基于支持向量机的电晕放电模式识别方法

Corona discharge pattern recognition based on support vector machine

应用自回归(Autoregression,简称AR)模型提取电晕放电信号的AR模型参数作为信号特征量,利用支持向量机(Support Vector Machine,简称SVM)作为分类器对放电模型进行识别,重点分析了核函数和支持向量机参数对分类器的影响。结果表明,AR模型参数作为信号特征量,并与支持向量机结合对电晕放电信号进行识别是有效的。

AR model parameters of corona discharge signal extracted by AR model as signal characteristic quantity and support vector machine as classifier,discharge model recognition is conducted and influences of kernel function and support vector machine on classifier are analyzed.Result indicates that AR model parameters,as signal characteristic quantity,together with support vector machine is effective to corona discharge recognition.