A Multilayer Perceptron Controller Applied to the Direct Power Control of a Doubly Fed Induction Generator

Author

Andreoli de Marchi, Rodrigo ; Dainez, Paulo Sergio ; Von Zuben, Fernando J. ; Bim, Edson

Author_Institution

Sch. of Electr. & Comput. Eng., State Univ. of Campinas (UNICAMP), Campinas, Brazil

Volume

5

Issue

2

fYear

2014

fDate

Apr-14

Firstpage

498

Lastpage

506

Abstract

This paper presents a direct power control strategy for a doubly fed induction generator by using an artificial neural network controller with the multilayer perceptron structure. This controller generates the direct- and quadrature-axis rotor voltage signals from both the stator current and voltage that are measured by the Hall sensors. The input variables of the control system are the rotor speed, the active and reactive power references, and their respective errors. The proposed control strategy allows the converter connected to the rotor terminals to operate with constant switching frequency. Digital simulation and experimental tests are performed for a 2.25-kW doubly fed induction generator to validate the proposed control strategy.

Keywords

asynchronous generators; controllers; multilayer perceptrons; reactive power control; artificial neural network controller; constant switching frequency; direct axis rotor voltage signals; direct power control; doubly fed induction generator; multilayer perceptron controller; quadrature axis rotor voltage signals; reactive power references; rotor speed; stator current; Control systems; Neurons; Reactive power; Rotors; Stators; Training; Voltage control; Artificial neural network (ANN); constant switching frequency; direct power control (DPC); doubly fed induction generator (DFIG); multilayer perceptron (MLP);

fLanguage

English

Journal_Title

Sustainable Energy, IEEE Transactions on

Publisher

ieee

ISSN

1949-3029

Type

jour

DOI

10.1109/TSTE.2013.2293621

Filename

6720130