Direct Power Control of DFIG Based on Artificial Neural Networks

This paper deals with an artificial neural network (ANN) based direct power control (DPC) of a doubly-fed induction generator (DFIG) for wind turbine. In this scheme thetraditional switching lookup table is replaced with a multi-layer neural network. This change causes reduction of the complexityof the controller and effects of DFIG parameter variations. It also causes improvement of drive robustness and controller time response. In this paper Levenberg-Marquardt algorithm is chosen to train the neural network. The ANN based DPC scheme of DFIG drive is simulated using MATLAB. Simulation results of a 2MW DFIG system demonstrate the effectiveness and robustness of the proposed control strategy during variations of active and reactive power, machine parameters, and wind speed.

کلیدواژه ها:

Artificial Neural Network ، Direct power control ، doubly fed induction generator ، wind turbine