A Wind Turbine Blade Damage Detection System Based on Data Analysis: An Academic Example on the Use of Histograms Leonardo Acho and Pablo Buenestado   2018/04/20

Abstract

The main objective of this paper is to introduce an academic example on the use of histograms to develop a wind turbine blade fault (or damage) detection system. This approach merely uses data analysis obtained from a generated wind turbine power. Then, and based on the power curve of a wind turbine, histograms are obtained, first, for the healthy wind turbine operation, and then, for two cases on faulty wind turbine operations. By comparing them, a faulty behaviour of a wind turbine is detectable. Finally, according to our numerical example, the proposed technique seems a realistic case to students on the statistic and probability fields as a useful academic example.

Authors and affiliations

Leonardo Acho1 and Pablo Buenestado1
1. Department of Mathematics. E.E.B.E., Polytechnic University of Catalonia. Barcelona (Spain)

Key words

Blade Wind Turbine, Data Analysis, Histograms, Fault Detection System.

References

[1] Wang, Jianzhou, Jianming Hu, and Kailiang Ma. "Wind speed probability distribution estimation and wind energy assessment." Renewable and Sustainable Energy Reviews60 (2016): 881-899.

[2] Arslan, Talha, Sukru Acitas, and Birdal Senoglu. "Generalized Lindley and Power Lindley distributions for modeling the wind speed data." Energy Conversion and Management 152 (2017): 300-311.

[3] Luo, Ningsu; Vidal, Yolanda; Acho, Leonardo (ed.). Wind turbine control and monitoring. Berlin: Springer, 2014.

[4] Vidal, Yolanda, et al. "Fault diagnosis and fault-tolerant control of wind turbines via a discrete time controller with a disturbance compensator." Energies 8.5 (2015): 4300-4316.

[5] Janssens, Olivier, et al. "Data-driven multivariate power curve modeling of offshore wind turbines." Engineering Applications of Artificial Intelligence 55 (2016): 331-338.

[6] Jung, Christopher, and Dirk Schindler. "Global comparison of the goodness-of-fit of wind speed distributions." Energy Conversion and Management 133 (2017): 216-234.

[7] Ouyang, Tinghui, Xiaoming Zha, and Liang Qin. "A combined multivariate model for wind power prediction." Energy Conversion and Management 144 (2017): 361-373.

[8] Mar.iukaitis, Mantas, et al. "Non-linear regression model for wind turbine power curve." Renewable Energy (2017).

[9] Devore, Jay L. Probability and Statistics for Engineering and the Sciences. Cengage learning, 2011.

[10] Leon-Garcia, Alberto. Probability, statistics, and random processes for electrical engineering. USA, 2017.

[11] Zaher, A. S. A. E., et al. "Online wind turbine fault detection through automated SCADA data analysis." Wind Energy 12.6 (2009): 574-593.

[12] EFRON, Bradley; TIBSHIRANI, Robert. Statistical data analysis in the computer age. Science, 1991, p. 390-395.

[13] KARIP, Emin. Mult.level Analys.s of H.erarch.cally Structured Educat.onal Data. Kuram ve Uygulamada Egitim Yonetimi Dergisi, 1996, vol. 2, no 3, p. 409-420.

[14] ANOVA, Split-plot. Statistical computing: an introduction to data analysis using S-Plus. 2002. [15] Crawley, Michael J. The R book. John Wiley & Sons, 2012.