As part of our ongoing research and development (R&D) efforts, we are pleased to announce the publication of a new technical paper: Static and Dynamic Yaw Misalignments of Wind Turbines and Machine Learning Based Correction Methods Using LiDAR Data.
Published in prominent industry journal IEEE Transactions on Sustainable Energy, the paper draws on results from two South Korean wind farms to demonstrate that machine learning algorithms are capable of mitigating both static and dynamic yaw misalignments – with an error reduction almost double that of static methods.
Key findings of the paper include:
- LiDAR is particularly effective for tackling static yaw misalignments as it can provide more accurate wind measurements then a vane sensor, and because it is cost effective when used for a limited time.
- The LiDAR method can be extended to dynamic yaw misalignment correction by modelling the misalignment error’s dependency on wind direction, wind speed, and rotor speed.
- Machine learning algorithms can be trained to estimate the LiDAR’s wind direction, meaning that dynamic errors can be mitigated from within SCADA data, even after the LiDAR is removed.
- Machine learning algorithms are capable of mitigating both static and dynamic yaw misalignments. Using machine learning doubled the error reduction level – from just 22.6% using a static method to 44.4% achieved with a machine learning method.
Download the paper here.