Adaptive control for variable-speed wind generation systems using advanced RBF Neural Network

The generation of clean energy from wind has recently received huge attention. Thanks to the current advances of adaptive algorithms due to their benefits and flexibility. The paper introduces a new smart radial basis function (RBF) neural network to extract the optimal energy from wind for wind energy conversion systems. This scheme uses the electrical energy of the doubly fed induction-generator (DFIG) as an input in wind turbines drives a DFIG to acquire maximum energy from the available wind under uncertainties and fast-changing wind conditions. Thus, to prove the quality of our proposed intelligent scheme, a comparative study with conventional optimum power is applied to a wind turbine driving a class of 1.5 MW DFIG during the transient operation. Furthermore, the analysis and the interpretation of raw and processed real measured data using the process of linear interpolation through Matlab/Simulink illustrate the relevance and the performance of the sensorless controller for the overall wind turbine system. Briefly, the numerical simulation studies show that a good efficiency and improved tracking of the smart RBF-neural network controller when implemented online below the real wind speed despite the unknown parameters.

show abstract

Adaptive control for variable-speed wind generation systems using advanced RBF Neural Network

Cited by 4 publications

References 13 publications

Control of Overload Safety in Wind Turbines Through Blade Pitch Control Implementing Artificial Intelligence

Control of Overload Safety in Wind Turbines Through Blade Pitch Control Implementing Artificial Intelligence

Artificial Intelligence-based MPPT Techniques in Wind Energy Systems: A Literature Review

Intelligent controller for maximum power extraction of wind generation systems using ANN

Contact Info

Product

Resources

About