France – Mardi 22/10/2019 – energiesdelamer.eu. Ancre – Colloque des Doctorants – 7ème intervenant : David Collet
“Wind energy production has been exponentially growing in the last decades, with about 591 GW globally installed in 2018 compared with 94 GW in 2007.
In order to achieve COP21 objective, which is to maintain CO2 emissions below 5.4 x 1012 kilograms per year, the wind energy industry is expected to develop even further. This energetic transition represents a large economic investment.In a context of wind power production growth, it is necessary to optimize the levelized cost of energy by reducing the wind turbine operation and maintenance costs.
This presentation addresses these issues through an innovative machine learning approach, applied to individual pitch control and based on wind conditions clustering, from light detection and ranging (LiDAR) wind field reconstruction. A set of controllers is first designed, and machine learning regression is performed to predict the economic cost of the wind turbine in closed-loop for each of these controllers, given a cluster of wind conditions. This allows online selection of the best-suited controller with respect to mechanical loads reduction for each wind condition. Preliminary tests show promising results regarding the effectiveness of this method in reducing wind turbine fatigue when compared to a single optimized individual pitch controller. The main advantages of this approach is to limit the sensitivities to controller tuning procedure and to provide an economically driven control strategy that can be effectively adapted to different wind turbine systems.”
Agenda des événements sélectionnés par energiesdelamer.eu : Journée Doctoriale sur les thématiques du GP5 de l’ANCRE 23/10/2019
Publicités Google :
