摘要
针对提升故障诊断的准确度问题,提出一种基于最小熵的故障诊断算法.首先,依据节点故障概率和各种噪声的发生概率计算一个可疑节点门限值;其次,计算各个节点对于探测结果的信息增益,与门限值对比,将高于门限值的节点视为可疑节点,存入可疑节点集合;最后,对可疑节点集合进行排序,将最小熵对应的节点视为故障节点,并经过仿真实验验证了该算法的有效性.
How to diagnose the fault of network is one of the problems in electric power data network.Currently,one of main factors that affect the accuracy of fault diagnosis in power integrated data network is the noise. However,there is almost no mention on the fault diagnosis method in the scheme,because it is difficult to improve the accuracy of fault diagnosis. A new fault diagnosis technique based on minimum entropy was proposed. Firstly,the information gain of each node is calculated according to the probability of node failure probability and the occurrence probability of each node. Then,the nodes are considered as suspicious nodes. Finally,the nodes are considered as nodes.
出处
《北京邮电大学学报》
EI
CAS
CSCD
北大核心
2016年第B06期10-13,共4页
Journal of Beijing University of Posts and Telecommunications
基金
国家电网公司科技项目
关键词
电力综合数据网
噪声
熵
故障诊断
electric power data network
noise
entropy
fault diagnosis