Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Wind turbines anomaly detection based on power curves and ensemble learning

  • Author(s): Sinvaldo R. Moreno 1, 2 ; Leandro dos Santos Coelho 1, 3 ; Helon V.H. Ayala 4 ; Viviana Cocco Mariani 1, 2
    • View affiliations
  • Source: Volume 14, Issue 19, 28 December 2020, p. 4086 – 4093
    DOI:  10.1049/iet-rpg.2020.0224 , Print ISSN 1752-1416, Online ISSN 1752-1424
© The Institution of Engineering and Technology
Received 26/02/2020, Accepted 30/11/2020, Revised 30/10/2020, Published 18/12/2020

Wind farms are increasingly important nowadays since in some countries can surpass conventional power sources. However, in countries where the exploration of this renewable source started recently, the lack of knowledge related to maintenance routines and efficient operation has led to fast performance degradation. In this context, wind turbine condition monitoring can detect anomalies in its performance as an unexpected failure, avoiding financial loss. In this study, machine learning approaches are applied as an online tool to detect abnormal wind turbine operation modes, evaluating the wind turbine operation in all regions of the power curve. The methodology has been validated with an original and real dataset collected from a large-scale onshore wind turbine in Northeast Brazil. The results exhibit an expressive reduction of energy loss and indicate the ability of the proposed approach to assessing the abnormal modes even when a small number of recorded data are available. The standard classifiers reached on average 98.64% accuracy in the holdout data set. Additionally, an ensemble of classifiers is proposed which helped to improve in 12% the accuracy of the best classifier alone, increasing the confidence of alarms raised by the predictive maintenance tool.

Inspec keywords: SCADA systems; learning (artificial intelligence); wind power plants; maintenance engineering; wind turbines; condition monitoring

Other keywords: renewable source; conventional power sources; coal plants; hydro; turbine performance; machine learning approaches; large-scale onshore wind turbine; power curve; wind farms; fast performance degradation; wind turbines; energy loss; abnormal wind turbine operation modes; wind turbine condition monitoring

Subjects: Wind power plants; Power engineering computing; Knowledge engineering techniques; Maintenance and reliability

