基于LMD-PCA和样本熵的瓷支柱绝缘子故障诊断

为了对变电站瓷支柱绝缘子状态进行有效评估,提出了一种将局域均值分解方法(Local Mean Decomposition,LMD)、主成分分析方法(Principal Components Analysis,PCA)和样本熵相结合的瓷支柱绝缘子振动信号故障诊断方法。首先,将瓷支柱绝缘子振动信号进行局域均值分解,得到PF(乘积函数)分量,利用主成分分析方法,提取主PF分量;其次,计算其样本熵作为表征瓷支柱绝缘子状态的特征向量,利用支持向量机(SVM)对输入的向量进行分类训练;最后,将测试样本特征向量输入训练好的SVM中进行分类识别。结果表明,该方法能有效提取瓷支柱绝缘子的故障特征并实现准确的故障分类。

Fault diagnosis of porcelain post insulator based on LMD-PCA and sample entropy

In order to evaluate the porcelain post insulator of substation effectively.An analysis method of vibration signal characteristics and fault diagnosis of porcelain post insulator based on the combination of local mean decomposition(LMD),principal component analysis(PCA)and sample entropy is proposed.Firstly,the diagnosis signal of porcelain post insulator is decomposed into local mean value,and then the PF component(the component with physical significance of instantaneous frequency after LMD decomposition)is obtained,Secondly,the sample entropy is calculated as the eigenvector to represent the state of porcelain post insulator,and SVM is used to train the input vector,Finally,the feature vector of the test sample is input into the trained SVM for classification and recognition.The results show that the method can effectively extract the fault features of porcelain post insulator and accurately and quickly realize the fault classification.