Robust dynamic sliding-mode control using adaptive RENN for magnetic levitation system

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

Research output: Contribution to journalArticle

80 Citations (Scopus)

Abstract

In this paper, a robust dynamic sliding mode control system (RDSMC) using a recurrent Elman neural network (RENN) is proposed to control the position of a levitated object of a magnetic levitation system considering the uncertainties. First, a dynamic model of the magnetic levitation system is derived. Then, a proportional-integral-derivative (PID)-type sliding-mode control system (SMC) is adopted for tracking of the reference trajectories. Moreover, a new PID-type dynamic sliding-mode control system (DSMC) is proposed to reduce the chattering phenomenon. However, due to the hardware being limited and the uncertainty bound being unknown of the switching function for the DSMC, an RDSMC is proposed to improve the control performance and further increase the robustness of the magnetic levitation system. In the RDSMC, an RENN estimator is used to estimate an unknown nonlinear function of lumped uncertainty online and replace the switching function in the hitting control of the DSMC directly. The adaptive learning algorithms that trained the parameters of the RENN online are derived using Lyapunov stability theorem. Furthermore, a robust compensator is proposed to confront the uncertainties including approximation error, optimal parameter vectors, and higher order terms in Taylor series. Finally, some experimental results of tracking the various periodic trajectories demonstrate the validity of the proposed RDSMC for practical applications.

Original languageEnglish
Pages (from-to)938-951
Number of pages14
JournalIEEE Transactions on Neural Networks
Volume20
Issue number6
DOIs
Publication statusPublished - 2009 May 8

Fingerprint

Magnetic levitation
Recurrent neural networks
Sliding mode control
Uncertainty
Control systems
Switching functions
Trajectories
Learning
Derivatives
Taylor series
Adaptive algorithms
Robustness (control systems)
Learning algorithms
Dynamic models
Hardware

Keywords

  • Dynamic sliding-mode control (DSMC)
  • Elman neural network (ENN)
  • Magnetic levitation
  • Robust control

ASJC Scopus subject areas

  • Software
  • Medicine(all)
  • Computer Science Applications
  • Computer Networks and Communications
  • Artificial Intelligence

Cite this

Robust dynamic sliding-mode control using adaptive RENN for magnetic levitation system. / Lin, Faa Jeng; Chen, Syuan-Yi; Shyu, Kuo Kai.

In: IEEE Transactions on Neural Networks, Vol. 20, No. 6, 08.05.2009, p. 938-951.

Research output: Contribution to journalArticle

@article{2c81099638e0462bb646978bdd567eb4,
title = "Robust dynamic sliding-mode control using adaptive RENN for magnetic levitation system",
abstract = "In this paper, a robust dynamic sliding mode control system (RDSMC) using a recurrent Elman neural network (RENN) is proposed to control the position of a levitated object of a magnetic levitation system considering the uncertainties. First, a dynamic model of the magnetic levitation system is derived. Then, a proportional-integral-derivative (PID)-type sliding-mode control system (SMC) is adopted for tracking of the reference trajectories. Moreover, a new PID-type dynamic sliding-mode control system (DSMC) is proposed to reduce the chattering phenomenon. However, due to the hardware being limited and the uncertainty bound being unknown of the switching function for the DSMC, an RDSMC is proposed to improve the control performance and further increase the robustness of the magnetic levitation system. In the RDSMC, an RENN estimator is used to estimate an unknown nonlinear function of lumped uncertainty online and replace the switching function in the hitting control of the DSMC directly. The adaptive learning algorithms that trained the parameters of the RENN online are derived using Lyapunov stability theorem. Furthermore, a robust compensator is proposed to confront the uncertainties including approximation error, optimal parameter vectors, and higher order terms in Taylor series. Finally, some experimental results of tracking the various periodic trajectories demonstrate the validity of the proposed RDSMC for practical applications.",
keywords = "Dynamic sliding-mode control (DSMC), Elman neural network (ENN), Magnetic levitation, Robust control",
author = "Lin, {Faa Jeng} and Syuan-Yi Chen and Shyu, {Kuo Kai}",
year = "2009",
month = "5",
day = "8",
doi = "10.1109/TNN.2009.2014228",
language = "English",
volume = "20",
pages = "938--951",
journal = "IEEE Transactions on Neural Networks and Learning Systems",
issn = "2162-237X",
publisher = "IEEE Computational Intelligence Society",
number = "6",

