Frontiers of Mechanical Engineering

, Volume 12, Issue 3, pp 357–366 | Cite as

Weak characteristic information extraction from early fault of wind turbine generator gearbox

  • Xiaoli Xu
  • Xiuli Liu
Research Article


Given the weak early degradation characteristic information during early fault evolution in gearbox of wind turbine generator, traditional singular value decomposition (SVD)-based denoising may result in loss of useful information. A weak characteristic information extraction based on μ-SVD and local mean decomposition (LMD) is developed to address this problem. The basic principle of the method is as follows: Determine the denoising order based on cumulative contribution rate, perform signal reconstruction, extract and subject the noisy part of signal to LMD and μ-SVD denoising, and obtain denoised signal through superposition. Experimental results show that this method can significantly weaken signal noise, effectively extract the weak characteristic information of early fault, and facilitate the early fault warning and dynamic predictive maintenance.


wind turbine generator gearbox μ-singular value decomposition local mean decomposition weak characteristic information extraction early fault warning 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.



This research was sponsored by the National Natural Science Foundation of China (Grant Nos. 51275052 and 51105041), and the Key Project Supported by Beijing Natural Science Foundation (Grant No. 3131002).


  1. 1.
    Wang G, He Z, Chen X, et al. Basic research on machinery fault diagnosis—What is the prescription. Journal of Mechanical Engineering, 2013, 49(1): 63–72 (in Chinese)CrossRefGoogle Scholar
  2. 2.
    Xu X, Wang H. Large Rotating Machinery Running Trend Forecasting. Beijing: Science Press, 2011 (in Chinese)Google Scholar
  3. 3.
    Xu X, Jiang Z, Ren B, et al. Extract method of flue gas generator set state feature weak information based on Birgé-Massart threshold. Journal of Mechanical Engineering, 2012, 48(12): 7–12 (in Chinese)CrossRefGoogle Scholar
  4. 4.
    Man Z, Wang W, Khoo S, et al. Optimal sinusoidal modeling of gear mesh vibration signals for gear diagnosis and prognosis. Mechanical Systems and Signal Processing, 2012, 33: 256–274CrossRefGoogle Scholar
  5. 5.
    Lv Z, Zhang W, Xu J. A denoising method based singular spectrum and its application in machine fault diagnosis. Chinese Journal of Mechanical Engineering, 1999, 35(3): 85–88Google Scholar
  6. 6.
    Chen J, Zhang L, Duan L, et al. Diagnosis of liquid valve based on undecimated lifting scheme packet and singular value decomposition. Journal of Mechanical Engineering, 2011, 47(9): 72–77 (in Chinese)CrossRefGoogle Scholar
  7. 7.
    Liu Y, Zhang J, Lin J, et al. Application of improved LMD, SVD technique and RVM to fault diagnosis of diesel valve trains. Transactions of Tianjin University, 2015, 21(4): 304–311CrossRefGoogle Scholar
  8. 8.
    Yu Z, Sun Y, Jin W. A novel generalized demodulation approach for multi-component signals. Signal Processing, 2016, 118: 188–202CrossRefGoogle Scholar
  9. 9.
    Zhao X, Ye B, Chen T. Difference spectrum theory of singular value and its application to the fault diagnosis of headstock of lathe. Journal of Mechanical Engineering, 2010, 46(1): 100–108 (in Chinese)CrossRefGoogle Scholar
  10. 10.
    Zhong Z, Zhang B, Durrani T S, et al. Nonlinear signal processing for vocal folds damage detection based on heterogeneous sensor network. Signal Processing, 2016, 126(S1): 125–133CrossRefGoogle Scholar
  11. 11.
    Zeng M, Yang Y, Zheng J, et al. µ-SVD based denoising method and its application to gear fault diagnosis. Journal of Mechanical Engineering, 2015, 51(3): 95–103 (in Chinese)CrossRefGoogle Scholar
  12. 12.
    Zhu S, Qiao Z, Yang Z. An improved method for the extraction of weak signal based on SVD and EMD. Measurement & Control Technology, 2014, 33(1): 60–62Google Scholar
  13. 13.
    Jiang W, Zheng Z, Zhu Y, et al. Demodulation for hydraulic pump fault signals based on local mean decomposition and improved adaptive multiscale morphology analysis. Mechanical Systems and Signal Processing, 2015, 58–59: 179–205CrossRefGoogle Scholar
  14. 14.
    Sun W, Xiong B, Huang J, et al. Fault diagnosis of a rolling bearing using wavelet packet de-noising and LMD. Journal of Vibration and Shock, 2012, 31(18): 153–156 (in Chinese)Google Scholar
  15. 15.
    Morzfeld M, Ajavakom N, Ma F. Diagonal dominance of damping and the decoupling approximation in linear vibratory systems. Journal of Sound and Vibration, 2009, 320(1–2): 406–420CrossRefGoogle Scholar
  16. 16.
    Wu Z, Cheng J, Yu Y, et al. Adaptive characteristic-scale decomposition method and its application. China Mechanical Engineering, 2015, 42(23): 7–15 (in Chinese)CrossRefGoogle Scholar
  17. 17.
    Wang B, Ren Z, Wen B. Fault diagnoses method of rotating machines based on nonlinear. Chinese Journal of Mechanical Engineering, 2012, 48(5): 63–69CrossRefGoogle Scholar
  18. 18.
    Cao L. Practical method for determining the minimum embedding dimension of a scalar time series. Physica D: Nonlinear Phenomena, 1997, 110(1–2): 43–50CrossRefzbMATHGoogle Scholar
  19. 19.
    Miao L, Ren W, Hu Y, et al. Separating temperature effect from dynamic strain measurements of a bridge based on analytical mode decomposition method. China Mechanical Engineering, 2012, 31 (21): 6–10 (in Chinese)Google Scholar
  20. 20.
    Wang H, Li X, Wang G, et al. Research on failure of wind turbine gearbox and recent development of its design and manufacturing technologies. China Mechanical Engineering, 2013, 24(11): 1542–1549 (in Chinese)Google Scholar
  21. 21.
    Vanhollebeke F, Peeters P, Helsen J, et al. Large scale validation of a flexible multibody wind turbine gearbox model. Journal of Computational and Nonlinear Dynamics, 2015, 10(4): 041006CrossRefGoogle Scholar

Copyright information

© Higher Education Press and Springer-Verlag Berlin Heidelberg 2017

Authors and Affiliations

  1. 1.Key Laboratory of Modern Measurement & Control Technology (Ministry of Education)Beijing Information Science and Technology UniversityBeijingChina

Personalised recommendations