Neural control of the self-excited induction generator for variable-speed wind turbine generation

Abstract

In this paper, a steady state and transient analysis of a stand alone Self Excited Induction Generator (SEIG) is presented. The conventional dynamic modelling of this system is enhanced by using an Artificial Neural Network (ANN) to model the induction generator. The proposed ANN model is used to obtain the inverse model of the SEIG.. The network is trained using the output voltage, the load and the wind turbine speed as an input vector and the required capacitor bank as the target output. The obtained inverse model is then cascaded with the SEIG.. The composed system results in an identity mapping between the desired response and the induction generator output voltage. Thus the network acts directly as a controller. The dynamic and simulation analysis of the SEIG are also studied in this paper. The d-q model is used to study the behaviour of the SEIG for both voltage build-up and wind speed disturbance conditions. © Springer-Verlag Berlin Heidelberg 2012.