高压电器2018，Vol.54Issue(1)：236-242,7.DOI:10.13296/j.1001-1609.hva.2018.01.036
基于改进凝聚层次聚类算法的变压器绕组及铁心故障诊断研究
Research on Fault Diagnosis of Transformer Winding and Core Based on the Improved Agglomerative Hierarchical Clustering Algorithm
摘要
Abstract
In order to realize online condition monitoring of transformer by vibration response method,this paper proposes one kind of transformer fauh diagnosis method based on the improved agglomerative hierarchical clustering algorithm.First of all,using ensemble empirical mode decomposition (EEMD)method to get vibration signal characteristic values of transformer.Then,agglomerative hierarchical clustering algorithm is used to classify vibration signal characteristic values of test transformers and get 4 kinds of characteristic values,including the normal state of transformer,winding axial deformation,winding radial deformation and iron core fault state.Meanwhile,to overcome the shortcoming of hierarchical clustering algorithm,which has a large amount of computation,improvements are made to speed on transformer classification.Finally,by testing practical examples,the experimental results prove that,this method can recognize transformer's state immediately and effectively,which can realize online monitoring and fault diagnosis for transformer winding and core.关键词
振动响应法/集合经验模态分解/凝聚层次聚类/故障诊断Key words
vibration response method/ensemble empirical mode decomposition/agglomerative hierarchical clustering/fault diagnosis引用本文复制引用
李敏,陈果,沈大千,陈飞洋,罗宇昆,王昕..基于改进凝聚层次聚类算法的变压器绕组及铁心故障诊断研究[J].高压电器,2018,54(1):236-242,7.基金项目
国家自然科学基金项目(61673268) （61673268）
国家自然科学基金重点项目(61533012) （61533012）
上海市自然科学基金(14ZR1421800) （14ZR1421800）
流程工业综合自动化国家重点实验室开放课题基金资助.Project Supported by National Natural Science Foundation of China(61673268),the Key Project of NSFC(61533012),Shanghai Natural Science Foundation(14ZR1421800),State Key Laboratory of Synthetical Automation for Process Industries. （61673268）
