What is unsupervised learning? Unsupervised Learning (see wikipedia) is used when no historical data is available that involves past faulty behaviour and/or ageing progression. Therefore,
Wind turbines ageing
Wind turbines are subject to a high level of stress due to several reasons. A fair estimation of the turbine state of health is mandatory for a rational optimization of inspection, and for a better load distribution in the case of farms.
Derive aging indicators of wind turbines operating in the same area from SCADA operating data (105 dimensional vector, Engie Open Data) in order to supervise the aging of a wind turbine farm and optimize its maintenance planning
An average aging model for the whole wind turbine farm was built showing comparative aging and load on wind turbines and their subsystems in the same farm. The comparative aging allowed to detect turbines that were over or under loaded and to spread the load in order to avoid premature aging.