Robust fault‐detection based on residual K–L divergence for wind turbines

Abstract

A robust fault-detection design based on residual Kullback-Leibler (K-L) divergence, which is applied to a 5 MW offshore wind turbine (WT) benchmark, is presented. The main challenges of the wind turbine fault detection lie in its complex operation conditions and disturbances as well as measurement noise. For overcoming these difficulties, the measured data are divided on the basis of the operation conditions of WT. The robust residual generator based on parity vector is adopted to calculate the residual under different operation conditions. The K-L divergence based on probability density function is employed to measure the residual. Then, the threshold for the fault detection is determined in line with both false alarm rate and missed detection rate. The simulation results show that the performance and effectiveness of the proposed robust fault detection are better than compared with other data-driven fault-detection approaches.