access icon free DNN-based approach for fault detection in a direct drive wind turbine

© The Institution of Engineering and Technology
Received 28/12/2017, Accepted 11/05/2018, Revised 17/04/2018, Published 14/05/2018

Incipient fault detection of wind turbines is beneficial for making maintenance strategy and avoiding catastrophic result in a wind farm. A deep neural network (DNN)-based approach is proposed to deal with the challenging task for a direct drive wind turbine, involving four steps: a preprocessing method considering operational mechanism is presented to get rid of the outliers in supervisory control and data acquisition (SCADA); the conventional random forest method is used to evaluate the importance of variables related to the target variable; the historical healthy SCADA data excluding outliers is used to train a deep neural network; and the exponentially weighted moving average control chart is adopted to determine the fault threshold. With the online data being input into the trained deep neural network model of a wind turbine with healthy state, the testing error is regarded as the metric of fault alarm of the wind turbine. The proposed approach is successfully applied to the fault detection of the fall off of permanent magnets in a direct drive wind turbine generator.

Inspec keywords: wind turbines; learning (artificial intelligence); electric drives; neural nets; permanent magnets; SCADA systems; maintenance engineering; power generation faults; fault diagnosis

Other keywords: maintenance strategy; exponential weighted moving average control chart; historical healthy SCADA data; direct drive wind turbine generator; DNN-based approach; testing error; fault alarm; deep neural network-based approach; random forest method; preprocessing method; operational mechanism; supervisory control-and-data acquisition; permanent magnets; incipient fault detection

Subjects: Power system control; Permanent magnets; Power engineering computing; Drives; Wind power plants; Plant engineering, maintenance and safety; Data acquisition systems; Neural computing techniques; Control engineering computing; Knowledge engineering techniques

