Intelligent control using cubic neural network for swinging up and stabilizing double pendulum

Masaki Takahashi, Kazuo Yoshida

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This study aims at establishing a robust intelligent control method with higher control performance and wider application region by developing the Cubic Neural Network (CNN) intelligent control method. In particular, this study deals with a nonlinear and failure-proof control problem for an intelligent control method of integrated CNN: The proposed CNN is applied to a control problem of a swung up and inverted double pendulum. In this study, the dynamical energy principle is embedded into the integrator of CNN that consists of multilevel parallel processing on different degrees of abstraction. In order to confirm the effectiveness of the integrated CNN controller, we carried out simulations and experiments. As a result of simulation and experiment, it was demonstrated that the integrated CNN controllers can stand up the double pendulum taking into account the cart position limit from the case of arbitrary initial condition of pendulum angle.

Original languageEnglish
Pages (from-to)3636-3643
Number of pages8
JournalNippon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C
Volume68
Issue number12
Publication statusPublished - 2002 Dec

Fingerprint

Intelligent control
Pendulums
Neural networks
Controllers
Robust control
Experiments
Processing

Keywords

  • Cubic Neural Network
  • Double Pendulum
  • Intelligent Control
  • Multi-Purpose Control
  • Nonlinear Control

ASJC Scopus subject areas

  • Mechanical Engineering

Cite this

@article{227c604125544d2f83dfb1463dd6c9cd,
title = "Intelligent control using cubic neural network for swinging up and stabilizing double pendulum",
abstract = "This study aims at establishing a robust intelligent control method with higher control performance and wider application region by developing the Cubic Neural Network (CNN) intelligent control method. In particular, this study deals with a nonlinear and failure-proof control problem for an intelligent control method of integrated CNN: The proposed CNN is applied to a control problem of a swung up and inverted double pendulum. In this study, the dynamical energy principle is embedded into the integrator of CNN that consists of multilevel parallel processing on different degrees of abstraction. In order to confirm the effectiveness of the integrated CNN controller, we carried out simulations and experiments. As a result of simulation and experiment, it was demonstrated that the integrated CNN controllers can stand up the double pendulum taking into account the cart position limit from the case of arbitrary initial condition of pendulum angle.",
keywords = "Cubic Neural Network, Double Pendulum, Intelligent Control, Multi-Purpose Control, Nonlinear Control",
author = "Masaki Takahashi and Kazuo Yoshida",
year = "2002",
month = "12",
language = "English",
volume = "68",
pages = "3636--3643",
journal = "Nihon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C",
issn = "0387-5024",
publisher = "Japan Society of Mechanical Engineers",
number = "12",

}

TY - JOUR

T1 - Intelligent control using cubic neural network for swinging up and stabilizing double pendulum

AU - Takahashi, Masaki

AU - Yoshida, Kazuo

PY - 2002/12

Y1 - 2002/12

N2 - This study aims at establishing a robust intelligent control method with higher control performance and wider application region by developing the Cubic Neural Network (CNN) intelligent control method. In particular, this study deals with a nonlinear and failure-proof control problem for an intelligent control method of integrated CNN: The proposed CNN is applied to a control problem of a swung up and inverted double pendulum. In this study, the dynamical energy principle is embedded into the integrator of CNN that consists of multilevel parallel processing on different degrees of abstraction. In order to confirm the effectiveness of the integrated CNN controller, we carried out simulations and experiments. As a result of simulation and experiment, it was demonstrated that the integrated CNN controllers can stand up the double pendulum taking into account the cart position limit from the case of arbitrary initial condition of pendulum angle.

AB - This study aims at establishing a robust intelligent control method with higher control performance and wider application region by developing the Cubic Neural Network (CNN) intelligent control method. In particular, this study deals with a nonlinear and failure-proof control problem for an intelligent control method of integrated CNN: The proposed CNN is applied to a control problem of a swung up and inverted double pendulum. In this study, the dynamical energy principle is embedded into the integrator of CNN that consists of multilevel parallel processing on different degrees of abstraction. In order to confirm the effectiveness of the integrated CNN controller, we carried out simulations and experiments. As a result of simulation and experiment, it was demonstrated that the integrated CNN controllers can stand up the double pendulum taking into account the cart position limit from the case of arbitrary initial condition of pendulum angle.

KW - Cubic Neural Network

KW - Double Pendulum

KW - Intelligent Control

KW - Multi-Purpose Control

KW - Nonlinear Control

UR - http://www.scopus.com/inward/record.url?scp=0036945255&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036945255&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0036945255

VL - 68

SP - 3636

EP - 3643

JO - Nihon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C

JF - Nihon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C

SN - 0387-5024

IS - 12

ER -