基于加权中智C均值算法的变压器故障诊断模型

Fault Diagnosis of Transformer Based on Feature-Weighted Neutrosophic C-Means Algorithm

为提高变压器故障诊断准确度,提出了一种基于加权中智C均值算法的变压器故障诊断方法。该方法利用基于样本相似度的加权方法对样本特征进行加权,再引入中智理论对样本的分布重新分配,建立起基于加权中智C均值算法的变压器故障诊断模型。研究结果表明,该方法不仅弥补了传统FCM相同权重分配的不足,有效提高了故障诊断的准确率,且诊断结果产生的中智点对故障的变化预测具有重要意义。

In order to improve the accuracy of transformer fault diagnosis,this paper proposes a transformer fault diagnosis method based on Feature-Weighted Neutrosophic C-Means algorithm(WNCM).Firstly,the weighting method based sample similarity is used to weight the sample features.Then with the help of the neutrosophic theory,the feature weights of the samples are redistributed.Finally,the transformer fault diagnosis model is established based on the Feature-Weighted Neutrosophic C-Means algorithm.The research results show that the method not only makes up for the deficiency of the same weight distribution of the traditional FCM,but also effectively improves the accuracy of the fault diagnosis,and the neutrosophic point generated by the diagnosis results has important practical significance for prediction of fault change.