Optimal estimation and control of WECS via a Genetic Neuro Fuzzy Approach

Megawatt class wind turbines generally turn at variable speed in wind farm. Thus turbine operation must be controlled in order to maximize the conversion efficiency below rated power and reduce loading on the drive train. In addition, researchers particularly employ pitch control of the blades to manage the energy captured throughout operation above and below rated wind speed. In this study, fuzzy rules have been successfully extracted from Neural Network (NN) using a new Genetic Fuzzy System (GFS). Fuzzy Rule Extraction from Neural network using Genetic Algorithm (FRENGA) rejects wind disturbance in Wind Energy Conversion Systems (WECS) input with pitch angel control generation. Consequently, our proposed approach has regulated output aerodynamic power and torque in the nominal range. Results indicate that the new proposed genetic fuzzy rule extraction system outperforms one of the best and earliest methods in controlling the output during wind fluctuation.

► The first proposal in utilizing Genetic Neuro Fuzzy Systems to regulate optimal power in wind energy conversion systems.
► Fuzzy rules have been successfully extracted from Neural Network (NN) according to pitch angle control.
► The new proposed system outperforms earliest methods in controlling the output during wind fluctuation.
► Simulation results suggest that rule selection methods are useful as a knowledge acquisition tool for WECS.