%0 Journal Article
%T 基于支持向量机和遗传算法的变压器故障诊断<br>Power transformer fault diagnosis based on a support vector machine and a genetic algorithm
%A 吐松江·卡日
%A 高文胜
%A 张紫薇
%A 莫文雄
%A 王红斌
%A 崔屹平
%J 清华大学学报（自然科学版）
%D 2018
%R 10.16511/j.cnki.qhdxxb.2018.25.032
%X 为了提高变压器故障诊断准确率，该文提出了一种基于支持向量机（support vector machine，SVM）和遗传算法（genetic algorithm，GA）的电力变压器故障诊断方法。基于5种常用油中溶解气体分析方法的20种不同输入建立初始特征集合，采用二进制方式将支持向量机惩罚因子、核参数及特征子集编码至遗传算法染色体，建立基于5折交叉验证正确率的适应度函数，联合优化最优特征子集和支持向量机参数组合。然后依据最优特征子集和参数组合训练诊断模型，并利用测试集和故障实例验证诊断性能。实例分析结果表明：该方法能准确、有效地诊断变压器故障，比基于传统特征子集的支持向量机-遗传算法模型、IEC三比值法、反向传播神经网络和朴素Bayes等方法具有更高的诊断准确率。<br>Abstract：A fault diagnosis method was developed based on a support vector machine (SVM) and a genetic algorithm (GA) to improve the accuracy of power transformer fault diagnoses. The system receives 20 different inputs from 5 common dissolved gas analysis (DGA) approaches to create the original feature set. Then, the penalty parameters, the SVM kernel function parameters and feature subsets are randomly encoded into the GA chromosome using a binary code technique with the 5-fold cross validation accuracy of the training set used as the fitness function. The SVM parameters and the feature subsets are then simultaneously optimized by the genetic algorithm. Finally, DGA samples from the testing set are examined by the model trained with the optimal parameters and the selected feature subsets. The results demonstrate that this method is able to accurately distinguish power transformer faults. This method has fault diagnosis accuracy than GA-SVM models with a non-optimal feature subset, the IEC method, the back propagation neuro network (BPNN) and the Na？ve Bayes method.
%K 故障诊断
%K 油中溶解气分析
%K 支持向量机(SVM)
%K 遗传算法(GA)
%K &lt
%K br&gt
%K fault diagnosis
%K dissolved gas analysis
%K support vector machine
%K genetic algorithm
%U http://jst.tsinghuajournals.com/CN/Y2018/V58/I7/623