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.

[1]  S. A. Saleh,et al.  Development and testing of wavelet packet transform-based detector for ice accretion on wind turbines , 2011, 2011 Digital Signal Processing and Signal Processing Education Meeting (DSP/SPE).

[2]  Wei Qiao,et al.  Imbalance Fault Detection of Direct-Drive Wind Turbines Using Generator Current Signals , 2012 .

[3]  Jennifer G. Dy,et al.  From Transformation-Based Dimensionality Reduction to Feature Selection , 2010, ICML.

[4]  Lucila Ohno-Machado,et al.  Logistic regression and artificial neural network classification models: a methodology review , 2002, J. Biomed. Informatics.

[5]  Wei Qiao,et al.  Simulation investigation of wind turbine imbalance faults , 2010, 2010 International Conference on Power System Technology.

[6]  Michael Y. Hu,et al.  Forecasting with artificial neural networks: The state of the art , 1997 .

[7]  Shu-Hsien Liao,et al.  Artificial neural networks classification and clustering of methodologies and applications - literature analysis from 1995 to 2005 , 2007, Expert Syst. Appl..

[8]  N. Huang,et al.  The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis , 1998, Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[9]  Mukta Paliwal,et al.  Neural networks and statistical techniques: A review of applications , 2009, Expert Syst. Appl..

[10]  M. W Gardner,et al.  Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences , 1998 .

[11]  Minghao Zhao,et al.  Research on fault mechanism of icing of wind turbine blades , 2009, 2009 World Non-Grid-Connected Wind Power and Energy Conference.

[12]  S. Chandel,et al.  Selection of most relevant input parameters using WEKA for artificial neural network based solar radiation prediction models , 2014 .