基于ANFIS的GIS设备局部放电故障辨识  

Fault identification of GIS equipment partial discharge based on ANFIS

作　　者：王姣[1] 刘利强[1] 胡凯旋[1] 吕超[2] 王连旌 

机构地区：[1]内蒙古工业大学电力学院,内蒙古呼和浩特010080 [2]内蒙古电力科学研究院,内蒙古呼和浩特010020

出　　处：《电工电能新技术》2016年第4期75-80,共6页Advanced Technology of Electrical Engineering and Energy

基　　金：内蒙古自治区研究生自然科学基金(S20141012805);内蒙古自治区自然科学基金(2015MS0543)资助项目

摘　　要：为了实现气体绝缘组合电器设备局部放电故障类型的辨识,本文通过分析四种典型绝缘缺陷局部放电时SF6气体分解组分特点,选取四种气体分解物含量比值作为特征向量,阐释了气体含量比值的物理意义,构造了三输入单输出的自适应模糊神经推理系统(ANFIS),对该模型的有效性进行了测试。测试结果表明局部放电类型的ANFIS辨识系统识别效果好,收敛速度快,且对样本数量要求低。GIS equipment is one of the most important equipment in the power system and is widely used. It is significant to make GIS insulation defect detection regarding to safe and reliable operation of GIS. When GIS insulation defect exists within the device,the internal partial discharge is likely to occur. Partial discharge signal contains a lot of insulation status information,through which its insulating status can be determined. In order to recognize the fault types of partial discharge of gas insulated switchgear equipment,the characteristics of SF6 gas decomposition component of four typical insulation defects are analyzed when partial discharge occurs. The content ratio of four gas decomposition is selected as a feature vector,and the physical meaning of gas content ratio is explained. A three-input single output system of ANFIS is constructed,and the effectiveness of the proposed model is tested.Test results show that the characteristics of the partial discharge type of ANFIS recognition system can satisfy the requirements of good recognition,fast convergence and low sample size.

关 键 词：气体绝缘组合电器 局部放电 自适应模糊神经推理系统 故障辨识 

分 类 号：TM855[电气工程—高电压与绝缘技术]