基于DGA特征量优选与GA-SVM的变压器故障诊断模型  

Transformer Based on DGA Feature Quantity Optimization and GA-SVM Fault Diagnosis Model

作　　者：王晶 许素安 洪凯星 王策 刘勇 陈兴 WANG Jing;XU Su-an;HONG Kai-xing;WANG Ce;LIU Yong;CHEN Xing(School of Mechanical and Electrical Engineering,China Jiliang University,Hangzhou 310018,China)

机构地区：[1]中国计量大学机电工程学院,浙江杭州310018

出　　处：《变压器》2020年第12期36-40,46,共6页Transformer

基　　金：浙江省公益技术应用研究资助项目(LGG20E050013);国家自然科学基金项目(51805504)。

摘　　要：为了解决变压器故障诊断传统方法中DGA特征量选取的主观性与完备性欠缺问题,本文选取5种常用故障诊断方法的20种不同特征量作为初始特征集合,结果证明本文方法能有效提高变压器故障诊断准确率。In order to solve the problem of subjectivity and lack of completeness of DGA feature selection in traditional transformer fault diagnosis methods, 20 different feature quantities from 5 common fault diagnosis methods are selected as initial feature sets.The results show that this method can effectively improve the accuracy of transformer fault diagnosis.

关 键 词：油中溶解气体 故障诊断 支持向量机 遗传算法 

分 类 号：TM411[电气工程—电器]