基于深度图卷积神经网络的GIS设备故障诊断方法  

Fault Diagnosis Method for GIS Equipment Based on Deep Graph Convolutional Neural Network

作　　者：刘志鹏 瞿哲 于聪 吴芊 陈博 方雅琪 LIU Zhipeng;QU Zhe;YU Cong;WU Qian;CHEN Bo;FANG Yaqi(State Grid Hubei Electric Power Co.,Ltd.Extra High Voltage Company,Wuhan 430050,Hubei,China;Hubei Engineering Research Center for Safety Monitoring of New Energy and Power Grid Equipment,Hubei University of Technology,Wuhan 430068,Hubei,China)

机构地区：[1]国网湖北省电力有限公司超高压公司,湖北武汉430050 [2]湖北工业大学新能源及电网装备安全监测湖北省工程研究中心,湖北武汉430068

出　　处：《电气传动》2024年第12期86-93,共8页Electric Drive

基　　金：智能电网保护和运行控制国家重点实验室开放基金(SGNR0000KJJS2200301);国网湖北省电力有限公司科技项目(521520220003)。

摘　　要：近年来,机器学习在气体绝缘组合电器(GIS)绝缘缺陷上获得了一定的突破,但传统的方法存在利用信息不全、过度依靠人工特征提取和诊断率较低等缺点,为了解决这些问题,提出了一种基于深度图卷积神经网络(DGCN)的诊断方法。首先,在220 kV真型GIS上搭建了局部放电(PD)实验平台,通过特高频传感器采集到的局部放电信号经傅里叶变换转换为频域谱图样本;然后,将谱图样本输入DGCN,经过图卷积、粗化、池化操作,使谱图结构更加清晰来丰富输入信息;最后,利用测试样本对设定好参数的DGCN进行测试,研究结果表明,提出的诊断方法对GIS故障缺陷的识别率可达98.77%,明显高于其他方法,并且具有较好的鲁棒性。Over the years,machine learning has made some breakthroughs in the insulation defects of gas insulated switchgear(GIS),but the traditional methods have the disadvantages of incomplete information,excessive reliance on artificial feature extraction and low diagnosis rate.In order to solve these problems,a diagnosis method based on deep graph convolutional neural network(DGCN)was proposed.Firstly,a partial discharge(PD)experimental platform was built on a 220 kV real GIS and the partial discharge signals collected by ultra high frequency sensor were converted into frequency domain spectrogram samples by Fourier transform.Then,the spectrogram samples were input into the DGCN,which undergoes graph convolution,coarsening and pooling operations to make the spectrogram structure was clearer and enrich the input information.Finally,the test samples were used to test the DGCN with set parameters.The experimental results show that the proposed method can achieve a recognition rate of 98.77%for GIS fault defects,which is significantly higher than other methods and has good robustness.

关 键 词：气体绝缘组合电器 局部放电 故障诊断 绝缘缺陷 深度图卷积神经网络 简单线性聚类法 

分 类 号：TM75[电气工程—电力系统及自动化]