Intelligent Control of a Large Variable Speed Wind Turbine

Abstract

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.

Optimized Fuzzy-Proportional/Integral/Derivative Controller for Aircraft Pitch Control

“…This allows the PSO to be applied for global optimization problems that are highly nonlinear, multimodel, or very high-dimensional. The algorithm has been successfully applied in fuzzy controller optimization problems [21,22,24,25] and has been known to demonstrate some advantages over GAs. In particular, the PSO uses the interaction between the particles in the swarm, has been known to demonstrate faster convergence rates, and has fewer parameters to adjust [19,22,24,30].…”

“…As generations are updated, the particles adjust their flying based on pbest and gbest, and both values are updated as needed as new solutions are discovered. The PSO algorithm also contains adjustable parameters representing inertial, cognitive, and social components of the swarm [21,22,28]. In this optimization problem, the best fitness of a solution corresponds to a minimal value as calculated by the cost function in Sec.…”

“…These controllers mesh the simplicity of PID controllers together with the nonlinear capabilities of fuzzy logic and can be applied to many different mechanical systems. The parameters for the fuzzy-PID controllers can be selected through expert knowledge and empirical testing, but evolutionary computational methods such as genetic algorithms (GAs) and particle swarm optimization (PSO) have been researched and applied to the tuning of both conventional PID and fuzzy controller parameters [19][20][21][22][23][24]. In the past, Mamdani-type fuzzy controllers have been successfully optimized by optimizing membership function shapes [25] or rules [26].…”

Validation of an integral sliding mode control for optimal control of a three blade variable speed variable pitch wind turbine

“…In [16] the WT controller is the combination of H 1 nonlinear torque control and linear blade pitch control. An intelligent control using neuro-fuzzy controller for a large wind turbine is proposed by the authors in [17]. PSO is used to train the adaptive neuro fuzzy controller.…”

Control of Variable Speed Variable Pitch Wind Turbine at Above and Below Rated Wind Speed

“…Nowadays fuzzy and neural networks (NN) are the powerful soft computing methods for controlling nonlinear systems. Authors in [17] discussed a fuzzy + and neurofuzzy controller for controlling the WT at above rated wind speed. PSO is used to train the adaptive neurofuzzy controller.…”