Hybrid Control of a Wind Induction Generator Based on Grey–Elman Neural Network

Author

Whei-Min Lin ; Chih-Ming Hong ; Cong-Hui Huang ; Ting-Chia Ou

Author_Institution

Dept. of Electr. Eng., Nat. Sun Yat-Sen Univ., Kaohsiung, Taiwan

Volume

21

Issue

6

fYear

2013

fDate

Nov. 2013

Firstpage

2367

Lastpage

2373

Abstract

This brief presents the design of an optimal wind energy control system for maximum power point tracking. With the help of a grey predictor for the preprocessor, a high-performance online training Elman neural network (ENN) is designed to derive the turbine speed needed to extract maximum power from wind. Moreover, the connective weights of the improved ENN are trained online by the backpropagation learning algorithm. Compared to earlier methods, better results are obtained when the ENN controller is used together with the grey system modeling approach. Performance of the proposed approach is verified by the experimental results.

Keywords

angular velocity control; asynchronous generators; backpropagation; control system synthesis; grey systems; neurocontrollers; wind power plants; ENN; ENN connective weights; Grey-Elman neural network; backpropagation learning algorithm; grey predictor; grey system modeling approach; high-performance online training Elman neural network; hybrid control; maximum power point tracking; optimal wind energy control system design; turbine speed; wind induction generator; Induction generators; Maximum power point trackers; Neural networks; Observers; Wind power generation; Wind turbines; Grey predictor; improved Elman neural network (ENN); maximum power point tracking; sliding-mode speed observer; wind turbine generator;

fLanguage

English

Journal_Title

Control Systems Technology, IEEE Transactions on

Publisher

ieee

ISSN

1063-6536

Type

jour

DOI

10.1109/TCST.2012.2231865

Filename

6407971