Recurrent functional-link-based fuzzy-neural-network-controlled induction-generator system using improved particle swarm optimization

Faa Jeng Lin, Li Tao Teng, Jeng Wen Lin, Syuan-Yi Chen

Research output: Contribution to journalArticle

83 Citations (Scopus)

Abstract

A recurrent functional-link (FL)-based fuzzy-neural-network (FNN) controller with improved particle swarm optimization (IPSO) is proposed in this paper to control a three-phase induction-generator (IG) system for stand-alone power application. First, an indirect field-oriented mechanism is implemented for the control of the IG. Then, an ac/dc power converter and a dc/ac power inverter are developed to convert the electric power generated by a three-phase IG from variable frequency and variable voltage to constant frequency and constant voltage, respectively. Moreover, two online-trained recurrent FL-based FNNs are introduced as the regulating controllers for both the dc-link voltage of the ac/dc power converter and the ac line voltage of the dc/ac power inverter. Furthermore, IPSO is adopted to adjust the learning rates to improve the online learning capability of the recurrent FL-based FNNs. Finally, some experimental results are provided to demonstrate the effectiveness of the proposed recurrent FL-based FNN-controlled IG system.

Original languageEnglish
Pages (from-to)1557-1577
Number of pages21
JournalIEEE Transactions on Industrial Electronics
Volume56
Issue number5
DOIs
Publication statusPublished - 2009 Jun 3

Fingerprint

Fuzzy neural networks
Asynchronous generators
Particle swarm optimization (PSO)
Electric potential
Power converters
Controllers

Keywords

  • Functional link neural network (FLNN)
  • Induction generator
  • Induction generator (IG)
  • Particle swarm optimization (PSO)
  • Power converter

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Control and Systems Engineering
  • Computer Science Applications

Cite this

Recurrent functional-link-based fuzzy-neural-network-controlled induction-generator system using improved particle swarm optimization. / Lin, Faa Jeng; Teng, Li Tao; Lin, Jeng Wen; Chen, Syuan-Yi.

In: IEEE Transactions on Industrial Electronics, Vol. 56, No. 5, 03.06.2009, p. 1557-1577.

Research output: Contribution to journalArticle

@article{5b42e7a6af1147e68c1d068ef1e83c48,
title = "Recurrent functional-link-based fuzzy-neural-network-controlled induction-generator system using improved particle swarm optimization",
abstract = "A recurrent functional-link (FL)-based fuzzy-neural-network (FNN) controller with improved particle swarm optimization (IPSO) is proposed in this paper to control a three-phase induction-generator (IG) system for stand-alone power application. First, an indirect field-oriented mechanism is implemented for the control of the IG. Then, an ac/dc power converter and a dc/ac power inverter are developed to convert the electric power generated by a three-phase IG from variable frequency and variable voltage to constant frequency and constant voltage, respectively. Moreover, two online-trained recurrent FL-based FNNs are introduced as the regulating controllers for both the dc-link voltage of the ac/dc power converter and the ac line voltage of the dc/ac power inverter. Furthermore, IPSO is adopted to adjust the learning rates to improve the online learning capability of the recurrent FL-based FNNs. Finally, some experimental results are provided to demonstrate the effectiveness of the proposed recurrent FL-based FNN-controlled IG system.",
keywords = "Functional link neural network (FLNN), Induction generator, Induction generator (IG), Particle swarm optimization (PSO), Power converter",
author = "Lin, {Faa Jeng} and Teng, {Li Tao} and Lin, {Jeng Wen} and Syuan-Yi Chen",
year = "2009",
month = "6",
day = "3",
doi = "10.1109/TIE.2008.2010105",
language = "English",
volume = "56",
pages = "1557--1577",
journal = "IEEE Transactions on Industrial Electronics",
issn = "0278-0046",
publisher = "IEEE Industrial Electronics Society",
number = "5",

}

TY - JOUR

T1 - Recurrent functional-link-based fuzzy-neural-network-controlled induction-generator system using improved particle swarm optimization

AU - Lin, Faa Jeng

AU - Teng, Li Tao

AU - Lin, Jeng Wen

AU - Chen, Syuan-Yi

PY - 2009/6/3

Y1 - 2009/6/3

N2 - A recurrent functional-link (FL)-based fuzzy-neural-network (FNN) controller with improved particle swarm optimization (IPSO) is proposed in this paper to control a three-phase induction-generator (IG) system for stand-alone power application. First, an indirect field-oriented mechanism is implemented for the control of the IG. Then, an ac/dc power converter and a dc/ac power inverter are developed to convert the electric power generated by a three-phase IG from variable frequency and variable voltage to constant frequency and constant voltage, respectively. Moreover, two online-trained recurrent FL-based FNNs are introduced as the regulating controllers for both the dc-link voltage of the ac/dc power converter and the ac line voltage of the dc/ac power inverter. Furthermore, IPSO is adopted to adjust the learning rates to improve the online learning capability of the recurrent FL-based FNNs. Finally, some experimental results are provided to demonstrate the effectiveness of the proposed recurrent FL-based FNN-controlled IG system.

AB - A recurrent functional-link (FL)-based fuzzy-neural-network (FNN) controller with improved particle swarm optimization (IPSO) is proposed in this paper to control a three-phase induction-generator (IG) system for stand-alone power application. First, an indirect field-oriented mechanism is implemented for the control of the IG. Then, an ac/dc power converter and a dc/ac power inverter are developed to convert the electric power generated by a three-phase IG from variable frequency and variable voltage to constant frequency and constant voltage, respectively. Moreover, two online-trained recurrent FL-based FNNs are introduced as the regulating controllers for both the dc-link voltage of the ac/dc power converter and the ac line voltage of the dc/ac power inverter. Furthermore, IPSO is adopted to adjust the learning rates to improve the online learning capability of the recurrent FL-based FNNs. Finally, some experimental results are provided to demonstrate the effectiveness of the proposed recurrent FL-based FNN-controlled IG system.

KW - Functional link neural network (FLNN)

KW - Induction generator

KW - Induction generator (IG)

KW - Particle swarm optimization (PSO)

KW - Power converter

UR - http://www.scopus.com/inward/record.url?scp=66149096709&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=66149096709&partnerID=8YFLogxK

U2 - 10.1109/TIE.2008.2010105

DO - 10.1109/TIE.2008.2010105

M3 - Article

AN - SCOPUS:66149096709

VL - 56

SP - 1557

EP - 1577

JO - IEEE Transactions on Industrial Electronics

JF - IEEE Transactions on Industrial Electronics

SN - 0278-0046

IS - 5

ER -