access icon free SCADA-based wind turbine anomaly detection using Gaussian process models for wind turbine condition monitoring purposes

The penetration of wind energy into power systems is steadily increasing; this highlights the importance of operations and maintenance, and specifically the role of condition monitoring. Wind turbine power curves based on supervisory control and data acquisition data provide a cost-effective approach to wind turbine health monitoring. This study proposes a Gaussian process (a non-parametric machine learning approach) based algorithm for condition monitoring. The standard IEC binned power curve together with individual bin probability distributions can be used to identify operational anomalies. The IEC approach can also be modified to create a form of real-time power curve. Both of these approaches will be compared with a Gaussian process model to assess both speed and accuracy of anomaly detection. Significant yaw misalignment, reflecting a yaw control error or fault, results in a loss of power. Such a fault is quite common and early detection is important to prevent loss of power generation. Yaw control error provides a useful case study to demonstrate the effectiveness of the proposed algorithms and allows the advantages and limitations of the proposed methods to be determined.

Inspec keywords: SCADA systems; power system analysis computing; power system security; statistical distributions; Gaussian processes; learning (artificial intelligence); condition monitoring; wind turbines; wind power

Other keywords: loss-of-power; yaw fault; supervisory control-and-data acquisition-based wind turbine anomaly detection; power systems; nonparametric machine learning approach; IEC approach; wind turbine condition monitoring purposes; Gaussian process models; operational anomalies; yaw misalignment; The standard IEC binned power curve; real-time power curve; wind turbine power curves; individual bin probability distributions; yaw control error; wind energy penetration; wind turbine health monitoring

Subjects: Power system protection; Maintenance and reliability; Data acquisition systems; Fluid mechanics and aerodynamics (mechanical engineering); Power and plant engineering (mechanical engineering); Control technology and theory (production); Data acquisition systems for control; Energy resources; Knowledge engineering techniques; Other engineering applications of IT; Power system management, operation and economics; Control engineering computing; Statistics; Control of electric power systems; Wind power plants; Power engineering computing; Other topics in statistics; Other topics in statistics; Power system control

