Intelligent control of integrated cubic neural network for robustness and fault-tolerance

Masaki Takahashi, Terumasa Narukawa, Kazuo Yoshida

Research output: Contribution to journalConference article

Abstract

This study aims at establishing a robust intelligent control method with higher control performance and wider applicable region by extending the Cubic Neural Network (CNN) intelligent control method which consists of multilevel parallel processing on different degrees of abstraction. In this study, an integrated CNN (ICNN) intelligent control method for nonlinear systems is proposed. In the method, an integrator neural network acquires suitable switching of several CNN controllers for a different local objective based on an evaluation of system states. the proposed ICNN is applied to a control problem of a swung up and inverted pendulum mounted on a cart for the case that arbitrary initial condition of pendulum angle. In order to confirm the performance of the ICNN, computer simulations and experiments using a real apparatus were carried out for the cases of parameter variation and sensor failure. As a result, it was demonstrated that the ICNN controller can stand up the pendulum taking into account the cart position limit at abnormal situations. Then, the robustness and the fault-tolerance of the ICNN were verified in comparison with the sliding mode control technique.

Original languageEnglish
Pages (from-to)493-498
Number of pages6
JournalIFAC Proceedings Volumes (IFAC-PapersOnline)
Volume37
Issue number12
DOIs
Publication statusPublished - 2004 Jan 1
Event2004 IFAC Workshop on Adaptation and Learning in Control and Signal Processing, ALCOSP 2004 and IFAC Workshop on Periodic Control Systems, PSYCO 2004 - Yokohama, Japan
Duration: 2004 Aug 302004 Sep 1

Fingerprint

Intelligent control
Fault tolerance
Pendulums
Neural networks
Controllers
Sliding mode control
Robust control
Nonlinear systems
Sensors
Computer simulation
Processing
Experiments

Keywords

  • Cubic Neural Network
  • Fault-tolerance
  • Intelligent Control
  • Inverted Pendulum
  • Qualitative Control
  • Robustness

ASJC Scopus subject areas

  • Control and Systems Engineering

Cite this

Intelligent control of integrated cubic neural network for robustness and fault-tolerance. / Takahashi, Masaki; Narukawa, Terumasa; Yoshida, Kazuo.

In: IFAC Proceedings Volumes (IFAC-PapersOnline), Vol. 37, No. 12, 01.01.2004, p. 493-498.

Research output: Contribution to journalConference article

@article{baedffbf4cbf49e79d3eb96d6b6248bb,
title = "Intelligent control of integrated cubic neural network for robustness and fault-tolerance",
abstract = "This study aims at establishing a robust intelligent control method with higher control performance and wider applicable region by extending the Cubic Neural Network (CNN) intelligent control method which consists of multilevel parallel processing on different degrees of abstraction. In this study, an integrated CNN (ICNN) intelligent control method for nonlinear systems is proposed. In the method, an integrator neural network acquires suitable switching of several CNN controllers for a different local objective based on an evaluation of system states. the proposed ICNN is applied to a control problem of a swung up and inverted pendulum mounted on a cart for the case that arbitrary initial condition of pendulum angle. In order to confirm the performance of the ICNN, computer simulations and experiments using a real apparatus were carried out for the cases of parameter variation and sensor failure. As a result, it was demonstrated that the ICNN controller can stand up the pendulum taking into account the cart position limit at abnormal situations. Then, the robustness and the fault-tolerance of the ICNN were verified in comparison with the sliding mode control technique.",
keywords = "Cubic Neural Network, Fault-tolerance, Intelligent Control, Inverted Pendulum, Qualitative Control, Robustness",
author = "Masaki Takahashi and Terumasa Narukawa and Kazuo Yoshida",
year = "2004",
month = "1",
day = "1",
doi = "10.1016/S1474-6670(17)31517-3",
language = "English",
volume = "37",
pages = "493--498",
journal = "IFAC-PapersOnLine",
issn = "2405-8963",
publisher = "IFAC Secretariat",
number = "12",

}

TY - JOUR

T1 - Intelligent control of integrated cubic neural network for robustness and fault-tolerance

AU - Takahashi, Masaki

AU - Narukawa, Terumasa

AU - Yoshida, Kazuo

PY - 2004/1/1

Y1 - 2004/1/1

N2 - This study aims at establishing a robust intelligent control method with higher control performance and wider applicable region by extending the Cubic Neural Network (CNN) intelligent control method which consists of multilevel parallel processing on different degrees of abstraction. In this study, an integrated CNN (ICNN) intelligent control method for nonlinear systems is proposed. In the method, an integrator neural network acquires suitable switching of several CNN controllers for a different local objective based on an evaluation of system states. the proposed ICNN is applied to a control problem of a swung up and inverted pendulum mounted on a cart for the case that arbitrary initial condition of pendulum angle. In order to confirm the performance of the ICNN, computer simulations and experiments using a real apparatus were carried out for the cases of parameter variation and sensor failure. As a result, it was demonstrated that the ICNN controller can stand up the pendulum taking into account the cart position limit at abnormal situations. Then, the robustness and the fault-tolerance of the ICNN were verified in comparison with the sliding mode control technique.

AB - This study aims at establishing a robust intelligent control method with higher control performance and wider applicable region by extending the Cubic Neural Network (CNN) intelligent control method which consists of multilevel parallel processing on different degrees of abstraction. In this study, an integrated CNN (ICNN) intelligent control method for nonlinear systems is proposed. In the method, an integrator neural network acquires suitable switching of several CNN controllers for a different local objective based on an evaluation of system states. the proposed ICNN is applied to a control problem of a swung up and inverted pendulum mounted on a cart for the case that arbitrary initial condition of pendulum angle. In order to confirm the performance of the ICNN, computer simulations and experiments using a real apparatus were carried out for the cases of parameter variation and sensor failure. As a result, it was demonstrated that the ICNN controller can stand up the pendulum taking into account the cart position limit at abnormal situations. Then, the robustness and the fault-tolerance of the ICNN were verified in comparison with the sliding mode control technique.

KW - Cubic Neural Network

KW - Fault-tolerance

KW - Intelligent Control

KW - Inverted Pendulum

KW - Qualitative Control

KW - Robustness

UR - http://www.scopus.com/inward/record.url?scp=85064412205&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064412205&partnerID=8YFLogxK

U2 - 10.1016/S1474-6670(17)31517-3

DO - 10.1016/S1474-6670(17)31517-3

M3 - Conference article

VL - 37

SP - 493

EP - 498

JO - IFAC-PapersOnLine

JF - IFAC-PapersOnLine

SN - 2405-8963

IS - 12

ER -