Skip to Main Content
Operation of wind turbine generator (WTG) systems in the above-rated region characterised by high wind turbulence intensities invariably induces fatigue stresses on the drive train components. This demands a trade-off between two performance metrics: maximisation of energy harvested from the wind and minimisation of the damage caused by mechanical fatigue. A learning adaptive controller in the form of a self-tuning regulator (STR) for output power levelling and decrementing fatigue loads is presented. The STR incorporates a hybrid controller of a linear quadratic Gaussian (LQG), neurocontroller and a linear parameter estimator (LPE). The main control objective is to regulate the relationship between rotational speed and wind speed by controlling the generator torque and further, the rotational speed. A pitch actuator ensures system operation geared toward maintaining output at rated power. A second-order model and a stochastic wind field model are used to systematically analyse the dynamical relationship between the WTG subsystems. The LQG is used as a basis upon which the performance of the proposed method in the trade-off studies is assessed. Simulation results indicate the proposed control scheme captures the performance and critical reliability loci thereby ensuring the wind turbine operates optimally in mechanically harmless conditions.