CAJ | 학술논문

针对典型小样本数据的变压器故障诊断，文章提出了一种基于差分进化算法优化的支持向量机构建电力变压器故障诊断方法。该方法是采用差分进化算法来优化支持向量机核函数参数g和惩罚因子C，将优化过的支持向量机对小样本故障数据进行故障诊断。实验结果表明，该方法比网格搜索优化算法和粒子群优化算法具有更高的准确率，非常适合于电力变压器的故障诊断。
침대전형소양본수거적변압기고장진단，문장제출료일충기우차분진화산법우화적지지향량궤구건전력변압기고장진단방법。해방법시채용차분진화산법래우화지지향량궤핵함수삼수g화징벌인자C，장우화과적지지향량궤대소양본고장수거진행고장진단。실험결과표명，해방법비망격수색우화산법화입자군우화산법구유경고적준학솔，비상괄합우전력변압기적고장진단。
In view of the transformer fault diagnosis for typical small sample data , this paper proposes a support vector machine of power transformer fault diagnosis method ( SVM) based on differential evolution algorithm optimization. This method uses the differential evolution algorithm to optimize function parameters C, and factor g in support vector machine, and applies the optimized support vector machine ( SVM) to fault diagnosis data of small sample.The ex-perimental results show that the accuracy is higher than grid search optimization method and particle swarm optimiza-tion algorithm, and it is very suitable for the fault diagnosis of power transformer.