Direct decentralized neural control for nonlinear MIMO magnetic levitation system

Syuan-Yi Chen, Faa Jeng Lin, Kuo Kai Shyu

Research output: Contribution to journalArticle

24 Citations (Scopus)

Abstract

A direct modified Elman neural networks (MENNs)-based decentralized controller is proposed to control the magnets of a nonlinear and unstable multi-input multi-output (MIMO) levitation system for the tracking of reference trajectories. First, the operating principles of a magnetic levitation system with two moving magnets are introduced. Then, due to the exact dynamic model of the MIMO magnetic levitation system is not clear, two MENNs are combined to be a direct MENN-based decentralized controller to deal with the highly nonlinear and unstable MIMO magnetic levitation system. Moreover, the connective weights of the MENNs are trained online by back-propagation (BP) methodology and the convergence analysis of the tracking error using discrete-type Lyapunov function is provided. Based on the direct and decentralized concepts, the computational burden is reduced and the controller design is simplified. Furthermore, the experimental results show that the proposed control scheme can control the magnets to track various periodic reference trajectories simultaneously in different operating conditions effectively.

Original languageEnglish
Pages (from-to)3220-3230
Number of pages11
JournalNeurocomputing
Volume72
Issue number13-15
DOIs
Publication statusPublished - 2009 Jan 1

Fingerprint

Magnetic levitation
Magnets
Neural networks
Controllers
Trajectories
Lyapunov functions
Backpropagation
Weights and Measures
Dynamic models

Keywords

  • Decentralized control
  • Elman neural network
  • MIMO system
  • Magnetic levitation system

ASJC Scopus subject areas

  • Computer Science Applications
  • Cognitive Neuroscience
  • Artificial Intelligence

Cite this

Direct decentralized neural control for nonlinear MIMO magnetic levitation system. / Chen, Syuan-Yi; Lin, Faa Jeng; Shyu, Kuo Kai.

In: Neurocomputing, Vol. 72, No. 13-15, 01.01.2009, p. 3220-3230.

Research output: Contribution to journalArticle

Chen, Syuan-Yi ; Lin, Faa Jeng ; Shyu, Kuo Kai. / Direct decentralized neural control for nonlinear MIMO magnetic levitation system. In: Neurocomputing. 2009 ; Vol. 72, No. 13-15. pp. 3220-3230.
@article{d3af5979885d40ab9ee94aacaf5dcaa2,
title = "Direct decentralized neural control for nonlinear MIMO magnetic levitation system",
abstract = "A direct modified Elman neural networks (MENNs)-based decentralized controller is proposed to control the magnets of a nonlinear and unstable multi-input multi-output (MIMO) levitation system for the tracking of reference trajectories. First, the operating principles of a magnetic levitation system with two moving magnets are introduced. Then, due to the exact dynamic model of the MIMO magnetic levitation system is not clear, two MENNs are combined to be a direct MENN-based decentralized controller to deal with the highly nonlinear and unstable MIMO magnetic levitation system. Moreover, the connective weights of the MENNs are trained online by back-propagation (BP) methodology and the convergence analysis of the tracking error using discrete-type Lyapunov function is provided. Based on the direct and decentralized concepts, the computational burden is reduced and the controller design is simplified. Furthermore, the experimental results show that the proposed control scheme can control the magnets to track various periodic reference trajectories simultaneously in different operating conditions effectively.",
keywords = "Decentralized control, Elman neural network, MIMO system, Magnetic levitation system",
author = "Syuan-Yi Chen and Lin, {Faa Jeng} and Shyu, {Kuo Kai}",
year = "2009",
month = "1",
day = "1",
doi = "10.1016/j.neucom.2009.02.009",
language = "English",
volume = "72",
pages = "3220--3230",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier",
number = "13-15",

}

TY - JOUR

T1 - Direct decentralized neural control for nonlinear MIMO magnetic levitation system

AU - Chen, Syuan-Yi

AU - Lin, Faa Jeng

AU - Shyu, Kuo Kai

PY - 2009/1/1

Y1 - 2009/1/1

N2 - A direct modified Elman neural networks (MENNs)-based decentralized controller is proposed to control the magnets of a nonlinear and unstable multi-input multi-output (MIMO) levitation system for the tracking of reference trajectories. First, the operating principles of a magnetic levitation system with two moving magnets are introduced. Then, due to the exact dynamic model of the MIMO magnetic levitation system is not clear, two MENNs are combined to be a direct MENN-based decentralized controller to deal with the highly nonlinear and unstable MIMO magnetic levitation system. Moreover, the connective weights of the MENNs are trained online by back-propagation (BP) methodology and the convergence analysis of the tracking error using discrete-type Lyapunov function is provided. Based on the direct and decentralized concepts, the computational burden is reduced and the controller design is simplified. Furthermore, the experimental results show that the proposed control scheme can control the magnets to track various periodic reference trajectories simultaneously in different operating conditions effectively.

AB - A direct modified Elman neural networks (MENNs)-based decentralized controller is proposed to control the magnets of a nonlinear and unstable multi-input multi-output (MIMO) levitation system for the tracking of reference trajectories. First, the operating principles of a magnetic levitation system with two moving magnets are introduced. Then, due to the exact dynamic model of the MIMO magnetic levitation system is not clear, two MENNs are combined to be a direct MENN-based decentralized controller to deal with the highly nonlinear and unstable MIMO magnetic levitation system. Moreover, the connective weights of the MENNs are trained online by back-propagation (BP) methodology and the convergence analysis of the tracking error using discrete-type Lyapunov function is provided. Based on the direct and decentralized concepts, the computational burden is reduced and the controller design is simplified. Furthermore, the experimental results show that the proposed control scheme can control the magnets to track various periodic reference trajectories simultaneously in different operating conditions effectively.

KW - Decentralized control

KW - Elman neural network

KW - MIMO system

KW - Magnetic levitation system

UR - http://www.scopus.com/inward/record.url?scp=78649386967&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78649386967&partnerID=8YFLogxK

U2 - 10.1016/j.neucom.2009.02.009

DO - 10.1016/j.neucom.2009.02.009

M3 - Article

AN - SCOPUS:78649386967

VL - 72

SP - 3220

EP - 3230

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

IS - 13-15

ER -