| KEYWORD |
Machine Learning Strategies for the Structural Health Monitoring of wind turbines and farms
Reference persons CECILIA SURACE
Description Recent years have seen an exponential growth of the investments in the field of wind energy in Italy and Europe. In the decade 2020-2030, the British government will allocate £ 160 million to offshore wind farms, creating over 60,000 jobs [1]. In the same decade, the European Commission's green deal will provide over € 503 billion for the "green industrial revolution" [2], including at least 37% of the recovery fund grants destined for Italy [3]; it is estimated that this funding will generate over 700,000 new jobs on the European continent [4].
The aim of the thesis is to compare several data-driven, Machine Learning (ML)-based Structural Health Monitoring (SHM) techniques for wind power applications [5]. The study will focus both on the single wind turbine and on an extended wind farm [6], on-shore as well as near- and off-shore [7].
The thesis work will be carried out mainly through MatLab software.
[1] https://www.bbc.com/news/uk-politics-54421489
[2] https://ec.europa.eu/commission/presscorner/detail/en/fs_20_40
[3] https://www.linkiesta.it/2020/09/recovery-plan-italia-europa-linee-guida/
[4] https://www.linkiesta.it/2020/05/recovery-fund-750-miliardi-commissione/
[5] Dervilis, N., Choi, M., Taylor, S. G., Barthorpe, R. J., Park, G., Farrar, C. R., & Worden, K. (2014). On damage diagnosis for a wind turbine blade using pattern recognition. Journal of sound and vibration, 333(6), 1833-1850.
[6] Papatheou, E., Dervilis, N., Maguire, A. E., Antoniadou, I., & Worden, K. (2015). A performance monitoring approach for the novel Lillgrund offshore wind farm. IEEE Transactions on Industrial Electronics, 62(10), 6636-6644.
[7] Antoniadou, I., Dervilis, N., Papatheou, E., Maguire, A. E., & Worden, K. (2015). Aspects of structural health and condition monitoring of offshore wind turbines. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 373(2035), 20140075.
Deadline 06/10/2021
PROPONI LA TUA CANDIDATURA