Sensorless control of PMSG in WECS using artificial neural network

This paper presents an artificial neural network (ANN) observer for a speed sensorless permanent magnet synchronous generator (PMSG) in wind energy conversion system (WECS). In order to perform maximum power point tracking control of the wind generation system, it is necessary to drive wind turbine at an optimal rotor speed. From the aspect of reliability and increase in cost, wind velocity sensor is not preferred too. Wind and rotor speeds sensorless operating methods for wind generation system using observer are proposed only by measuring phase voltages and currents. Maximum wind energy extraction is achieved by running the wind turbine generator in variable-speed mode. The robustness of the ANN against stator resistance variation is studied.