Open AccessPower‐control and speed‐control modes of a DFIG using adaptive sliding mode type‐2 neuro‐fuzzy for wind energy conversion system
Author(s) -
Moradi Hassan,
Yaghobi Hamid,
AlinejadBeromi Yousef,
Bustan Danyal
Publication year - 2020
Publication title -
iet renewable power generation
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.005
H-Index - 76
eISSN - 1752-1424
pISSN - 1752-1416
DOI - 10.1049/iet-rpg.2019.1270
Subject(s) - control theory (sociology) , controller (irrigation) , sliding mode control , electronic speed control , variable speed wind turbine , wind power , fuzzy logic , fuzzy control system , wind speed , pid controller , computer science , engineering , control engineering , voltage , permanent magnet synchronous generator , temperature control , control (management) , nonlinear system , physics , electrical engineering , quantum mechanics , artificial intelligence , meteorology , agronomy , biology
This study proposes an adaptive sliding mode type‐2 neuro‐fuzzy control scheme for power‐control and speed‐control modes of doubly fed induction generator (DFIG). DFIG‐based wind turbine system operates as variable‐speed wind energy conversion system (WECS) with constant frequency. In the proposed controller design, a sliding mode control (SMC) strategy is used for online training of the parameters of type‐2 fuzzy set (T2FS) membership functions. Due to the uncertainty of the wind speed and variation in parameters in the WECS, an interval T2FS is used in the proposed control scheme. Based on the controller inputs, the SMC adaptive strategy is used to tune the parameters of antecedent and consequent parts of T2FS. These inputs are active and reactive power and rotor speed errors and their time derivative. These inputs fed to the type‐2 neuro‐fuzzy system. The results of simulation for a 1.5 MW DFIG‐based WECS are compared with the classical proportional–integral (PI) controller and type‐1 neuro‐fuzzy controller to validate the effectiveness of the proposed controller in power‐control and speed‐control regions. The results of simulation indicate that, in comparison to the PI and type‐1 neuro‐fuzzy controller, the proposed control scheme has better performance in both power‐control and speed‐control modes.