Wind Turbine Rotor Speed Design Optimization Considering Rain Erosion Based on Deep Reinforcement Learning

Rain erosion is one of the most detrimental factors contributing to wind turbine blade (WTB) coating fatigue damage especially for utility-scale wind turbines (WTs). For preventing WTB coating fatigue damage induced by rain erosion, this paper proposes a deep reinforcement learning (DRL)-based optimization method for finding the optimal rotor speed under different rain intensities and wind speeds. The paper first presents an efficient physics-based model for predicting WTB coating fatigue damage considering comprehensive blade coating fatigue mechanism, rain intensity distribution, and wind speed distribution. Then, a WT rotor speed design optimization problem is constructed to search optimal rotor speed under different rain intensities and wind speeds. To address the challenge of optimization efficiency, the original design optimization problem is converted to a DRL-based design optimization model. A hybrid reward is proposed to enhance the DRL agent trained by a deep deterministic policy gradient algorithm. Finally, the proposed DRL-based design optimization method is utilized to guide the optimal rotor speed scheduling of a 5-MW WT under given wind speeds and rain intensities data. The results show that the proposed method could extend the predicted WTB blade coating fatigue life by 2.55 times with a minor reduction in the energy yield (0.027%) compared to the original rotor speed schedule that only considers maximum power capture. The computational time of the proposed method is reduced significantly compared to that of the traditional gradient and evolutional design optimization methods