On-line estimation of induction generator parameters using adaptive neuro-fuzzy inference systems for wind energy conversion systems

This paper proposes a new method for online estimation of the induction generator parameters by means of adaptive neuro-fuzzy inference systems (ANFIS). The suggested technique can be applied to induction generators that are used in wind energy conversion systems (WECS). The WECS structure comprises a wind turbine, a three-phase induction generator and two back-to-back power converters. The WECS provides electric energy to the utility grid through an LCL filter. The selfadjustment of the induction generator parameters provides accuracy in the implementation of the field oriented control and therefore accomplishes optimal operation on the WECS. The proposed method is simple and, since it does not require time consuming off-line laboratory experiments, it can be easily applied to any wind energy system that is already in operation. Several simulation results will be presented in order to validate the theoretical considerations and demonstrate the operational improvements of the proposed system.