Nonlinear control system using Learning Petri Network

Masanao Ohbayashi, Kotaro Hirasawa, Singo Sakai, Takayuki Furuzuki

Research output: Contribution to journalArticle

Abstract

According to recent understanding of brain science, it is suggested that there is a distribution of functions in the brain, which means that different neurons are activated depending on which sort of sensory information the brain receives. We have already developed a learning network with a function distribution which is called the Learning Petri Network (LPN) and have shown that this network could learn nonlinear and discontinuous mappings which the Neural Network (NN) cannot. In this paper, a more realistic application which has dynamic characteristics is studied. From simulation results of a nonlinear crane control system using LPN controller, it is clarified that the control performance of LPN controller is superior to that of NN controller.

Original languageEnglish
Pages (from-to)58-69
Number of pages12
JournalElectrical Engineering in Japan (English translation of Denki Gakkai Ronbunshi)
Volume131
Issue number3
Publication statusPublished - 2000 May
Externally publishedYes

Fingerprint

Nonlinear control systems
Brain
Controllers
Neural networks
Cranes
Neurons
Distribution functions
Control systems

Keywords

  • Function distribution
  • Learning Petri network
  • Neural network
  • Nonlinear control
  • Optimization

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Nonlinear control system using Learning Petri Network. / Ohbayashi, Masanao; Hirasawa, Kotaro; Sakai, Singo; Furuzuki, Takayuki.

In: Electrical Engineering in Japan (English translation of Denki Gakkai Ronbunshi), Vol. 131, No. 3, 05.2000, p. 58-69.

Research output: Contribution to journalArticle

@article{03bd0316c7a843faab4ca2f4b72e3711,
title = "Nonlinear control system using Learning Petri Network",
abstract = "According to recent understanding of brain science, it is suggested that there is a distribution of functions in the brain, which means that different neurons are activated depending on which sort of sensory information the brain receives. We have already developed a learning network with a function distribution which is called the Learning Petri Network (LPN) and have shown that this network could learn nonlinear and discontinuous mappings which the Neural Network (NN) cannot. In this paper, a more realistic application which has dynamic characteristics is studied. From simulation results of a nonlinear crane control system using LPN controller, it is clarified that the control performance of LPN controller is superior to that of NN controller.",
keywords = "Function distribution, Learning Petri network, Neural network, Nonlinear control, Optimization",
author = "Masanao Ohbayashi and Kotaro Hirasawa and Singo Sakai and Takayuki Furuzuki",
year = "2000",
month = "5",
language = "English",
volume = "131",
pages = "58--69",
journal = "Electrical Engineering in Japan (English translation of Denki Gakkai Ronbunshi)",
issn = "0424-7760",
publisher = "John Wiley and Sons Inc.",
number = "3",

}

TY - JOUR

T1 - Nonlinear control system using Learning Petri Network

AU - Ohbayashi, Masanao

AU - Hirasawa, Kotaro

AU - Sakai, Singo

AU - Furuzuki, Takayuki

PY - 2000/5

Y1 - 2000/5

N2 - According to recent understanding of brain science, it is suggested that there is a distribution of functions in the brain, which means that different neurons are activated depending on which sort of sensory information the brain receives. We have already developed a learning network with a function distribution which is called the Learning Petri Network (LPN) and have shown that this network could learn nonlinear and discontinuous mappings which the Neural Network (NN) cannot. In this paper, a more realistic application which has dynamic characteristics is studied. From simulation results of a nonlinear crane control system using LPN controller, it is clarified that the control performance of LPN controller is superior to that of NN controller.

AB - According to recent understanding of brain science, it is suggested that there is a distribution of functions in the brain, which means that different neurons are activated depending on which sort of sensory information the brain receives. We have already developed a learning network with a function distribution which is called the Learning Petri Network (LPN) and have shown that this network could learn nonlinear and discontinuous mappings which the Neural Network (NN) cannot. In this paper, a more realistic application which has dynamic characteristics is studied. From simulation results of a nonlinear crane control system using LPN controller, it is clarified that the control performance of LPN controller is superior to that of NN controller.

KW - Function distribution

KW - Learning Petri network

KW - Neural network

KW - Nonlinear control

KW - Optimization

UR - http://www.scopus.com/inward/record.url?scp=24044525734&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=24044525734&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:24044525734

VL - 131

SP - 58

EP - 69

JO - Electrical Engineering in Japan (English translation of Denki Gakkai Ronbunshi)

JF - Electrical Engineering in Japan (English translation of Denki Gakkai Ronbunshi)

SN - 0424-7760

IS - 3

ER -