}

TY - JOUR

T1 - Robust dynamic sliding-mode control using adaptive RENN for magnetic levitation system

AU - Lin, Faa Jeng

AU - Chen, Syuan-Yi

AU - Shyu, Kuo Kai

PY - 2009/5/8

Y1 - 2009/5/8

N2 - In this paper, a robust dynamic sliding mode control system (RDSMC) using a recurrent Elman neural network (RENN) is proposed to control the position of a levitated object of a magnetic levitation system considering the uncertainties. First, a dynamic model of the magnetic levitation system is derived. Then, a proportional-integral-derivative (PID)-type sliding-mode control system (SMC) is adopted for tracking of the reference trajectories. Moreover, a new PID-type dynamic sliding-mode control system (DSMC) is proposed to reduce the chattering phenomenon. However, due to the hardware being limited and the uncertainty bound being unknown of the switching function for the DSMC, an RDSMC is proposed to improve the control performance and further increase the robustness of the magnetic levitation system. In the RDSMC, an RENN estimator is used to estimate an unknown nonlinear function of lumped uncertainty online and replace the switching function in the hitting control of the DSMC directly. The adaptive learning algorithms that trained the parameters of the RENN online are derived using Lyapunov stability theorem. Furthermore, a robust compensator is proposed to confront the uncertainties including approximation error, optimal parameter vectors, and higher order terms in Taylor series. Finally, some experimental results of tracking the various periodic trajectories demonstrate the validity of the proposed RDSMC for practical applications.

AB - In this paper, a robust dynamic sliding mode control system (RDSMC) using a recurrent Elman neural network (RENN) is proposed to control the position of a levitated object of a magnetic levitation system considering the uncertainties. First, a dynamic model of the magnetic levitation system is derived. Then, a proportional-integral-derivative (PID)-type sliding-mode control system (SMC) is adopted for tracking of the reference trajectories. Moreover, a new PID-type dynamic sliding-mode control system (DSMC) is proposed to reduce the chattering phenomenon. However, due to the hardware being limited and the uncertainty bound being unknown of the switching function for the DSMC, an RDSMC is proposed to improve the control performance and further increase the robustness of the magnetic levitation system. In the RDSMC, an RENN estimator is used to estimate an unknown nonlinear function of lumped uncertainty online and replace the switching function in the hitting control of the DSMC directly. The adaptive learning algorithms that trained the parameters of the RENN online are derived using Lyapunov stability theorem. Furthermore, a robust compensator is proposed to confront the uncertainties including approximation error, optimal parameter vectors, and higher order terms in Taylor series. Finally, some experimental results of tracking the various periodic trajectories demonstrate the validity of the proposed RDSMC for practical applications.

KW - Dynamic sliding-mode control (DSMC)

KW - Elman neural network (ENN)

KW - Magnetic levitation

KW - Robust control

UR - http://www.scopus.com/inward/record.url?scp=67649359712&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67649359712&partnerID=8YFLogxK

U2 - 10.1109/TNN.2009.2014228

DO - 10.1109/TNN.2009.2014228

M3 - Article

C2 - 19423437

AN - SCOPUS:67649359712

VL - 20

SP - 938

EP - 951

JO - IEEE Transactions on Neural Networks and Learning Systems

JF - IEEE Transactions on Neural Networks and Learning Systems

SN - 2162-237X

IS - 6

ER -