摘要
气体绝缘组合电器(GIS)内的绝缘介质SF6及其衍生物的种类与体积严重地影响G IS的绝缘能力,定量分析故障GIS内SF6衍生物有助于评估设备发生故障的原因。为了从GIS设备内SF6气体的红外光谱中获取衍生物的种类及体积,使用支持向量机(SVM)回归法建立了SF6及其部分衍生物的定量分析模型,采用粒子群优化(PSO)算法对支持向量机的参数进行了优化选择,与遍历选择参数方法相比,粒子群优化避免了交叉验证的耗时与盲性。
The dielectric SF6 and its derivative＇s type and volume in GIS play a decisive role in GIS insulating property. A quantitative analysis of SF6 and its decompositions can help to find the reason of fault. In order to find the concentration information of some special ramifications of SF6 from the infrared spectrum of GIS＇s gas, in this paper, tbe regrcssion model of Support Vector Machine is used to analyze infrared spectrum of insulating medium SF6 and SF6＇s ramifications quantitatively. The Particle Swarm Optimization is used to train the Support Vector Machine. In contrast with Traverse Optimization, Particle Swarm Optimization avoids the time consumption and blindness in cross validation.
出处
《洛阳理工学院学报（自然科学版）》
2011年第2期19-23,共5页
Journal of Luoyang Institute of Science and Technology：Natural Science Edition
基金
襄樊学院科研基金项目(2009YB022)
襄樊学院大学生科研项目(2010DXS011)