References

    1. 1)
      • 8. Kusiak, A., Zheng, H., Song, Z.: ‘Online monitoring of power curves’, Renew. Energy, 2009, 34, pp. 1487–1493.
    2. 2)
      • 37. Dietterich, T.G.: ‘An experimental comparison of three methods for constructing ensembles of decision trees: bagging, boosting, and randomization’, Mach. Learn., 2000, 40, pp. 139–157.
    3. 3)
      • 24. Pelletier, F., Masson, C., Tahan, A.: ‘Wind turbine power curve modelling using artificial neural network’, Renew. Energy, 2016, 89, pp. 207–214.
    4. 4)
      • 18. Lydia, M., Kumar, S.S., Selvakumar, A.I., et al: ‘A comprehensive review on wind turbine power curve modeling techniques’, Renew. Sustain. Energy Rev., 2014, 30, pp. 452–460.
    5. 5)
      • 2. Cambron, P., Lepvrier, R., Masson, C., et al: ‘Power curve monitoring using weighted moving average control charts’, Renew. Energy, 2016, 94, pp. 126–135.
    6. 6)
      • 10. Casau, P., Rosa, P., Tabatabaeipour, S. M., et al: ‘Fault detection and isolation and fault tolerant control of wind turbines using set-valued observers’. 8th IFAC SAFE PROCESS, Mexico City Mexico, 2012, pp. 29–31.
    7. 7)
      • 3. Wang, S., Huang, Y., Li, L., et al: ‘Wind turbines abnormality detection through analysis of wind farm power curves’, Measurement, 2016, 93, pp. 178–188.
    8. 8)
      • 38. Vapnik, V.N.: ‘The nature of statistical learning theory’ (Springer-Verlag, New York, 1995).
    9. 9)
      • 1. W.W.E. Association: Statistics report (WWEA), https://wwindea.org/information-2/information/, 2020.
    10. 10)
      • 25. Sainz, E., Llombart, A., Guerrero, J.J.: ‘Robust filtering for the characterization of wind turbines: improving its operation and maintenance’, Energy Convers. Manage., 2009, 50, pp. 2136–2147.
    11. 11)
      • 11. Soares, M.N., Yves, M., Kinnaert, M., et al: ‘Robust power-electronic-converter fault detection and isolation technique for DFIG wind turbines’, J. Phys., Conf. Ser., 2018, 1037, p. 032043.
    12. 12)
      • 32. Cost, S., Salzberg, S.: ‘A weighted nearest neighbor algorithm for learning with symbolic features’, Mach. Learn., 1993, 10, pp. 57–78.
    13. 13)
      • 4. Kim, K., Parthasarathy, G., Uluyol, O., et al: ‘Use of SCADA data for failure detection in wind turbines’. ASME Energy Sustainability, ASME 2011 5th Int. Conf. on Energy Sustainability, Parts A, B, and C, Washington, DC, USA, 2011, pp. 2071–2079.
    14. 14)
      • 19. Askarzadeh, A., Coelho, L.S.: ‘A novel framework for optimization of a grid independent hybrid renewable energy system: a case study of Iran’, Sol. Energy, 2015, 112, pp. 383–396.
    15. 15)
      • 17. Lee, J., Wu, F., Zhao, W., et al: ‘Prognostics and health management design for rotary machinery systems - reviews, methodology and applications’, Mech. Syst. Signal Process., 2014, 42, pp. 314–334.
    16. 16)
      • 5. Kusiak, A., Li, W.: ‘The prediction and diagnosis of wind turbine faults’, Renew. Energy, 2011, 36, pp. 16–23.
    17. 17)
      • 29. Sobie, C., Freitas, C., Nicolai, M.: ‘Simulation-driven machine learning: bearing fault classification’, Mech. Syst. Signal Process., 2018, 99, pp. 403–419.
    18. 18)
      • 15. Ferguson, D., McDonald, A., Carroll, J., et al: ‘Standardisation of wind turbine SCADA data for gearbox fault detection’, J. Eng., 2019, 18, pp. 5147–5151.
    19. 19)
      • 28. Kung, S. Y.: ‘Kernel methods and machine learning’ (Princeton University, New Jersey, 2014).
    20. 20)
      • 20. Mérigaud, A., Ringwood, J.V.: ‘Condition-based maintenance methods for marine renewable energy’, Renew. Sustain. Energy Rev., 2016, 66, pp. 53–78.
    21. 21)
      • 40. Ren, Y., Zhang, L., Suganthan, P.N.: ‘Ensemble classification and regression- recent developments, applications and future directions’, IEEE Comput. Intell. Mag., 2016, 11, pp. 41–53.
    22. 22)
      • 33. Sutton, C.D.: ‘11 – classification and regression trees, bagging, and boosting’, Handb. Stat., 2005, 24, pp. 303–329.
    23. 23)
      • 6. Kusiak, A., Zhang, Z.: ‘Analysis of wind turbine vibrations based on SCADA data’, ASME. J. Sol. Energy Eng., 2010, 132, pp. 1–10.
    24. 24)
      • 21. Vianna Neto, J.X., Guerra Junior, E.J., Moreno, S.R., et al: ‘Wind turbine blade geometry design based on multi-objective optimization using metaheuristics’, Energy, 2018, 162, pp. 645–658.
    25. 25)
      • 48. Coelho, L.S., Alotto, P.: ‘Multiobjective electromagnetic optimization based on a nondominated sorting genetic approach with a chaotic crossover operator’, IEEE Trans. Magn., 2008, 44, pp. 1078–1081.
    26. 26)
      • 42. Rodriguez, J.J., Kuncheva, L.I., Alonso, C.J.: ‘Rotation forest: a new classifier ensemble method’, IEEE Trans. Pattern Anal. Mach. Intell., 2006, 28, pp. 1619–1630.
