基于SVM的电力变压器故障诊断方法与分析

Transformer Fault Diagnosis Method and Analysis Based on SVM

在电网中,变压器属于一类重要的装备。对变压器故障类型的科学诊断,能够为电网安全稳定运行提供基础。变压器故障诊断方法以变压器油中气体分析技术,即DGA的运用最为普遍,其在变压器的预防保护试验中发挥着积极作用,是目前变压器故障诊断的重点技术。但是DGA技术存在大量的缺陷,例如无法准确诊断多重故障、诊断准确率相对较低等。本方法在支持向量机(SVM)模型的基础上,针对非线性问题的优化解决方法,提出了判断变压器工作方式创新型方法。经测试,新型方法的判断准确率达到96.7%,符合变压器故障诊断工作的精度要求。

In the power grid,the transformer belongs to a class of important equipment,and scientific diagnosis is made for its fault type,which can provide a basis for the safe and stable operation of the power grid.At present,the focus is on fault diagnosis of dissolved gases in transformer oil.From the research work of transformer fault diagnosis methods,the use of oil gas analysis technology,DGA,is the most common,and it plays an active role in the preventive protection test of transformers.However,DGA technology contains a large number of defects,such as the inability to accurately diagnose multiple faults,the relatively low diagnostic accuracy,and so on.Based on the support vector machine(SVM)model,this paper proposes an innovative method for judging the working mode of the transformer for the optimization of nonlinear problems.After testing,the accuracy of the judgment can reach 96.7%,which is in line with the accuracy requirements of the transformer fault diagnosis work.