Open AccessHardware implementation of type‐2 neuro‐fuzzy controller‐based direct power control for three‐phase active front‐end rectifiers
Author(s) -
Acikgoz Hakan,
Kumar Amit,
Beiranvand Hamzeh,
Sekkeli Mustafa
Publication year - 2019
Publication title -
international transactions on electrical energy systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.428
H-Index - 42
ISSN - 2050-7038
DOI - 10.1002/2050-7038.12066
Subject(s) - rectifier (neural networks) , control theory (sociology) , converters , controller (irrigation) , dspace , computer science , front and back ends , power (physics) , three phase , artificial neural network , electronic engineering , engineering , control engineering , control (management) , algorithm , recurrent neural network , artificial intelligence , voltage , electrical engineering , agronomy , physics , quantum mechanics , biology , operating system , stochastic neural network
Summary Simple implementation, robust response, good dynamic, and steady‐state performances are empowering direct power control (DPC) as an accepted control method in power electronic converters. One of the key converters are active front‐end rectifiers that are used in many applications. In this paper, type‐2 neuro‐fuzzy controller based DPC (T2NFC‐DPC) is designed for active front‐end rectifier. T2NFC uses an upper and lower bounds for membership functions and provides a better tool for defining uncertain systems and also neural networks help to improve the speed of convergence in tracking the reference signals. In the proposed method, error and change of error are used to train T2NFC‐DPC. The effectiveness of the proposed method is validated using experimental model. An experimental setup is developed using dSPACE 1104 control board in order to show the applicability of the proposed method. Experimental results show that T2NFC‐DPC outperforms against conventional proportional‐integral DPC (PI‐DPC) method.