a b s t r a c tThis paper proposes an approach of forming the average performance by Grey Modeling, and use an average performance as reference model for performing evolutionary computation with error type control performance index. The idea of the approach is to construct the reference model based on the performance of unknown systems when users apply evolutionary computation to fine-tune the control systems with error type performance index. We apply this approach to particle swarm optimization for searching the optimal gains of baseline PI controller of wind turbines operating at the certain set point in Region 3. In the numerical simulation part, the corresponding results demonstrate the effectiveness of Grey Modeling.
We present two intelligent controllers for large and flexible wind turbines operating in high-speed winds, a Fuzzy-P + I and an adaptive neuro-fuzzy controller. The control objective is to regulate the rotor speed at the given rated power in region 3 (full load) via collective blade pitch angle. The modeled turbine is a three-bladed, upwind machine with a flexible blade and tower. We use the particle swarm optimization method in off-line training for our adaptive neuro-fuzzy controller. Numerical simulations are performed using wind inflow step change with a set of input–output data of a nonlinear wind turbine model. We compare the performance of the proposed controllers with the baseline PI-controller. Simulation results confirm successful performance of the proposed controllers.
An adaptive neuro-fuzzy controller for large and flexible wind turbines operating in high-speed winds is presented. The control objective is to regulate the rotor speed at the given rated power in region 3 (full load) via collective blade pitch angle. The modeled turbine is a three-bladed, upwind machine with flexible blade and tower. We use the particle swarm optimization (PSO) method in off-line training of our adaptive neuro-fuzzy controller. Numerical simulations are performed using wind inflow step change with the nonlinear wind turbine model. We compare the performance of the proposed controller with the baseline PI controller. Simulation results confirm successful performance of the proposed controller.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.