Open AccessTakagi–Sugeno–Kang type probabilistic fuzzy neural network control for grid‐connected LiFePO 4 battery storage system
Author(s) -
Lin FaaJeng,
Huang MingShi,
Hung YingChih,
Kuan ChiHsuan,
Wang ShengLong,
Lee YihDer
Publication year - 2013
Publication title -
iet power electronics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.637
H-Index - 77
eISSN - 1755-4543
pISSN - 1755-4535
DOI - 10.1049/iet-pel.2012.0327
Subject(s) - computer science , battery (electricity) , artificial neural network , probabilistic logic , grid , fuzzy logic , control theory (sociology) , computer data storage , fuzzy control system , power (physics) , artificial intelligence , control (management) , computer hardware , mathematics , physics , geometry , quantum mechanics
A Takagi–Sugeno–Kang type probabilistic fuzzy neural network (TSKPFNN) control is proposed to control a grid‐connected LiFePO 4 battery storage system in this study. First, the modelling of the battery and bidirectional AC–DC converter are described in detail. Then, the active and reactive power controls using phase‐lock loop are briefly introduced. Moreover, to improve the control performance of the grid‐connected LiFePO 4 battery storage system, the TSKPFNN control, which combines the advantages of Takagi–Sugeno–Kang type fuzzy logic system and three‐dimensional membership function, is developed. The network structure, online learning algorithm using delta adaptation law and convergence analysis of the TSKPFNN are described in detail. Furthermore, a 32‐bit fixed‐point digital signal processor, TMS320F28035, is adopted for the implementation of the proposed intelligent controlled battery storage system. Finally, some experimental results are illustrated to show the validity of the proposed TSKPFNN control for the grid‐connected LiFePO 4 battery storage system.