References

    1. 1)
      • 10. Skrimpas, G. A., Sweeney, C. W., Marhadi, K. S., et al: ‘Employment of kernel methods on wind turbine power performance assessment’, IEEE Trans. Sustain. Energy, 2015, 6, (3), pp. 698706.
    2. 2)
      • 45. Wang, Y., Infield, D. G.: ‘Power curve based online condition monitoring for wind turbines’. COMDEM 2013 Conf. doi: 10.13140/2.1.4492.9928.
    3. 3)
      • 48. Hartikainen, J., Särkkä, S.: ‘Kalman filtering and smoothing solutions to temporal Gaussian process regression models’. IEEE International Workshop on Machine Learning for Signal Processing, Kittila, 2010, pp. 379384.
    4. 4)
      • 31. Powell, W. R.: ‘An analytical expression for the average output power of a wind machine’, Sol. Energy, 1981, 26, (1), pp. 7780.
    5. 5)
      • 19. Bulaevskaya, V., Wharton, S., Clifton, A., et al: ‘Wind power curve modeling in complex terrain using statistical models’, J. Renew. Sustain. Energy, 2015, 7, p. 013103.
    6. 6)
      • 9. Shokrzadeh, S., Jafari Jozani, M., Bibeau, E.: ‘Wind turbine power curve modeling using advanced parametric and nonparametric methods’, IEEE Trans. Sustain. Energy, 2014, 5, (4), pp. 12621269.
    7. 7)
      • 17. Wang, Y., Infield, D., Stephen, B., et al: ‘Copula based model for wind turbine power curve outlier rejection’, Wind Energy, 2014, 17, (11), pp. 16771688.
    8. 8)
      • 18. Zhou, J., Guo, P., Wang, X.-R.: ‘Modeling of wind turbine power curve based on Gaussian process’. Proc. 2014 Int. Conf. on Machine Learning and Cybernetics, Lanzhou, 13–16 July 2014, pp. 7176.
    9. 9)
      • 27. Schlechtingen, M., Santos, I.F.: ‘Comparative analysis of neural network and regression based condition monitoring approaches for wind turbine fault detection’, Mech. Syst. Signal Process., 2011, 25, (5), pp. 18491875.
    10. 10)
      • 14. de Andrade Vieira, R. J., Sanz-Bobi, M. A., Kato, S.: ‘Wind turbine condition assessment based on changes observed in its power curve’. Proc. Int. Conf. on Renewable Energy Research and Applications Madrid, Spain, 20–23 October 2013, pp. 3136.
    11. 11)
      • 3. Hedevang, E.: ‘Wind turbine power curves incorporating turbulence intensity’, Wind Energy, 2014, 17, pp. 173195.
    12. 12)
      • 40. Davidov, O.: ‘Combining p-values using order-based methods’, Comput. Stat. Data Anal., 2011, 55, (7), pp. 24332444.
    13. 13)
      • 29. Mathew, S.: ‘Wind energy-fundamentals, resource analysis and economics’ (Springer, Berlin, Germany, 2006).
    14. 14)
      • 2. Martin, C. M., Lundquist, J. K., Clifton, A., et al: ‘Wind turbine power production and annual energy production depend on atmospheric stability and turbulence’, Wind Energy Sci., 2014, 17, pp. 173195.
    15. 15)
      • 25. ‘How to improve the LCOE of wind power’. Available at http://new.abb.com/power-generation/in-control/01-2015/how-to-improve-the-lcoe-of-wind-power, publish in 2015.
    16. 16)
      • 32. Chang, T.-P., Liu, F.-J., Ko, H.-H., et al: ‘Comparative analysis on power curve models of wind turbine generator in estimating capacity factor’, Energy, 2014, 73, pp. 8895.
    17. 17)
      • 11. Skrimpas, G. A., Sweeney, C. W., Marhadi, K. S., et al: ‘Detection of wind turbine power performance abnormalities using eigenvalue analysis’. Annual Conf. of the Prognostics and Health Management Society, Texas, 2014.
    18. 18)
      • 43. McDermott, M.P.: ‘Generalized orthogonal contrast tests for homogeneity of ordered means’, Can. J. Stat., 1999, 27, pp. 457470.
    19. 19)
      • 12. Lee, G., Ding, Y., Xie, L., et al: ‘A kernel plus method for quantifying wind turbine performance upgrades’, Wind Energy, 2015, 18, pp. 12071219.
    20. 20)
      • 1. IEC 61400-12-1: ‘International electro-technical commission, wind turbines — part 12-1: power performance measurements of electricity producing wind turbines’, 2016.
    21. 21)
      • 44. Cox, C.P., Han, C.: ‘Testing multivariate means when the covariance matrix has intraclass correlation structure’, J. Stat. Comput. Simul., 1982, 16, pp. 97107.
    22. 22)
      • 41. Brown, M. B.: ‘400: a method for combining non-independent, one-sided tests of significance’, Biometrics, 1975, 31, (4), pp. 987992. Available at http://www.jstor.org/stable/2529826.
    23. 23)
      • 35. Wind Turbines—Part 12-1: Power Performance Measurements of Electricity Producing Wind Turbines, British Standard, IEC 61400-12-1, 2006.
    24. 24)
      • 47. Gonzalez, J.: ‘Linear-time inverse covariance matrix estimation in Gaussian processes’. Available at http://www.cs.cmu.edu/~sahong/docs/jegonzal_sahong_final.pdf.
    25. 25)
      • 5. Long, H., Wang, L., Zhang, Z., et al: ‘Data-driven wind turbine power generation performance monitoring’, IEEE Trans. Ind. Electron., 2015, 62, (10), pp. 66276635.
