Wind turbine load optimization control and verification based on wind speed estimator with time series broad learning system method

Abstract

With the rapid development of wind power, the power performance and mechanical load characteristics of wind turbine are simultaneously considered and focused. Normally, wind turbine senses the incoming flow characteristics through the nacelle mounted anemometer, due to the inability to perceive the characteristics of wind speed in advance, the control strategy makes the wind turbine itself to be at a passive state during the operation process. In this paper, a wind turbine mechanical load optimization control strategy based on an accurate wind speed estimator with time series Broad Learning System Method (BLSM) is designed, simulated and also verified. Firstly, the basic control theory of the BLSM and also a mechanical load optimization controller is designed. Then the OpenFAST is used to conduct a full-life cycle simulation comparison study on mechanical load characteristics of wind turbine before and after the implementation of the optimization control strategy. Finally, a field empirical mechanical load test is performed on the wind turbine, which is configured with BLSM mechanical load optimization control technology. The findings indicate that the implementation of this control strategy can significantly mitigate the ultimate and fatigue loads of wind turbines, particularly the fatigue loads of tower base tilt and roll bending moments, with a reduction rate of approximately 6.2% and 4.3%, respectively.