### 抄録

Boiling water reactors (BWRs) represent a large fraction of the world's installed nuclear power capacity. The core model of a BWR is very complex because it has many fuel assemblies and strong axial heterogeneities such as coolant voiding, partial control rod insertion, and non-uniform fuel assembly design. In order to operate a BWR safely, it is necessary to supervise the performance of the reactor core during the operation cycle. Therefore, the operation of the reactor core in a BWR is supervised using a 3-dimensional on-line simulator. In order to raise the calculation accuracy of this 3-dimensional simulator, the calculation power distribution is corrected using the neutron flux distribution obtained by the in-core instrumentation. In this paper, a model that uses a neural network was developed in order to raise the calculation accuracy of this 3-dimensional simulator further. In order to apply a neural network to the complicated reactor core of a BWR, the learning algorithm needs to be improved. Therefore, a technique using the Quasi-Newton method for renewal of the connection weights of the Back-Propagation (BP) method was developed. Using this algorithm, the convergent ability of neural network learning was improved in the strongly nonlinear problems. When this algorithm was applied to a BWR, the calculation accuracy of a 3-dimensional simulator was improved considerably.

元の言語 | English |
---|---|

ホスト出版物のタイトル | IEEE International Symposium on Industrial Electronics |

出版者 | Institute of Electrical and Electronics Engineers Inc. |

ページ | 294-298 |

ページ数 | 5 |

巻 | 1 |

ISBN（印刷物） | 0780373693, 9780780373693 |

出版物ステータス | Published - 2002 |

イベント | 2002 IEEE International Symposium on Industrial Electronics, ISIE 2002 - L'Aquila, Italy 継続期間: 2002 7 8 → 2002 7 11 |

### Other

Other | 2002 IEEE International Symposium on Industrial Electronics, ISIE 2002 |
---|---|

国 | Italy |

市 | L'Aquila |

期間 | 02/7/8 → 02/7/11 |

### Fingerprint

### ASJC Scopus subject areas

- Electrical and Electronic Engineering
- Control and Systems Engineering

### これを引用

*IEEE International Symposium on Industrial Electronics*(巻 1, pp. 294-298). [1026081] Institute of Electrical and Electronics Engineers Inc..

**Improvement of the accuracy of a 3-dimensional simulator of a BWR using a neural network.** / Kobayashi, Y.; Aiyoshi, E.

研究成果: Conference contribution

*IEEE International Symposium on Industrial Electronics.*巻. 1, 1026081, Institute of Electrical and Electronics Engineers Inc., pp. 294-298, 2002 IEEE International Symposium on Industrial Electronics, ISIE 2002, L'Aquila, Italy, 02/7/8.

}

TY - GEN

T1 - Improvement of the accuracy of a 3-dimensional simulator of a BWR using a neural network

AU - Kobayashi, Y.

AU - Aiyoshi, E.

PY - 2002

Y1 - 2002

N2 - Boiling water reactors (BWRs) represent a large fraction of the world's installed nuclear power capacity. The core model of a BWR is very complex because it has many fuel assemblies and strong axial heterogeneities such as coolant voiding, partial control rod insertion, and non-uniform fuel assembly design. In order to operate a BWR safely, it is necessary to supervise the performance of the reactor core during the operation cycle. Therefore, the operation of the reactor core in a BWR is supervised using a 3-dimensional on-line simulator. In order to raise the calculation accuracy of this 3-dimensional simulator, the calculation power distribution is corrected using the neutron flux distribution obtained by the in-core instrumentation. In this paper, a model that uses a neural network was developed in order to raise the calculation accuracy of this 3-dimensional simulator further. In order to apply a neural network to the complicated reactor core of a BWR, the learning algorithm needs to be improved. Therefore, a technique using the Quasi-Newton method for renewal of the connection weights of the Back-Propagation (BP) method was developed. Using this algorithm, the convergent ability of neural network learning was improved in the strongly nonlinear problems. When this algorithm was applied to a BWR, the calculation accuracy of a 3-dimensional simulator was improved considerably.

AB - Boiling water reactors (BWRs) represent a large fraction of the world's installed nuclear power capacity. The core model of a BWR is very complex because it has many fuel assemblies and strong axial heterogeneities such as coolant voiding, partial control rod insertion, and non-uniform fuel assembly design. In order to operate a BWR safely, it is necessary to supervise the performance of the reactor core during the operation cycle. Therefore, the operation of the reactor core in a BWR is supervised using a 3-dimensional on-line simulator. In order to raise the calculation accuracy of this 3-dimensional simulator, the calculation power distribution is corrected using the neutron flux distribution obtained by the in-core instrumentation. In this paper, a model that uses a neural network was developed in order to raise the calculation accuracy of this 3-dimensional simulator further. In order to apply a neural network to the complicated reactor core of a BWR, the learning algorithm needs to be improved. Therefore, a technique using the Quasi-Newton method for renewal of the connection weights of the Back-Propagation (BP) method was developed. Using this algorithm, the convergent ability of neural network learning was improved in the strongly nonlinear problems. When this algorithm was applied to a BWR, the calculation accuracy of a 3-dimensional simulator was improved considerably.

UR - http://www.scopus.com/inward/record.url?scp=84902345294&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84902345294&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84902345294

SN - 0780373693

SN - 9780780373693

VL - 1

SP - 294

EP - 298

BT - IEEE International Symposium on Industrial Electronics

PB - Institute of Electrical and Electronics Engineers Inc.

ER -