特征分类算法下的GIS故障诊断策略
|
摘要
在我国科学技术不断发展的过程中,对于现代电力需求在不断的提高。目前,在电压等级不断提高的过程中,对于电能可靠性也提出了较高的要求。SF6气体绝缘金属封闭式组合电器(GIS)因为占据面积比较小,具有较高的可靠性,成为现代电力系统中的主要构成部分。但是目前在国民用电不断提高的过程中,电网故障的事故发生较为频繁,GIS属于最为主要的环节,如果出现故障就会导致大规模停电事故,提高电网的损失。所以,保证GIS运行的安全性利国利民。本文对于GIS故障诊断的方法,提出了基于支持向量机及核主成分分析的气体绝缘开关故障检测方法,通过实际样本检验,对算法可靠性及精准性进行验证。
In the process of the continuous development of science and technology in our country,the demand for modern electric power is constantly improving. At present,in the process of continuously improving the voltage level,higher requirements are put forward for power reliability. SF6 gas insulated metal enclosed combined electrical apparatus( GIS) has become the main component of modern power system because of its small occupation area and high reliability. However,in the process of continuous improvement of national electricity consumption,power grid fault accidents occur more frequently. GIS is the most important link. If there are faulures fault. It will lead to large-scale blackouts and improve the loss of power grid. There fore,to ensure the seeurity of GIS ofzeration is beneficial to the couwtry and the people. In this paper,support vector machine( SVM) and kernel principal component analysis( KPCA) method for gas insulated switch are proposed for GIS fault diagnosis. The reliability and accuracy of the algorithm are tested by actual samples.
In the process of the continuous development of science and technology in our country,the demand for modern electric power is constantly improving. At present,in the process of continuously improving the voltage level,higher requirements are put forward for power reliability. SF6 gas insulated metal enclosed combined electrical apparatus( GIS) has become the main component of modern power system because of its small occupation area and high reliability. However,in the process of continuous improvement of national electricity consumption,power grid fault accidents occur more frequently. GIS is the most important link. If there are faulures fault. It will lead to large-scale blackouts and improve the loss of power grid. There fore,to ensure the seeurity of GIS ofzeration is beneficial to the couwtry and the people. In this paper,support vector machine( SVM) and kernel principal component analysis( KPCA) method for gas insulated switch are proposed for GIS fault diagnosis. The reliability and accuracy of the algorithm are tested by actual samples.
引文
[1]张湛,杨光,黄志,等.基于特征分类算法的GIS故障诊断方法研究[J].电工电气,2016,(11):16-20.
[2]张帆.GIS平台配电网故障目前所用诊断算法特点分析[J].电子世界,2014,(19):48-48.
[3]曹倩倩.GRASS中基础空间分析算法的并行策略研究与实现[D].天津理工大学,2016.
[4]郑浩,朱胜龙,欧阳昱,等.基于改进HHT算法的GIS机械振动信号时频分析[J].电气自动化,2018,(1):15-18.
[5]侯焰.基于异常振动分析的GIS机械故障诊断技术研究[D].山东大学,2017.
[6]张晓星,舒娜,徐晓刚,等.基于三维谱图混沌特征的GIS局部放电识别[J].电工技术学报,2015,30(1):249-254.
[7]米晓萍,李雪梅,贾春花.电力系统故障节点快速定位算法研究[J].计算机仿真,2016,33(1):112-115.
[8]黄勇东,牛雪松.基于模糊K-近邻算法的GIS局部放电模式识别[J].广东电力,2014,(1):81-84.
[9]徐茜子.基于GIS的决策树算法在空间数据分类中的分析与研究[J].科技信息,2006(11X):38-38.
[10]徐枫.浅析数据挖掘分类方法中的决策树算法[J].商场现代化,2010,(23):54-55.
[11]李振星,邵峰晶,孙仁诚,等.基于分类的GIS地图符号快速标注算法[J].软件,2012,33(2):108-110.
[12]沈涤.GIS地图符号快速标注算法应用分析[J].信息与电脑(理论版),2017,(20):75-76.
[13]吕德奎,崔艳军.基于网格的地图标注避让算法[J].电子技术与软件工程,2016,(22):13-13.
[14]张晓慧,孙连山.基于改进K-中心点的电子地图数据质量检查算法[J].软件导刊,2017,16(2):81-84.
[15]申闫春,王锐,翟春丽.海量地形的GIS特征数据实时渲染算法研究[J].计算机仿真,2011,28(10):223-227.
[2]张帆.GIS平台配电网故障目前所用诊断算法特点分析[J].电子世界,2014,(19):48-48.
[3]曹倩倩.GRASS中基础空间分析算法的并行策略研究与实现[D].天津理工大学,2016.
[4]郑浩,朱胜龙,欧阳昱,等.基于改进HHT算法的GIS机械振动信号时频分析[J].电气自动化,2018,(1):15-18.
[5]侯焰.基于异常振动分析的GIS机械故障诊断技术研究[D].山东大学,2017.
[6]张晓星,舒娜,徐晓刚,等.基于三维谱图混沌特征的GIS局部放电识别[J].电工技术学报,2015,30(1):249-254.
[7]米晓萍,李雪梅,贾春花.电力系统故障节点快速定位算法研究[J].计算机仿真,2016,33(1):112-115.
[8]黄勇东,牛雪松.基于模糊K-近邻算法的GIS局部放电模式识别[J].广东电力,2014,(1):81-84.
[9]徐茜子.基于GIS的决策树算法在空间数据分类中的分析与研究[J].科技信息,2006(11X):38-38.
[10]徐枫.浅析数据挖掘分类方法中的决策树算法[J].商场现代化,2010,(23):54-55.
[11]李振星,邵峰晶,孙仁诚,等.基于分类的GIS地图符号快速标注算法[J].软件,2012,33(2):108-110.
[12]沈涤.GIS地图符号快速标注算法应用分析[J].信息与电脑(理论版),2017,(20):75-76.
[13]吕德奎,崔艳军.基于网格的地图标注避让算法[J].电子技术与软件工程,2016,(22):13-13.
[14]张晓慧,孙连山.基于改进K-中心点的电子地图数据质量检查算法[J].软件导刊,2017,16(2):81-84.
[15]申闫春,王锐,翟春丽.海量地形的GIS特征数据实时渲染算法研究[J].计算机仿真,2011,28(10):223-227.