    26. 26)
      • 22. Davoust, S.: ‘Optimising annual energy production with apt handling of yaw misalignment’. New Energy Update, 2013, available at: http://http://newenergyupdate.com/wind-energy-update/optimising-annual-energy-production-apt-handling-yaw-misalignment, accessed January 2018.
    27. 27)
      • 16. Gill, S., Stephen, B., Galloway, S.: ‘Wind turbine condition assessment through power curve copula modeling’, IEEE Trans. Sustain. Energy, 2012, 3, (1), pp. 94101.
    28. 28)
      • 8. Carrillon, C., Obando Montaño, A.F., Cidrás, J., et al: ‘Review of power curve modelling for wind turbines’, Renew. Sustain. Energy Rev., 2013, 21, pp. 572581.
    29. 29)
      • 4. Bulaevskaya, V., Wharton, S., Clifton, A., et al: ‘Wind power curve modeling in simple and complex terrain using statistical models’, J. Renew. Sustain. Energy, 2015, 62, pp. 66276635.
    30. 30)
      • 39. Fisher, R.A.: ‘Statistical methods for research workers’ (Oliver and Boyd, London, 1932).
    31. 31)
      • 36. Li, P., Chen, S.: ‘A review on Gaussian process latent variable models’. CAAI Transactions on Intelligence Technology, 2016, 1, (4), pp. 366376.
    32. 32)
      • 49. Sarkka, S., Solin, A., Hartikainen, J.: ‘Spatiotemporal learning via infinite-dimensional Bayesian filtering and smoothing’, IEEE Signal Processing Magazine, 2013, 30, (4), pp. 5161.
    33. 33)
      • 20. ‘Renewable energy sources: wind’. Available at http://www.beaufortcourt.com/energy-generation/wind-energy, accessed 27 November 2017.
    34. 34)
      • 42. Kost, J. T., McDermott, M. P.: ‘Combining dependent P-values’, Stat. Probab. Lett., 2002, 60, (2), pp. 183190.
    35. 35)
      • 23. Kragh, K. A., Hansen, M. H.: ‘Load alleviation of wind turbines by yaw misalignment’, Wind Energy, 2014, 17, pp. 971982.
    36. 36)
      • 33. Kusiak, A., Zheng, H., Song, Z.: ‘Models for monitoring wind farm power’, Renew. Energy, 2009, 34, (3), pp. 583590.
    37. 37)
      • 24. ‘Wind turbines: correcting yaw error’. Available at http://www.engineerlive.com/content/wind-turbines-correcting-yaw-error, accessed 19 December 2018.
    38. 38)
      • 7. Lydiaa, M., Suresh Kumarb, S., Immanuel Selvakumara, A., et al: ‘A comprehensive review on wind turbine power curve modeling techniques’, Renew. Sustain. Energy Rev., 2014, 30, pp. 452460.
    39. 39)
      • 37. Rasmussen, C. E., Williams, C. K. I.: ‘Gaussian processes for machine learning’ (The MIT Press, Massachusetts, 2006), ISBN 026218253X.
    40. 40)
      • 34. Park, J.-Y., Lee, J.-K., Oh, K.-Y., et al: ‘Development of a novel power curve monitoring method for wind turbines and its field tests’, IEEE Trans. Energy Convers., 2014, 29, (1), pp. 119128.
    41. 41)
      • 13. Lee, G., Ding, Y., Genton, M. G., et al: ‘Power curve estimation with multivariate environmental factors for inland and offshore wind farms’, J. Am. Stat. Assoc., 2015, 110, (509), pp. 5667.
    42. 42)
      • 15. Mohan Raj, M. S., Alexander, M., Lydia, M.: ‘Modeling of wind turbine power curve’. Proc. 2011 IEEE PES Innovative Smart Grid Technologies Conf., India, 2011.
    43. 43)
      • 38. Wagner, R., Antoniou, I., Pedersen, S. M., et al: ‘The influence of the wind speed profile on wind turbine performance measurements’, Wind Energy, 2009, 12, (4), pp. 348362.
    44. 44)
      • 21. ‘Flexible solutions to optimize turbine performance’. Available at http://www.aventlidartechnology.com/en/applications/yaw-error-correction_116.html, accessed 15 December 2018.
    45. 45)
      • 30. Jowder, F. A. L.: ‘Wind power analysis and site matching of wind turbine generators in Kingdom of Bahrain’, Appl. Energy, 2009, 86, (4), pp. 538545.
    46. 46)
      • 6. Uluyol, O., Parthasarathy, G., Foslien, W., et al: ‘Power curve analytic for wind turbine performance monitoring and prognostics’. Annual Conf. of the Prognostics and Health Management Society, Montreal, Canada, September 2011.
    47. 47)
      • 26. Mamidipudi, P., Dakin, E., Hopkins, A. F., et al: ‘Yaw control: the forgotten controls problem’. EWEA Brussels, 2011.
    48. 48)
      • 28. Schlechtingen, M., Santos, I. F., Achiche, S.: ‘Using data mining approaches for wind turbine power curve monitoring: a comparative study’, IEEE Trans. Sustain. Energy, 2013, 4, (3), pp. 671679.
    49. 49)
      • 46. Neyman, J.: ‘Outline of a theory of statistical estimation based on the classical theory of probability’, Philos. Trans. R. Soc. Lond. A, 1937, 236, pp. 333380. doi: 10.1098/rsta.1937.0005.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-rpg.2018.0156
Loading

Related content

content/journals/10.1049/iet-rpg.2018.0156
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading