An improved elman neural network controller based on quasi-ARX neural network for nonlinear systems

Imam Sutrisno, Mohammad Abu Jami'in, Takayuki Furuzuki

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

An improved Elman neural network (IENN) controller with particle swarm optimization (PSO) is presented for nonlinear systems. The proposed controller is composed of a quasi-ARX neural network (QARXNN) prediction model and a switching mechanism. The switching mechanism is used to guarantee that the prediction model works well. The primary controller is designed based on IENN using the backpropagation (BP) learning algorithm with PSO. PSO is used to adjust the learning rates in the BP process for improving the learning capability. The adaptive learning rates of the controller are investigated via the Lyapunov stability theorem. The proposed controller performance is verified through numerical simulation. The method is compared with the fuzzy switching and 0/1 switching methods to show its effectiveness in terms of stability, accuracy, and robustness.

Original languageEnglish
Pages (from-to)494-501
Number of pages8
JournalIEEJ Transactions on Electrical and Electronic Engineering
Volume9
Issue number5
DOIs
Publication statusPublished - 2014

Fingerprint

Nonlinear systems
Neural networks
Controllers
Particle swarm optimization (PSO)
Backpropagation algorithms
Backpropagation
Learning algorithms
Computer simulation

Keywords

  • Elman neural network
  • Lyapunov stability theorem
  • Particle swarm optimization
  • Quasi-ARX neural network

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

An improved elman neural network controller based on quasi-ARX neural network for nonlinear systems. / Sutrisno, Imam; Abu Jami'in, Mohammad; Furuzuki, Takayuki.

In: IEEJ Transactions on Electrical and Electronic Engineering, Vol. 9, No. 5, 2014, p. 494-501.

Research output: Contribution to journalArticle

@article{2242d6ec0b4b4c44a21b9a851ed46663,
title = "An improved elman neural network controller based on quasi-ARX neural network for nonlinear systems",
abstract = "An improved Elman neural network (IENN) controller with particle swarm optimization (PSO) is presented for nonlinear systems. The proposed controller is composed of a quasi-ARX neural network (QARXNN) prediction model and a switching mechanism. The switching mechanism is used to guarantee that the prediction model works well. The primary controller is designed based on IENN using the backpropagation (BP) learning algorithm with PSO. PSO is used to adjust the learning rates in the BP process for improving the learning capability. The adaptive learning rates of the controller are investigated via the Lyapunov stability theorem. The proposed controller performance is verified through numerical simulation. The method is compared with the fuzzy switching and 0/1 switching methods to show its effectiveness in terms of stability, accuracy, and robustness.",
keywords = "Elman neural network, Lyapunov stability theorem, Particle swarm optimization, Quasi-ARX neural network",
author = "Imam Sutrisno and {Abu Jami'in}, Mohammad and Takayuki Furuzuki",
year = "2014",
doi = "10.1002/tee.21998",
language = "English",
volume = "9",
pages = "494--501",
journal = "IEEJ Transactions on Electrical and Electronic Engineering",
issn = "1931-4973",
publisher = "John Wiley and Sons Inc.",
number = "5",

}

TY - JOUR

T1 - An improved elman neural network controller based on quasi-ARX neural network for nonlinear systems

AU - Sutrisno, Imam

AU - Abu Jami'in, Mohammad

AU - Furuzuki, Takayuki

PY - 2014

Y1 - 2014

N2 - An improved Elman neural network (IENN) controller with particle swarm optimization (PSO) is presented for nonlinear systems. The proposed controller is composed of a quasi-ARX neural network (QARXNN) prediction model and a switching mechanism. The switching mechanism is used to guarantee that the prediction model works well. The primary controller is designed based on IENN using the backpropagation (BP) learning algorithm with PSO. PSO is used to adjust the learning rates in the BP process for improving the learning capability. The adaptive learning rates of the controller are investigated via the Lyapunov stability theorem. The proposed controller performance is verified through numerical simulation. The method is compared with the fuzzy switching and 0/1 switching methods to show its effectiveness in terms of stability, accuracy, and robustness.

AB - An improved Elman neural network (IENN) controller with particle swarm optimization (PSO) is presented for nonlinear systems. The proposed controller is composed of a quasi-ARX neural network (QARXNN) prediction model and a switching mechanism. The switching mechanism is used to guarantee that the prediction model works well. The primary controller is designed based on IENN using the backpropagation (BP) learning algorithm with PSO. PSO is used to adjust the learning rates in the BP process for improving the learning capability. The adaptive learning rates of the controller are investigated via the Lyapunov stability theorem. The proposed controller performance is verified through numerical simulation. The method is compared with the fuzzy switching and 0/1 switching methods to show its effectiveness in terms of stability, accuracy, and robustness.

KW - Elman neural network

KW - Lyapunov stability theorem

KW - Particle swarm optimization

KW - Quasi-ARX neural network

UR - http://www.scopus.com/inward/record.url?scp=84906266254&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84906266254&partnerID=8YFLogxK

U2 - 10.1002/tee.21998

DO - 10.1002/tee.21998

M3 - Article

AN - SCOPUS:84906266254

VL - 9

SP - 494

EP - 501

JO - IEEJ Transactions on Electrical and Electronic Engineering

JF - IEEJ Transactions on Electrical and Electronic Engineering

SN - 1931-4973

IS - 5

ER -