On-line Nuclear Reactor Monitoring and Diagnosis in earliest stages using Neural Network

使用神经网络进行核反应堆在线监测和诊断

• 批准号: 16560735
• 负责人: KUDO Kazuhiko
• 金额: $ 2.3万
• 依托单位: Kyushu University
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (C)
• 财政年份: 2004
• 资助国家: 日本
• 起止时间: 2004 至 2006
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-16560735/
• 关键词: Nuclear Reactor; Diagnosis; Neural Network; Kohonenn Model; HTTR; PWR; 原子炉; 原子力プラント

The object of this research is to develop the on-line nuclear reactor monitoring and diagnosis system using Neural Network theory. The nuclear reactor diagnostic system was developed and examined using reactor simulator and existing reactor data.In 2004 the diagnostic system applying auto-associative neural network theory was developed and examined about the ability of anomaly detection.In 2005 application of Kohonen network theory was investigated selectively. It was thought that in addition to anomaly detection, reactor diagnosis will be realized by using Kohonen network. The operational data of existing nuclear reactor which contain noise and power fluctuations was used for training the diagnosis system and the ability of diagnosis was tested.In 2006 the occurrence of error signal and anomaly diagnosis was examined using PWR simulator. The diagnosis of research reactor data(RSG-GAS, Indonetia) which contain noise was tested and succeeded. The detection of small helium leak which occur in HTTR ( High Temperature Gas Cooled Test Reactor, JAEA ) and power change caused by reactivity change was estimated correctly using this diagnosis system.These results were presented in some international proceedings and journals.

本研究的目的是利用神经网络理论开发核反应堆在线监测与诊断系统。利用反应堆模拟器和现有反应堆数据开发并检验了核反应堆诊断系统。2004年开发了应用自联想神经网络理论的诊断系统并检验了异常检测能力。2005年选择性地研究了Kohonen网络理论的应用。人们认为，除了异常检测之外，还可以利用 Kohonen 网络来实现反应堆诊断。利用现有核反应堆含有噪声和功率波动的运行数据对诊断系统进行训练，检验诊断能力。2006年利用压水堆模拟器对错误信号的发生情况和异常诊断情况进行了检查。对含有噪声的研究堆数据（RSG-GAS、Indonetia）的诊断进行了测试并取得成功。使用该诊断系统可以正确估计HTTR（高温气冷试验堆，JAEA）中发生的小氦泄漏和反应性变化引起的功率变化。这些结果在一些国际会议和期刊上发表。

项目成果

Development of Real-Time PWR Monitoring System using Neuro-Expert

使用 Neuro-Expert 开发实时压水堆监测系统

• 发表时间: 2006
• 期刊: Proceedings of The 2nd Information and Communication Technology Seminar (ICTS2006) Kitakyushu,Japan
• 作者: S.MUHAMMAD;T.OHNO;K.NABESHIMA;K.KUDO
• 通讯作者: K.KUDO

Development of On-Line Monitoring System for Nuclear Power Plant (NPP) Using Neuro-Expert, Noise Analysis, and Modified Neural Networks

使用神经专家、噪声分析和改进的神经网络开发核电厂 (NPP) 在线监测系统

• 发表时间: 2006
• 期刊: Proceedings of 17th International Topical Meeting on Nuclear Plant, Instrumentation, Controls, and Human Machine Interface Tech. (NPIC＆HMIT2006) Albuquerque,USA
• 作者: S.MUHAMMAD;T.OHNO;K.TAKAMATSU;K.NABESHIMA;K.KUDO
• 通讯作者: K.KUDO

On-line Reactor Monitoring with Neural Network for RSG-GAS

RSG-GAS 神经网络反应器在线监测

• 发表时间: 2005
• 期刊: Proceeding of Computational Intelligence Methods ＆ Applications (CIMA' 5) Intanbul, Turky
• 作者: S.MUHAMMAD;T.OHNO;K.NABESHIMA;K.KUDO
• 通讯作者: K.KUDO

Full-Integrated System of Real-Time Monitoring Based on Distributed Architecture for High Temperature Engineering Test Reactor (HTTR)

基于分布式架构的高温工程试验堆（HTTR）实时监控全集成系统

• 发表时间: 2005
• 期刊: Proc. GLOBAL 2005, International Conference of Nuclear Energy Systems for Future Generation and Global Sustainability Tsukuba, Japan
• 作者: S.MUHAMMAD;T.OHNO;K.KUDO;K.TAKAMATSU;K.NABESHIMA
• 通讯作者: K.NABESHIMA

ニューラルネットワークを用いたHTTR制御棒引抜き試験の事前解析手法

HTTR控制棒拉拔试验神经网络初步分析方法

• 发表时间: 2005
• 期刊: 日本原子力学会和文論文誌 第4巻第2号
• 作者: Tomio OHNO;S.MUHAMMAD;K.KUDO;K.TAKAMATSU;S.Nakagawa;K.NABESHIMA;大野富生 他
• 通讯作者: 大野富生 他