摘要
气体绝缘金属封闭开关设备(GIS)局部放电故障类型识别是故障预警和制定检修计划的重要基础,对维护电力设备的安全稳定运行意义重大。在此背景下,首先分析常见的几种GIS故障类型;然后,在超高频传感器采集到的图谱信号处理和分类上,由于卷积神经网络(CNN)和深度置信网络(DBN)融合而成的复合神经网络模型可以快速实现有效特征信号的提取和故障类型准确分类,因此该文融合CNN和DBN,建立复合神经网络的主体结构,并利用该网络进行GIS局部放电故障类型识别;最后进行实验验证。结果表明该复合神经网络模型识别故障的准确性最高可达99%。
Gas insulated switchgear(GIS)partial discharge fault type identification is an important basis for fault warning and maintenance planning,and is of great significance for maintaining the safe and stable operation of power equipment.This paper firstly analyzes several common types of GIS faults.Then,in the processing and classification of the spectral envelop signal collected by the UHF sensor,the composite neural network model formed by the fusion of the convolutional neural network(CNN)and the deep belief network(DBN)can quickly realize the extraction of effective feature signals and accurate classification of fault types.Therefore this paper integrates CNN and DBN,establishes the main structure of the composite neural network,and uses this network to identify GIS partial discharge fault types.Finally,the method is verified in simulation experiments.Results show that the accuracy of the composite neural network model to identify faults can reach up to 99%.
作者
袁文海
刘彪
徐浩
王喆
董小顺
汪沨
钟理鹏
司羽飞
夏鑫
YUAN Wenhai;LIU Biao;XU Hao;WANG Zhe;DONG Xiaoshun;WANG Feng;ZHONG Lipeng;SI Yufei;XIA Xin(Urumqi Power Supply Company,State Grid Xinjiang Electric Power Co.,Ltd.,Urumqi 830011,China;College of Electrical and Information Engineering,Hunan University,Changsha 410082,China)
出处
《电力科学与技术学报》
CAS
北大核心
2021年第4期157-164,共8页
Journal of Electric Power Science And Technology
基金
国网新疆电力有限公司科技项目(SGXJWL00YJJS1901002)。
关键词
GIS设备
特征图像
卷积神经网络
深度置信网络
模型训练
GIS
characteristic image
convolution neural network(CNN)
deep belief network(DBN)
model training
作者简介
通信作者:董小顺(1989-),女,硕士,中级工程师,主要从事带电检测及高压试验研究,E-mail:1061545589@qq.com。
