LIDAR‐assisted radial basis function neural network optimization for wind turbines

Abstract

Increasing use of large commercial wind turbines motives energy efficiency improvement and fatigue load mitigation in wind turbines. Advanced control methods designed with remote sensing techniques are considered as promising solutions. In this paper, we design a radial basis function neural network feedforward control based on light detection and ranging (LIDAR) measurement. In this control method, the measurements of wind‐speed disturbance from LIDAR are used to train weights online in a neural network for optimizing the blade pitch angle and electromagnetic torque in a wind turbine, which is helpful in tracking the maximum wind energy and alleviate fatigue loads. The effectiveness of the proposed controller is validated with the National Renewable Energy Laboratory's typical three‐blade wind turbine. © 2017 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.