References

    1. 1)
      • 21. Breiman, L.: ‘Random forest’, Mach. Learn., 2001, 45, pp. 5–32.
    2. 2)
      • 10. Schlechtingen, M., Santos, I.F., Achiche, S.: ‘Wind turbine condition monitoring based on SCADA data using normal behavior models: part 1 – system description’, Appl. Soft Comput., 2013, 13, (1), pp. 259–270.
    3. 3)
      • 14. Yang, W.X., Tavner, P.J., Court, R.: ‘An online technique for condition monitoring the induction generators used in wind and marine turbines’, Mech. Syst. Signal Process., 2013, 38, pp. 103–112.
    4. 4)
      • 1. Sahu, B.K.: ‘Wind energy developments and policies in China: a short review’, Renew. Sustain. Energy Rev., 2017, 81, pp. 1393–1405.
    5. 5)
      • 29. Ruder, S.: ‘An overview of gradient descent optimization algorithms’, arXiv preprint, arXiv:1609.04747, 2016.
    6. 6)
      • 23. Strobl, C., Boulesteix, A.L., Zeileis, A., et al: ‘Bias in random forest variable importance measures: illustrations, sources and a solution’, BMC Bioinf., 2007, 8, (25), pp. 1–21.
    7. 7)
      • 20. Wang, L., Zhang, Z.J., Long, H., et al: ‘Wind turbine gearbox failure identification with deep neural networks’, IEEE Trans. Ind. Inf., 2017, 13, (3), pp. 1360–1368.
    8. 8)
      • 17. Chen, Z.Q., Li, C., Sanchez, R.V.: ‘Gearbox fault identification and classification with convolutional neural networks’, Shock Vib., 2015, 2015, (2), pp. 1–10.
    9. 9)
      • 11. Schlechtingen, M., Santos, I.F.: ‘Wind turbine condition monitoring based on SCADA data using normal behavior models: part 2 – application examples’, Appl. Soft Comput., 2014, 14, (1), pp. 447–460.
    10. 10)
      • 22. Menze, B.H., Kelm, B.M., Masuch, R., et al: ‘A comparison of random forest and its Gini importance with standard chemometric methods for the feature selection and classification of spectral data’, BMC Bioinf., 2009, 10, (213), pp. 1–16.
    11. 11)
      • 6. Barszcz, T., Randall, R.B.: ‘Application of spectral kurtosis for detection of a tooth crack in the planetary gear of a wind turbine’, Mech. Syst. Signal Process., 2009, 23, pp. 1352–1365.
    12. 12)
      • 2. Liu, W.Y., Tang, B.P., Han, J.G., et al: ‘The structure healthy condition monitoring and fault diagnosis methods in wind turbines: a review’, Renew. Sustain. Energy Rev., 2015, 44, pp. 466–472.
    13. 13)
      • 3. Yang, W., Tavner, P.J., Wilkinson, M.R.: ‘Condition monitoring and fault diagnosis of a wind turbine synchronous generator drive train’, IET Renew. Power Gener., 2009, 3, (1), pp. 1–11.
    14. 14)
      • 16. Tran, V.T., AlThobiani, F., Ball, A.: ‘An approach to fault diagnosis of reciprocating compressor valves using Teager-Kaiser energy operator and deep belief networks’, Expert Syst. Appl., 2014, 41, pp. 4113–4122.
    15. 15)
      • 27. Hunter, J.S.: ‘The exponentially weighted moving average’, J. Qual. Technol., 1986, 18, pp. 203–210.
    16. 16)
      • 7. Ha, J.M., Youn, B.D., Oh, H., et al: ‘Autocorrelation-based time synchronous averaging for condition monitoring of planetary gearboxes in wind turbines’, Mech. Syst. Signal Process., 2016, 70–71, pp. 161–175.
    17. 17)
      • 30. Kingma, D.P., Ba, J.L.: ‘Adam: a method for stochastic optimization’, arXiv preprint arXiv:1412.6980, 2014.
    18. 18)
      • 18. Jia, F., Lei, Y.G., Lin, J., et al: ‘Deep neural networks: a promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data’, Mech. Syst. Signal Process., 2016, 72–73, pp. 303–315.
    19. 19)
      • 26. Lucas, J.M., Saccucci, M.S.: ‘Exponentially weighted moving average control schemes: properties and enhancements’, Technometrics, 1990, 32, (1), pp. 1–12.
    20. 20)
      • 5. Zhang, Y., Lu, W.X., Chu, F.L.: ‘Planet gear fault localization for wind turbine gearbox using acoustic emission signals’, Renew. Energy, 2017, 109, pp. 449–460.
    21. 21)
      • 9. Kusiak, A., Verma, A.: ‘Analyzing bearing faults in wind turbines: a data-mining approach’, Renew. Energy, 2012, 48, pp. 110–116.
    22. 22)
      • 24. Hinton, G., Salakhutdinov, R.R.: ‘Reducing the dimensionality of data with neural networks’, Science, 2006, 313, (5789), pp. 504–507.
    23. 23)
      • 8. Sun, H.L., Zi, Y.Y., He, Z.J.: ‘Wind turbine fault detection using multiwavelet denoising with the data-driven block threshold’, Appl. Acoust., 2014, 77, pp. 122–129.
    24. 24)
      • 12. Guo, P., Infield, D., Yang, X.Y.: ‘Wind turbine generator condition-monitoring using temperature trend analysis’, IEEE Trans. Sustain. Energy, 2012, 3, (1), pp. 124–133.
    25. 25)
      • 19. Ince, T., Kiranyaz, S., Eren, L., et al: ‘Real-time motor fault detection by 1-D convolutional neural networks’, IEEE Trans. Ind. Electron., 2016, 63, (11), pp. 7067–7075.
    26. 26)
      • 13. Yang, W.X., Court, R., Jiang, J.S.: ‘Wind turbine condition monitoring by the approach of SCADA data analysis’, Renew. Energy, 2013, 53, pp. 365–376.
    27. 27)
      • 25. Hinton, G., Srivastava, N., Krizhevsky, A., et al: ‘Improving neural networks by preventing co-adaptation of feature detectors’, Comput. Sci., 2012, 3, (4), pp. 212–223.
    28. 28)
      • 28. Goodfellow, I., Bengio, Y., Courville, A.: ‘Deep learning’ (MIT press, Cambridge, 2016).
    29. 29)
      • 15. LeCun, Y., Bengio, Y., Hinton, G.: ‘Deep learning’, Nature, 2015, 521, (7553), pp. 436–444.
    30. 30)
      • 4. Azevedo, H.D.M., Araújo, A.M., Bouchonneau, N.: ‘A review of wind turbine bearing condition monitoring: state of the art and challenges’, Renew. Sustain. Energy Rev., 2016, 56, pp. 368–379.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-rpg.2017.0867
Loading

Related content

content/journals/10.1049/iet-rpg.2017.0867
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading