【作者】 卓然；

【导师】 唐炬；

【作者基本信息】 重庆大学 ， 电气工程， 2014， 博士

【摘要】 气体绝缘组合电器(Gas Insulated Switchgear,简称GIS)因其运行安全、可靠性高、占地面积小及电磁环境友好等突出优点，正逐渐普及于城市供电系统中。然而，GIS设备在生产、运输、装配、运行和维修等过程都会不可避免的产生各种潜伏性绝缘缺陷，当这些绝缘缺陷发展到一定程度，若得不到及时治理，会在运行电压的作用下逐步加剧并最终诱发GIS设备绝缘故障，甚至威胁整个电网的安全。研究发现，因绝缘缺陷导致击穿故障之前，往往会先产生不同形式和程度的局部放电（Partial Discharge，简称PD），而PD形式又与绝缘缺陷类型和故障严重程度有着极为密切的内在联系。因此，通过对GIS内部PD进行科学合理的在线检测，并采用与之相适应的识别方法进行故障诊断，是保障GIS设备安全可靠运行的重要途径。但是，目前针对GIS PD在线监测的手段比较单一，所得到的反映GIS内部绝缘状态的PD信息也不够全面。鉴于此，本文提出采用脉冲电流法、超高频（UltraHigh Frequency，简称UHF）法和荧光光纤检测法对GIS内部典型绝缘缺陷PD进行联合同步检测，通过得到GIS内部金属突出物、金属污染物、绝缘气隙及自由金属微粒等4种典型绝缘缺陷下的复合PD信息，提取出反映不同绝缘缺陷特征的PD统计特征量，并据此构建出一种适用于GIS设备PD识别的支持向量数据描述（Support Vector Data Description，简称SVDD）故障诊断方法。为此，本文所做的主要研究工作有：①结合电磁波、天线辐射理论及光电子辐射原理，推导UHF信号能量与视在放电量的平方呈线性相关，荧光光纤信号的一次积分值与视在放电量之间的关联关系。通过实验，对不同气压SF6中UHF信号与视在放电量的关联关系做出修正，研究气压的影响特性及修正公式，并实测检验修正公式的有效性。同时，针对不同尺寸绝缘缺陷对PD光信号能量的影响，研究光信号能量受绝缘缺陷尺寸大小的影响特性与修正公式，并通过电场分析影响机理。实测检验荧光光纤检测法对微小绝缘缺陷引起的PD具有较高的灵敏度。②结合脉冲电流法、UHF法和荧光光纤法，构建出用于检测GIS内部典型绝缘缺陷PD的联合检测系统。通过大量实验，获取了反映GIS典型绝缘缺陷特征的PD复合信息，构造出各类PD信号的φ-u-n三维谱图及φ-u、φ-n二维谱图，并提取出13个表征4种典型绝缘缺陷产生PD信息的统计特征量。在此基础上，采用核主成分分析方法，提取表征4种典型绝缘缺陷产生PD综合特点的特征子集TKPCA，并借鉴最大相关最小冗余算法对原始统计特征进行择优降维，结合能够表征PD源特征的视在放电量q、UHF信号能量E以及荧光光纤信号一次积分A，共同构造出辨识4种典型绝缘缺陷的最优特征子集TBEST。研究表明，该方法不仅有效保留了每类PD信号的特征，同时还显著降低了特征信息的冗余度。③在PD类型识别中，引入SVDD方法，并借鉴支持向量机(support vectormachine，简SVM)最大化“间隔”思想，提出一种优化半径的OR-SVDD(OptimalRadius SVDD，简称OR-SVDD)方法来解决SVM辨识PD类型存在的漏分或错分问题，弥补了SVDD分类裕度不足的缺点，实现了多类缺陷的有效分类。④针对SVM和SVDD算法中核函数参数σ与惩罚因子C的选择存在盲目性的问题，结合局部遗传算法和模拟退火算法对SVDD分类器中的核函数参数σ和惩罚因子C进行优化，解决了以往依靠经验设定参数的问题，使σ与C这两个对分类性能影响最大的参数的设置具有科学依据，并提升了算法分类性能和识别效率。⑤针对实际故障诊断中存在的预定义故障重叠问题，使用主成分分析方法来优化Fisher判别分析（Fisher Discriminant Analysis，简称FDA），结合前文所构建的SVDD故障识别方法，提出一种使重叠的两类预定义故障在原始空间尽量分离后，再在Fisher投影空间实现最大分离的PF-SVDD方法。研究表明：该方法可将存在故障重叠情况时的60%低识别率提高到接近80%，显著增加了该诊断方法实用性。更多还原

【Abstract】 Gas Insulated Substation (GIS) is widely used in urban power substation becauseof its advantages of small area coverage, operational reliability and low electromagneticpollution. However, due to some reasons in structure and transportation, there areinevitable insulation defects which may cause partial discharge in regular operation.The safe operation of grid is threatened seriously by insulation damage. Therefore, theon-line monitoring and fault type recognition in GIS has been the focus of research inthis field.In this paper, statistical characteristics of different insulation defects PD signals arestudied based on analyzing researches about PD type recognition home and abroad.Methods to obtain different characteristic parameters are developed from differentangles of partial discharge pattern, Support Vector Data Description method is presentedfor PD type recognition in GIS. The main work and achievements are as follows.①Large data of discharge experiment in different intensity is acquired by PDUHF monitoring system which has been developed for the detection of four kinds oftypical insulation defects model in the laboratory. The φ-u-n3D PD image and thecorresponding φ-u, φ-n two-dimensional image has been constructed.The results showthat: the differences of four PD image shape are rather obvious, the same type of PDimage shape remains unchanged in different voltage levels. Obtaining the13statisticalfeatures based on the two-dimensional image can lay a foundation for the research ofPD type recognition.②Based on the electromagnetic theory, antenna and photoelectron radiationtheory, the relationship between apparent discharge quantity calculated by IEC60270and the detection signal could be obtained. Linear relationship between energy of UHFsignal and square of apparent discharge quantity has been found, while linearrelationship between the integral value of the signal of the optical method and thecharge quantity comes out. According to the practical situation, the correction formulaof gas pressure has been get by the research on the influence of different gas pressure toUHF signal and apparent discharge quantity. The effectiveness of optical method hasbeen also proved by experiment result.③The KPCA method is presented for the extraction of feature subset of fourkinds of insulation defects discharge comprehensive characteristic. The Maximal Relevance Minimal Redundancy method is put forward for dimension reduction of theoriginal statistical characteristics. With apparent discharge quantity q, energy of UHFsignal E and optical energy A, two algorithms are combined to construct optimal featuresubset TBESTto identify four kinds of defects, which effectively retained thecharacteristics of each class of the PD signal and reduced the redundancy of statisticalcharacteristics.④SVDD is introduced into PD type recognition, based on the principle ofMaximum interval of support vector machine and one to multiple of multipleclassification method, an optimal radius support vector data description algorithm(OR-SVDD) is proposed to solve the disadvantages of missing and wrong classificationin SVM and the lack of classification margin small in SVDD. The principle of“one-to-many” is adopted to solve the difficult problem of multi-class defectclassification, and to improve the identification ability and application value.⑤As a result of optimization of classification performance, local GA algorithmand SA algorithm have been applied to optimize the kernel parameter σ and the penaltyfactor C of SVDD classifier. According to the real project, PCA-FDA has been proposed.Two overlapping classes of fault would desperate in original space, and then reach themaximum level in Fisher projection space. With the method, the low recognition ratio60%would rise high to80%to improve the applying value.更多还原