基于神经网络方法的LOCA事故诊断

李仕鲜; 刘井泉; 沈永刚

doi:10.11889/j.0253-3219.2017.hjs.40.080604

您当前的位置：

首页 >

文章列表页 >

基于神经网络方法的LOCA事故诊断

核能科学与工程 | 更新时间：2021-05-19

- 基于神经网络方法的LOCA事故诊断
- Fault diagnosis of LOCA based on ANN methods
- 核技术 2017年40卷第8期文章编号：080604
- 作者机构：
  
  1.清华大学工程物理系北京 100084
  2.中广核研究院有限公司深圳 518000
- 作者简介：
  
  [ "李仕鲜, 男, 1992年出生, 2015年毕业于南华大学, 现为硕士研究生, 研究领域为核电厂安全分析", "LI Shixian, male, born in 1992, graduated from University of South China in 2015, master student, focusing on safety analysis of nuclear power plant" ]
  刘井泉, E-mail:jingquan@tsinghua.edu.cnLIU Jingquan, E-mail:jingquan@tsinghua.edu.cn
- 基金信息：
- DOI：10.11889/j.0253-3219.2017.hjs.40.080604
  中图分类号： TL364.4
- 收稿日期：2017-02-27，
  
  修回日期：2017-04-19，
  
  纸质出版日期：2017-08-10
- 稿件说明：
移动端阅览
李仕鲜, 刘井泉, 沈永刚. 基于神经网络方法的LOCA事故诊断[J]. 核技术, 2017,40(8):080604

Shixian LI, Jingquan LIU, Yonggang SHEN. Fault diagnosis of LOCA based on ANN methods[J]. Nuclear techniques, 2017, 40(8): 080604
李仕鲜, 刘井泉, 沈永刚. 基于神经网络方法的LOCA事故诊断[J]. 核技术, 2017,40(8):080604 DOI： 10.11889/j.0253-3219.2017.hjs.40.080604.

Shixian LI, Jingquan LIU, Yonggang SHEN. Fault diagnosis of LOCA based on ANN methods[J]. Nuclear techniques, 2017, 40(8): 080604 DOI： 10.11889/j.0253-3219.2017.hjs.40.080604.

摘要

冷却剂丧失事故（Loss of Coolant Accident，LOCA）是核电厂安全分析中的一类典型事故，不同的破口位置和破口尺寸将直接影响到事故的处置和后果。为判断LOCA事故的破口位置和尺寸，可以借助于神经网络的模式识别功能。针对CPR1000核电系统，利用CATHARE软件建模并仿真不同破口位置和尺寸的LOCA事故，提取事故发生时的6类热工水力参数对BP（Back Propagation）神经网络、Elman神经网络、RBF（Radial Basis Function）神经网络和支持向量机进行训练，再将训练后的神经网络用于破口位置和尺寸的诊断。结果表明，在4种神经网络中，参数优化后的支持向量机对破口位置和尺寸的诊断准确率较高且诊断稳定性较好。在LOCA事故发生时，可以利用支持向量机获取破口的详细信息，辅助操纵员高效地处理事故。

Abstract

Background

Loss of coolant accident (LOCA) is one of the typical accidents in safety analysis of nuclear power plant and the location and the size of break will affect its treatment and consequences directly.

Purpose

This study aims to diagnose the location and the size of break by using artificial neural network (ANN) based pattern recognition approach.

Methods

CATHARE program was used to model and simulate different location and size of break in LOCA for the CPR1000 nuclear power system. Six types of thermal-hydraulic parameters were extracted to train four types of ANN methods (back propagation (BP) neural network

Elman neural network

radial basis function (RBF) neural network and support vector machine) and the trained ANNs were utilized to diagnose the location and the size of break.

Results

The optimized support vector machine (SVM) is best method in terms of diagnosis accuracy and stability among 4 ANNs.

Conclusion

The operators can obtain more detailed information about break by SVM to deal with the accident efficiently

when a LOCA happens.

关键词

Keywords

references

林支康 , 殷煜皓 , 梁国兴 . AP1000核电厂RELAP5 SB-LOCA分析模式建立与应用 . 电力与能源 , 2011 . 6 457 - 461 . http://www.cnki.com.cn/Article/CJFDTOTAL-LYJI201106011.htm .

Zhikang LIN , Yuhao YIN , Guoxing LIANG . Establishing and application of AP1000 nuclear power plant RELAPS-code SB-LOCA model . Power & Energy , 2011 . 6 457 - 461 . http://www.cnki.com.cn/Article/CJFDTOTAL-LYJI201106011.htm .

中广核工程有限公司 . 中国百万千瓦级核电自主化依托工程 , : 北京中国原子能出版社 , 2013 .

China Nuclear Power Engineering Co., Ltd . China's million kilowatt class nuclear power self-reliance project , : Beijing China Atomic Energy Press , 2013 .

T V Santosh , G Vinod , A K Saraf , . Application of artificial neural networks to nuclear power plant transient diagnosis . Reliability Engineering and System Safety , 2007 . 92 1468 - 1472 . DOI: 10.1016/j.ress.2006.10.009 http://doi.org/10.1016/j.ress.2006.10.009 .

S W Cheon , S H Chang , H Y Chung , . Application of neural networks to multiple alarm processing and diagnosis in nuclear power plants . IEEE Transactions on Nuclear Science , 1993 . 40 ( 1 ): 11 - 20 . DOI: 10.1109/23.199482 http://doi.org/10.1109/23.199482 .

赵云飞 , 张立国 , 童节娟 , . BP神经网络在AP1000核电站事故诊断应用中的初步研究 . 原子能科学技术 , 2014 . 48 ( S1 ): 480 - 484 . DOI: 10.7539/YZK.2014.48.S0.0480 http://doi.org/10.7539/YZK.2014.48.S0.0480 .

Yunfei ZHAO , Liguo ZHANG , Jiejuan TONG , . Preliminary study on application of BP neural network in AP1000 nuclear power plant accident diagnosis . Atomic Energy Science and Technology , 2014 . 48 ( S1 ): 480 - 484 . DOI: 10.7539/YZK.2014.48.S0.0480 http://doi.org/10.7539/YZK.2014.48.S0.0480 .

蔡猛 , 张大发 , 张宇声 . 基于遗传算法的核动力设备实时故障诊断系统 . 核动力工程 , 2009 . 30 ( 3 ): 111 - 114, 130 . http://www.cnki.com.cn/Article/CJFDTOTAL-HDLG200903025.htm .

Meng CAI , Dafa ZHANG , Yusheng ZHANG . Nuclear power plant real-time fault diagnosis system based on genetic algorithm . Nuclear Power Engineering , 2009 . 30 ( 3 ): 111 - 114, 130 . http://www.cnki.com.cn/Article/CJFDTOTAL-HDLG200903025.htm .

刘永阔 , 夏虹 , 谢春丽 , . BP-RBF神经网络在核电厂故障诊断中的应用 . 原子能科学技术 , 2008 . 42 ( 3 ): 193 - 199 . http://www.cnki.com.cn/Article/CJFDTOTAL-YZJS200803001.htm .

Yongkuo LIU , Hong XIA , Chunli XIE , . Application of BP-RBF neural network to fault diagnosis of nuclear power plant . Atomic Energy Science and Technology , 2008 . 42 ( 3 ): 193 - 199 . http://www.cnki.com.cn/Article/CJFDTOTAL-YZJS200803001.htm .

肖岷 , 郝思雄 , 韩庆浩 , . 中广核CPR1000核岛堆芯概念设计和安全裕度评估初探 . 核动力工程 , 2005 . ( S1 ): 11 - 18 . http://www.cnki.com.cn/Article/CJFDTOTAL-HDLG2005S1003.htm .

Min XIAO , Sixiong HAO , Qinghao HAN , . Primary study on core concept design and safety margin of CPR1000 . Nuclear Power Engineering , 2005 . ( S1 ): 11 - 18 . http://www.cnki.com.cn/Article/CJFDTOTAL-HDLG2005S1003.htm .

谢春丽 , 夏虹 , 刘永阔 , . BP神经网络改进算法在核电设备故障诊断中的应用 . 核动力工程 , 2007 . 28 ( 4 ): 85 - 90 . http://www.cnki.com.cn/Article/CJFDTOTAL-HDLG200704019.htm .

Chunli XIE , Hong XIA , Yongkuo LIU , . Application of improved BP algorithm in fault diagnosis of nuclear power equipment . Nuclear Power Engineering , 2007 . 28 ( 4 ): 85 - 90 . http://www.cnki.com.cn/Article/CJFDTOTAL-HDLG200704019.htm .

熊晋魁 , 谢春玲 , 施小成 , . RBF人工神经网络在核电厂故障诊断中的应用 . 核动力工程 , 2006 . 27 ( 3 ): 57 - 60, 96 . http://www.cnki.com.cn/Article/CJFDTOTAL-HDLG200603012.htm .

Jinkui XIONG , Chunling XIE , Xiaocheng SHI , . Application of RBF artificial neural network to fault diagnose in nuclear power plant . Nuclear Power Engineering , 2006 . 27 ( 3 ): 57 - 60, 96 . http://www.cnki.com.cn/Article/CJFDTOTAL-HDLG200603012.htm .

S Seker , E Ayaz , E Türkcan . Elman's recurrent neural network applications to condition monitoring in nuclear power plant and rotating machinery . Engineering Applications of Artificial Intelligence , 2003 . 16 647 - 656 . DOI: 10.1016/j.engappai.2003.10.004 http://doi.org/10.1016/j.engappai.2003.10.004 .

汤宝平 , 习建民 , 李锋 . 基于Elman神经网络的旋转机械故障诊断 . 计算机集成制造系统 , 2010 . 10 2148 - 2152 . http://cdmd.cnki.com.cn/Article/CDMD-10220-2004050719.htm .

Baoping TANG , Jianmin XI , Feng LI . Fault diagnosis for rotating machinery based on Elman neural network . Computer Integrated Manufacturing Systems , 2010 . 10 2148 - 2152 . http://cdmd.cnki.com.cn/Article/CDMD-10220-2004050719.htm .

X G Zhang . Introduction to statistical learning theory and support vector machines . Acta Automatica Sinica , 2000 . 26 ( 1 ): 33 - 41 . http://en.cnki.com.cn/Article_en/CJFDTOTAL-MOTO200001005.htm .

袁胜发 , 褚福磊 . 支持向量机及其在机械故障诊断中的应用 . 振动与冲击 , 2007 . 11 29 - 35, 181 . DOI: 10.3969/j.issn.1000-3835.2007.02.008 http://doi.org/10.3969/j.issn.1000-3835.2007.02.008 .

Shengfa YUAN , Fulei CHU . Support vector machines and its applications in machine fault diagnosis . Journal of Vibration and Shock , 2007 . 11 29 - 35, 181 . DOI: 10.3969/j.issn.1000-3835.2007.02.008 http://doi.org/10.3969/j.issn.1000-3835.2007.02.008 .

宋梅村 , 蔡琦 . 基于支持向量回归的设备故障趋势预测 . 原子能科学技术 , 2011 . 45 ( 8 ): 972 - 976 . http://www.cnki.com.cn/Article/CJFDTOTAL-YZJS201108013.htm .

Meicun SONG , Qi CAI . Fault trend prediction of device based on support vector regression . Atomic Energy Science and Technology , 2011 . 45 ( 8 ): 972 - 976 . http://www.cnki.com.cn/Article/CJFDTOTAL-YZJS201108013.htm .

黄彦平 , 曹念 , 文彦 , . CATHARE程序的主要特征及应用 . 核动力工程 , 2003 . 24 ( 6 ): 540 - 544 . http://www.cnki.com.cn/Article/CJFDTOTAL-HDLG200306010.htm .

Yanping HUANG , Nian CAO , Yan WEN , . Main features of CATHARE code and its application . Nuclear Power Engineering , 2003 . 24 ( 6 ): 540 - 544 . http://www.cnki.com.cn/Article/CJFDTOTAL-HDLG200306010.htm .

陈明 . MATLAB神经网络原理与实例精解 , : 北京清华大学出版社 , 2013 .

Ming CHEN . MATLAB neural network theory and examples , : Beijing Tsinghua University Press , 2013 .

李坤 , 刘鹏 , 吕雅洁 , . 基于Spark的LIBSVM参数优选并行化算法 . 南京大学学报(自然科学) , 2016 . 52 ( 2 ): 343 - 352 . http://www.cnki.com.cn/Article/CJFDTOTAL-NJDZ201602016.htm .

Kun LI , Peng LIU , Yajie LYU , . The parallel algorithms for LIBSVM parameter optimization based on Spark . Journal of Nanjing University (Natural Sciences) , 2016 . 52 ( 2 ): 343 - 352 . http://www.cnki.com.cn/Article/CJFDTOTAL-NJDZ201602016.htm .

王小川 . MATLAB神经网络43个案例分析 , : 北京北京航空航天大学出版社 , 2013 .

Xiaochuan WANG . MATLAB neural network analysis of 43 cases , : Beijing Beijing University of Aeronautics and Astronautics Press , 2013 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

移动式微型裂变电离室中子探测器研制与核特性测试

一种用于高温高压环境高量程辐射监测仪的研制

某核电机组安全壳打压试验期间安全壳外加应变计数据分析研究