期刊
ENERGIES
卷 13, 期 5, 页码 -出版社
MDPI
DOI: 10.3390/en13051063
关键词
wind turbine; maintenance; autoencoder; machine learning; reliability; data driven model; service; performance
资金
- German Federal Ministry for Economic Affairs and Energy through the research project ModernWindABS [0324128]
The usage of machine learning techniques is widely spread and has also been implemented in the wind industry in the last years. Many of these techniques have shown great success but need to constantly prove the expectation of functionality. This paper describes a new method to monitor the health of a wind turbine using an undercomplete autoencoder. To evaluate the health monitoring quality of the autoencoder, the number of anomalies before an event has happened are to be considered. The results show that around 35% of all historical events that have resulted into a failure show many anomalies. Furthermore, the wind turbine subsystems which are subject to good detectability are the rotor system and the control system. If only one third of the service duties can be planned in advance, and thereby the scheduling time can be reduced, huge cost saving potentials can be seen.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据