基于动态阈值的变压器异常状态检测.doc

基于动态阈值的变压器异常状态检测
刘勇1，尹豪杰2，张星海1，范松海1，严磊1，高波2
(1. 国网四川省电力公司，成都 610041；2. 西南交通大学电气工程学院，成都，610031）
摘 要：为提升电力变压器状态检修效率和异常状态检测、预警能力，考虑变压器在线监测数据、检修数据及设备本体数据间的相关性，提出了一种基于动态阈值的变压器异常运行状态检测方法，通过构造动态预测模型对特征参数基线进行刻画。在此基础上，采用贝叶斯网络推算变压器运行状态，以概率大小判断变压器可能状态，并基于实际运行数据对所提方法进行了验证分析。计算结果表明文中方法可对异常检测数据有效检测，能够对变压器异常状态准确识别和预测。
关键词：动态阈值；贝叶斯网络；电力变压器；异常状态
中图分类号： 文献标识码： 文章编号：1001-1390（2017）00-0000-00
Abnormal condition detection of power transformer based on
dynamical threshold
Liu Yong1, Yin Haojie2, Zhang Xinghai1 ,Xinghai1, Fan Songhai1,Yan, Yan Lei1, Gao Bo2
(1. State Grid Sichuan Electric Power Company, Chengdu 610041, China; . 2. School of Electrical Engineering, Southwest Jiaotong University, Chengdu 610031, China)

Abstract: In order To to improve the efficiency of condition based maintenance and the capability of abnormal condition detection and warning ability, a new method which based on dynamical threshold for abnormal operation
condition detection was proposed. Baselines of the parameters are depicted through the establishment of
dynamical prediction model. On such basis, the Bayesian network is utilized for calculating the operating state of transformer, which uses the probability to decide its potential condition. Finally, the proposed method is verified through using the field acquired data. Numerical simulation results show that the