The topic of vortex-induced vibrations on a wind turbine blade has recently gained much attention due to its growing size and flexibility. To address this concern, a wind tunnel test was conducted to study the forced plunging and surging motion of a NACA0021 airfoil at 90° angle of attack. Results indicate that vortex lock-in occurred for a motion amplitude of one chord length even for a small frequency ratio (between motion frequency and static Strouhal frequency) of 0.39. Analysis of the drag coefficient, derived from the phase-averaged Particle Image Velocimetry (PIV) data, shows that a plunging airfoil experiences higher average loading than a surging airfoil, which is deemed to be more harmful considering the higher loading in the crossflow-direction due to the variation of effective angle of attack.

@en

Machine learning method has always been popular to solve wind turbine related problems at a data level. However, with the limitation of the availability of relevant data, transfer learning has gained increasing attention. In this study, traditional machine learning method of artificial neural networks (ANN), together with parameter-based transfer learning method has been used to estimate wind turbine load. First, ANN load model was built for DTU 10MW wind turbine as well as NREL 5MW wind turbine. Then, parameter-based transfer learning has been applied to the above-mentioned models to estimate load for a different turbine type or two mixed turbine types. Results indicate that ANN method provides good estimation on wind turbine fatigue load. For DTU 10MW ANN model, the trend of accuracy becomes steady as the number of input samples increases and 1500 samples is deemed as the optimal number of samples for training DTU 10MW. In addition, with transfer learning, it was succeeded in building NREL 5MW model with corresponding DTU 10MW pretrained model but failed in establishing mixed dataset model neither with DTU 10MW nor with NREL 5MW pretrained model. @en