Real-time yaw-misalignment calibration and field-test verification of wind turbine via machine learning methods

It has become a general consensus that nacelle-mounted LiDAR can be used to calibrate the yaw misalignment or drive the real-time yaw motions for wind turbines, which would improve the power-generation efficiency. The advantage of LiDAR utilization is that the accuracy of inflow wind measurement would be greatly improved, while its disadvantage is that the cost remains high and the data validity is not sufficiently high. In this paper, an efficient machine learning method for estimating LiDAR measurement is developed to establish the real-time yaw calibration framework and sustain the LiDAR rolling utilization. Firstly, the correlation of LiDAR measurement with SCADA features is analyzed to estimate LiDAR measurement using only SCADA data. Secondly, several machine learning algorithms are studied for performance comparison, and the dependence of each algorithm on data size is also analyzed. Experimental results show that, the proposed XGBoost algorithm has high accuracy, requires less data, and can quickly calibrate the yaw misalignment. Finally, the field testing is held for a commercial 2 MW wind turbine to verify the effectiveness. The field-test results show that the proposed method is feasible for industrial applications and can improve the annual theoretical power generation by 3.66% compared to the situation without calibration, which also provides an executable and economical solution for LiDAR replacement planning.