基于神经网络综合分析的变压器油色谱在线监测系统 online monitoring system of transformer oil chromatography based on neural network integrated analysis.pdfVIP

基于神经网络综合分析的变压器油色谱在线监测系统 电工电气 (20 3 No.6) 基于神经网络综合分析的变压器油色谱在线监测系统 1 1 1 2 1 史晏廷 ，杨波 ，陈尔奎 ，李锦川 ，谭小艳 (1 山东科技大学 信息与电气工程学院，山东 青岛 266590； 2 东北电力大学 电气工程学院，吉林 吉林 132012) 摘 要：油色谱在线监测是电力变压器在线监测领域常用的方法之一。变压器故障诊断的结果将直 接作为变压器是否需要检修的决策依据，鉴于变压器故障原因的复杂性，仅靠单一的故障诊断方法很难 满足故障诊断的要求，故将传统故障诊断方法与 BP 神经网络方法通过 Borda 模型相结合，以提高变压 器故障诊断的准确率，最后用 C# 语言设计开发了故障诊断系统。该系统改变了以往的定期试验模式， 实现了变压器状态在线监测和分析。 关键词：变压器在线监测；故障诊断；BP神经网络；Borda模型；C#语言 中图分类号：TM411 文献标识码：A 文章编号：1007-3175(2013)06-0045-05 Online Monitoring System of Transformer Oil Chromatography Based on Neural Network Integrated Analysis SHI Yan-ting   2  , YANG Bo , CHEN Er-kui , LI Jin-chuan , TAN Xiao-yan  College of Information and Electrical Engineering, Shandong University of Science and Technology, Qingdao 26650, China; （ 2 Electrical Engineering College, Northeast Dianli University, Jilin 3202, China ） Abstract: Oil chromatography monitoring is one of the commonly used methods in the online monitoring field of power transformers. The re- sults of fault diagnosis for a transformer will provide a direct basis for determining whether the transformer needs an overhaul. Due to the complex reasons of transformer faults, it is difficult for a single diagnosis method to meet the requirements of fault diagnosis. In order to improve the ac- curacy of fault diagnosis, this paper combined the traditional fault diagnosis method with the back propagation (BP) neural network method by the Borda model. The fault diagnosis system developed by C# language improved the traditional mode of routine test and achieved online m