基于S_Kohonen网络的GIS局部放电类型识别  

Recognition of GIS Discharge Types Based on the S_Kohonen Network

作　　者：律方成[1] 张波[1] 

机构地区：[1]华北电力大学河北省输变电设备安全防御重点实验室,河北保定071003

出　　处：《电测与仪表》2014年第20期21-24,共4页Electrical Measurement & Instrumentation

基　　金：国家高技术研究发展计划项目(863计划)(2011AA05A121);中央高校基本科研业务费专项资金资助项目(13ZD14)

摘　　要：文中在气体绝缘组合电器(Gas Insulated Switchgear,GIS)实体模型中分别放置了针-板、悬浮金属颗粒和绝缘子表面固定金属颗粒缺陷模型,在相同的电压下用超声波传感器测得其放电波形。针对放电波形的特征,提取了7个特征参数,用7个特征参数组成的特征量作为S_Kohonen网络的输入,对放电类型进行识别,识别结果很好,说明S_Kohonen网络有一定的实用价值。In this paper,the defect model,with the needle-plate,the suspended metal particles and the metal parti-cles fixed on the insulator surface,was put in the entity model of the gas insulated switchgear（ GIS）. Discharge wave-forms were detected by the ultrasonic sensor at the same voltage. According to the characteristics of the discharge waveforms,seven characteristic parameters were extracted as the input of the S Kohonen network to identify the dis-charge types. The recognition result was good. This indicates that the S Kohonen network has some practical values.

关 键 词：GIS 超声波传感器 S KOHONEN网络 放电类型识别 

分 类 号：TM855[电气工程—高电压与绝缘技术]