Data-driven Decision-Making Methodology for Prognostic and Health Management of Wind Turbines

The energy sector is undergoing a profound transition to meet climate objectives while ensuring global access. Out of all the renewable energy alternatives, wind energy is the most developed technology worldwide. In order to ensure the profitability of wind farms, it is necessary to reduce maintenance and operating costs. To this end, the wind energy industry has recently set its sight on the benefits of Prognostic. This latter aims to accurately predict when a certain equipment might fail by continuously monitoring the wind turbine health. In this paper, a data-driven decision-making methodology that combines prognostic and health management is proposed for a wind farm. The prognostic step aims to predict and isolate five components failures before they occur while the health management step uses this information to make decisions about the maintenance scheduling of wind turbines. The proposed methodology takes into account three maintenance actions, each associated to a specific cost: inspection, replacement or repair. Based on our predictions and associated maintenance costs, a total decision saving can be computed to evaluate our decision-making strategy and compare it with the literature. Finally, the proposed methodology is implemented and validated on real world data sets.