基于分层多维故障识别的核电站主管道预警系统研究

Research on Early-warning System of Main Pipeline in Nuclear Power Plants based on Hierarchical and Multidimensional Method for Fault Identification

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_L＇OCA, an early-warning sys- tem 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 va- lidity and feasibility of this early-warning system.