Abstract
Wind turbines typically do not operate in the ideal operating conditions, leading to abnormal behaviour that is reflected in their power curves. This abnormal behaviour can affect the performance of condition monitoring processes, as it may mask faulty behaviour. By cleaning other abnormal data, such as curtailment, models can learn the normal behaviour of the turbines. This paper presents a novel cleaning technique that utilises a combination of data binning and the Mahalanobis distance. This removes between 5 to 6% of the data, without great loss of normal data. When compared against other data cleaning techniques, the one presented in this paper produces a more ideal power curve. This technique could improve the performance of data-based condition monitoring techniques.
Original language | English |
---|---|
Title of host publication | Journal of Physics: Conference Series |
Subtitle of host publication | Journal of Physics: Conference Series Table of contents Volume 2151 2022 Previous issueNext issue WindEurope Electric City 2021 23/11/2021 – 25/11/2021 Copenhagen, Denmark |
Publisher | IOP Science |
Volume | 2151 |
DOIs | |
Publication status | Published - 19 Jan 2022 |
Event | WindEurope Electric City 2021 Conference - Copenhagen, Denmark Duration: 23 Nov 2021 → 25 Nov 2021 |
Conference
Conference | WindEurope Electric City 2021 Conference |
---|---|
Country/Territory | Denmark |
City | Copenhagen |
Period | 23/11/21 → 25/11/21 |