LVQ神经网络在GIS局部放电类型识别中的应用  

Application of the LVQ Neutral Network to the Recognition of GIS Discharge Types

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18期112-115,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：通过在气体绝缘组合电器(gas insulated switchgear,GIS)实体模型内部分别放置针-板、悬浮金属颗粒和绝缘子表面固定金属颗粒三种缺陷模型,用超声波传感器在相同电压下采集到良好的局部放电波形。针对波形选取了7个特征参数,最后用LVQ神经网络对放电类型进行识别,其综合识别率达到96.7%,高于S_Kohonen神经网络,有很好的实用价值。The needle-plate, suspended separately in the GIS entity model. The same voltage. Aiming at the waveforms, done with the LVQ neural network and neural network. So it has some practical metal particles and metal particles fixed on the insulator surface were placed discharge waveforrns were detected by using the ultrasonic sensor under the seven parameters were selected. Finally, the discharge type recognition was the recognition rate reached 96.7 percent,higher than that of the S_Kohonen values.

关 键 词：气体绝缘组合电器 超声波传感器 LVQ网络 放电类型识别 

分 类 号：TM855[电气工程—高电压与绝缘技术]