基于优化形态特征的变压器局部放电模式识别  

Pattern Recognition of Transformer Partial Discharge Based on Pattern Characteristics Optimization

作　　者：任先文[1] 薛雷[1] 宋阳[1] 孙守鑫[1] 沈重[1] 郭丹丹[1] 

机构地区：[1]东北电力大学,吉林132012

出　　处：《高压电器》2011年第6期39-42,47,共5页High Voltage Apparatus

摘　　要：针对变压器的4种典型局部放电模型的脉冲波形,应用多尺度数学形态学开运算提取局部放电脉冲波形的形态谱,通过形态谱的提取可看出每种放电类型具有不同的形态特征。同时,为了去掉冗余的特征量,优化形态特征,对每种放电类型的不同形态特征进行相关性分析。实验结果表明,应用优化后的特征量进行识别能够得到良好的识别效果,并且能够降低识别系统的复杂度。Aiming at four typical partial discharge pulse in transformer, the pattern spectrums of partial discharge signals are extracted by multi-scale open operation of mathematical morphology, from this it is observed that each type of discharge possesses its own pattern characteristics.Correlation analysis of pattern characteristics of each discharge type, in order to remove the redundant features and optimize the pattern characteristics.The experiment results show that the applications of optimized features enable to detect a good recognition rate and reduce the complexity of the recognition system.

关 键 词：局部放电 数学形态学 形态谱 相关性分析 优化 模式识别 

分 类 号：TM855[电气工程—高电压与绝缘技术]