摘要
针对电力变压器故障诊断精度较低的问题,提出用GWO算法串联KPCA算法处理DGA数据,并引入DEGWO-SVM模型对数据进行分类。首先利用KPCA对原始DGA数据进行特征提取,降低模型复杂度;其次为提高迭代速度与诊断准确率,利用DEGWO算法对SVM模型进行参数寻优,同时建立最优诊断模型;最后用所得模型进行电力变压器故障诊断,输出诊断结果。最终的实验结果表明:本文建立的DEGWO-SVM电力变压器故障诊断模型的诊断准确率高达93.3333%,明显高于现有的一些常用模型。同时,本文所选用的SVM模型较其他分类模型效果更好,效率更高。
To solve the problem of low accuracy of power transformer fault diagnosis,a GWO algorithm cascade KPCA algorithm is proposed to process DGA data,and the DeGGO-SVM model is introduced to classify the data.Firstly,KPCA is used to extract features from the original DGA data to reduce the complexity of the model;Secondly,in order to improve the iteration speed and diagnosis accuracy,DEGWO algorithm is used to optimize the parameters of SVM model,and the optimal diagnosis model is established at the same time.Finally,the model is used for power transformer fault diagnosis,and the diagnosis results are output.The final experimental results show that the diagnostic accuracy of the proposed DeGGO-SVM power transformer fault diagnosis model is up to 93.3333%,which is significantly higher than some existing common models.At the same time,the SVM model is more effective and more efficient than other classification models.
作者
何柳
张梅
He Liu;Zhang Mei(School of Electrical and Information Engineering,Anhui University of Technology,Huainan,Anhui 232001,China)
出处
《黑龙江工业学院学报（综合版）》
2023年第3期44-50,共7页
Journal of Heilongjiang University of Technology(Comprehensive Edition)
基金
安徽高校自然科学研究项目(项目编号:KJ2020A0309)
国家自然科学基金资助项目(项目编号:51874010)。
