Root-cause analysis of occurring alarms in thermal power plants based on Bayesian networks
Root-cause analysis of occurring alarms in thermal power plants based on Bayesian networks
复制标题
DOI：
10.1016/j.ijepes.2018.05.029
复制
发表时间：
2018-12
影响因子：
5.2
通讯作者：
Jiandong Wang;Zijiang Yang;Su Jianjun;Yan Zhao;Song Gao;X. Pang;Donghua Zhou
中科院分区：
文献类型：
--
作者：
Jiandong Wang;Zijiang Yang;Su Jianjun;Yan Zhao;Song Gao;X. Pang;Donghua Zhou
针对火电厂中一类特殊的报警变量，即由二值根本原因变量引起的报警，提出了一种分析报警发生根本原因的方法。使用具有一个子节点和多个父节点的贝叶斯网络来描述警报变量和根本原因变量之间的关系。递归地更新网络中的概率参数。从具有最大后验条件概率的父节点集合确定发生警报的根本原因。该方法可以消除节点中误报和漏报的负面影响，处理多个根源的共存，并检测已知根源的不完整性。最后通过工业实例验证了该方法的有效性。
The paper proposes a method to analyze root causes of occurring alarms, for a special type of alarm variables in thermal power plants, where alarms are arisen from binary-valued root-cause variables. A Bayesian network with one child node and multiple parent nodes is used to describe the relationship between an alarm variable and root-cause variables. Probability parameters in the network are updated recursively. Root causes of occurring alarms are determined from the parent node set with the largest posterior conditional probability. The proposed method can remove negative effects of false and missing alarms in the nodes, handle the co-existence of multiple root causes, and detect the incompleteness of known root causes. Industrial examples are provided to illustrate the effectiveness of the proposed method.