Robustness and fault-tolerance of cubic neural network intelligent control method - Comparison with sliding mode control

Masaki Takahashi, T. Narukawa, K. Yoshida

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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 particular, this study deals with a nonlinear and failure-proof control problem. In the control, the dynamical energy principle is embedded into an integrator neural network of the integrated CNN (ICNN). 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 controller, computer simulations and experiments using a real apparatus were carried out for the cases of parameter variation and sensor failure. As a result, it is demonstrated that the ICNN controller can stand up the pendulum taking into account the cart position limit at abnormal simulations. Then, the robustness and the fault-tolerance of the proposed CNN controller were verified in comparison with the sliding mode control technique.

Original languageEnglish
Title of host publicationIEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages17-22
Number of pages6
Volume1
ISBN (Print)0780377591
DOIs
Publication statusPublished - 2003
Event2003 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2003 - Kobe, Japan
Duration: 2003 Jul 202003 Jul 24

Other

Other2003 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2003
CountryJapan
CityKobe
Period03/7/2003/7/24

Fingerprint

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

Keywords

  • Cellular neural networks
  • Control systems
  • Design engineering
  • Fault tolerance
  • Intelligent control
  • Neural networks
  • Robust control
  • Sliding mode control
  • Systems engineering and theory
  • Uncertainty

ASJC Scopus subject areas

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

Cite this

Takahashi, M., Narukawa, T., & Yoshida, K. (2003). Robustness and fault-tolerance of cubic neural network intelligent control method - Comparison with sliding mode control. In IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM (Vol. 1, pp. 17-22). [1225065] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/AIM.2003.1225065

Robustness and fault-tolerance of cubic neural network intelligent control method - Comparison with sliding mode control. / Takahashi, Masaki; Narukawa, T.; Yoshida, K.

IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM. Vol. 1 Institute of Electrical and Electronics Engineers Inc., 2003. p. 17-22 1225065.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Takahashi, M, Narukawa, T & Yoshida, K 2003, Robustness and fault-tolerance of cubic neural network intelligent control method - Comparison with sliding mode control. in IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM. vol. 1, 1225065, Institute of Electrical and Electronics Engineers Inc., pp. 17-22, 2003 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2003, Kobe, Japan, 03/7/20. https://doi.org/10.1109/AIM.2003.1225065
Takahashi M, Narukawa T, Yoshida K. Robustness and fault-tolerance of cubic neural network intelligent control method - Comparison with sliding mode control. In IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM. Vol. 1. Institute of Electrical and Electronics Engineers Inc. 2003. p. 17-22. 1225065 https://doi.org/10.1109/AIM.2003.1225065
Takahashi, Masaki ; Narukawa, T. ; Yoshida, K. / Robustness and fault-tolerance of cubic neural network intelligent control method - Comparison with sliding mode control. IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM. Vol. 1 Institute of Electrical and Electronics Engineers Inc., 2003. pp. 17-22
@inproceedings{0123d05870014d1aa3c236425a6e64c1,
title = "Robustness and fault-tolerance of cubic neural network intelligent control method - Comparison with sliding mode control",
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 particular, this study deals with a nonlinear and failure-proof control problem. In the control, the dynamical energy principle is embedded into an integrator neural network of the integrated CNN (ICNN). 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 controller, computer simulations and experiments using a real apparatus were carried out for the cases of parameter variation and sensor failure. As a result, it is demonstrated that the ICNN controller can stand up the pendulum taking into account the cart position limit at abnormal simulations. Then, the robustness and the fault-tolerance of the proposed CNN controller were verified in comparison with the sliding mode control technique.",
keywords = "Cellular neural networks, Control systems, Design engineering, Fault tolerance, Intelligent control, Neural networks, Robust control, Sliding mode control, Systems engineering and theory, Uncertainty",
author = "Masaki Takahashi and T. Narukawa and K. Yoshida",
year = "2003",
doi = "10.1109/AIM.2003.1225065",
language = "English",
isbn = "0780377591",
volume = "1",
pages = "17--22",
booktitle = "IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Robustness and fault-tolerance of cubic neural network intelligent control method - Comparison with sliding mode control

AU - Takahashi, Masaki

AU - Narukawa, T.

AU - Yoshida, K.

PY - 2003

Y1 - 2003

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 particular, this study deals with a nonlinear and failure-proof control problem. In the control, the dynamical energy principle is embedded into an integrator neural network of the integrated CNN (ICNN). 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 controller, computer simulations and experiments using a real apparatus were carried out for the cases of parameter variation and sensor failure. As a result, it is demonstrated that the ICNN controller can stand up the pendulum taking into account the cart position limit at abnormal simulations. Then, the robustness and the fault-tolerance of the proposed CNN controller 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 particular, this study deals with a nonlinear and failure-proof control problem. In the control, the dynamical energy principle is embedded into an integrator neural network of the integrated CNN (ICNN). 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 controller, computer simulations and experiments using a real apparatus were carried out for the cases of parameter variation and sensor failure. As a result, it is demonstrated that the ICNN controller can stand up the pendulum taking into account the cart position limit at abnormal simulations. Then, the robustness and the fault-tolerance of the proposed CNN controller were verified in comparison with the sliding mode control technique.

KW - Cellular neural networks

KW - Control systems

KW - Design engineering

KW - Fault tolerance

KW - Intelligent control

KW - Neural networks

KW - Robust control

KW - Sliding mode control

KW - Systems engineering and theory

KW - Uncertainty

UR - http://www.scopus.com/inward/record.url?scp=84943617150&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84943617150&partnerID=8YFLogxK

U2 - 10.1109/AIM.2003.1225065

DO - 10.1109/AIM.2003.1225065

M3 - Conference contribution

AN - SCOPUS:84943617150

SN - 0780377591

VL - 1

SP - 17

EP - 22

BT - IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM

PB - Institute of Electrical and Electronics Engineers Inc.

ER -