals by information theoretic criteria: performance analysis and an improved estimator’, IEEE Trans. Signal Process., 2010, 58, pp. 27462756.
    12. 12)
      • 12. Varun, B., Pachori, R.B.: ‘Classification of seizure and nonseizure EEG signals using empirical mode decomposition’, IEEE Trans. Inf. Technol. Biomed., 2012, 16, (6), pp. 11351142.
    13. 13)
      • 2. Chen, Y., Meng, J.: ‘Study on BSS algorithm used on fault diagnosis of gearbox’, TELKOMNIKA Indonesian J. Electr. Eng., 2013, 11, pp. 29422947.
    14. 14)
      • 11. Qin, S., Guo, J., Zhu, C.: ‘Sparse component analysis using time-frequency representations for operational modal analysis’, Sensors, 2015, 15, pp. 64976519.
    15. 15)
      • 23. Sheng, S.: ‘Wind turbine gearbox condition monitoring round robin study – vibration analysis’, Contract, 2012, 303, pp. 2753000.
    16. 16)
      • 1. U.S. Department of Energy. Available at http://www.energy.gov/eere/wind/articles/statistics-show-bearing-problems-cause-majority-wind-turbine-gearbox-failures, 17 September2015.
    17. 17)
      • 4. Gelle, G., Colas, M., Serviere, C.: ‘Blind source separation: a tool for rotating machine monitoring by vibrations analysis’, J. Sound Vib., 2001, 248, pp. 865885.
    18. 18)
      • 14. Bin, G.F., Gao, J.J., Li, X.J., et al: ‘Early fault diagnosis of rotating machinery based on wavelet packets – empirical mode decomposition feature extraction and neural network’, Mech. Syst. Signal Process., 2012, 27, pp. 696711.
    19. 19)
      • 13. Lei, Y., Lin, J., He, Z., et al: ‘A review on empirical mode decomposition in fault diagnosis of rotating machinery’, Mech. Syst. Signal Process., 2013, 35, (1), pp. 108126.
    20. 20)
      • 19. Havens, T.C., Bezdek, J.C., Leckie, C., et al: ‘Fuzzy c-means algorithms for very large data’, Fuzzy Syst., 2012, 20, (6), pp. 11301146.
    21. 21)
      • 5. Bouguerriou, N., Haritopoulos, M., Capdessus, C., et al: ‘Novel cyclostationarity-based blind source separation algorithm using second order statistical properties: theory and application to the bearing defect diagnosis’, Mech. Syst. Signal Process., 2005, 19, pp. 12601281.
    22. 22)
      • 16. Soumi, G., Dubey, S.K.: ‘Comparative analysis of k-means and fuzzy c-means algorithms’, Int. J. Adv. Comput. Sci. Appl., 2013, 4, (4), pp. 3439.
    23. 23)
      • 24. Wei, L., Yang, H.-Z.: ‘A maximum entropy based nonlinear blind source separation approach using a two-layer perceptron network’. 2013 Tenth IEEE Int. Conf. on Control and Automation (ICCA), 2013, pp. 978982.
    24. 24)
      • 18. Wu, K.L.: ‘Parameter selections of fuzzy c-means based on robust analysis’, World Acad. Sci. Eng. Technol., 2010, 65, pp. 554557.
    25. 25)
      • 15. Celebi, M., Emre, H., Kingravi, A., et al: ‘A comparative study of efficient initialization methods for the k-means clustering algorithm’, Expert Syst. Appl., 2013, 40, (1), pp. 200210.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-rpg.2016.0240
Loading

Related content

content/journals/10.1049/iet-rpg.2016.0240
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading