动态不确定因果图用于复杂系统故障诊断

删除或更新信息，请邮件至freekaoyan#163.com(#换成@)

清华大学辅仁网/2017-07-07

动态不确定因果图用于复杂系统故障诊断

赵越¹, 董春玲², 张勤^1,2

1. 清华大学核能与新能源技术研究院, 先进核能技术协同创新中心, 先进反应堆工程与安全教育部重点实验室, 北京 100084;
2. 清华大学计算机科学与技术系, 北京 100084

Fault diagnostics using DUCG incomplex systems

ZHAO Yue¹, DONG Chunling², ZHANG Qin^1,2

1. Key Laboratory of Advanced Reactor Engineering and Safety of the Ministry of Education, Collaborative Innovation Center of Advanced Nuclear Energy Technology, Institute of Nuclear and New Energy Technology, Tsinghua University, Beijing 100084, China;
2. Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China

摘要:

输出: BibTeX | EndNote (RIS)

摘要商用核电站中的操作员在电站正常运行时需要密切监测核反应堆的运行状态。当故障发生时, 对核电站进行迅速、有效的故障诊断和对故障进行正确处理极为重要。该文介绍了动态不确定因果图(dynamic uncertain causality graph, DUCG)理论方法, 并将DUCG方法应用于核电站的故障诊断。以中国广核集团有限公司的宁德核电站1号机组CPR1000为原型建立了8类典型的二回路故障模型, 进行故障诊断验证和故障发展预测。同时, 应用该公司全配置仿真系统对每个故障进行了20次实际测试。验证和测试结果均表明: DUCG能够准确、快速、高效地进行故障诊断。

关键词 ：动态不确定因果图,复杂系统,故障诊断

Abstract：The status of nuclear reactors in commercial nuclear power plants needs to be closely monitored to maintain normal operations. When a failure occurs, rapid and effective fault diagnostics and proper handling of failures is extremely important. This paper applies dynamic uncertain causality graph (DUCG) theory to fault diagnostics of nuclear power plants. The method was applied to a model with 8 typical second and loop faults based on the Ningde Nuclear Power Plant Unit 1 CPR1000 of the China Guangdong Nuclear Power Group (CGNPC) to verify the fault diagnostics and initial progression forecasts. Simulations were used to test each fault 20 times. The method and stimulator tests both showed that DUCG can accurately, quickly and efficiently diagnose faults.

Key words：DUCG complex system fault diagnosis

收稿日期: 2015-09-17 出版日期: 2016-05-19

ZTFLH:

TL361

通讯作者:张勤, 教授, E-mail: qinzhang@tsinghua.edu.cnE-mail: qinzhang@tsinghua.edu.cn

引用本文:

赵越, 董春玲, 张勤. 动态不确定因果图用于复杂系统故障诊断[J]. 清华大学学报（自然科学版）, 2016, 65(5): 530-537,543.
ZHAO Yue, DONG Chunling, ZHANG Qin. Fault diagnostics using DUCG incomplex systems. Journal of Tsinghua University(Science and Technology), 2016, 65(5): 530-537,543.

链接本文:

http://jst.tsinghuajournals.com/CN/10.16511/j.cnki.qhdxxb.2016.25.012或 http://jst.tsinghuajournals.com/CN/Y2016/V65/I5/530

图表:

表１　变量定义

图１　事件展开示意图

表２　符号定义表

表２　符号定义表（续表）

图２　部分异常参数随时间变化

图３　宁德１号机组的二回路故障诊断DUCG 图

图４　拆减后因果图

表３　故障发展预测表

表４　诊断结果表

表４　诊断结果表（续表）

参考文献:

[1] United States. President's Commission on the Accident at Three Mile Island. The Need for Change, the Legacy of TMI:Report of the President's Commission on the Accident at Three Mile Island[M]. Washington D C, USA:Government Printing Office, 1979.
[2] Rogovin M. Three Mile Island:A Report to the Commissioners and to the Public[R]. Washington D C,USA:Nuclear Regulatory Commission, 1979.
[3] ZHANG Qin. Dynamic uncertain causality graph for knowledge representation and reasoning:Discrete DAG cases[J].Journal of Computer Science and Technology, 2012,27(1):1-23.
[4] ZHANG Qin. Dynamic uncertain causality graph for knowledge representation and probabilistic reasoning:directed cyclic graph and joint probability distribution[J].IEEE Transactions on Neural Networks and Learning Systems, 2015,26(7):1503-1517.
[5] ZHANG Qin, DONG Chunling, CUI Yan, et al. Dynamic uncertain causality graph for knowledge representation and probabilistic reasoning:Statistics base, matrix, and application[J].IEEE Transactions on Neural Networks and Learning Systems, 2014,25(4):645-663.
[6] ZHANG Qin, GENG Shichao. Dynamic uncertain causality graph applied to dynamic fault diagnoses of large and complex systems[J].IEEE Transactions on Reliability, 2015,64(3):910-927.
[7] ZHANG Qin. Dynamic uncertain causality graph for knowledge representation and reasoning:Continuous variable, uncertain evidence, and failure forecast[J].IEEE Transactions on Systems, Man, and Cybernetics, 2015,45(7):990-1003.
[8] 赵越, 张勤, 邓宏琛, 等. DUCG在核电站二回路故障诊断中的应用[J]. 原子能科学技术, 2014,48(S1):496-501. ZHAO Yue, ZHANG Qin, DENG Hongchen, et al. Application of DUCG in fault diagnosis of nuclear power plant secondary loop[J].Atomic Energy Science and Technology, 2014,48(S1):496-501. (in Chinese)
[9] DONG Chunling, WANG Yanjun, ZHANG Qin, et al. The methodology of dynamic uncertain causality graph for intelligent diagnosis of vertigo[J].Computer Methods and Programs in Biomedicine, 2014,113(1):162-174.
[10] Nelson W R. Reactor:An expert system for diagnosis and treatment of nuclear reactor accidents[C]//Proceedings of the 2nd National Conference on Artificial Intelligence. Pittsburgh, USA:AAAI Press, 1982:296-301.
[11] 周刚, 杨立. 核电厂智能诊断方法研究的进展[J]. 原子能科学技术, 2008,42(B09):92-99. ZHOU Gang, YANG Li. Advance in study of intelligent diagnostic method for nuclear power plant[J].Atomic Energy Science and Technology, 2008,42(B09):92-99. (in Chinese)
[12] 陈志辉, 夏虹, 刘邈. 核电系统故障诊断专家系统研究[J]. 核动力工程, 2006,26(5):523-527. CHEN Zhihui, XIA Hong, LIU Miao. Study of expert system of fault diagnosis for nuclear power plant[J].Nuclear Power Engineering, 2006,26(5):523-527. (in Chinese)

No related articles found!