摘要
为提高对核电站主管道破裂识别的及时性和准确性,提出一种分层多维故障识别方法,建立主管道的预警系统,在事故初期对小破口主管道破裂进行故障定位和故障程度评估,提高核电站的运行安全。根据核电的机理模型、测试和专家经验等综合确定故障集合、征兆集合和各识别规则,在核电模型中人为引入不同故障位置和不同故障程度的小破口主管道破裂,并利用该预警系统进行识别。结果表明,可在事故初期对微小程度的主管道破裂进行准确的故障定位和故障程度评估,为核电站操作人员提供更完整的多维故障识别结果,从而验证了主管道预警系统的有效性和可行性。
In order to improve the timeliness and accuracy of identifying SB_LOCA,an early-warning system based on a hierarchical and multidimensional method is established to locate the fault and evaluate its degree in the early stage. It is capable to improve the operational security of nuclear power plants. The fault set,symptom set and identifying rules are comprehensively determined according to nuclear testing platform,mechanism model and expert experience. Different kinds of SB_LOCA( in different positions and of degrees) are inserted into the nuclear power simulator and recognized by the early-warning system. The results show that it can locate faults accurately and evaluate the faults even of tiny degree at the early stage,which provides to operators with more complete fault identification and furthermore verifies the validity and feasibility of this early-warning system.
引文
[1]周刚,杨立.核电厂智能识别方法研究的进展[J].原子能科学技术,2008,S1:92-99.ZHOU Gang,YANG Li.Advance in study of intelligent diagnostic method for nuclear power plant[J].Atomic Energy Science and Technology,2008,S1:92-99.
[2]骆建波.核电站报警触发式智能识别专家系统的研究[D].上海:上海电力学院,2015.LUO Jian-bo.Research on alarm triggered int-elligent fault diagnosis expert system of nucl-ear power plant[D].Shanghai:Shanghai University of Electric Power,2015.
[3]慕昱,夏虹,刘永阔.基于邻域粗糙集和决策树算法的核电厂故障诊断方法[J].原子能科学技术,2011,45(1):44-47.MU Yu,XIA Hong,LIU Yong-kuo.Fault on diagnosis method for nuclear power plant based decision tree and neighborhood roughsets[J].Atomic Energy Science and Technology,2011,45(1):44-47.
[4]徐金良,陈五星,唐耀阳.基于粗糙集理论和支持向量机算法的核电厂故障诊断方法[J].核动力工程,2009,30(4):52-54.XU Jin-liang,CHEN Wu-xing,TANG Yao-yang.Study on fault diagnosis in nuclear power plant based on rough sets and support vector machine[J].Nuclear Power Engineering,2009,30(4):52-54.
[5]王晓龙,蔡琦,张晓奇,等.基于多分类SVM的船用核动力装置主回路系统破口特征识别技术研究[J].原子能科学技术,2014(3):462-468.WANG Xiao-long,CAI Qi,ZHANG Xiao-qi,et al.Study on diagnostic technique for nuclear power plant primary coolant circuit system break characteristics based on multi-classification SVM[J].Atomic Energy Science and Technology,2014(3):462-468.
[6]刘永阔,夏虹,谢春丽,等.基于RS-FNN的核电厂设备智能故障诊断方法的研究[J].核动力工程,2007,28(1):110-114.LIU Yong-kuo,XIA Hong,XIE Chun-li,et al.Study on intelligence fault diagnosis method for nuclear power plant equipment based on rough set and fuzzy neural network[J].Nuclear Power Engineering,2007,28(1):110-114.
[7]董雅欣.核电厂主冷却剂系统分布式故障诊断技术研究[D].哈尔滨:哈尔滨工程大学,2012.DONG Ya-xin.Research on distributed fault diagnosis technology of reactor coolant system in nuclear power plant[D].Harbin:Harbin Engineering University,2012.
[8]马杰,郭立峰,彭俏.基于粒子群优化算法的压水堆失水事故研究[J].核动力工程,2012,33(3):89-91.MA Jie,GUO Li-feng,PENG Qiao.Research on loss of coolant accident of pressurized water reactor based on PSO algorithm[J].Nuclear Power Engineering,2012,33(3):89-91.
[9]马良玉,马永光,王兵树.不同负荷下高加给水系统程度迥异故障识别的新方法[J].中国电机工程学报,2010(2):115-121.MA Liang-yu,MA Yong-guang,WANG Bing-shu.A new approach to diagnose variable degree faults under different operating points for high-pressure feed-water heater system[J].Proceedings of the CSEE,2010(2):115-11.
[10]周志杰,杨剑波,胡昌华,等.置信规则库专家系统与复杂系统建模[M].北京:科学出版社,2011.ZHOU Zhi-jie,YANG Jian-bo,HU Chang-hua,et al.Confidence rule based expert system and complex system modeling[M].Beijing:Science Press,2011.
[11]钱虹,骆建波,金蔚霄,等.报警触发式蒸汽发生器传热管破裂事故识别系统的研究[J].核动力工程,2015,36(1):98-103.QIAN Hong,LUO Jian-bo,JIN Wei-xiao,et al.Research on alarm triggered fault diagnosisexpert system for U-shaped tube breaking accident of steam generators[J].Nuclear Power Engineering,2015,36(1):98-103.