A Combined Data-Driven and Simulation Approach for Wind Turbine Blade Icing Prediction in Cold Regions

The occurrence of freezing and icing on wind turbine blades during a cold wave can lead to partial or complete loss of power generation, which can have a significant impact on the power grid. Accurate prediction of the impact of a cold wave on wind turbine generation is essential for power grid control centers to apply emergency plans. However, determining the correlation between ice weight and weather conditions is technically challenging, as data-driven methods rely heavily on data quality and simulation methods can be time-consuming. Therefore, this study proposes a novel approach that combines data-driven and simulation methods to build a dependable wind turbine blade icing prediction model. Firstly, the mechanism and numerical simulation of icing on wind turbine blades were discussed. Secondly, the necessary data for a reliable prediction model was generated through numerical simulation. Lastly, a statistical approach was adopted for building the icing prediction model. The proposed model enables blade icing prevention in wind turbines via meteorological warning information ahead of a cold wave. The findings of this study have significant implications for the wind energy industry in cold regions.