Multilayer feedforward networks are universal approximators
Neural Networks
Universal approximation using radial-basis-function networks
Neural Computation
A learning algorithm for continually running fully recurrent neural networks
Neural Computation
Hi-index | 0.00 |
Wind turbine generators (WTGs) are usually equipped with one or more well-calibrated anemometers to measure wind speed for system monitoring, control, and protection. The use of these mechanical sensors increases the cost and hardware complexity and reduces the reliability of the WTG system. This paper proposes an echo-state-network (ESN)-based real-time wind speed estimation algorithm for WTG systems. The ESN is designed to provide a nonlinear inverse model of the WTG dynamics, which is used to estimate the wind speed in real time from the measured WTG output electrical power and shaft speed at any turbine blade pitch angle. The estimated wind speed is then used for wind-speed-sensorless control of the WTG system. The proposed algorithm is verified by sim ulation studies on a 3.6-MW wind turbine equipped with a doubly fed induction generator (DFIG).