Artificial neural network and empirical mode decomposition based imbalance fault diagnosis of wind turbine using TurbSim, FAST and Simulink

In this study, an artificial neural network (ANN) and empirical mode decomposition (EMD) based condition monitoring approach of a wind turbine using Simulink, FAST (fatigue, aerodynamics, structures and turbulence) and TurbSim is presented. The complete dynamics of a permanent magnet synchronous generator (PMSG) based wind turbine [i.e. wind turbine generator (WTG)] model is simulated in an amalgamated domain of Simulink, FAST and TurbSim under six distinct conditions, i.e. aerodynamic asymmetry, rotor-furl imbalance, tail-furl imbalance, blade imbalance, nacelle-yaw imbalance and normal operating scenarios. The simulation results in time domain of the PMSG output stator current are decomposed into the intrinsic mode functions using EMD method then RapidMiner-based principal component analysis method is used to select most relevant input variables. An ANN model is then proposed to differentiate the normal operating scenarios from five fault conditions. The analysed results proclaim the effectiveness of the proposed approach to identify the different imbalance faults in WTG. The presented work renders initial results that are helpful for online condition monitoring and health assessment of WTG.