Fuzzy Rule Extraction from a trained artificial neural network using Genetic Algorithm for WECS control and parameter estimation
H. Kasiri, Mohammad Saniee Abadeh, Hamidreza Momeni, A. R. Motavalian · 2011
New wind turbines typically turn at variable speed. Thus, pitch control of the blades is generally employed to manage the energy captured throughout operation above and below rated wind speed. In this study, a new Genetic Fuzzy System (GFS) has been successfully executed to extract rules from Neural Network (NN). Fuzzy Rule Extraction from Neural network using Genetic Algorithm (FRENGA) recognizes disturbance wind in turbine input. Thus it generates desired pitch angle control. Consequently, output power has been regulated in the nominal range. Results indicate that the new proposed genetic fuzzy rule extraction system outperforms other existing methods in controlling the output during wind fluctuation.