A Study of Wind Turbine Performance Decline with Age through Operation Data Analysis

作者: Raymond Byrne , Davide Astolfi , Francesco Castellani , Neil J. Hewitt

DOI: 10.3390/EN13082086

关键词:

摘要: Ageing of technical systems and machines is a matter fact. It therefore does not come as surprise that an energy conversion system such wind turbine, which in particular operates under non-stationary conditions, subjected to performance decline with age. The present study presents analysis the deterioration age Vestas V52 installed 2005 at Dundalk Institute Technology campus Ireland. turbine has operated from October 2018 its original gearbox, subsequently been replaced 2019. Therefore, key point operation data spanning over thirteen years have analysed for estimating how degrades time. To this end, one most innovative approaches control monitoring employed: multivariate Support Vector Regression Gaussian Kernel, whose target power output turbine. Once model trained reference set, degradation assessed by studying residuals between estimates measurements evolve. Furthermore, curve through binning method performed estimate Annual Energy Production variations suggests convenient strategy test case (running gearbox until end life) indeed adopted. Summarizing, main results are follows: ten-year period, declined order 5%; seems be nonlinear pass by; after replacement, fraction recovered, though all because rest operating state. Finally, it should noted basically consistent few available literature.

参考文章(34)
Huan Long, Long Wang, Zijun Zhang, Zhe Song, Jia Xu, Data-Driven Wind Turbine Power Generation Performance Monitoring IEEE Transactions on Industrial Electronics. ,vol. 62, pp. 6627- 6635 ,(2015) , 10.1109/TIE.2015.2447508
Yogesh Kumar, Jordan Ringenberg, Soma Shekara Depuru, Vijay K Devabhaktuni, Jin Woo Lee, Efstratios Nikolaidis, Brett Andersen, Abdollah Afjeh, None, Wind energy: Trends and enabling technologies Renewable & Sustainable Energy Reviews. ,vol. 53, pp. 209- 224 ,(2016) , 10.1016/J.RSER.2015.07.200
Alex J. Smola, Bernhard Schölkopf, A tutorial on support vector regression Statistics and Computing. ,vol. 14, pp. 199- 222 ,(2004) , 10.1023/B:STCO.0000035301.49549.88
Antonino Marvuglia, Antonio Messineo, Monitoring of wind farms’ power curves using machine learning techniques Applied Energy. ,vol. 98, pp. 574- 583 ,(2012) , 10.1016/J.APENERGY.2012.04.037
Davide Astolfi, Francesco Castellani, Alberto Garinei, Ludovico Terzi, Data mining techniques for performance analysis of onshore wind farms Applied Energy. ,vol. 148, pp. 220- 233 ,(2015) , 10.1016/J.APENERGY.2015.03.075
Iain Staffell, Richard Green, How does wind farm performance decline with age Renewable Energy. ,vol. 66, pp. 775- 786 ,(2014) , 10.1016/J.RENENE.2013.10.041
Wenxian Yang, Richard Court, Jiesheng Jiang, Wind turbine condition monitoring by the approach of SCADA data analysis Renewable Energy. ,vol. 53, pp. 365- 376 ,(2013) , 10.1016/J.RENENE.2012.11.030
Shane Butler, John Ringwood, Frank O'Connor, Exploiting SCADA system data for wind turbine performance monitoring conference on control and fault tolerant systems. pp. 389- 394 ,(2013) , 10.1109/SYSTOL.2013.6693951
Andrew Kusiak, Anoop Verma, Monitoring Wind Farms With Performance Curves IEEE Transactions on Sustainable Energy. ,vol. 4, pp. 192- 199 ,(2013) , 10.1109/TSTE.2012.2212470
Edzel Lapira, Dustin Brisset, Hossein Davari Ardakani, David Siegel, Jay Lee, Wind turbine performance assessment using multi-regime modeling approach Renewable Energy. ,vol. 45, pp. 86- 95 ,(2012) , 10.1016/J.RENENE.2012.02.018