基于Vague集的模糊聚类在变压器故障诊断中的研究  

Researeh of Power Transformer Fault Diagnosis Based on Vague Clustering Analysis

作　　者：兰华[1] 郑广瑞[1] 孙学林[1] 侯彩霞[2] 

机构地区：[1]东北电力大学电气工程学院,吉林吉林132012 [2]内蒙古民族大学,内蒙古通辽028043

出　　处：《电测与仪表》2011年第1期46-49,71,共5页Electrical Measurement & Instrumentation

摘　　要：油中溶解气体分析(DGA)方法是诊断变压器潜伏性故障的常用方法之一。该方法在提取样本模式特征量时缺乏科学的数据分析,导致故障诊断模型的输入模式特征量和输出模式类型不能实现或产生错误的非线性映射。将Vague集的模糊聚类方法应用到变压器故障诊断的研究,是通过建立Vague相似关系矩阵,运用传递闭包法进行Vague聚类分析,并在变压器故障诊断中验证了该方法的可行性和有效性。Among various preventive measures,DGA has long been recognized as the best method for the detection and identification of incipient faults in transformer.Exciting lacking scientific analysis in sample extraction model characteristics,leading to the input mode characteristic quantities and output mode type of fault diagnosis model can not achieve or make mistake in nonlinear mapping.In this paper,vague clustering analysis is applied into the fault diagnosis of power transformer.First of all,a similarity relationship Vague matrix is established,Vague cluster analysis is carried on by transitive closure method.The example of incipient faults in transformer proves that it is feasible and valid.

关 键 词：VAGUE集 传递闭包法 DGA 电力变压器 故障诊断 

分 类 号：TM407[电气工程—电器]