    27. 27)
      • 41. Breiman, L.: ‘Random forests’, Mach. Learn., 2001, 45, pp. 5–32.
    28. 28)
      • 16. Leite, G.N.P., Araújo, A.M., Rosas, P.A.C.: ‘Prognostic techniques applied to maintenance of wind turbines: a concise and specific review’, Renew. Sustain. Energy Rev., 2018, 81, pp. 1917–1925.
    29. 29)
      • 30. Widodo, A., Kim, E.Y., Son, J.-D., et al: ‘Fault diagnosis of low speed bearing based on relevance vector machine and support vector machine’, Expert Syst. Appl., 2009, 36, pp. 7252–7261.
    30. 30)
      • 27. Lee, J.H., Shin, J., Realff, M.J.: ‘Machine learning: overview of the recent progress and implications for the process systems engineering field’, Comput. Chem. Eng., 2017, 114, pp. 111–121.
    31. 31)
      • 46. Coelho, L.S., Mariani, V.C., Luz, M.V.F., et al: ‘Novel gamma differential evolution approach for multiobjective transformer design optimization’, IEEE Trans. Magn., 2013, 49, pp. 2121–2124.
    32. 32)
      • 36. Kuncheva, L.I., Skurichina, M., Duin, R.P.W.: ‘An experimental study on diversity for bagging and boosting with linear classifiers’, Inf. Fusion, 2002, 3, pp. 245–258.
    33. 33)
      • 44. Rohani, A., Taki, M., Abdollahpour, M.: ‘A novel soft computing model (Gaussian process regression with K-fold cross validation) for daily and monthly solar radiation forecasting (part: I)’, Renew. Energy, 2018, 115, pp. 411–422.
    34. 34)
      • 31. Cover, T., Hart, P.: ‘Nearest neighbor pattern classification’, IEEE Trans. Inf. Theory, 1967, 13, pp. 21–27.
    35. 35)
      • 23. Thapar, V., Agnihotri, G., Sethi, V.K.: ‘Critical analysis of methods for mathematical modelling of wind turbines’, Renew. Energy, 2011, 36, pp. 3166–3177.
    36. 36)
      • 26. Papatheou, E., Dervilis, N., Maguire, A.E., et al: ‘Performance monitoring of a wind turbine using extreme function theory’, Renew. Energy, 2017, 113, pp. 1490–1502.
    37. 37)
      • 49. Silva, L.: ‘A feature engineering approach to wind power forecasting: GEFCom 2012’, Int. J. Forecast., 2014, 30, pp. 395–401.
    38. 38)
      • 13. Melero, J.J., Guerrero, J.J., Beltrán, J., et al: ‘Efficient data filtering for wind energy assessment’, IET Renew. Power Gener., 2012, 6, pp. 446–454.
    39. 39)
      • 7. Zaher, A., McArthur, S.D.J., Infield, D.G., et al: ‘Online wind turbine fault detection through automated SCADA data analysis’, Wind Energy, 2009, 12, pp. 574–593.
    40. 40)
      • 35. Quinlan, J.R.: ‘Induction of decision trees’, Mach. Learn., 1986, 1, pp. 81–106.
    41. 41)
      • 9. Zhao, H., Liu, H., Hu, W., et al: ‘Anomaly detection and fault analysis of wind turbine components based on deep learning network’, Renew. Energy, 2018, 127, pp. 825–834.
    42. 42)
      • 34. Polat, K., Güneş, S.: ‘Classification of epileptiform EEG using a hybrid system based on decision tree classifier and fast Fourier transform’, Appl. Math. Comput., 2007, 187, pp. 1017–1026.
    43. 43)
      • 39. Chen, W., Pourghasemi, H. R., Kornejady, A., et al: ‘Landslide spatial modeling: introducing new ensembles of ANN, MaxEnt, and SVM machine learning techniques’, Goderma, 2017, 305, pp. 314–327.
    44. 44)
      • 14. Zhang, J.H., Xiong, J., Ren, M.F., et al: ‘Fault diagnosis of wind energy conversion systems with sensor faults’. 2nd IET Renewable Power Generation Conf., Beijing China, 2013, pp. 1–7.
    45. 45)
      • 12. Huang, Q., Jiang, D., Hong, L., et al: ‘Application of wavelet neural networks on vibration fault diagnosis for wind turbine gearbox’. Int. Symp. on Neural Networks, Advances in Neural Networks, Beijing China, 2008, pp. 313–320.
    46. 46)
      • 43. Kuncheva, L.I.: ‘Combining pattern classifiers: methods and algorithms’ (John Wiley & Sons, USA, 2014).
    47. 47)
      • 45. Coelho, L.S., Mariani, V.C., Guerra, F.A., et al: ‘Multiobjective optimization of transformer design using a chaotic evolutionary approach’, IEEE Trans. Magn., 2014, 50, Article 7016504, pp. 669–672.
    48. 48)
      • 47. Neto, J.X.V., Bernert, D.L.A., Coelho, L.S.: ‘Improved quantum-inspired evolutionary algorithm with diversity information applied to economic dispatch problem with prohibited operating zones’, Energy Convers. Manage., 2011, 52, pp. 8–14.
    49. 49)
      • 22. Moreno, S.R., Coelho, L.S.: ‘Wind speed forecasting approach based on singular spectrum analysis and adaptive neuro fuzzy inference system’, Renew. Energy, 2018, 126, pp. 736–754.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-rpg.2020.0224
Loading

Related content

content/journals/10.1049/iet-rpg.2020.0224
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address