Automated core design

Yoko Kobayashi, Eitaro Aiyoshi

Research output: Contribution to journalArticle

Abstract

Multistate searching methods are a subfield of distributed artificial intelligence that aims to provide both principles for construction of complex systems involving multiple states and mechanisms for coordination of independent agents' actions. This paper proposes a multi-state searching algorithm with reinforcement learning for the automatic core design of a boiling water reactor. The characteristics of this algorithm are that the coupling structure and the coupling operation suitable for the assigned problem are assumed and an optimal solution is obtained by mutual interference in multistate transitions using multiagents. Calculations in an actual plant confirmed that the proposed algorithm increased the convergence ability of the optimization process.

Original languageEnglish
Pages (from-to)77-85
Number of pages9
JournalNuclear Technology
Volume151
Issue number1
Publication statusPublished - 2005 Jul

Fingerprint

boiling water reactors
artificial intelligence
Boiling water reactors
Reinforcement learning
reinforcement
complex systems
learning
Artificial intelligence
Large scale systems
interference
optimization

Keywords

  • Core design
  • Multistate searching
  • Optimization

ASJC Scopus subject areas

  • Nuclear Energy and Engineering

Cite this

Kobayashi, Y., & Aiyoshi, E. (2005). Automated core design. Nuclear Technology, 151(1), 77-85.

Automated core design. / Kobayashi, Yoko; Aiyoshi, Eitaro.

In: Nuclear Technology, Vol. 151, No. 1, 07.2005, p. 77-85.

Research output: Contribution to journalArticle

Kobayashi, Y & Aiyoshi, E 2005, 'Automated core design', Nuclear Technology, vol. 151, no. 1, pp. 77-85.
Kobayashi Y, Aiyoshi E. Automated core design. Nuclear Technology. 2005 Jul;151(1):77-85.
Kobayashi, Yoko ; Aiyoshi, Eitaro. / Automated core design. In: Nuclear Technology. 2005 ; Vol. 151, No. 1. pp. 77-85.
@article{dd7ce1fd107a4880b7f6c42fac04e2aa,
title = "Automated core design",
abstract = "Multistate searching methods are a subfield of distributed artificial intelligence that aims to provide both principles for construction of complex systems involving multiple states and mechanisms for coordination of independent agents' actions. This paper proposes a multi-state searching algorithm with reinforcement learning for the automatic core design of a boiling water reactor. The characteristics of this algorithm are that the coupling structure and the coupling operation suitable for the assigned problem are assumed and an optimal solution is obtained by mutual interference in multistate transitions using multiagents. Calculations in an actual plant confirmed that the proposed algorithm increased the convergence ability of the optimization process.",
keywords = "Core design, Multistate searching, Optimization",
author = "Yoko Kobayashi and Eitaro Aiyoshi",
year = "2005",
month = "7",
language = "English",
volume = "151",
pages = "77--85",
journal = "Nuclear Technology",
issn = "0029-5450",
publisher = "American Nuclear Society",
number = "1",

}

TY - JOUR

T1 - Automated core design

AU - Kobayashi, Yoko

AU - Aiyoshi, Eitaro

PY - 2005/7

Y1 - 2005/7

N2 - Multistate searching methods are a subfield of distributed artificial intelligence that aims to provide both principles for construction of complex systems involving multiple states and mechanisms for coordination of independent agents' actions. This paper proposes a multi-state searching algorithm with reinforcement learning for the automatic core design of a boiling water reactor. The characteristics of this algorithm are that the coupling structure and the coupling operation suitable for the assigned problem are assumed and an optimal solution is obtained by mutual interference in multistate transitions using multiagents. Calculations in an actual plant confirmed that the proposed algorithm increased the convergence ability of the optimization process.

AB - Multistate searching methods are a subfield of distributed artificial intelligence that aims to provide both principles for construction of complex systems involving multiple states and mechanisms for coordination of independent agents' actions. This paper proposes a multi-state searching algorithm with reinforcement learning for the automatic core design of a boiling water reactor. The characteristics of this algorithm are that the coupling structure and the coupling operation suitable for the assigned problem are assumed and an optimal solution is obtained by mutual interference in multistate transitions using multiagents. Calculations in an actual plant confirmed that the proposed algorithm increased the convergence ability of the optimization process.

KW - Core design

KW - Multistate searching

KW - Optimization

UR - http://www.scopus.com/inward/record.url?scp=21244498675&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=21244498675&partnerID=8YFLogxK

M3 - Article

VL - 151

SP - 77

EP - 85

JO - Nuclear Technology

JF - Nuclear Technology

SN - 0029-5450

IS - 1

ER -