Faults diagnosis of wind energy conversion chain based on doubly fed induction generator by principal components analysis method

Abstract

This paper deals with the faults diagnosis of wind energy conversion chain based on doubly fed induction generator (DFIG). A complete model of the device is presented. An accurate model of the induction machine is proposed because the considered faults are come from this element. The developed model of the conversion chain allows studying both the cases with and without faults. The principal components analysis (PCA) method is then used for system diagnosis. This approach is based on residues analysis. The complete model has been implemented on the Matlab software to perform the matrix data needed for PCA method. The simulation results of several variables such as stator and rotor currents, shaft rotational speed, electrical power, electromagnetic torque and other variables issued from mathematical transformations of healthy and faulted DFIG are analyzed. Comparisons of simulation results with those of other diagnostic methods are performed to show importance of the PCA method in fault diagnosis of systems. The results show the efficiency of the approach but require a good choice of the number of principal components.