Power converter faults in wind turbines often lead to costly downtime and repeated maintenance. We present a practical, explainable, and fully data-driven approach that utilizes high-resolution converter control system records, 1 min operating data, and event logs to predict whether a fault leads to a long or short standstill. By combining engineered features with interpretable feature reduction, we achieve 89 % accuracy and an F1 score of 0.86, providing support for remote decision-making.

Vortex generators (VGs) are being used to prevent flow separation and stall on wind turbine blades. Optimal VG designs are chosen from steady investigations, assuming similar separation control characteristics between steady and unsteady conditions. Surface pressure measurements on a thick pitching airfoil with VGs show that VGs larger than the optimal steady size and rectangular VGs instead of the common triangular VGs must be used to consistently prevent unsteady flow separation and dynamic stall.

We formulate a controller for wind turbines that has three main characteristics. First, it optimizes profit by balancing revenue from power generation with cost. Second, cost includes the effects of cyclic fatigue that, departing from most of the existing literature on control, is rigorously accounted for by an exact cycle counting on receding horizons. Third, it uses a model capable of learning and improving its performance based on measured or synthetic data.

Mesoscale simulations with the Fitch wind farm parameterization were compared to large-domain large-eddy simulations for three planned offshore wind farms under varied atmospheric conditions. Mesoscale runs captured key wake deficit patterns and stability effects in the wind farm wake evolution but underestimated power losses from internal wakes, especially in aligned winds or stable conditions. Results highlight mesoscale strengths for large-scale wakes and limits for turbine-level losses.